基于神经网络及遗传算法的电渣熔铸优化系统设计  

Optimized System Design for Electro-slag Casting based on Artificial Neural Network and Genetic Algorithm

作　　者：饶磊[1] 李小龙[1] 张莹[1] 耿茂鹏[1] 

机构地区：[1]南昌大学机电工程学院

出　　处：《特种铸造及有色合金》2010年第2期117-119,共3页Special Casting & Nonferrous Alloys

基　　金：国家高技术研究发展计划(863计划)资助项目(715-009-0110)

摘　　要：电渣熔铸是一种将精炼和成形相结合的技术,在实际生产中既要充分发挥它在材料提纯精炼方面的优势,又要兼顾生产效率和生产成本等因素,因此是一个典型的多目标组合优化的问题。为此,提出了用电极锥头提纯系数、自耗电极熔化率和有效功率因数3个指标作为最终优化目标,以熔铸电流、渣池深度和冷却水流量为设计变量,基于人工神经网络和遗传算法理论,在Matlab平台上建立了电渣熔铸工艺参数的多目标优化系统,较好地协调了3个指标的相互关系,并预测了最佳的工艺参数组合。Electro-slag casting is a technology combining refinement with forming, which exhibits a multi-objective problem due to not only utilizing the advantages of purifying materials but also considering product efficiency and cost. The purification coefficient of consumable electrode end, melting ratio of consumable electrode and effective power factor are presented to be taken as the optimized target. A multi-objective optimized system of processing parameters for electroslag casting was established on the Matlab platform based on artificial neural network and genetic algorithm theory by designing remelting current, depth of slag pool and flow rate of cooling water as variables, showing a positive reference for practical production.

关 键 词：神经网络 遗传算法 优化 电渣熔铸 

分 类 号：TG249.9[金属学及工艺—铸造]