Equipment monitoring and diagnosing method

Abstract

The invention provides an equipment monitoring and diagnosing method, comprising the following steps of obtaining a vibration signal of the equipment under a fixed rotation speed; calculating the characteristic value complying with Gaussian distribution within the corresponding frequency width range according to the vibration signal so as to establish at least one benchmark line; subsequently judging the normality or abnormality of the equipment according to the benchmark line, the corresponding frequency width range and the characteristic value; therefore, if the vibration signal exceeds the benchmark line of safe range, the abnormality and failure type can be diagnosed and recognized; and furthermore, the aim of owning the automatic monitoring and diagnosing and learning capabilities can be realized. Furthermore, the equipment monitoring and diagnosing method does not need to consider all failure types that may occur in the whole service life of the equipment so as to greatly reduce the development scale and difficulty of the failure monitoring and diagnosing system, thus improving the visualization of the equipment condition and increasing the completion rate of the equipment.

Description

technical field [0001] The present invention relates to a method for monitoring and diagnosing equipment, in particular, relates to a method for monitoring and diagnosing equipment at a constant rotational speed. Background technique [0002] Equipment fault monitoring is developed for the effective implementation of equipment maintenance and management. In the development process of the existing fault monitoring technology, the focus of the analysis process is a top-down approach. Among them, the analysis process with vibration as the monitoring object is roughly vibration signal extraction, digital signal processing, signal feature extraction and decision analysis. [0003] In this existing fault monitoring process, it is faced with the problem of many choices. First of all, according to the operating conditions of the monitoring equipment, should you choose to measure acceleration, velocity or displacement amplitude signals? The signal selection part will determine the...

AI Technical Summary

Problems solved by technology

[0007] However, in actual application, the following factors affect its practicability and replication to other devices, so the application effect is reduced

[0008] The best normalized problem: the input value and expected value of the neural network, in order to cooperate with the nonlinear function in the calculation process, need to be normalized to [0, 1] or [-1, 1], the size of the normalization will affect the sensitivity of the identification system, so there is an optimal regularization problem

[0011] How to represent the evolution process of trend analysis in the identification process? If the neural network is based on the input value (eigenvalue after digital signal processing) and its related frequency, it can distinguish whether the equipment has (simultaneous or single) fault conditions such as imbalance, eccentricity, or bearing damage under good regularization conditions. , but using this method will encounter great difficulties in failure trend analysis, that is, under the same eigenfrequency, the eigenvalue increases with the increase of the failure trend. Once it increases to a certain value, it may be due to the change of the cluster center , and another new fault type is issued, but it should be regarded as the same fault type rather than a new fault generation, the difference between them is only in the degree, so in such a learning process, there is over-learning and sample explosion question

[0012] As mentioned above, when the above-mentioned existing problems of fault monitoring and analysis technology in practical application cannot be overcome, let alone how to use this technology to assist equipment management

Images