Archived Industry News and Success Stories
2014 CI Industrial Success Story
Applications of Intelligent Evolutionary Algorithms in Optimal System Modeling and Mechanical Design
- National Kaohsiung University of Applied Sciences (807)
- National Kaohsiung First University of Science and Technology (824)
Kaohsiung , Taiwan, ROC,
- Professor Jyh-Horng Chou, Department of Electrical Engineering, National Kaohsiung University of Applied Sciences, 415 Chien-Kung Road, Kaohsiung 807, Taiwan, Republic of China.
- Professor Jinn-Tsong Tsai, Department of Computer Science, National Pingtung University of Education, 4-18 Min-Sheng Road, Pingtung 900, Taiwan, Republic of China.
- Professor Tung-Kuan Liu, Department of Mechanical and Automation Engineering, National Kaohsiung First University of Science and Technology, 1 University Road, Yenchao, Kaohsiung 824, Taiwan, Republic of China.
- Professor Wen-Hsien Ho, Department of Healthcare Administration and Medical Informatics, Kaohsiung Medical University, 100 Shi-Chuan 1st Road, Kaohsiung 807, Taiwan, Republic of China.
- Professor Chiu-Hung Chen, Department of Information Technology, Kao Yuan University, 1821 Jhongshan Rd., Lujhu, Kaohsiung 821, Taiwan, Republic of China.
- Dr. Gong-Ming Hsu (Engineer), Metal Industries Research and Development Centre, 1001 Kaonan Highway, Kaohsiung 811, Taiwan, Republic of China.
- Dr. Kuo-Ming Lee (Engineer), Metal Industries Research and Development Centre, 1001 Kaonan Highway, Kaohsiung 811, Taiwan, Republic of China.
The research team leader of this project is Dr. Jyh-Horng Chou, who is a Chair Professor at National Kaohsiung University of Applied Sciences in Taiwan. Dr. Chou wanted to promote the research level in Taiwan industries, when he recruited well-known above-mentioned professors and industrial experts to develop intelligent evolutionary algorithms for industrial research and development.
Computational Intelligence Technique
Neural Networks, Genetic Algorithms, Evolutionary Computation and Intelligent Systems Application were used in this successful computational intelligence application in the industry field.
For methods were used in this technology transfer: Licensing Patents Collaborative Projects Publications in Journals and/or Conferences.
One of the main factors of the success was the source of funding, where more than one organization has provided fund and support. These organizations are:
- The National Science Council in Taiwan, 2004-2013,
- Tekuan Co. Ltd., 2009,
- Technology Base Co. Ltd., 2005-2006 and 2011-2012,
- Metal Industries Research and Development Centre, 2008-2011,
- Kwang Yang Motor Co. Ltd., 2010-2011,
- HighForward Co. Ltd., 2013.
The kernel optimization approach is the hybrid Taguchi-genetic algorithm (HTGA), which possesses the merits of global exploration, fast convergence, robustness, and statistical soundness.
The HTGA combines the traditional genetic algorithm (TGA), which has a powerful global exploration capability, with the Taguchi method, which can exploit the optimum offspring. The Taguchi method is inserted between crossover and mutation operations of a TGA. Then, the systematic reasoning ability of the Taguchi method is incorporated in the crossover operations to select the better genes to achieve crossover, and consequently enhance the genetic algorithm (Tsai et al., 2004). The published paper on the HTGA (Tsai et al., 2004) has been selected to be one of the "Highly Cited Papers" by the ISI Web of Knowledge (WOS), Essential Science Indicators (ESI), and also was selected to be one of the "Research Fronts" by the ISI WOS ESI in 2010. The proposed HTGA approach has also received Taiwan Patent I220954. The following applications have contributed to Taiwan's industries major benefits by providing the most advanced intelligent evolutionary-based methods. Due to the significant contributions to industries, our research accomplishments have been selected for inclusion in the Science and Technology Yearbook of Taiwan in 2009 and 2012, respectively. Besides, in recognition of excellent technical achievements and outstanding contributions in advanced evolutionary computation and genetic algorithm, the research team leader, Professor Jyh-Horng Chou, received the 2012 IEEE Outstanding Technical Achievement Award from the IEEE Tainan Section.
[I] The proposed modeling and optimization approach integrates the Taguchi method, the artificial neural network (ANN), and the HTGA. First, the Taguchi method is applied to minimize experimental numbers and to collect experimental data representing the quality performances of a system. Next, the ANN is used to build a system model based on the data from the Taguchi experimental method. Then, the HTGA is employed to search for the optimal process parameters. A process parameters design for a titanium dioxide (TiO2) thin film in the vacuum sputtering process is studied in this application study, as shown in Fig. 1. The quality objective is to form a smaller water contact angle on the TiO2 thin-film surface. The water contact angle is 4° obtained from the system model of the proposed procedure. The process parameters obtained from the proposed procedure were used to conduct the experiment in the vacuum sputtering process for the TiO2 thin film. The water contact angle given from the practical experiment is 3.93°. The difference percent is 1.75% between 4° and 3.93°. The result obtained from the system model of the proposed procedure is promising (Ho et al., 2010). This modeling and optimization technique for the vacuum sputtering process has been licensed to the Metal Industries Research and Development Centre (http://www.mirdc.org.tw), Taiwan.
|Fig. 1 Diagram of water contact angle, the unbalanced magnetron vacuum sputtering equipment, and a test piece of the high speed steel|
[II] A Taguchi sliding-based differential evolution algorithm with orthogonal array (TDEOA), which is inspired from the HTGA, is proposed for solving tolerance design problems. Tolerance affects system performance and leads to violation of design constraints. By including a Taguchi three-level orthogonal array, the proposed TDEOA obtains robust optimal solutions that minimize the impact of variations in machining variables and that maintain compliance with a comprehensive set of process constraints. After evaluating its performance in practical case studies of rough and finish grinding processes, as shown in Fig. 2, the performance of the proposed TDEOA is compared with those of other nature-inspired optimization approaches. The major contribution of the TDEOA is the use of three-level OA to account for tolerance at the evaluation stage in order to minimize the effect of variations in the grinding variable specifications. In so doing, the solutions are obtained within a specified tolerance, when an average value is used to be the fitness value. The average is farther off the boundary of imposed constraints, hence able to avoid violations (Tsai et al., 2013). This robust evolutionary optimal tolerance design technique has been licensed to the Metal Industries Research and Development Centre (http://www.mirdc.org.tw), Taiwan.
|Fig. 2 Experimental setup for precision stamping mold used in surface grinding experiments|
[III] While designing practical linkage mechanisms, someone encounters two kinds of collision problems: one is the interference problem happened in the practical physical linkage structures, and the other is the collision problem existed in the manufacturing environment. However, most of the previous studies on the design of linkage mechanisms do not directly consider the collision problems. This application study demonstrates a collision-free design work based on an industry project which started from a draft design containing the essential layer structures, as shown in Fig. 3. Based on the HTGA, our research team proposes a multiobjective approach that utilizes inferred kinematical equations and the Euclidean-distance-based MMGA (EDMMGA) to explore the Pareto set, with results that simultaneously meet the collision-free constraints and various manufacturing criteria. A related systematic methodology is developed to assist the design of collision-free linkage mechanisms, and can be easily extended or modified to meet other practical requirements. From the positive results, our approach illustrates a successful method considering both geometrical constraints and manufacturing criteria in the optimization algorithms. In addition, this application work has been successfully verified and applied to the design of a commercially used ladle mechanism in which the obstacles come from the related peripheral equipment (Chen et al., 2012). This multiobjective optimization technique for designing practical collision-free linkage mechanisms has been successfully adopted and transferred into the Technology Base Co. Ltd. (http://www.techbasecorp.com), Taiwan.
|Fig. 3 Practical situation during beta-testing. These pictures are captured from a live video file. Sub-figures (a)-(c) demonstrate the whole process transferring operation, and sub-figures (d)-(f) show the linkage structure in more detail.|
- Tsai, J. T., T. K. Liu, and J. H. Chou, 2004, "Hybrid Taguchi-genetic algorithm for global numerical optimization," IEEE Trans. on Evolutionary Computation, Vol. 8, pp. 365-377.
- Ho, W. H., J. T. Tsai, G. M. Hsu, and J. H. Chou, 2010, "Process parameters optimization: a design study for TiO2 thin film of vacuum sputtering process," IEEE Trans. on Automation Science and Engineering, Vol. 7, pp. 143-146.
- Tsai, J. T., K. M. Lee, and J. H. Chou, 2013, "Robust Evolutionary Optimal Tolerance Design for Machining Variables of Surface Grinding Process," IEEE Transactions on Industrial Informatics. DOI:10.1109/TII.2013.2240311.
- Chen, C. H., T. K. Liu, I. M. Huang, and J. H. Chou, 2012, "Multiobjective Synthesis of Six-Bar Mechanisms under Manufacturing and Collision-Free Constraints," IEEE Computational Intelligence Magazine, Vol. 7, pp. 36-48.
- Tsai, J. T., T. K. Liu, and J. H. Chou, "Intelligent Global Searching Method for Optimization", Taiwan Patent I220954, Period: September 2004 to December 2022.
[I] "The intelligent-evolutionary-based optimization technique has been used to obtain the optimal design parameters for the titanium dioxide thin film in the vacuum sputtering process as well as for the rough and finish grinding processes; the results are better than those obtained by the traditional methods usually used in the industry."
Dr. Gong-Ming Hsu and Dr. Kuo-Ming Lee,
Metal Industries Research and Development Centre.
[II] "The evolutionary-based multiobjective optimization software has been adopted by the Technology Base Corporation to design collision-free linkage mechanisms in the commercial metal-mold-die-casting systems and to plan production scheduling. The proposed optimization software provides a systematically design procedure instead of the previous trial and error method used in our corporation, and several design cases have also successfully verified the effectiveness of the presented software."
Mr. Tsung-Wen Cheng,
Manager of R & D Department, Technology Base Co. Ltd.
[III] Correspondence Addressee：