Sporadic Anomaly Detection in Vehicle Power Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle failure detection systems fail to account for sporadic anomalies that do not meet predetermined duration and occurrence thresholds, leading to undetected issues that may cause vehicle failures.
Innovation Solution
A method and computer system that detect anomalies by measuring duration and occurrence, incrementing counters for sporadic anomalies, and confirming them based on predefined thresholds, allowing for the identification and recording of sporadic anomalies for diagnostic procedures and potential system degradation to prevent failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system tracks all anomalies regardless of duration, then no sporadic anomalies are missed, but processing complexity increases
Solution Approach 1:
The anomaly detection system is segmented into distinct functional modules: a pre-processing module that identifies potential sporadic anomaly types, a real-time detection module that monitors incoming anomaly data, a counter management module that tracks occurrences, and a confirmation module that determines whether sporadic anomalies are confirmed. This segmentation allows each module to perform its specific function efficiently without overwhelming the entire system.
Solution Approach 2:
The system applies different detection strategies to different anomaly types based on their characteristics. For common anomalies with clear duration thresholds, traditional threshold-based detection is used. For identified sporadic anomaly types, the system applies specialized tracking with occurrence counters and confirmation criteria. This localized approach optimizes processing resources by applying complex tracking only where necessary.
Data Source
AI summary
A method for managing the sporadic anomalies of a power system of a motor vehicle, the system including a computer and a set of sensors. The computer including a memory area capable of receiving measurements made by the set of sensors and detecting anomalies on the basis of the measurements received, the anomalies of the system being defined in a predetermined list of sporadic anomalies at a given instant. The method including: detecting an anomaly; measuring the duration of the detected anomaly; if the measured duration is less than a predetermined duration threshold, and if the detected anomaly is present in the predetermined list of sporadic anomalies at the current instant, incrementing an occurrence counter; and if the value of the occurrence counter is greater than a predetermined occurrence threshold, confirming the detected anomaly as a sporadic anomaly.