DTC Rulebook Generation for Predictive Vehicle Fault Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Vehicle Health Management (VHM) solutions are primarily preventive and reactive, providing information only after a malfunction has occurred, lacking predictive capabilities to detect issues early through Diagnostic Trouble Code (DTC) patterns in telemetric data.
Innovation Solution
A Diagnostic Trouble Code (DTC) rulebook generation system that processes telematics trace data and malfunction occurrence data to extract ride records, label them as healthy or faulty, train machine learning models, and generate DTC rules with precision thresholds, enabling early detection of malfunctions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional preventive and reactive maintenance solutions are used, then the system provides information after malfunction occurrence, but it lacks predictive capability for early malfunction detection
Solution Approach 1:
The system performs preliminary actions by training machine learning models on historical telematics data and malfunction records before actual malfunctions occur. This creates pre-established prediction capabilities that enable early detection of malfunctions by analyzing DTC patterns in real-time data, transforming reactive maintenance into predictive maintenance.
Solution Approach 2:
The system prepares beforehand by building a comprehensive database of historical telematics trace data and malfunction occurrence records, and by training multiple machine learning models (logistic regression, decision trees, gradient boosting, neural networks) in advance. This preparatory work cushions against future malfunctions by establishing prediction frameworks that can immediately detect and alert potential issues before they manifest as actual failures.
2Measurement precision
If machine learning models are trained on historical data to discover DTC patterns, then predictive accuracy improves, but system complexity increases
Solution Approach 1:
The system segments the prediction task by training multiple specialized machine learning models (logistic regression, decision tree, gradient boosting, neural network) on different aspects of the historical data. Each model focuses on specific DTC patterns and malfunction types, allowing the system to achieve high prediction accuracy through ensemble methods while managing complexity by dividing the overall prediction function into manageable specialized components.
Solution Approach 2:
The system creates a universal predictive framework that handles multiple types of malfunctions and DTC patterns through a single integrated architecture. The machine learning models are trained on comprehensive historical data encompassing various vehicle types, malfunction scenarios, and telematics parameters, enabling the system to generalize across different situations and maintain high prediction accuracy without requiring separate specialized systems for each malfunction type.
3Measurement precision
If multiple machine learning models are trained on labeled ride records, then rule precision improves, but training time and computational resources increase
Solution Approach 1:
The system applies partial action by training multiple machine learning models on different subsets or aspects of the labeled ride records rather than requiring all models to process the entire dataset equally. This approach allows each model to achieve sufficient precision on its specific task without the excessive computational burden of training all models on all data, balancing prediction accuracy with training efficiency.
Data Source
AI summary
A Diagnostic Trouble Code (DTC) rulebook generation system, the DTC rulebook generation system comprising a processing circuitry configured to: obtain: telematics trace data records and malfunction occurrence data records; and extract one or more ride records from the obtained telematics trace data records and the obtained malfunction occurrence data records, wherein at least one ride record of the ride records is for a given vehicle; label at least one ride record of the ride records as a healthy ride or a faulty ride, wherein a ride record associated with a given vehicle where no malfunction occurrence data records are associated with the given vehicle is labeled as a healthy ride, otherwise the ride record is labeled as a faulty ride; train one or more machine learning models on one or more subsets of the labeled ride records; determine one or more DTC rules utilizing at least one of the trained machine learning models.