期刊
NEUROCOMPUTING
卷 109, 期 -, 页码 94-104出版社
ELSEVIER SCIENCE BV
DOI: 10.1016/j.neucom.2012.04.033
关键词
Soft computing; Unsupervised learning; Genetic algorithm; Identification systems; Optimisation; Dental milling process
资金
- Spanish Ministry of Economy and Competitiveness [TIN2010-21272-C02-01]
- European Regional Development Fund
- Junta de Castilla y Leon [Exp: CCTT/10/BU/0002]
- IT4 Innovations Centre of Excellence [CZ.1.05/1.1.00/02.0070]
- European Union
- state budget of the Czech Republic, EU
- [Exp: SA405A12-2]
- [CCTT/10/BU/0002]
This study presents a novel soft computing procedure based on the application of artificial neural networks, genetic algorithms and identification systems, which makes it possible to optimise the implementation conditions in the manufacturing process of high precision parts, including finishing precision, while saving both time and financial costs and/or energy. This novel intelligent procedure is based on the following phases. Firstly, a neural model extracts the internal structure and the relevant features of the data set representing the system. Secondly, the dynamic system performance of different variables is specifically modelled using a supervised neural model and identification techniques. This constitutes the model for the fitness function of the production process, using relevant features of the data set. Finally, a genetic algorithm is used to optimise the machine parameters from a non parametric fitness function. The proposed novel approach was tested under real dental milling processes using a high-precision machining centre with five axes, requiring high finishing precision of measures in micrometres with a large number of process factors to analyse. The results of the experiment, which validate the performance of the proposed approach, are presented in this study. (C) 2012 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据