A Vibration Fault Diagnosis Method for Turbine Generator Based on Forward Reasoning

Abstract

The invention discloses a turbo generator set vibration fault diagnosis method based on forward reasoning. After a diagnosed turbo generator set starts, a parameter detection device is employed to carry out real-time detection on related work parameters in a start and operation process of the diagnosed turbo generator set and synchronously sends the detection information to a vibration fault diagnosis device for automatic vibration fault diagnosis, vibration faults of the diagnosed turbo generator set are diagnosed level by level by the vibration fault diagnosis device according to the detection result transmitted by the parameter detection device in combination with the active power value of the diagnosed turbo generator set, and the fault diagnosis process comprises steps of 1, shaft vibration swinging value diagnosis; 2, start process vibration fault diagnosis; 3, zero load operation vibration fault diagnosis; and 4, loaded operation vibration fault diagnosis. The method is advantaged in that the steps are simple, and the method is reasonable in design, is convenient to realize, has good use effects, can conveniently and rapidly accomplish the online steam turbine vibration fault diagnosis process and can further realize accurate and reliable diagnosis results.

Description

technical field [0001] The invention belongs to the technical field of steam turbine fault diagnosis, in particular to a vibration fault diagnosis method of a steam turbine generator set based on forward reasoning. Background technique [0002] The steam turbine generator set (hereinafter referred to as the steam turbine set) is the most important precision large-scale rotary equipment in thermal power plants. It consists of multiple rotors, and the working state of each rotor directly affects the production and safety of the power plant. The vibration of the unit is the most important part of the equipment. Common faults that directly endanger the safe operation of equipment. In order to eliminate this fault, it is necessary to diagnose the cause of the fault. However, due to the complex mechanism of vibration fault and its wide range, it has long been a major technical problem, and vibration fault has always been a problem. Troubled the safe operation of the steam turbine ...

AI Technical Summary

Problems solved by technology

However, the reliability of the diagnostic results of the above-mentioned existing vibration fault diagnosis system mainly depends on the expert experience and thinking mode, that is, the thinking mode and process of expert diagnosis are followed, and the diagnosis is carried out based on the expert's fault knowledge base. The thinking mode and process are compiled into the language of the computer, and the R&D personnel have encountered difficulties. Therefore, no matter whether the expert system installed and used is imported or domestic, the diagnostic results are not credible. Therefore, after the diagnostic system is put into operation, no one Therefore, the service life of these diagnostic systems in power plants generally does not exceed 3 years, and they are finally forgotten and discarded

[0004] After analysis, it is found that the diagnosis results of the existing online vibration fault diagnosis system have low accuracy and are not credible, mainly due to the following two reasons: First, reverse reasoning is used to diagnose faults, although the online vibration fault diagnosis systems developed by various companies use the The specific diagnostic methods are different, including the use of neural networks, fuzzy theory, mathematical models to calculate the credibility of symptoms, system self-learning functions, etc., but the diagnostic thinking mode is carried out by reverse reasoning; reverse reasoning is also called target direct Inference, it deduces vibration faults based on vibration characteristics; however, since the relationship between vibration characteristics and faults is not a simple one-to-one correspondence, but multiple cross-relationships, it is inevitable that misdiagnosis and missed diagnosis will occur during the reverse reasoning process, such as At present, all diagnostic systems diagnose one of the important faults, rotor misalignment, based on whether the vibration signal contains 2X (that is, twice the frequency) vibration as a sufficient criterion, but there are 5 to 6 reasons for the actual unit to produce 2X vibration faults When the system detects a 2X vibration component, it makes a diagnosis of rotor misalignment before giving a judgment value standard and excluding other 2X vibration faults. This obviously has loopholes and makes the diagnosis result unreliable; 2. The diagnostic criterion is unreliable. The current online diagnostic fault judgment basis is based on the vibration characteristics listed in the traditional textbooks, many of which have major misunderstandings, such as the actual cause of vibration faults that cause 2X (2-fold frequency) vibration There are as many as 5 to 6 types, and 2X vibration is almost always used as the only criterion for rotor misalignment (unit vibration is the most common) fault in online diagnosis; obviously, if this fault feature is used as the criterion, the diagnosis result cannot be in line with reality, so In the case of unreliable criteria, the diagnostic results made are clearly unreliable

Images