Pascal Lhoste

A Fuzzy Reasoning Classification Method for Pattern Recognition

This paper focuses on a Fuzzy Reasoning Classification Method to improve the potential of pattern recognition in the automated inspection and classification of wooden boards. After the definition of the characteristic features, we implement a fuzzy inference mechanism allowing to take into account the subjectivity of the human visual system. In this article, we have decided to work on the distribution and the representation of the Information. In this sense, our study speaks about the impact of fuzzification on the recognition rates and the structure of our decision module. The part concerning the classification mechanism allows ourselves to integrate knowledge in the generation of the numeric model. This knowledge is enquired at the different field experts thanks to the NIAM formalism. The results, which are presented on a generic benchmark and real data, show the efficiency of such an approach.

A FUZZY RECOGNITION MODEL BASED ON HUMAN SKILL INTEGRATION

Abstract This article presents the improvement of a defect recognition system for fibrous products by using knowledge integration from two expert fields. These two kinds of knowledge that we want to integrate respectively concern wood expertise and industrial vision expertise. First, extraction, modelling and integration of knowledge use the Natural language Information Analysis Method (NIAM) to be formalised from their natural language expression. Then, to improve a classical industrial recognition system using vision, we propose to use the resulting symbolic model of knowledge to partially build a numeric model of defect recognition. This model is created according to a tree structure where each inference engine is a Fuzzy Rules based Inference System. The expert knowledge model previously obtained is used to configure each node of the resulting hierarchical structure. The practical results we obtained with industrial data show the efficiency of such an approach.

Category Theory Based Approach for IMS Modelling

Abstract Main researches and developments in IMS, MAS (Multi-Agent System) and HMS (Holonic Manufacturing System) for manufacturing plant control and management as well as manufacturing enterprise networking are based on ICTs (Information & Communication Technologies) based approaches. Beyond these technology-driven approaches, the field of ‘Intelligence in Manufacturing’ requires sound scientific foundations in order to meet systematisation in modelling as originally addressed by (Yoshikawa, 1995). In this way, this paper deals with principles and elements of the Category Theory as a coherent mathematical framework in order to move to more prescriptive and ‘bottom-up’ modelling approaches able to better understand and model the dynamical emergent properties of new agile manufacturing systems.