Abolfazl Mohebbi, S. Achiche, L. Baron, L. Birglen
{"title":"基于神经网络的机电一体化多准则系统概念设计决策支持","authors":"Abolfazl Mohebbi, S. Achiche, L. Baron, L. Birglen","doi":"10.1109/IDAM.2014.6912679","DOIUrl":null,"url":null,"abstract":"A mechatronic product is a complex multi-domain system which integrates several disciplines where mechanics are combined with electronics, control and software. The task of designing mechatronic systems is understood to be very tedious and complex because of the high number of components, the multi-physics aspects, the couplings between the different domains involved and the interacting design criteria. Due to this inherent complexity, a systematic and multi-objective approach is needed to replace the traditional methods used to support the design activity and design performance evaluation. In this paper we present a Choquet integral-based neural network alongside with a new multi-criteria profile for mechatronic system performance evaluation in conceptual design stage. The newly introduced Mechatronic Multi-criteria Profile (MMP) includes various quantitative evaluation criteria such as machine intelligence, reliability, complexity, flexibility and cost. The Choquet integral-based neural network will be used for the aggregation of criteria and fitting the intuitive requirements for decision-making in the presence of interacting criteria. Finally, a case study of designing a robotic visual servoing system is presented to validate the effectiveness of the proposed method.","PeriodicalId":135246,"journal":{"name":"Proceedings of the 2014 International Conference on Innovative Design and Manufacturing (ICIDM)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2014-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Neural network-based decision support for conceptual design of a mechatronic system using mechatronic multi-criteria profile (MMP)\",\"authors\":\"Abolfazl Mohebbi, S. Achiche, L. Baron, L. Birglen\",\"doi\":\"10.1109/IDAM.2014.6912679\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A mechatronic product is a complex multi-domain system which integrates several disciplines where mechanics are combined with electronics, control and software. The task of designing mechatronic systems is understood to be very tedious and complex because of the high number of components, the multi-physics aspects, the couplings between the different domains involved and the interacting design criteria. Due to this inherent complexity, a systematic and multi-objective approach is needed to replace the traditional methods used to support the design activity and design performance evaluation. In this paper we present a Choquet integral-based neural network alongside with a new multi-criteria profile for mechatronic system performance evaluation in conceptual design stage. The newly introduced Mechatronic Multi-criteria Profile (MMP) includes various quantitative evaluation criteria such as machine intelligence, reliability, complexity, flexibility and cost. The Choquet integral-based neural network will be used for the aggregation of criteria and fitting the intuitive requirements for decision-making in the presence of interacting criteria. Finally, a case study of designing a robotic visual servoing system is presented to validate the effectiveness of the proposed method.\",\"PeriodicalId\":135246,\"journal\":{\"name\":\"Proceedings of the 2014 International Conference on Innovative Design and Manufacturing (ICIDM)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-09-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2014 International Conference on Innovative Design and Manufacturing (ICIDM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IDAM.2014.6912679\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2014 International Conference on Innovative Design and Manufacturing (ICIDM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IDAM.2014.6912679","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Neural network-based decision support for conceptual design of a mechatronic system using mechatronic multi-criteria profile (MMP)
A mechatronic product is a complex multi-domain system which integrates several disciplines where mechanics are combined with electronics, control and software. The task of designing mechatronic systems is understood to be very tedious and complex because of the high number of components, the multi-physics aspects, the couplings between the different domains involved and the interacting design criteria. Due to this inherent complexity, a systematic and multi-objective approach is needed to replace the traditional methods used to support the design activity and design performance evaluation. In this paper we present a Choquet integral-based neural network alongside with a new multi-criteria profile for mechatronic system performance evaluation in conceptual design stage. The newly introduced Mechatronic Multi-criteria Profile (MMP) includes various quantitative evaluation criteria such as machine intelligence, reliability, complexity, flexibility and cost. The Choquet integral-based neural network will be used for the aggregation of criteria and fitting the intuitive requirements for decision-making in the presence of interacting criteria. Finally, a case study of designing a robotic visual servoing system is presented to validate the effectiveness of the proposed method.