Parallel Problem Solving from Nature - PPSN XIII
Parallel Problem Solving from Nature - PPSN XIII
复制标题
自然的并行问题解决 - PPSN XIII
DOI：
10.1007/978-3-319-10762-2_73
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Allmendinger R
中科院分区：
文献类型：
--
作者：
Allmendinger R
提纯是生物制药生产中必不可少的一步。在开发过程中，资源通常是有限的，无法对通常由两个或更多个层析步骤组成的给定纯化过程的操作条件进行全面评估。提出了一种基于进化多目标优化算法(EMOA)的同时优化所有运行条件的方法。在建立了受制于约束和资源分配问题的闭环优化问题之后，对四种最先进的EMAs-NSGAII、MOEA/D、SMS-EMOA和ParEGO-根据文献中提供的真实世界数据创建的测试问题进行了调整和评估。仿真结果表明，EMOA的性能取决于种群规模的设置，以及所采用的约束和资源问题处理策略。调整这些算法参数表明，EMAs，特别是SMS-EMOA和ParegO，能够在100个评估范围内可靠地发现导致高产量和产品纯度的操作条件。
Purification is an essential step in the production of biopharmaceuticals. Resources are usually limited during development to make a full assessment of operating conditions for a given purification process commonly consisting of two or more chromatographic steps. This study proposes the optimization of all operating conditions simultaneously using an evolutionary multiobjective optimization algorithm (EMOA). After formulating the closed-loop optimization problem, which is subject to constraints and resourcing issues, four state-of-the-art EMOAs — NSGAII, MOEA/D, SMS-EMOA, and ParEGO — were tuned and evaluated on test problems created from real-world data available in the literature. The simulation results revealed that the performance of an EMOA depends on the setting of the population size, and constraint and resourcing issue-handling strategies adopted. Tuning these algorithm parameters revealed that the EMOAs, in particular SMS-EMOA and ParEGO, are able to discover reliably within 100 evaluations operating conditions that lead to high levels of yield and product purity.