Combustion system of Power plant boiler is taken as the research object of this thesis. The research mainly focuses on the faults of boiler combustion system, such as flame center deflection, powder feed inequality or break, primary air pipe jammed, spontaneous combustion, and backfire or kill in burner spout. The character of boiler combustion system and the causes of the faults are analyzed in detail and the online system of fault diagnosis for boiler combustion system is developed by using fuzzy modular networks and malfunction diagnose regulation warehouse and expert system technology etc. By the experiment data testing proves that in this system, both symbol reasoning and nerve network reasoning can be combined very well and has such a capability of simulating the speculation of human expert to a certain degree that it can diagnose the faults for boiler accurately and timely. It can also provide operation guidance for boiler-operators to eliminate faults.
|