Papers by Keyword: BP

Abstract: As an important part of the micro-grid, the energy storage devices are playing an important role to stabilize power and energy fluctuations of micro-grid system, improve the stability and schedulability of the system and the quality of electricity. All-Vanadium Redox Flow Battery (VRB) has been more and more used because of its advantages on environmentally friendly, long cycle life, safety and reliability, achieving economies of scale energy storage and so on. State of Charge (SOC) prediction is an important part to the Power Control System (PCS) and Energy Management System (EMS) of the energy storage devices. This paper established a SOC prediction model of VRB based on Elman Neural Network because Neural Network has the characteristics of non-linear and self-learning to simulate external characteristic of VRB which is a highly non-linear system. Then we trained the Elman Neural Network with the experimental data. The result shows that this method has a high accuracy. By contrast with the BP neural network, the prediction is better than Back Propagation (BP)Neural Network.

Abstract: Stereo matching methods are widely used in computer vision and stereo reconstruction, from the perspective of improving the matching accuracy, this paper focuses on the global optimization algorithm. An improved Belief Propagation method is proposed in this paper, by involving more pixels into information transmission, our method improves the accuracy ofstereo matching. The experimental results verify the efficiencyand reliability of our method.

Abstract: In the process of three-dimensional curved hull plate forming, springback caused serious influence on the forming accuracy, in order to ensure the forming quality of the asymmetric multiple pressure heads CNC bending machine of ship hull 3D surface plate, to achieve the automatic processing, it is necessary to solve the problem of springback in the hull plate forming process. It is rarely to see the research on the cold bending springback problem of middle-thickness hull plate now. To established nonlinear model of plate parameters and springback amount based on BP neural network, accurately analyzing the prediction of springback, and getting the sptringback prediction model based on the BP neural network in the Matlab programming.

Abstract: In order to overcome the defects and limitations of the application of HMM in voice recognition, neural network is introduced into voice recognition. Also the model theory of the neural network and its characteristics are also considered in the paper’s study which mainly focuses on the application of neural network in voice recognition. Based on studies of BP neural network, the paper establishes the voice recognition model and algorithm for the recognition of isolated words under MATLAB environment, and elaborates on the specific process of realization and the results of the simulation experiment.

Abstract: BP network is one of the most popular artificial neural networks because of its special advantage such as simple structure, distributed storage, parallel processing, high fault-tolerance performance, etc. However, with its extensive use in recent years, it is discovered that BP algorithm has the defects on slow convergent speed and easy convergence to a local minimum point. The paper proposes a method of BP Neural Network improved by Particle Swarm Optimization (PSO). The hybrid algorithm can not only avoid local minimum, but also raise the speed of network training and reduce the convergence time.

Abstract: A new approach to weapons and equipment effectiveness evaluation based on artificial neural network (ANN) performs better than traditional method, which is in view of the complex relationship between the effectiveness and many factors that influence the evaluation. The structure and learning algorithm of BP neural network is evaluated the fighters’ air-to-air combat capability. The evaluation is accomplished by a two-layer BP neural network and MATLAB toolbox. The simulation results show that the artificial neural network have better generalization ability and approximation performance for continuous function, which is valuable in weapons and equipment effectiveness evaluation application.

Abstract: The aim of this paper is to research the image recognition system and its applications, which is based on combining the traditional BP neural networks and the third-generation pulse coupled neural network (PCNN).The process is by extracting the image's time and entropy sequences, then through the fast Fourier transform, and finally as inputs of the pattern classification. In order to test the stability of the system, we make some varies by rotating, tension and compressing the original image, meanwhile, combined with the statistics of the entropy information to determine the time delay parameter of the pcnn, the recognition results is satisfactory.

Abstract: To reduce the prediction error rate of earthquake casualties, the paper proposed a prediction model with two steps: (1) screening of the earthquake casualties correlation factors; (2) improving the predictive veracity of general BP(Back Propagation) neural network model.By the analysis of 9 kinds of correlation factors, the paper established the MIV(Mean Impact Value) model based on BP neural network to screen the final correlation factors, and the paper got 6 main correlation factors according to the size of output weights of the factors. Finally, the paper verified the accuracy and practicability of the model through the validation of the model and the solving of prediction error of relevant factors hasn't been selected.

Abstract: This paper combined Rumelhart’s adding inertial impulse and dynamically adjusting the learning rate and proposed an improved algorithm to optimize the Back Propagation (BP) networks with applied technology. This improved BP networks is used to determining membership function and applied in fuzzy diagnosing vapor congealing equipment. The application results prove that the improved BP algorithm is effective and the convergence speed is accelerated and is much faster than the classic BP algorithm. The applied technology is very useful in the application course.

Abstract: Back Propagation network, Widely used in automatic control, image recognition, hydrological forecasting and water quality evaluation, etc., as one of the Artificial Neural Networks, has stronger property of mapping, classification, functional fitting. This article takes the water flow of Lanzhou section of Yellow river as example by use of BP model to predict the water flow. It is well proved that BP network model can reach the purposes of early warning and forecasting.