Research On The Monitor And Diagnosis System For The Air Blower Of Thermal Power Plant

Based on the condition monitoring and fault diagnosis technique, The project "research on the monitor and diagnosis system for the air blower of thermal power plant" is carried out. In this project, the following research works have been launched:(1) The common fault type, the sign and administration measure of the air blower are summarized. The parameter and position of monitoring are confirmed. The frame of the system is set up on investigate and survey.(2) After studying the principle and method of fuzzy fault diagnosis, utilize the dynamic data of the air blower to establish the jurisdiction function fuzzily about the fault and fault characteristic information. After confirming the diagnostic flow for the diagnosis of the air blower, a spot instance is brought forward in the thesis. The result of diagnosis is consistent with the result of on-site inspection, which confirms the feasibility of the method.(3) Combined prediction based on neural network is being put forward. On the foundation of multinomial regression, GM(1, 1) prediction and feed-forward neural network prediction, all of which have their own characters, combined prediction based on neural network is assembled. taking advantage of great nonlinear and terribly strong self-learning ability of neural network, the difficulty of confirming weight coefficient of each prediction method in combined prediction is solved. Data is pretreated by means of principal component analysis technology. Precision of combined prediction is further improved.(4) Software used for the air blower's condition monitoring and fault diagnosis is developed.