Method for detecting gear engagement, random forest model, training method and system

• Main Authors: RONG RONG, DING XIAOYU
• Format: Patent
• Language: Chinese; English
• Published: 22.04.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention provides a method for detecting gear engagement, a random forest model, and a training method and system. The training method comprises the following steps: acquiring a vibration image sequence of a gear mechanism under different gear engagement state tests; extracting vibration displacement signals of a preset number of pixel points in a target area in the vibration image sequence; respectively calculating a corresponding characteristic value according to the vibration displacement signal of each pixel point, and constructing a training sample; and training a to-be-trained random forest model by taking the characteristic values in the training samples as input and taking the predicted gear engagement state category as output. Compared with an accelerometer for collecting the vibration signals, the vibration displacement signal of the position corresponding to each pixel point in the vibration image can be extracted at the same time, in this way, enough data can be obtained by increasing the sig