混凝投藥的神經(jīng)模糊控制的研究與設(shè)計.doc
約84頁DOC格式手機打開展開
混凝投藥的神經(jīng)模糊控制的研究與設(shè)計,全文68頁30000余字圖文并茂論述詳細摘 要混凝環(huán)節(jié)是水處理中非常重要的環(huán)節(jié),準確的投加混凝劑可以有效減輕過濾、消毒設(shè)備的負擔(dān),是提高水質(zhì)、取的良好混凝效果及經(jīng)濟效益的關(guān)鍵。目前國內(nèi)眾多水廠采用的混凝投藥控制主要是基于流動電流的反饋投藥控制和基于傳統(tǒng)數(shù)學(xué)模型的前饋投藥控制,控制效果都...
內(nèi)容介紹
此文檔由會員 癡狂少年 發(fā)布
混凝投藥的神經(jīng)模糊控制的研究與設(shè)計
全文68頁30000余字 圖文并茂 論述詳細
摘 要
混凝環(huán)節(jié)是水處理中非常重要的環(huán)節(jié),準確的投加混凝劑可以有效減輕過濾、消毒設(shè)備的負擔(dān),是提高水質(zhì)、取的良好混凝效果及經(jīng)濟效益的關(guān)鍵。目前國內(nèi)眾多水廠采用的混凝投藥控制主要是基于流動電流的反饋投藥控制和基于傳統(tǒng)數(shù)學(xué)模型的前饋投藥控制,控制效果都不太理想,存在沉淀池出水濁度波動大,藥劑浪費嚴重等問題。如何在線得到適合水質(zhì)變化的最佳混凝劑量,實現(xiàn)混凝劑量的最佳投加,是目前水工業(yè)中亟待解決的問題。
混凝過程包括混凝劑的投加、混合、絮凝和沉淀部分,這個過程需要40 min以上的時間;影響因素眾多,受原水濁度、溫度、PH、堿度等的影響,還受配水流量和混凝工藝的影響,是個復(fù)雜的物理化學(xué)過程,難以準確數(shù)學(xué)模型?;炷^程是大滯后、非線性、時變系統(tǒng),難以按傳統(tǒng)的控制方法進行有效的投藥控制。蓬勃發(fā)展的智能控制理論為這一問題的解決提供了新的出路。
本文首先介紹了水處理過程和混凝投藥控制的發(fā)展、現(xiàn)狀,在簡要介紹智能控制理論中的神經(jīng)網(wǎng)絡(luò)控制和模糊邏輯系統(tǒng)之后,引入神經(jīng)網(wǎng)絡(luò)與模糊邏輯的融合,并詳細介紹了一種用多層前饋神經(jīng)網(wǎng)絡(luò)優(yōu)化模糊邏輯系統(tǒng)的自適應(yīng)模糊推理系統(tǒng)-ANFIS。然后在分析混凝過程特性和目前主要使用的投藥控制方案的基礎(chǔ)上,分別設(shè)計了能夠取代燒杯試驗投藥控制的基于原水濁度、溫度、PH、堿度的BP神經(jīng)網(wǎng)絡(luò)前饋投藥控制器和ANFIS前饋投藥控制器,重點為后者。在ANFIS前饋投藥控制器的設(shè)計中,運用減法聚類對樣本數(shù)據(jù)進行空間劃分,獲取初始模糊隸屬函數(shù)和模糊規(guī)則,得到ANFIS模型的初始結(jié)構(gòu)。用成功的燒杯試驗歷史數(shù)據(jù)進行了仿真驗證,為了比較還進行了傳統(tǒng)的數(shù)學(xué)模型前饋投藥控制仿真,從投藥預(yù)測值-實際值的對比圖和均方根誤差(RMSE)等可以看出ANFIS投藥前饋控制模型明顯優(yōu)于其它兩種控制模型,它能夠根據(jù)原水水質(zhì)適時有效預(yù)測混凝投藥量,而神經(jīng)網(wǎng)絡(luò)前饋控制器模型的投藥預(yù)測效果一般。最后本文又進行了ANFIS前饋投藥控制的工程實現(xiàn)方案初步設(shè)計。
關(guān)鍵詞:混凝投藥控制 前饋控制 BP神經(jīng)網(wǎng)絡(luò) 自適應(yīng)神經(jīng)模糊推理系統(tǒng)(ANFIS) 水處理
Abstract
Coagulation is one of the most important processes of water treatment. It can reduce the operating load of filtration and antisepsis equipments by adding coagulant dosing accurately, which is very important to improve water qualities and economic benefits. At present the dosing control of domestic factory is based on streaming current detector (SCD) feed-back control and based on mathematic model feed-forward coagulant dosing control. But the results of both coagulant control schemes are not satisfying. There are some questions of chemicals wastage and sediment output water qualities varieties. It is a pending problem how to calculate the efficient coagulant dosage according currently raw water qualities in water treatment industry .
It takes more than 40 minutes to finish coagulant process which includes the projecting of chemicals, mixing, flocculating and subsiding. It is affected by many factors such as many characteristics of raw water quality, capacity of treating water and coagulant technics. Coagulant process is not only a complicity physical-chemical process of difficultly modeling but also a big time-delay, nonlinear and uncertain system. So it is difficult to control by traditional control approaches. The blooming artificial control provides a new way for coagulation control.
In this thesis,the water treatment process and the actuality and trend of coagulant dosing control scheme are first introduced. After briefly introduced Neural Network Control (NNC) and Fuzzy Control of IC , Adaptive-Network-Based Fuzzy Inference System (ANFIS) ,one of the combination of NNC and FC, is expatiated in detail. By analyzing the characteristics of coagulant process and the main schemes of coagulant dosing control, NN feed-forward controller and ANFIS feed-forward controller based on raw water turbidity, temperature, PH, alkalinity are designed which can substitute Jar-Test coagulant dosage control. In designing ANFIS scheme, some sample data is classified by subtractive cluster method, and some fuzzy membership functions and rules are obtained, and a initial ANFIS structure is established. NN control model and ANFIS control model are simulated and tested by using Jar-test historical data. Traditional mathematic model is also simulated for comparison. The results of simulation suggest that ANFIS feed-forward control model is distinct superior to the others. It can predict coagulant dosage effectively according to raw water in time. The control performance of NN model is generic, not very good. At last, the scheme of ANFIS feed-forward control of coagulant dosage is discussed on how to practice in engineering.
Keyword: coagulant dosing control BP ANFIS feed-forward control water treatment
目 錄
第一章 緒論……………………………………………………1
1.1水處理過程…………………………………………………………………1
1.1.1水中雜質(zhì)及處理方法…………………………………………………1
1.1.2 凈水處理基本工藝 ……………………………………………… 2
1.1.2.1 預(yù)處理…………………………………………………………2
1.1.2.2混凝、沉淀……………………………………………………3
1.1.2.3 過濾、消毒……………………………………………………3
1.2 混凝投藥系統(tǒng)研究意義 …………………………………………………4
1.3 混凝投藥控制的發(fā)展、現(xiàn)狀 ……………………………………………4
1.3.1 手動控制階段 ……………………………………………………5
1.3.2 自動控制階段 ……………………………………………………5
1.3.2.1 簡單反饋控制系統(tǒng)…………………………………………5
1.3.2.2 前饋控制系統(tǒng)………………………………………………7
1.3.2.3 復(fù)合控制系統(tǒng)………………………………………………7
1.3.3智能控制階段…………………………………………………… 8
1.4 本文主要工作……………………………………………………………9
第二章 神經(jīng)模糊控制理論概述 …………………………………………………12.1神經(jīng)網(wǎng)絡(luò)控制………………………………………………………… 10
2.1.1神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)……………………………………………………11
2.1.2 BP神經(jīng)網(wǎng)絡(luò)……………………………………………………12
2.1.3 神經(jīng)網(wǎng)絡(luò)特點 …………………………………………………15
2.2 模糊控制………………………………………………………………15
2.2.1基本概念,基本思想 ……………… …………………………16
2.2.2模糊控制的特點…………………………………………………18
2.3 自適應(yīng)神經(jīng)模糊推理系統(tǒng)……………………………………………18
2.4 小結(jié)………………………………………………………………… 22
第三章 混凝投藥控制系統(tǒng)分析……………………………………………………23
3.1 影響混凝效果因素……………………………………………………23
3.2 被控對象特性…………………………………………………………24
3.2.1 影響混凝的水質(zhì)因素分析………………………………………24
3.2.2混凝過程的主要特點……………………………………………25
3.3 混凝投藥控制方案分析 ………………………………………………25
3.3.1 反饋投藥控制方式 ……………………………………………26
3.3.2前饋投藥控制方式………………………………………………27
3.3.3本文采用方案 …………………………………………………28
3.3.4 小節(jié) ……………………………………………………………30
第四章 混凝投藥量前饋控制器的設(shè)計和仿真……………………………………31
4.1 數(shù)據(jù)來源………………………………………………………………31
4.2 投藥量的神經(jīng)網(wǎng)絡(luò)前饋控制器………………………………………33
4.2.1 BP神經(jīng)網(wǎng)絡(luò)控制器的設(shè)計……………………………………33
4.2.1.1 數(shù)據(jù)歸一化……………………………………………33
4.2.2 仿真實現(xiàn)………………………………………………………36
4.3混凝投藥量的ANFIS前饋控制………………………………………38
4.3.1初始模糊推理系統(tǒng)的建立……………………………………38
4.3.1.1減法聚類 ……………………………………………39
4.3.1.2 由聚類中心構(gòu)造一階T-S模型 ……………………40
4.3.2 仿真實現(xiàn)…………………………………………………… 41
4.4 傳統(tǒng)的回歸模型法仿真結(jié)果………………………………………43
4.5 仿真結(jié)果比較分析…………………………………………………45
4.6 小結(jié)…………………………………………………………………46
第五章 ANFIS投藥控制的工程實現(xiàn)方案…………………………………………47
5.1水廠現(xiàn)狀……………………………………………………………47
5.2 ANFIS前饋控制部分的軟硬件實現(xiàn) ……………………………47
5.2.1 離線學(xué)習(xí)的實現(xiàn)……………………………………………47
5.2.2 在線控制的實現(xiàn)……………………………………………48
5.2.3 離線再優(yōu)化…………………………………………………49
5.3藥液投加控制………………………………………………………49
5.4 小節(jié) ………………………………………………………………50
第六章 結(jié) 束 語 ………………………………………………………………51
參考文獻 ……………………………………………………………………………52
致謝 …………………………………………………………………………………55
部分參考文獻:
【39】 孫連鵬, 南軍, 楊艷玲. 原水濁度對透光率脈動混凝投藥控制技術(shù)的影響分析. 給水排水, 2002, No.7:19-22
【40】 楊萬東, 楊振海, 王東田. 流動電流法混凝投藥控制的取樣系統(tǒng). 中國給水排水, 1998, No.4:33-34
【41】 Katsuhiko Ogata著, 現(xiàn)代控制工程(第四版)(盧伯英,于海勛, 等譯), 北京:電子工業(yè)出版社, 2003, 1.3節(jié)
全文68頁30000余字 圖文并茂 論述詳細
摘 要
混凝環(huán)節(jié)是水處理中非常重要的環(huán)節(jié),準確的投加混凝劑可以有效減輕過濾、消毒設(shè)備的負擔(dān),是提高水質(zhì)、取的良好混凝效果及經(jīng)濟效益的關(guān)鍵。目前國內(nèi)眾多水廠采用的混凝投藥控制主要是基于流動電流的反饋投藥控制和基于傳統(tǒng)數(shù)學(xué)模型的前饋投藥控制,控制效果都不太理想,存在沉淀池出水濁度波動大,藥劑浪費嚴重等問題。如何在線得到適合水質(zhì)變化的最佳混凝劑量,實現(xiàn)混凝劑量的最佳投加,是目前水工業(yè)中亟待解決的問題。
混凝過程包括混凝劑的投加、混合、絮凝和沉淀部分,這個過程需要40 min以上的時間;影響因素眾多,受原水濁度、溫度、PH、堿度等的影響,還受配水流量和混凝工藝的影響,是個復(fù)雜的物理化學(xué)過程,難以準確數(shù)學(xué)模型?;炷^程是大滯后、非線性、時變系統(tǒng),難以按傳統(tǒng)的控制方法進行有效的投藥控制。蓬勃發(fā)展的智能控制理論為這一問題的解決提供了新的出路。
本文首先介紹了水處理過程和混凝投藥控制的發(fā)展、現(xiàn)狀,在簡要介紹智能控制理論中的神經(jīng)網(wǎng)絡(luò)控制和模糊邏輯系統(tǒng)之后,引入神經(jīng)網(wǎng)絡(luò)與模糊邏輯的融合,并詳細介紹了一種用多層前饋神經(jīng)網(wǎng)絡(luò)優(yōu)化模糊邏輯系統(tǒng)的自適應(yīng)模糊推理系統(tǒng)-ANFIS。然后在分析混凝過程特性和目前主要使用的投藥控制方案的基礎(chǔ)上,分別設(shè)計了能夠取代燒杯試驗投藥控制的基于原水濁度、溫度、PH、堿度的BP神經(jīng)網(wǎng)絡(luò)前饋投藥控制器和ANFIS前饋投藥控制器,重點為后者。在ANFIS前饋投藥控制器的設(shè)計中,運用減法聚類對樣本數(shù)據(jù)進行空間劃分,獲取初始模糊隸屬函數(shù)和模糊規(guī)則,得到ANFIS模型的初始結(jié)構(gòu)。用成功的燒杯試驗歷史數(shù)據(jù)進行了仿真驗證,為了比較還進行了傳統(tǒng)的數(shù)學(xué)模型前饋投藥控制仿真,從投藥預(yù)測值-實際值的對比圖和均方根誤差(RMSE)等可以看出ANFIS投藥前饋控制模型明顯優(yōu)于其它兩種控制模型,它能夠根據(jù)原水水質(zhì)適時有效預(yù)測混凝投藥量,而神經(jīng)網(wǎng)絡(luò)前饋控制器模型的投藥預(yù)測效果一般。最后本文又進行了ANFIS前饋投藥控制的工程實現(xiàn)方案初步設(shè)計。
關(guān)鍵詞:混凝投藥控制 前饋控制 BP神經(jīng)網(wǎng)絡(luò) 自適應(yīng)神經(jīng)模糊推理系統(tǒng)(ANFIS) 水處理
Abstract
Coagulation is one of the most important processes of water treatment. It can reduce the operating load of filtration and antisepsis equipments by adding coagulant dosing accurately, which is very important to improve water qualities and economic benefits. At present the dosing control of domestic factory is based on streaming current detector (SCD) feed-back control and based on mathematic model feed-forward coagulant dosing control. But the results of both coagulant control schemes are not satisfying. There are some questions of chemicals wastage and sediment output water qualities varieties. It is a pending problem how to calculate the efficient coagulant dosage according currently raw water qualities in water treatment industry .
It takes more than 40 minutes to finish coagulant process which includes the projecting of chemicals, mixing, flocculating and subsiding. It is affected by many factors such as many characteristics of raw water quality, capacity of treating water and coagulant technics. Coagulant process is not only a complicity physical-chemical process of difficultly modeling but also a big time-delay, nonlinear and uncertain system. So it is difficult to control by traditional control approaches. The blooming artificial control provides a new way for coagulation control.
In this thesis,the water treatment process and the actuality and trend of coagulant dosing control scheme are first introduced. After briefly introduced Neural Network Control (NNC) and Fuzzy Control of IC , Adaptive-Network-Based Fuzzy Inference System (ANFIS) ,one of the combination of NNC and FC, is expatiated in detail. By analyzing the characteristics of coagulant process and the main schemes of coagulant dosing control, NN feed-forward controller and ANFIS feed-forward controller based on raw water turbidity, temperature, PH, alkalinity are designed which can substitute Jar-Test coagulant dosage control. In designing ANFIS scheme, some sample data is classified by subtractive cluster method, and some fuzzy membership functions and rules are obtained, and a initial ANFIS structure is established. NN control model and ANFIS control model are simulated and tested by using Jar-test historical data. Traditional mathematic model is also simulated for comparison. The results of simulation suggest that ANFIS feed-forward control model is distinct superior to the others. It can predict coagulant dosage effectively according to raw water in time. The control performance of NN model is generic, not very good. At last, the scheme of ANFIS feed-forward control of coagulant dosage is discussed on how to practice in engineering.
Keyword: coagulant dosing control BP ANFIS feed-forward control water treatment
目 錄
第一章 緒論……………………………………………………1
1.1水處理過程…………………………………………………………………1
1.1.1水中雜質(zhì)及處理方法…………………………………………………1
1.1.2 凈水處理基本工藝 ……………………………………………… 2
1.1.2.1 預(yù)處理…………………………………………………………2
1.1.2.2混凝、沉淀……………………………………………………3
1.1.2.3 過濾、消毒……………………………………………………3
1.2 混凝投藥系統(tǒng)研究意義 …………………………………………………4
1.3 混凝投藥控制的發(fā)展、現(xiàn)狀 ……………………………………………4
1.3.1 手動控制階段 ……………………………………………………5
1.3.2 自動控制階段 ……………………………………………………5
1.3.2.1 簡單反饋控制系統(tǒng)…………………………………………5
1.3.2.2 前饋控制系統(tǒng)………………………………………………7
1.3.2.3 復(fù)合控制系統(tǒng)………………………………………………7
1.3.3智能控制階段…………………………………………………… 8
1.4 本文主要工作……………………………………………………………9
第二章 神經(jīng)模糊控制理論概述 …………………………………………………12.1神經(jīng)網(wǎng)絡(luò)控制………………………………………………………… 10
2.1.1神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)……………………………………………………11
2.1.2 BP神經(jīng)網(wǎng)絡(luò)……………………………………………………12
2.1.3 神經(jīng)網(wǎng)絡(luò)特點 …………………………………………………15
2.2 模糊控制………………………………………………………………15
2.2.1基本概念,基本思想 ……………… …………………………16
2.2.2模糊控制的特點…………………………………………………18
2.3 自適應(yīng)神經(jīng)模糊推理系統(tǒng)……………………………………………18
2.4 小結(jié)………………………………………………………………… 22
第三章 混凝投藥控制系統(tǒng)分析……………………………………………………23
3.1 影響混凝效果因素……………………………………………………23
3.2 被控對象特性…………………………………………………………24
3.2.1 影響混凝的水質(zhì)因素分析………………………………………24
3.2.2混凝過程的主要特點……………………………………………25
3.3 混凝投藥控制方案分析 ………………………………………………25
3.3.1 反饋投藥控制方式 ……………………………………………26
3.3.2前饋投藥控制方式………………………………………………27
3.3.3本文采用方案 …………………………………………………28
3.3.4 小節(jié) ……………………………………………………………30
第四章 混凝投藥量前饋控制器的設(shè)計和仿真……………………………………31
4.1 數(shù)據(jù)來源………………………………………………………………31
4.2 投藥量的神經(jīng)網(wǎng)絡(luò)前饋控制器………………………………………33
4.2.1 BP神經(jīng)網(wǎng)絡(luò)控制器的設(shè)計……………………………………33
4.2.1.1 數(shù)據(jù)歸一化……………………………………………33
4.2.2 仿真實現(xiàn)………………………………………………………36
4.3混凝投藥量的ANFIS前饋控制………………………………………38
4.3.1初始模糊推理系統(tǒng)的建立……………………………………38
4.3.1.1減法聚類 ……………………………………………39
4.3.1.2 由聚類中心構(gòu)造一階T-S模型 ……………………40
4.3.2 仿真實現(xiàn)…………………………………………………… 41
4.4 傳統(tǒng)的回歸模型法仿真結(jié)果………………………………………43
4.5 仿真結(jié)果比較分析…………………………………………………45
4.6 小結(jié)…………………………………………………………………46
第五章 ANFIS投藥控制的工程實現(xiàn)方案…………………………………………47
5.1水廠現(xiàn)狀……………………………………………………………47
5.2 ANFIS前饋控制部分的軟硬件實現(xiàn) ……………………………47
5.2.1 離線學(xué)習(xí)的實現(xiàn)……………………………………………47
5.2.2 在線控制的實現(xiàn)……………………………………………48
5.2.3 離線再優(yōu)化…………………………………………………49
5.3藥液投加控制………………………………………………………49
5.4 小節(jié) ………………………………………………………………50
第六章 結(jié) 束 語 ………………………………………………………………51
參考文獻 ……………………………………………………………………………52
致謝 …………………………………………………………………………………55
部分參考文獻:
【39】 孫連鵬, 南軍, 楊艷玲. 原水濁度對透光率脈動混凝投藥控制技術(shù)的影響分析. 給水排水, 2002, No.7:19-22
【40】 楊萬東, 楊振海, 王東田. 流動電流法混凝投藥控制的取樣系統(tǒng). 中國給水排水, 1998, No.4:33-34
【41】 Katsuhiko Ogata著, 現(xiàn)代控制工程(第四版)(盧伯英,于海勛, 等譯), 北京:電子工業(yè)出版社, 2003, 1.3節(jié)