Fusion diagnosing method of centrifugal pump vibration accidents and vibration signals sampling device

Abstract

The invention relates to an eccentric pump vibration accidence fusion diagnose method and relative vibration signal collector, wherein said invention is characterized in that: it uses the eccentric pump vibration signal collector to collect the normal state, the quantity imbalance, asymmetry rotate and loose base of eccentric pump; uses wavelet decomposition and reconstruction to extract the character of vibration signal; and inputs the character vectors into sub fuzzy neural networks I and II; to be treated and replace the relation factor matched with sensor signal function; the whole fuzzy neural network comprises data fuzzy layer, input layer, hidden layer and output layer; uses D-S theory to obtain the fused signal function distribution, realize the fusion diagnose on normal state, quantity imbalance, asymmetry rotate and loose base. The invention has simple structure and high effect.

Description

technical field [0001] The invention relates to the field of fault diagnosis, and relates to a centrifugal pump vibration fault fusion diagnosis method and a vibration signal acquisition device. Background technique [0002] Equipment fault diagnosis technology is a new marginal comprehensive engineering discipline gradually formed in the past 20 years. Equipment fault diagnosis technology is one of the basic measures to ensure the safe operation of equipment. It can make early forecasts for the development of equipment faults and make judgments on the causes of faults. However, equipment diagnosis technology starts with fault feature quantities, which are determined by According to the analysis of the original signal collected, the follow-up work of diagnosis is only meaningful if the signal reflecting the actual state of the equipment is collected. Therefore, signal acquisition technology is one of the foundations of equipment diagnosis. [0003] The traditional signal fe...

AI Technical Summary

Problems solved by technology

[0003] The traditional signal feature extraction mostly uses the spectrum analysis method, which only uses Fourier transform to analyze the fault of the centrifugal pump from the power spectrum. It only analyzes the frequency domain, and does not analyze it from the time domain and frequency domain. It cannot fully reflect the characteristics of the fault. Therefore, it is impossible to accurately diagnose the fault of the centrifugal pump; at present, the vibration signal fault diagnosis of the centrifugal pump mostly uses a single sensor to collect the signal and diagnose the fault of the centrifugal pump. faults; there are also multi-class classification algorithms using support vector machines, which have some advantages over traditional BP methods, but do not consider the multi-information resources of sensors, and the accuracy of fault diagnosis is still limited

Images