Search

The enterprises of the make-to-order production mode are required to make accurate judgments and reasonable decisions when dealing with the disturbance factors in the manufacturing process to ensure the timely completion of orders. Order remaining completion time (ORCT) prediction can quantify the production process and is an important basis to ensure the delivery date of orders. However, an accurate prediction model of the ORCT is challenging because of the spatial and temporal (ST) characteristics of the manufacturing process. An ST features-based prediction method is proposed to solve this problem. Firstly, the ST data sets are established on the basis of analysing ST characteristics of the manufacturing process. Secondly, the spatial feature extraction network and temporal feature extraction network are built to make a more comprehensive analysis. Finally, the prediction model of the ORCT is proposed by fusing the spatial and temporal features and validated in a practical workshop. Experimental results show that considering the spatial and temporal characteristics of the manufacturing process can significantly improve the prediction model's performance, and the proposed prediction model is superior to graph convolutional neural network, gated recurrent unit network, deep auto-encoder, deep neural network, and back propagation neural network. [ABSTRACT FROM AUTHOR]

Acid and peroxide values are important indicators to evaluate the hydrolysis or oxidation level of vegetable oil. In order to achieve rapid determination of these parameters by Raman spectroscopy, rapeseed and soybean oil were analyzed, and a competitive adaptive reweighted sampling-back propagation neural network (CARS-BPNN) method was developed. First, the Raman spectrum was preprocessed to reduce noise using moving window smoothing. Next, competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination (UVE) was applied to extract the Raman characteristic information that indicated the acid and peroxide values. Based on the extracted characteristic information, back propagation neural network (BPNN), partial least squares regression (PLSR), and support vector machine (SVM) prediction models were established and compared. The results showed that the best accuracy was obtained using CARS-BPNN. For rapeseed oil, the coefficients of determination (R2) of acid value and peroxide value were 0.9207 and 0.9772. The root mean square error (RMSE) values were 0.0909 and 0.0022, respectively. For soybean oil, the coefficients of determination (R2) of acid and peroxide values were 0.9381 and 0.9716. The RMSE values were 0.1250 and 0.0027, respectively. A good correlation coefficient and a small RMSE value were obtained. The results indicate that Raman spectroscopy combined with CARS-BPNN accurately evaluated the acid and peroxide values, which provides a reference for the optimization of the Raman spectrum and creates a new approach for the evaluation of vegetable oil quality. [ABSTRACT FROM AUTHOR]

Flow admission control (FAC) aims to efficiently manage the service requests while maximizing the network utilization. With multiple connection requests, access delay or even service interruption may occur. This paper proposes a novel FAC approach to reduce the contention between the end nodes and ensure high utilization of the networking resources for software defined IIoT. First, incoming flows are classified into different priorities using back propagation neural network based on selected features representing the current network status. Second, with the designed flow admission policies, bandwidth and buffer size are estimated with stochastic network calculus model. Finally, the thresholds of the proposed FAC scheme are dynamically decided based on the above two parameters. Various flows are admitted or rejected via the proposed FAC to maintain real time processing. Unlike traditional FAC schemes rely on static priority systems, the proposed scheme leverages machine learning technique for dynamic flow prioritization and the stochastic network calculus model for precise estimation. Computer simulation reveals that the proposed scheme accurately classifies the flows, and substantially decreases the transmission delay and improves the network utilization compared to the existing FAC schemes. This highlights the superiority of the proposed scheme meeting the demands of software defined IIoT. [ABSTRACT FROM AUTHOR]

This study seeks to enhance the entrepreneurial quality of college students by introducing advanced technologies such as deep learning and blockchain. A student majoring in electronic information at a university is the research object. Based on the background of the Internet of Things and blockchain technology, the innovation and entrepreneurship information data platform for college students is constructed. The results show that the α values of students' background, students' professional ability, students' practical ability, and students' development ability are greater than 0.7. When determining the number of neurons in the hidden layer, the training error curve decreases continuously. The test error rises and then decreases when the number of neurons in the hidden layer is 10, 11, and 12. The Levenberg-Marquardt algorithm, selected as the training function, exhibits optimal performance with a training step count of 1,000 and achieves a performance score of 4.9. The actual values of the enhanced BPNN align closely with the expected values, demonstrating minimal deviation. The findings emphasize the importance for students in electronic information majors to actively engage in diverse social practices. This study serves as a valuable reference for enhancing the entrepreneurial quality of college students. [ABSTRACT FROM AUTHOR]

Waterless and low temperature transportation is a green and efficient way for the transportation of live fish. However, waterless and low temperature conditions could lead to a stress response in live fish, resulting in reduced transport survival rates. It is still a challenge to intelligently monitor the breath stress state of live fish under adversity stress. Temperature (T), relative humidity (RH), oxygen (O 2) and carbon dioxide (CO 2) signals can reflect changes in adversity stress environment; while the breath angle sensors can monitor the gill opening and closing angle (breath angle) to reflect changes in fish breath. In this work, microenvironment and breath angle sensor systems were designed and developed to comprehensively evaluate the breath stress state of fish. Meanwhile, the Kalman filter-quaternion-fast Fourier transform method was established to process the breath angle signal. The breath angle signal indicated that the sturgeon had three levels of breath stress: acute fluctuation stage (0–2.5h), organismal regulation stage (2.5–16h) and cumulative stress stage (>16h). In addition, linear regression (LR), back propagation neural network (BPNN), support vector regression (SVR), and radial basis function neural network (RBFNN) models were established for breath efficiency signal prediction. The R2 of the RBFNN (0.9544) model was significantly higher than the LR (0.8092), BPNN (0.9289), and SVR (0.9428) models. This study provided a reference for further intelligent monitoring and management of the fish breath stress state under waterless and low temperature conditions. • Development of sensor systems for measuring microenvironment and breath angle. • Kalman filter-quaternion-fast Fourier transform based breath angle processing. • Comprehensive evaluation of the breath stress states of live fish. • Machine learning-based compensation and modelling of breath stress states. [ABSTRACT FROM AUTHOR]

Artifact correction is a great challenge in cardiac imaging. During the correction of coronary tissue with motion‐induced artifacts, the spatial distribution of CT value not only shifts according to the motion vector field (MVF), but also shifts according to the volume change rate of the local voxels. However, the traditional interpolation method does not conserve the CT value during motion compensation. A new sample interpolation algorithm is developed based on the constraint of conservation of CT value before and after image deformation. This algorithm is modified on the existing interpolation algorithms and can be embedded into neural networks with deterministic back propagation. Comparative experimental results illustrate that the method can not only correct motion‐induced artifacts, but also ensure the conservation of CT value in the region of interest (ROI) area, so as to obtain corrected images with clinically recognized CT value. Both effectiveness and efficiency are proved in forward motion correction process and backward training steps in deep learning. Simultaneously, using the network to learn the MVF making this method more interpretable than the existing image‐based end‐to‐end deep learning method. [ABSTRACT FROM AUTHOR]

This study proposes a novel ensemble method based on weighted majority voting to evaluate the slope stability. The ensemble classifier is composed of 5 base classifiers, including random forest, logistic regression, naive bayes, support vector classifier and back propagation. An integrated approach was developed using 213 slope cases collected from the literature and the performance of the proposed approach was validated. The selection of training parameters was carried out by the definition of safety factor and the correlation analysis of parameters. The search for the optimal hyperparameters of the base classifiers is performed using a grid search algorithm combined with a five-fold cross-validation. Weights to each base classifier is obtained by the AUC (area under the curve) value of the training dataset. Finally, the ensemble method based on weights is established to predict the stability of slopes in this paper. It is demonstrated that the ensemble algorithm is superior to the base classifier with regard to accuracy, kappa, precision, recall, F1 score and the receiver's operating characteristic curve AUC. Also, the importance scores of training parameters are obtained by the random forest theory. [ABSTRACT FROM AUTHOR]

In order to maintain the battery SOC, the fuel cell power will fluctuate dramatically, as well as frequent start-stop, which will greatly increase the life attenuation of the fuel cell and reduce the durability. An optimization-based energy management strategy with a real-time model predictive control and pontryagin's maximum principle for FCHEV is proposed in this paper, both the fuel economy and the fuel cell durability are considered in the optimization. A novel model predictive control is studied to achieve energy distribution. After the calculation of predicted speed sequence through back propagation neural network, pontryagin's maximum principle is introduced to solve the optimal control problem in each prediction horizon and obtain the ideal control strategy. In addition, the fuel cell degradation model is introduced in the modeling process, the minimum power point of the fuel cell system is designed to improve the fuel economy and durability of the fuel cell. Compared with the rule-based strategy, the proposed MPC strategy has better performance to reduce the total equivalent hydrogen consumption, which can save up to 8.44% in the test case of the mid-size fuel cell passenger car while maintaining the stability of the battery's state of charge. [ABSTRACT FROM AUTHOR]

Copyright of Revista Brasileira de Engenharia Agricola e Ambiental - Agriambi is the property of Revista Brasileira de Engenharia Agricola e Ambiental and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Time series analysis and prediction have attained significant attention from the research community in the past few decades. However, the prediction accuracy of the models highly depends on the models' learning process. In order to optimize resource usage, a better learning methodology, in terms of accuracy and learning time, is needed. In this context, the current research work proposes EvoLearn, a novel method to improve and optimize the learning process of neural-based models. The presented technique integrates the genetic algorithm with back-propagation to train model weights during the learning process. The fundamental idea behind the proposed work is to select the best components from multiple models during the training process to obtain an adequate model. To demonstrate the applicability of EvoLearn, the method is tested on the state-of-the-art neural models (namely MLP, DNN, CNN, RNN, and GRU), and performances are compared. Furthermore, the presented study aims to forecast two types of time series, i.e. air pollution and energy consumption time series, using the developed framework. In addition, the considered neural models are tested on two datasets of each time series type. From the performance comparison and evaluation of EvoLearn using a one-tailed paired T-test against the conventional back-propagation-based learning approach, it was found that the proposed method significantly improves the prediction accuracy. [ABSTRACT FROM AUTHOR]

Introduction: Traditional statistical methods cannot find quantitative relationship from environmental data. Methods: We selected gene expression programming (GEP) to study the relationship between pollutant gas and PM2.5 (PM10). They were used to construct the relationship between pollutant gas and PM2.5 (PM10) with environmental monitoring data of Xi'an, China. GEP could construct a formula to express the relationship between pollutant gas and PM2.5 (PM10), which is more explainable. Back Propagation neural networks (BPNN) was used as the baseline method. Relevant data from January 1st 2021 to April 26th 2021 were used to train and validate the performance of the models from GEP and BPNN. Results: After the models of GEP and BPNN constructed, coefficient of determination and RMSE (Root Mean Squared Error) are used to evaluate the fitting degree and measure the effect power of pollutant gas on PM2.5 (PM10). GEP achieved RMSE of [8.7365-14.6438] for PM2.5; RMSE of [13.2739-45.8769] for PM10, and BP neural networks achieved average RMSE of [13.8741-34.7682] for PM2.5; RMSE of [29.7327-52.8653] for PM10. Additionally, experimental results show that the influence power of pollutant gas on PM2.5 (PM10) situates between -0.0704 and 0.6359 (between -0.3231 and 0.2242), and the formulas are obtained with GEP so that further analysis become possible. Then linear regression was employed to study which pollutant gas is more relevant to PM2.5 (PM10), the result demonstrates CO (SO2, NO2) are more related to PM2.5 (PM10). Discussion: The formulas produced by GEP can also provide a direct relationship between pollutant gas and PM2.5 (PM10). Besides, GEP could model the trend of PM2.5 and PM10 (increase and decrease). All results show that GEP can be applied smoothly in environmental modelling. [ABSTRACT FROM AUTHOR]

Summary 5G communication technology is projected to provide extreme data rates that surpass user exposure, low power consumption, and greater short latency. A diverged multi‐layer approach is implemented by cellular networks with macro‐cells and various schemes of small cells to aid users with diverged quality of service (QoS) that affects more research by employing intervention management in 5G networks. Along with the escalating requirement for cellular services and adequate resources to furnish it and capable of handling the network traffic has become a resource distribution concern. The major concern is to facilitate the network jam having QoS. To overcome this concern, a potent investigation is developed for power and resource allocation, which is named as transit Archimedes optimization algorithm (TAOA). First, the non‐orthogonal multiple access (NOMA) system module is created with the aid of power consumption and energy modules. Then, user clustering (UC) is performed to gather the NOMA users into single or multiple clusters utilizing deep embedded clustering (DEC) in accordance with user grouping parameters, like signal‐to‐interference and noise ratio (SINR), position, initial power, and channel gain. After that, sub‐channel assignment and power allocation are done by the back propagation neural network (BPNN). Lastly, the presented module TAOA is performed to update the network parameters of BPNN, where TAOA is developed by the fusion of transit search (TS) optimization and Archimedes optimization algorithm (AOA). The analytic metrics utilized for finding the performance of the proposed TAOA‐BPNN are achievable rate, energy efficiency, sum rate, and throughput. The experimental results demonstrate that the proposed method offers good performance with the achievable rate of 3.273 Mbits, energy efficiency of 0.00000000473 J, sum rate of 0.00000248 s, and throughput of 0.00000346 Mbps. [ABSTRACT FROM AUTHOR]

Aiming to address the timing skew mismatch in the time‐interleaved analog‐to‐digital converter (TIADC) system, this paper presents a timing skew mismatch calibration method based on a back propagation (BP) neural network optimized by an adaptive genetic algorithm (AGA). In this paper, a trained BP neural network is used to detect the timing skew mismatch in the TIADC system, and the variable delay line is used to calibrate it. In this paper, AGA is used to optimize the BP neural network, accelerating its training speed and improving the detection accuracy of timing skew mismatch in the system. The proposed approach boasts superior detection speed and accuracy compared to other methods. In this paper, an 18‐bit 1GS/S 4‐channel TIADC system is simulated and the timing skew mismatch in the system is corrected. Simulation results show that the proposed calibration method has fast detection speed, high detection accuracy, and calibration accuracy. After completing the timing skew mismatch correction, the performance of the TIADC system is dramatically improved. The effective number of bits (ENOB) of the system increases by 9.5 bits, and the spurious‐free dynamic range (SFDR) increases by 59.9 dB. [ABSTRACT FROM AUTHOR]

In this era of information technology, information leakage and file corruption due to computer virus intrusion have been serious issues. How to detect and prevent the spread of the computer virus is the major challenge we are facing now. To target this problem, a class of virus propagation models with hybrid control scheme are formulated to investigate the dynamic evolution and prevention from a spatial-temporal perspective in this paper. Diffusion-induced Turing instability is detected in response to the computer virus propagation. The introduction of hybrid control scheme can effective suppress Turing instability and turn the propagation system back to a stable state. And then, the time delay is selected as the bifurcation parameter. If the time delay exceeds the bifurcation threshold, the propagation will be destabilised and a Hopf bifurcation will occur. The hybrid control tactic can not only regulate the occurrence of Hopf bifurcation well, but also optimise the properties of bifurcating period solutions. In the end, the correctness and validity of the theoretical results are verified via numerical simulations. [ABSTRACT FROM AUTHOR]

Using Antarctic krill (Euphausia superba) as the research object, we optimized the process conditions for Antarctic krill sauce (AkS) by including three factors (salt addition, rock sugar addition, and the oil-to-material ratio) and sensory evaluation as response values. The data from the response surface were fed into the back propagation (BP) neural network training, generating a model mapping the process conditions and sensory scores, which were subsequently combined with the genetic algorithm (GA) for global optimization to determine the optimal process for AkS preparation. The results revealed that the response surface model was well suited to the BP neural network training and prediction sets, with correlation values of 0.98 and 0.95, respectively. The fitting prediction effect was obvious for the sensory scoring results of the product. The parameters obtained from the GA's global optimization search accord with the analytical results of the response surface. The findings demonstrated that combining a BP neural network with a GA can enhance the AkS preparation technique. Under optimal processing conditions, AkS has a high sensory score and protein and carbohydrate contents, moderate fat content, minimal fat oxidation, and non-detectable pathogens, indicating that the AkS in this study was nutritious and safe to consume. [ABSTRACT FROM AUTHOR]

In this paper, a prediction model of the coupling coefficient based on a multi-module neural network (MMNN) is developed to quickly optimize the installation position of the roof antenna of the 5G-Railway (5G-R) communication system, so as to improve the anti-interference performance of the roof antenna. Firstly, a simulation model of the coupling coefficient between the pantograph arcing and the roof antenna (a monopole antenna operating frequency of 2 GHz) was established to construct the dataset. It is also verified that the influence of the electromagnetic interference (EMI) of pantograph arcing can be significantly reduced by predicting the new installation position (minimum coupling coefficient), and the installation position optimization of roof antenna can be realized. Then, the mind evolutionary algorithm of the back propagation neural network (MEA-BP) algorithm and particle swarm optimization—extreme learning machine (PSO-ELM) algorithm were adopted, respectively. The extreme learning machine algorithm constructed a different prediction model. And, by setting the integrated strategy of piecewise prediction, the prediction results are optimized and the accuracy of the prediction model based on the MMNN is further improved. Finally, the prediction model is proven to be able to replace the complicated electromagnetic simulation work accurately and efficiently by a variety of prediction performance indices, which provides an effective prediction method for the rapid optimization of the installation position of the roof antenna. [ABSTRACT FROM AUTHOR]

As a new technology, microbial electrolysis cell-assisted anaerobic digestion (MEC-AD) has been applied to the utilization of swine manure. Methane production and total energy efficiency are both important indicators in MEC-AD; thus, it is necessary to simultaneously optimize methane production and total energy efficiency. In this study, the Box–Behnken design (BBD) was used as the experimental design, the response surface methodology (RSM) and back propagation neural network (BP-NN) methods were used to construct multi-objective models, and the non-dominated sorting genetic algorithm II (NSGA II) was used for multi-objective optimization. The BP-NN model was superior to the RSM model in terms of goodness of fit. Additionally, the relative error between the predicted and experimental values of the Pareto front was determined to be <3%. The maximum methane production and total energy efficiency were 333.97 mL/g total solid and 61.38%, respectively. Therefore, multi-objective optimization of MEC-AD systems may be accomplished using BBD-(BP-NN)-NSGA II. • A novel approach for multi-objective optimization of MEC-AD systems is presented. • The multi-objective optimization framework, BBD-(BP-NN)-NSGA II, was established. • The methane production and total energy efficiency were optimized simultaneously. • The BP-NN model demonstrated superior prediction capabilities in MEC-AD systems. • Maximum methane production and energy efficiency were 333.97 mL/g TS and 61.38%. [ABSTRACT FROM AUTHOR]

Introduction: Rapid and accurate estimation of leaf area index (LAI) is of great significance for the precision agriculture because LAI is an important parameter to evaluate crop canopy structure and growth status. Methods: In this study, 20 vegetation indices were constructed by using cotton canopy spectra. Then, cotton LAI estimation models were constructed based on multiple machine learning (ML) methods extreme learning machine (ELM), random forest (RF), back propagation (BP), multivariable linear regression (MLR), support vector machine (SVM)], and the optimal modeling strategy (RF) was selected. Finally, the vegetation indices with a high correlation with LAI were fused to construct the VI-fusion RF model, to explore the potential of multivegetation index fusion in the estimation of cotton LAI. Results: The RF model had the highest estimation accuracy among the LAI estimation models, and the estimation accuracy of models constructed by fusing multiple VIs was higher than that of models constructed based on single VIs. Among the multi-VI fusion models, the RF model constructed based on the fusion of seven vegetation indices (MNDSI, SRI, GRVI, REP, CIred-edge, MSR, and NVI) had the highest estimation accuracy, with coefficient of determination (R2), rootmean square error (RMSE), normalized rootmean square error (NRMSE), and mean absolute error (MAE) of 0.90, 0.50, 0.14, and 0.26, respectively. Discussion: Appropriate fusion of vegetation indices can include more spectral features in modeling and significantly improve the cotton LAI estimation accuracy. This study will provide a technical reference for improving the cotton LAI estimation accuracy, and the proposed method has great potential for crop growth monitoring applications. [ABSTRACT FROM AUTHOR]

The volatilization of volatile organic compounds following a leakage event is a crucial mechanism that influences their migration and transformation in the soil. It is noteworthy that this process is intricately shaped by soil properties and environmental factors, exhibiting highly complex nonlinear relationships. However, there is currently no reliable mathematical model to predict the nonlinear relationship. To address this gap, the study conducted dynamic experiments considering various factors, including particle size, organic matter content, temperature, wind speed and moisture content. The volatilization rate (k ), an important parameter in volatilization kinetics reflecting the speed of volatilization, was calculated by first-order kinetic principle. Finally, an innovative approach was introduced using a Back Propagation Neural Network (BPNN) model for prediction. The findings indicate that wind speed exerts the most significant impact on the volatilization rate of benzene among the examined factors. The application of BPNN demonstrates the model's accuracy in simulating benzene volatilization rates under diverse conditions. The results of K-fold cross-validation alleviate concerns of potential over-prediction, affirming the reliability of the constructed model. This research introduces a novel methodology for predicting volatilization parameters in real-world scenarios. Highlights: : Five factors including particle size, organic matter content, temperature, wind speed and moisture content were considered. : Wind speed has the most significant impact on the volatilization of benzene among five factors. : A Back Propagation Neural Network model was successfully implemented to predict the volatilization rates of benzene. [ABSTRACT FROM AUTHOR]

Introduction: Early prediction and timely treatment are essential for minimizing the risk of visual loss or blindness of retinopathy of prematurity, emphasizing the importance of ROP screening in clinical routine. Objective: To establish predictive models for ROP occurrence based on the risk factors using artificial neural network. Methods: A cohort of 591 infants was recruited in this retrospective study. The association between ROP and perinatal factors was analyzed by univariate analysis and multivariable logistic regression. We developed predictive models for ROP screening using back propagation neural network, which was further optimized by applying genetic algorithm method. To assess the predictive performance of the models, the areas under the curve, sensitivity, specificity, negative predictive value, positive predictive value and accuracy were used to show the performances of the prediction models. Results: ROP of any stage was found in 193 (32.7%) infants. Twelve risk factors of ROP were selected. Based on these factors, predictive models were built using BP neural network and genetic algorithm-back propagation (GA-BP) neural network. The areas under the curve for prediction models were 0.857, and 0.908 in test, respectively. Conclusions: We developed predictive models for ROP using artificial neural network. GA-BP neural network exhibited superior predictive ability for ROP when dealing with its non-linear clinical data. [ABSTRACT FROM AUTHOR]

Colleges and universities are large consumers of energy, with a huge potential for building energy efficiency, and need to reduce energy consumption to build a low-carbon, energy-saving campus. Predicting the energy consumption of campus buildings can help to accurately manage the electricity consumption of buildings and reduce the energy consumption of buildings. However, the electricity consumption of a building's operation is affected by many factors, and it is difficult to establish a model for analysis and prediction. Therefore, in this study, the training building of the BIM education center on campus was selected as the research object, and a digital twin O&M platform was established by integrating IoT, digital twin technology (DDT), smart meter monitoring devices, and indoor environment monitoring devices. The O&M management platform can monitor real-time changes in indoor power consumption data and environmental parameters, and organize data on multiple influencing factors and power consumption. Following training, validation, and testing, the machine learning models (back propagation neural network, support vector model, and multiple linear regression model) were assessed and compared for accuracy. Following the multiple linear regression and support vector models, the backpropagation neural network model exhibited the highest accuracy. Consistent with the actual power consumption detection results in the BIM education center, the backpropagation neural network model produced results. Consequently, the BP model created in this study demonstrated its dependability and ability to forecast campus building power usage, assisting the university in organizing its energy supply and creating a campus that prioritizes conservation. [ABSTRACT FROM AUTHOR]

As renewable energy sources such as wind and photovoltaics continue to enter the grid, their intermittency and instability leads to an increasing demand for peaking and frequency regulation. An efficient dynamic monitoring method is necessary to improve the safety level of intelligent operation and maintenance of power stations. To overcome the insufficient detection accuracy and poor adaptability of traditional methods, a novel fault early warning method with careful consideration of dynamic characteristics and model optimization is proposed. A combined loss function is proposed based on the dynamic time warping and the mean square error from the perspective of both shape similarity and time similarity. A prediction model of steam turbine intermediate-stage extraction temperature based on the gate recurrent unit is then proposed, and the change in prediction residuals is utilized as a fault warning criterion. In order to further improve the diagnostic accuracy, a human evolutionary optimization algorithm with lens opposition-based learning is proposed for model parameter adaptive optimization. Experiments on real-world normal and faulty operational data demonstrate that the proposed method can improve the detection accuracy by an average of 1.31% and 1.03% compared to the long short-term memory network, convolutional neural network, back propagation network, extreme learning machines, gradient boosting decision tree, and LightGBM models. [ABSTRACT FROM AUTHOR]

In this paper, artificial intelligence (AI) technology is applied to the electromagnetic imaging of anisotropic objects. Advances in magnetic anomaly sensing systems and electromagnetic imaging use electromagnetic principles to detect and characterize subsurface or hidden objects. We use measured multifrequency scattered fields to calculate the initial dielectric constant distribution of anisotropic objects through the backpropagation scheme (BPS). Later, the estimated multifrequency permittivity distribution is input to a convolutional neural network (CNN) for the adaptive moment estimation (ADAM) method to reconstruct a more accurate image. In the meantime, we also improve the definition of loss function in the CNN. Numerical results show that the improved loss function unifying the structural similarity index measure (SSIM) and root mean square error (RMSE) can effectively enhance image quality. In our simulation environment, noise interference is considered for both TE (transverse electric) and TM (transverse magnetic) waves to reconstruct anisotropic scatterers. Lastly, we conclude that multifrequency reconstructions are more stable and precise than single-frequency reconstructions. [ABSTRACT FROM AUTHOR]

A four‐degree‐of‐freedom upper limb exoskeleton rehabilitation robot system with a gravity compensation device is constructed. The objective is to address the rehabilitation training needs of patients with upper limb motor dysfunction. A BP neural network adaptive control method based on particle swarm optimization is proposed. First, the degrees of freedom of the human body are analyzed, and a Lagrange method is employed to construct a dynamic model. Second, a particle swarm optimization back propagation neural network adaptive control algorithm based on particle swarm optimization is presented. Subsequently, the range of motion of the upper limbs is analyzed with reference to muscle anatomy and a three‐dimensional motion capture system. And the robot structure design is analyzed in detail. Finally, simulation experiments were conducted, and the results demonstrated that the proposed method exhibited high effectiveness and accuracy. [ABSTRACT FROM AUTHOR]

A multistage machining process is employed to machine the blades with low stiffness. Nonetheless, machining errors can be transferred and accumulate throughout the multistage machining process, complicating the precise prediction of the final accuracy of thin-walled blades. Consequently, this paper introduces a machining accuracy prediction model for thin-walled blades that takes into account initial error. The machining error prediction model of thin-walled blades is developed using Gaussian process regression optimized by the sparrow search algorithm (SSA-GPR) with the initial contour error, depth of cut, feed per tooth, and spindle speed as inputs, and the machining error as the output. And the results show that the prediction accuracy of the SSA-GPR is 6.73 % higher than that of the Gaussian process regression (GPR), 13.73 % higher than that of the back propagation neural network (BPNN), and 32.32 % higher than that of the support vector machine regression (SVR). The influence of the initial error and milling parameters on the machining error is analyzed through the length-scales of the Gaussian kernel function. The findings indicate that the depth of cut, feed per tooth and initial error significantly affect the machining error, whereas the spindle speed has a minor impact on the machining error. Furthermore, the 3D graph based on the SSA-GPR shows that the increase of the initial error will increase the machining error of thin-walled blades. This research provides a theoretical foundation for the process optimization of thin-walled blades. • A machining accuracy prediction method considering initial error is proposed. • Combine SSA with GPR to improve the prediction accuracy of GPR. • The correlation is conveniently examined via the hyperparameters of the GPR. • The initial error significantly affects the machining error of thin-walled blades. [ABSTRACT FROM AUTHOR]

Accurate calculation of equivalent circuit parameters is a prerequisite for accurately calculating the large‐capacity synchronous condenser parameter model. Due to its special transient operating conditions, the high transient magnetic saturation effect during operation causes the non‐linearity and time‐varying of the equivalent circuit parameters. The field mutual leakage reactance is the critical factor affecting the field current, and the time‐varying of the equivalent circuit parameters is closely related to the field current. However, the existing equivalent circuit parameter calculation methods considering field leakage reactance cannot achieve time‐varying parameters. A calculation method of time‐varying equivalent circuit parameters based on a back propagation neural network algorithm is proposed, which solves the calculation problem of time‐varying equivalent circuit parameters considering field mutual leakage reactance. Then, a 300MVar condenser is taken as the research object, and the proposed method is used to simulate the different operating conditions of the condenser and verified by the finite element method and experiment. The results show that the method improves the calculation accuracy of the equivalent circuit parameter model, reduces the calculation time, and applies to different operating conditions. [ABSTRACT FROM AUTHOR]

This paper aims to study an optimization method for the lightweight design of bus superstructure. According to the requirements of ECE R66, the bus rollover finite element model has been developed, and the bus rollover process has been simulated and validated by experimental tests. The maximum error between test results and simulation results was 6.8%, which indicated that the simulation of bus rollover had good accuracy. A multi-objective optimization method for rollover safety has been proposed by combining a back propagation (BP) neural network model with a non-dominated sorting genetic algorithm (NSGA-II). The neural network model considered a different joint scheme of closed loop, wall thickness of side frame longitudinal beam, section of side frame longitudinal beam, wall thickness of side frame beam and section of side frame beam as inputs. It took the minimum distance of the survival space from the side column and the mass of the superstructure as outputs. The results show that the coupling optimization of the BP neural network and NSGA-II can reduce the total mass of the bus by 7.7%, which verifies the feasibility of applying the intelligent algorithm to the lightweight design of the bus. [ABSTRACT FROM AUTHOR]

The final particle moisture content of ceramic slurry spray drying affects the processing, product quality, and process energy consumption. While the real-time moisture content determination is very difficult for spray drying process due to nonlinear, severe lag, interference factors, and complexity of the systems, the high temperature, high humidity drying environment and short drying process. In current work, an improved moth optimization (IMFO) algorithm combined with backpropagation neural network (BPNN) was proposed to predict the moisture content of ceramic slurry particles during spray drying. The performance of the model is trained and tested. Results demonstrate that IMFO has better convergence ability and speed compared to other algorithms such as particle swarm optimization (PSO) and gravitational search algorithm (GSA). The IMFO-BPNN model achieves a MAE of 0.0293, RMSE of 0.0383, and R2 value of 0.9113, outperforming the prediction performance of BPNN and MFO-BPNN models. The absolute error rate of the IMFO-BPNN model (0–5%) is lower compared to BPNN (5–10%) and MFO-BPNN model (>10%), showcasing superior accuracy in predicting moisture content. This mathematical model established in the study provides an efficient, accurate, and nondestructive method for predicting the drying endpoint of ceramic slurry spray drying. [ABSTRACT FROM AUTHOR]

Color, firmness, soluble solid content, and pH are important indices for assessing the quality and maturity of loquats. To explore the feasibility of rapid and non‐destructive determination of loquat quality and maturity, this study utilized hyperspectral imaging combined with chemometrics to predict four quality indices of loquats and discriminate their maturity. Partial least squares regression models were developed using both raw and pre‐processed spectral data to determine the optimal pre‐processing method of multiple scattering correction and standard normal variate (SNV). The competitive adaptive reweighted sampling (CARS) and successive projection algorithms were used to extract spectral features. Feature wavelength models were subsequently developed using multiple linear regression (MLR) and error back propagation neural network. Finally, maturity determination models for loquats were developed by partial least squares discrimination analysis (PLS‐DA), support vector machine, and random forest. The SNV‐CARS‐MLR model performed relatively better than the other models for predicting four quality indices. The PLS‐DA model exhibited superior performance, with discrimination accuracies of 99.19% and 96.67% for the calibration and prediction sets. This study demonstrates that integrating hyperspectral imaging and chemometrics enables rapid and non‐destructive determination of loquat quality and maturity. [ABSTRACT FROM AUTHOR]

Micro-crack propagation in polycrystalline materials can strongly depend on the defect size and its ratio to specimen size, and local variation in the microstructural features such as grain orientation, size, etc. While the dependencies are understood heuristically, the use of mechanistic models to capture the effect of various factors influencing micro-crack propagation can enable accurate prediction of fracture properties of polycrystalline materials and their engineering. To this end, a crystal plasticity coupled to damage model for micro-crack propagation on cleavage planes has been developed in this work and is shown to successfully capture the grain orientation dependent growth. In order to identify a suitable integration scheme for the coupled model, a one-dimensional model is developed and a detailed comparative analysis of three different schemes is performed. The analysis shows that the coupled explicit–implicit scheme is the most suitable and is a key finding of this work. Subsequently, a two-scale multi-scale method has been developed to include the interaction between the defect, its surrounding microstructure and the specimen. The two-scale method along with the coupled crystal plasticity-damage model has been applied to perform finite element method based micro-crack growth simulations for a microstructurally short and physically long crack with two different microstructures with random orientation and texture. Such a study comparing microstructural effects on crack growth from pre-existing defects of drastically disparate sizes hasn't been performed before and is a novelty of this work. The analyses clearly show that though the micro-crack path from long crack is different depending on the orientation distribution, the rates are nearly independent of the local behavior. Moreover, the micro-crack propagation rate from long crack is significantly larger at the initial stages, with the latter showing significant acceleration after a small growth. Overall, the influence of microstructure on the crack growth behavior is stronger for short cracks, which conform with experimental observations and is successfully captured by the proposed model. [ABSTRACT FROM AUTHOR]

• Orbit maneuver-free approach to the angle-only relative orbit determination for is proposed. • The angles-only orbital observability problem is solved by introducing radial basis function neural network to capture the nonlinearity of the perturbed dynamics. • The RBFNN frame including training data acquisition, data pre-processing, and the network design for angles-only orbit determination problem is developed. • The validity of the proposed algorithm is evaluated by numerical simulations. • The anti-noise, generalization performance, and the sensitivity of the solution are checked. Angles-only orbit determination during space situational awareness missions for non-cooperative targets such as space debris is subject to the well-known observability problem, that is, the orbital state is weakly observable or even unobservable because of missing range measurements. The key point to solve this problem is how to quickly capture the nonlinearity of orbit dynamics if only one space-based passive sensor is available to observe the target and translational maneuvers are not executed. To solve the short-arc angles-only problem, this study develops a simple and fast orbit determination method by exploiting the advantages of radial basis function neural network (RBFNN). Emphasis was placed on the design of the RBFNN, which was trained to construct a mapping network model from line-of-sight (LOS) measurements to the relative orbit. First, the perturbed relative orbit dynamics considering the Earth's non-spherical J2 term and air drag was established with the LOS measurement model. Second, a RBFNN-based angles-only orbit determination frame was developed, in which the generator of the training dataset, data preprocessing algorithm, and RBF network structure were designed. Finally, the proposed method was verified and tested using a set of numerical simulations of low-Earth orbit cases. The anti-noise and generalization performance of the designed network and the sensitivity of the solution accuracy to the measurement frequency and span were presented and discussed. Additionally, the advantages of the RBFNN-based method were confirmed by comparison with the results obtained using the BPNN (Back Propagation Neural Network)-based method. The simulation results show that the average orbit prediction error for LEO scenarios is approximately 0.08% using the index of initial relative distance, where only three sets of LOS angles are measured within a span of 24 s. [ABSTRACT FROM AUTHOR]

A hybrid compensation scheme for piezoelectric ceramic actuators (PEAs) is proposed. In the hybrid compensation scheme, the input rate-dependent hysteresis characteristics of the PEAs are compensated. The feedforward controller is a novel input rate-dependent neural network hysteresis inverse model, while the feedback controller is a proportion integration differentiation (PID) controller. In the proposed inverse model, an input rate-dependent auxiliary inverse operator (RAIO) and output of the hysteresis construct the expanded input space (EIS) of the inverse model which transforms the hysteresis inverse with multi-valued mapping into single-valued mapping, and the wiping-out, rate-dependent and continuous properties of the RAIO are analyzed in theories. Based on the EIS method, a hysteresis neural network inverse model, namely the dynamic back propagation neural network (DBPNN) model, is established. Moreover, a hybrid compensation scheme for the PEAs is designed to compensate for the hysteresis. Finally, the proposed method, the conventional PID controller and the hybrid controller with the modified input rate-dependent Prandtl-Ishlinskii (MRPI) model are all applied in the experimental platform. Experimental results show that the proposed method has obvious superiorities in the performance of the system. [ABSTRACT FROM AUTHOR]

The deposition and dynamics of smoke layers in large-space building fires are governed by a complex interplay of factors, making the prediction of such dynamics using traditional mathematical models challenging. In response, this study introduces a Back Propagation (BP) neural network model, devised from field simulation data, to efficiently forecast the temporal progression of smoke layers. It was observed that the model exhibits minimal training errors and high processing speeds, thereby fulfilling the stringent accuracy demands of fire engineering. Specifically, the model achieved a minimum relative error of 0.0005 and a maximum of 0.0845 across various prediction points, underscoring its reliability and precision. The ability of this BP neural network model to predict smoke layer changes significantly enhances the design optimization of smoke control systems swiftly and accurately in large buildings and supports rapid, informed decision-making during fire emergencies. Moreover, the model facilitates the development of engineering calculation models tailored for the quick prediction of fire smoke dynamics, which are essential for both theoretical research and practical applications. This approach not only conserves experimental resources but also advances the implementation of scientific, effective rescue operations in the event of large space building fires. [ABSTRACT FROM AUTHOR]

Real-time heart rate monitoring and early detection of heart abnormalities are vital to determine heart health before it worsens. To achieve this goal, this project uses the backpropagation neural network (BPNN) method including its capability to classify heartbeats into normal or abnormal by inputting heartbeat values in BPM units derived from prototypes utilizing sensors like Sensor Easy Pulse and NodeMCU, along with considerations of age and sports activity. All data from sensors will be stored in Firebase. Then Firebase will connect to Android, and the normal and abnormal heart classification results will be displayed on the Android system. Simulation results successfully examined 40 people as a sample and provided information from real-time heart rate monitoring, age, and sports activity as input. This research seeks to contribute to improving health services at various public health service centers and independently in detecting heart health early. [ABSTRACT FROM AUTHOR]

The performance improvement of CMOS computer fails to meet the enormous data processing requirement of artificial intelligence progressively. The memristive neural network is one of the most promising circuit hardwares to make a breakthrough. This paper proposes a novel memristive synaptic circuit that is composed of four MOS transistors and one memristor (4T1M). The 4T1M synaptic circuit provides flexible control strategies to change memristance or respond to the input signal. Applying the 4T1M synaptic circuit as the cell of memristive crossbar array, based on the structure and algorithm of the back-propagation (BP) neural network, this paper proposes circuit design of the memristive crossbar-based BP neural network. By reusing the 4T1M memristive crossbar array, the computations in the forward-propagation process and back-propagation process of BP neural network are accomplished on the memristive crossbar-based circuit to accelerate the computing speed. The 4T1M memristive crossbar array can change all the cells' memristance at a time, accordingly, the memristive crossbar-based BP neural network can realize synchronous memristance adjustment. The proposed memristive crossbar-based BP neural network is then evaluated through experiments involving XOR logic operation, iris classification, and MNIST handwritten digit recognition. The experimental results present fewer iterations or higher classification accuracies. Further, the comprehensive comparisons with the existing memristive BP neural networks highlight the advantages of the proposed memristive crossbar-based BP neural network, which achieves the fastest memristance adjustment speed using relatively few components. [ABSTRACT FROM AUTHOR]

Paddy field leveling is an essential step before rice transplanting. During the operation of a paddy field grader, a common issue is the wrapping of rice straw around the blades, resulting in a low rice straw burial rate. This study focused on analyzing the operating parameters of a disc spring–tooth-combined paddy field grader. A soil–straw mechanism simulation model was created using EDEM 2021 software to simulate the field operation status. Firstly, the single-factor test was carried out, with the working speed, the working depth of the disc cutter roller, and the rotation speed of the cutter roller as the factors and the straw-buried rate (SBR) and the machine forward resistance (MFR) as the test indexes, and the parameter range was optimized. The parameters were optimized by the response surface method (RSM) and machine learning algorithms. The results indicated that the genetic algorithm–back propagation (GA-BP) neural network outperformed other optimization models in terms of prediction accuracy and stability. By utilizing the GA-BP regression model and RSM model for regression fitting, two sets of optimal parameter combinations were obtained. Verification experiments were carried out using two sets of parameter combinations. Taking the average of the experimental results, the simulation results showed that the straw burial rate was 93.47% and the forward resistance was 6487 N for the parameter combinations of RSM, and the straw burial rate was 94.86% and the forward resistance was 6352 N for the parameter combinations of GA-BP; the field experiments showed that the straw burial rate was 92.86% and the forward resistance was 6518 N for the parameter combinations of RSM, and the straw burial rate was 95.17% and the forward resistance was 6249 N for the parameter combinations of GA-BP. The results demonstrated that the GA-BP prediction model exhibited better predictive capabilities compared to the traditional RSM, providing more accurate predictions of the paddy field grader's field operation performance. [ABSTRACT FROM AUTHOR]

Due to the hot climate, energy consumption for refrigeration is significantly higher in the subtropical monsoon climate region. Combined with renewable energy and ice-storage technology, a model predictive control model of the regional cooling system was proposed, which was conducive to improving the flexibility of the regional cooling system and the ability of peak shifting and valley filling. In this model, an artificial bee colony (ABC) optimized back propagation (BP) neural network was used to predict the cooling load of the regional cooling system, and the model parameter identification method was adopted, combining utilizing a river-water-source heat pump and ice-storage technology. The results showed that the load prediction algorithm of the ABC-BP neural network had a high accuracy, and the variance coefficient of load prediction root-mean-square error (RMSE) was 16.67%, which was lower than BP, support vector regression (SVR), and long short-term memory (LSTM). In addition, compared with the three control strategies of chiller priority, ice-storage priority, and fixed proportion, the operation strategy optimized by the comprehensive model can reduce the average daily cost by 19.20%, 4.45%, and 5.10%, respectively, and the maximum daily energy consumption by 30.02%, 18.08%, and 8.90%, respectively. [ABSTRACT FROM AUTHOR]

The production capacity of shale oil reservoirs after hydraulic fracturing is influenced by a complex interplay involving geological characteristics, engineering quality, and well conditions. These relationships, nonlinear in nature, pose challenges for accurate description through physical models. While field data provides insights into real-world effects, its limited volume and quality restrict its utility. Complementing this, numerical simulation models offer effective support. To harness the strengths of both data-driven and model-driven approaches, this study established a shale oil production capacity prediction model based on a machine learning combination model. Leveraging fracturing development data from 236 wells in the field, a data-driven method employing the random forest algorithm is implemented to identify the main controlling factors for different types of shale oil reservoirs. Through the combination model integrating support vector machine (SVM) algorithm and back propagation neural network (BPNN), a model-driven shale oil production capacity prediction model is developed, capable of swiftly responding to shale oil development performance under varying geological, fluid, and well conditions. The results of numerical experiments show that the proposed method demonstrates a notable enhancement in R² by 22.5% and 5.8% compared to singular machine learning models like SVM and BPNN, showcasing its superior precision in predicting shale oil production capacity across diverse datasets. [ABSTRACT FROM AUTHOR]

The wide diversity of species and the remarkable variation in morphological features that allow plants to adapt to a wide range of terrestrial environments is a fact that highlights the fundamental and crucial role of plants in the field of biodiversity studies. Currently, research on leaf classification is limited and in its early stages. A novel classification system based on laser-induced breakdown spectroscopy (LIBS) technology was proposed in this paper, integrated with machine learning for real-time, in situ detection and analysis of leaves. Four representative leaf samples—Ilex chinensis, Camellia japonica, Cinnamomum camphora, and Osmanthus fragrans—were subjected to spectral analysis and machine learning techniques. Spectral analysis revealed distinct spectral lines corresponding to elements such as Ca, Al, Mg, Na, and Fe, alongside common elements including C, N, and O. Principal component analysis (PCA) was employed to reduce the dimensionality of the spectral data, and the first 13 principal components used in this study captured 98.76% of the total variance. Following this, support vector machine (SVM), backpropagation artificial neural network and convolutional neural network (CNN) algorithms were applied for machine learning on the principal components to develop leaf recognition classification models. Through comparison, the CNN algorithm, boasting a classification accuracy of up to 94.44%, was ultimately selected. The models established by SVM and back propagation artificial neural network achieved accuracy of only 83.33% and 90.00%, respectively. The results suggest that integrating LIBS with machine learning is an effective and precise approach for leaf classification, offering promising applications in biodiversity research. [ABSTRACT FROM AUTHOR]

The necessity for precise determination of fruit storage durations is paramount in both industrial and domestic spheres, with hyperspectral imaging (HSI) technology emerging as a pivotal tool for prognosticating the physicochemical attributes indicative of mature fruit quality. This investigation employed hyperspectral imaging to conduct a noninvasive analysis of variations in soluble solids content (SSC), hardness, and moisture content (MC) in jujube fruit over the course of storage at divergent temperatures. Throughout the storage intervals (0, 7, 14, and 21 days) at varying temperatures (4 and 20°C), both physicochemical and spectral data were amassed. The raw spectral information underwent preprocessing through multiple scattering correction (MSC), standard normal variation (SNV), and Savitzky–Golay (SG) algorithms to refine the methodologies for SSC, hardness, and moisture content. Subsequently, the competitive adaptive reweighted sampling (CARS) algorithm facilitated the discernment and elimination of extraneous variables, thereby enhancing feature wavelength extraction. This process underpinned the development of partial least squares regression (PLSR), back propagation (BP), and genetic algorithm‐back propagation (GA‐BP) models predicated on CARS‐derived features, culminating in the selection of an optimal model. The findings underscore the capability of hyperspectral imaging technology to swiftly and nondestructively ascertain the SSC, hardness, and MC of jujube throughout the storage phase, thereby enabling the assessment of quality attributes over varying storage durations and facilitating the surveillance of jujube quality maintenance during storage. Practical Applications: The winter jujube garners appreciation from consumers owing to its exquisite flavor, yet its quality diminishes over time in storage due to various factors, thereby impacting its market value. Consequently, it is imperative to surveil the quality alterations of jujube throughout its storage to mitigate the degradation of its quality. Hyperspectral imaging technology offers a sophisticated means to forecast the physicochemical index changes indicative of the fruit's quality at maturity. This research delineates the development of predictive models for the soluble solids, hardness, and moisture content of jujube at divergent temperatures throughout the storage interval, selecting the paramount model through a holistic assessment, thereby fully harnessing the capabilities of hyperspectral imaging technology in monitoring jujube quality during storage. Moreover, the methodology employed herein is adaptable to other fruits in storage, harboring the potential for future application in the real‐time quality monitoring of fruits as they exit the storage facilities. [ABSTRACT FROM AUTHOR]

The reliability and stability of marine diesel engines are pivotal to the safety and economy of maritime operations. Accurate and efficient prediction of the states of these engines is essential for performance evaluation and operational continuity. This paper introduces a novel hybrid deep learning model, the multi-dimensional global temporal predictive (MDGTP) model, designed for synchronous multi-state prediction of marine diesel engines. The model incorporates parallel multi-head attention mechanisms, an enhanced long short-term memory (LSTM) with interleaved residual connections, and gated recurrent units (GRUs). Additionally, we propose a dynamic arithmetic tuna optimization algorithm, which synergizes tuna swarm optimization (TSO), and the arithmetic optimization algorithm (AOA) for hyperparameter optimization, thereby enhancing prediction accuracy. Comparative experiments using actual marine diesel engine data demonstrate that our model outperforms the LSTM, GRU, LSTM–GRU, support vector regression (SVR), random forest (RF), Gaussian process regression (GPR), and back propagation (BP) models, achieving the lowest root mean squared error (RMSE) and mean absolute error (MAE), as well as the highest Pearson correlation coefficient across three sampling periods. Ablation studies confirm the significance of each component in improving prediction accuracy. Our findings validate the efficacy of the proposed MDGTP model for predicting the multi-dimensional operating states of marine diesel engines. [ABSTRACT FROM AUTHOR]

Accurate prediction of estuarine salinity can effectively mitigate the adverse effects of saltwater intrusion and help ensure the safety of water resources in estuarine regions. Presently, diverse data-driven models, mainly neural network models, have been employed to predict tidal estuarine salinity and obtained considerable achievements. Due to the nonlinear and nonstationary features of estuarine salinity sequences, this paper proposed a multi-factor salinity prediction model using an enhanced Long Short-Term Memory (LSTM) network. To improve prediction accuracy, input variables of the model were determined through Grey Relational Analysis (GRA) combined with estuarine dynamic analysis, and hyperparameters for the LSTM model were optimized using a multi-strategy Improved Sparrow Search Algorithm (ISSA). The proposed ISSA-LSTM model was applied to predict salinity at the Cangqian and Qibao stations in the Qiantang Estuary of China, based on measured data from 2011–2012. The model performance is evaluated by mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), and Nash-Sutcliffe efficiency (NSE). The results show that compared to other models including Back Propagation neural network (BP), Gate Recurrent Unit (GRU), and LSTM model, the new model has smaller errors and higher prediction accuracy, with NSE improved by 8–32% and other metrics (MAP, MAPE, RMSE) improved by 15–67%. Meanwhile, compared with LSTM optimized with the original SSA (SSA-LSTM), MAE, MAPE, and RMSE values of the new model decreased by 13–16%, 15–16%, and 11–13%, and NSE value increased by 5–6%, indicating that the ISSA has a better hyperparameter optimization ability than the original SSA. Thus, the model provides a practical solution for the rapid and precise prediction of estuarine salinity. [ABSTRACT FROM AUTHOR]

This study introduces an integrated structural optimization design method based on a BP neural network and NSGA-II multi-objective genetic algorithm. Initially, a two-dimensional axisymmetric finite element model of the Giant Magnetostrictive Actuator (GMA) was established, and the coupling simulation of the electromagnetic field, structural field, and temperature field was conducted to obtain the GMA's performance parameters. Subsequently, the structural parameters of the GMA magnetic circuit, including the magnetic conducting ring, magnetic conducting sidewall, magnetic conducting body, and coil, were used as inputs, and the axial magnetic induction intensity, uniformity of axial magnetic induction intensity, and coil loss on the Giant Magnetostrictive Material (GMM) rod were used as outputs to establish a back propagation (BP) neural network model. This model delineated the nonlinear relationship between structural parameters and performance parameters. Then, the BP-NSGA-II algorithm was applied to perform multi-objective optimization on the actuator's structural parameters, resulting in a set of Pareto optimal non-dominated solutions, from which a set of optimal solutions was obtained using the entropy weight method. Finally, simulation analysis of this optimal solution was conducted, indicating that under a 5 A power supply excitation, the maximum axial magnetic induction intensity on the optimized GMM rod increased from 0.87 T to 1.12 T; the uniformity of axial magnetic induction intensity improved from 93.1% to 96.5%; and the coil loss decreased from 7.79 × 104 W/m3 to 4.97 × 104 W/m3. Based on the optimization results, a prototype actuator was produced, and the test results of the prototype's output characteristics proved the feasibility of this optimization design method. [ABSTRACT FROM AUTHOR]

The converter is a complex, high temperature, high pressure reactor with limited internal moitoring. At present, data‐driven models mainly focus on the prediction differences between algorithms, and there is relatively little analysis of the impact of different hyperparameters on prediction accuracy. Taking a 120 t converter in a Chinese steel plant as an example, this paper explores the application of particle swarm optimization‐back propagation neural network (PSO‐BP) in converter temperature prediction. First, the Pauta criterion or Box plot method was used to preprocess the data by prescreening. Subsequently, the influence of the activation function, learning rate, and number of hidden layer nodes of BP on the prediction accuracy of the endpoint temperature were explored. Then we investigated the influence of PSO parameters on the optimal result of BP initial value. Comparing the temperature prediction hit rate before and after optimization, the BP model has hit rates of 63.64%, 79.22%, and 87.45% within ±10, ±15, and ±20 °C, respectively, and the PSO‐BP model has hit rates of 68.40%, 84.85%, and 94.81%, respectively. In comparison, PSO‐BP extracts data features more accurately, has higher stability, and has better accuracy in predicting the endpoint temperature of the converter. [ABSTRACT FROM AUTHOR]

The randomness and fluctuation of large-scale distributed photovoltaic (PV) power will affect the stable operation of the distribution network. The energy storage system (ESS) can effectively suppress the power output fluctuation of the PV system and reduce the PV curtailment rate through charging/discharging states. In order to improve the operation capability of the distribution network and PV consumption rate, an optimal multi-objective strategy is proposed based on PV power prediction. First, the back propagation (BP) neural network with an improved genetic algorithm (GA) is used to predict PV power output. Furthermore, an adaptive variability function is added to the GA to improve the prediction accuracy. Then, the distribution network model containing distributed PV and the ESS is constructed. The optimal object contains network power loss, voltage deviation, and PV consumption. The model is solved based on the improved multi-objective particle swarm optimization (MOPSO) algorithm of Pareto optimality. The probabilistic amplitude is adopted to encode the particles for avoiding local optimal. Finally, the proposed optimal strategy is verified by the IEEE 33-bus distribution network. The results show that the proposed strategy has an obvious effect on reducing the network power loss and voltage deviation, as well as improving the PV consumption rate. [ABSTRACT FROM AUTHOR]

Exploring the impact of different monitoring angles from unmanned aerial vehicle (UAV) on the monitoring accuracy of soil moisture content (SMC) is crucial for precision irrigation. To this end, experiment was conducted to monitor the SMC of winter wheat at different growth stages under different irrigation treatments in Yangling, Shaanxi, China. At a solar zenith angle of 45°, multispectral remote sensing data from a UAV were collected at thirteen different monitoring zenith angles. Simultaneously, the SMC in the wheat root zone was measured. From the UAV multispectral images, spectral reflectance was extracted for the construction of vegetation indices. Then the correlation between the vegetation indices and the measured SMC was analyzed. With the vegetation indices as input variables, SMC monitoring models were constructed using Extreme Learning Machine (ELM), Random Forest (RF), and Back Propagation Neural Network (BPNN). The study also examined the effect of specific angles (hotspot and dark spot angles) on the estimation accuracy of the SMC at the nadir angle. The results indicated that different monitoring angles significantly impact the SMC estimation accuracy. Band reflectance and vegetation indices exhibited significant peak values and angular effects at the monitoring zenith angle of 45°. The models achieved the optimal inversion accuracy at the hotspot angle (at a monitoring zenith angle of 45° in the solar principal plane), and the accuracy was ranked as follows: BPNN (R2 = 0.71; RMSE = 1.69) > ELM (R2 = 0.52; RMSE = 1.94) > RF (R2 = 0.48; RMSE = 2.10). By eliminating shadows at the nadir angle through the threshold of dark spot, inversion accuracy similar to the hotspot direction is achieved. This study provides a basis for appropriate selection of UAV flight angles for the monitoring of SMC in the root zone of winter wheat. [ABSTRACT FROM AUTHOR]

The physicochemical properties of steel slag were investigated using SEM and IR, and it was found that free calcium oxide and free magnesium oxide in steel slag produce calcium hydroxide when in contact with water, leading to volume expansion. Thus, the expansion rate of steel slag itself was first investigated, and it was found that the volume expansion of steel slag was more obvious in seven days after water immersion. Then, the cement dosages of 5% and 6% of the steel slag expansion rate and cement-stabilized gravel volume changes between the intrinsic link were further explored after the study found that the cement bonding effect can be partially inhibited due to the volume of expansion caused by the steel slag, so it can be seen that increasing the dosage of cement can reduce the volume expansion of steel slag cement-stabilized gravel with the same dosage of steel slag. Finally, a prediction model of the expansion rate of steel slag cement-stabilized gravel based on the BP (back propagation) neural network was established, which was verified to be a reliable basis for predicting the expansion rate of steel slag cement-stabilized aggregates and improving the accuracy of the proportioning design. [ABSTRACT FROM AUTHOR]