Search

To improve the breakdown voltage (BV), a GaN-based high-electron-mobility transistor with a hybrid AlGaN back barrier (HBB-HEMT) was proposed. The hybrid AlGaN back barrier was constructed using the Al0.25Ga0.75N region and Al0.1G0.9N region, each with a distinct Al composition. Simulation results of the HBB-HEMT demonstrated a breakdown voltage (1640 V) that was 212% higher than that of the conventional HEMT (Conv-HEMT) and a low on-resistance (0.4 mΩ·cm2). Ultimately, the device achieved a high Baliga's figure of merit (7.3 GW/cm2) among reported devices of similar size. A back-propagation (BP) neural network-based prediction model was trained to predict BV for enhanced efficiency in subsequent work. The model was trained and calibrated, achieving a correlation coefficient (R) of 0.99 and a prediction accuracy of 95% on the test set. The results indicated that the BP neural network model using the Levenberg–Marquardt algorithm accurately predicted the forward breakdown voltage of the HBB-HEMT, underscoring the feasibility and significance of neural network models in designing GaN power devices. [ABSTRACT FROM AUTHOR]

The objective of this study is to investigate the impact of emotional design and sustainable product design on user experience and satisfaction. Additionally, the study aims to optimize the combination efficiency and material selection methods of these two design approaches, extracting optimization parameters based on emotional and sustainable product design principles. By analyzing user satisfaction through questionnaires, various product indicators were examined. The study ultimately establishes a BP neural network optimization model by analyzing the design elements of different products and the satisfaction levels of various indicators. This BP neural network design optimization model, integrating emotional and sustainable design, demonstrates an accuracy rate of over 95% in predicting user satisfaction for different design schemes. Upon examining the emotional design and sustainable design parameter tables following data standardization, and analyzing various product models, it was concluded that the rate of change in each design parameter significantly impacts the satisfaction of each product indicator, highlighting the importance of these parameters in product design optimization. [ABSTRACT FROM AUTHOR]

The smart city concept has taken center stage as a paradigm shift in urban governance, promising innovation, sustainability, and strategic upgrades, and drawing the attention of researchers globally. However, existing frameworks for assessing smart cities remain incomplete and simplistic. This paper aims to address the following question: what is the process and current situation of 30 capitals in China after the implementation of smart city construction, especially from the new perspective of social, physical, and informational space development? To this end, we focus on 30 national and provincial capitals in China, proposing a novel, tri-dimensional SPI model—Social, Physical, and Information space—for smart city spatial development assessment. Employing a robust methodological approach, including entropy weighting, coupled coordination degree models, and the Dagum Gini coefficient, we conduct a spatial development and coordination analysis of these cities from 2011 to 2021. In addition, we utilize BP neural networks to evaluate the contribution of each indicator to the spatial coupled coordination. Our findings indicate a steady increase in the spatial coupled coordination development level of smart capitals in China, alongside a narrowing disparity in development speeds across regions, resulting in a staggered spatial distribution pattern. Specifically, the Information space subsystem represents the most influential driver of coupled coordination. The significance of this research lies in its unique tri-dimensional spatial perspective, offering valuable insights into the spatial development and coordination discrepancies in the smart city concept. These insights offer evidence-based support for regional planning and optimization strategies in China. [ABSTRACT FROM AUTHOR]

Predicting soil moisture accurately is the precondition of realizing accurate irrigation and improving the utilization rate of water resource and the necessary step of developing water‐saving agriculture, which can alleviate the water shortage in our agricultural effectively. In order to further improve the accuracy of soil water content prediction, a combined soil water content prediction model based on Autoregressive moving average model (ARIMA model) and back propagation neural network (BP neural network) neural network is proposed. The model considers the linear and nonlinear characteristics of soil water content data, combines them according to the characteristics of the model itself, gives full play to the advantages of ARIMA model and BP neural network. At the same time, two data smoothing methods were used to establish the ARIMA model, and the adaptive moment estimation algorithm (Adam algorithm) and mind evolutionary algorithm (MEA) optimization BP neural network model were used to propose an improved combined prediction model to predict soil water content data. The experimental results show that the average relative error of the improved combinatorial prediction model is 1.51%, which is 4.18%, 0.95% and 3.1% lower than the combinatorial prediction model, BP neural network model and ARIMA model, respectively, and the overall prediction effect is better, which can be used to save agricultural water and provide a strong basis for the development of water‐saving agriculture in China. At the same time, it can also ensure that crop production is increased and the purpose of national food security is guaranteed. [ABSTRACT FROM AUTHOR]

The early identification of potential hazards is crucial for landslide early warning and prevention and is a key focus and challenging issue in landslide disaster research. The challenges of traditional investigation and identification methods include identifying potential hazards of landslides triggered by heavy rainfall and mapping areas susceptible to landslides based on rainfall conditions. This article focuses on the problem of early identification of rainfall-induced accumulation landslide hazards and an early identification method is proposed, which is "first identifying the accumulation that is prone to landslides and then determining the associated rainfall conditions". This method is based on identifying the distribution and thickness of accumulation, analyzing the rainfall conditions that trigger landslides with varying characteristics, and establishing rainfall thresholds for landslides with different accumulation characteristics, ultimately aiming to achieve early identification of accumulation landslide hazards. In this study, we focus on the Zigui section of the Three Gorges Reservoir as study the area, and eight main factors that influence the distribution and thickness of accumulation are extracted from multi-source data, then the relative thickness information extraction model of accumulation is established by using the BP neural network method. The accumulation distribution and relative thickness map of the study area are generated, and the study area is divided into rocky area (less than 1 m), thin (1 to 5 m), medium (5 to 10 m), and thick area (thicker than 10 m) according to accumulation thickness. Rainfall is a significant trigger for landslide hazards. It increases the weight of the sliding mass and decreases the shear strength of soil and rock layers, thus contributing to landslide events. Data on 101 rainfall-induced accumulation landslides in the Three Gorges Reservoir area and rainfall data for the 10 days prior to each landslide event were collected. The critical rainfall thresholds corresponding to a 90% probability of landslide occurrence with different characteristics were determined using the I-D threshold curve method. Prediction maps of accumulation landslide hazards under various rainfall conditions were generated by analyzing the rainfall threshold for landslides in the Three Gorges Reservoir area, serving as a basis for early identification of rainfall-induced accumulation landslides in the region. The research provides a method for the early identification of landslides caused by heavy rainfall, delineating landslide hazards under different rainfall conditions, and providing a basis for scientific responses, work arrangements, and disaster prevention and mitigation of landslides caused by heavy rainfall. [ABSTRACT FROM AUTHOR]

This paper proposes a new optimization algorithm for backpropagation (BP) neural networks by fusing integer-order differentiation and fractional-order differentiation, while fractional-order differentiation has significant advantages in describing complex phenomena with long-term memory effects and nonlocality, its application in neural networks is often limited by a lack of physical interpretability and inconsistencies with traditional models. To address these challenges, we propose a mixed integer-fractional (MIF) gradient descent algorithm for the training of neural networks. Furthermore, a detailed convergence analysis of the proposed algorithm is provided. Finally, numerical experiments illustrate that the new gradient descent algorithm not only speeds up the convergence of the BP neural networks but also increases their classification accuracy. [ABSTRACT FROM AUTHOR]

Isothermal constant strain rate compression experiments were carried out on TC20 titanium alloy using a Gleeble- 1500 thermal simulation tester to investigate its high temperature flow behaviour at deformation temperatures of 750 - 900 °C and strain rates of 0,001 - 1 s-1. The results show that the flow stress basically decreases with increasing deformation temperature and increases with increasing strain rate. The correlation coefficients and mean relative errors were 0,998 and 5,06 % respectively, proving that the BP neural network-based intrinsic structure model is effective in predicting the flow stress of the alloy.

The difference in farming culture is the basis for the exchange, reference, and integration of agricultural culture. We propose a method based on data fusion and extraction method for analyzing differences in farming culture between China and Japan in this paper. Specifically, we designed a farming culture difference analysis model based on deep learning technology and improved algorithm. We combined deep neural network and particle swarm algorithm to design and improve the analysis model of farming culture difference. Firstly, we introduce in detail the designed analysis model based on deep learning, namely BP neural network. Secondly, we adopt the particle swarm algorithm (PSO) to improve and upgrade the defects of the BP neural network model. The experimental and comparative analysis of the results shows the characteristics of China's vast land and abundant resources and the characteristics of Japan, an island country with limited cultivated land. [ABSTRACT FROM AUTHOR]

The autonomous driving simulation field lacks evaluation and forecasting systems for simulation results. The data obtained from the simulation of target algorithms and vehicle models cannot be reasonably estimated. This problem affects subsequent vehicle improvement and parameter calibration. The authors relied on the simulation results of the AEB algorithm. We selected the BP Neural Network as the basis and improved it with a genetic algorithm optimized via a roulette algorithm. The regression evaluation indicators of the prediction results show that the GA-BP neural network has better prediction accuracy and generalization ability than the original BP neural network and other optimized BP neural networks. This GA-BP neural network also fills the Gap in Evaluation and Prediction Systems. [ABSTRACT FROM AUTHOR]

Background: Although the spatio-temporal structure of muscle activation in cutting have been studied extensively, including time-varying motor primitives and time-invariant motor modules under various conditions, the factorisation methods suitable for cutting are unclear, and the extent to which each factorisation method loses information about movement during dimensionality reduction is uncertain. Research question: To clarify the extent to which NMF, PCA and ICA retain information about movement when downscaling, and to explore the factorisation method suitable for cutting. Methods: The kinematic data during cutting was captured with a Vicon motion capture system, from which the kinematic features of the pelvic centre of mass were calculated. NMF, PCA and ICA were used to obtain muscle synergies based on sEMG of the cutting at different angles, respectively. A back propagation neural network was constructed using temporal component of synergy as input and the kinematics data of pelvic as output. Calculation of the Hurst index using fractal analysis based on the temporal component of muscle synergy. Results: The quality of sEMG reconstruction is significantly higher with ICA (P

The objective of this study is to investigate the impact of emotional design and sustainable product design on user experience and satisfaction. Additionally, the study aims to optimize the combination efficiency and material selection methods of these two design approaches, extracting optimization parameters based on emotional and sustainable product design principles. By analyzing user satisfaction through questionnaires, various product indicators were examined. The study ultimately establishes a BP neural network optimization model by analyzing the design elements of different products and the satisfaction levels of various indicators. This BP neural network design optimization model, integrating emotional and sustainable design, demonstrates an accuracy rate of over 95% in predicting user satisfaction for different design schemes. Upon examining the emotional design and sustainable design parameter tables following data standardization, and analyzing various product models, it was concluded that the rate of change in each design parameter significantly impacts the satisfaction of each product indicator, highlighting the importance of these parameters in product design optimization.

The reliability of modern building electrical systems are receiving increasing attention as they become more intelligent and complex. As the majority of building electrical systems use neutral point grounding, earth faults or short circuits can get worse over time and damage both the distribution system and the electrical equipment. To this end, the corresponding three phases and four categories, namely three-phase voltage, three-phase current after fault, three-phase voltage distortion rate, three-phase current distortion rate, a total of 12 dimensional fault feature vectors and 10 fault simulation types, were summarised and extracted in conjunction with the actual operating conditions of the system. Using traditional fault identification ideas and neural network algorithm as reference, a 12-dimensional fault feature vector is used as the model input to construct a building electrical fault diagnosis and detection model based on ELM algorithm. Results showed that the ELM-based model's classification accuracy for this experimental sample was 97.56 %, its AUC was 0.92, and its RMSE was 0.3521. These figures were higher than the classification accuracy and performance of the BP algorithm and GA-BP algorithm fault diagnosis models, and they also demonstrate better robustness and generalizability. The model also has a 97.27 % correct rate in fault discrimination, while the computation time is only 0.201 s, and its fault identification and diagnosis speed is faster than other algorithmic models. At the same time, this research model has a good fault monitoring accuracy of up to 98.6 % for building electrical systems. The research can provide a more sensitive, accurate and rapid fault monitoring method for the current building electrical system. It also improves the reliability of the building electrical system in a complex environment and achieves better protection of the system. This has a certain significance for the development of the building electrical industry. [ABSTRACT FROM AUTHOR]

BP neural network is characterized by fitting nonlinear data in machine tool thermal error modeling, but it has poor robustness. This paper proposes a PLS-BP neural network modeling method to effectively improve the prediction accuracy and robustness of the model. First, this method employs the partial least squares to reduce the dimensionality of temperature data and extract principal components, eliminating redundant information. Second, a regression mapping model is established on the basis of BP neural network and thermal error, and its prediction performance is compared with that of traditional BP models. The results indicate the PLS-BP modeling method achieves high prediction accuracy and robustness. It is also shown that the method is markedly superior to the traditional BP models, keeping the maximum mean and maximum standard deviation of residual standard deviation sets of prediction results below 3.13 jxm and 1.32 jxm respectively [ABSTRACT FROM AUTHOR]

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) 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.)

This paper distributed questionnaires to permanent residents of Shaanxi Province, on the basis of valid data, the simple descriptive statistical analysis was carried out, and an evaluation model of the status of dissemination of intangible cultural heritage based on factor analysis and BP neural network was established. The results showed that the communication status of intangible cultural heritage in Shaanxi Province is in the "general" stage. [ABSTRACT FROM AUTHOR]

With the increasing application of UAVs, UAV positioning technology for indoor complex environment has become a hot research issue in the industry. The traditional UWB positioning technology is affected by problems such as multipath effect and non-line-of-sight propagation, and its application in complex indoor environments has problems such as poor positioning accuracy and strong noise interference. We propose an improved LSE-EKF optimisation algorithm for UWB positioning in indoor complex environments, which optimises the initial measurement data through a BP neural network correction model, then optimises the coordinate error using least squares estimation to find the best pre-located coordinates, finally eliminates the interference noise in the pre-located coordinate signal through an EKF algorithm. It has been verified by experiments that the evaluation index can be improved by more than 9% compared with EKF algorithm data, especially under non-line-of-sight (NLOS) conditions, which enhances the possibility of industrial application of indoor UAV. [ABSTRACT FROM AUTHOR]

This paper explores the digital learning model from the 4 paths of macro education reform. The four paths of macro education reform include improving the education system, changing the education model, updating education content, and establishing a comprehensive evaluation system. The construction of a learning port is based on the aspects of the learning environment and learning service, as well as research on the characteristics of digital learning modes. Based on BP neural networks, an evaluation model for community education digital resources has been established. The defects of the BP neural network are optimized by using an artificial fish school-frog jump hybrid algorithm, and 19 index factors are selected to construct the evaluation system of digital learning resources. Students’ digital learning abilities and the degree of innovation of digital learning resources in community education were separately analyzed using pre-and post-tests. The average performance of students in the experimental class improved by 9.89 points, and the score interval improved to [85,98], which was significantly better than the control class. The most obvious effect is the improvement of resource use performance, from 7.596 to 9.161. Improved learning ability and innovation of learning resources can be achieved through the use of digital learning modes.

In order to overcome the problems of poor real-time performance, high false alarm rate and underreport alarm rate of mine external fire monitoring, a method of fire monitoring using the fusion of visible visual features is proposed.Firstly, the visual features corresponding to the video images of fire sources in different monitoring environments are analyzed, and the extraction methods of fire source texture, sharp corners, similarity coefficient and flicker frequency are designed.Then, an improved seed region growth algorithm is used to segment the suspected fire area, and different feature extraction methods are used to calculate the dynamic and static characteristics of the suspected fire area.Secondly, the extracted dynamic and static features are used to construct fire feature vectors.Finally, a fire monitoring model using BP neural network is constructed, and monitoring model is verified.The results show that the proposed fire monitoring method can effectively detect mine external fire in different scenes and distances.The correct rate and detection rate are 98.60% and 99.06%, respectively, the false detection rate is as low as 2.00%.It has strong anti-interference ability and robustness.

With the development of urban engineering construction, the issue of construction engineering accidents has become more and more prominent. The geotechnical parameter interval obtained by using the traditional methods cannot meet the needs of actual engineering. Based on the idea of unsupervised learning, the peaty soil with the worst engineering properties is considered, and 8 physical indexes are selected as the input set. The principal component analysis (PCA) algorithm is used to realize the dimensionality reduction of multi-sample and multi-parameter decoupling, and the correlation and sensitivity of each physical index is obtained. Combined with its correlation and sensitivity, the comprehensive evaluation value of physical indexes of peat soil with different buried depths is given. The k-means clustering is used to analyze the relationship among physical index, and comprehensive evaluation value and engineering characteristics of peaty soil provide a theoretical basis for the selection of geotechnical parameters. The supervised learning method-BP neural network algorithm is used to analyze the unsupervised results and verify the accuracy of the (PCA—k-means) algorithm model. The normal samples obtained by clustering analysis are optimized by a variety of truncation methods to obtain a reliable value range, and the value results are compared with the actual engineering values to verify the rationality of the model engineering parameters. The algorithm model is of good engineering application value. The research results can provide references for engineering investigation, design and construction parameter values, and also provide a new analysis method for geotechnical parameter value analyses.

The smart city concept has taken center stage as a paradigm shift in urban governance, promising innovation, sustainability, and strategic upgrades, and drawing the attention of researchers globally. However, existing frameworks for assessing smart cities remain incomplete and simplistic. This paper aims to address the following question: what is the process and current situation of 30 capitals in China after the implementation of smart city construction, especially from the new perspective of social, physical, and informational space development? To this end, we focus on 30 national and provincial capitals in China, proposing a novel, tri-dimensional SPI model—Social, Physical, and Information space—for smart city spatial development assessment. Employing a robust methodological approach, including entropy weighting, coupled coordination degree models, and the Dagum Gini coefficient, we conduct a spatial development and coordination analysis of these cities from 2011 to 2021. In addition, we utilize BP neural networks to evaluate the contribution of each indicator to the spatial coupled coordination. Our findings indicate a steady increase in the spatial coupled coordination development level of smart capitals in China, alongside a narrowing disparity in development speeds across regions, resulting in a staggered spatial distribution pattern. Specifically, the Information space subsystem represents the most influential driver of coupled coordination. The significance of this research lies in its unique tri-dimensional spatial perspective, offering valuable insights into the spatial development and coordination discrepancies in the smart city concept. These insights offer evidence-based support for regional planning and optimization strategies in China.

The early identification of potential hazards is crucial for landslide early warning and prevention and is a key focus and challenging issue in landslide disaster research. The challenges of traditional investigation and identification methods include identifying potential hazards of landslides triggered by heavy rainfall and mapping areas susceptible to landslides based on rainfall conditions. This article focuses on the problem of early identification of rainfall-induced accumulation landslide hazards and an early identification method is proposed, which is “first identifying the accumulation that is prone to landslides and then determining the associated rainfall conditions”. This method is based on identifying the distribution and thickness of accumulation, analyzing the rainfall conditions that trigger landslides with varying characteristics, and establishing rainfall thresholds for landslides with different accumulation characteristics, ultimately aiming to achieve early identification of accumulation landslide hazards. In this study, we focus on the Zigui section of the Three Gorges Reservoir as study the area, and eight main factors that influence the distribution and thickness of accumulation are extracted from multi-source data, then the relative thickness information extraction model of accumulation is established by using the BP neural network method. The accumulation distribution and relative thickness map of the study area are generated, and the study area is divided into rocky area (less than 1 m), thin (1 to 5 m), medium (5 to 10 m), and thick area (thicker than 10 m) according to accumulation thickness. Rainfall is a significant trigger for landslide hazards. It increases the weight of the sliding mass and decreases the shear strength of soil and rock layers, thus contributing to landslide events. Data on 101 rainfall-induced accumulation landslides in the Three Gorges Reservoir area and rainfall data for the 10 days prior to each landslide event were collected. The critical rainfall thresholds corresponding to a 90% probability of landslide occurrence with different characteristics were determined using the I-D threshold curve method. Prediction maps of accumulation landslide hazards under various rainfall conditions were generated by analyzing the rainfall threshold for landslides in the Three Gorges Reservoir area, serving as a basis for early identification of rainfall-induced accumulation landslides in the region. The research provides a method for the early identification of landslides caused by heavy rainfall, delineating landslide hazards under different rainfall conditions, and providing a basis for scientific responses, work arrangements, and disaster prevention and mitigation of landslides caused by heavy rainfall.

This paper proposes a new optimization algorithm for backpropagation (BP) neural networks by fusing integer-order differentiation and fractional-order differentiation, while fractional-order differentiation has significant advantages in describing complex phenomena with long-term memory effects and nonlocality, its application in neural networks is often limited by a lack of physical interpretability and inconsistencies with traditional models. To address these challenges, we propose a mixed integer-fractional (MIF) gradient descent algorithm for the training of neural networks. Furthermore, a detailed convergence analysis of the proposed algorithm is provided. Finally, numerical experiments illustrate that the new gradient descent algorithm not only speeds up the convergence of the BP neural networks but also increases their classification accuracy.

The piston ring pack is one of the most important components to affect the power, economy and emission of a diesel engine. Among them, lube oil consumption (LOC) and crankcase blow-by (CB) are the main indicators to evaluate the lubrication and sealing performance of the piston ring pack. In this study, the multi-factor analysis was implemented to predict the influencing factors on the LOC, CB and the sensitivity between them in the piston ring pack for an agricultural diesel engine. A YNF40 diesel engine was taken as the research object. Firstly, the test bench of LOC and CB was built for the diesel engine. The kinematics and dynamics models were established using hydrodynamic lubrication and gas flow theoretical of piston pack friction subsets, technical and structural parameters. A series of experimental tests were also carried out to verify the accuracy and reliability of the simulation. Secondly, the grey relational grade (GRG) of different influencing factors was obtained by grey relation analysis (GRA). The sensitivity analysis between the influencing factors and LOC-CB was then carried out using GRG calculation and ranking. Finally, the time-series prediction models were established for the transient variations of LOC and CB under different speed conditions using a back propagation (BP) neural network. The multi-factor GRG analysis indicated that the most sensitive influencing factor on the LOC and CB in the piston ring pack for a diesel engine was the chamfer of the bottom edge of the 1st ring groove of the piston, whereas, the most insensitive influencing factor was the back clearance of the 3rd ring groove of piston. The maximum GRG between LOC and CB and the chamfer of the bottom edge of the 1st ring groove of the piston was 0.892 79, whereas, the minimum GRG between LOC and CB and the back clearance of the 3rd ring groove of the piston was 0.583 61. The descending order of sensitivity was obtained between the target and influencing factors. The LOC and CB gradually increased in the piston ring pack for a diesel engine, as the chamfer of the bottom edge of the 1st ring groove of the piston increased. The back clearance of the 3rd ring groove of the piston shared no significant effect. The average standard deviation of the variation of LOC and CB with the chamfer of the bottom edge of the 1st ring groove of the piston were 2.81, and 3.90, respectively. By contrast, the average standard deviation of the variation of LOC and CB with the back clearance of the 3rd ring groove of the piston were 0.003 and 0.209, respectively. Therefore, the larger the GRG between LOC and CB, and each influencing factor were, the larger the mean standard deviation of LOC and CB with the influencing factors were, and the more sensitive the objectives were to the influencing factors. The time-series prediction showed that there was a better consistent trend of the predicted and actual values on the transient variations of LOC and CB. The prediction accuracy and reliability of the time series prediction model were higher than before, which were distributed within the 95% confidence band. The research findings can provide effective guidance to improve the thermal efficiency with the less carbon emissions of agricultural diesel engines. [ABSTRACT FROM AUTHOR]

Copyright of Hydrogeology & Engineering Geology / Shuiwendizhi Gongchengdizhi is the property of Hydrogeology & Engineering Geology Editorial Office 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.)

The study of unmanned ground vehicles (UGVs) operating under unstructured roads is of great significance to intelligent transportation, agricultural development and military technology. In order to ensure reliable and stable operation of UGVs on unstructured terrain, it is necessary to identify the current road terrain and perform vehicle stability adjustment. Road terrain identification is a prerequisite for stability control. Most of the existing road terrain identification methods use a single vehicle sensor, which has the problem that complex algorithms need to be applied for data processing, which reduces the real-time performance. Moreover, the single sensor is weak in anti-interference and limited in recognizing the road. To address these problems, a method is proposed to collect vehicle motion data using on-board gyroscope sensors and velocity sensors. Back propagation (BP) neural network is used to identify the category of the road. For the problem that the conventional proportional-integral differential (PID) algorithm cannot be adapted to different road stability control, a multi-loop adaptive proportional-integral differential (PID) control system with the velocity loop as the outer loop and the torque (current) loop as the inner loop is proposed. In order to verify the feasibility and effectiveness of the method, experiments are conducted on a UGV using robot operating system (ROS), and the results verify the feasibility and superiority of the road identification and stability control method proposed in this paper. It provides a good theoretical basis and valuable technical guidance for the UGV operation and control on unstructured roads.

The intelligent and automatic evaluation for teaching quality has been a more and more general demand in the digital society. The most intuitive solution is to make an assessment based on examination results, which cannot comprehensively reflect the course situation. To deal with such a problem, this paper designs a smart knowledge discovery system for teaching quality evaluation using a genetic algorithm-based BP neural network. Three aspects of factors are selected as the features: teaching conditions, teaching process, and teaching effect. The BP neural network is formulated to learn a nonlinear mapping from initial features to evaluation results. The learned parameters are then re-optimized by introducing the genetic algorithm. The proposed evaluation framework is also assessed concerning running performance on a real-world course-teaching dataset. The obtained results reflect that the proposal can realize the intelligent evaluation of the teaching effect and the evaluation effect is close to artificial experience-based evaluation results.

The autonomous driving simulation field lacks evaluation and forecasting systems for simulation results. The data obtained from the simulation of target algorithms and vehicle models cannot be reasonably estimated. This problem affects subsequent vehicle improvement and parameter calibration. The authors relied on the simulation results of the AEB algorithm. We selected the BP Neural Network as the basis and improved it with a genetic algorithm optimized via a roulette algorithm. The regression evaluation indicators of the prediction results show that the GA-BP neural network has better prediction accuracy and generalization ability than the original BP neural network and other optimized BP neural networks. This GA-BP neural network also fills the Gap in Evaluation and Prediction Systems.

Aerobic compost has been commonly used to efficiently dispose of resources recycling and environmental protection in modern agriculture. Among them, aeration can be one of the most important environmental factors to affect composting fermentation. It is necessary for a feasible network model to accurately control the oxygen supply of aeration. This study aims to improve the aeration efficiency and prediction accuracy of aerobic composting aeration. In-depth learning was selected to train a network model, in order to predict the oxygen supply of aeration during aerobic composting fermentation in this experiment. Raw materials were taken as cow dung, cow dung biogas residue, chicken manure, and corn straw in the Haihua Biogas Plant in Miyun District, Beijing, China. The corn straw was crushed by 1-2 cm in grain size. The cow dung, cow dung biogas residue, and chicken manure were uniformly mixed with the crushed corn straw for composting and fermentation. The sensor was used in the composting fermentation tank to collect the parameter data during aerobic fermentation. 268 groups of data were selected as the sample data, 218 groups of data were randomly selected as the input data, and 50 groups of data were selected as the test data. Clonal genetic algorithm (CGA) was used to predict the standard back propagation (BP) neural network model for the aeration oxygen supply, whereas, the 6-14-1 three-layer network structure was used as the basic structure of the prediction model. The input parameters were the temperature, humidity, oxygen concentration, room temperature, pH value, and electrical conductivity (EC). The mean square error (MSE) of the number of hidden layer nodes was determined to be 14 after training and calculation. The output data was aeration. This article establishes BP neural network model for predicting aeration oxygen supply. Then the genetic algorithm (GA) and clonal selection algorithm were used to improve the prediction accuracy of the model. The experiment shows that the CGA-BP neural network model has the best prediction effect on aeration oxygen supply. 1) The CGA-BP neural network model accelerated the obtaining of the optimal solution, with an efficiency improvement of 75.36% and 51.30% compared to the BP model and GA-BP model, respectively. 2) In the prediction model of aeration oxygen supply, the CGA-BP model had a more accurate prediction effect, with a prediction accuracy of 99.65%. The prediction accuracy of aeration oxygen supply was 96.99% and the prediction accuracy of the GA-BP neural network model reached 99.26%. A comparison was made to evaluate the errors of BP, GA-BP and CGA-BP neural models. The model evaluation showed that the best performance was found in the CGA-BP neural network model with the smallest error, as shown by the mean absolute error (MAE), mean absolute percentage error (MAPE) and mean square error (MSE). 3) The improved CGA-BP neural network model can be predicted the aeration oxygen supply of aerobic composting, increasing the aeration control efficiency by 3.22%. The improved model can be expected to accurately predict the aeration oxygen supply of aerobic compost. The finding can provide a strong reference for accurate data for the next aeration. [ABSTRACT FROM AUTHOR]

The equipotential switching algorithm of the traditional mechanical static compensator (MSC) device had many limitations in the operation of the single machine, such as the long operation time of the microcontroller control chip, the poor convergence of the calculation results had been affected by the hardware, and so on. In recent years, the research on devices that can communicate with the back end through the message queuing telemetry transport, MQTT protocol through the internet of things(IoT)platform has becoming more and more mature, and the development of IoT technology has also made it possible to apply machine learning algorithms such as neural networks to stand-alone electrical equipment. In the experiment, through a large number of data sets training, the switching time in different electrical environments could be predicted to achieve the adaptive equipotential switching effect, the adaptive switching without spark, no inrush, no overvoltage etc, was achieved in the developed device. The research and development focus includes the equipotential switching principle and simulation of the device, the IoT communication method between the device and the back-end software, the implementation process and training results of the BP neural network algorithm, and the experimental results and experimental analysis of the switching experiment. [ABSTRACT FROM AUTHOR]

Weiwei Wang, Ting Wei, Suihuai Yu, Jian Chen, Xiaoyan Yang College of Art and Design, Shaanxi University of Science and Technology, Xi’an City, People’s Republic of ChinaCorrespondence: Ting Wei, College of Art and Design, Shaanxi University of Science and Technology, Xi’an City, People’s Republic of China, Email wt@joya.cnIntroduction: The telecommuting experience and job performance have been significantly impacted by the COVID-19 pandemic, and job performance stability of telecommuting employees has become a critical concern.Objective: A decision model for telecommuting experience service design was constructed based on a backpropagation (BP) neural network to provide a theoretical basis for enterprises to evaluate telework performance and the psychological health of employees.Methods: The analytic hierarchy process (AHP) was used to determine the core stakeholders. The grey relational analysis (GRA) method and the NASA Task Load Index (NASA-TLX) scale were used to measure the factors affecting employees’ telecommuting experience and job performance. A BP neural network relationship model of employees’ telecommuting experience was established to predict its impact on employees’ job performance.Results: Based on the model prediction results, a service system map was created, and the potential to enhance the telework performance of employees was evaluated.Discussion: It was concluded that the factors affecting the telecommuting experience were diverse, but emotions had the dominant influence. Significant positive correlations were found between emotional impact and temporal perception, execution difficulty, and communication barriers.Conclusion: The proposed decision model for telecommuting experience service design accurately predicted the impact of telecommuting efficiency, providing an effective approach for innovative remote management.Keywords: design decision, job performance, telecommuting experience, BP neural networks, NASA-TLX scale

Multi-physics modelling of the Solid Oxide Fuel Cell (SOFC) stack requires significant computational resources. Design optimization of large-scale stacks and stack towers has always been a challenge in recent years. This study establishes a three-dimensional multi-physics model based on a two-step coupling using the BP neural network. The comparison between the novel model and the traditional fully coupled model in both accuracy and computing resource requirements are explored. The novel method has high effectiveness for modelling the large-scale stacks. Based on this, planar SOFC 50-cell stacks and 150-cell stack towers are simulated. The results show that, the flow uniformity of fuel distribution of the stack towers can decrease more than 30% comparing with the 50-cell stack, which leads to significant deterioration of the voltage and temperature distribution. The parameters of manifold and buffer area and channel height of the stack tower is optimized to achieve better uniformity of flow and voltage distribution and lower temperature gradient simultaneously. • Alternative mapping model is compared to fully coupled model in accuracy and computing resources. • Planar SOFC 50-cell stacks and 150-cell stack towers are structurally optimized. • Flow uniformity of stack towers can decrease more than 30% comparing to a single stack. • The co-flow and counter-flow stacks and stack towers are compared. [ABSTRACT FROM AUTHOR]

Tidal phenomenon is a significant dynamical phenomenon in the ocean, and the accurate prediction of tide is an important task for various maritime activities. This paper proposes analysis method considering tidal periodicity and apply it to the actual tide prediction. The results prove that this method can solve the delay problem in tide prediction, improve the accuracy of prediction. Compared with the tidal harmonic analysis method, the prediction result of this method is more accurate and requires less data for short-term tidal forecast. Although this study can only provide an accurate forecast for 3 days, it is enough to deal with risks. How to improve the accuracy of long-term prediction is one of the future research directions. [ABSTRACT FROM AUTHOR]

Emergency logistics is not only a part of emergency management system, but also an important link of disaster relief and disaster reduction. The performance evaluation of emergency logistics capability is the foundation of improving emergency logistics capability. This paper took emergency logistics capability based on COVID-19 region as the research object. Firstly, we analyse the characteristics and influencing factors of public health emergency logistics. Secondly, we construct the evaluation system of public health emergency logistics capability. Thirdly, we establish the evaluation model of emergency logistics capability based on BP neural network. Finally, the evaluation model was applied to COVID-19 events, and the scientific nature and feasibility of the evaluation model were verified. [ABSTRACT FROM AUTHOR]

In this paper, a traveling wave model is proposed to explore its influence on the aerodynamic drag of a Ahmed model, the experimental and numerical results of aerodynamic drag coefficient CD for the Ahmed model are in good agreement. Then by defining the aerodynamic benefit coefficient ΔCD as the evaluation index for the orthogonal experiment, range analysis is conducted to determine the influences of the amplitude A, wavelength λ and frequency ω of the wave and the vehicle speed u on ΔCD. After the analysis it can been found that λ has the least importance among these parameters, hence A, ω and u are used to construct the 105 samples for training the BP neural network to predict ΔCD, results show that ΔCD obtained from the neural network is significantly affected by the parameters of traveling wave. The prediction accuracy of the network is furtherly verified by another 15 samples which are also built on A, ω and u, and the corresponding data overlap rate of ΔCD is 96 %, so it can be concluded that the BP neural network constructed in this paper is accurate enough to predict ΔCD. [ABSTRACT FROM AUTHOR]

The nonlinear representation of active devices plays an important role in microwave circuit design. Whereas, it takes a long time to extract a large amount of large signal data, and the problem of memory resource and CPU occupancy becomes significant. In order to address the problems in traditional large-signal modeling methods, in this paper an X-parameter modeling method for microwave power devices based on extreme learning machine (ELM) is proposed. To demonstrate the effectiveness of this method, a double layer back propagation (BP) neural network model is established. Then, harmonic balance simulations are used to verify the accuracy of these two models. After comparisons, it is proved that the three harmonic errors of double layer BP neural network model are 9.525dBm, 1.309dBm and 14.593dBm, respectively, and the three harmonic errors of ELM model are 0.673 dBm, 0.314 dBm, 3.09 dBm, respectively. Furthermore, the three harmonic modulus errors of double layer BP neural network model are 0.031, 0.002, 7.665e-4, respectively, and the errors of ELM model are 0.005, 0.001, 8.38e-5, respectively. Finally, in order to verify the accuracy of the predicted model in circuit design, the predicted X-parameter is used in the design of power amplifier. Moreover, the errors of the double layer BP neural network prediction model at 2.5 GHz, 5 GHz and 7.5 GHz are 1.142 dBm, 1.436 dBm and 2.294 dBm, respectively. The output power error of the ELM model at 2.5 GHz, 5 GHz and 7.5 GHz are 0.089 dBm, 0.311 dBm and 0.309 dBm, respectively. These experimental results demonstrate that the established ELM model is an efficient and valid approach for modeling GaN high electron mobility transistor types of nonlinear microwave devices.

Due to fuel price fluctuations and greenhouse gas emissions caused by international shipping, the reduction of ship fuel consumption is important. In this paper, a ship energy consumption prediction model is established based on the BP neural network optimized by the Levenberg-Marquardt (LM) algorithm to predict ship energy consumption. Firstly, the ship navigation data are analyzed. Ship speed, draught and current speed are selected as the main factors affecting ship energy consumption and their weights are determined by the spearman and regression analysis. Then, the ship energy consumption model is established based on the LM-BP algorithm. Finally, ship speed, draught and current velocity are used as the input and ship energy consumption is considered as output for the model to validate the model. The predicted results is compared with the real energy comsumption and the final RMSE is approximately 259.74 kW. For ships sailing with power ranging from 6000 kW to 8500 kW, the model prediction error is 3.06 %. The results of this study could be used to optimize ship operational plans to improve the economics of waterway transport. • The effect of factors are quantified on ship energy consumption through Spearman analysis and regression analysis. • A prediction model based on LM-BP algorithm is established to predict ship energy consumption. • The model is trained and verified using the real data from 40 voyages of the ship. • The strength of the model is shown by comparing the results with the BP and LSTM models. [ABSTRACT FROM AUTHOR]