Method and system for predicting degradation trend of mechanical system

Abstract

The invention discloses a method and a system for predicting the degradation trend of a mechanical system. The method collects vibration acceleration time series signals of a mechanical system of a certain length at equal time interval points to establish a nonlinear time series model and a linear autoregressive time series model, and the non-normalized least square integral error value at each sampling time is obtained by using the nonlinear time series model and the linear autoregressive time series model, A mechanical system degradation index series is obtained by using that normalization method. At last, an exponential model is adopt to fit that degradation index series to obtain a normalized mechanical system state degradation index model, and the normalize mechanical system state degradation index model is adopted to realize the prediction of the degradation trend of the mechanical system, which has the advantages of simple calculation steps, easy realization and accurate result.In addition, the method provided by the invention can be applied to state evaluation and trend prediction of degradation process of various mechanical systems.

Description

technical field [0001] The invention relates to the technical field of mechanical system state monitoring and life assessment, in particular to a method and system for predicting the degradation trend of a mechanical system. Background technique [0002] During the operation of mechanical equipment, its health status directly threatens people's property and even life safety. Due to the working nature of these mechanical equipment, the degradation of the mechanical system is inevitable due to the coupling effect of environmental pollution, material corrosion and aging, overload operation and a series of man-made or natural disaster factors during the long-term working process. Accumulation of degradation to a certain extent will lead to attenuation of resistance, and its life will continue to decrease. The consequence of this is that the mechanical system’s ability to withstand external natural disasters and normal loads will be reduced, which may lead to a series of catastro...

AI Technical Summary

Problems solved by technology

The temperature monitoring method is sensitive to changes in load, speed and lubrication conditions. However, this method can only be detected when the fault reaches a certain severity, and the temperature detection basically does not respond to relatively small degradation state changes.

The disadvantage of the oil sample analysis method is that it is difficult to extract the wear particles in the lubricating oil, and the analysis equipment is relatively complicated, and needs to be further miniaturized to realize online monitoring

As an emerging dynamic non-destructive testing technology, acoustic emission technology, when using acoustic emission technology for online detection, its detection effect is easily limited by various noise interference, and it is difficult to achieve effective real-time detection.

Among the state monitoring of many mechanical systems, the vibration analysis method has the characteristics of fast diagnosis and online monitoring, and has been widely used in the state monitoring and fault diagnosis of rotating machinery; however, the existing vibration method degradation state identification technology is generally Based on the assumption of a linear model, or linearly approximating a nonlinear model, this method is feasible for some mechanical systems with weak dynamic behavior, but it is more difficult for mechanical systems with strong nonlinear dynamic behavior. error

Images