Fault diagnosis method for dynamic and static information of mega-kilowatt ultra-supercritical units

Abstract

The invention discloses a distributed Bayesian online fault diagnosis method for the dynamic and static information of a million-kilowatt ultra-supercritical unit. The invention aims at the problem that the fault types of million-kilowatt ultra-supercritical units are difficult to distinguish due to the diversification of fault information, and uses the Bayesian network classifier to capture the static information of the fault, and at the same time, combines the slow feature analysis algorithm to extract the dynamic information of the fault . Finally, an online fault diagnosis model for improving the accuracy of fault diagnosis is constructed by using both dynamic and static fault information. This method overcomes the problem of insufficient fault information extraction caused by too many variables in large-scale coal-fired units, effectively solves the problem of difficult online diagnosis of faults containing diverse dynamic and static fault information, and greatly improves the accuracy of unit faults that are difficult to distinguish. The on-line diagnosis performance helps thermal power plants to carry out effective and timely inspection and maintenance of the plant, thus ensuring the safe and reliable operation of million-kilowatt ultra-supercritical generating units.

Description

Technical field [0001] The present invention belongs to the field of thermal power generation process fault diagnosis, in particular to a distributed Bayesian online fault diagnosis method for a million kilowatt ultra-supercritical unit. Background technique [0002] In the 21st century, with the improvement of industrial automation and the trend of economic globalization, the thermal power generation industry developed towards large-scale and complicated direction. At the same time, in order to achieve the sustainable development of electricity, the thermal power generation industry actively carried out structural adjustments, with high-capacity, high parameters, low energy consumption supercritical and ultra-supercritical units to replace high-energy small thermal power units, basically form an ultra-supercritical unit The power energy structure of the main body. For large-scale fire generators, there is a high temperature, high pressure and high noise. In addition, millions of...

AI Technical Summary

Problems solved by technology

However, existing data analysis methods, such as principal component analysis, partial least squares method, and Fisher's discriminant analysis, only consider the static information of the fault and ignore the dynamic information of the fault.

Therefore, applying it to a million-kilowatt ultra-supercritical unit cannot obtain a good diagnostic effect

Images