{"title":"A micro-EDM/assembly system unit for microparts fabrication","authors":"H. H. Langen, T. Masuzawa, M. Fujino","doi":"10.1109/ETFA.1993.396406","DOIUrl":"https://doi.org/10.1109/ETFA.1993.396406","url":null,"abstract":"A new method is introduced for the fabrication and assembly of high aspect ratio microparts. Pins with a diameter of 100 /spl mu/m are produced by wire electrodischarge grinding (WEDG) and connected into a thin plate. Defining such a pin/plate assembly as a workstation means that it can be used as tool workstation or subassembly workstation in a more compound assembly process. The tool workstation is used to machine the inside shape of a workpiece by reverse micro-EDM (RMEDM) to enable it for further assembly purposes. A more complicated assembly process is described, taking the fabrication of a micro ion beam emitter as an example. After the applicability of the assembly method is shown, the RMEDM process characteristics of the tool workstation is studied. The machining conditions are improved in order to produce a micropart with an inside shape with higher accuracy within reasonable machining time.<<ETX>>","PeriodicalId":239174,"journal":{"name":"Proceedings of IEEE 2nd International Workshop on Emerging Technologies and Factory Automation (ETFA '93)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130197103","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":"Fuzzy Critic for intelligent planning by genetic algorithm","authors":"T. Shibata, T. Fukuda, K. Tanie","doi":"10.1109/ETFA.1993.396426","DOIUrl":"https://doi.org/10.1109/ETFA.1993.396426","url":null,"abstract":"A new strategy for motion planning is proposed. The strategy applies a genetic algorithm (GA) to optimize the motion planning. To evaluate the planned motion, the strategy also applies fuzzy logic to a fitness function. The fitness function is referred to as Fuzzy Critic. The Fuzzy Critic evaluates plans as populations in the GA with respect to multiple factors. Depending on the goals of the tasks, human operators can easily determine inference rules in the Fuzzy Critic because of the fuzzy logic. The strategy determines a path for a mobile robot which moves from a starting point to a goal point, while avoiding obstacles in a work space and picking up loads on the way. Simulation illustrates the effectiveness of the proposed strategy.<<ETX>>","PeriodicalId":239174,"journal":{"name":"Proceedings of IEEE 2nd International Workshop on Emerging Technologies and Factory Automation (ETFA '93)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125473998","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":"Well suited modelling and evaluation techniques based on GSPN for real production systems","authors":"B. Mazigh, J. Gresser, F. Simon","doi":"10.1109/ETFA.1993.396414","DOIUrl":"https://doi.org/10.1109/ETFA.1993.396414","url":null,"abstract":"Modeling of production systems used in automobile factories with behavior which is complicated by failure occurrence and repair or maintenance actions is reported. The method is based on generalized stochastic Petri nets (GSPN) which are well-suited for complex system evaluation. To reduce the state space complexity an equivalent model is proposed for the production lines. It permits addressing the problem of production management and the enhancement of the production rate by the addition of buffers. A software package which aids in the creation of models from a module library is developed.<<ETX>>","PeriodicalId":239174,"journal":{"name":"Proceedings of IEEE 2nd International Workshop on Emerging Technologies and Factory Automation (ETFA '93)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132883888","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":"Fuzzy algorithm for the control of a mobile robot","authors":"L. Deist, C. Fourie","doi":"10.1109/ETFA.1993.396431","DOIUrl":"https://doi.org/10.1109/ETFA.1993.396431","url":null,"abstract":"An integrated system is proposed for the control of a mobile robot on both a local and global level. The local controller uses fuzzy reasoning and ultrasonic sensing to guide a mobile robot along a specific path segment, without physical guidance and without a priori knowledge of the path. It is able to steer the robot along straight segments and left/right turns, while avoiding collision with obstacles. The global controller uses a world map representation of the factory to plan the dispatching and the routing of the mobile robot.<<ETX>>","PeriodicalId":239174,"journal":{"name":"Proceedings of IEEE 2nd International Workshop on Emerging Technologies and Factory Automation (ETFA '93)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123915998","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":"Optimising the JIT methodology using distributed artificial intelligence techniques","authors":"P. A. Wilson, L. Dunn, S. Milliner","doi":"10.1109/ETFA.1993.396417","DOIUrl":"https://doi.org/10.1109/ETFA.1993.396417","url":null,"abstract":"The authors discuss the way in which distributed AI techniques can handle both the one-off problem of planning the layout of a factory appropriate to just-in-time operation, and the problem of scheduling and controlling just-in-time manufacturing at the process level and in real time. It is demonstrated that in order to obtain the necessary accuracy and speed of response, the AI-based system must be distributed and localized. This concept is called the localization principle. A two layer model of localized distributed AI and an appropriate system architecture are presented.<<ETX>>","PeriodicalId":239174,"journal":{"name":"Proceedings of IEEE 2nd International Workshop on Emerging Technologies and Factory Automation (ETFA '93)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115325212","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":"Parts-oriented and distributed task planning for multiple robots","authors":"T. Nagata, J. Hirai","doi":"10.1109/ETFA.1993.396408","DOIUrl":"https://doi.org/10.1109/ETFA.1993.396408","url":null,"abstract":"Assembly task planning for multiple robots is highly complicated and cumbersome. A new assembly task planning system for multiple robots is proposed to avoid this problem and to improve the flexibility and the reliability in assembly tasks. In this system, parts with which a machine is composed are handled as part-objects and plans for assembling the machine are automatically generated as results of autonomous behaviors of these objects. The outline of the planning system, based on this concept is described. Some simulation results using a cooperative computational model are given.<<ETX>>","PeriodicalId":239174,"journal":{"name":"Proceedings of IEEE 2nd International Workshop on Emerging Technologies and Factory Automation (ETFA '93)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114635900","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":"Automated knowledge acquisition using unsupervised learning","authors":"T. Dillon, S. Sestito, M. Witten, M. Suing","doi":"10.1109/ETFA.1993.396421","DOIUrl":"https://doi.org/10.1109/ETFA.1993.396421","url":null,"abstract":"Previously developed methods for automated knowledge acquisition are based on decision trees, progressive rule generation and supervised neural networks. In some real world situations, supervised learning is not possible. Previous methods are not applicable in these situations. A method, based on neural networks, is presented which learns symbolic knowledge representations using unsupervised learning. It is illustrated that symbolic knowledge extraction can be successfully performed using unsupervised neural networks, where no target output vectors are available to the automated knowledge acquisition technique during training.<<ETX>>","PeriodicalId":239174,"journal":{"name":"Proceedings of IEEE 2nd International Workshop on Emerging Technologies and Factory Automation (ETFA '93)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125314125","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":"Dispatching rule exchangeable optimization planning system","authors":"Y. Ikkai, T. Ohkawa, N. Komoda","doi":"10.1109/ETFA.1993.396419","DOIUrl":"https://doi.org/10.1109/ETFA.1993.396419","url":null,"abstract":"A new method for selection of dispatching rules, called a status selection method is discussed. In this method, the most promising status is selected from tentative statuses that are generated by applying all dispatching rules. Since the dispatching rules and the knowledge of status selection are independent, it is easy to exchange the dispatching rules. From the result of the application of the proposed method to a simple flow shop problem, it is confirmed that the status selection method is effective.<<ETX>>","PeriodicalId":239174,"journal":{"name":"Proceedings of IEEE 2nd International Workshop on Emerging Technologies and Factory Automation (ETFA '93)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125814599","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 algorithm for the automatic generation of neural network structures","authors":"T. Naghan, A. Zomaya","doi":"10.1109/ETFA.1993.396429","DOIUrl":"https://doi.org/10.1109/ETFA.1993.396429","url":null,"abstract":"A backpropagation-based algorithm that dynamically configures the structure of feedforward multilayered neural networks and demonstrates its potential for control applications. The algorithm presents a systematic method for selecting neural network structures according to the complexity of the required mappings. A generate-and-test scheme is employed to evaluate the learning performance of the structure used and modify it accordingly by exploring different alternative structures and selecting the most suitable one. The efficiency of the algorithm is demonstrated using two case studies.<<ETX>>","PeriodicalId":239174,"journal":{"name":"Proceedings of IEEE 2nd International Workshop on Emerging Technologies and Factory Automation (ETFA '93)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132936042","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":"Auto fuzzy tuning having minimum structure by using genetic algorithm and delta rule","authors":"T. Fukuda, H. Ishigami, T. Shibata, F. Arai","doi":"10.1109/ETFA.1993.396425","DOIUrl":"https://doi.org/10.1109/ETFA.1993.396425","url":null,"abstract":"An auto tuning algorithm of fuzzy inference for Fuzzy neural networks using the genetic algorithm and the delta rule is presented. Some auto-tuning methods are proposed to reduce time-consuming operations by human experts. This tuning method brings the minimal and optimal structure of the fuzzy model. Two types of the fuzzy model are prepared, whose membership functions on the antecedent part consist of triangular and Gaussian type, respectively. The effectiveness of the proposed methods compared with the former methods is shown by simulation. The proposed method has the potential to be applied to robotic motion control, sensing and recognition problems.<<ETX>>","PeriodicalId":239174,"journal":{"name":"Proceedings of IEEE 2nd International Workshop on Emerging Technologies and Factory Automation (ETFA '93)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128325071","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}