Expert System Approach Research Articles

An expert system approach to design of automotive air-conditioning systems

AbstractAn expert system approach for designing air-conditioning systems for cars and trucks is presented. A brief introduction to the automotive application of the vapor-compression refrigeration cycle is provided as general background. The method presented uses an integrated approach combining the power of conventional analysis programs, databases and model-based expert system technology. Some sample rules from the knowledge base have been included in the paper to illustrate the application of the domain knowledge and its interaction with algorithmic programs. The system architecture is very open and modular, and it lends itself to easy modifications and future expansions. Possibilities for system enhancements are also outlined in the paper. The approach presented in this paper provides substantial benefits to the automotive air-conditioning design engineer particularly in the early stages of new vehicle platform planning and development. A pilot system has been successfully tested at General Motors for preliminary design of automotive air-conditioning systems.

Application of FBOLES—a prototype expert system for fault diagnosis in nuclear power plants

Abstract The basic concept of a frequency-based on-line expert system (FBOLES) approach for the on-line fault diagnoses of nuclear power plants has been previously presented in our companion papers. This paper reports on the status of the protoype software development and the real time on-line experiment results. The main steam and feedwater condensate system (MSFCS, namely, the secondary loop) of a nuclear power plant (950 MW, three loops) simulated by the Tsinghua simulator has been selected as a target system at the present stage of development. The knowledge bases for MSFCS have been initially constructed. A total of 62 signals from the simulator have been selected as the on-line evidence for diagnosis. Thirty-three fault experiments were performed in which 21 were detected accurately (only one candidate) by FBOLES immediately after the first abnormal signals were received and the other 12 were detected accurately within 0·5 to 3 min as the development of abnormality. These experiments include not only the failures of pumps, valves, pipes, etc., of MSFCS itself, but also the failures outside MSFCS. Three of them involve non-initiating events. As a software package, FBOLES can perform either the on-line diagnosis where the signals are input from the simulator directly or the off-line diagnosis that either repeats the on-line diagnosis in a selectable time scale by using the data received on-line and stored on disk or allows users to input signals from a keyboard. Also, the integrated information base, including the modular mini knowledge bases and other necessary data, can be edited and assembled by users easily and compiled by FBOLES into coded format.

Filter tuning system using fuzzy logic

The authors describe an expert system approach for tuning filters using fuzzy logic. The proposed system adjusts the filter components in order to meet the given window specifications. The system is described and experimental results are presented for a lowpass filter implemented with OTAs.

An Expert System Approach to Curriculum Development in Engineering Education

SUMMARY RÉSUMÉ This paper focuses on demonstrating the feasibility of applying expert system methodology as a new approach for assisting the development of engineering degree curricula particularly in developing countries. A number of subdomains in which a rule-based system can be applied have been identified in the field of curriculum development. The subdomain developed and presented in this paper concerns methods of identifying curriculum content, and the major subgoal of developing a profile of ‘staff experience’ in this context is investigated in depth. Knowledge in this subdomain has been encapsulated in an expert system which has been refined to the satisfaction of a curriculum expert and tested by potential end-users of the system. RÉSUMÉ On s'est concentré dans cet article sur une démonstration de la possibilité d'appliquer ks méthodes d'Intelligence Artificelle, au développement des programmes d' études pour la formation des ingénieurs au niveau de licence (surtout dans les pays en voie de developpement). On a identifié, dans le domaine du developpement des programmes d' études, plusieurs sous-domaines auxquels s'appliquerait un systeme d'Intelligence Artificielle à base de régies. Le sous-domaine qu'on presente ici concerne les methodes qu'on se sen pour déterminer le contenu des programmes d' études; en meme temps, un autre but majeur de nos recherches a été d'examiner à fond le profit d'experience du personnel enseignant en ce qui s'agit du développement des programmes d' études. On a encapsulé le savoir dans ce sous-domaine au moyen d'un système d'Intelligence Artificielle qui a ete mis au point à la satisfaction d'un expert en matières de programmes d' études et, qui a été, de plus, vérifié par des représentants de ceux qui, en toute probabilité, se serviront d'un tel système.

A frequency and knowledge tree/causality diagram based expert system approach for fault diagnosis

Abstract Developed from the initial idea presented in a companion paper (Zhang, Q. et al., Reliability Engng System Safety , 34 (1991) 121–142), a novel frequency and knowledge tree/causality diagram based expert system approach for the on-line/off-line fault diagnoses of engineering systems such as nuclear power plants is presented in this paper. The newly made progress includes the modular knowledge base construction, how to utilize the information of the order of signal appearance, how to express uncertainties of experts' opinions in the tree based knowledge bases, how to find the possible fault hypotheses and propagate uncertainties through the time-specific knowledge trees or causality diagrams that may include many loops, and how to deal with the imperfectness of knowledge bases and unknown signals. A tutorial examples is included to illustrate the methodology.

An expert system approach to liquefaction analysis part 1: Development and implementation

This paper presents the development of the rule-based expert system, LIQUEFY, which evaluates the liquefaction potential of sites using several commonly accepted liquefaction evaluation methods. In this paper the issues in the design of the rule-based are addressed including: knowledge acquisition, knowledge representation, and system validation. LIQUEFY was developed for the personal computer and includes 470 rules, an explanation facility, and methods for handling uncertainty in input data and resulting conclusions.

Using machine apprentices for transient knowledge work

This paper characterizes a class of problems that are knowledge intensive but with characteristics differing from those traditionally amenable to an expert system approach. They are transient, emerging and receding in importance over time. They appear in environments where knowledge intensive attention is highly scarce. And the opportunity cost in searching for confirming and clarifying data is high. The paper details a system for addressing such problems and continues by illustrating the system's effectiveness through a case study of the system's use.

An Expert System Approach to Teaching Problem Solving in Biological Instrumentation

An Expert System Approach to Teaching Problem Solving in Biological Instrumentation

Chemometric investigation of complex equilibria in solution phase II: Sensitivity of chemical models for the interaction of AADH and FAH with Ni(II) in aqueous medium

A detailed study of the species formed in the complex equilibria involving adipic acid dihydrazide (AADH)/2-furoic acid hydrazide (FAH) with Ni(II) using pH titration with glass electrode is performed. The results of modeling studies and effect of errors on the equilibrium constants of AADH/FAH with Ni(II) refined by the non-linear least squares program MINIQUAD75 are reported. Based on the expert system approach developed in our laboratory for the species formed from secondary formation data ( n and n H), several preliminary chemical models were tested. For the four species identified (MLH, ML, ML 2H, ML 2), an exhaustive search of a different combination of models (15) was performed. Then other suspected minor species (ML 2H 2, ML 3 and ML 3H) were tested. The final best fit chemical model was found to contain ML 3H to an extent of 3% along with the other four major species. In order to ascertain the accuracy of the stability constants and consequently distribution of the species, a detailed error analysis is attempted. As the existing least squares procedures cannot suppress the systematic errors, three-dimensional plots of the simultaneous effects of pH and TLO:TMO (1.5:1 to 5:1) on the percentage of species are drawn which are of immense use in arriving at optimum conditions for the preparation of a complex of definite stoichiometry.

113 Dynamic job-shop scheduling in CIM: A novel expert system approach

113 Dynamic job-shop scheduling in CIM: A novel expert system approach

Fuzzy supervision and application to lean production†

Abstract A novel philosophy of process supervision based on functional redundancy, i.e., analytical or knowledge based redundancy which may specifically be used for lean production, is suggested. The key idea is to replace the conventional residual evaluator of the fault diagnosis system based on crisp logic, by both a decision maker with fuzzy logic for residual pre-evaluation and the human operator to make the final decisions using his natural intelligence, experience and common sense. The purpose of the employment of fuzzy logic for residual pre-evaluation is to release only weighted alarms instead of yes-no decisions, so that (by definition) no false alarms can be produced; besides this, the man-machine interaction becomes much easier. In contrast to the conventional expert system approach, the proposed concept leaves the final yes-no decisions to the natural intelligence, capability and responsibility of the human operator which are still superior to the artificial intelligence and decision making ca...

Diagnostic accuracy of pancreatic enzymes evaluated by use of multivariate data analysis

We analyzed pancreatic enzyme data from 508 patients with suspected pancreatitis by neural network analysis, by an Expert multirule generation protocol, and by receiver-operator characteristic (ROC) curve analysis of a single test result. Neural network analysis showed that use of lipase provided the best means for diagnosing pancreatitis. Diagnostic accuracies achieved by using amylase only, lipase only, and amylase and lipase in combination were 76%, 82%, and 84%, respectively. Use of the Expert rule generation protocol provided a diagnostic accuracy of 92% when rules for single and multiple samplings were combined. ROC curve analysis for initial enzyme activities showed the maximal diagnostic accuracy to be 82% and 85% for amylase and lipase, respectively; use of peak enzyme activities yielded accuracies of 81% and 88%, respectively. The evaluation of laboratory test data should include analysis of the diagnostic accuracy of laboratory tests by multivariate techniques such as neural network analysis or an Expert systems approach. Multivariate analysis should allow for a more realistic assessment of the diagnosis accuracy of laboratory tests because all the available data are included in the evaluation.

Development of an expert system for scheduling work content in a job shop environment

Experts estimate that 65% of all manufacturing firms employ fifty or less employees, and many of these small manufacturing firms operate as job shop environments. This paper will focus on a methodology for the development of an expert systems approach to job shop scheduling. Specifically, the concept of prototyping and life cycle development will be discussed. Prototyping combines the steps of knowledge acquisition, knowledge representation, knowledge implementation, and verification and validation into a repetitive cycle, rather than having the steps in a sequential fashion. By using a prototyping cycle, a small expert system is developed first and then gradually enlarged as exception cases are identified, instead of attempting to complete each step entirely before continuing with the next.

Discrete VAR optimization in a distribution system using mixed-integer programming with an expert system

A new solution procedure for the discrete VAR optimization of a power distribution system is presented in this paper. In orderto obtain an optimal discrete solution within a reasonable time, a mixed-integer programming method combined with an expert system is proposed to achieve these requirements. The proposed expert system helps the system planning engineers to allocate an appropriate initial feasible solution, and to decide the position of transformer tap settings as well as the number of capacitor units. From three solution stages using the linear programming approach, the expert system approach, and the mixed-integer programming approach, the discrete VAR optimization problem is promptly solved. Numerical simulations of a small-scale system and a practical system are demonstrated with significant results. The results demonstrate the effectiveness and improvement of the proposed method to solve the VAR optimization problem in a power distribution system.

Expert system approach for spectra-structure correlation for vapor-phase infrared spectra

Computerized interpretation of vapor-phase infrared spectra using a novel expert system approach for spectra-structure correlation for vapor-phase spectra is introduced. Rapid identification of several functional groups of components in gaseous mixtures can be achieved using this expert system.

“Rule-based forecasting: Development and validation of an expert systems approach to combining time series extrapolations”: Fred Collopy and J. Scott Armstrong, Management science, 38 (1992) 1394–1414

“Rule-based forecasting: Development and validation of an expert systems approach to combining time series extrapolations”: Fred Collopy and J. Scott Armstrong, Management science, 38 (1992) 1394–1414

Bridge Planning Using GIS and Expert System Approach

In the planning process of a new road network, the planner should consider possible locations of bridges and tunnels. The selection of the best alignment imposes the need to investigate the effect of the location of each bridge on the bridge type that fits this location. This task has not been done so far because of the large volume of data needed and the complicated interaction between many factors. In this paper, it is shown that considering this task in the early stage of road alignment planning can result in a more rational design. Geographic information systems and expert systems are proposed as two methodologies that can help in comparing candidate sites and candidate types simultaneously. Having this computation power, quantitative comparison can be done faster and much more precisely than in the case of conventional simplified methods. This can result in improving the design of the road network in general and in having bridges designed to meet the requirements of erection, maintenance, driving comfort, and landscape.

Studying the emotion-antecedent appraisal process: An expert system approach

Abstract The surprising convergence between independently developed appraisal theories of emotion elicitation and differentiation is briefly reviewed. It is argued that three problems are responsible for the lack of more widespread acceptance of such theories: (1) the criticism of excessive cognitivism raised by psychologists working on affective phenomena; (2) the lack of process orientation in linking appraisal to the complex unfolding of emotion episodes over time; and (3) the lack of consensus on the number and types of appraisal criteria between theorists in this domain. Although readers are referred to recent theoretical discussions and evidence from the neurosciences with respect to the first two issues, an empirical study using computerised experimentation is reported with respect to the third issue. Data obtained with an expert system based on Scherer's (1984a) “stimulus evaluation check” predictions show the feasibility of this approach in determining the number and types of appraisal criteria n...

An expert system intervention for smoking cessation.

Intervention efficacy can be increased when the treatment is maximally matched to the needs of the client. One means of achieving such matching is through use of an expert system, a computer-based decision-making system designed to utilize client information to produce unique, matched information and interventions. An expert system can combine the individual matching possible in a clinic-based intervention and the low cost associated with a public health approach. This paper begins by discussing several alternative implementations of the expert system approach within the general context of communication theory. Second, the theoretical model and related empirical evidence which form the basis of the expert system is described briefly. Third, the details of a computer-driven, expert system intervention specifically developed for smoking cessation is described. Finally, empirical results from a study comparing the expert system intervention to three alternative interventions for smoking cessation are presented. In general, the expert system approach can provide a cost effective, viable, and efficacious means of intervening in a specific problem behavior area. Implications and potential areas of development are discussed.

The value of empirical work: A personal view

Collopy, F. and J.S. Armstrong, 1992 “Rule-based forecasting: Development and validation of an expert systems approach to combining time series extrapolations”, Management Science, 3X, 1394-1414. Fildes. R., 19X5 “Quantitative forecasting-The state of the art: Econometric models”, Journal of the Operational Research Society, 36, 549-580. Geriner. P.T. and J.K. Ord, 1991, “Automatic forecasting using explanatory variables: A comparative study”, International Journal of Forecasting, 7. 127-140. Koehler, A.B., R.B. Snyder and J.K. Ord, 1992, “Simple exponential smoothing and variances of forecast error”. Unpublished manuscript. Ord. J.K., 19X9, “Future developments in forecasting: the time series connexion”, International Journal of Forecasting, 4, 389-401.