一种基于电机温度监测的故障预警方法及系统
By constructing a LOF algorithm that corrects for temperature rise anomaly factor and local density fluctuation factor, the problems of high false alarm rate and high missed alarm rate in motor temperature monitoring are solved, and high-precision detection and automated early warning of motor faults are realized.
CN121813987BActive Publication Date: 2026-07-17GUANGDONG DONGGUAN DIANJI CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUANGDONG DONGGUAN DIANJI CO LTD
- Filing Date
- 2025-12-23
- Publication Date
- 2026-07-17
Smart Images
Figure CN121813987B_ABST
Abstract
本发明涉及温度监测技术领域，更具体地，本发明涉及一种基于电机温度监测的故障预警方法及系统，包括：获取包含电机绕组温度、环境温度和负载电流有效值的运行数据；计算温升异常因子，所述温升异常因子与所述电机绕组温度和环境温度的差值呈正相关，与所述负载电流有效值的平方和预设电机热阻的乘积呈负相关。本发明引入局部密度波动因子对传统LOF（局部异常因子）算法中的距离度量进行自适应修正，利用数据点邻域内的波动稳定性（方差）来调整局部密度，使得处于故障演变期虽未大幅偏离但呈现不稳定状态的数据点被赋予更低的密度值，从而显著提高了算法对电机缓慢演变型初发故障的敏感度，降低了漏报率。
Need to check novelty before this filing date? Find Prior Art