根據(jù)油品調(diào)合的特點(diǎn)，應(yīng)用人工神經(jīng)網(wǎng)絡(luò)(Neural Network，NN)對(duì)油品在線優(yōu)化調(diào)合
系統(tǒng)進(jìn)行建模， 并采用量化正交遺傳算法(Orthogonal Genetic Algorithm with Quantization，OGA/Q)對(duì)神經(jīng)網(wǎng)絡(luò)模型進(jìn)行學(xué)習(xí)。提出了用于油品在線優(yōu)化調(diào)合系統(tǒng)的人工神經(jīng)網(wǎng)絡(luò)適宜的拓?fù)浣Y(jié)構(gòu)，給出了量化正交遺傳算法優(yōu)化的具體執(zhí)行過(guò)程，實(shí)現(xiàn)了系統(tǒng)的主要功能，該系統(tǒng)已經(jīng)廣泛地應(yīng)用于生產(chǎn)實(shí)踐中。
關(guān)鍵詞：神經(jīng)網(wǎng)絡(luò)；在線優(yōu)化；油品調(diào)合；量化正交遺傳算法
A Novel Intelligent Control Approach Based on NN and OGA/Q Zhang changnian1, 2
(1 School of Information Engineering, University of Science and Technology Beijing, Beijing, 100083, China) (2 Department of Computer, Guilin College of Aerospace Technology, Guilin 541004, China) Abstract: According to the characteristics of oil blending, develop the on-line optimization of oil blending system using the artificial neural network, and then train the neural network model by the orthogonal genetic algorithm with quantization. The artificial neural network topology for the on-line optimization of oil blending system is proposed in this work. The implementation process of orthogonal genetic algorithm with quantization is introduced in this paper too. The major function of oil blending system is achieved, and this system is wildly applied to the practice.
Keywords: neural network; on-line optimization; oil blend; orthogonal genetic algorithm with
quantization