Vehicle Prognostics Using Multivariate Mixture Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle prognostic systems lack the ability to accurately detect anomalies in vehicle subsystems using multivariate data analysis, leading to inefficient remedial actions and potential vehicle failures.
Innovation Solution
A method involving the extraction of feature combination data from vehicle sensor data, using multivariate mixture models such as bivariate and trivariate Gaussian mixture models to evaluate anomaly detection scores, and determining affected vehicle subsystems for targeted remedial actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multivariate mixture models are used to evaluate anomaly detection scores for feature combinations, then measurement precision of anomaly detection is improved, but device complexity increases
Solution Approach 1:
The system segments the anomaly detection process by creating multiple anomaly detection functions, each specialized for specific feature combinations (bivariate, trivariate, etc.). This segmentation allows complex multivariate analysis to be broken down into manageable, specialized functions that can be selected and applied based on the specific features being analyzed, improving precision without overwhelming system complexity.
Solution Approach 2:
The system changes parameters by selecting different mixture model configurations (bivariate, trivariate, etc.) based on the specific feature combination being analyzed. This parameter-based approach allows the system to adapt the complexity of the analysis to the specific needs of each feature set, achieving high measurement precision when needed while managing overall device complexity through selective application.
2Reliability
If multiple anomaly detection functions are created for different feature combinations, then reliability of vehicle subsystem monitoring is improved, but device complexity increases
Solution Approach 1:
The system implements universality by creating a framework where multiple anomaly detection functions operate under a unified architecture. Each function is specialized for particular feature combinations but they all follow the same evaluation and scoring methodology, allowing the system to achieve high reliability through comprehensive coverage while managing complexity through standardized processing routines.
Solution Approach 2:
The system applies preliminary action by pre-defining multiple anomaly detection functions for different feature combinations before runtime. This allows the system to have reliable, pre-configured detection capabilities for various vehicle subsystems while avoiding the complexity of dynamically creating detection logic during operation. The functions are prepared in advance and simply selected and applied based on the features being monitored.
3Productivity
If feature combination data is extracted and evaluated using multivariate models, then productivity of anomaly detection is improved, but use of energy increases
Solution Approach 1:
The system applies partial action by selecting and applying only the necessary anomaly detection functions based on the specific feature combinations being analyzed. Rather than running all possible multivariate models continuously, the system selectively applies bivariate, trivariate, or other models only when relevant feature combinations are present, improving productivity while reducing unnecessary energy consumption from excessive computational operations.
Data Source
AI summary
A system and method of method of carrying out a remedial action in response to a vehicle prognosis, the method including: receiving vehicle feature data from a vehicle; extracting a plurality of feature combination data from the vehicle feature data, wherein each of the feature combination data pertains to a feature combination, wherein each of the feature combinations includes two or more vehicle features; for each extracted feature combination data, then: (i) evaluating the extracted feature combination data using an anomaly detection function based on a multivariate distribution mixture model; and (ii) obtaining an anomaly detection score for each extracted feature combination based on the evaluating step; determining a vehicle subsystem that comprises a portion of vehicle electronics installed on the vehicle and that is likely experiencing a problem or unusual behavior based on the anomaly detection scores; and carrying out a remedial action in response to the determining step.