Fuzzy pattern recognition approach with symptom zoom technology to diagnose a slight and incipient fault in a thermodynamic system

摘要

To diagnose a slight or incipient fault in a thermodynamic system correctly and timely, a new fault recognition approach is put forward by joint application of fault symptom zoom technology (SZT) and fuzzy pattern recognition. By studying the rules of the thermal system faults related to energy and mass balance, a fault symptom preprocessing method, which is called "fault symptom zoom technology", is put forward to preprocess the fault characteristic parameters, with which the complexity of the thermal system fault knowledge library can be effectively reduced and the slight fault recognition ability can be greatly enhanced. The fault fuzzy pattern recognition method is introduced, and a new general-purpose fuzzy recognition function is given, which fits for various kinds of fault symptoms and is with favorable fault classifying ability. Some fault diagnostic examples for incipient and slight faults of the thermodynamic system are given, which verify the effectiveness of the method.