| The appearance and development of vehicle promoted anthropic civilization,but it has been become the chief criminal about the power and circumstance's pollution of the world.From the 1980,with the attention on more badly pollution and the scarcity of energy, the new technology of power electronic,micro-electronics,electronic machine as well as it's driven technique and new material's swift and violent development help the electric vehicle renewedly to obtain people's attention. Accordingly the zero-voidance Act of Cal. USA promote the recognition. With the development of the science and technology and deeper research of the HEV ,the research is devided into several parts ,one of the most important systems is the driven timing system,and its performance decide whether the driven system can work well or badly.The paper focuses on the application of the theories of Expert System and Neural Network in the fault diagnosis of electrical power system of HEV respectively. The design and realization of the HEV electrical power system fault diagnosis software are introduced in detail. The fault diagnosis software of power supply system applying the Expert System Theory is programmed under VB 6.0. While the fault diagnosis of electric machine center and solid state power controller is based on the Neural Network Theory, whose software is realized through adopting the Neural Network Toolbox of Matlab 6.5 in VB 6.0. Procreant knowledge expression and forward inference engine are adopted in the method of fault diagnosis based on Expert System Theory. In the fault diagnosis applying Neural Network Theory, six kinds of improved arithmetic of back-propagation arithmetic, including gradient descent with momentum, variable learning rate back-propagation, resilient back-propagation, quasi-Newton, Levenberg-Marquardt and conjugate gradient, are applied to diagnose the faults of electric load manage center and solid state power controller. Different diagnostic results gotten by simulation are compared at last. |
PDF Full Text Request