Improved BP Neural Network Algorithm Research Articles

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.

SOC Estimation of Mine Power Supply Based on Improved BP Neural Network Algorithm

Ni-MH, with high electric energy density and high stability, is the main backup battery of mine power supply. To improve the estimation accuracy of battery SOC (state of charge) and prolong its service life, this paper takes the single Ni-MH battery as the experimental object, and adopts an improved BP neural network that adds an adaptive rate momentum term to increase the discharged amount of electricity. The input characteristics of the network are the same as temperature, current and terminal voltage. According to the variance of the error between the expected output and the actual output of the training sample, the momentum term is adjusted; The adaptive learning rate is increased according to the change direction of the back propagation error. By comparing the standard BP neural network algorithm, the convergence speed is increased by 70%, and the generalization error is within 4%.

Prediction of Regional Economic Trend with f Improved BP Neural Network Algorithm

Traditional BP neural network-based prediction method cannot accurately predictregional economic trend, and the operation efficiency is low. To this end, a method based on improved BP neural network algorithm is developed to predict regional economic trend. The Cobb-Douglas production function is used to select the most influential number of working people and economic investment in fixed assets, fiscal expenditure, gross foreign export value, retail sales of social consumer goods index as the sample data and normalized. The error of sample data is calculated by TangXC_BPModel model, and the the weights are modified uniformly so that and the regional economic trend is predicted accurately.

Optimal Trajectory Planning of Electromagnetic Valve-Train Based on Multiple Algorithms for Improving Engine Performance

Electromagnetic valve-train (EMVT) is a camless variable valve technology that can adjust the valve movement state independently, continuously and in real time. It can adjust the engine charge efficiency according to engine working conditions. In this paper, in order to achieve the optimal inflation efficiency, a new-style moving-coil electromagnetic linear actuator (ELA) was designed and genetic algorithm (GA) was used to plan the valve motion trajectory in common working conditions. Furthermore, an improved BP neural network algorithm was used to optimize the valve operation mode in all working conditions. The new valve operation scheme was applied to the modified intake system of engine, and its simulation and test analysis were carried out. Compared with the prototype, the results showed that the charging efficiency was greatly improved in the range of full rotating speed, especially in the range of middle and low rotating speed up to 95.6%.

Learning perception prediction and English hierarchical model based on neural network algorithm

The traditional English examination and the current examination system have been unable to meet the needs of the education industry for English examinations. In view of this, based on the neural network algorithm, this study proposes a hierarchical network management model from the user’s perspective. Based on the in-depth study of the neural network, this study combined with the network performance characteristics of large data volume, complex data to propose a new BP neural network algorithm. By dynamically changing the momentum factor and learning rate, the algorithm has greatly improved the accuracy and stability of the error. In addition, this study proposes a user perception prediction model, and the model is continuously trained on the model based on the improved BP neural network algorithm and the monitored network performance. In order to study the performance of the research model, a control experiment is designed to analyze the performance of the model. The research results show that the intelligent model and algorithm proposed in this paper are completely feasible and effective.

Discussion on the prediction of engineering cost based on improved BP neural network algorithm

Discussion on the prediction of engineering cost based on improved BP neural network algorithm

Vehicle License Plate Recognition Based on Wavelet Transform and Vertical Edge Matching

With the improvement of our country’s economic level and quality of life, the numbers and scales of highway networks and motor vehicles are constantly expanding, which makes the current road traffic burden more and more serious. As an important means of traffic automation management, license plate recognition (LPR) technology plays an important role in traffic surveillance and control. However, the recognition rate and accuracy of the traditional license plate recognition methods still need to be improved. In the case of poor surrounding environment, it is prone to localization failure, vehicle license plate recognition errors or unrecognizable phenomena. Wavelet transform, as another landmark signal processing method after Fourier transform, has been widely used in the field of image processing. In China, the number of horizontal lines is usually larger than that of vertical lines. If the two vertical boundaries of the license plate can be detected successfully, the four angles of the license plate can be determined efficiently to complete the license plate positioning. In view of the advantages of wavelet transform technology and the characteristics of vehicle license plate, in this paper, a vehicle license plate recognition algorithm based on wavelet transform and vertical edge matching is proposed. The edge of the license plate is detected by wavelet transform technology, and then the license plate is located by vertical edge matching technology. After the location is realized, the characters are segmented by vertical projection method and the characters are recognized by improved BP neural network algorithm. The experimental results show that the proposed vehicle license plate recognition algorithm based on wavelet transform and vertical edge matching performs well in algorithm performance, which provides a good reference for the development of vehicle license plate recognition system.

Electric Energy Substitution Potential Prediction Based on Logistic Curve Fitting and Improved BP Neural Network Algorithm

In order to predict the potential of electric energy substitution in the next decade in China, this paper proposes a prediction method based on Logistic curve fitting and improved BP neural network algorithm. The amount of electric energy substitution is defined to quantify the potential of electric energy substitution. Then the important influencing factors of electric energy substitution based on the Impact by Population, Affluence and Technology (IPAT) model are established and quantified. For different influencing factors, logistic curve fitting and polynomial function fitting method were used to estimate the data fitting. A two-node output layer model of BP neural network is established and improved with additional momentum factors and adaptive learning rate to learn and train the data related to electric energy substitution from 2003 to 2017, and calculate the amount of electric energy substitution which are substitution potential from 2018 to 2020, 2025 and 2030. The calculation results show that the method has higher computational accuracy and fewer iterations. The prediction results are reasonable and effective, which can be the reference of the research of energy substitution.

Research on fault diagnosis of B737 aircraft fuel system based on improved BP neural network

In this paper, an improved BP neural network algorithm is applied to the fault diagnosis of aircraft fuel system. The simulation results show that the algorithm has the characteristics of fast diagnosis speed and low misdiagnosis rate, and lays a foundation for the development of aircraft fuel fault diagnosis expert system based on neural network.

Recognition and Analysis of Motor Imagery EEG Signal Based on Improved BP Neural Network

With the rapid development of neuroinformatics and related intelligent algorithms, the research of recognition and classification based on EEG signals is becoming more and more important and valuable. With the progress of science and technology, the related research of EEG signal recognition and processing has been gradually applied to rehabilitation medicine, intelligent information processing, and other cross-cutting fields. As one of the most important research directions in the field of the brain-computer interface, motor imagery EEG has a wide range of applications. At the same time, it shows a good application effect in the process of application practice. At present, the main EEG recognition and analysis algorithms always have some problems and defects in data processing, such as low signal-to-noise ratio, unclean noise filtering, and high data dimension. In this paper, based on the improved BP neural network algorithm, weight splitting technology is added to the traditional BP neural network algorithm. In order to solve the filtering problem, this paper uses the non-linear mapping function of the traditional BP neural network, and intelligently trains the small weight particles by combining the particle swarm filter algorithm, so as to improve the filtering performance of the whole BP algorithm. Based on the above two algorithms, the problem of low signal-to-noise ratio (SNR) and unclean filtering in EEG data processing caused by fast weight degradation in traditional BP algorithm can be solved. Finally, according to the actual data of brain-computer interface, this paper compares the improved BP neural network algorithm with the traditional BP neural network algorithm in recognition and analysis of motor imagery EEG signals. The experiment shows that the proposed algorithm has obvious advantages in recognition accuracy and analysis effect.

Intelligent Flood Disaster Forecasting Based on Improved Neural Network Algorithm

Based on the existing researches, and in combination with the knowledge of artificial intelligence, management decision science, and theoretical derivation, this study constructs a flood forecasting model based on the improved neural network algorithm, applies it to flood forecasting and flood damage assessment, proposes a flood decision support system consisting of external conversion layer, information processing application layer and database layer, and optimizes BP neural system in view of its defects of slow convergence speed and long iteration time by genetic algorithm. The actual forecasting results show that the improved BP neural network proposed in this study has higher forecasting accuracy, and the correlation coefficient between forecasting results and actual monitoring results reaches 96%, far exceeding the forecasting accuracy of RBF neural network algorithm (68%), which proves the feasibility and rapidity of the proposed algorithm. The improved BP neural network algorithm is used for rapid flood disaster assessment, and the needs of flood disaster assessment in different stages are specifically analyzed. In terms of accuracy, the RBF algorithm's disaster assessment grades are relatively small, and the assessment effect using the algorithm proposed in this paper is the best.

SoC Estimation of Lithium Battery Based on Improved BP Neural Network

Lithium iron phosphate battery as the research object, in view of the traditional battery state of charge (SoC) estimate methodological shortcomings and deficiencies, combined with battery charge and discharge characteristics. This paper presents an improved BP neural network algorithm which can significantly reduce the SoC prediction error of the lithium iron phosphate battery. Through a lot of experiments, the improved training function is put forward in this paper. Comparing the SoC value of the lithium battery and the actual SoC value estimated by the neural network, the effectiveness of the algorithm is proved. Research results show that the consumption of the algorithm to the real-time measurement of voltage, current and temperature value and the internal resistance value as input to learn lithium battery power remaining, with estimated speed, wide application range and prediction error is small, the engineering easy to achieve, can effectively solve the prediction problem of the state of charge (SoC) of the lithium batteries for electric vehicles.

Modeling and optimization of polysaccharide precipitation of traditional Chinese medicine injection

This study investigates Ophiopogon japonicas, a traditional Chinese medicine, by establishing the process model of polysaccharide precipitation based on a neural network algorithm. First, the principle of the BP neural network and the selection method of the model parameters are discussed, and the improved BP neural network algorithm is proposed. Then, the BP neural network model based on the population genetic algorithm (PGA) is established by analyzing the precipitation process of Ophiopogon japonicus polysaccharide. The weights and thresholds are trained and optimized to improve the precision of the polysaccharide precipitation model. Finally, the effect of the algorithm is illustrated by numerical simulation, and the simulation results are analyzed. This work lays the foundation for the future control system design.

Inventory Prediction Research based on the Improved BP Neural Network Algorithm

Since the idea of the supply chain management is proposed, many enterprises have attached great importance to the supply chain management and pay a lot of manpower and resources to study. It is also the focus to study the inventory in the field of the supply chain. Quantity of the inventory is not only related to the profit of the enterprises, but also related to the survival of the entire supply chain. Predicting the inventory can improve the ability of enterprises to prevent risk, increase the profits and reduce the losses. In order to predict better on inventory, we propose an improved BP neural network algorithm. In the algorithm, we use the improved GSA algorithm to optimize the parameters of BP neural network algorithm and improve the BP neural network algorithm aiming at its deficiency. The experimental results show that this method has good prediction effect.

Research on Food Demand Prediction Algorithm Based on Supply Chain Management

An improved BP neural network algorithm for food demand prediction based on supply chain management is presented to realize market and sale management target effectively for food enterprises. First, the working principle of BP neural network algorithm is analyzed to explore the root reasons of its low convergence speed; Second, the paper integrates genetic algorithm with BP algorithm to present a new algorithm, then improves it through encoding chromosome, formatting fitness function, designing selection operator, redesigning crossover operator, designing mutation operator, integrating BP algorithm and optimal individual, improving calculation process step by step; Finally, a supply chain of a food enterprise is taken for experimental sample to illustrate the calculation performance of the improved algorithm and the simulation results indicate that the improved algorithm not only can solve the problem of low convergence speed, but also can improve the demand prediction accuracy and can be used for predicting supply chain demand for food enterprises practically.

Application of Improved BP Neural Network Algorithm in Data Mining Research

With the development of network technology, the data capacity become more abundant. How to effectively manage the data, the retrieval more quickly, accurately, improve the data classification accuracy becomes crucial. The BP neural network algorithm with its learning speed, strong ability to adapt and is widely used in network in data mining. Exist but its convergence rate is not high and big error and other shortcomings, therefore, on the basis of traditional algorithm, an improved BP neural network algorithm is put forward. Low error, through experimental analysis, the improved algorithm convergence rate is better.

Application of Improved Neural Network Algorithm in Image Denoising and Edge Detection

The knowledge involved in digital image processing is very wide, and there are many kinds of methods. Traditional image processing technology is mainly focused on the acquisition, transformation, enhancement, restoration, compression encoding, segmentation, edge extraction and so on. With the emergence of new tools and new methods, the image processing technology has been updated and developed. In this paper, an effective method for edge detection and image de-noising is proposed. In this article, the impulse noise detector is composed of a BP neural network (BPNN) and a decision switch. BPNN requires four input values, which are the current pixel value, grey median value, energy value, and contrast. To take these four values as the input values, the impulse noise detector can show good performance. The output of the BPNN is transferred to the decision switch, and the output value is converted to 0 or 1, which is used to distinguish whether the pixels are polluted. At this point, we introduce an additional impulse term and establish the improved BPNN model. The additional impulse term can effectively speed up the convergence of the network, avoid the emergence of the local minimum problem, and ensure the stability of the training process. In this way, the IBPNN filter of this paper only uses the information of the non polluted pixels to filter the noise pixels, which avoids the secondary pollution, and obtains a better performance. This algorithm has high PSNR value and strong detail information and edge preserving ability. Finally, the improved BPNN algorithm is applied to the image edge detection, and we use the improved neural network model to detect the edge of the image. Because the method can be used to include the prior knowledge, the IBPNN method is better than the traditional method in image edge detection.

Research on the process optimization model of micro-clearance electrolysis-assisted laser machining based on BP neural network and ant colony

A new technology of micro-clearance electrolysis-assisted laser machining is presented in this thesis. Laser thermal effects and electrolytic corrosion can etch materials with a time division; thus, the recast layer produced by laser machining is effectively removed and the machining quality is improved. Methods like high-frequency pulse power supply, side wall insulating tubular electrode, and acidic composite electrolyte are applied to improve machining precision in the electrolytic machining. Considering the cooling effects of electrolyte fluid and the influences of uneven distribution of electrolyte conductivity, the experiment of micro-clearance electrolysis-assisted laser machining is designed and improved BP neural network algorithm is adopted to predict experiment results accurately and efficiently. Regarding the maximum material removal rate as optimization objective, the process optimization model based on improved ant colony algorithm is built; thus, the optimal experiment scheme can be found out efficiently. The experimental results demonstrate that micro-clearance electrolysis-assisted laser machining, which meets the technical requirements, can remove the recast layer in the hole wall effectively and the machining efficiency and the machining precision of that increase more than 20 and 18 %, respectively, compared to electrolytic machining.

Application of Improved BP Neural Network with Correlation Rules in Network Intrusion Detection

To detect various network attacks in real time, this paper developed a network intrusion detection system based on artificial neural network. This paper first introduced the recent development of neural network, BP algorithm and structure of a simple perceptron. Then, this paper developed an improved BP neural network algorithm to detect anomaly network traffic with adjusted correlation rules. Finally, the network intrusion system in this paper was tested in a real network situation; the improved BP algorithm neural network with adjusted correlation rules shows a reduction in total error and increment in alarm rate compared to the traditional basic BP algorithm model.

Data Mining Model Based on the Improved BP Neural Network Algorithm

A data mining algorithm based on fuzzy FKM algorithm and BP was proposed to solve the problem of long training time and low efficiency when the sample data contains the attributes unrelated to target data. The attributes of in- put data was clustered by using FKM clustering algorithm, and the attributes with weak correlation to target data were abandoned, and then there remain the attributes with strong correlation to target data, which reduce the training samples of neural network, and improving the training efficiency of the network. Tests on forecasting the content of Hemoglobin in the body of children show that the proposed algorithm is very practicable and reliable.