摘要
Three-layer feedforward networks have been widely used in modeling chemical engineering processes and prior-knowledge-based methods have been introduced to improve their performances.In this paper,we propose the methodology of designing better prior-knowledge-based hybrid methods by combining the existing ones. Then according to this methodology,two hybrid methods,interpolation-optimization (IO) method and interpolation penalty-function (IPF) method,are designed as examples.Finally,both methods are applied to modeling two cases in chemical engineering to investigate their effectiveness.Simulation results show that the performances of the hybrid methods are better than those of their parents.
Three-layer feedforward networks have been widely used in modelingchemical engineering processes and prior-knowledge-based methods havebeen introduced to improve their performances. In this paper, wepropose the methodology of designing better prior-knowledge-basedhybrid methods by combining the existing ones. Then according to thismethodology, two hybrid methods, interpolation-optimization (IO)method and interpolation- penalty-function (IPF) method, are designedas examples. Finally, both methods are applied to modeling two casesin chemical engineering to investigate their effectiveness.Simulation results show that the performances of the hybrid methodsare better than those of their parents.
基金
Supported by the National Natural Science Foundation of China (No. 20076041)
关键词
混合方法
应用化学工程
前馈网络
编码
hybrid method
interpolation-optimization method
interpolation-penalty-function method
prior knowledge