| Summary: | 碩士 === 大同大學 === 機械工程學系(所) === 92 === In last few years there is a great increase of interest in learning biologically inspired systems. Some biologically inspired algorithms such as artificial neural network, genetic algorithms, artificial immune algorithm and ant colony system are emphasized in many published papers. The biologically inspired system is a comprehensive and complex system. The artificial immune algorithm specially has capability of performing several tasks including adaptive learning, memory acquisition, generation of diversity, noise tolerance, and distributed detection. Those characteristics are also the system feature of optimization algorithms and it is useful to transform the biological system into searching algorithm for design optimization.
Due to the development of computer, the computer-aided engineering(CAE) software becomes powerful and friendly. The pressure of competition among time, cost and quality is increased for product. It becomes important to design product using CAE software for low cost and high quality product in a short period of time. The integration of CAE software with a robust and efficient search engine becomes important for improving complex design in quality and precision. It is time-consuming work for using CAE software for optimization search and may take more than one month to finish a single design optimization job by using just single personal computer. In order to reduce the design period and cost, the only way is to use cluster PCs for parallel or distributed computation environment.
A distributed artificial immune algorithm will be developed in this study for Windows operation systems using TCP/IP, winksock and C++ language. The ANSYS software will be integrated with distributed artificial immune algorithm for engineering optimization. Some test functions are used first to verify the correctness and performance of developed program. Then multi-modal topological optimization of structure will be used to prove the performance of distributed artificial immune algorithm. This also shows that the integration of CAE software with distributed artificial immune algorithm can really help the industry to develop low cost, and high quality complex design in short design period. The design of satisfied product will become faster and easier. The design compatibility, product quality, and cost control will be improved for competition.
|
|---|
