Method for judging working state of mechanical equipment based on vibration signal analysis

• Main Authors: LIU SHITAO, CHEN GONGZHENG, SHI YUNFEI, PAN YUPO
• Format: Patent
• Language: Chinese; English
• Published: 11.01.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC ORINFRASONIC WAVES; MEASURING; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; TESTING

The invention relates to the technical field of mechanical equipment, in particular to a method for judging the working state of mechanical equipment based on vibration signal analysis. The judging method comprises four steps of signal acquisition, feature extraction, model training and model prediction. According to the main principle, classification models of different working states are established by extracting collected vibration signal characteristics of the mechanical equipment, so that whether the mechanical equipment is in a static state, an idling state or a working state is analyzed in real time, and basic data of a refined analysis scene is provided for the requirements of subsequent man-hour analysis, bill settlement and the like. 本发明涉及机械设备技术领域，具体地说是一种基于振动信号分析的机械设备工作状态判别方法。本判别方法包括信号采集、特征提取、模型训练和模型预测四个步骤；其主要原理是通过提取采集到的机械设备振动信号特征，建立不同工作状态的分类模型，以此实时分析机械设备处于静止、怠速还是工作状态，为后续工时分析、账单结算等需求，提供精细化分析场景的基础数据。