Numerical control machine tool rolling bearing fault diagnosis method

Abstract

The invention provides a numerical control machine tool rolling bearing fault diagnosis method based on a whale optimization algorithm to optimize a variational mode decomposition algorithm, and the method comprises the steps: collecting original vibration signals of a bearing in a machine tool spindle box in four states, optimizing the variation modal decomposition algorithm by using whale optimization algorithm and using envelope entropy as a fitness function of the whale optimization algorithm to obtain parameter combinations (alpha and K) which are originally required to be set according to human experience, decomposing the original signals by using the optimized variation modal decomposition algorithm to obtain a plurality of intrinsic modal components IMF, selecting the IMF component with the most fault characteristics from the IMF components to carry out Teager energy demodulation, and finally comparing a Teager energy spectrogram with a fault characteristic theoretical value to judge whether the bearing has faults and the type of the faults. The problem that the number of the variation modal decomposition algorithm is required to be set manually in advance is solved, so that the result has more theoretical basis, the reliability is higher; and the intrinsic characteristic component is selected by using the envelope entropy, so that the accuracy and effectiveness of the result are improved.

Description

technical field [0001] The present invention relates to bearing vibration signal identification, in particular to a numerically controlled machine tool rolling bearing fault diagnosis method based on a whale optimization algorithm optimized variational mode decomposition algorithm and a Teager energy operator. Background technique [0002] As the "industrial mother machine" of modern manufacturing, CNC machine tools play a pivotal role in modern manufacturing. Whether a country's industrial level is advanced or not is reflected in CNC machine tools to a certain extent. With the rapid development of CNC technology, the quality, precision and efficiency of machined parts have been greatly improved, but the ensuing problem is that the complexity and precision of CNC machine tools continue to increase, and the structure is also more complicated. The difficulty of fault diagnosis has also increased. As one of the core components of CNC machine tools, rolling bearings often dire...

AI Technical Summary

Problems solved by technology

The commonly used method for extracting fault features is Empirical Mode Decomposition (EMD), but EMD has modal aliasing, endpoint effects, and is greatly affected by sampling frequency. Foreign scholars such as Dragomiretskiy proposed an adaptive A new method of signal processing - Variational Mode Decomposition (VMD), VMD overcomes the shortcomings of EMD, but VMD has influencing parameters, such as the number of components and penalty factors, which need to be determined in advance, and parameters need to be optimized , for the above problems

Images