基于自适应软测量策略的排水管网传感器异常检测方法
By employing an adaptive soft measurement strategy, utilizing the topology of the drainage network and the mutual information analysis of sensor data, combined with deep learning and dynamic update methods, the adaptability and accuracy issues of sensor anomaly detection are resolved, achieving efficient detection of sensor anomalies.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- INNOVATION CENTER OF YANGTZE RIVER DELTA ZHEJIANG UNIVERSITY
- Filing Date
- 2026-03-10
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for detecting anomalies in drainage pipe networks suffer from problems such as strong dependence on fixed thresholds, poor model adaptability, and frequent false alarms and missed alarms, making them difficult to adapt to complex drainage system environments.
Based on an adaptive soft measurement strategy, upstream and downstream sensor data are selected as input features through pipeline topology analysis and sensor data mutual information analysis. The KAN-Attention deep learning algorithm is applied to construct a soft measurement model. Combined with the dynamic search of confidence intervals and the dynamic moving window method of probability density function, sensor anomaly detection is achieved.
This improves the accuracy and robustness of sensor anomaly detection, reduces false alarm and false negative rates, and ensures the long-term effectiveness of the detection method.
Smart Images
Figure CN121808648B_ABST