Ontology-driven data collection and validation framework for the diagnosis of vehicle healthmanagement

Abstract

The current warranty data collection processes exhibit several data quality issues – the level of detail and precision is missing in the collected data, the semantic heterogeneity is observed and no systematic data quality validation mechanism to automatically certify the data quality. Such data cannot be translated seamlessly into the knowledge assets to perform business functions, for example, fault diagnosis. An ontology-driven structured data collection framework is proposed to acquire the necessary data in the warranty domain. The proposed framework uses the integrated vehicle health management ontology as an information model to populate necessary data acquisition fields of the framework. A novel three-dimensional data quality metric is proposed to validate the completeness, correctness and relevance of newly collected data. We also evaluate the performance of the tool by using the real-life data. The data accuracy precision after using the framework has been improved from 0.30 to 0.80, whereas the recall is improved from 0.28 to 0.70. Furthermore, the precision and recall of the tool is evaluated for the 500 real-life field failure cases and it was greater than 90% for data completeness and relevance. Throughout this paper we will use the words ‘correctness’ and ‘accuracy’ interchangeably.

Keywords:

• data integration and exchange
• knowledge management
• knowledge sharing and reuse
• ontology
• computer integrated manufacturing

Acknowledgements

The authors thank Dr. Kallappa Pattada and Dr.Ravikumar Karumanchi (General Motors, Global R&D) for their valuable feedback on the earlier drafts of the paper, which helped to improve its quality.

Notes

1. FRACAS: http://www.aldservice.com/en/reliability-products/fracas.html.

2. The DTCs are generated when the vehicle components violate the threshold limit to which they are set. These DTCs are stored in a vehicle memory bus of an on-board computer. When a customer visits a dealer to report a fault, the DTCs are extracted to get an insight into the nature of faults associated with systems, subsystems andcomponents, and the appropriate corrective repair actions are taken.

3. The status byte information is associated with each DTC, which helps technician to determine whether a specific DTC is a current symptom associated with a fault or a historical one set previously.

4. Parameter Identifiers (PIDs) are the codes used to request diagnostic specifications sensory data (e.g. Voltage, Temperature, Pressure, and so on) from vehicles in compliance with the OBD-II system.

5. The data specifying the manner in which a system or a subsystem failure has occurred. Typical failure modes can be premature failure, failing to operate at a prescribed time, failure to cease operation and degradation in the performance.

6. RDFS is a World Wide Web Consortium specification for describing the Metadata model.