Vehicle Failure Sensing Using Feature Clustering and Periodic Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current failure symptom sensing systems for vehicles face challenges in efficiently processing and analyzing data from various sensors to accurately detect vehicle failures while minimizing processing burden and power consumption during driving operations.
Innovation Solution
The system employs a hybrid ECU (HVECU) that acquires data from sensors, generates feature quantity data using algorithms, performs clustering processing, and sets reference values to determine failure symptoms, with these processes being executed when the vehicle is stopped to reduce processing burden and power consumption during driving.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If failure symptom sensing is performed continuously during vehicle operation, then detection reliability is improved, but processing burden and power consumption increase
Solution Approach 1:
The system performs failure symptom sensing periodically based on vehicle operation states rather than continuously. The HVECU determines whether to perform sensing based on current vehicle state (e.g., engine running, gear position, acceleration state), executing the sensing process only when appropriate conditions are met. This periodic execution maintains detection reliability while significantly reducing power consumption and processing burden compared to continuous monitoring.
2Measurement precision
If complex data processing and clustering algorithms are executed in real-time, then measurement precision is improved, but processing burden increases
Solution Approach 1:
The system performs data preprocessing and feature extraction in advance before the actual failure sensing. The HVECU acquires sensor data, performs normalization, extracts feature quantities, and conducts clustering processing to establish reference values before the vehicle operation begins or during idle periods. This preliminary preparation reduces the computational burden during real-time failure detection, allowing complex algorithms to execute with acceptable processing requirements while maintaining high detection precision.
3Measurement precision
If multiple sensor data are processed simultaneously, then measurement precision is improved, but processing time increases
Solution Approach 1:
The system segments the failure sensing process into distinct processing stages: data acquisition from multiple sensors, normalization processing, feature quantity extraction, clustering analysis, and comparison with reference values. Each stage processes specific portions of the data independently, allowing parallel execution where possible and reducing overall processing time. This segmented approach enables comprehensive multi-sensor analysis while maintaining efficient processing throughput.
Data Source
AI summary
A failure symptom sensing system may comprise an acquisition unit configured to acquire, while a driving function of a vehicle is in operation, a plurality of data from a plurality of sensors configured to sense a state of the vehicle. The failure symptom sensing system may comprise a generation unit configured to generate, from the plurality of data, feature quantity data indicating a feature quantity of each of the plurality of data in accordance with a predetermined algorithm. The failure symptom sensing system may comprise a sensing unit configured to sense, when the sensing unit senses an instruction to stop the driving function of the vehicle, whether an indication of failure of the vehicle exists based on the feature quantity data and a predetermined reference feature quantity data.