The client-centred approach: expert system development

Abstract: This paper describes a project that is studying an expert system (ES) development method tailored to meet the requirements of small and medium-sized enterprises (SMEs). It is posited that many such organisations cannot use ES technology because of its high entry price and because the available tools and methods were developed for and by large organisations. Within this context our development method encompasses the entire life cycle of an ES from initial conception to implementation through to maintenance and updating. The central premise is that the method should be 'client-centred', emphasising what the client can see, rather than being 'technology-centred', emphasising how the knowledge engineers work. Discussion includes how this methodology addresses many criticisms of current ES development methods, including rapid prototyping and KADS.     

A graph-based approach for rule integrity and maintainability in expert system maintenance

Just as conventional software systems have maintenance costs far exceeding development costs, so too do rule-based expert systems. They are frequently developed by an incremental and iterative method, where knowledge and decision rules are extracted and added to the system in a piecemeal manner throughout system evolution. Thus, ensuring the correctness and consistency of the rule base (RB) becomes an important, though challenging task. However, most research work in expert systems has focused on building and validating rule bases, leaving the maintenance issue unexplored. We propose a graph-based approach, called the object classification model (OCM), as a methodology for RB maintenance. An experiment was conducted to compare the OCM with traditional RB maintenance methods. The results show that the OCM helps knowledge engineers retain rule-base integrity and, thus, increase rule-base maintainability.     

Compass: an expert system for telephone switch maintenance

Abstract: GTE's Compass (Central Office Maintenance Printout Analysis and Suggestion System) is an expert system that aids in the maintenance of a telephone switching system. It analyzes maintenance printouts of telephone company central office switching equipment and suggests maintenance actions to be performed. The results from several field trials indicate that the current version of Compass performs well in identifying system faults and in suggesting corresponding maintenance actions. An expanded version of the expert system is under development while the present version is being put into field use.     

Transfer: An expert system approach to transfer pricing

This paper explores the development of a PC-based expert system for transfer price decision making. The expert system (TRANSFER) is based on the premise that, if the corporate goal structure, market structure, costing systems, and other relevant variables are known, it is possible to arrive at the appropriate transfer price by applying a set of optimization rules. VP-Expert was the PC-based expert system shell used to develop TRANSFER. VP-Expert uses backward chaining to solve problems using IF-THEN rules. TRANSFER was designed, tested, and modified to yield the appropriate transfer pricing strategy in a variety of decision scenarios.     

An expert system approach to quality control

This paper describes the basic actions proposed for quality inspection. These actions involve structuring a Decision Supporting Expert System (DSES) to help with those decisions related to the preliminary activities for inspection development—most of them relating to determining of the need or convenience of carrying out the inspection itself. Once the opportunity to carry it out is defined, the expert system helps the user to select the type of inspection to adopt from amongst: (1) automatic or sensorial inspection; (2) inspection by samples or complete; (3) acceptance or rectifying and, in the most relevant module, (4) inspection by attributes or by variables. The complementary documentation of the DSES contains the directions to operate it, the rules and qualifiers that make up the system, as well as the results achieved through its experimental implementation.     

School bus routing and scheduling: An expert system approach

This paper proposes an expert system approach to routing and scheduling school buses for a rural school system. The expert system is programmed in TURBO PROLOG for use on an IBM/XT and is applied to rural county school systems in Alabama.

The busing problem considered here consists of two components: routing and scheduling. The routing problem is concerned with the determination of a stop-to-stop route to be traversed to each school by each bus whereas the scheduling problem, the determination of times at all bus stops for each bus. A bus may be used for multiple runs. Each route is designed in such a way that the bus capacity, student riding time, school time window and road condition constraints are satisfied while attempting to minimize the number of buses required in operation, minimize the fleet travel time and balance the bus loads.

Conventionally, a predetermined algorithm is coded into computer programs for generating efficient routes and schedules. The user or route designer neither has any knowledge about the algorithm nor has any input of personal expertise into the solution process. As a result, a veteran designer is skeptical of the computer-generated routes and schedules. Moreover, non-quantifiable factors such as safety, preference and judgment are not taken into consideration in the traditional approach.

To alleviate these deficiencies, an expert system approach, which enables the expert knowledge to be kept separately from its execution, is utilized. This knowledge base contains factual knowledge such as road map, school locations, but capacities, stop locations, number of students at each stop, and drivers' homes. It also contains procedural knowledge such as heuristics for finding a route and scheduling multiple runs for a bus subject to various constraints. The inference engine or control program chooses the appropriate heuristics used in constructing efficient routes and schedules with respect to various objectives or goals. A user interface includes the graphic display of road maps and determined routes.     

Analysis of assembly operations difficulty: a fuzzy expert system approach

Typical mechanical products can be assembled in various sequences of assembly operations. These sequences have high impact on the assembly time, machine utilization and even on the product quality. In order to select the best sequence of assembly operations, proper evaluation of the various sequences of assembly operations is required. This, in turn, requires the consistent evaluation of each assembly operation in the sequence. The assembly operations can be evaluated for various criteria, of which the operation difficulty is the most meaningful. This paper describes a methodology to analyse the assembly operations and calculates an operation's degree of difficulty using an expert system. This analysis consists of two steps: the first one identifies the main parameters that affect the assembly difficulty and assigns fuzzy triangular values to these parameters. The second step assigns weights to the parameters in order to maximize the agreement with a domain expert. The expert system analyses the difficulty of the assembly operation performed in two orientations: horizontal and vertical. The expert system then assigns a triangular fuzzy number as the aggregate measure of the operation's difficulty.     

The Fossil expert system

Abstract: Fossil is an expert system for Palaeontology, written in Prolog. It consists of a knowledge base and three interfaces: a collector's 'query' interface; an expert's 'update' interface and a student's 'review' interface. As such, it covers the major uses of a knowledge base in palaeontology. The underlying model of expert system use and its supporting tools are described. This view is an alternative to that provioded by expert system shells of the Apes type. Such an approach has proved useful in Palaeontology and is likely to be applicable to other areas where the knowledge is arranged taxonomically. The use of Prolog as an implementation tool is briefly discussed.     

Using MCRDR based Agile approach for expert system development

Various expert system development approaches were proposed but most of them cannot deal with two problems: the difficulty of analysis and maintenance. Rather than to spend time waiting any longer, it is better to find an alternative solution from other research fields. In computer software development area, researchers have been suffering from the difficulty of maintenance and analysis, just as the researchers in the expert system development field. To solve this issue, researchers in the software used both agile software development and business rules approach: agile software development is for overcoming the the difficulty of analysis, and business rules approach is for reducing issues in the maintenance. There is a big opportunity that those two approaches can also be solve the two issues in the expert system development field. The paper describes requirements of the approach based on agile software development and the business rules approach. As a result, we consider and specify why the Multiple Classification Ripple Down Rules is the novel approach for the expert system development.     

A graph-based expert system approach to geometric feature recognition

Geometric feature recognition is a crucial task in the development of concurrent engineering software. This paper presents a new methodology for geometric feature recognition which combines the advantages of face-edge adjacency graphs and expert systems. The methodology uses several new concepts such as enhanced winged edge data structure (EWEDS) and multi-attributed adjacency graphs (MAAG). The object model is presented as a set of facts. The rules for the recognition of each feature are derived from the corresponding feature-MAAG. This simplifies the process of writing the rules while enabling the inclusion of new features into the rule base as they are encountered.     

Sub-sea fiber optic cable maintenance using a ROV-based flux leakage expert system

World events have increased the demand for secure high-band-width under water fiber optic communications, and at the same time the telecommunications service providers are struggling with containing the expense of maintenance and protection. As a result of the extended use of sub-sea industries, the number of sub-sea optic services installed continues to increase, and the potential for external attacks on these cables also increases. This article addresses the evolution of a specially designed sub-sea remotely operated vehicle (ROV) with a dedicated electromagnetic flux leakage searching arm as part of an associated maintenance arrangement. Current research achievements can apply expert system techniques to the diagnostic system of sub-sea fiber optic cables. These are based on the concept of Ampere’s law, and a method of measuring circulating currents without any physical destruction by testing the suspect section, which is already subject to alternating current flow with selected frequencies.     

基于MFC的故障维修专家系统设计与实现

针对现代工业机械设备维修的复杂性，根据设备的故障现象、故障原因、故障排除的原理，结合以往维修人员的经验，采用Access数据库构建树状结构进行节点管理与节点消息响应，从而实现故障信息管理和故障信息提取。运用C＋＋语言和面向对象的方法实现了人机交互界面，开发出设备故障维修专家库系统。实际应用表明，该系统提高了维修人员的维修效率、减少了人力成本，为实际维修提供参考和指导。     

Troubleshooting expert systems for industrial maintenance: pre-development guidelines

Abstract: The sophisticated nature of new production facilities means more complex maintenance units and costly breakdowns. For users of high tech machinery, the efficiency of their maintenance services is becoming an increasingly important factor, and for manufacturers, the maintainability of their equipment they sell is an element that has to be taken into account in their battle for market share. Troubleshooting Expert Systems (TES) are one possible means of improving maintenance capability and maintenance units. Surveying cases of success or failure that the authors have witnessed themselves or come across in the literature, they propose a checklist of seven questions to be considered at the outset of TES development, which deal with the human, managerial and organisational aspects of TES.     

Constraint maintenance in engineering design system: An active object-oriented approach

This paper proposes a framework of engineering constraint maintenance using an active object-oriented database and solves a problem encountered when implementing the framework. The framework is proposed for the information-driven CIM system that integrates engineering constraints as well as its data. It resolves problems of the existing application-oriented constraint maintenance in which constraints are scattered in heterogeneous applications. It is possible due to the integrated management of constraints on a database using triggers, that is, on an “active” database. Existing active object-oriented databases, however, cannot properly support certain constraints that are specified on a set of classes. Those are the cases where the constraints must be maintained in the forward direction along a class composition hierarchy as well as in the backward direction. We call these kinds of problems “backward propagation problems” and investigate several approaches to resolve them using currently available techniques. Based on an approach which uses virtual classes, a new constructor, called CONSTRAINT^CCH is proposed to support the backward propagation. Advantages of the proposed framework and the constructor for the backward propagation are demonstrated on a design constraint management that supports a control panel design.     

A structure for expert systems maintenance

An approach to the design of maintainable expert systems is presented. Central to this approach is a conceptual model in which the data and knowledge are both modelled as formal “items” in a uniform way. “Objects” are introduced as “item building” operators. The notion of the “decomposition” of items and objects provides the foundation for a single rule of normalization. This single rule applies to all items and objects, including knowledge items, and is a non-trivial generalization of the traditional normal forms for database. Coupling relationships represent the necessary maintenance paths in the conceptual model. A complete characterization of coupling relationships is given, and the value of normalization to the reduction of maintenance costs is discussed.     

Minimizing maintenance anomalies in expert systems

Expert systems are emerging as a powerful technology for solving many problems previously requiring human experts. However, maintenance has been identified as a major difficulty in expert system implementations. Surprisingly, the problem of maintenance has only recently begun to receive attention in expert systems research, though it has long been an issue in databases. Databases are in a constant state of change, and the prevention of maintenance anomalies is essential. As similar maintenance operations are performed on rule bases, this paper investigates techniques to avoid maintenance anomalies in expert system rule bases. The result is an expert system rule base structure that is appropriate for volatile production use. In addition to lower maintenance demands, this approach favorably impacts on verification, computational efficiency, and storage requirements.     

An expert system approach for die and mold making operations

In the modern manufacturing of sophisticated parts with 3D sculptured surfaces, die and mold making operations are the most widely used machining processes to remove unwanted material. To manufacture a die or a mold, many different cutting tools are involved, from deep hole drills to the smallest ball nose end mills. Since the specification of each tool is very different from each other, each mold or die is specific with their complicated shapes and many machining rules exist to consider, a great deal of expertise is needed in planning the machining operations. An expert system (DieEX) developed for this purpose is described in the present work. The geometry and the material of the workpiece, tool material, tool condition and operation type are considered as input values and various recommendations about the tool type, tool specifications, work holding method, type of milling operation, direction of feed and offset values are provided.     

An expert system approach to fault diagnosis in hydraulic systems

Abstract: Increased interest in problem-solving decisions in the area of engineering leads to an increased demand for expert system applications. This paper presents an expert system that detects faults in hydraulic systems by simulating the reasoning of the expert, using as guide the hydraulic circuit of the system on the screen and extensive graphical information. A graphical user interface, appropriate explanations by using hypertext and user modelling have been implemented in order to produce a system that overcomes the usual interface problems of expert systems in engineering.
This system has been developed in close collaboration with the company Automation Systems SA (Mannesmann Rexroth — Greece) and is currently used to detect faults in hydraulic presses, a fact that presents evidence of its usefulness.     

故障诊断专家系统中知识库组织和维护技术的研究

在开发化工过程实时故障诊断专家系统的基础上,本文讨论了知识库的组织和维护技术,对知识表示和知识库结构进行了详细介绍。在知识库维护方面,采用面向对象的方法描述领域知识,并实现知识获取和转换;对于知识校验,提出一种基于有向图的知识校验方法。以润滑油生产过程为例,讨论了系统的知识校验过程。本文讨论的技术和策略已应用于润滑油过程实时故障诊断专家系统。实际应用表明,该技术和策略保证了知识库和专家系统的稳定和高效率。