지능시스템을 이용한 pH 중화공정의 모델링에 관한 연구
(A) Study on The pH Neutralization Process Modeling Using Intelligent Systems
지능시스템 pH 중화공정 모델링;
- 원문 URL
This thesis is concerned with the modeling and identification of pH neutralization process via intelligent systems. The problem of regulating and controlling a pH process can be found in a variety of practical areas. However, owing to the highly nonlinear nature of the pH neutralization process it is difficult to handle. To reflect the essential aspect and construct predictive model of the pH process two types of the intelligent system is applied. One is the polynomial neural network (PNN) which has an architecture similar to feed forward neural networks whose neurons are replaced by polynomial nodes. The output of the each node in PNN structure is obtained using several types of high-order polynomial such as linear, quadratic, and modified quadratic of input variables. PNNs have fewer nodes than NNs, but the nodes are more flexible. The other is genetic algorithm based PNN(GA-PNN). GA-PNN is a sophisticated and versatile architecture which can construct models for limited data set as we1l as poorly defined complex problems. The order of the polynomial, the number of input variables, and the optimum input variables are encoded as a chromosome and fitness of each chromosome is computed. So the appropriate information of each node are evolved accordingly and tuned gradually throughout the GA iterations. Comprehensive comparisons show that the performance of the GA-PNN is significantly improved in the sense of approximation ability with a much simpler structure compared with the conventional PNN model as well as previous identification methods. Extensive simulations have shown that the nonlinear pH neutralization process can be modeled reasonably well by the intelligent systems which are simple but efficient.