Sensor Attribution Using Binary Codes for Anomaly Isolation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Complex systems with numerous sensors generate vast time series data, making it challenging to identify anomalous behavior and determine which sensors are responsible for abnormal readings.
Innovation Solution
Generating historical binary codes from time series segments, comparing them to historical data to detect anomalies, ranking sensors based on their contribution to the anomaly, and performing corrective actions prioritized by the sensor ranking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If numerous sensors are installed to monitor complex systems, then system monitoring capability is improved, but data analysis complexity increases
Solution Approach 1:
The patent segments the complex time series data into smaller subsequences and represents each segment using a binary code generated by a finite state machine. This segmentation transforms the overwhelming complex data into manageable discrete units that can be efficiently stored and compared, resolving the contradiction between comprehensive monitoring and analysis complexity.
Solution Approach 2:
The patent introduces binary codes as an intermediary representation between the raw sensor data and the anomaly detection process. These binary codes serve as a simplified mediator that captures essential patterns while reducing data complexity, enabling efficient comparison against historical patterns without processing the full complexity of原始 time series data.
2Measurement precision
If all sensor data is analyzed to detect anomalies, then detection accuracy is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary action by pre-computing binary codes for historical time series data and organizing them into a database for efficient retrieval. When anomalies need to be detected, the system generates binary codes for current data and compares them against the pre-processed historical patterns, significantly reducing processing time while maintaining detection accuracy through the use of pre-analyzed reference patterns.
Solution Approach 2:
The patent extracts essential characteristics from time series data by converting them into binary codes that capture the essential patterns and states. This extraction process removes redundant information while preserving the critical features needed for anomaly detection, enabling fast comparison and reducing processing time without sacrificing detection accuracy.
3Measurement precision
If sensor attribution analysis is performed to identify specific sensors causing anomalies, then diagnostic precision is improved, but computational complexity increases
Solution Approach 1:
The patent applies partial action by focusing the attribution analysis only on the specific time series segments that are identified as anomalous through binary code comparison. Instead of analyzing all sensor data comprehensively, the system selectively applies attribution analysis only where needed, reducing computational complexity while maintaining diagnostic precision for the actual anomaly sources.
Solution Approach 2:
The patent implements local quality by providing detailed sensor-level diagnostic information specifically for the anomalous segments rather than uniformly analyzing all sensors. The attribution analysis is applied locally to identify which specific sensors contribute to the anomaly, providing precise diagnostic information only where required rather than performing exhaustive analysis across the entire system.
Data Source
AI summary
Methods and systems for detecting and correcting anomalies includes generating historical binary codes from historical time series segments. The historical time series segments are each made up of measurements from respective sensors. A latest binary code is generated from a latest time series segment. It is determined that the latest time series segment represents anomalous behavior, based on a comparison of the latest binary code to the historical binary codes. The sensors are ranked, based on a comparison of time series data of the sensors in the latest time series segment to respective time series data of the historical time series, to generate a sensor ranking. A corrective action is performed responsive to the detected anomaly, prioritized according to the sensor ranking.