Approximate Life Cycle Assessment of Product Concepts Using a Hybrid Genetic Algorithm and Neural Network Approach

Environmental impact assessment of products has been a key area of research and development for sustainable product development. Many companies copy these trends and they consider environmental criteria into the product design process. Life Cycle Assessment (LCA) is used to support the decision-making for product design and the best alternative can be selected by its estimated environmental impacts and benefits. The need for analytical LCA has resulted in the development of approximate LCA. This paper presents an optimization strategy for approximate LCA using a hybrid approach which incorporate genetic algorithms (GAs) and neural networks (NNs). In this study, GAs are employed to select feature subsets to eliminate irrelevant factors and determine the number of hidden nodes and processing elements. In addition, GAs will optimize the connection weights between layers of NN simultaneously. Experimental results show that a hybrid GA and NN approach outperforms the conventional backpropagation neural network and verify the effectiveness of the proposed approach.

[1]  Ingoo Han,et al.  Hybrid neural network models for bankruptcy predictions , 1996, Decis. Support Syst..

[2]  Mary Ann Curran,et al.  Environmental life-cycle assessment , 1996 .

[3]  Julie L. Eisenhard,et al.  Product descriptors for early product development : an interface between environmental experts and designers , 2000 .

[4]  Donald R. Cooper,et al.  Business Research Methods , 1980 .

[5]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[6]  David Wallace,et al.  Approximate Life‐Cycle Assessment of Product Concepts Using Learning Systems , 2000 .

[7]  David Taniar,et al.  Computational Science and Its Applications - ICCSA 2005, International Conference, Singapore, May 9-12, 2005, Proceedings, Part I , 2005, ICCSA.

[8]  Hojjat Adeli,et al.  Machine Learning: Neural Networks, Genetic Algorithms, and Fuzzy Systems , 1994 .

[9]  Ingoo Han,et al.  Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index , 2000 .

[10]  Hun-Woo Yoo,et al.  Artificial Neural Network Based Life Cycle Assessment Model for Product Concepts Using Product Classification Method , 2005, ICCSA.

[11]  Kwang-Kyu Seo,et al.  Approximate life cycle assessment of classified products using artificial neural network and statistical analysis in conceptual product design , 2001, Proceedings Second International Symposium on Environmentally Conscious Design and Inverse Manufacturing.

[12]  Ingoo Han,et al.  Integrating statistical and inductive learning methods for knowledge acquisition , 1990 .

[13]  Kwang-Kyu Seo,et al.  Approximate life cycle assessment of product concepts using multiple regression analysis and artificial neural networks , 2003 .

[14]  M. Goedkoop,et al.  The Eco-indicator 99, A damage oriented method for Life Cycle Impact Assessment , 1999 .

[15]  J. P. Rombouts.  LEADS-II. A knowledge-based system for ranking DfE-Options , 1998, Proceedings of the 1998 IEEE International Symposium on Electronics and the Environment. ISEE - 1998 (Cat. No.98CH36145).