On-Board Computing Predictive Failure Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicular diagnostic systems fail to efficiently identify and predict component failures, leading to unexpected breakdowns and unsafe circumstances, as they require trained technicians for diagnosis and do not provide advance statistical forecasting of component failures.
Innovation Solution
An automotive predictive failure and alerting system that uses on-board computing devices to collect and analyze data from vehicle sensors, creating primary and secondary datasets to detect performance deviations and predict failures, notifying owners or drivers through real-time alerts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional diagnostic systems are used with trained technicians performing pass/fail tests, then defect detection can be performed, but the system cannot statistically forecast component failure in advance and requires human intervention
Solution Approach 1:
The system performs preliminary actions by continuously collecting sensor data and calculating performance efficiencies before actual failure occurs. The OBC device computes part-performance efficiency metrics in real-time, establishing baseline patterns of normal operation, and uses these to predict future failures before they happen, enabling preventive maintenance
Solution Approach 2:
The system implements feedback by continuously monitoring sensor data, comparing actual performance against established patterns and thresholds, and generating alerts when degradation is detected. The system feeds back performance efficiency calculations to the owner/driver through notifications, creating a closed-loop diagnostic system that adapts to vehicle-specific operating patterns
2Measurement precision
If pass/fail testing is performed by trained technicians, then automotive problems can be identified, but the process is not efficient and cannot detect small deviations from normal performance
Solution Approach 1:
The system enables self-service diagnostics by automatically collecting sensor data, calculating performance efficiencies, identifying deviations from normal patterns, and generating failure predictions without requiring trained technicians. The OBC device autonomously processes sensor inputs and provides diagnostic information to the owner/driver through the user interface
Solution Approach 2:
The system applies partial action by focusing measurements on critical performance parameters that indicate potential failures. Rather than performing comprehensive pass/fail tests on all components, the system continuously monitors key sensor data points and calculates performance efficiencies for specific vehicular parts, detecting small deviations before they become critical failures
3Loss of information
If the vehicular user interface indicates general warnings without specific problem identification, then owners/drivers can be alerted, but further testing by trained technicians is still required to detect the exact problem
Solution Approach 1:
The system replaces the mechanical need for trained technicians to interpret diagnostic data with an automated computational system. The OBC device processes sensor inputs, calculates performance efficiencies, identifies failure patterns, and communicates specific diagnostic information to the owner/driver through the user interface, substituting human expertise with automated analysis
Data Source
AI summary
A method of predicting failure for vehicular components is implemented within a vehicle through a plurality of part sensors and an on-board computing (OBC) device as the part sensors are communicably coupled with the OBC device. The OBC device continuously timestamps and uploads a plurality of performance time-dependent data (PTDD) points to the OBC device throughout a current vehicular trip. The OBC device then analyzes the uploaded PTDD points with an updatable total time duration and an active performance-define range that are calculated from prior vehicular trips. The OBC device is then able to identify a potential vehicular problem during the current trip, based upon the uploaded PTDD points. When a potential vehicular problem is detected within the current trip, an annotating assessment is generated and wirelessly sent to a personal computing device of the owner/operator of the vehicle.