Study On Multi-sensor Failure Detection Of Fuel Cell Based On Information Fusion

The shortage of oil resource and the environmental pollution are two major problems in the world. The automobile consume of oil and exhaust emission are main reasons. As the new energy automobile of the environmental protection and energy conservation, the fuel cell electric automobile have broad prospect in the future. As main energy in the fuel cell electric automobile, the fuel cell engine is a complex system, in which there are many sensors which often work under bad conditions, breaking down is unavoidable. Once breaking down, less causes the automatic system's performance drop, more leads to a disaster. Therefore, it seems especially important to diagnose and remove the fault of the fuel cell engine multi-sensor prompt and accurately and ensure the fuel cell engine working under a safety and reliable condition. This paper takes the fuel cell electric automobile of 25kW PEMFC engine system as research object, Uses the information fusion technology to carry on the fault diagnosis to its multi- sensors system. Main research results as follows:According to the performance index which the fuel cell engine must achieve, this paper has studied the overall structure of the fuel cell engine system as well as the sensor system structure, combining to the special working condition of fuel cell engine, choose some fit sensors and design high Precise circuit.Used federal Kalman integrated filter processing fuel cell multi-sensor data signal, modeling and simulating, the simulation result has indicated that, this method is very good. Used VB6.0 language and serial communication technology design the entire fuel cell engine multi-sensor data acquisition system, including supervising interface, communication agreement and flow chart. This system can get and save the data on time.Based on the Theory knowledge of information fusion technology, we can get the basic Schematic diagram, Structural style and fault diagnosis frame of fuel cell multi-sensor information fusion fault diagnosis technology.In view of the characteristic and complex environment of fuel cell engine multi-sensor system, we can get the common breakdown type, and uses the nerve network information fusion method to carry on the fault diagnosis of the fuel cell engine multi-sensor system, and get the fault diagnosis system structure, Finally, through the temperature of fuel cell engine simulation experiment, The simulation experiment indicated that, this method is very good in fault diagnosis.This paper has thoroughly studied information fusion fault diagnosis question of fuel cell engine multi-sensors system. When sensors break down, this system can make the real-time estimate and feedback the signal from the detection data of disable sensors, which has ensured the stability and the reliability of system.