Diagnostic system of non-contact type rotary mechanical failure

Abstract

The invention relates to a diagnostic system of a non-contact type rotary mechanical failure in the technical field of detection, comprising a sound pressure measurement device, a computer, a sound field reconstructing module, an acoustic holography training sample storage module, an acoustic holography test sample storage module, an off-line training module and an online diagnostic module, wherein the sound pressure measurement device is connected with the computer, the computer is connected with the sound field reconstructing module, the sound field reconstructing module is connected with the acoustic holography training sample storage module and the acoustic holography test sample storage module, the acoustic holography training sample storage module is connected with the off-line training module, the acoustic holography test sample storage module is connected with the online diagnostic module, the off-line training module is connected with the online diagnostic module, the acoustic holography training sample storage module and the acoustic holography test sample storage module are connected with the computer, and the acoustic holography training sample storage module is connected with the online diagnostic module. The invention is a non-contact type, has simplicity and high accuracy rate and obtains favorable online diagnostic effect through optimization.

Description

technical field [0001] The invention relates to a system in the technical field of detection, in particular to a non-contact fault diagnosis system for rotating machinery. Background technique [0002] At present, the fault diagnosis of rotating machinery is mainly based on the measurement and analysis of vibration signals. However, for fault diagnosis based on vibration signals, sensors must be placed on the surface of the vibrating machine. However, it is difficult to arrange sensors in harsh environments such as complex component vibration surfaces, moving parts, high temperature or oil dirt, and can only detect the vibration of several isolated measuring points on the vibration surface. Therefore, it can only reflect the local vibration information of the equipment; and the vibration characteristics are not obvious in some fault situations, while other characteristics (such as acoustic characteristics) are more obvious. [0003] Mechanical noise contains rich machine st...

AI Technical Summary

Problems solved by technology

[0004] After searching the existing literature, it is found that the Chinese patent application number is: 200810214410.0, and the name is "On-line Diagnosis Device and Method for Mechanical Equipment Faults". The device includes: microprocessor, liquid crystal display, digital signal processing chip, complex programmable logic Devices, high-speed signal analog-to-digital conversion chips, first-in-first-out memory, dynamic random access memory, etc., this paper collects vibration signals (temperature signals) of bearing housings and shafts, and diagnoses equipment failures according to the correlation dimension and shaft center trajectory, but the technology Acquisition of signals is limited to tactile measurements where sensors are easily placed

[0005] After searching, it was found that the Chinese patent application number is: 03135535.8, and the name is "Intelligent Diagnosis Method and Device for Rotating Machinery Faults". The fault diagnosis system is composed of four modules: decision fusion module, expert knowledge base, data engine module and intelligent reasoning engine to realize intelligent fault diagnosis of equipment. The disadvantages of measurement, and the intelligent diagnosis based on fuzzy neural network needs to be based on a large number of sample data

Images