Diesel engine fault diagnosis method based on vibration analysis

Abstract

A diesel engine fault diagnosis method based on vibration analysis includes acquiring normal conditions and vibration signals in fault of the diesel engine by a vibration acceleration sensor; decomposing the acquired vibration signals by means of improved inherent time scale and generating a plurality of inherent time scale components and residual signals; computing energy of the inherent time scale components, sequencing the inherent time scale components according to energy, and selecting former N components with accumulative energy larger than original signal energy by 95% as main components; computing kurtosis and waveform factor of the main components as fault characteristics; constructing a multi-classification correlation vector machine model by an error correcting and encoding method based on probability output for fault diagnosis. By the diesel engine fault diagnosis method, kurtosis and waveform factor as sensitive fault characteristics are determined, and an error correcting and encoding correlation vector machine multi-classification model based on probability output is provided; the diesel engine fault diagnosis method can accurately judge the operating states of a diesel engine and is applicable to fault diagnosis of diesel engines.

Description

technical field [0001] The invention relates to a diesel engine fault diagnosis method. In particular, it relates to a diesel engine fault diagnosis method based on vibration analysis. Background technique [0002] Diesel engine is an important reciprocating power machine, which is widely used in industry, agriculture, military, construction, transportation and other fields, and plays a pivotal role in the national economy and people's daily life. On the one hand, it can greatly increase labor productivity, reduce production costs and energy consumption; on the other hand, if a certain component fails, it will often cause the paralysis of the entire equipment, stop the entire production line, cause huge economic losses and even endanger personal safety. , so carrying out research on diesel engine fault diagnosis is of great significance for improving the safety and reliability of diesel engines, and it also contains huge economic and social benefits. [0003] The vibration...

AI Technical Summary

Problems solved by technology

However, problems such as over-envelope, modal confusion, endpoint effects, and unexplainable negative frequencies caused by Hilbert transform have not been properly resolved in this method.

However, since the vibration signal of diesel engine is more complex, it is necessary to study the optimization method of smoothing method and end effect if the intrinsic time scale decomposition is used for the analysis of vibration signal of diesel engine

[0004] After using the vibration analysis method to extract the fault features, the pattern recognition method is required to distinguish the fault. The widely used pattern recognition methods include neural networks, support vector machines, etc., but these methods cannot give probabilistic output.

Images