Pumped Pipeline Anomaly Detection Using Pump Event Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing anomaly detection systems for pumped pipelines, particularly rising mains, often require pressure monitors at pump stations, generate false positives, and miss small bursts or those near the end of the main, especially in complex systems with variable pump speeds and uphill delivery.
Innovation Solution
Anomaly detection using pump start and stop event data from SCADA or similar sources, calculating flow rates based on sump volume and pump durations, and combining with pressure data for a hybrid system to reduce false alarms and improve detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pressure monitors are installed at pump stations for anomaly detection, then detection capability is improved, but device complexity and cost increase
Solution Approach 1:
The patent extracts the anomaly detection capability from the pressure monitoring system and implements it using only pump control system data. By analyzing pump start/stop events and calculating flow rates from operational duration, the system detects anomalies without requiring separate pressure monitor hardware, thus reducing device complexity while maintaining detection capability
Solution Approach 2:
The pump control system performs dual functions: it both controls pump operation and detects anomalies. The existing pump control data is repurposed for anomaly detection, eliminating the need for dedicated pressure monitoring equipment and reducing overall system complexity
2Device complexity
If traditional anomaly detection systems are used, then system simplicity is maintained, but false positives and missed detections increase
Solution Approach 1:
The patent transitions from analyzing single-pressure data to analyzing pump operational characteristics (start/stop events, duration, frequency). This dimensional shift in data analysis provides more reliable anomaly detection by examining the temporal patterns of pump operation rather than relying solely on pressure measurements
Solution Approach 2:
The system continuously monitors pump operational data and compares actual flow rates against expected flow rates calculated from pump cycle patterns. This feedback mechanism enables the system to adapt to varying operational conditions and reduce false positives by distinguishing between intentional pump cycle changes and actual pipeline anomalies
3Device complexity
If pump event data analysis is used instead of pressure monitoring, then device complexity is reduced, but detection sensitivity to small bursts may decrease
Solution Approach 1:
The system pre-calculates expected flow rates based on pump operational patterns before anomalies occur. By establishing baseline expectations for pump cycle duration and frequency under normal conditions, the system can detect even small deviations caused by minor bursts or leaks, maintaining high sensitivity without complex hardware
Data Source
Figure 1~2
Figure 3
Figure 4~5
AI summary
A method and system for detecting an anomaly in a pumped pipeline is disclosed. A data stream is received over time on operation of the pump and pump start and pump stop event data is obtained from the data stream. For each pair in time of a pump start event and preceding pump stop event in the data stream flow is calculated and compared to expected flow. Variation between calculated flow and expected flow is recorded as an exception and an alarm is triggered in dependence on the exception.