Integrated decision support and expert systems in a computer integrated manufacturing environment

In a computer integrated manufacturing (CIM) environment, well planning, control and operational process require both expert knowledge of the area, and powerful decision support capabilities. This paper discusses the features of decision support systems and expert systems, and their integration to support the major functions from marketing and strategic level considerations to manufacturing operational planning and process. From the hierarchical structure of information flow in a company, this paper attempts to find the best way of combining decision support systems with expert systems in enhancing the planning, control and operational functions in a CIM environment.     

The future role of expert systems in manufacturing

Expert Systems is an AI technique that is getting a lot of attention in the technical press. The number of articles seems to far exceed the number of functional systems.

It is this author's opinion that a very long, rough road lies ahead before Expert Systems will be functional on the factory floor. However, there are tremendous values possible if the technology can be applied.     

Applicability of expert systems to flexible manufacturing

The following report will discuss the applicability and impact of knowledge-based systems in flexible manufacturing using the Integrated Manufacturing and Assembly System at the Machine Tool Laboratory (WZL), Technical University of Aachen, as a potential application case.     

Assessment of the application of expert systems in flexible manufacturing

The following report will discuss the applicability and impacts of knowledge-based systems in flexible manufacturing using the Integrated Manufacturing and Assembly System at the Machine Tool Laboratory (WZL), Technical University of Aachen, as a potential application case.     

An expert system for manufacturing systems machine selection

This work presents the development of a prototype expert system (ES) for the machine selection of manufacturing systems. This tool, called ESMRS (Expert System for Manufacturing Resource Selection) is used in a simulation based approach in order to structure the solution search mechanism and to overcome the try and error aspect. In fact, in such an approach a number of ‘simulation—ES optimization’ cycles are run until obtaining non-improvable performance measures. The ES main role is to suggest resource modifications based on due date related performance measures obtained through simulation. So, this paper introduces the ‘ES—simulation approach’ that constitutes the utilization scope of ESMRS and then describes the ES static and dynamic knowledge representation before presenting the basic ES features as well as its development using a commercial ES shell. Finally a simple case study illustrates the validity of the approach and its potential applicability for real cases.     

The application of expert systems to manufacturing process control

In recent years the control of the manufacturing process has received prime focus of manufacturers throughout the world. Expert systems technology allows for the implementation of sophisticated and efficient process control systems. This paper provides a framework for the application of expert systems to manufacturing process control. It details the unique features of such a system and explains the constitution of the knowledge base.     

Visual programming environment for hybrid expert systems

This paper proposes an architecture for hybrid expert system development which combines expert problem-solving functions and other conventional computational functions by visual programming technology. The visual programming technique is used both for task-specific knowledge representation and for procedural programming for connecting functional components. In knowledge representation, knowledge is visually represented in the form of decision tables and decision trees. In procedural visual programming, each functional object is displayed as a box-shaped icon with accessible ports which are connected by wires on the graphic editor. Based on the architecture, an expert system shell for the classification task, called HOLON/VP(DT), is incorporated in a visual programming system called HOLON/VP. This paper briefly describes the tool and its evaluation based on some application systems developed with the tool.     

Designing wire-rope-based mechanical systems in an expert system environment

This paper presents concepts related to the development of an expert system suitable for wire-rope-based mechanical system design. The design of mechanical systems with wire ropes, involving the selection of a wire rope and its supporting structure, is currently accomplished by implementing a cataloged solution for the given application and is typically performed without benefit of detailed analysis. For the most part, resulting systems reflect the wire rope engineer's preferences and experience with various wire rope configurations and designs. The current study presents concepts for an expert systems approach to the design problem that utilizes recently developed, detailed wire rope analysis capabilities. Thus the expert system not only incorporates the expertise in the form of rules but also interacts with analysis packages for design development. It is believed that wire rope systems designed in this manner may prove less costly to manufacture and have lifetimes exceeding those currently specified for most applications.     

GAMEES: a probabilistic environment for expert systems

This paper describes GAMEES (Graphical Modelling Environment for Expert Systems), an interactive graphical environment for building and processing Belief Networks and Influence Diagrams. We review the existing systems designed for analogous purposes, and, after a brief introduction to Belief Networks and Influence Diagrams, we describe the graphical interface, discuss algorithms for probabilistic inference on these networks and illustrate the current implementation of GAMEES. The system has been designed for being integrated within wider expert systems and actually it is part of the Therapy Advisor module within an expert system for the management of anemic patients.     

An intelligent simulation environment for manufacturing systems

The manufacturing field is an area where the application of simulation is an essential tool for validating methods and architectures before applying them on the factory floor. Despite the fact that there are a great number of simulation tools, most of them do not take into account the specific requirements of the “new manufacturing era” such as distributed organization, interoperability, cooperation, scalability, fault tolerance and agility. On the other hand, Multiagent System technology has demonstrated its utility in manufacturing system modeling and implementation. Agenthood features such as proactivity, reactivity, and sociability may also be useful for associating them with the specific simulation needs of the new changing requirements for manufacturing systems. In this paper, an Agent-supported Simulation Environment for intelligent manufacturing systems is presented. The different roles that are played by the agents of the simulation environment are defined taking into account the specific dynamic features in manufacturing simulation and the requirements of the new manufacturing era. Moreover, the interaction and cooperation scenarios among these agents are specified to facilitate manufacturing simulation in an appropriate and flexible way. A detailed evaluation study, with regards to the new manufacturing era requirements, demonstrates the advantages of the proposed approach over current state-of-the-art proposals.     

Object knowledge environment for manufacturing systems layout design

This article proposes an object knowledge environment to support manufacturing systems layout design, as an alternative to classical functional softwares. It justifies this transition to an object-oriented paradigm by the advantages in openness of the system, as well as increased flexibility and modularity, and higher potential for abstraction and hierarchical structure formation. the implemented environment uses the SMALLTALK-80 language. It supports hierarchical classes of objects such as cell, aisle set, facilities structure, flow, set, relationship set, flow networks, independent objects, evaluators, and optimizers. the layout designer can interact directly with all defined objects through the use of individual model-view-controller triads.     

Flexible manufacturing systems—Manpower problems and policies

Flexible manufacturing systems can be seen as the latest stage in the automation of small batch production. The prevealing manpower approach to these systems is characterized by a hierarchical and highly specialized job structure. An alternative is to have a homogenous job structure on an advanced skill level. The latter approach increases problems and costs of implementation processes; however, it may ensure higher utilization times, more flexibility, and better quality in the long run. Trends in small batch and process manufacturing, the labor market, and union policies provide opportunities for the alternative approach.     

Integrating the grouping and layout problems in cellular manufacturing systems

In this paper, the simultaneous solution of the machine grouping and layout problems in cellular manufacturing systems is explored. A model for the combined problem is presented. Since the model is complex to solve using traditional optimization techniques, a suboptimal procedure involving the use of a simulated annealing based algorithm is suggested. Results with a numerical example are presented. An alternative formulation based on quandratic assignment problem is also presented.     

Multi-period part selection and loading problems in flexible manufacturing systems

We consider multi-period part selection and loading problems in flexible manufacturing systems with the objective of minimizing subcontracting costs. The part selection problem is to select sets of part types and to determine their quantities to be produced during the upcoming planning horizon while satisfying due dates of all orders for the parts, and the loading problem involves allocation of operations and required tools to machines. Production demands should be satisfied for periods through subcontracting if production demands cannot be satisfied by the system due to machine capacity or tool magazine capacity constraints. For the part selection and loading problems, we develop three iterative algorithms, called the forward algorithm, the backward algorithm and the capacity approximation algorithm, that solve the part selection and loading problems iteratively for each period. To compare the three algorithms, a series of computational experiments is done on randomly generated test problems.     

The complementary roles of expert systems and database management systems in a design for manufacture environment

Effective product design that satisfies functional requirements and can be manufactured easily requires vast amounts of knowledge on the part of the design engineer. This paper focuses on the complementary roles of expert systems and database management systems as they relate to the Intelligent Design System (IDS) in a Design for Manufacture (DFM) environment. Each technology complements the other in its strengths and abilities. The database management system provides during the design process. The expert system provides a reasoning mechanism for identifying manufacturing violations and generating meaningful recommendations. These components work cooperatively with a CAD interface to form a unified, intelligent design environment.An information flow analysis of the Intelligent Design System resulted in the development of three distinct classifications of information within the database: CAD data, a design catalog, and a knowledge base. The CAD data tables employ an, object oriented approach to store specific information about the physical contains cost, weight, and strength characteristics of the standard parts and fasteners used within the system. The knowledge base contains rules and heuristics concerning design and manufacturing methodologies.The placement of the expert system rules in the database represents an innovation. As a result, the expansion and updating of the materials, fasteners, standard parts, or manufacturing processes used by the Intelligent Design System is facilitated without increased due to the efficient management of the knowledge base by the database management system. This allows the designer to modify the knowledge and help the system to learn without the need for a knowledge engineer.     

Enabling multi-use, multi-tool models of manufacturing systems through an experimental frame expert system

A significant shortcoming of traditional modeling methodologies is the limited access they provide for decision-makers who are not modeling specialists. This paper presents an expert system approach to address this shortcoming. An expert system called the experimental frame expert system (EFES) was developed for this purpose within an advanced modeling environment for manufacturing systems. EFES reduces the dependence upon modeling specialists, and thus, makes models, both analytical and simulation, more accessible to decision-makers. This is accomplished by using two knowledge bases, one related to the manufacturing system specific symptoms and problems, and the other to system analysis and optimization tools. This paper presents the dissertation research effort that led to development of these two knowledge bases as well as the EFES framework within the advanced modeling environment.     

Design and planning problems in flexible manufacturing systems: a critical review

This review paper describes the state-of-the-art research on flexible manufacturing systems (FMS) design and planning issues. The emphasis is on presenting research results coming out of the current FMS literature that help the FMS manager in setting up a highly efficient manufacturing system. In addition to that, it discusses relevant research contributions after 1986, that were not part of any of the previous survey papers on operations research models for FMSs. Also, applications of combinatorial optimization approaches to FMS planning problems are adequately exposed in the paper.     

Intelligent design of a dynamic machine layout in uncertain environment of flexible manufacturing systems

Since Facility Layout Problem (FLP) affects the total manufacturing cost significantly, it can be considered as a critical issue in the early stages of designing Flexible Manufacturing Systems (FMSs), particularly in volatile environments where uncertainty in product demands is inevitable. This paper proposes a new mathematical model by using the Quadratic Assignment Problem formulation for designing an optimal machine layout for each period of a dynamic machine layout problem in FMSs. The product demands are considered as independent normally distributed random variables with known Probability Density Function (PDF), which changes from period to period at random. In this model, the decision maker’s defined confidence level is also considered. The confidence level represents the decision maker’s attitude about uncertainty in product demands in such a way that it affects the results of the problem significantly. To validate the proposed model, two different size test problems are generated at random. Since the FLP, especially in multi-period case is a hard Combinatorial Optimization Problem (COP), Simulated Annealing (SA) meta-heuristic resolution approach programmed in Matlab is used to solve the mathematical model in a reasonable computational time. Finally, the computational results are evaluated statistically.