Intelligent design and planning of manual assembly workstations: A neuro-fuzzy approach

Abstract

The design of manual assembly workstations, as with most forms of designs, is highly iterative and interactive. The designer has to consider countless constraints and solutions for contradictory goals. In order to assist the designer in design process, it is required to develop a new intelligent methodology and system. This paper develops a neurofuzzy hybrid approach to intelligent design and planning of manual assembly workstations. Problems, related to workstation layout design, planning, and evaluation, are discussed in detail. A fuzzy neural network is used to predict the ranges of anatomical joint motions and to design or adjust workstations and tasks. The neuro-fuzzy computing scheme is integrated with operator's posture analysis and evaluation. For training and test purposes, experiment is carried out to simulate assembly tasks on a multi-adjustable assembly workstation equipped with a flexible PEAK motion measurement and analysis system. The trained neural network is capable of memorizing and predicting the joint angles associated with a range of workstation configurations. Thus, it can also be used for the design/layout and on-line adjustment of manual assembly workstations. Thus, the developed system provides a unified, computational intelligent framework for the design, planning and simulation of manual assembly workstations.