On Applying Case-based Reasoning And Association Rules In Car Intelligent Fault Diagnosis

Aiming at developing a chery car fault diagnosis system, the paper proposed a series of approaches to solve the problem encountered in car intelligent fault diagnosis on the basis of fault diagnosis, case-base reasoning and association rules.Case-based reasoning (CBR) is a recently developing technique in fault diagnosis field. It's quite significant for pushing the development of the fault diagnosis technique to apply the technique in fault diagnosis field。The car fault case is classified as case sets by characteristic according to the demand of fault diagnosis system on the foundation of characteristic-based case expression. The multi-Categories structure of the knowledge base of the system is formed in accordance with the key characteristic abstracted from fault cases, which reduces the complexity of case expression and management and construction and enhances the index speed and efficiency dramatically.Association rule mining is one of the important contents in data mining and it aims to discover the interesting connection or the correlation with a set of objects in a database. Application of association rules in car fault diagnosis, finds the relationships between fault categories from data mining in a large number of car fault cases, which are reflected in the form of the rules, and predict the fault. Association rule and case-based reasoning, accomplish fault diagnosis, and improve the car fault diagnostic ability, which made a new solution for car fault diagnosis.