A Hybrid Failure Diagnosis and Prediction using Natural Language-based Process Map and Rule-based Expert System

Abstract

Preventive maintenance is required in large scale industries to facilitate highly efficient performance. The efficiency of production can be maximized by preventing the failure of facilities in advance. Typically, regular maintenance is conducted manually in which case, it is hard to prevent repeated failures. Also, since measures to prevent failure depend on proactive problem-solving by the facility expert, they have limitations when the expert is absent, or any error in diagnosis is made by an unskilled expert. In many cases, an alarm system is used to aid manual facility diagnosis and early detection. However, it is not efficient in practice, since it is designed to simply collect information and is activated even with small problems. In this paper, we designed and developed an automated preventive maintenance system using experts' experience in detecting failure, determining the cause, and predicting future system failure. There are two main functions in order to acquire and analyze domain expertise. First, we proposed the network-based process map that can extract the expert's knowledge of the written failure report. Secondly, we designed and implemented an incremental learning rule-based expert system with alarm data and failure case. The evaluation results shows that the combination of two main functions works better than another failure diagnosis and prediction frameworks.