Research on Full Life Cycle Fault Detection of Rolling Bearings under Mathematical Morphology and LMD Algorithm
When the rolling bearings rotate at high speed,the vibration and friction generated can easily cause minor wear and damage in the bearing surface.In harsh working environments,it can exacerbate bearing wear and corrosion,making it difficult to distinguish surface defects.For this purpose,a fault detection method for the entire life cycle of rolling bearings is studied.Based on the fault mechanism and characteristics of rolling bearings,set fault detection standards for rolling bearings,and simulate the entire life cycle working process of rolling bearings.Collect and preprocess surface image data and internal vibration data of rolling bearings,extract small features of rolling bearing surface images based on shape features using mathematical morphology,decompose complex signals into multiple single frequency and narrowband frequency components using the LMD algorithm,and extract key features such as kurtosis and frequency.The feature matching is used to obtain the detection results of the type,location,and quantity of rolling bearing faults.Experimental results show that the fault type false detection rate of the optimized design method is significantly re-duced,with a good fault detection ability.
mathematical morphologyLMD algorithmrolling bearingsfull life cyclefault detection
万方数据
维普
