Improved BP Neural Network Algorithm Research Articles

Measurement and modeling of moisture equilibrium and methane adsorption in shales from the southern Sichuan Basin

The adsorption characteristic of methane in water-bearing shale is essential for the accurate estimation of shale gas reserves. The sorption mechanisms of moisture and methane in shale remain poorly understood. In this work, moisture equilibrium measurements in shales were conducted to study moisture absorption characteristics. The governing factors for moisture absorption were determined, and the suitability of moisture absorption models was evaluated. An innovative water saturation apparatus and an improved methane adsorption system were built to measure methane adsorption in high water-bearing shales. The suitability of the Langmuir model in describing methane adsorption in water-bearing shale was studied. A predictive model for methane adsorption in water-bearing shale was developed based on improved BP neural network algorithm, which was further utilized to determine the primary governing factors for methane adsorption. The results revealed that the equilibrated moisture content in shale presents a three-stage and S-type ascending trend with increasing relative humidity. The methane adsorption amount shows a slide-type downward trend with the increase of water content. The Peleg model demonstrates the superior performance in describing the hygroscopic isotherms, and the Langmuir model performs poorly in characterizing methane adsorption in shales with high water contents. The controlling factors for the ultimate moisture content mainly include specific surface area, average pore diameter, carbonate and pyrite content. The methane adsorption in water-bearing shale is mainly governed by water content and specific surface area. The results of this work enrich the understanding of the adsorption mechanisms of shale gas and provide a solid basis for the assessment of shale gas reserves.

Construction of Quality Evaluation System for Blended Physical Education Teaching in Colleges and Universities

Abstract The evaluation of the quality of blended physical education teaching in colleges and universities, as a part of the evaluation of university education, is of great significance in guiding the construction and development of blended physical education teaching. This paper examines the evaluation system for hybrid physical education teaching quality in colleges and universities using the principle of evaluation system construction. There are 4 primary indicators, 11 secondary indicators, and 31 tertiary indicators in the system. By using the fuzzy comprehensive evaluation method to calculate the weights of each level 1 index and level 2 index, the weights of each index are judged to account for the proportion. The improved BP neural network algorithm was used to score the indicators. Through empirical analysis, it was found that the weight share of teaching effect, teaching implementation, teaching background, and teaching implementation were 0.33, 0.27, 0.21, and 0.19, respectively, and the teaching effect accounted for the largest share. The total evaluation score was 3.9. The scores of each level indicator in descending order are teaching background (4.13), teaching implementation (4.07), teaching effect (4.05), and teaching setup (3.37). The quality of blended physical education teaching in Colleges and Universities of S is better from the overall point of view.

Improved BP neural network algorithm to SOC estimation of mine power supply

Since Ni MH battery has the characteristics of high energy density and good stability, it is mainly used as a backup power supply for mining at present, but the accuracy of estimation the SOC of the power supply is poor. To enhance the precision of estimation and extend the lifespan of the battery, based on a single nickel-hydrogen battery, this paper applies a new BP neural network to rise the self-adaption and momentum terms. At the same time, the discharged power is included in the Input feature quantity of the estimation network. The temperature, current and terminal voltage are also included in the input characteristic quantity of the estimation network. There is output during training, and then the momentum term is adjusted based on the Variance of variance error by comparing the actual output. The error of the estimated network should be back propagated from the output to the input to correct the weight. The direction of change in the error determines the adaptive learning rate of the improved BP neural network. The speed of the algorithm is increased by 72% and the error rate is less than 5%, compared to the traditional BP neural network algorithm.

Optimized Design of Large-Body Structure of Pile Driver Based on Particle Swarm Optimization Improved BP Neural Network

Optimization of the pile driver’s large-body structure is important to achieve the driver’s overall light weight. This paper studies the large-body structure of a hydraulic static pile driver. We used the APDL parametric design language provided by ANSYS to construct a geometric model of the large-body structure and performed a static analysis of the finite element model. Under the assumption that the strength and stiffness meet the design requirements, the optimization model was constructed with the thickness of each plate of the large-body structure as the design variable, the structural strength and stiffness as the constraints, and the minimum mass as the objective function. Finally, two optimization algorithms were used to solve the model, and the comparison of the two sets of solutions shows that the improved BP neural network algorithm based on the particle swarm optimization algorithm performs better. The optimized mass of the large-body structure was reduced from 82,556.1 kg to 65,046.15 kg, a mass reduction of 21%. The lightweight design of the pile driver was achieved.

Design of a prediction model based on improved BP neural network and particle swarm optimization for more accurate budget of biogas production

In order to accurately predict the daily gas production of large and medium-sized biogas projects, the improved BP neural network algorithm was used, and the PSO algorithm was introduced to optimize the parameters. According to the anaerobic fermentation mechanism and the actual engineering operation status, a prediction model was established with temperature, daily feed volume, NH3, TS concentration and pH value as input layer nodes, and daily biogas production as output layer nodes. The 116 sets of data obtained by remote data acquisition are used as training samples and test samples of the model, and the simulation is carried out by Matlab software. The results show that the PSO-LM-BP neural network has good predictive ability for the daily gas production of biogas. The established biogas daily gas production prediction model not only converges fast but also has high accuracy.

Research on macroeconomic Forecasting model based on grey theory

In the modern economic innovation and development, the grey theory and BP neural network algorithm are used to build a new macroeconomic prediction model. On the one hand, the input data can be comprehensively preprocessed, on the other hand, the improved BP neural network algorithm can be used to predict the final results. This paper studies the feasibility and effectiveness of the new macroeconomic forecasting model based on the grey forecasting principle and BP neural network algorithm. The final results show that both grey prediction and BP algorithm can help the staff to predict and analyze the macro economy as soon as possible, so as to grasp more valuable data information and put forward targeted management decisions.

Research on macroeconomic Forecasting model based on grey theory

In the modern economic innovation and development, the grey theory and BP neural network algorithm are used to build a new macroeconomic prediction model. On the one hand, the input data can be comprehensively preprocessed, on the other hand, the improved BP neural network algorithm can be used to predict the final results. This paper studies the feasibility and effectiveness of the new macroeconomic forecasting model based on the grey forecasting principle and BP neural network algorithm. The final results show that both grey prediction and BP algorithm can help the staff to predict and analyze the macro economy as soon as possible, so as to grasp more valuable data information and put forward targeted management decisions.

A BP Neural Network Algorithm for Multimedia Data Monitoring of Air Particulate Matter.

In order to study a BP neural network algorithm for air particulate matter data monitoring, firstly, the monitoring data collected by particle sensor using the light scattering method are proposed. Then, based on the improved BP neural network method, the mapping relationship between the actual measured value of the sensor, weather and other influencing factors, and the standard value of the monitoring station is established, and the calibration model of air particulate matter is realized. Finally, through theoretical analysis and experimental comparison, the results show that the model based on BP neural network algorithm has good accuracy and generalization ability in the evaluation of air particulate index, which makes it possible to scientifically and accurately refine the evaluation and management of urban air particulate index. The experimental results show that the air particle calibration model based on the light scattering method and improved BP neural network algorithm is practical and effective.

Leakage Diagnosis of Air Conditioning Water System Networks Based on an Improved BP Neural Network Algorithm

Compared with traditional pipe networks, the complexity of air conditioning water systems (ACWSs) and the alternation of cooling and heating are more likely to cause pipe network leakage. Pipe leakage failure seriously affects the reliability of the air conditioning system, and can cause energy waste or reduce human comfort. In this study, a two-stage leakage fault diagnosis (LFD) method based on an Adam optimization BP neural network algorithm, which locates leakage faults based on the change values of monitoring data from flow meters and pressure sensors in air conditioning water systems, is proposed. In the proposed LFD method, firstly, the ACWS network’s hydraulic model is built on the Dymola platform. At the same time, a cuckoo algorithm is used to identify the pipe network’s characteristics to modify the model, and the experimental results show that the relative error between the model-simulated value and the actual values is no more than 1.5%. Secondly, all possible leakage conditions in the network are simulated by the model, and the dataset is formed according to the change rate of the observed data, and is then used to train the LFD model. The proposed LFD method is verified in a practical project, where the average accuracy of the first-stage LFD model in locating the leaking pipe is 86.96%; The average R2 of the second-stage LFD model is 0.9028, and the average error between the predicted location and its exact location with the second-stage LFD model is 6.3% of the total length of the leaking pipe. The results show that the proposed method provides a feasible and convenient solution for timely and accurate detection of pipe network leakage faults in air conditioning water systems.

Fault Diagnosis of Automobile Engine Based on Improved BP Neutral Network

With the continuous enrichment of automobile functions and the complexity of automobile structure, the difficulty of automobile fault diagnosis is constantly increasing. The study of fault diagnosis methods with high real-time performance, accuracy, and predictability is of great significance to improve automobile safety performance and ensure driving safety. Since the convergence speed of the traditional BP neural network algorithm is slow and the accuracy is insufficient in the process of automobile engine fault diagnosis, this paper improves convergence speed of the algorithm by introducing the momentum term, and the weights and thresholds of the neural network are optimized by using GA selection, crossover, and genetic characteristics, to propose a genetic algorithm (GA) optimization BP neural network fault diagnosis method. The average absolute error of the traditional BP neural network algorithm is 0.5976, while the average absolute error of the improved BP neural network algorithm in this paper is 0.1027. The comparative simulation results show that the proposed improved algorithm is better than the traditional BP neural network algorithm in diagnosis precision, accuracy, and other key indicators.

Analysis of Winning Experience and Technical Training Effect of Badminton Match Based on BP Neural Network.

The success or failure of badminton competition often depends on the training level of technical, physical, tactical, and psychological quality, as well as the competitive ability to comprehensively use these factors in the competition. Aiming at the improvement of the BP neural network algorithm, the improved BP neural network algorithm is used to analyze the multidimensional attributes of the collected data, and the simulation experiment is carried out to find out our competitive advantages and disadvantages. This paper presents a statistical study on the change of service area, the application of service receiving technology, and the treatment of the third stroke technology in the badminton competition. The innovative contribution of this paper is to explore the differences of double service decision-making of badminton at different levels and form a theoretical mechanism analysis system. The research shows that the relationship between active and passive attack and hitting quality has been dealt with in the game. In training, mastering the basic technical movements of badminton is conducive to improving the technical level of badminton.

THE USE OF NONLINEAR DYNAMIC SYSTEM AND DEEP LEARNING IN PRODUCTION CONDITION MONITORING AND PRODUCT QUALITY PREDICTION

To improve the product quality and production efficiency in industrial production, the industrial production process is explored. First, for the production state in industrial production, the radio frequency identification technology (RFID) is used to monitor the state of the nodes in the production process and collect data. Based on the problem of blind area in industrial production, an adaptive controller design based on uncertain nonlinear dynamic systems is introduced; second, based on this, for the problem that product quality is difficult to guarantee in the process flow, the improved multi-layer feedforward network (back propagation, BP) algorithm is used to predict it. Finally, the control diagnosis algorithm based on multi-order least squares support vector machine (LS-SVM) is used to analyze the abnormal cause of the product. The results show that the use of the RFID can monitor the production process in real time and obtain real-time product quality information data. The proposed adaptive controller based on uncertain nonlinear dynamic system has good applicability in solving the problem of blind area. The improved BP neural network algorithm improves the prediction accuracy in the process of product quality prediction and increases the convergence speed of the algorithm. The control diagnosis algorithm based on multi-order least squares that support vector machine (SVM) can classify and learn the historical data of products, as well as perform multi-order search and analysis on the causes of abnormal quality. It helps relevant personnel to carry out process improvement and control, thereby achieving the purpose of improving product quality. Through this investigation, it is found that the method proposed can monitor the state of industrial production in real time and help relevant personnel to control and predict product quality. It can be applied in actual processes.

Analysis of Human Resource Allocation Model for Tourism Industry Based on Improved BP Neural Network

This paper analyzes the deficiencies of human resource allocation in the tourism industry by investigating the human resource allocation in the tourism industry, puts forward corresponding improvement measures and suggestions, and strives to provide certain guidance and helpful effects for the construction of tourism resource informatization. In this paper, a modified BP neural network model is proposed by introducing random perturbation terms on the hidden layer in the BP neural network algorithm, and the weight matrix connecting the input values is added with the random perturbation matrix to obtain a new weight matrix so that the convergence effect of the improved BP neural network algorithm is improved. Then, to address the problem that the initial weights of the long and short‐term memory neural network and gated BP unit neural network have a large impact on the convergence speed and prediction accuracy of the algorithm after the initial weight selection is determined, this paper introduces the random perturbation term into the gate structure of the long and short‐term memory neural network and gated BP unit neural network and proposes and connects an improved long and short‐term memory neural network and gated BP unit neural network. The weight matrix of the input values is added with the random perturbation matrix to obtain the new weight matrix so that the convergence effect of the improved long and short‐term memory neural network algorithm and the gated BP unit neural network algorithm is improved. Constructing the human resource allocation model of the tourism industry and proposing coping strategies and countermeasures and taking the human resource allocation system of the tourism industry as the core, the human resource allocation model of the tourism industry is established by combining the network image crisis life cycle system of tourism scenic spots and the network public opinion dissemination model. From the perspective of managers, the human resource allocation management policy and management procedures of the tourism industry are proposed. Using the quantifiable and disenable characteristics of online text information, the response strategy of online monitoring and propaganda and offline management and enhancement is proposed, and innovative countermeasures to the human resource allocation of the tourism industry are proposed in three categories: network originated, reality coexisting, and reality originated. Through this paper, we propose a new approach to human resource allocation management and development in the tourism industry and improve the efficiency of human resource allocation in the tourism industry.

Entrepreneurial Mentality Analysis for College Students Based on the Improved BP Neural Network.

In this study, the fuzzy comprehensive evaluation model is used to evaluate the characteristics of college students' entrepreneurial psychology, and a prediction model of college students' entrepreneurial psychology characteristics is established, which is simulated by Matlab to achieve good validity. Based on the research on the characteristics of college students' entrepreneurial psychology, this study proposes a design method of indicators and parameters for evaluating the characteristics of college students' entrepreneurial psychology. In this study, the genetic algorithm is used to optimize the BP neural network. The optimized neural network greatly improves the global search and local search capabilities. The performance of the model is tested through simulation tests. Through the simulation comparison test between the improved model and the standard model, the results show that the model can predict the entrepreneurial psychological characteristics of college students. By comparing the improved BP neural network algorithm with the original algorithm simulation experiment, the improved BP neural network improves the sensitivity by 20%, the specificity by 5%, and the accuracy by 8%.

An Improved BP Neural Network Algorithm for Prediction of Roadway Support

Based on the engineering practice and the research and analysis of the knowledge in the field of roadway support, the paper puts forward to use an improved BP neural network to study the supporting types by the investigation, and obtained the related factors of the supporting types of the mining roadway and the successful reinforcement cases of the roadway. The proposed algorithm is applied to the prediction of coal roadway support parameters, and the main influencing factors of coal roadway support design are determined. From the typical engineering cases of roadway support collected on site as neural network training samples, the forecasting model of support parameters is established. Through the experimental data and simulation results, it can be seen that both the error convergence process and results of convergence speed, convergence accuracy and support types are ideal, the prediction error is within the allowable range, and the prediction accuracy is high, which verifies the reliability of this method and provides a new research idea and good application value for the study of support types of mining roadway.

Image Recognition and Simulation Based on Distributed Artificial Intelligence

This paper studies the traditional target classification and recognition algorithm based on Histogram of Oriented Gradients (HOG) feature extraction and Support Vector Machine (SVM) classification and applies this algorithm to distributed artificial intelligence image recognition. Due to the huge number of images, the general detection speed cannot meet the requirements. We have improved the HOG feature extraction algorithm. Using principal component analysis (PCA) to perform dimensionality reduction operations on HOG features and doing distributed artificial intelligence image recognition experiments, the results show that the image detection efficiency is slightly improved, and the detection speed is also improved. This article analyzes the reason for these changes because PCA mainly uses the useful feature information in HOG features. The parallelization processing of HOG features on graphics processing unit (GPU) is studied. GPU is used for high parallel and high-density calculations, and the calculation of HOG features is very complicated. Using GPU for parallelization of HOG features can make the calculation speed of HOG features improved. We use image experiments for the parallelized HOG feature algorithm. Experimental simulations show that the speed of distributed artificial intelligence image recognition is greatly improved. By analyzing the existing digital image recognition methods, an improved BP neural network algorithm is proposed. Under the premise of ensuring accuracy, the recognition speed of digital images is accelerated, the time required for recognition is reduced, real-time performance is guaranteed, and the effectiveness of the algorithm is verified.

Prediction of drilling force for high volume fraction SiCp/Al composite based on neural network

High volume fraction SiCp/Al composite is an important particle reinforced composite material, which is widely used in the aerospace and automotive fields. Drilling is a common processing method of SiCp/Al composite. It is of great significance to study the prediction of drilling force to improve the drilling efficiency and optimize the drilling parameters. In this paper, a high-volume fraction SiCp/Al composite drilling experiment was designed to obtain the drilling force at different drill rotational speed and feed rate. The improved BP neural network algorithm was used to predict the drilling force. The result shows that the predicted drilling force based on the improved neural network algorithm is consistent with the experimental drilling force, and the prediction model has high prediction accuracy. This study lays a good foundation for further research on tool wear and control of drilling surface quality.

Study of online learning resource recommendation based on improved BP neural network

Personalised recommendation has gradually become an effective way to solve the problem of information overload in the era of big data. Therefore, in order to improve the efficiency of online learning, this paper discusses the design of online learning resource recommendation algorithm based on improved BP neural network, and the results show that it has high value for popularisation and application. Based on the transmission network, the improved BP neural network of momentum factor can achieve more efficient data mining. After training learning resources and user data, it can match the real score and the predicted score, so as to ensure the accuracy of personalised recommendation. The main contribution of this paper is to propose a recommendation algorithm to online learning resources through improved BP neural network algorithm, and the feasibility of the algorithm is verified. The research method of this paper provides a reference for the research of personalised recommendation algorithm of online resources.

Study of online learning resource recommendation based on improved BP neural network

Personalised recommendation has gradually become an effective way to solve the problem of information overload in the era of big data. Therefore, in order to improve the efficiency of online learning, this paper discusses the design of online learning resource recommendation algorithm based on improved BP neural network, and the results show that it has high value for popularisation and application. Based on the transmission network, the improved BP neural network of momentum factor can achieve more efficient data mining. After training learning resources and user data, it can match the real score and the predicted score, so as to ensure the accuracy of personalised recommendation. The main contribution of this paper is to propose a recommendation algorithm to online learning resources through improved BP neural network algorithm, and the feasibility of the algorithm is verified. The research method of this paper provides a reference for the research of personalised recommendation algorithm of online resources.

Application of an improved BP neural network algorithm in intrusion detection

Based on the analysis of the existing problems of BP neural network used in the detection system, on the basis of the traditional BP algorithm, the automatic variable rate learning method is adopted, the forgetting factor and random optimization operator are introduced, and they are used in the network intrusion detection system. The simulation results show that the improved BP neural network algorithm is fast and easy to converge. The algorithm effectively improves the detection rate, reduces the false positive rate and false negative rate, and has obvious advantages.