Vehicle Sensor Failure Detection Using Baseline Signal Similarity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional failure detection methods in machine operations, such as knowledge-based, model-based, and signal-based detection, face limitations in precisely detecting sensor failures and maintaining high sensor bandwidth, making it difficult to accurately capture and diagnose machine anomalies.
Innovation Solution
A predictive analysis system comprising a central electronic processing system connected via wireless infrastructure to vehicle electronics, utilizing a diagnostic unit with data acquisition, comparison, and failure analysis modules to compare baseline and failure analysis signals, calculating a quantified degree of failure through similarity matrix and weight ratio analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If knowledge-based detection or model-based detection is used, then sensor readings can be classified and correlated, but sensor bandwidth decreases and individual sensor failures cannot be precisely detected
Solution Approach 1:
The patent extracts and analyzes individual sensor signals separately from the classified time series data. By isolating each sensor's frequency spectrum and comparing it against baseline spectra, the system can precisely detect individual sensor failures without being constrained by the bandwidth limitations of knowledge-based or model-based detection methods.
Solution Approach 2:
The patent applies frequency-domain analysis to sensor signals, treating sensor failures as detectable vibrations or anomalies in the frequency spectrum. By transforming sensor readings into frequency spectra and comparing them against baseline spectra, the system can identify sensor failures through spectral analysis, achieving both high precision and maintained bandwidth.
2Difficulty of detecting and measuring
If signal-based detection with frequency-domain analysis is used, then detection capability is improved, but accuracy in capturing sensor failures is limited
Solution Approach 1:
The patent performs preliminary action by establishing baseline frequency spectra for each sensor during normal operation before failures occur. These baseline spectra are stored and used for comparison against future sensor readings, enabling accurate detection of deviations that indicate sensor failures. This preliminary characterization of normal sensor behavior significantly improves detection accuracy.
Solution Approach 2:
The patent implements feedback by continuously comparing current sensor frequency spectra against the stored baseline spectra and using the comparison results to detect failures. The system provides feedback through the generation of failure detection signals when deviations exceed threshold values, enabling real-time monitoring and accurate capture of sensor failures.
3Reliability
If conventional diagnosis technology is used to distinguish normal state from anomaly, then abnormal states can be detected, but identification of specific failure causes including abnormal phenomena and parts is difficult
Solution Approach 1:
The patent segments the diagnosis process into distinct stages: baseline spectrum generation, current spectrum analysis, deviation calculation, and failure cause identification. By dividing the complex diagnosis task into manageable segments with clear sequential steps, the system achieves reliable abnormal state detection while simplifying the identification of specific failure causes through structured analysis.
Data Source
Figure 1
Figure 2A~2B
Figure 3
AI summary
A system for performing predictive analysis and diagnostics is disclosed. The system includes a plurality of sensors communicatively coupled to a vehicle electronics unit. The plurality of sensors are configured to generate at least one first signal indicative of a first sensed condition and at least one second signal indicative of a second sensed condition. A remote central processing system is coupled to the vehicle electronics unit. The remote central processing system comprises a remote processor and a remote data storage device, wherein the remote central processing system is configured to receive each of the at least one first and second signals. A predictive diagnostic unit is arranged in the remote data storage device and comprises machine readable instructions that, when executed by the remote processor, causes the system to partition the second signal into a predetermined number of successive time intervals; generate a similarity value based on a comparative analysis between the partitioned second signal and a stored first signal; and determine an estimated degree of failure of a machine component based in part on a computed average of the similarity value.