Agent‐based monitoring using case‐based reasoning for experience reuse and improved quality

The purpose of this paper is to propose an agent‐based condition monitoring system for use in industrial applications. An intelligent maintenance agent is described that is able to autonomously perform necessary actions and/or aid a human in the decision‐making process. An example is presented as a case‐study from manufacturing of industrial robots.

The paper is mainly based on a case‐study performed at a large multi‐national company aiming to explore the usefulness of case‐based experience reuse in production.

This paper presents a concept of case‐based experience reuse in production. A maintenance agent using a case‐based reasoning (CBR) approach to collect, preserve and reuse available experience in the form of sound recordings exemplifies this concept. Sound from normal and faulty robot gearboxes are recorded during the production end test and stored in a case library together with their diagnosis results. Given an unclassified sound signal, relevant cases are retrieved to aid a human in the decision‐making process. The maintenance agent demonstrated good performance by making right judgments in 91 per cent of all the tests, which is better than an inexperienced technician.

Experienced staffs acquire their experience during many years of practice and sometimes also through expensive mistakes. The acquired experience is difficult to preserve and transfer and it often gets lost if the corresponding personnel leave their job due to retirements, etc. The proposed CBR approach to collect, preserve and reuse the available experience enables a large potential for time and cost savings, predictability and reduced risk in the daily work. The paper exemplifies experience reuse for quality improvement in production using a number of methods and techniques from artificial intelligence.

The main focus of this paper is to show how to perform efficient experience reuse in modern production industry to improve quality of products. Two approaches are used: a case‐study describing an example of experience reuse in production using a fault diagnosis system recognizing and diagnosing audible faults on industrial robots and an efficient approach on how to package such a system using the agent paradigm and agent architecture.