一种低压开关柜温湿度监测和预警方法、系统
By constructing a dynamic temperature and humidity benchmark model based on the physical laws of heat and mass transfer and an improved long short-term memory network model, combined with Bayesian inference methods, the problems of false alarms and missed alarms in temperature and humidity monitoring of low-voltage switchgear were solved, and early warning and accurate handling of insulation degradation were achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- XIAN THERMAL POWER RES INST CO LTD
- Filing Date
- 2026-06-16
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies for temperature and humidity monitoring in low-voltage switchgear suffer from several drawbacks. Fixed threshold methods cannot adapt to load and environmental changes, leading to false alarms or missed alarms. They also lack consideration for the linkage between temperature, humidity, and insulation degradation. Multi-parameter fusion methods fail to effectively warn of long-term cumulative insulation damage, and machine learning methods suffer from imbalanced samples and are black-box, making early warning impossible.
A dynamic benchmark model of temperature and humidity based on the physical laws of heat and mass transfer is constructed. The uncertainty of the model parameters is quantified by Bayesian inference. Combined with an improved long short-term memory network model, the cumulative risk is updated by adaptive forgetting factor. A graded early warning strategy is formulated and linkage control operation is executed.
It enables dynamic deviation risk assessment of temperature and humidity in low-voltage switchgear, improves the accuracy and foresight of monitoring, provides early warning of insulation degradation, reduces false alarm rate, and enhances the reliability of system judgment and the accuracy of handling.
Smart Images
Figure CN122408893A_ABST