Rolling bearing degradation trend prediction method and device

• Main Authors: DENG MINQIANG, ZHANG QIUSHENG, ZHANG ZHENGJIE, YANG YONG, YAO YUAN, LI JING, ZHANG YU, YAN ZONGLIANG, ZHANG LI, CUI CHUNPENG
• Format: Patent
• Language: Chinese; English
• Published: 13.08.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MEASURING; PHYSICS; TESTING; TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES; TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR

The invention provides a rolling bearing degradation trend prediction method and device, and belongs to the field of mechanical part health management. The method comprises the steps of obtaining rolling bearing vibration signal sampling data; calculating Hjorth parameters of the rolling bearing vibration signal sampling data; forming a degradation characteristic index curve according to the Hjorth parameters; training data are obtained according to the degradation characteristic index curve extension; training and verifying the long-short-term memory network by using the training data; and processing the output of the trained and verified long and short-term memory network into a predicted rolling bearing degradation trend. The Hjorth parameter is used as a rolling bearing degradation index, degradation trend information contained in a vibration signal can be well reflected, and in addition, the prediction precision of the degradation trend is improved in combination with the strong time sequence feature ext