本文關(guān)鍵詞：基于遺傳算法與人工神經(jīng)網(wǎng)絡(luò)的加熱爐建模方法研究　出處：《中國科學(xué)技術(shù)大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： BP神經(jīng)網(wǎng)絡(luò) 遺傳算法 非線性建模 權(quán)值優(yōu)化 樣本數(shù)據(jù) 加熱爐

【摘要】：加熱爐是一個特性復(fù)雜的工業(yè)生產(chǎn)對象,對于加熱爐的建模,傳統(tǒng)的建模方法往往不夠精確,投運效果不盡如人意。隨著智能技術(shù)的蓬勃發(fā)展,以BP神經(jīng)網(wǎng)絡(luò)為代表的神經(jīng)網(wǎng)絡(luò)建模方法在工業(yè)過程中的應(yīng)用日漸廣泛。遺傳算法作為一種進(jìn)化計算方法,具有的全局搜索能力能夠較好地克服BP神經(jīng)網(wǎng)絡(luò)容易陷入局部極小值的缺點。因此,研究將BP神經(jīng)網(wǎng)絡(luò)與遺傳算法相結(jié)合的方法十分必要。本文提出了一種基于歷史數(shù)據(jù)的加熱爐神經(jīng)網(wǎng)絡(luò)建模方法。該方法首先確定BP神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)得到網(wǎng)絡(luò)模型的參數(shù)個數(shù)。然后通過遺傳算法對編碼后的個體反復(fù)地選擇、交叉、變異,最終獲得的最優(yōu)個體包含BP神經(jīng)網(wǎng)絡(luò)權(quán)值和閾值的最佳參數(shù)組合,將其解碼后作為BP神經(jīng)網(wǎng)絡(luò)的初始值。最后通過BP算法訓(xùn)練得到加熱爐對象的神經(jīng)網(wǎng)絡(luò)模型。本文所做的主要工作與貢獻(xiàn)有以下幾點:(1)針對加熱爐對象的復(fù)雜特性,本文從對象的輸入輸出特性出發(fā),研究了利用神經(jīng)網(wǎng)絡(luò)對加熱爐爐溫建模的有效性,通過對比有效性指標(biāo),解決了神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)難以選擇的問題。(2)本文提出了將遺傳算法應(yīng)用于加熱爐神經(jīng)網(wǎng)絡(luò)建模中,通過遺傳算法的大規(guī)模全局搜索能力優(yōu)化BP神經(jīng)網(wǎng)絡(luò)模型的權(quán)值和閾值,避免了網(wǎng)絡(luò)陷入局部極小值的缺點,加快了網(wǎng)絡(luò)的收斂速度�；谠摲椒ǐ@得的模型學(xué)習(xí)能力更強,預(yù)測效果更好。(3)為了加快遺傳算法的收斂速度,提高運算效率,本文基于加熱爐的運行數(shù)據(jù),對遺傳算法進(jìn)行參數(shù)自適應(yīng)調(diào)整。設(shè)計并實現(xiàn)了變異概率自適應(yīng)的遺傳算法,加快了神經(jīng)網(wǎng)絡(luò)模型參數(shù)的收斂速度。(4)本文以唐山某鋼鐵廠的加熱爐為研究對象,選取該對象的樣本數(shù)據(jù)來設(shè)計加熱爐神經(jīng)網(wǎng)絡(luò)模型,通過對比驗證了該方法的可行性。結(jié)果表明應(yīng)用該方法進(jìn)行加熱爐爐溫建模是行之有效的。
[Abstract]:Reheating furnace is a complex industrial production object. The traditional modeling method is often not accurate enough and the operation effect is not satisfactory. With the rapid development of intelligent technology. BP neural network modeling method, represented by BP neural network, is widely used in industrial process. Genetic algorithm (GA) is an evolutionary computing method. The global search ability can overcome the shortcoming that BP neural network is easy to fall into local minima. It is necessary to study the method of combining BP neural network with genetic algorithm. In this paper, a neural network modeling method for heating furnace based on historical data is proposed. This method first determines the BP neural network structure to get the network. The number of parameters of the model. Then the genetic algorithm is used to select the coded individuals repeatedly. Crossover, mutation, and the final optimal individuals include BP neural network weights and threshold values of the best combination of parameters. After decoding it as the initial value of BP neural network, the neural network model of heating furnace object is trained by BP algorithm. The main work and contribution of this paper are as follows: 1). Aiming at the complex characteristics of heating furnace object. Based on the input and output characteristics of the object, this paper studies the effectiveness of modeling the furnace temperature with neural network, and compares the validity index. It solves the problem that the neural network structure is difficult to select. (2) in this paper, the genetic algorithm is applied to the neural network modeling of heating furnace. The weight and threshold of BP neural network model are optimized by the large scale global search ability of genetic algorithm, which avoids the shortcoming that the network falls into local minima. Based on this method, the model learning ability is stronger, the prediction effect is better.) in order to speed up the convergence speed of genetic algorithm, improve the operation efficiency. Based on the operation data of heating furnace, this paper adaptively adjusts the parameters of genetic algorithm, and designs and implements a genetic algorithm with adaptive mutation probability. This paper takes the heating furnace of a steel plant in Tangshan as the research object, and selects the sample data of the object to design the neural network model of the heating furnace. The feasibility of the method is verified by comparison and the results show that the method is effective in modeling furnace temperature.
【學(xué)位授予單位】：中國科學(xué)技術(shù)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TG307;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 馬軍;竇超;;我國鋼鐵行業(yè)產(chǎn)能利用率的測度及產(chǎn)能過剩影響因素分析[J];經(jīng)濟問題;2017年02期

2 魏建新;吳漢軍;;2017年宏觀經(jīng)濟形勢與鋼鐵市場展望[J];中國鋼鐵業(yè);2017年01期

3 吳思;;2016產(chǎn)業(yè)大事件[J];中國經(jīng)濟報告;2017年01期

4 朱海兵;崔玉;熊浩;;基于改進(jìn)型BP神經(jīng)網(wǎng)絡(luò)的電網(wǎng)負(fù)荷預(yù)測[J];現(xiàn)代電子技術(shù);2016年20期

5 薛美盛;孫勝杰;袁鑫;李先知;;一種基于歷史數(shù)據(jù)的加熱爐溫度模糊控制規(guī)則提取方法[J];化工自動化及儀表;2016年09期

6 蘇鑫;裴華健;吳迎亞;高金森;藍(lán)興英;;應(yīng)用經(jīng)遺傳算法優(yōu)化的BP神經(jīng)網(wǎng)絡(luò)預(yù)測催化裂化裝置焦炭產(chǎn)率[J];化工進(jìn)展;2016年02期

7 何維達(dá);潘崢嶸;;產(chǎn)能過剩的困境擺脫:解析中國鋼鐵行業(yè)[J];廣東社會科學(xué);2015年01期

8 郭亦文;李軍;耿林霄;;基于遺傳算法獲取模糊規(guī)則[J];計算機應(yīng)用;2014年10期

9 王玲;;基于BP算法的人工神經(jīng)網(wǎng)絡(luò)建模研究[J];裝備制造技術(shù);2014年01期

10 王樂一;趙文哠;;系統(tǒng)辨識:新的模式、挑戰(zhàn)及機遇[J];自動化學(xué)報;2013年07期

相關(guān)博士學(xué)位論文 前1條

1 王吉權(quán);BP神經(jīng)網(wǎng)絡(luò)的理論及其在農(nóng)業(yè)機械化中的應(yīng)用研究[D];沈陽農(nóng)業(yè)大學(xué);2011年

相關(guān)碩士學(xué)位論文 前6條

1 袁鑫;蓄熱式加熱爐爐溫廣義預(yù)測控制器設(shè)計與實現(xiàn)[D];中國科學(xué)技術(shù)大學(xué);2016年

2 孫勝杰;基于樣本數(shù)據(jù)的模糊規(guī)則提取方法研究及其應(yīng)用[D];中國科學(xué)技術(shù)大學(xué);2016年

3 候志強;基于遺傳算法的PID控制參數(shù)優(yōu)化在爐溫監(jiān)控系統(tǒng)中的應(yīng)用[D];中南大學(xué);2012年

4 何楚衡;基于改進(jìn)BP神經(jīng)網(wǎng)絡(luò)的鋼坯加熱爐溫度優(yōu)化控制的研究[D];南華大學(xué);2010年

5 朱文龍;基于遺傳算法的BP神經(jīng)網(wǎng)絡(luò)在多目標(biāo)優(yōu)化中的應(yīng)用研究[D];哈爾濱理工大學(xué);2009年

6 段侯峰;基于遺傳算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的變壓器故障診斷[D];北京交通大學(xué);2008年

，

本文編號：1381489