A knowledge-based decision support system for the management of parts and tools in FMS

Abstract

Flexible manufacturing systems (FMS) are very complex systems with large part, tool, and information flows. The aim of this work is to develop a knowledge-based decision support system (KBDSS) for short-term scheduling in FMS strongly influenced by the tool management concept to provide a significant operational control tool for a wide range of machining cells, where a high level of flexibility is demanded, with benefits of more efficient cell utilization, greater tool flow control, and a dependable way of rapidly adjusting short-term production requirements. Development of a knowledge-based system to support the decision making process is justified by the inability of decision makers to diagnose efficiently many of the malfunctions that arise at machine, cell, and entire system levels during manufacturing. In this context, this paper proposes three knowledge-based models to ease the decision making process: an expert production scheduling system, a knowledge-based tool management decision support systems, and a tool management fault diagnosis system. The entire system has been created in a hierarchical manner and comprises more than 400 rules. The expert system (ES) was implemented in a commercial expert system shell, Knowledge Engineering System (KES) Production System (PS).

Introduction

Increasing global competition has made many manufacturing companies recognize that competitive manufacturing in terms of low cost and high quality is crucial for success. In an attempt to improve their competitive edge, manufacturers have for some time been turning to flexible manufacturing systems (FMS). Management of tools and parts is recognized as a critical issue in the operation of FMS. Although new technologies, such as sophisticated machining facilities, factory-wide intelligent handling mechanisms, and hierarchical cell control systems, have increased the flexibility and provided system users with a significant infrastructure, many systems have failed to take advantage because of increasing complexity in operation and control of machining cells.

Part and tool flows, two major dynamic entities, are the key factors for managing successful manufacturing. Stecke and Kim [19] formulated the tool allocation problem as a nonlinear programming model. Positioning of tools in the magazine and the magazine capacity were considered as primary constraints. Balancing the assigned machine processing times and maximising the tool density of each magazine with the tool allocation are the objectives of the formulation. Coleman et al. [7] studied tool management and job allocation in flexible machining cells using work-oriented strategies. This spreadsheet-based model presents and investigates strategies for tool management and job allocation in a demand-driven system. The paper's major concern is to measure the effects of tool management strategies on machining cells under the influence of job allocation rules. Coleman et al. [8] developed a similar model of tool management and job allocation in machining cells using tool-oriented strategies. This paper presents a tool-oriented approach to provide further tooling economy. The model employs a clustering algorithm to identify part and tool groups. These clustered groups are allocated to a particular machining cell configuration with respect to the additional constraints of balancing the overall work load per machine and managing tool kit exchange under limited tool magazine capacity.

Amoaka-Gyampah et al. [3] compared tool management strategies and part selection rules. They described four tool management strategies and three part selection rules, two concentrating on tooling and the rest on earliest due date (EDD). They also developed a simulation model and used five performance measures. Although this paper primarily deals with tool management in FMS, all of the performance measures used focus on the part and general system spectrum, neglecting major tool management performance criteria such as tool requirements and tool inventory. Rahimifard and Newman [16] developed a multischeduler system that schedules the jobs, fixtures, and tools. This simulation-based work uses the traditional part and tool scheduling strategies along with careful planning and scheduling of fixtures within a highly automated flexible cell. Three planning strategies are considered, namely workpiece-dominated planning strategy, tool-dominated planning strategy, and fixture-dominated planning strategy when the schedule of the three concerned dynamic entities. The paper argues that the simultaneous assignment planning of these three dynamic entities has great advantages in terms of cell performance and cell control and presents the several simulation results and performance measures.

Acaccia et al. [1] developed an expert simulation of tool distribution for factory automation and discussed tooling integration in flexible manufacturing for a short-term manufacturing period. Tool dispatching is considered, in an integrated environment, to be delivering the required tools at the right time to the right station while keeping plant flexibility and other performance criteria of the system. Acaccia et al. [2] proposed another expert system (ES) approach to provide an expert scheduling system for tool stock to satisfy long-term production requirements. An expert simulation system algorithm has been developed to satisfy production requirements as well as keep the tool stock level reasonably low. An extensive and more detailed literature survey of TMS can be found in Ref. [13]. There are some researches that offer decision support solutions to part scheduling, fault diagnosis, or system design in flexible manufacturing systems [6], [10], [11], [15], [17], [18]. However, none of the papers found in the literature deals with the decision support system (DSS) for the integrated management of tool and part flows in FMS. There is a shortage of research in DSS for integrated tool and part flow management as well as cell control and tool management system operation diagnosis.

In this paper, we aim to apply a knowledge-based decision support system (KBDSS) to short-term scheduling in FMS, strongly influenced by tool management concept to provide a significant operational control tool for a wide range of machining cells, where a high level flexibility is demanded, with benefits of more efficient cell utilization, greater tool flow control and a dependable way of rapidly adjusting short-term production requirements. The development of a knowledge-based system to support the decision making process was justified by the inability of decision makers to efficiently diagnose many malfunctions, which arose at machine, cell, and entire system levels during manufacturing operations. In this context, this paper proposes three integrated knowledge-based models to ease the decision making process by providing an expert aid both at design and at operational levels. These are the knowledge-based production scheduling, the knowledge-based tool management strategy selection (KBTMSS) system, and the knowledge-based manufacturing and tool management fault diagnosis system.