{"title":"Efficient planning for a miniature assembly line","authors":"Inger Klein , Peter Jonsson , Christer Bäckström","doi":"10.1016/S0954-1810(98)00009-0","DOIUrl":"10.1016/S0954-1810(98)00009-0","url":null,"abstract":"<div><p>This paper presents a provably correct and efficient, polynomial time, planning tool and its application to a miniature assembly line for toy cars. Although somewhat limited, this process has many similarities with real industrial processes. One of our previous polynomial-time planning algorithms has been extended and adapted to work for a larger class of planning problems, including this particular process. The plans produced by the planner are then translated into GRAFCET charts, which are compiled into code for a programmable logic controller. Although capable of producing ordinary assembly plans, the system is mainly intended for producing plans in error recovery situations.</p></div>","PeriodicalId":100123,"journal":{"name":"Artificial Intelligence in Engineering","volume":"13 1","pages":"Pages 69-81"},"PeriodicalIF":0.0,"publicationDate":"1999-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/S0954-1810(98)00009-0","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82021808","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":"Reasoning about function and its applications to engineering","authors":"Luca Chittaro , Amruth N Kumar","doi":"10.1016/S0954-1810(97)10008-5","DOIUrl":"10.1016/S0954-1810(97)10008-5","url":null,"abstract":"<div><p>We provide an introduction to the field of functional representation and reasoning from an engineering point of view. Our main goals are to: (i) present and clarify the notion of function with the aim of unifying diverse perspectives, (ii) identify the various current approaches to represent function, and (iii) highlight the potential of functional reasoning for engineering applications.</p></div>","PeriodicalId":100123,"journal":{"name":"Artificial Intelligence in Engineering","volume":"12 4","pages":"Pages 331-336"},"PeriodicalIF":0.0,"publicationDate":"1998-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/S0954-1810(97)10008-5","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76781747","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":"Function-directed electrical design analysis","authors":"C.J Price","doi":"10.1016/S0954-1810(97)10013-9","DOIUrl":"10.1016/S0954-1810(97)10013-9","url":null,"abstract":"<div><p>Functional labels provide a simple, but very reusable way for defining the functionality of a system and for making use of that knowledge. Unlike more complex functional representation schemes, these labels can be efficiently linked to a behavioral simulator to interpret the simulation in a way that is meaningful to the user. They are also simple to specify, and highly reusable with different behavioral implementations of the system's functions. This claim has been substantiated by the development of the FLAME application, a practical automated design analysis tool in regular use at several automotive manufacturers. The combination of functional labels and behavioral simulator can be employed for a variety of tasks—simulation, failure mode and effects analysis (FMEA), sneak circuit analysis, design verification, diagnostic candidate generation—producing results that are very valuable to engineers and presented in terms that are easily understood by them. The utility of functional labels is illustrated in this paper for the domain of car electrical systems, with links to a qualitative circuit simulator. In this domain, functional labels provide a powerful way of interpreting the behavior of the circuit simulator in terms an engineer can understand.</p></div>","PeriodicalId":100123,"journal":{"name":"Artificial Intelligence in Engineering","volume":"12 4","pages":"Pages 445-456"},"PeriodicalIF":0.0,"publicationDate":"1998-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/S0954-1810(97)10013-9","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76598860","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":"Failure modes and effects analysis of complex engineering systems using functional models","authors":"P G. Hawkins, D.J Woollons","doi":"10.1016/S0954-1810(97)10011-5","DOIUrl":"10.1016/S0954-1810(97)10011-5","url":null,"abstract":"<div><p>A set of models developed by Chittaro for fault diagnosis is extended to represent more complex engineering systems. A novel methodology for qualitative reasoning about behaviour change has been developed for the purpose of failure modes and effects analysis to cope with complete and partial failure modes. The method is demonstrated on an electrically driven gear pump. A further extension is the ability to cope with control systems by distinguishing the function of two closed loop control schemes. Different types of failure of the control scheme can be identified by analysing three different responses of the faulty plant. This method is demonstrated on a manufactured aerospace component called a fuel-metering unit controlled by a negative feedback control scheme.</p></div>","PeriodicalId":100123,"journal":{"name":"Artificial Intelligence in Engineering","volume":"12 4","pages":"Pages 375-397"},"PeriodicalIF":0.0,"publicationDate":"1998-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/S0954-1810(97)10011-5","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72971225","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":"Principled negotiation between intelligent agents: a model for air traffic management","authors":"John P. Wangermann, Robert F. Stengel","doi":"10.1016/S0954-1810(98)80001-0","DOIUrl":"10.1016/S0954-1810(98)80001-0","url":null,"abstract":"<div><p>The worldwide aircraft/airspace system (AAS) is faced with a large increase in air traffic in the coming decades, yet many flights already experience delays. The AAS is comprised of many different <em>agents</em>, such as aircraft, airlines, and traffic control units. Technology development will make all the agents in the AAS more intelligent; hence, there will be an increasing overlap of the <em>declarative functions</em> of the agents. This paper describes the basis for an <em>Intelligent Aircraft/Airspace System</em> (IAAS) that provides improved system performance, redundancy, and safety by utilizing the overlapping capabilities of the agents. <em>Principled Negotiation</em> between agents allows all the agents in the system to benefit from multiple independent declarative analyses of the same situation. <em>Multi-attribute utility theory</em> and <em>decision trees</em> are used as the basis for analyzing the behavior of different types of agents. Intelligent agents are modeled as <em>rule-based expert systems</em> whose <em>side-effects</em> are the procedural and reflexive functions of the agent. Principled negotiation also is a side-effect of the expert systems' declarative functions. A hierarchical organization of agents in the IAAS is proposed to facilitate negotiation and to maintain clear lines of authority.</p></div>","PeriodicalId":100123,"journal":{"name":"Artificial Intelligence in Engineering","volume":"12 3","pages":"Pages 177-187"},"PeriodicalIF":0.0,"publicationDate":"1998-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/S0954-1810(98)80001-0","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76384753","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 case study on the use of model-based systems for electronic fault diagnosis","authors":"Pádraig Cunningham","doi":"10.1016/S0954-1810(97)10004-8","DOIUrl":"10.1016/S0954-1810(97)10004-8","url":null,"abstract":"<div><p>A generic model-based system for fault diagnosis of switching-mode power supplies is described in this paper. The system contains a generic deep model that captures structural and behavioural knowledge about modules and components used in switching-mode power supplies. This deep model provides building blocks that can be instantiated to describe particular power-supply designs. Once this generic system has been developed, it is a simple matter to develop a diagnostic system for a particular circuit. This represents a considerable knowledge engineering advantage over the alternative shallow KBS approach. The generic nature of the diagnostic competence of the system suggests that it should be weaker than an alternative shallow system, specific to a particular circuit. However, the evaluation of the system shows that it can locate between 80% and 90% of faults. This evaluation is described in detail in the paper.</p></div>","PeriodicalId":100123,"journal":{"name":"Artificial Intelligence in Engineering","volume":"12 3","pages":"Pages 283-295"},"PeriodicalIF":0.0,"publicationDate":"1998-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/S0954-1810(97)10004-8","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83237830","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":"Democracy in pattern classifications: combinations of votes from various pattern classifiers","authors":"Geok See Ng , Harcharan Singh","doi":"10.1016/S0954-1810(97)00016-2","DOIUrl":"10.1016/S0954-1810(97)00016-2","url":null,"abstract":"<div><p>The objective of this paper is to show that a combination of votes from various pattern classifiers is better than a single vote from each individual classifier. A proposed support function is used in the combination of votes. The combination of outputs is motivated by the fact that decisions made by teams are generally better than those made by individuals. The decision maker at the outputs of the front-end classifiers is called the combined classifier (CC). The proof of the theory of the combining method is obtained using the principle of mathematical induction. Experimental investigation has been conducted to verify the theory. The first experiment was conducted using 5000 training digits and the second experiment was conducted using 10 000 training digits. CC achieved a recognition accuracy of 86.67% compared with 70% of the best individual classifier in the second experiment. The results show that the theoretical and the experimental values are in good agreement.</p></div>","PeriodicalId":100123,"journal":{"name":"Artificial Intelligence in Engineering","volume":"12 3","pages":"Pages 189-204"},"PeriodicalIF":0.0,"publicationDate":"1998-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/S0954-1810(97)00016-2","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77803086","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":"Intelligent control of wastewater treatment plants","authors":"S.A. Manesis , D.J. Sapidis , R.E. King","doi":"10.1016/S0954-1810(97)10002-4","DOIUrl":"10.1016/S0954-1810(97)10002-4","url":null,"abstract":"<div><p>In recent years intelligent control of large-scale industrial processes has brought about a revolution in the field of advanced control. Knowledge-based techniques which use linguistic rules elicited from human experts are at the core of this class of systems, of which fuzzy and neural controllers are two examples that have been applied with success. This paper presents an intelligent control system which can be embedded in a commercial programmable logic controller for the control of wastewater treatment plants.</p></div>","PeriodicalId":100123,"journal":{"name":"Artificial Intelligence in Engineering","volume":"12 3","pages":"Pages 275-281"},"PeriodicalIF":0.0,"publicationDate":"1998-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/S0954-1810(97)10002-4","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82914632","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 predictor based on adaptive resonance theory","authors":"D.T. Pham, M.F. Sukkar","doi":"10.1016/S0954-1810(97)00020-4","DOIUrl":"10.1016/S0954-1810(97)00020-4","url":null,"abstract":"<div><p>This paper describes two alternative modifications to the self-organising ART2 neural network to enable it to act as a predictor of outputs from a dynamic system. The modifications are to make the vigilance parameter self-adjusting and include a new learning sub-system for the F2 nodes. The paper presents the results of employing an ART2 network incorporating one of the proposed modifications to yield the outputs of two simulated dynamic systems.</p></div>","PeriodicalId":100123,"journal":{"name":"Artificial Intelligence in Engineering","volume":"12 3","pages":"Pages 219-228"},"PeriodicalIF":0.0,"publicationDate":"1998-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/S0954-1810(97)00020-4","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89526981","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":"Intelligent tool wear estimation system through artificial neural networks and fuzzy modeling","authors":"R.J. Kuo , P.H. Cohen","doi":"10.1016/S0954-1810(97)00027-7","DOIUrl":"10.1016/S0954-1810(97)00027-7","url":null,"abstract":"<div><p>In the metal cutting process, tool wear results in a loss in dimensional accuracy of the finished product and possible damage to the workpiece. It is very critical to estimate the amount of tool wear during cutting. Thus, this paper proposed an on-line estimation system which consists of data acquisition, feature extraction, pattern recognition and multi-sensor integration for tool flank wear. In multi-sensor integration, a proposed model, self-organizing and self-adjusting fuzzy model, is compared with artificial neural network with error backpropagation algorithm and multiple regression model using the experimental data which were collected from force, vibration, and acoustic emission sensors. The results showed that the proposed model is better than the other two methods.</p></div>","PeriodicalId":100123,"journal":{"name":"Artificial Intelligence in Engineering","volume":"12 3","pages":"Pages 229-242"},"PeriodicalIF":0.0,"publicationDate":"1998-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/S0954-1810(97)00027-7","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81751619","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}