Multiconcept classification of diagnostic knowledge to manufacturing systems: Analysis of incomplete data with continuous-valued attributes

The performance of a manufacturing system is largely dependent upon the condition of its system components. By closely monitoring the condition of critical system components and carrying out timely system diagnosis as soon as a fault symptom is detected would help to reduce system down time as well as improving overall productivity. To achieve this, an effective diagnostic system is absolutely necessary. In recent years, computerized diagnostic systems such as knowledge-based systems have been developed to assist engineers in performing system diagnosis. These computerized systems require sufficient knowledge to be acquired within a short time, which is not an easy task in reality, especially in the case of acquiring knowledge from imprecise/incomplete data. Consequently, there is a need to look into ways to extract diagnostic rules from the raw information/data gleaned from a manufacturing system in an efficient manner. The paper presents an approach that can extract diagnostic knowledge from incomplete data with continuous-valued attributes. It begins with a brief discussion on the treatment of continuous-valued attributes for both twin-concept and multiconcept classification. Subsequently, a detailed discussion on the treatment of incomplete information is presented. A case study is used to validate the application of the proposed approach. Results show that the rules induced are logical and quite consistent with those obtained from domain experts. The details of the case study and results are presented.