Search

This article presents an approach for predicting Lockout/Tagout (LOTO) procedure sheets, which are commonly used in the manufacturing industry to prevent premature equipment restart during maintenance. The prediction problem of energetic devices to lock from machine names is regarded as a multi-task classification problem. The dataset was obtained by processing LOTO sheets in Portable Document Format (PDF). The K-Nearest Neighbours (KNN), Random Forest (RF), and Deep Neural Network (DNN) algorithms were compared for this problem. The best prediction performance was achieved with the DNN method, with top-1 accuracies exceeding 63% and top-2 accuracies exceeding 90% for all devices. The sensitivity analysis conducted on the results indicates that the approach is robust and reliable, regardless of the industrial sector considered. In other words, the approach is not significantly affected by variations in the industry or its specific characteristics. These results suggest that the proposed approach can be used to assist workers in drafting LOTO sheets, and offers strong potential for concrete applications in safety management in the era of smart manufacturing. [ABSTRACT FROM AUTHOR]

This project aims to mitigate the critical decline in bee populations, essential for crop pollination and food security. With a shortage of taxonomic specialists to identify the vast array of bee species, the project's goal is to enhance the monitoring of population changes through an automated classification system. Utilizing a dataset of bee wing images, the project aims to develop a computational pipeline to identify species based on their unique wing vein patterns. This approach not only supports bee conservation efforts but also expands our understanding of complex geometric variations in nature, offering wider applications in biological research. This poster was presented at the UCSB Data Science Capstone showcase in 2024.

Previously, we introduced photomagnetic imaging (PMI) that synergistically utilizes laser light to slightly elevate the tissue temperature and magnetic resonance thermometry (MRT) to measure the induced temperature. The MRT temperature maps are then converted into absorption maps using a dedicated PMI image reconstruction algorithm. In the MRT maps, the presence of abnormalities such as tumors would create a notable high contrast due to their higher hemoglobin levels. In this study, we present a new artificial intelligence-based image reconstruction algorithm that improves the accuracy and spatial resolution of the recovered absorption maps while reducing the recovery time. Technically, a supervised machine learning approach was used to detect and delineate the boundary of tumors directly from the MRT maps based on their temperature contrast to the background. This information was further utilized as a soft functional a priori in the standard PMI algorithm to enhance the absorption recovery. Our new method was evaluated on a tissue-like phantom with two inclusions representing tumors. The reconstructed absorption map showed that the well-trained neural network not only increased the PMI spatial resolution but also improved the accuracy of the recovered absorption to as low as a 2% percentage error, reduced the artifacts by 15%, and accelerated the image reconstruction process approximately 9-fold.

Summary: This paper addresses the adaptive saturation prescribed performance control problem for air‐breathing hypersonic vehicles with parameter uncertainties and unknown external disturbances. First of all, different from the traditional performance function, a novel class of performance functions is presented without the initial state information, which does not require to reset parameters even if the initial velocity and altitude change. To ensure the successful design of the velocity controller and altitude controller, the constrained errors are transformed into the unconstrained errors by the projection technique. Secondly, the adaptive neural network and the sliding mode control techniques are combined to design the adaptive neural network sliding mode controllers, which guarantee that the velocity and altitude tracking errors can respectively approach the predetermined regions within the identical preset finite time. Finally, the effectiveness of the designed controllers is verified by an example with comparisons. [ABSTRACT FROM AUTHOR]

This article introduces the problem of predefined‐time attitude takeover control for spacecraft. A novel radial basis function neural network predefined‐time extended state observer is presented, which facilitates estimation of external disturbance, unmeasurable angular velocity, and actuator installation deviation within a predefined‐time. A quantizer is then employed to quantize control input signal in controller‐to‐actuator side to mitigate communication pressure. Thereafter, a novel predefined‐time attitude controller is proposed to ensure system states converge within a predefined‐time. Finally, the effectiveness of the proposed control scheme is substantiated via numerical simulation. [ABSTRACT FROM AUTHOR]

In the context of India's evolving economy, where agriculture remains a vital yet limited sector, the challenge is to enhance productivity on finite cultivable land. This research addresses this imperative by introducing the Crop Yield Prediction Using Deep Learning (CYPBL) model, leveraging the Bi-Directional Long Short-Term Memory (Bi-LSTM) algorithm. Employing soil health and crop yield data from the Government of India, the CYPBL model is implemented through PySpark for scalability. Featuring 20 LSTM layers with a 12 × 1 input shape, including a bidirectional LSTM layer, the model achieves exceptional accuracy at 99.5 percent on test data. With a focus on real-time data, a batch size of 1 ensures optimal responsiveness. Beyond technological advancements, CYPBL emerges as a groundbreaking soil health monitoring system, bridging the gap between experts and farmers. By empowering farmers with insights into soil conditions, crop suitability, and improvement strategies, this research paves the way for data-driven, responsive agriculture in India and globally, contributing to the pressing issue of global food security. [ABSTRACT FROM AUTHOR]

This paper presents Fix-YOLOX (Fixmatch-You Only Look Once X), a semisupervised target detection model that uses a small amount of annotated data for fully supervised training, and adds a semisupervised training module using both pseudolabelling and consistent regularization to prevent overfitting in fully supervised training by using unlabelled data. Additionally, the generalization of the model and its fault tolerance to labelled data are improved. The experimental results show that the proposed semisupervised visual detection algorithm, Fix-YOLOX, can substantially reduce the amount of data annotation required for the target detection task while effectively overcoming the problem caused by annotated data with uneven quality. The YOLOX model achieves 91.95% accuracy with 50% annotated data and an average detection time of 10.4 ms per image/frame, which is consistent with the detection time of original YOLOX. Therefore, the model has good real-time performance and generalizability. [ABSTRACT FROM AUTHOR]

This paper was to develop a prediction framework for obtaining the rheological properties of extracted and recovered asphalt binders utilizing mixture performance and other factors such as in-place air voids, pavement structure, traffic level, and aging duration. A total of 21 field projects consisting of 66 pavement sections were included in the analysis, which were located in different climatic zones with various RAP contents, traffic levels, pavement structures, pavement age, and material properties. Results indicate that the neural network can be successfully adopted to predict cracking-related binder properties consisting of effective asphalt binder, G*sin(δ) and binder fracture energy, and rutting-related binder properties including high temperature performance grade (PG), MSCR Jnr3.2, and R3.2. Both prediction and validation models worked well for pavement sections with varied contents of RAP when new data was introduced. [ABSTRACT FROM AUTHOR]

In this study, the effects of suction and buoyancy are used to analyze the Ternary hybrid nanofluid flow on a stretching sheet through a porous media. Ternary hybrid nanofluid is (Carbon nanotubes) CNT + Graphene + Al 2 O 3 with base fluid as Water. Case-1 Buoyancy Assisting flow and Case-2 Buoyancy Opposing flow. Hybrid nanofluids have been used to speed up the heat transfer process. Nonlinear partial differential equations (PDEs) have been converted to ordinary differential equations (ODEs) using Lie group transformations. The ODE45, an algorithmic approach, has been using the aid of this built-in solver, and the resulting Ordinary differential equations were resolved. The general relationship between temperature, velocity, heat transfer rate, and shear stress on a stretchy surface is shown for a range of values of the significant factors. The temperature profiles have been rising with the impact of Da , f w . Using streamlines to examine the flow pattern of a fluid and a method of machine learning, in terms of modern language, an artificial neural network (ANN) made up of artificial neurons or nodes is known as a neural network. A neural network is a network or circuit of genetic neurons. [ABSTRACT FROM AUTHOR]

This paper proposes a microstructure reconstruction framework with denoising diffusion models for the first time. The novelty and strength of the proposed model lie in its universality and generality for the microstructure characterization and reconstruction (MCR) that can be applied to various types of composite materials. The applicability of the diffusion-based models is validated with several types of microstructures (e.g., polycrystalline alloy, carbonate, ceramics, copolymer, fiber composite, etc.) that have different morphological characteristics. Moreover, an implicit probabilistic model (which yields non-Markovian diffusion processes) is formulated to accelerate the sampling process, thereby controlling the computational cost considering the practicability and reliability. [ABSTRACT FROM AUTHOR]

The fast and nondestructive identification of mobile phone cases is a crucial task for law enforcement personnel in the field of forensic science. Attenuated total reflection-Fourier transform infrared spectroscopy (ATR-FTIR) has been employed in conjunction with feature extraction and deep learning algorithms to develop a method for distinguishing mobile phone cases. As preprocessing steps, multivariate scatter correction and standard normal variate were performed. Feature variables were extracted using the competitive adaptive reweighted sampling and shuffled frog leaping algorithm. Several supervised pattern recognition methods, namely ResNet50, VGG16, and multilayer perceptron (MLP), were utilized for constructing classifiers. The results indicated that the model's performance based on multivariate scattering correction (MSC) with competitive adaptive re-weighted sampling (CARS) surpassed that of other approaches. Notably, the ResNet50 model exhibited superior discriminative ability compared to the VGG16 and MLP models, achieving 100% accuracy in the differentiation of all samples. This designed method represents a potentially rapid and nondestructive approach for identifying mobile phone cases in forensic science. [ABSTRACT FROM AUTHOR]

In traditional machine tool thermal error detection, eddy current or capacitive probes are mainly used. We propose a new data sensing architecture consisting of two main components: a thermal error sensing model and a temperature sensing module. The thermal error sensing model is composed of two quadrant detectors forming a 3D displacement error sensing module. The temperature sensing module consists mainly of multiple PT100 sensors. In the thermal rise experiment, spindle XYZ directional thermal errors are detected by the displacement error sensing module, while temperature changes at various locations are detected by the PT100 sensors. The experimental results show that the main thermal errors of the spindle are in the YZ direction. Therefore, we introduce four neural network algorithm methods [Temporal Convolutional Network (TCN), Generative Adversarial Network (GAN), Long Short-Term Memory (LSTM), and Bi-directional LSTM (BiLSTM)] to establish various models for predicting the spindle's thermal errors in the YZ direction. The predictive results indicate that Z-direction predictions are more accurate, with model accuracy maintained up to 70% after six months. In the Y-direction thermal error model, significant improvements in prediction results were observed after the RPM parameter was incorporated into the model. Among the various models compared, TCN and BiLSTM show the best performance in terms of accuracy over extended periods and across different thermal error directions. [ABSTRACT FROM AUTHOR]

In this paper, a deep learning based time-domain inversion method is proposed to reconstruct high-contrast scatterers from the measured electromagnetic fields. The scatterers investigated in this study include four kinds of geometry shapes, which cover the arbitrary geometrical shapes, handwritings and lossy medium. After being well trained, the performance of the proposed method is evaluated from the perspective of accuracy, noise interference, and computational acceleration. It can be proven that the proposed framework can realize high-precision inversion in several milliseconds. Compared with typical reconstruction methods, it avoids the iterative calculation by utilizing the parallel computing ability of GPU and thus significantly reduce the computing time. Besides, the proposed method has shown the potential to be applied in practical scenarios with experimental results. Herein, it is confident that the proposed method has the potential to serve as a new path for real-time quantitative microwave imaging for various practical scenarios. In the end, the limitation of the method is also discussed. [ABSTRACT FROM AUTHOR]

Continuously reinforced concrete pavement (CRCP), crucial for the resilience of transportation infrastructure owing to its continuous steel reinforcement, confronts a critical challenge in the form of spalling—a distress phenomenon posing a threat to pavement durability and overall structural integrity. The detachment or breakage of concrete from the surface compromises CRCP's functionality and raises safety concerns and escalating maintenance costs. To address this pressing issue, our study investigates the multifaceted factors influencing spalling, employing a comprehensive approach that integrates statistical and machine learning techniques for predictive modeling. Descriptive statistics meticulously profile the dataset, emphasizing age, thickness, precipitation, temperature, and traffic parameters. Regression analysis unveils key relationships, emphasizing the significance of age, annual temperature, annual precipitation, maximum humidity, and the initial International Roughness Index (IRI) as influential factors. The correlation matrix heatmap guides feature selection, elucidating intricate interdependencies. Simultaneously, feature importance analysis identifies age, Average Annual Daily Traffic (AADT), and total pavement thickness as crucial contributors to spalling. In machine learning, adopting models, including Gaussian Process Regression and ensemble tree models, is grounded in their diverse capabilities and suitability for the complex task at hand. Their varying predictive accuracies underscore the importance of judicious model selection. This research advances pavement engineering practices by offering nuanced insights into factors influencing spalling in CRCP, refining our understanding of spalling influences. Consequently, the study not only opens avenues for developing improved predictive methodologies but also enhances the durability of CRCP infrastructure, addressing broader implications for informed decision-making in transportation infrastructure management. The selection of Gaussian Process Regression and ensemble tree models stems from their adaptability to capture intricate relationships within the dataset, and their comparative performance provides valuable insights into the diverse predictive capabilities of these models in the context of CRCP spalling. [ABSTRACT FROM AUTHOR]

In this paper, the problem of attitude tracking control for a class of vertical take-off landing (VTOL) aircraft in the presence of uncertain disturbances is addressed. The active disturbance rejection control (ADRC) method is utilized to address uncertain disturbances, while the radial basis function (RBF) neural network is considered for handling unknown nonlinear dynamics. By incorporating a modified tracking differentiator, a nonlinear state error feedback controller, and an extended state observer, the disturbance observation problem in the aircraft system is solved. These disturbances, seen as a combined disturbance in the aircraft system, are counteracted through the extended state observer. Furthermore, the unknown nonlinear dynamics within the aircraft system are approximated using the RBF neural network. Subsequently, the paper suggests adaptive ADRC strategies based on neural network and formulates adaptive control laws to estimate unknown parameters. The Lyapunov stability theory proves the effectiveness of the proposed control strategies. The simulation results show that the attitude tracking control problem of VTOL aircraft can be achieved under the proposed control strategies and adaptive control laws. [ABSTRACT FROM AUTHOR]

To improve the motivation and enthusiasm of subjects during active rehabilitation training, this paper proposes a novel training task planning-based adaptive assist-as-needed (TTP-AAAN) control algorithm for an upper limb exoskeleton. The overall controller contains an outer control loop to determine the required assistive force, and an inner control loop to drive the exoskeleton to track subject motion and to provide desired assistive force obtained from the outer control loop. In the outer control loop, a motion intention and task performance evaluation (MITPE) strategy is established to learn the motor capability of the subject. Based on the obtained evaluation result, the radius and frequency of multi-periodic trajectory tracking task, and the gain of the assistive force are adaptively adjusted by using the adaptive central pattern generator (ACPG) algorithm. Then, in the inner control loop, an asymmetric barrier Lyapunov function-based adaptive output feedback (ABLF-AOF) controller, in combination with a neural network (NN) state observer, is developed. The exoskeleton tracking errors are constrained by the asymmetric barrier Lyapunov function, and the state variables and uncertainty terms of the exoskeleton are simultaneously estimated by the NN state observer. Experiments are carried out with an upper limb exoskeleton to demonstrate the effectiveness of the proposed control strategy. The experimental results show that the developed control scheme can provide assistance and achieve task parameter adaption for the subjects with different motion patterns. In addition, the proposed controller has better training performance than task performance-based adaptive velocity assist-as-needed (AAN) controller and minimal AAN controller. [ABSTRACT FROM AUTHOR]

In this paper, a disturbance observer‐based adaptive neural backstepping integral sliding mode control (BISMC) is developed for a flexible joint robot (FJR) with the integration of an adjustable stiffness rotary actuator (ASRA). This system suffers from unknown system dynamics, external disturbance, and the influence of variable stiffness, which is a challenge for achieving precision tracking performance. Considering the lumped disturbances in FJR generated by the hydraulic system and the stiffness modulation of the ASRA, we investigate the structural dynamics nonlinear model of the FJR system, including hydraulic actuator dynamics. While other linear control strategies are applied for the FJR, the proposed controller uses BISMC, neural networks (NN), and nonlinear disturbance observers to deal with the disadvantages mentioned above. Radial basis function neural networks (RBFNN) are designed to tackle unknown nonlinear functions, and the disturbance observers are introduced to compensate for the influence of the variable stiffness, disturbance, and the approximation error caused by NN. Simulations and experiments are independently implemented to demonstrate the effectiveness and feasibility of the proposed controller. Results exhibit that the integral absolute error‐index is reduced by 20.4% when the proposed method is deployed for the experiment with a multistep trajectory. [ABSTRACT FROM AUTHOR]

Objective: To develop and validate a method for detecting ureteral stent encrustations in medical CT images based on Mask-RCNN and 3D morphological analysis. Method: All 222 cases of ureteral stent data were obtained from the Fifth Affiliated Hospital of Sun Yat-sen University. Firstly, a neural network was used to detect the region of the ureteral stent, and the results of the coarse detection were completed and connected domain filtered based on the continuity of the ureteral stent in 3D space to obtain a 3D segmentation result. Secondly, the segmentation results were analyzed and detected based on the 3D morphology, and the centerline was obtained through thinning the 3D image, fitting and deriving the ureteral stent, and obtaining radial sections. Finally, the abnormal areas of the radial section were detected through polar coordinate transformation to detect the encrustation area of the ureteral stent. Results: For the detection of ureteral stent encrustations in the ureter, the algorithm's confusion matrix achieved an accuracy of 79.6% in the validation of residual stones/ureteral stent encrustations at 186 locations. Ultimately, the algorithm was validated in 222 cases, achieving a ureteral stent segmentation accuracy of 94.4% and a positive and negative judgment accuracy of 87.3%. The average detection time per case was 12 s. Conclusion: The proposed medical CT image ureteral stent wall stone detection method based on Mask-RCNN and 3D morphological analysis can effectively assist clinical doctors in diagnosing ureteral stent encrustations. [ABSTRACT FROM AUTHOR]

Image compression is a widely used technique to reduce the spatial redundancy in images. Recently, learning based image compression has achieved significant progress by using the powerful representation ability from neural networks. However, the current learning based image compression methods suffer from the huge computational cost, which limits their capacity for practical applications. In this paper, we propose a unified framework called Efficient Deep Image Compression (EDIC) based on three new technologies, including a channel attention module, a Gaussian mixture model and a decoder-side enhancement module. Specifically, we design an auto-encoder style network for learning based image compression. To improve the coding efficiency, we exploit the channel relationship between latent representations by using the channel attention module. Besides, the Gaussian mixture model is introduced for the entropy model and improves the accuracy for bitrate estimation. Furthermore, we introduce the decoder-side enhancement module to further improve image compression performance. Our EDIC method can also be readily incorporated with the Deep Video Compression (DVC) framework (Lu et al. 2019) to further improve the video compression performance. Simultaneously, our EDIC method boosts the coding performance significantly while bringing slightly increased computational cost. More importantly, experimental results demonstrate that the proposed approach outperforms the current image compression methods and is up to more than 150 times faster in terms of decoding speed when compared with Minnen's method (Minnen et al. 2018). Moreover, we also evaluate the performance of the human-centric task (i.e., face recognition) by using different coding strategies. [ABSTRACT FROM AUTHOR]

Highlights It is more and more difficult to identify defects in carbon fiber composite materials due to the difficulty in making defect samples and the single signal analysis method. In order to better solve the problem of defect identification in carbon fiber composite materials, this study uses ultrasonic phased array equipment to quantitatively locate and detect carbon fiber composite laminates with embedded delamination defects, so as to more intuitively and effectively display the appearance of different delamination defects. The time domain analysis of the collected ultrasonic original signal and the time‐frequency domain analysis using wavelet packet are carried out. A total of 6 eigenvalues were extracted to reflect the ultrasonic signals of different delamination defects. By using genetic algorithm to optimize BP neural network, the recognition accuracy of delamination defects of different sizes is more than 95%, and the recognition accuracy of delamination defects of different depths is 100%, so as to realize the effective intelligent recognition of delamination defects of different sizes and depths of carbon fiber composites. This study is of great significance to improve the accuracy and reliability of defect identification of carbon fiber composite materials. The ultrasonic phased array equipment is used to quantitatively locate the carbon fiber composite laminates with embedded delamination defects, so that the appearance of different defects can be displayed more intuitively and effectively. Using time domain analysis and time‐frequency domain analysis based on wavelet packet, the combination of the two can more comprehensively extract the effective features of the defect signal. The BP neural network is optimized by genetic algorithm, and the results can effectively and automatically identify different layered defects, which lays a good foundation for the rapid and accurate identification of more defects in the future. [ABSTRACT FROM AUTHOR]

AbstractThe laminated thermoelectric cylindrical shell is favorable for solar thermal energy harvesting, but the thermo-electric-mechanical coupling field is relatively complex. An optimization design model of thermoelectric structure is required to promote its practical application. In this paper, based on variable separation method, thermo-electric-mechanical coupled model of laminated thermoelectric cylindrical device under thermal shock is constructed. Transient temperature field, thermal stress and power generation efficiency are obtained. Numerical results show that both power generation efficiency and thermal stress are affected by material parameters simultaneously. In order to analyze efficiency and structural reliability comprehensively, a fitness function is introduced in this paper. Based on the data which are collected from thermoelectric coupled model, a neural network is established and trained, which can predict and evaluate the performance of thermoelectric cylindrical shell based on the fitness function. The optimal material parameters for thermoelectric shells with high efficiency and low thermal stress are obtained. Combining neural network technique and the theoretical model developed in this paper, the computation time of numerical results can be reduced from 50 to 3 min, and this neural network optimization method has higher computational efficiency. These research results will provide guidance for the optimization design of cylindrical thermoelectric device. [ABSTRACT FROM AUTHOR]

A neural network adaptive integral terminal sliding mode control method with input saturation is proposed for the horizontal vibration problem of high‐speed elevator car systems caused by uncertainties such as guideway excitation and shaft piston wind change. First, considering the input saturation problem existing in the elevator control actuator, a class of smooth functions is introduced to approximate the nonlinearity of switching saturation, and an eight‐degree‐of‐freedom asymmetric anti‐saturation nonlinear system model of the high‐speed elevator car is established; second, in order to solve the singularity problem existing in the terminal sliding‐mode control, a nonlinear term is introduced into the sliding‐mode design, and a neural network is utilized for the fitting of the complex unknown function, and the design of the an adaptive integral terminal sliding mode controller (AITSMC), which enables the state variables of the system to achieve finite time convergence and proves the stability of the system by using Lyapunov theory; finally, under the action of two typical guide excitations, the proposed controller is compared with the passive control and adaptive control (AC), and the results show that, after adopting the proposed control method, the vibration acceleration eigenvalue is reduced by more than 60%, which effectively suppresses the horizontal vibration of the car system and verifies the effectiveness of the proposed controller. [ABSTRACT FROM AUTHOR]

In this paper, a neuro-adaptive PI control strategy for a water-cooled centrifugal chiller system is developed, and its control performance is examined. The system model consists of a flooded evaporator, a flooded condenser, a centrifugal compressor, and an electronic expansion valve. The overall system consists of three control loops: a compressor speed control loop, an inlet guide vane (IGV) control loop, and a condenser liquid level control loop. A neuro-adaptive control strategy for compressor speed control was designed. The control performance of the chiller was tested by carrying out simulation runs using an integrated building and HVAC (IB-HVAC) system model. The major details of the IB-HVAC model are described in this paper. Results show that the neuro-adaptive controller can adapt to new system dynamics of the IB-HVAC system and give good setpoint tracking responses under a wide range of operating conditions. The results show that the neuro-adaptive controller performs better than the constant gain PI controller in terms of speed of response and setpoint tracking properties. [ABSTRACT FROM AUTHOR]

Dynamic random access memory (DRAM) serves as a critical component in medical equipment. Given the exacting standards demanded by medical equipment products, manufacturers face pressure to improve their product quality. The electrical characteristics of these products are based on the resistance value of the DRAM components. Hence, the purpose of this study is to optimize the resistance value of DRAM components in medical equipment. We proposed a novel FMEA-TSTM-NNGA framework that integrates failure mode and effect analysis (FMEA), the two-stage Taguchi method (TSTM), neural networks (NN), and genetic algorithms (GA) to optimize the manufacturing process. Moreover, the proposed FMEA-TSTM-NNGA framework achieved a substantial reduction in experimental trials, cutting the required number by a factor of 85.3 when compared to the grid search method. Our framework successfully identified optimal manufacturing condition settings for the resistance values of DRAM components: Depo time = 27 s, Depo O2 flow = 151 sccm, ARC-LTO etch time = 43 s, ARC-LTO etch pressure = 97 mTorr, Ox-SiCO etch time = 91 s, Ox-SiCO gas ratio = 22%, and Polish time = 84 s. The results helped the case company improve the resistance value of DRAM components from 191.1 × 10−3 Ohm to 176.84 × 10−3 Ohm, which is closer to the target value of 176.5 × 10−3 Ohm. The proposed FMEA-TSTM-NNGA framework is designed to operate efficiently on resource-constrained, facilitating real-time adjustments to production attributes. This capability enables DRAM manufacturers to swiftly optimize product quality. [ABSTRACT FROM AUTHOR]

To enhance the detection of pavement-sealed cracks and ensure the long-term stability of pavement performance, a novel approach called the shuffle attention-based pavement-sealed crack detection is proposed. This method consists of three essential components: the feature extraction network, the detection head, and the Wise Intersection over Union loss function. Within both the feature extraction network and the detection head, the shuffle attention module is integrated to capture the high-dimensional semantic information of pavement-sealed cracks by combining spatial and channel attention in parallel. The two-way detection head with multi-scale feature fusion efficiently combines contextual information for pavement-sealed crack detection. Additionally, the Wise Intersection over Union loss function dynamically adjusts the gradient gain, enhancing the accuracy of bounding box fitting and coverage area. Experimental results highlight the superiority of our proposed method, with higher mAP@0.5 (98.02%), Recall (0.9768), and F1-score (0.9680) values compared to the one-stage state-of-the-art methods, showcasing improvements of 0.81%, 1.8%, and 2.79%, respectively. [ABSTRACT FROM AUTHOR]

The current study aims to evaluate the performance of the ultrasonic vibration-assisted milling (USVAM) process when machining two different materials with high deviations in mechanical properties, specifically 7075 aluminium alloy and Ti-6Al-4V titanium alloy. Additionally, this study seeks to develop an AI-based model to predict the process performance based on experimental data for the different workpiece characteristics. In this regard, an ultrasonic vibratory setup was designed to provide vibration oscillations at 28 kHz frequency and 8 µm amplitude in the cutting feed direction for the two characterised materials of 7075 aluminium alloy (150 BHN) and Ti-6Al-4V titanium alloy (350 BHN) workpieces. A series of slotting experiments were conducted using both conventional milling (CM) and USVAM techniques. The axial cutting force and machined slot surface roughness were evaluated for each method. Subsequently, Support Vector Regression (SVR) and artificial neural network (ANN) models were built, tested and compared. AI-based models were developed to analyse the experimental results and predict the process performance for both workpieces. The experiments demonstrated a significant reduction in cutting force by up to 30% and an improvement in surface roughness by approximately four times when using USVAM compared to CM for both materials. Validated by the experimental findings, the ANN model accurately and better predicted the performance metrics with RMSE = 0.11 µm and 0.12 N for Al surface roughness and cutting force. Regarding Ti, surface roughness and cutting force were predicted with RMSE of 0.12 µm and 0.14 N, respectively. The results indicate that USVAM significantly enhances milling performance in terms of a reduced cutting force and improved surface roughness for both 7075 aluminium alloy and Ti-6Al-4V titanium alloy. The ANN model proved to be an effective tool for predicting the outcomes of the USVAM process, offering valuable insights for optimising milling operations across different materials. [ABSTRACT FROM AUTHOR]

With the wide application of wind energy as a clean energy source, to cope with the challenge of increasing maintenance difficulty brought about by the development of large-scale wind power equipment, it is crucial to monitor the operating status of wind turbines in real time and accurately identify the specific location of faults. In this study, a CNN-LSTM-based wind motor fault detection model is constructed for four types of typical faults, namely gearbox faults, electrical faults, yaw faults, and pitch faults of wind motors, combining CNN's advantages of excelling in feature extraction and LSTM's advantages of dealing with long-time sequence data, to achieve the simultaneous detection of multiple fault types. The accuracy of the CNN-LSTM-based wind turbine fault detection model reaches 90.06%, and optimal results are achieved for the effective discovery of yaw system faults, pitch system faults, and gearbox faults, obtaining 94.09%, 96.46%, and 97.39%, respectively. The CNN-LSTM wind turbine fault detection model proposed in this study improves the fault detection effect, avoids the further deterioration of faults, provides direction for preventive maintenance, reduces downtime loss due to restorative maintenance, and is essential for the sustainable use of wind turbines and maintenance of wind turbine service life, which helps to improve the operation and maintenance level of wind farms. [ABSTRACT FROM AUTHOR]

A photovoltaic (PV) power forecasting prediction is a crucial stage to utilize the stability, quality, and management of a hybrid power grid due to its dependency on weather conditions. In this paper, a short-term PV forecasting prediction model based on actual operational data collected from the PV experimental prototype installed at the engineering college of Misan University in Iraq is designed using various machine learning techniques. The collected data are initially classified into three diverse groups of atmosphere conditions—sunny, cloudy, and rainy meteorological cases—for various seasons. The data are taken for 3 min intervals to monitor the swift variations in PV power generation caused by atmospheric changes such as cloud movement or sudden changes in sunlight intensity. Then, an artificial neural network (ANN) technique is used based on the gray wolf optimization (GWO) and genetic algorithm (GA) as learning methods to enhance the prediction of PV energy by optimizing the number of hidden layers and neurons of the ANN model. The Python approach is used to design the forecasting prediction models based on four fitness functions: R2, MAE, RMSE, and MSE. The results suggest that the ANN model based on the GA algorithm accommodates the most accurate PV generation pattern in three different climatic condition tests, outperforming the conventional ANN and GWO-ANN forecasting models, as evidenced by the highest Pearson correlation coefficient values of 0.9574, 0.9347, and 0.8965 under sunny, cloudy, and rainy conditions, respectively. [ABSTRACT FROM AUTHOR]

Detecting clouds, snow, and lakes in remote sensing images is vital due to their propensity to obscure underlying surface information and hinder data extraction. In this study, we utilize Sentinel-2 images to implement a two-stage random forest (RF) algorithm for image labeling and delve into the factors influencing neural network performance across six aspects: model architecture, encoder, learning rate adjustment strategy, loss function, input image size, and different band combinations. Our findings indicate the Feature Pyramid Network (FPN) achieved the highest MIoU of 87.14%. The multi-head self-attention mechanism was less effective compared to convolutional methods for feature extraction with small datasets. Incorporating residual connections into convolutional blocks notably enhanced performance. Additionally, employing false-color images (bands 12-3-2) yielded a 4.86% improvement in MIoU compared to true-color images (bands 4-3-2). Notably, variations in model architecture, encoder structure, and input band combination had a substantial impact on performance, with parameter variations resulting in MIoU differences exceeding 5%. These results provide a reference for high-precision segmentation of clouds, snow, and lakes and offer valuable insights for applying deep learning techniques to the high-precision extraction of information from remote sensing images, thereby advancing research in deep neural networks for semantic segmentation. [ABSTRACT FROM AUTHOR]

Precipitation nowcasting, as a crucial component of weather forecasting, focuses on predicting very short-range precipitation, typically within six hours. This approach relies heavily on real-time observations rather than numerical weather models. The core concept involves the spatio-temporal extrapolation of current precipitation fields derived from ground radar echoes and/or satellite images, which was generally actualized by employing computer image or vision techniques. Recently, with stirring breakthroughs in artificial intelligence (AI) techniques, deep learning (DL) methods have been used as the basis for developing novel approaches to precipitation nowcasting. Notable progress has been obtained in recent years, manifesting the strong potential of DL-based nowcasting models for their advantages in both prediction accuracy and computational cost. This paper provides an overview of these precipitation nowcasting approaches, from which two stages along the advancing in this field emerge. Classic models that were established on an elementary neural network dominated in the first stage, while large meteorological models that were based on complex network architectures prevailed in the second. In particular, the nowcasting accuracy of such data-driven models has been greatly increased by imposing suitable physical constraints. The integration of AI models and physical models seems to be a promising way to improve precipitation nowcasting techniques further. [ABSTRACT FROM AUTHOR]

The phase problem in the context of focusing synchrotron beams with X‐ray lenses is addressed. The feasibility of retrieving the surface error of a lens system by using only the intensity of the propagated beam at several distances is demonstrated. A neural network, trained with a few thousand simulations using random errors, can predict accurately the lens error profile that accounts for all aberrations. It demonstrates the feasibility of routinely measuring the aberrations induced by an X‐ray lens, or another optical system, using only a few intensity images. [ABSTRACT FROM AUTHOR]

Over the past decades, technological advancements have included the production of a huge number of data streams. Data streams comprise large amounts of partially sequenced, infinite data. Changes in the statistical properties of the input data distribution, such as mean, variance and standard deviation or changes in their relationships with the target label, are referred to as concept drift. Concept drift and class imbalance poses challenges in maintaining accurate classification, adapting to evolving data patterns and effectively classifying minority classes. Addressing this problem requires techniques that handle both class imbalance and concept drift. If such problems are left unaddressed, they will hinder the learning model's performance. The proposed model in the paper uses adaptive synthetic sampling (ADASYN) to deal with class imbalances. The ADASYN method generates synthetic data by using a weighted distribution based on the severity of the minority class and hard to learn minority class samples. To adapt to concept drift, the performance-based diversified dynamic weighted ensemble is used subsequently. In addition, the cumulative sum statistical test is used to detect drift and, one of the ensemble's base learners, the self-organizing neural network model, which automatically creates a new layer when drift occurs and provide solution to catastrophic forgetting, performance-based pruning and ensemble evolution if more drift occurs. The proposed model's efficacy is assessed by utilizing a variety of state-of-the-art ensemble methods and seven datasets in a prequential test-then-train approach with single-pass learning. The results of the experiments show that the proposed model outperforms state-of-the-art ensemble methods. [ABSTRACT FROM AUTHOR]

This study fixates on determining the optimum laser input parameters that simultaneously meet the desired kerf width and depth during CO2 laser cutting of various polymethylmethacrylate (PMMA) sheets. It has three contributions. The first is to model the cutting process of PMMA by polynomial curve fitting as a function of laser power, laser speed, and standoff distance. R-squared (R2), adjusted R2 and root-mean-square error (RMSE) criteria were taken into account to measure the performance of the proposed model. The effect of laser parameters on the process is investigated by analysis of variance (ANOVA) and sensitivity analysis. The second is to optimize the derived nonlinear regression models using genetic algorithm (GA), particle swarm optimization (PSO), whale optimization algorithm (WOA) and ant lion optimization (ALO) metaheuristic methods and compare the performances of the algorithms. The third is to compare the adequacy of the optimization process with the artificial neural network (ANN). The investigations exhibited that the best-fitting polynomials are obtained with the R2 and adjusted R2 values of over 99% and 97%, respectively. ANOVA and sensitivity test revealed that the sensitivity of the laser power, which is the most effective parameter, was 150 at low powers and decreased to 0 as the power value increased. When the nozzle distance is 4.1, the proposed metaheuristics gave effective and sufficiently accurate results. PSO stood out in terms of both best cost value (3.49 × 10–8) and relative error value (0.19%). The relative error of the ANN was found as 3% in terms of kerf depth. [ABSTRACT FROM AUTHOR]

The escalating climate instability and extreme weather events significantly jeopardize food security. The study assessed the impact of long-term climatic variables and extreme weather events on soybean and wheat yields in rainfed central India. To address inherent spatial variability, the study area was divided into homogeneous zones based on rainfall and soil parameters. Crop yields were correlated with a comprehensive set of driving variables at seasonal and monthly scales within each zone. Machine learning algorithms, including Random Forest Regression (RFR) and Neural Networks (NN), were employed to analyze crop yield anomalies caused by climate and weather extremes. The Sobol' index was utilized for global sensitivity analysis to identify key parameters. Results showed significant negative correlations between thermo-meteorological parameters and yields of both monsoon soybean and winter wheat across multiple districts. Soybean yield exhibited a notable positive correlation with hydro-meteorological parameters, while wheat yield displayed a significant positive correlation with cold temperature extremes. RFR and NN demonstrated similar performance, with Root Mean Square Error (RMSE) values ranging from 0.27 to 0.39 t/ha for soybean and 0.4 to 0.6 t/ha for wheat. The Sobol' index highlighted the high sensitivity of soybean yield to rainfall and rainy days during July and August, corresponding to the crop development and flowering stages. In contrast, wheat yield was primarily influenced by temperature extremes, particularly cold nights and hot days during the reproductive-maturity stage. These crop- and growth-stage-specific analyses of meteorological parameters are essential for devising effective strategies to adapt and mitigate climate emergencies. [ABSTRACT FROM AUTHOR]

Accurate prediction of tunnel boring machine (TBM) penetration rates is of great significance for intelligent TBM construction. Traditional empirical and theoretical models of TBM penetration rates are difficult to adapt to complex and changeable formation environments. To improve the adaptability, this paper proposes a TBM penetration rate prediction model based on the particle swarm optimization (PSO)-Elman algorithm fusion. Particle swarm optimization (PSO) was used to find the optimal connection weight matrix, which was inserted into the Elman network, and the TBM penetration rate was predicted by the machine learning method. This study examined field data from two distinct tunnel sections, focusing on their geological conditions, construction challenges, and environmental impacts. By analyzing the characteristics unique to these sites, the research offers a comparative perspective on tunnel engineering in diverse settings. Five parameters—uniaxial compressive strength (UCS), rock integrity index (Kv), cutter head thrust (Fn), cutter head speed (RPM), and penetration degree (P)—were selected as the input parameters. The TBM penetration rate was estimated by neural network training of the model. The results show that the PSO method effectively can overcome the problem of being prone to a local minimum using the single Elman method, and the PSO-Elman model has a fast convergence speed and high accuracy. In the 20 groups of experimental samples selected, the mean absolute percentage error (MAPE) was 3.38%, and the coefficient of determination (R2) was 0.936. The prediction quality was better than that of the single Elman method or the backpropagation neural network (BP) method. The study yields specific insights into efficient tunnel construction methodologies and practical neural network tools for risk management, highlighting innovative approaches in environmental preservation and safety enhancement in tunnel engineering. [ABSTRACT FROM AUTHOR]

The yellow stem borer (YSB), Scirpophaga incertulas (Walker), is a major insect pest that significantly damages rice crop. This study investigates methods to predict YSB populations in rice fields, aiming to develop an early warning system. Traditionally, rice farmers rely on light traps to monitor YSB presence. However, this study goes beyond this approach by combining light‐trap data with weather information (temperature, humidity, rainfall) and utilizing powerful artificial intelligence (AI) techniques to forecast future YSB populations. Two AI methods, multilayer perceptron (MLP) and long short‐term memory (LSTM), were employed to estimate YSB populations and assess their performance. The results revealed that the LSTM model outperformed the MLP model based on statistical metrics like RMSE, MAE, and R2 values. Utilizing LSTM model with historical data, stakeholders in the Eastern Coastal Plains and Hills agro‐climatic zone of India can gain a significant advantage in predicting YSB populations well in advance. This early warning system can alert stakeholders of potential YSB outbreaks, allowing them to take timely management actions and protect their rice crops from substantial yield losses. [ABSTRACT FROM AUTHOR]

Summary: According to recent research work, increasing electric power generation is one of the significant advantages of the dual‐rotor wind turbine (DRWT) compared to the other types for the same wind speed. In this research work, a modified super‐twisting sliding mode control (STSMC) based on the neural network (NN) is suggested to regulate the stator powers of a DRWT‐based doubly‐fed induction generator (DFIG) in normal and unbalanced grid fault modes. The design of this strategy involves replacing the gains of conventional STSMC with the NN algorithm to enhance robustness, mitigate the impact of unbalanced grid voltage, and consequently improve the quality of the generated power of DRWT‐based DFIG. This forms the primary contribution of this work. The suggested strategy is compared with vector control (VC) and conventional STSMC in terms of reference tracking, power ripples, response dynamics, harmonic distortion of stator current, and the effect of an unbalanced grid fault. Finally, the utility and effectiveness of the designed controller are confirmed through computer simulations. Furthermore, when the grid is subjected to a 20% voltage drop, the results demonstrate that the suggested strategy reduced the total harmonic distortion (THD) value of the stator current by 12.92% compared to VC and by 9.29% compared to conventional STSMC. [ABSTRACT FROM AUTHOR]

The advent of Internet of Things and artificial intelligence in the era of Industry 4.0 has transformed decision-making within production systems. In particular, many decisions that previously required significant human activity are now made automatically with minimal human intervention via so-called digital twins (DTs). In the context of maintenance and reliability modeling, this naturally calls for new paradigms that can be seamlessly integrated within DTs for decision-making. The input data for time to failure needed in reliability computations are directly collected from the work center in a digital setting and often do not satisfy a known distribution. A neural network (NN) is proposed here to bypass this difficulty within the DT. Further, an algorithm inspired from machine learning is employed to solve the underlying semi-Markov decision process, whose transition model is captured via the NN. Numerical studies are carried out to demonstrate the usefulness of the approach. Finally, convergence properties of the algorithm are analyzed mathematically. [ABSTRACT FROM AUTHOR]

Optimal control of multivariable systems is a complex dynamic process that minimizes the cost function to obtain the optimal control strategy. Unfortunately, for nonlinear systems, it is not possible to use the traditional linear quadratic regulator (LQR), which would be optimal over the entire range of parameter variation. The problem of nonlinear multivariable systems and their optimal control is very momentous. The solution presented in this paper is based on the application of Reinforcement Learning (RL) networks in controlling a five-degree-of-freedom overhead crane system. Additionally, unlike the classical approach, the algorithm is adapted to directly analyze tabular data of inputs and outputs of the controlled model instead of analyzing its state as feedback (model-free). Implementing the new control structure for the multivariable system improved control quality compared to the classical LQR controller with linearization at the operating point. In addition to quality, the resource indicators, which in the LQR controller are represented by the matrix R, have been significantly improved. The architecture of the neural control system is presented, ensuring that over the entire range of nonlinearity, the quality of control is preserved while reducing the cost of its resource intensity. Obtaining optimal control with reduced resources for its implementation induces a wide range of applications of such neural control in engineering systems. The effectiveness of the proposed control system has been demonstrated in simulation studies. The simulation results present the system's excellent control performance and adaptability over the entire range of object nonlinearity. The neural algorithm resulted in significantly shorter adjustment time and better control quality with significantly less system resource consumption and increased system dynamics. [ABSTRACT FROM AUTHOR]