Backpropagation Neural Network Learning Research Articles

Optimization of thermal management performance of direct-cooled power battery based on backpropagation neural network and deep reinforcement learning

The batteries of new energy vehicles generate a large amount of heat when discharged at large multiplication rates, which can cause safety hazards if the heat is not eliminated in time. In this paper, a Swiss roll-type cooling belt is used to improve the thermal performance of lithium-ion battery packs. This paper selects six key parameters as optimization parameters, including the structure of Swiss roll-type cooling belt, coolant type, inlet coolant mass flow rate, inlet coolant gas volume fraction, battery discharge rate, and ambient temperature. Use neural network fitting and deep reinforcement learning to optimize these six parameters in order to achieve optimized cooling performance. The results show that after the cold plate has been structurally optimised and the inlet parameters have been optimised by deep reinforcement learning, the thermal performance has been significantly improved. Not only does the cold plate inlet require less mass flow, but the battery pack also performs better in terms of temperature difference.

Development and application of data-driven CHF model in system analysis code

In nuclear reactor systems, when the fuel rods reach the critical heat flux (CHF), a sharp increase in fuel temperature occurs due to a drastic reduction in heat transfer capacity, thus posing a considerable risk to the reactor’s safety. Consequently, accurate CHF prediction holds paramount importance in accurately simulating accident scenarios and enhancing the overall safety of reactor systems. To tackle the challenge of limited prediction accuracy in existing CHF models, this study initially established a comprehensive database by utilizing available experimental data and lookup tables. Subsequently, various methodologies, including the Back Propagation Neural Network (BPNN), Random Forest (RF), and Physics-Informed Machine Learning (PIML), were employed to develop multiple CHF prediction models, and their performance was thoroughly evaluated. Furthermore, the optimal CHF model was integrated into the self-developed analysis code ARSAC, which was then validated using the ORNL-THTF experiment. The results indicated that the BPNN-based model not only demonstrated exceptional prediction accuracy but also exhibited rapid calculation speeds. Notably, the average relative error between the experimental data points and the calculation results of the modified code is 3.64%, while for the original code, it is 22.84%. This study effectively leverages the strengths of data-driven approaches, providing a robust technical solution for high-precision, efficient, and adaptive numerical prediction and analysis of reactor accidents.

Carbon peaking prediction scenarios based on different neural network models: A case study of Guizhou Province.

Global warming, caused by greenhouse gas emissions, is a major challenge for all human societies. To ensure that ambitious carbon neutrality and sustainable economic development goals are met, regional human activities and their impacts on carbon emissions must be studied. Guizhou Province is a typical karst area in China that predominantly uses fossil fuels. In this study, a backpropagation (BP) neural network and extreme learning machine (ELM) model, which is advantageous due to its nonlinear processing, were used to predict carbon emissions from 2020 to 2040 in Guizhou Province. The carbon emissions were calculated using conversion and inventory compilation methods with energy consumption data and the results showed an "S" growth trend. Twelve influencing factors were selected, however, five with larger correlations were screened out using a grey correlation analysis method. A prediction model for carbon emissions from Guizhou Province was established. The prediction performance of a whale optimization algorithm (WOA)-ELM model was found to be higher than the BP neural network and ELM models. Baseline, high-speed, and low-carbon scenarios were analyzed and the size and time of peak carbon emissions in Liaoning Province from 2020 to 2040 were predicted using the WOA-ELM model.

Research on DEM geomorphic factor terrain recognition algorithm using probabilistic neural networks based on tactile systems

The accurate recognition of unknown terrain by robots plays a vital role in completing walking tasks. Haptic-based terrain recognition methods have their own advantages over visual, audio, and vibration-based terrain recognition methods. With the increasing complexity of robot application scenarios, there are still many technical difficulties in using tactile systems to recognize terrain. For real-time terrain detection technology, how to improve the accuracy of terrain recognition and shorten recognition time based on tactile systems is an urgent problem to be solved. In this paper, the digital elevation model (DEM) geomorphic factor terrain recognition algorithm using probabilistic neural networks (DGFTRA-PNN) based on tactile force-feedback system is proposed to solve this problem. First, the tactile force-feedback system is mounted on the foot ends of the hexapod robot to collect terrain data. Second, the feasibility of using DEM geomorphic factors as terrain features to identify terrain was demonstrated. Third, DGFTRA-PNNs are established based on the different walking gait of the hexapod robot, achieving terrain recognition based on DEM feature values. Finally, the accuracy and speed of DGFTRA-PNN were verified through field experiments. Compared with the terrain recognition algorithm based on back propagation neural network (BP) and extreme learning machine (ELM) algorithm, the DGFTRA-PNN has advantages in terms of terrain recognition accuracy and recognition time: the average recognition accuracy for various types of terrain is 96%, and the calculation time is 0.04 seconds.

Empirical study of college students' extracurricular reading preference by functional data analysis of the library book borrowing behavior.

Library data contains many students' reading records that reflect their general knowledge acquisition. The purpose of this study is to deeply mine the library book-borrowing data, with concerns on different book catalogues and properties to predict the students' extracurricular interests. An intelligent computing framework is proposed by the fusion of a neural network architecture and a partial differential equations (PDE) function module. In model designs, the architecture is constructed as an adaptive learning backpropagation neural network (BPNN), with automatic tuning of its hyperparameters. The PDE module is embedded into the network structure to enhance the loss functions of each neural perceptron. For model evaluation, a novel comprehensive index is designed using the calculus of information entropy. Empirical experiments are conducted on a diverse and multimodal time-series dataset of library book borrowing records to demonstrate the effectiveness of the proposed methodology. Results validate that the proposed framework is capable of revealing the students' extracurricular reading interests by processing related book borrowing records, and expected to be applied to "big data" analysis for a wide range of various libraries.

Research on Shovel-Force Prediction and Power-Matching Optimization of a Large-Tonnage Electric Wheel Loader

Nowadays, rapid development has been achieved with respect to the electric wheel loader (EWL). The operational efficiency of EWLs is affected by many factors; especially, shovel force is a very important factor. For large-tonnage EWLs, when employing empirical, formula-based methods to predict shovel force, the generated errors are significant, with errors frequently reaching levels of up to 30%. To solve this problem, a method, based on the discrete element method (DEM), to predict shovel force is put forward in this paper. The material parameters are calibrated by a backpropagation (BP) neural network learning algorithm (NNLA). The material model is inputted into multi-body-dynamics software. A simulation model to accurately predict the shovel force is created. The error between the test results and the simulation results is 7.8%, demonstrating a high level of consistency. To validate the reliability of this method, the 35-ton EWL is taken as an example for research, and the straight-line driving test and the power-matching test are conducted. While ensuring the operational efficiency of the EWLs, the power loss is also a crucial consideration. The drastic changes in shovel force often result in front-tire slippage of the EWLs. To minimize wheel slippage during the shoveling section, the matching of the electric motor was optimized. In summary, material parameters were calibrated using a combined method of BP NNLA to predicate shovel force of a large-tonnage EWL. Additionally, the power matching of the EWL has been optimized to accord with the shoveling section of the device.

An interval water demand prediction method to reduce uncertainty: A case study of Sichuan Province, China

Effective prediction of water demand is a prerequisite for decision makers to achieve reliable management of water supply. Currently, the research on water demand prediction focuses on point prediction method. In this study, we constructed a GA-BP-KDE hybrid interval water demand prediction model by combining non-parametric estimation and point prediction. Multiple metaheuristic algorithms were used to optimize the Back-Propagation Neural Network (BP) and Kernel Extreme Learning Machine (KELM) network structures. The performance of the water demand point prediction models was compared by the Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), Kling-Gupta Efficiency (KGE), computation time, and fitness convergence curves. The kernel density estimation method (KDE) and the normal distribution method were used to fit the distribution of errors. The probability density function with the best fitting degree was selected based on the index G. The shortest confidence interval under 95% confidence was calculated according to the asymmetry of the error distribution. We predicted the impact indicator values for 2025 using the exponential smoothing method, and obtained water demand prediction intervals for various water use sectors. The results showed that the GA-BP model was the optimal model as it exhibited the highest computational efficiency, algorithmic stability, and prediction accuracy. The three prediction intervals estimated after adjusting the KDE bandwidth parameter covered most of the sample points in the test set. The prediction intervals of the four water use sectors were evaluated as F values of 1.6845, 1.3294, 1.6237, and 1.3600, which indicates high accuracy and quality of the prediction intervals. The mixed water demand interval prediction based on GA-BP-KDE reduces the uncertainty of the point prediction results and can provide a basis for water resource management by decision makers.

Shallow water bathymetry based on a back propagation neural network and ensemble learning using multispectral satellite imagery

Shallow water bathymetry based on a back propagation neural network and ensemble learning using multispectral satellite imagery

Optimal forecast combination based on PSO-CS approach for daily agricultural future prices forecasting

Forecasting agricultural commodity prices accurately is a challenging task due to the complexity of the trading market and the variability of influencing factors. Many studies have proven that forecast combination is an effective strategy for improving forecast performance relative to individual forecasting. In the field of forecast combination, how to determine the reasonable weights for combination is still an open question. This study proposed an optimal forecast combination framework for agricultural commodity prices forecasting, which integrates the decomposition–reconstruction–ensemble methodology with an improved nature-inspired global optimization algorithm. The update mechanism of particle swarm optimization (PSO) is introduced to improve cuckoo search (CS), in order to reduce the searching blindness in the huge exploration space. The framework consists of four steps. First, data decomposition using empirical wavelet transform (EWT), singular spectral analysis (SSA), and variational mode decomposition (VMD); Second, component reconstruction via a modified reconstruction approach based on the largest comprehensive grey correlation degree clustering (CGCD); Third, individual forecasting using autoregressive integrated moving average regression (ARIMA), exponential smoothing (ETS), back propagation neural network (BPNN) and extreme learning machine (ELM); Fourth, forecast combination via PSO-CS weight assignment method. Using corn and wheat future prices as research samples, the experimental results demonstrated that: (a) the PSO-CS weight assignment approach is superior to other combination approaches in most cases; (b) the CGCD approach can effectively reduce the computational cost of forecasting and improve the prediction performance; (c) the Full-PSO-CS model provides the most accurate forecast due to the diversity of individual forecasts, it reduces MAPE by 43.66% and improves directional accuracy by 30.80% on average compared with the best single model.

Identify the Color and Shape of Eggplant Using Back Propagation Method

Currently, artificial neural networks are being developed as a tool that can help human tasks. The main purpose of this study is to identify the structure of an eggplant, in order to distinguish the type of eggplant. This study empirically tested the shape and color of several eggplants using the back propagation neural network learning method. The data is obtained from an image that will be entered into the program. The data used in the identification process are two photos containing two types of eggplant, the first eggplant is green and round and the next eggplant is purple and oval. The results of the identification process using this back propagation from the tests that have been carried out previously, the highest calculation results obtained with the best results using a learning rate of 0.7 and epoch iterations of 500 and producing an accuracy of 73.33%.

Combined Forecasting of Ship Heave Motion Based on Induced Ordered Weighted Averaging Operator

AbstractHeave motion of ships is a complex nonlinear dynamic process and cannot be accurately forecasted using a single prediction model. In this paper, an effective combined forecasting method is proposed to perform ship's heave motion prediction. The proposed method combines back propagation neural network (BPNN), autoregressive model (AR) and extreme learning machine (ELM) through an induced ordered weighted averaging (IOWA) operator. The prediction accuracy is selected as the induced variable and the prediction results are sorted according to prediction accuracy and IOWA operator assigns larger weights to the position with the smallest prediction error. The optimal weights are determined by maximizing the B‐mode relational degree. Experimental results demonstrate its effectiveness of the proposed method. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Industrial big data-driven mechanical performance prediction for hot-rolling steel using lower upper bound estimation method

Industrial big data technology has become one of the important driving forces to intelligent manufacturing in the steel industry. In this study, the characteristics of data in steel production are analyzed and an industrial big data platform for steeling process is developed to extract the quality-related parameters. A data-driven approach to construct prediction intervals (PIs) of mechanical performances for hot-rolling strips is proposed to represent the uncertainty and reliability of the prediction results. The proposed method employs a new manifold visualization method, SLISEMAP, to reduce the feature dimensions with interpretability, utilizes lower upper bound estimation (LUBE) method to obtain the PIs, in which the broad learning system (BLS) is used as the basic training network model and the artificial bee colony (ABC) algorithm is applied to optimize the weighting parameters of BLS under the LUBE framework. A hot-rolling steel coil dataset consisting of 39 variables and 1335 coil samples is used to validate the proposed method. Two Delta-based approaches, namely back propagation neural network (BPNN) and extreme learning machine (ELM); and three LUBE-based approaches, namely ABC-BPNN, ABC-ELM, and ABC-support vector regression (SVR) are compared with the proposed method. Results show that the proposed ABC-BLS in LUBE is effective and efficient in constructing the PIs with a higher coverage probability and a narrower interval width.

Neural Network Model Design for Landscape Ecological Planning Assessment Based on Hierarchical Analysis.

In this paper, an in-depth study and analysis of landscape ecological planning and evaluation are carried out using the analytic hierarchy process (AHP) algorithm that integrates neural networks. The application of AHP in the field of tree species planning and the introduction of quantitative analysis methods can effectively change the subjectivity of previous qualitative analysis in tree species selection and make it objective, scientific, and reasonable. The research can provide a reference for other urban tree species planning. From the connotation of landscape ecological service process and ecological space structure, the analysis of landscape ecological service process involves service supply area and service association area, which correspond to different key components of ecological space structure. With the help of the platform, based on the identification and identification methods and theories of ecological spatial structure, the key components of ecological spatial structure in different environments are identified and extracted by using the representation model, binary suitability model, weighted suitability model, and process model. The type of service is based on the different service processes supported by the key components of the ecological spatial structure, forming the ecological spatial structure under different service types. Spatial structure; on this basis, the basic characteristics of the key components of the ecological spatial structure are analyzed, and the correlation characteristics of the ecological spatial structure are analyzed based on the correlation classification system of ecological spatial structure. A backpropagation (BP) neural network-based state assessment method of the grid structure is established. The method takes the parameters of the autoregressive model constructed by the acceleration signals of different working conditions as the feature quantity and the results of the fuzzy hierarchical analysis method as the labels, divides the data set into a training set and a test set, and uses the BP neural network learning method and the training set to supervised train the BP neural network learning assessment model. The test set is used to test the effectiveness and accuracy of the BP neural network-based learning method. The study shows that the evaluation system established by the BP neural network structure is fast and accurate and can substantially reduce the cost of manual testing.

Research on Chlorophyll-a Concentration Retrieval Based on BP Neural Network Model—Case Study of Dianshan Lake, China

The Chlorophyll-a (Chl-a) concentration is an important indicator of water environmental conditions; thus, the simultaneous monitoring of large-area water bodies can be realized through the remote sensing-based retrieval of the Chl-a concentrations. The back propagation (BP) neural network learning method has been widely used for the remote sensing retrieval of water quality in first and second-class water bodies. However, many Chl-a concentration measurements must be used as learning samples with this method, which is constrained by the number of samples, due to the limited time and resources available for simultaneous measurements. In this paper, we conduct correlation analysis between the Chl-a concentration data measured at Dianshan Lake in 2020 and 2021 and synchronized Landat-8 data. Through analysis and study of the radiative transfer model and the retrieval method, a BP neural network retrieval model based on multi-phase Chl-a concentration data is proposed, which allows for the realization of remote sensing-based Chl-a monitoring in third-class water bodies. An analysis of spatiotemporal distribution characteristics was performed, and the method was compared with other constructed models. The research results indicate that the retrieval performance of the proposed BP neural network model is better than that of models constructed using multiple regression analysis and curve estimation analysis approaches, with a coefficient of determination of 0.86 and an average relative error of 19.48%. The spatial and temporal Chl-a distribution over Dianshan Lake was uneven, with high concentrations close to human production and low concentrations in the open areas of the lake. During the period from 2020 to 2021, the Chl-a concentration showed a significant upward trend. These research findings provide reference for monitoring the water environment in Dianshan Lake.

Exploration on the Construction of Cross-Border E-Commerce Logistics System Using Deep Learning

The intention of this article is to solve the disadvantages of the current logistics model and promote the healthy development of modern cross-border e-commerce (CBEC) Logistics. First, this paper expounds on and compares the traditional and CBEC logistics models. Then, the CBEC logistics system is constructed and adjusted according to system construction requirements. Further, two key subsystems are designed: the logistics object distribution subsystem and risk detection subsystem, based on the deep learning backpropagation neural network (BPNN) algorithm. The relevant parameters of the object distribution subsystem are calculated and sent to the risk detection subsystem model and tested. It is concluded that the sorting completion rate before 18:00 can reach 95.2%, indicating that the proposed CBEC logistic system can meet the needs of CBEC logistics enterprises. Logistics risk detection’s expected and actual outputs can fit 99%, indicating a tiny deviation. The research has certain reference significance for clarifying the logistics system and service mode of CBEC.

Finite element-based machine learning approach for optimization of process parameters to produce silicon carbide ceramic complex parts

Design and fabrication of silicon carbide ceramic complex parts introduce considerable difficulties during injection molding. Due to the great importance in processing optimization, an accurate prediction on the stress and displacement is required to obtain the desired final product. In this paper, a conceptual framework on combination of finite element method (FEM) and machine learning (ML) method was developed to optimize the injection molding process, which can be used to manufacture large-aperture silicon carbide mirror. The distribution characteristics of temperature field and stress field were extracted from FEM simulation to understand the injection molding process and construct database for ML modeling. To select the most appropriate model, the predictive performance of three ML models were estimated, including generalized regression neural network (GRNN), back propagation neural network (BPNN) and extreme learning machine (ELM). The results show that the developed ELM model exhibits exceptional predictive performance and can be utilized to predict the stress and displacement of the green body. This work allows us to obtain reasonable technique parameters with particular attention to the loading speed and provides some fundamental guidance for the fabrication of lightweight SiC ceramic optical mirror.

Wetland Ecotourism Development Using Deep Learning and Grey Clustering Algorithm from the Perspective of Sustainable Development.

The purpose is to promote the sustainable development of wetland ecotourism in China and plan the passenger flow in different tourism periods. This work selects Zhangye Heihe wetland ecotourism spot as the research object. Firstly, the two single wetland ecotourism Demand Prediction Models (DPMs) are proposed based on the time series of the optimized Fuzzy Clustering Algorithm (FCA), grey theory, and the Markov Chain Method. The proposed wetland ecotourism DPM simulates and predicts the ecotourism passenger flow of wetland-scenic spots and verifies the maximum passenger flow. Then, a hybrid model combining the above two single models is proposed, namely, the wetland ecotourism DPM based on an optimized fuzzy grey clustering algorithm. Further, the proposed three models predict the passenger flow in wetland ecotourism spots from 2015 to 2019. A wetland Water Quality Evaluation (WQE) model based on Deep Learning Backpropagation Neural Network (Deep Learning (DL) BPNN) is proposed to evaluate the water quality in different water periods. The results show that the hybrid model's Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) are 1.25% and 0.2532. By comparison, for two single models, the MAPE is 11.67% and 1.45%, respectively, and the RMSE is 0.2526 and 0.1652, respectively. Therefore, the mixed hybrid has the highest accuracy and stability. The water quality of the scenic spot in the wet season is obviously better than that in the dry season and flat season. It is suggested that the natural environmental factors, such as water quality and passenger flow in different periods, should be considered when formulating ecotourism development strategies.

Error Backpropagation Neural Network for Classifying Diabetic Diseases based on the Grading Method of Circular Region

Diabetic retinopathy grading is an important issue after detecting lesions of retina to estimate their risk and to take a suitable decision for treatment. Here, the grading of diabetic retinopathy is examined by consistent medical approaches to build a computer model for grading in automated way, which improve the efficiency of diabetic screening services. After the grading of diabetic retinopathy, Error Backpropagation Neural Network Learning Rule is used to give suggestions to a doctor for suitable treatment for the patient. Here, sixteen different cases are trained, and it takes about 8.368 seconds with 20820 iterations. The Neural network diagnosis four-treatment cases and they are urgent, moderate, mild and normal. It is also found from the results that Neural Network is very fast algorithm to give these decisions. In addition, the program that is used for carrying out processes is MATLAB Program version 2015, the computer is HP core i7.

Forecasting residential electricity consumption using a hybrid machine learning model with online search data

Accurate forecasting of residential electricity consumption plays an important role in formulating energy plans and ensuring the safety of power system operations. In order to improve forecasting accuracy, we propose a novel hybrid model with online search data for residential electricity consumption forecasting. Two main steps are involved: (1) Time difference correlation analysis, cointegration test, and Granger causality test are employed to investigate the relationship between online search data and residential electricity consumption. Qualified search keywords are selected to serve as predictors. (2) An extreme learning machine model optimized by Jaya algorithm, together with the selected search keywords from the first step, is proposed to predict residential electricity consumption. Furthermore, monthly residential electricity consumption data from China are used to validate the effectiveness of the proposed model. The experimental results show that the incorporation of online search data into the model can significantly improve forecasting accuracy. After incorporating online search data, improvement rates of all the forecasting models exceed 10%. In addition, the proposed model has the best forecasting performance compared with seasonal autoregressive integrated moving average (SARIMA(X)), support vector regression (SVR), back propagation neural network (BPNN) and extreme learning model (ELM). Root mean squared error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE) of the proposed model with online search data decrease by 34%-51.2%, 43.03%-53.92%, and 41.35%-54.85% relative to other benchmark models, respectively.

Optimization of diesel engine dual-variable geometry turbocharger regulated two-stage turbocharging system based on radial basis function neural network-quantum genetic algorithm

ABSTRACT Aiming at the problem of power and economy reduction in high-altitude operation of diesel engines, a radial basis function neural network-quantum genetic algorithm (RBFNN-QGA) optimization method is proposed to optimize diesel engine dual-variable geometry turbocharger (VGT) regulated two-stage turbocharging (RTST) system. Firstly, the GT-power simulation model of dual-VGT RTST diesel engine was established, and then calibrated with test data. The latin hypercube sampling (LHS) algorithm was selected for the experimental design, and the back propagation neural network (BPNN), RBFNN, and extreme learning machine (ELM) were used to establish three diesel engine high-altitude performance prediction models based on the sample data, to compare the ability of the three neural networks in predicting the performance of diesel engines. Finally, RBFNN is coupled with QGA to establish the optimization model of dual-VGT RTST system at different altitudes with torque, fuel consumption rate as the optimization target, and vortex front row temperature and in-cylinder combustion pressure as the constraints. The study results show that three kinds of neural networks have achieved satisfactory prediction results, BPNN and RBFNN are better than ELM in prediction accuracy, and ELM training is faster than BPNN and RBFNN; QGA converges faster and has higher optimization efficiency than GA, and the maximum torque of the optimized dual-VGT diesel engine is restored to more than 85% of the plain level, compared with the single-turbocharged diesel engine and the single-VGT two-stage turbocharged diesel engine, the low-speed torque of the dual-VGT RTST diesel engine is increased by 384% and 100%. This optimization model has better optimization effect and efficiency.