Novel Agent Based-approach for Industrial Diagnosis: A Combined use Between Case-based Reasoning and Similarity Measure

Abstract

-In spunlace nonwovens industry, the maintenance task is very complex, it requires experts and operators collaboration. In this paper, we propose a new approach integrating an agentbased modelling with case-based reasoning that utilizes similarity measures and preferences module. The main purpose of our study is to compare and evaluate the most suitable similarity measure for our case. Furthermore, operators that are usually geographically dispersed, have to collaborate and negotiate to achieve mutual agreements, especially when their proposals (diagnosis) lead to a conflicting situation. The experimentation shows that the suggested agent-based approach is very interesting and efficient for operators and experts who collaborate in INOTIS enterprise.

An Adapted Approach for User Profiling in a Recommendation System: Application to Industrial Diagnosis

“…In order to demonstrate the effectiveness of the new tool and its influence in the collaborative platform, precisely in reasoning engine as shown in Fig. 3 (section 3) we use the same cases presented in [26].…”

“…We discussed the results which are obtained from the recommendation tool and collaborative support system (without recommendation tool). This discussion presents the quality of documents that are recommended to industrial operators is not based only on the similarity measure of case-based reasoning [26] but on the number of relevant documents that are considered as inputs also. This comparative study allowed us…”

Editor's Note

“…Continuing with multi-agent based approaches, next paper authored by Benkaddour et al [11] proposes a system for solving industrial diagnostic problems based on agent-based modelling with case-based reasoning, as an alternative to reasoning rules. The system specifically provides a classification of the solutions given by operators in maintenance tasks, ranking them.…”