在本文中，提出了兩種改良式的微分進化演算法(differential evolution algorithm，DEA)，稱為田口微分進化演算法（Taguchi-differential evolution algorithm，TDEA）及可調整式田口微分進化演算法（ adjustable Taguchi-differential evolution algorithm，ATDEA）。其演算法應用於模式簡化 （model reduction），降階模型的動作使得模擬、分析或是控制設計能夠更容易。TDEA 修改了傳統DEA 突變之法則。利用田口實驗法具有的系統規劃參數設計理念，應用於突變機制中，取代了傳統DEA 在突變機制中隨機產生擾動向量的動作，提升了避免搜索過程中陷入局部解的機率。然而在搜尋最佳解時，最大的問題在於無法得知其範圍是多大，故ATDEA 引入了搜尋空間擴大機制（search space expansion scheme），讓搜尋範圍空間成為動態，使得搜索效率能提升。最後利用TDEA及ATDEA 去做模式簡化的應用，並與文獻中提出的DEA 來做分析比較。In this paper, the problems of model reduction are solved by using two improved differential evolution algorithms (DEA), which are called Taguchi-differential evolution algorithm (TDEA) and adjustable Taguchi-differential evolution algorithm （ATDEA）. The use of a reduced-order model makes it easier to implement analyses, simulations and control designs. The proposed TDEA is modified from the traditional DEA with mutation operation. The systematic reasoning ability of the Taguchi method can promote the mutation efficiency. The Taguchi method applied into mutation operation and replaced the action of perturbed vectors were chosen randomly in the tradition DEA. TDEA can avoid premature convergence with controllable deteriorating probability. However, the biggest problem in optimal solution is that we can’t know the range of searching.Here, we incorporate a search space expansion scheme in the ATDEA approach and let search space dynamical. The efficiency will be promoted. Finally, we use TDEA and ATDEA to solve the example of model reduction. Simulation results show that the proposed TDEA and ATDEA approaches can obtain better performances than the existing DEA reported recently in the literature.
