BP Neural Network Method Research Articles

Organic integration of ideological and political education and entrepreneurship education based on artificial neural network

Entrepreneurship is a systematic project, and it needs entrepreneurial knowledge, skills, psychology and many other basic qualities. Therefore, it is imperative to educate college students on entrepreneurship. IPE (Ideological and political education) courses offered by universities should adhere to the spirit of the Chinese dream and integrate with 2E (Entrepreneurship Education), which will not only provide more theoretical guidance for college entrepreneurs in practice but also promote their practical experience to theoretical innovation and promote their all-round development. Therefore, this research is based on ANN (artificial neural network) to study the organic integration of IPE and entrepreneurship education. According to the practice of carrying out quality education in our university, a set of index systems suitable for comprehensive quality evaluation of students in engineering colleges is established. Use BPNN (BP neural network) method to construct the test model, and IL (Input layer) is responsible for receiving external input information. Through the learning rules in HL (Hidden layer), this paper refers to the weight values of various quality indicators, transforms the input values, and adjusts the deviation of test results. OL (Output layer) is responsible for outputting calculation results, that is, evaluating students' comprehensive quality information. The results of BPNN show that the actual value and the expected value are within a reasonable range, and the maximum relative error is 1.607 %, which meets the accuracy requirements. The established evaluation index system of 2E is reasonable and effectively reflects students' innovation and entrepreneurship abilities.

State of Charge Estimation for Power Battery Using Improved Extended Kalman Filter Method Based on Neural Network

In order to enhance the accuracy of the traditional extended Kalman filter (EKF) algorithm in the estimation of the state of charge (SoC) of power batteries, we first derived the state space equation and measurement equation of lithium power batteries based on the Thevenin battery model and the modified Ampere-Hour integralalgorithm. Then, the basic principles of EKF, backpropagation neural networks (BPNNs), and a biogeography-based optimization (BBO) algorithm were analyzed, and the arc curve mobility model was used to improve the global search ability of the BBO algorithm. By combining these three algorithms, this paper proposes a BP neural network method based on the BBO algorithm. This method uses the BBO algorithm to optimize the incipient weight and threshold of the BP neural network and uses this improved neural network to modify the estimated value of the extended Kalman filter algorithm (BBOBP-EKF). Finally, the BBOBP-EKF algorithm, the extended Kalman filter algorithm based on the BP neural network (BP-EKF), and the EKF algorithm are used to estimate the error value of the SOC of a power battery, and according to the experimental data, it was confirmed that the proposed BBOBP-EKF algorithm has been improved compared to other algorithms with respect to each error index term, in which the maximum error is 1% less than that of the BP-EKF algorithm and 2.4% less than that of the EKF algorithm, the minimum error is also the smallest, and the estimation accuracy is improved compared to the traditional algorithms.

Geophysical prediction of organic matter abundance in source rocks based on geochemical analysis: A case study of southwestern Bozhong Sag, Bohai Sea, China

The Bozhong Sag is the largest petroliferous sag in the Bohai Bay Basin, and the source rocks of Paleogene Dongying and Shahejie Formations were buried deeply. Most of the drillings were located at the structural high, and there were few wells that met good quality source rocks, so it is difficult to evaluate the source rocks in the study area precisely by geochemical analysis only. Based on the Rock-Eval pyrolysis, total organic carbon (TOC) testing, the organic matter (OM) abundance of Paleogene source rocks in the southwestern Bozhong Sag were evaluated, including the lower of second member of Dongying Formation (E3d2L), the third member of Dongying Formation (E3d3), the first and second members of Shahejie Formation (E2s1+2), the third member of Shahejie Formation (E2s3). The results indicate that the E2s1+2 and E2s3 have better hydrocarbon generative potentials with the highest OM abundance, the E3d3 are of the second good quality, and the E3d2L have poor to fair hydrocarbon generative potential. Furthermore, the well logs were applied to predict TOC and residual hydrocarbon generation potential (S2) based on the sedimentary facies classification, using ΔlogR, generalized ΔlogR, logging multiple linear regression and BP neural network methods. The various methods were compared, and the BP neural network method have relatively better prediction accuracy. Based on the pre-stack simultaneous inversion (P-wave impedance, P-wave velocity and density inversion results) and the post-stack seismic attributes, the three-dimensional (3D) seismic prediction of TOC and S2 was carried out. The results show that the seismic near well prediction results of TOC and S2 based on seismic multi-attributes analysis correspond well with the results of well logging methods, and the plane prediction results are identical with the sedimentary facies map in the study area. The TOC and S2 values of E2s1+2 and E2s3 are higher than those in E3d3 and E3d2L, basically consistent with the geochemical analysis results. This method makes up the deficiency of geochemical methods, establishing the connection between geophysical information and geochemical data, and it is helpful to the 3D quantitative prediction and the evaluation of high-quality source rocks in the areas where the drillings are limited.

Source Rock Evaluation of Hydrocarbons in Deep-Water Offshore Areas Based on a BP Neural Network

Due to the lack of drilling data and poor quality of seismic data in deep-water offshore areas, conventional methods cannot effectively predict the total organic carbon (TOC) content. In this paper, the BP neural network method is used to predict the TOC of the strata overlying the target layer, which adds to the TOC information in the study area. Then, the highest TOC value of the strata overlying the target layer is used to select the most sensitive seismic attributes. Finally, the sensitive seismic attributes are used to evaluate the source rocks with no or few wells. A set of TOC prediction technology flows is established for TOC combined with seismic attributes under the condition of no wells and few wells in deep-water areas. The application example shows the reliability of TOC prediction by this technical process, and the study has a certain reference significance for the evaluation of hydrocarbon source rocks in offshore deep water.

Analysis of the impact of college students’ innovation and entrepreneurship on human resource index of science and technology enterprises based on logistic regression model

Abstract Considering the immediate phenomenon of uncoordinated advancement, unbalanced distribution and unreasonable structure of regional human resources and academy undergraduates’ innovation and start an undertaking ability in China, this paper fundamentally constructs academy undergraduates’ innovation and entrepreneurship system through a logistic regression model. The study takes 29 provinces and regions in China as research samples and adopts the logistic regression model BP neural network method to conduct a more in-depth theoretical discussion and empirical analysis on the interaction mechanism and the coupled and coordinated development of regional manpower capital and produce and start an undertaking ability in China. The coupling and coordination degree of manpower capital and production and start an undertaking in 29 provinces and regions in China is lower than 0.8, and the average value is 0.358, which is in the “mild dysfunctional decline” stage. There are some mutual constraints between the subsystems of human resources of science and technology enterprises and the products and start an undertaking ability of academy undergraduates, and more efforts must be made in their respective “shortcomings” and comparative disadvantages to promote the synergy and consistency of their development levels. We should strive to strengthen cooperation with foreign countries and introduce advanced technology and outstanding talents from developed countries. In the “import” at the same time “go out”, in the learning from the same time also “teach others to fish”, in order to achieve win-win cooperation.

Power Transformer Fault Diagnosis Based on Improved BP Neural Network

Power transformers are complex and extremely important piece of electrical equipment in a power system, playing an important role in changing voltage and transmitting electricity. Its operational status directly affects the stability and safety of power grids, and once a fault occurs, it may lead to significant economic losses and social impacts. The traditional detection methods rely on the technical level of power system operation and maintenance personnel, and are based on Dissolved Gas Analysis (DGA) technology, which analyzes the components of dissolved gases in transformer oil for preliminary fault diagnosis. However, with the increasing accuracy and intelligence requirements for transformer fault diagnosis in power grids, the DGA analysis method is no longer able to meet the requirements. Therefore, this article proposes an improved transformer fault diagnosis method based on a residual BP neural network. This method deepens the BP neural network by stacking multiple residual network modules, and fuses and expands gas feature information through an improved BP neural network. In the improved residual BP neural network, SVM is introduced to judge the extracted feature vectors at each layer, screen out feature vectors with high accuracy, and increase their weights. The feature vector with the highest cumulative weight is selected as an input for transformer fault diagnosis. This method utilizes multi-layer neural network mapping to extract gas feature information with more significant feature differences after fusion expansion, thereby effectively improving diagnostic accuracy. The experimental results show that, compared with traditional BP neural network methods, the proposed algorithm has higher accuracy in transformer fault diagnosis, with an accuracy rate of 92%, which can ensure the sustainable, normal, and safe operation of power grids.

Cluster analysis of carboniferous gas reservoirs and application of recovery prediction model

Since the discovery of the Carboniferous gas reservoirs in East Sichuan in 1977, after more than 40 years of development, most of the gas reservoirs have entered the middle and late stages of development. The gas reservoir is characterized by strong heterogeneity, large difference in permeability, and serious impact of water invasion in some blocks. Therefore, how to make a correct decision on gas field development and deployment is of vital importance. Combined with system clustering, BP neural network, correlation analysis and other methods, this paper first analyzes and calculates the static indicators of the Carboniferous gas reservoirs, and then divides the gas reservoirs into four categories using ward clustering method according to the calculated weight value, and determines the characteristics of each type of gas reservoirs using correlation coefficient analysis method. Finally, the recovery prediction model of each type of gas reservoir is established according to the BP neural network. The results indicate that: (1) The recovery rate prediction model can predict the trend of cumulative gas production changes, thereby obtaining the space for improving recovery rate, and the accuracy of the prediction results is high, which can be used as a reference for gas field planning. (2) The sub-active gas reservoirs with strong heterogeneous water bodies and the inactive gas reservoirs with low permeability water bodies have a certain space for enhanced oil recovery.

Identification of Key Production Factors in China's Environmental Protection Industry Based on Deep Learning

Analyzing from the micro level of the basic unit of environmental protection industry -- enterprise, this paper takes   relevant information of more than 8000 key enterprises in China's environmental protection industry from 2018 to 2020 as the big data training samples, and uses BP neural network method to identify the key production factors that have great impact on the output of the whole China's environmental protection industry and its main subdivisions. The results show that China's environmental protection industry is still in the growing stage in the current stage, with significant capital pulling, technological innovation driving, and management innovation also plays an important role. There are differences in the performance of water, air and solid waste in the environmental protection industry. In detail, R&D expenses from the government plays the most important role in water pollution prevention and control industry. Technology innovation plays the most important role in air pollution prevention and control industry. And staff play the most important role in solid waste treatment and resource recycling industry.

Risk Management of Supply Chain Green Finance Based on Sustainable Ecological Environment

Green supply chain finance is a new financing method that focuses on corporate restructuring and promotes corporate capital flow and the development of environmental protection. This paper used BP neural network technology to study the green financing of the supply chain under the sustainable ecological environment. The method played an important role in the trial. Due to the more uncertain factors faced and the more complex environment, the risks of green supply chain finance are more hidden, diverse, and complex. The BP neural network is relatively mature in both network theory and performance. Its outstanding advantages are its strong nonlinear mapping ability and flexible network structure. The positive effect of BP neural network on green financial risk management is verified by experiments. Green supply chain finance is an innovative model of green finance. This experiment studies the risk management of green finance in supply chain and the evaluation index of green finance risk management through BP neural network method, and shows that the evaluation results are highly scientific. In addition, based on the green supply chain model, the historical data of different regions provide a scientific basis for the sustainable ecological development of the region. This paper provides guidance for the sustainable development of green finance in the supply chain and makes contributions to promoting the development of green economy. In order to control the risks of supply chain financing business, the risks of supply chain financing business are classified and analyzed, and specific project risk levels and points are determined to propose control measures to ensure effective control of the business risks.

Modeling of Ship Turning Motion Prediction Based on BP Neural Network

To more correctly grasp the ship turning performance and provide better references for initial design and safe handling of the ship, combined with the ship turning motion characteristics, a simulation prediction model of the ship turning motion is created by using the BP neural network method, which takes the transverse and longitudinal distance of the ship turning motion as the output. Within that study, the neural network model is trained by utilizing 12 real ship motion data as training examples. This research generates predictions using data from two more real ships as test samples once the training is complete. The discrepancy between the estimated and real ship outcomes is also compared, and the error is examined. The results verify that the constructed prediction model has stronger generalization ability and better accuracy, indicating that the model can successfully realize the simulation prediction for the ship turning motion.

Evaluation and prediction of the safety management efficiency of coal enterprises based on a DEA-BP neural network

With the development of big data technology, big data have gradually become the main driving force of safety management. To effectively predict and evaluate the changes in the safety management efficiency of coal enterprises under big data technology, the model-driven DEA method and the data-driven BP neural network method are combined. A DEA-BP neural network hybrid-driven model, in which safety management efficiency is considered, is constructed for coal enterprise evaluation and prediction. The data of 20 coal enterprises from 2015 to 2020 are used for empirical research. The results indicate that the static analysis shows a fluctuating upwards trend in the level of safety management of coal enterprises. The dynamic analysis shows that the decline in the technical efficiency change is mainly caused by the decline in the pure technical efficiency change. In terms of improving safety management efficiency, coal enterprises mainly target a single aspect of technical progress efficiency, without realizing that the improvement of safety efficiency is the result of the combined effect of technical efficiency and technical progress efficiency. An accuracy of 90% can be achieved using the BP neural network prediction based on the addition of new indicators, demonstrating that the evaluation and prediction model has good adaptability.

Glass Classification and Identification based on K-means++ Clustering Analysis and BP Neural Network Method

The weathering caused by the burial environment will cause the ancient glass to exchange material with the environment, and the weathering layer produced by the material exchange will have an impact on the class judgment of ancient glass. In this paper, we analyze the classification rules of high potassium glass and lead-barium glass; select the appropriate chemical composition for subclass division and establish the classification model of glass. After this, a binary classification (high potassium/lead-barium) model is established by BP neural network training, and the subclassified main components of each type of glass derived from the classification model are used as adjustment variables to analyze the chemical composition of unknown categories of glass artifacts and identify the types to which they belong by controlling a single variable.

Supply Chain Finance Assistance for Small and Medium-Sized Enterprises Using Cognitive Web Services

When it comes to offering loans to small and medium-sized enterprises, the supply chain finance industries will produce cash flow and commodities (SMEs). The supply management is implemented with cognitive web service. Under the terms of information exchange, a credit risk assessment will be performed for supply chain finance with data analytics. In support vector machine technology, parameters are chosen using a genetic algorithm. To analyze the credit risk of support vector machines, a BP neural network was used to link the evolutionary algorithm with supply chain finance (GA-SVM-BPNN-SCF). Using a genetic algorithm and a support vector machine has overall classification accuracy equal to the BP neural network method. In addition, the role of the supply chain (SC) in mediating the link between SCF adoption, and the importance of supply chain effectiveness (SCE) is discussed. This research helps marketers and professionals better understand how to use SCF in their enterprises to reduce risk and improve SCF by providing data and connecting with financial institutions.

Retraction Note: Multi-level Dynamic Fuzzy Evaluation and BP Neural Network Method for Performance Evaluation of Chinese Private Enterprises

Retraction Note: Multi-level Dynamic Fuzzy Evaluation and BP Neural Network Method for Performance Evaluation of Chinese Private Enterprises

Short-term photovoltaic power generation power prediction method based on SOA-BP neural network

The size of photovoltaic power generation has a certain uncertainty, which affects the quality of photovoltaic power generation, and affects the safety and stable operation of the power grid. By predicting the photovoltaic power generation, this problem can be better solved. A photovoltaic power generation power prediction method combining SOA (Seagull optimization algorithm) and BP neural network is proposed. The convergence speed of BP neural network prediction model is relatively slow, and it is easy to fall into local optimum. Optimizing its weights and thresholds through SOA can improve these situations. Through experiments, Through experimental comparison, it is found that the BP neural network method optimized by seagull algorithm has higher accuracy in predicting photovoltaic power generation.

Analysis and Prediction of Regional Land Subsidence with InSAR Technology and Machine Learning Algorithm

As a worldwide environmental and geological disaster, land subsidence may cause serious harm to urban development. Therefore, the prediction of land subsidence is a key scientific problem. Decheng county, Shandong Province in China is taken as the research object. Based on BP neural network (BPNN) and random forest (RF) method, the analysis and prediction of regional land subsidence are carried out by applying multi-source monitoring data, Geographic Information System (GIS), and machine learning algorithm. Combined with Short Baseline Synthetic Aperture Interferometric Radar (SBAS-InSAR) and GIS technology, the spatiotemporal evolution characteristics of land subsidence from 2017 to 2020 are analyzed. The impact of different groundwater levels on land subsidence is quantitatively analyzed by BPNN and RF algorithm. The real-time prediction model of regional land subsidence is established. The results show that: 1) The area with the most serious land subsidence is located in Songguantun town, the maximum annual average subsidence rate is −40.71 mm/yr. 2) Land subsidence is mainly affected by deep groundwater and shallow groundwater in the research area. 3) The accuracy of the prediction results of the BPNN model is higher than that of the RF model when groundwater level change is used to predict land subsidence.

Retracted: Research on Modeling and Dynamic Characteristics of Complex Biological Neural Network Model considering BP Neural Network Method

Retracted: Research on Modeling and Dynamic Characteristics of Complex Biological Neural Network Model considering BP Neural Network Method

A New Mixed-Gas-Detection Method Based on a Support Vector Machine Optimized by a Sparrow Search Algorithm.

To solve the problem of the low recognition rate of mixed gases and consider the phenomenon of low prediction accuracy when traditional gas-concentration-prediction methods deal with nonlinear data, this paper proposes a mixed-gas identification and gas-concentration-prediction method based on a support vector machine (SVM) optimized by a sparrow search algorithm (SSA). Principal component analysis (PCA) is applied to perform data dimensionality reduction on the input data, and SSA is adopted to optimize the SVM hyperparameters to improve the recognition rate and gas-concentration-prediction accuracy of mixed gases. For the mixed-gas identification, the classification accuracy is significantly improved under the proposed SSA optimization SVM method (SSA-SVM), compared with random forest (RF), extreme-learning machine (ELM), and BP neural network methods. With respect to gas-concentration prediction, the maximum fitting degrees reached 99.34% for single gas-concentration prediction and 97.55% for mixed-gas-concentration prediction. The experimental results show that the SSA-SVM method had a high recognition rate and high concentration-prediction accuracy in gas-mixture detection.

Projected harmful algal bloom frequency in the Yangtze River Estuary and adjacent waters

Harmful algal blooms (HABs) are a frequent occurrence in China's offshore waters due to climate change and human activity, particularly in the Yangtze River Estuary and adjacent waters. Here, we studied HABs and their relationship with climatic and environmental factors in these waters from 1979 to 2016 using historical observations and reanalysis data. We then projected HABs frequency under various climate scenarios using the “environmental impact factor-frequency of HABs” mathematical model built using the BP neural network method and CIMP5 model data (RCP 2.6, RCP 4.5, and RCP 8.5). The results suggest a significant positive correlation between HABs frequency and seawater nutrient concentration, winter sea surface temperature, and low-wind days, and HABs frequency is anticipated to increase significantly by the 2040s compared with that of the historical era. Furthermore, future phytoplankton conditions are predicted to favor HAB species.

Reliability study on the fatigue life of film cooling blades in advanced aero-engine turbines: Neglected crystal orientation uncertainty in casting

The orientation uncertainty of single-crystal turbine blades is a neglected practical engineering problem, and previous research has paid little attention to it. The work innovatively presents the random distribution regularity of the spatial orientation formed in the casting of single crystal blades and its influence on the structural reliability, which establish a foundation for the orientation design of blades. In this work, the uncertain characteristics of the spatial orientation for single crystal cast blades are mathematically quantified. Meanwhile, based on the classical material constitutive and life equations, the elastic-plastic theoretical and fatigue life evaluation models related to orientation are deduced and firstly applied to turbine blade engineering analysis. The elastic-plastic stress distributions of single-crystal turbine blades considering thermal effects are obtained by the fluid-structure interaction simulation. The spatial orientation distribution characteristics is presented from analyzing hundreds of samples. Finally, the influence of the uncertain orientation on the low cycle fatigue life reliability and structural failure probability of single-crystal turbine blades are clarified for the first time by using the BP neural network and stepwise response method. Our results demonstrate that crystal orientation uncertainty, especially in long-life design, can cause a serious failure probability, proving the necessity of orientation control for single crystal turbine blades clearly.