基于神经网络的超临界锅炉四管泄漏故障诊断

ANN-Based Diagnosis of Four-Tube Leakage Faults for Supercritical Boiler Unit

摘要:

四管泄漏是电站锅炉的常见故障,不仅导致非正常停炉和经济损失,严重时会危及运行人员的生命安全,深入研究四管泄漏故障规律并采用先进方法对四管泄漏故障类型和位置进行实时诊断具有重要意义;为此,借助火电机组全范围仿真系统,针对不同的协调运行方式,对某600 MW超临界机组锅炉四管泄漏故障的规律进行了详细的仿真研究;在此基础上,采用神经网络与征兆缩放技术相结合的智能诊断方法,实现四管泄漏故障的实时诊断;实验结果表明:该方法对不同协调运行方式下程度不同的四管泄漏故障均可得到具有较高故障分离度的正确诊断结果,具有较好的工程实用性。

Abstract:

Four-tube leakage faults are the most common faults of a power plant boiler, not only resulting in abnormal boiler shutdown and economic loss, but also endangering the safety of operating personnel. It is of great significance to grasp the changing rules of four-tube leakge faults and to recognize the fault type and location real-time with advanced fault diagnosis method. With the help of a full-scope simulator, detailed fault simulation tests are carried out for the four-tube leakage faults of a 600MW supercritical boiler unit under different coordinated control modes. An intelligent fault diagnosis method, which combines artificial neural network with symptom zoom technology, is applied to realize online fault diagnosis of four-tube leakage faults of varied severity at different load points and operating modes. The fault diagnosis simualtion tests show that this method can recognize and position the four-tube leakage faults correctly with good engineering practicability.