遗传算法优化框架中使用嵌入的混合可视化和数据分析的过程设计优化

Process design optimization using embedded hybrid visualization and data analysis techniques within a genetic algorithm optimization framework

非线性、非凸、不连续的数学模型的使用,使得过程优化问题难以求解。虽然确定性方法已经取得了重大的进步,但随机方法,特别是遗传算法提供了一种更有优势的方法。然而,遗传算法的性质决定了其不适合求解带有高约束的问题。本文提出了一个适用于高度约束问题的目标遗传算法,算法中的算子：交叉和变异,是在数据分析步骤得到的关于可行区域和目标函数行为信息的基础上定义。数据分析是以平行坐标系中的可视化描述为基础,一种模式匹配算法,扫描园算法,通过学习向量量化的使用被扩展来自动地确定目标函数和搜索空间的关键特征,这些特征被用于确定遗传算子。对石油稳定问题应用新的目标遗传算法,其结果证明了方法的有用、高效和健壮性。作为数据分析的核心,可视化技术的使用也可以用于解释优化过程得到的结果。

Process optimization is a difficult task due to the non-linear, non-convex and often discontinuous nature of the mathematical models used. Although significant advances in deterministic methods have been made, stochastic procedures, specifically genetic algorithms, provide attractive technology for solving these optimization problems. However, genetic algorithms are not naturally suited to highly constrained problems. We propose a targeted genetic algorithm for process optimization which is suitable for highly constrained problems. The genetic operators, crossover and mutation, are defined based on information gained about the feasible region and the behavior of the objective function through the use of a data analysis procedure. The data analysis is based on a visual representation, the parallel co-ordinate system. A pattern matching algorithm, the Scan Circle Algorithm is extended through the use of Learning Vector Quantization to identify, automatically, key features of the objective function and the search space. These features are used to target the genetic operators. Results from the application of the new targeted genetic algorithm to an oil stabilization problem are presented, demonstrating the effective, efficient and robust nature of the implementation. The use of visualization as the core of the data analysis step also provides a useful tool for explaining the results obtained by the optimization procedure.