基于混合高斯回歸的動(dòng)態(tài)軟測(cè)量方法研究
發(fā)布時(shí)間：2018-09-13 06:43
【摘要】：工業(yè)過(guò)程中,許多關(guān)鍵變量難以在線測(cè)量。軟測(cè)量技術(shù)成為解決該問(wèn)題的關(guān)鍵技術(shù)之一。目前,許多模型是基于測(cè)量過(guò)程處于穩(wěn)態(tài)工況的假設(shè),故模型大多為靜態(tài)軟測(cè)量模型。由于生產(chǎn)過(guò)程中工藝改變、物理結(jié)構(gòu)特性變化以及環(huán)境等因素的影響使得生產(chǎn)過(guò)程通常處于動(dòng)態(tài)工況,僅考慮對(duì)象靜態(tài)特性是不夠的,有必要對(duì)動(dòng)態(tài)軟測(cè)量建模方法進(jìn)行深入研究。本文以青霉素仿真過(guò)程和工業(yè)紅霉素發(fā)酵過(guò)程為對(duì)象,采用高斯過(guò)程回歸以及混合高斯回歸方法來(lái)研究建立動(dòng)態(tài)軟測(cè)量模型。具體工作如下:(1)針對(duì)靜態(tài)軟測(cè)量模型預(yù)測(cè)精度低和魯棒性差等問(wèn)題,本文提出了一種基于多準(zhǔn)則和高斯過(guò)程回歸的動(dòng)態(tài)軟測(cè)量建模方法。該方法綜合考慮多種模型定階準(zhǔn)則,提出了高斯過(guò)程回歸動(dòng)態(tài)軟測(cè)量模型定階策略,為模型階數(shù)確定提供了依據(jù),并將所提動(dòng)態(tài)軟測(cè)量模型應(yīng)用于紅霉素發(fā)酵過(guò)程的生物量濃度估計(jì)。研究結(jié)果表明,基于高斯過(guò)程回歸的動(dòng)態(tài)軟測(cè)量建模方法可以實(shí)現(xiàn)對(duì)生物量濃度的高精度預(yù)測(cè),且預(yù)測(cè)結(jié)果具有較小的置信度區(qū)間。(2)針對(duì)單高斯過(guò)程回歸動(dòng)態(tài)軟測(cè)量模型的局限性,提出了一種混合高斯回歸動(dòng)態(tài)軟測(cè)量模型。該模型有兩個(gè)重要參數(shù),即高斯元的個(gè)數(shù)和模型階數(shù),為了獲得優(yōu)化軟測(cè)量模型,提出一個(gè)迭代策略優(yōu)化兩個(gè)結(jié)構(gòu)參數(shù)。將所提出的動(dòng)態(tài)混合高斯回歸軟測(cè)量模型應(yīng)用于青霉素仿真過(guò)程和工業(yè)紅霉素發(fā)酵過(guò)程的生物量濃度估計(jì),并和現(xiàn)有的動(dòng)態(tài)高斯過(guò)程回歸軟測(cè)量模型比較。結(jié)果表明,所提動(dòng)態(tài)混合高斯回歸軟測(cè)量模型具有較高的預(yù)測(cè)精度,更適合于動(dòng)態(tài)多相/多模態(tài)發(fā)酵過(guò)程。(3)針對(duì)移動(dòng)窗口算法和混合高斯回歸軟測(cè)量模型中移動(dòng)窗口算法的大量更新,降低了模型的計(jì)算效率,并占用大量的計(jì)算機(jī)內(nèi)存資源等問(wèn)題。本文提出了一種基于模型性能評(píng)估的遞推混合高斯回歸建模方法來(lái)減少遞推混合高斯回歸建模方法的模型校正頻率。首先,根據(jù)過(guò)程初始特性自動(dòng)生成模型的初始置信限。然后,將預(yù)測(cè)均方根誤差指標(biāo)作為評(píng)價(jià)模型的標(biāo)準(zhǔn)。根據(jù)模型的性能評(píng)估結(jié)果,選擇性地激活模型校正,同時(shí)更新置信限。最后,將開(kāi)發(fā)的模型用于青霉素仿真過(guò)程和工業(yè)紅霉素發(fā)酵過(guò)程的生物量濃度軟測(cè)量。仿真結(jié)果表明,所開(kāi)發(fā)的模型大大提高了計(jì)算效率(模型校正頻率大大降低),而預(yù)測(cè)精度的損失可以忽略不計(jì),且與混合高斯回歸模型相比,預(yù)測(cè)精度明顯提高。
[Abstract]:In the industrial process, many key variables are difficult to measure online. Soft sensing technology has become one of the key technologies to solve this problem. At present, many models are based on the assumption that the measurement process is in steady state, so most of the models are static soft sensor models. Due to the influence of process change, physical structure characteristic change and environment factors, the production process is usually in dynamic condition, so it is not enough to consider the static characteristics of the object. It is necessary to study the modeling method of dynamic soft sensor. In this paper, the simulation process of penicillin and the fermentation process of industrial erythromycin were used to establish dynamic soft sensor model by using Gao Si process regression and mixed Gao Si regression method. The main works are as follows: (1) aiming at the problems of low prediction accuracy and poor robustness of the static soft-sensor model, a dynamic soft-sensor modeling method based on multi-criteria and Gao Si process regression is proposed in this paper. This method synthetically considers several model order determination criteria, and puts forward the order determination strategy of Gao Si process regression dynamic soft sensor model, which provides the basis for determining the model order. The dynamic soft sensor model was applied to estimate the biomass concentration of erythromycin fermentation process. The results show that the dynamic soft sensor modeling method based on Gao Si process regression can achieve high precision prediction of biomass concentration. The prediction results have a small confidence range. (2) in view of the limitation of single Gao Si regression dynamic soft sensor model, a hybrid Gao Si regression dynamic soft sensor model is proposed. The model has two important parameters, namely, the number of Gao Si elements and the order of the model. In order to obtain the optimized soft sensor model, an iterative strategy is proposed to optimize the two structural parameters. The dynamic mixed Gao Si regression soft sensor model was applied to estimate the biomass concentration of penicillin simulation process and industrial erythromycin fermentation process. The results show that the proposed dynamic mixed Gao Si regression soft sensor model has high prediction accuracy. It is more suitable for dynamic multiphase / multimodal fermentation process. (3) aiming at a large number of updates of moving window algorithm and mixed Gao Si regression soft sensor model, the computational efficiency of the model is reduced. And occupy a large number of computer memory resources and other problems. In this paper, a recursive mixed Gao Si regression modeling method based on model performance evaluation is proposed to reduce the frequency of model correction of recursive mixed Gao Si regression modeling method. First, the initial confidence limits of the model are automatically generated according to the initial characteristics of the process. Then, the root-mean-square error index is taken as the criterion of the evaluation model. Based on the performance evaluation of the model, the model correction is selectively activated and the confidence limit is updated. Finally, the developed model is applied to the soft measurement of biomass concentration in penicillin simulation process and industrial erythromycin fermentation process. The simulation results show that the developed model greatly improves the calculation efficiency (the calibration frequency of the model is greatly reduced), and the loss of prediction accuracy can be negligible, and compared with the mixed Gao Si regression model, the prediction accuracy is obviously improved.
【學(xué)位授予單位】：江蘇大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：O212.1
本文編號(hào)：2240385
[Abstract]:In the industrial process, many key variables are difficult to measure online. Soft sensing technology has become one of the key technologies to solve this problem. At present, many models are based on the assumption that the measurement process is in steady state, so most of the models are static soft sensor models. Due to the influence of process change, physical structure characteristic change and environment factors, the production process is usually in dynamic condition, so it is not enough to consider the static characteristics of the object. It is necessary to study the modeling method of dynamic soft sensor. In this paper, the simulation process of penicillin and the fermentation process of industrial erythromycin were used to establish dynamic soft sensor model by using Gao Si process regression and mixed Gao Si regression method. The main works are as follows: (1) aiming at the problems of low prediction accuracy and poor robustness of the static soft-sensor model, a dynamic soft-sensor modeling method based on multi-criteria and Gao Si process regression is proposed in this paper. This method synthetically considers several model order determination criteria, and puts forward the order determination strategy of Gao Si process regression dynamic soft sensor model, which provides the basis for determining the model order. The dynamic soft sensor model was applied to estimate the biomass concentration of erythromycin fermentation process. The results show that the dynamic soft sensor modeling method based on Gao Si process regression can achieve high precision prediction of biomass concentration. The prediction results have a small confidence range. (2) in view of the limitation of single Gao Si regression dynamic soft sensor model, a hybrid Gao Si regression dynamic soft sensor model is proposed. The model has two important parameters, namely, the number of Gao Si elements and the order of the model. In order to obtain the optimized soft sensor model, an iterative strategy is proposed to optimize the two structural parameters. The dynamic mixed Gao Si regression soft sensor model was applied to estimate the biomass concentration of penicillin simulation process and industrial erythromycin fermentation process. The results show that the proposed dynamic mixed Gao Si regression soft sensor model has high prediction accuracy. It is more suitable for dynamic multiphase / multimodal fermentation process. (3) aiming at a large number of updates of moving window algorithm and mixed Gao Si regression soft sensor model, the computational efficiency of the model is reduced. And occupy a large number of computer memory resources and other problems. In this paper, a recursive mixed Gao Si regression modeling method based on model performance evaluation is proposed to reduce the frequency of model correction of recursive mixed Gao Si regression modeling method. First, the initial confidence limits of the model are automatically generated according to the initial characteristics of the process. Then, the root-mean-square error index is taken as the criterion of the evaluation model. Based on the performance evaluation of the model, the model correction is selectively activated and the confidence limit is updated. Finally, the developed model is applied to the soft measurement of biomass concentration in penicillin simulation process and industrial erythromycin fermentation process. The simulation results show that the developed model greatly improves the calculation efficiency (the calibration frequency of the model is greatly reduced), and the loss of prediction accuracy can be negligible, and compared with the mixed Gao Si regression model, the prediction accuracy is obviously improved.
【學(xué)位授予單位】：江蘇大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：O212.1
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 夏陸岳;朱群娣;王海寧;潘海天;;動(dòng)態(tài)選擇性集成神經(jīng)網(wǎng)絡(luò)軟測(cè)量建模[J];計(jì)算機(jī)與應(yīng)用化學(xué);2016年02期
2 李翔宇;高憲文;侯延彬;;基于在線動(dòng)態(tài)高斯過(guò)程回歸抽油井動(dòng)液面軟測(cè)量建模[J];化工學(xué)報(bào);2015年06期
3 呂游;劉吉臻;楊婷婷;;基于非線性偏最小二乘回歸的軟測(cè)量建模及應(yīng)用[J];高�；瘜W(xué)工程學(xué)報(bào);2014年04期
4 王振雷;唐苦;王昕;;一種基于D-S和ARIMA的多模型軟測(cè)量方法[J];控制與決策;2014年07期
5 何志昆;劉光斌;趙曦晶;王明昊;;高斯過(guò)程回歸方法綜述[J];控制與決策;2013年08期
6 賀曉冉;陳宸;金光石;熊智華;;青霉素發(fā)酵過(guò)程的模型仿真與補(bǔ)料優(yōu)化[J];化工學(xué)報(bào);2012年09期
7 趙麗;朱永明;付梅臣;張蓬濤;曹銀貴;;主成分分析法和熵值法在農(nóng)村居民點(diǎn)集約利用評(píng)價(jià)中的比較[J];農(nóng)業(yè)工程學(xué)報(bào);2012年07期
8 任江洪;陳韜;曹長(zhǎng)修;;混合高斯過(guò)程回歸模型在鐵水硅含量預(yù)報(bào)中的應(yīng)用[J];重慶大學(xué)學(xué)報(bào);2012年02期
9 李煒;章寅;趙小強(qiáng);;混合核函數(shù)稀疏LS-SVM軟測(cè)量建模與應(yīng)用[J];控制工程;2012年01期
10 傅永峰;;一種動(dòng)態(tài)軟測(cè)量建模方法及其工業(yè)應(yīng)用[J];自動(dòng)化儀表;2011年09期
，本文編號(hào)：2240385
本文鏈接：http://sikaile.net/kejilunwen/yysx/2240385.html
最近更新
教材專著
