Power Storage Abnormality Detection Sensitivity Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing abnormality detection systems in power storage systems face challenges in maintaining sensitivity during repeated updates of the reference database, leading to potential false detection of normal events as abnormal or vice versa, due to expansion or contraction of the normal space.
Innovation Solution
Incorporating a sensitivity test mechanism after database updates and a rollback mechanism to revert the reference database if the sensitivity test results in undesired abnormality or normality determinations, ensuring consistent abnormality detection sensitivity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the reference database is updated repeatedly during operation to accommodate exceptional behaviors, then the system becomes more adaptable to new normal conditions, but the sensitivity to detect abnormality deteriorates due to expansion of the normal space
Solution Approach 1:
The patent segments the reference database into multiple versions (current version and previous version) and selectively applies different versions based on the type of data being analyzed. Normalizing data uses the current updated version for adaptability, while abnormality detection uses the previous version to maintain sensitivity, thus resolving the contradiction between adaptability and measurement precision.
Solution Approach 2:
The system dynamically switches between different reference database versions depending on the operational context. The reference database is updated over time to accommodate new normal conditions, but the system can revert to previous versions when sensitivity is needed, making the system adaptive while preserving detection capability.
2Adaptability or versatility
If the reference database is updated to include new operation data sets, then the normal space expands to cover more exceptional behaviors, but false detection increases where normal events are erroneously identified as abnormal
Solution Approach 1:
The patent divides the reference database into current and previous versions, allowing the system to maintain an expanded normal space in the current version while preserving the original detection sensitivity in the previous version. This segmentation enables the system to accommodate new operation data without compromising detection accuracy.
Solution Approach 2:
The system incorporates a feedback mechanism where abnormality detection results are evaluated against the previous reference database version. When false detections occur, the system can adjust or revert database versions, creating a feedback loop that maintains reliability while allowing adaptability.
3Adaptability or versatility
If the reference Mahalanobis distance is updated repeatedly, then the system adapts to changing operation conditions, but the consistency of abnormality detection deteriorates
Solution Approach 1:
The system dynamically manages reference database versions, allowing the Mahalanobis distance to be updated for adaptability while maintaining previous versions for consistency. The system can switch between versions based on operational needs, achieving both adaptation and stability.
Solution Approach 2:
The system performs preliminary updates to the reference database to accommodate new operation conditions before actual abnormality detection occurs. By preparing multiple versions in advance, the system ensures both adaptability to new conditions and consistency in detection when using stable previous versions.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A power storage system includes: a power storage unit including a storage battery, a charging section that charges the storage battery, and a detection section that detects at least one status of the storage battery and the charging section from a plurality of perspectives; and an abnormality detection unit including an input section that acquires transmission information from the power storage unit via a transmission path, the transmission information including a plurality of detected status values, and an abnormality detection section that detects abnormality of the power storage unit by a multivariate analysis performed on the plurality of acquired status values.