{"title":"Knowledge-based performance evaluation of computer architectures","authors":"B. Scherf","doi":"10.1109/AIIA.1988.13299","DOIUrl":"https://doi.org/10.1109/AIIA.1988.13299","url":null,"abstract":"Presents an application area for artificial intelligence techniques in the context of designing and evaluating computer architectures. A knowledge-based approach to performance evaluation of computer architectures is described which is suited for application during the early phases of design. Taxonomical knowledge is used to develop an architecture description facility that allows descriptions to be constructed quickly and easily. Heuristical knowledge about the influence of design characteristics on the architecture's performance helps to assess the run time for benchmark programs with respect to a specific architecture, without the need for time-consuming simulations. Using these kinds of knowledge, a system can be built which is flexible and fast enough to allow the comparison of many design alternatives during the early phases of architectural design. A prototypical system has been implemented; and it is concluded that the results obtained by this system support the feasibility of the knowledge-based approach to performance evaluation.<<ETX>>","PeriodicalId":112397,"journal":{"name":"Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116956156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Development of an AI supporting system for knowledge acquisition and refinement (nuclear power plant applications)","authors":"N. Asai, K. Onishi, S. Mori, Y. Otsuka, S. Makino","doi":"10.1109/AIIA.1988.13268","DOIUrl":"https://doi.org/10.1109/AIIA.1988.13268","url":null,"abstract":"Knowledge acquisition and refinement are becoming a bottleneck in developing expert systems. To solve this kind of problem, the authors have developed a supporting system for knowledge acquisition and refinement called the Knowledge Catcher. The system is designed to make knowledge acquisition and refinement effective in building a knowledge base applicable to the diagnosis for nuclear power plants. An overview of the Knowledge Catcher is presented, with attention given to knowledge structure, system function, the approach to knowledge acquisition, and verification.<<ETX>>","PeriodicalId":112397,"journal":{"name":"Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116860232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An object-oriented representation of a power system and the use of it in real-time operations","authors":"J. Keronen","doi":"10.1109/AIIA.1988.13310","DOIUrl":"https://doi.org/10.1109/AIIA.1988.13310","url":null,"abstract":"Model-based reasoning was applied to real-time operation planning and event analysis for a power system. The main idea is to represent the power system with object-oriented techniques and the required knowledge with rules, methods, logic programs, daemons, and attributes. The prototype for real-time operation planning is developed for the 110-kV transmission network of the Helsinki Energy Board.<<ETX>>","PeriodicalId":112397,"journal":{"name":"Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124103840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An expert system for power generation scheduling","authors":"S. Osaka, M. Amano, J. Kawakami","doi":"10.1109/AIIA.1988.13347","DOIUrl":"https://doi.org/10.1109/AIIA.1988.13347","url":null,"abstract":"A prototype of an expert system is presented which assists planners in making power generation schedules. The system takes advantage of knowledge engineering to overcome some drawbacks of conventional methods. Since the scheduling problem is too large to solve, it is divided into several subscheduling problems. To solve the subscheduling problems efficiently, the system adopts heuristic solution methods in addition to mathematical programming methods. The architecture of the system allows easy changes and additions of constraints, planning strategies, and heuristic and numerical solution methods, ensuring a flexible scheduling environment. The system effectiveness is verified using several sets of small-scale model data.<<ETX>>","PeriodicalId":112397,"journal":{"name":"Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125901557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A new type of fuzzy controller based upon a fuzzy expert system shell FLOPS","authors":"H. Ying, W. Siler, D. Tucker","doi":"10.1109/AIIA.1988.13322","DOIUrl":"https://doi.org/10.1109/AIIA.1988.13322","url":null,"abstract":"The authors propose a type of fuzzy controller which is not based on existing fuzzy control theory. Instead, it is based on the general-purpose parallel rule-firing fuzzy logic production system shell, FLOPS. Several different process models are controlled by this fuzzy controller to evaluate its control performances. The performance of the proposed fuzzy controller is compared to that of a fine-tuned proportional-integral controller by using a first-order linear model. Theoretical aspects of the proposed fuzzy controller are studied using different kinds of fuzzy logic for evaluating the fuzzy control rules.<<ETX>>","PeriodicalId":112397,"journal":{"name":"Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128422325","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Y. Miyajima, T. Katou, R. Inaba, S. Kobayashi, H. Ezure
{"title":"A knowledge-based water purification control system","authors":"Y. Miyajima, T. Katou, R. Inaba, S. Kobayashi, H. Ezure","doi":"10.1109/AIIA.1988.13331","DOIUrl":"https://doi.org/10.1109/AIIA.1988.13331","url":null,"abstract":"An expert system for a water purification control system that performs supervisory control of water quantity and automatic filter base in control based on knowledge has been developed. In this knowledge-based water purification control system, the expert system is incorporated into the supervisory control section. This knowledge-based water purification control system has been in online operation at a plant with a 544000-m/sup 3//day supply capacity since October, 1986. The configuration of the knowledge-based purification control system and the operation results are discussed.<<ETX>>","PeriodicalId":112397,"journal":{"name":"Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129617010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Expert system building tool for process control: MARKS-II","authors":"K. Takenaka, T. Yokoi","doi":"10.1109/AIIA.1988.13321","DOIUrl":"https://doi.org/10.1109/AIIA.1988.13321","url":null,"abstract":"An expert system-building tool for process control, MARKS-II, can cooperate with conventional control systems and can infer at a very high speed. This tool is described, and its close linkage function with conventional systems is examined in detail. A case study is presented which demonstrates the efficiency of the tool. The implementation is also described.<<ETX>>","PeriodicalId":112397,"journal":{"name":"Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128900885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Automatic train operation system based on predictive fuzzy control","authors":"H. Oshima, S. Yasunobu, Shingo Sekino","doi":"10.1109/AIIA.1988.13336","DOIUrl":"https://doi.org/10.1109/AIIA.1988.13336","url":null,"abstract":"A predictive fuzzy control including control rules to achieve desirable conditions has been proposed and applied to an automatic train operation (ATO) system. The capability of the fuzzy ATO to control train operation as skilfully as experienced operators was confirmed by a trial run made in the Sendai municipal subway system. The control rules of the fuzzy ATO and results of the test run are described.<<ETX>>","PeriodicalId":112397,"journal":{"name":"Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123134547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An expert system for generating switching sequences at substations","authors":"T. Abe, H. Goto, T. Mizutori, N. Matsuki","doi":"10.1109/AIIA.1988.13313","DOIUrl":"https://doi.org/10.1109/AIIA.1988.13313","url":null,"abstract":"An expert system, VIRGO, for planning switching sequences in substations has been developed. A substation model has been developed on a knowledge database, and, based on this model, the expertise of the operator has been described in terms of production rules. These rules must be layered as metarules to reflect the understanding of the domain expert. VIRGO comprises four functions: it makes specific commands by which any equipment involved should be operated; it makes a switching sequence table in accordance with these commands by reasoning from production rules: it converts the table into an easily readable format: and it simulates the substation model with the sequences on a color CRT screen. VIRGO has been implemented in the knowledge description language, KDL, on the VAX workstation.<<ETX>>","PeriodicalId":112397,"journal":{"name":"Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126828640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"VLSI logic design with logic programming and knowledge base technology","authors":"N. Hamada, K. Bekki, T. Yokota","doi":"10.1109/AIIA.1988.13295","DOIUrl":"https://doi.org/10.1109/AIIA.1988.13295","url":null,"abstract":"A logic-synthesis expert system called ProLogic was developed, and the system was evaluated for some MPU-type VLSIs. A universal connecting procedure for any compound functional module was proposed which unified the behavioral and structural specifications between a total module and its parts, so that the efficiency of logic design was improved by a factor of two. Logic programming, an object oriented frame, and a rule base were applied and implemented in Prolog, so that software productivity was improved by a factor of five, and an architecture for ProLogic has been build up efficiently through a trial-and-error method.<<ETX>>","PeriodicalId":112397,"journal":{"name":"Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122464251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}