本論文應用基因演算法在薄膜氣體分離之單目標、雙目標與三目標函數最適化，並建立了三種系統配置，包括單一氣提滲透器、串聯雙氣提滲透器及連續薄膜塔之數學模式，以及基因演算法之程式。本論文並針對自空氣分離出增濃氧氣產物之問題完成個案研究，進行以Rony值、Poxy值與薄膜面積為目標函數，且在不同氧氣產物純度要求與進料流量下之最適化，並包括高壓與低壓(真空)兩種操作模式。與文獻結果比較，對單目標函數最適化而言，基因演算法獲得同等於或優於傳統最適化法之結果。對多目標函數最適化，結果均以Pareto圖表達，最終族群解呈現了相互妥協之特質。 整體而言，較之高壓操作，低壓操作可獲回收率較低。對不同氧氣產物純度與進料流量而言，連續薄膜塔均在最佳族群解中，為最具彈性之系統配置。 Genetic Algorithm or Evolutionary Algorithm is applied for the optimization of membrane gas separation systems. Optimizations for single, binary as well as triple objective functions are studied. The optimization problem involves the selection of the optimal system schemes from three alternatives, which are Continuous Membrane Column (CMC), Single Stripper Permeator (SSP), and Two Stripper in Series Permeator (TSSP). The mathematic models for these three configurations and the program of Genetic Algorithm are developed. The air separation for enriched oxygen production is the selected system for investigation. The three objective functions include the Rony index, power consumption per unit equivalent pure oxygen, and the membrane area. Both high pressure and low pressure (vacuum) operation modes are optimized and the effects of different oxygen product purity and feed rate are analyzed. For single objective function optimization, the solutions obtained using Genetic Algorithm are equivalent or superior than those by traditional optimization methods. For binary and triple objective functions optimization, the Pareto plots presenting multiple trade-off solutions are generated. In general, compared to high pressure operation mode, the product recovery for low pressure operation mode is lower. For different product purities and feed rates, CMC scheme is always in the optimal solutions.
