Papers by Keyword: BP Network

Abstract: The output of pressure sensor is affected by non-objection parameters in its application, its defect is the sensitivity to temperature. The method of the data fusion from the two sensors based on BP network can eliminate the side effect of temperatures and improve the accuracy and reliability for the pressure sensors. This method based on Levenberg-Marquardt algorithm of BP network has not only a simple network structure, but also a quick learning rate, showing a better prospect.

Abstract: In recent years, many approaches were proposed to deal with the settlement prediction problem. However, because of the complexity of geography and other conditions, the current solutions still have some deficiencies and do not work well. To improve the accuracy of settlement prediction, the authors of this paper propose an extended BP network-based approach. This method first designed the model of BP network according to the dataset. This network includes one input layer, one output layer, one middle layer and an extended middle layer. After trained by samples, this network is used to predict the settlement value. The experiment indicates that our approach is available and work well in most situations.

Abstract: The hydrological forecasting model are established respectively by the traditional method and the new methods, BP network and projection pursuit, in order to study the feasibility and practicality. The result shows that the accuracy of the BP model is within 10%, has better forecasting effect and more practical value than the others.

Abstract: BP neural network has parallel processing capabilities and a good approximation of the nonlinear mapping and gradually been widely used in the forecast. Because it is difficult to determine the BP neural network structural model, this paper presents the design ideas from six aspects. Combined with the practical example-mushroom classification, this paper presents the affect of the hidden layer, learning rate, training function on BP network and has some practical significance.

Abstract: To solve the problem of design and manufacturing on the production of many varieties of small batch, the parts grouping method that based on clustering algorithm, clustering validity index and BP neural network method for new parts is proposed. At first, mathematical model of part clustering is built, and parts grouping is based on the similarity of data and cluster centers which is calculated by Euclidean distance, then the effectiveness of parts group is tested by Function Index and optimal number of clusters group can be found. The algorithm is achieved by Matlab clustering toolbox, so the best part family structure is built. Furthermore, the grouped parts are used to train the BP neural network toolbox in Matlab, then simulate new parts on network to find the match group. At last, a case study was also presented to verify the feasibility of this method．

Abstract: Aiming to the layout structure design and performance prediction for globoidal cam machine, a dynamic performance prediction method for machine layout structure is proposed in this paper. With the method, the motion transmission and layout structure are determined based on the mapping rules between function and structure. The prediction model for dynamic performance is established based on BP neural network, which is used to optimize the dynamic performance of layout structure for globoibal cam machine.

Abstract: Aimed at the problem in the gun barrel life prediction, a method of gun barrel life prediction based on record of firing was pointed out. On the basis of internal trajectory resolving, the equivalent life transform coefficient for gun barrel based on the overall heat in origin of rifling and the overall gun pressure was computed. And by assuming we wore gun barrel life in canonical record of firing, a conversion model between the equivalent life transform coefficient for gun barrel and variety of record of firing which could be used to realize the gun barrel life prediction was built by using BP network.

Abstract: Preventing tramcar accidents is very important in the production of the coal mine. In this paper, S7-200PLC and BP neural network are used to design a intelligent flexible anti-running system. The control system adopts normally closed and flexible bufferred barrier. Following is the simulation experiment scheme. The BP neural network is adopted to eliminate the influence of temperature and filter by photo-electric coupler, which can measure the accurate and reliable tramcar speed. If the speed is faster than set point, the system will give an alarm and barrier does not work ,which stops the harvesters continuing running. This method guarantees the safe operation of coal mine.

Abstract: In order to study the feasibility and practicality, the hydrological forecasting model are established respectively by the traditional method and the new methods, BP network and projection pursuit. The result shows that the accuracy of the BP model is within 10%, has better forecasting effect and more practical value than the others.

Abstract: A new structure of 6-RSPS simulator platform which can be rotated infinitely is presented. The solution of direct kinematics problem of parallel structure is the fundamental problem. For the solution of this problem, according to the links vector diagram, the relationship of the position and orientation of the platform between the length of links and the rotate angle of the under-hinge is derived. BP network is applied, then using the previous data obtained by inverse kinematics as the training data and testing data of BP network, the direct kinematics solution is obtained. Simulation results verified that the solution of direct kinematics applied the BP network can be meet the requirements completely and the error percentages are within the acceptable range.