本文選題：空氣質(zhì)量監(jiān)測系統(tǒng) + 氣體交叉干擾��； 參考：《北京交通大學(xué)》2017年碩士論文

【摘要】：近年來,空氣污染日益嚴(yán)重,提升空氣質(zhì)量是民眾的迫切期盼,因此空氣質(zhì)量監(jiān)測系統(tǒng)的建設(shè)也成為各地環(huán)境保護局和眾多環(huán)境保護企業(yè)所關(guān)注的焦點領(lǐng)域。建設(shè)空氣質(zhì)量監(jiān)測系統(tǒng)首先要在需要進行監(jiān)測的位置布置氣體傳感器,然后將所有氣體傳感器連接組成一個傳感器網(wǎng)絡(luò)。由于氣體傳感器的氣敏特性,氣體傳感器在監(jiān)測混合氣體污染物時會受到交叉干擾,導(dǎo)致監(jiān)測不準(zhǔn)確。本文主要針對電化學(xué)氣體傳感器在工業(yè)園區(qū)周圍監(jiān)測無機氣體污染物時產(chǎn)生交叉干擾的問題進行具體的校正方法研究。目前,主流的校正方法是基于氣體傳感器集群形成的物聯(lián)網(wǎng),利用神經(jīng)網(wǎng)絡(luò)對上傳的數(shù)據(jù)進行訓(xùn)練學(xué)習(xí),構(gòu)建傳感器校正模型。因此,本文對基于誤差反向傳播(BP)神經(jīng)網(wǎng)絡(luò)的傳感器校正模型,進行了算法優(yōu)化以及模型改進。論文的主要工作包括:首先對常規(guī)的基于BP神經(jīng)網(wǎng)絡(luò)的校正模型使用的BP算法進行分析,指出BP算法由于其理論缺陷,在訓(xùn)練校正模型階段易于陷入局部最優(yōu)的誤區(qū),并提出將粒子群(PSO)算法與BP算法結(jié)合的優(yōu)化算法。該優(yōu)化算法從優(yōu)化網(wǎng)絡(luò)初始權(quán)重的角度,充分發(fā)揮PSO算法全局尋優(yōu)的優(yōu)勢,結(jié)合BP算法局部最優(yōu)的特點,有效避免了校正模型在訓(xùn)練過程中陷入局部極小的情況,并加快了校正模型訓(xùn)練的收斂速度。然后對校正模型的工作方式以及實際氣體傳感器的監(jiān)測數(shù)據(jù)進行分析,從信息利用以及校正模型實際應(yīng)用所處環(huán)境的角度,指出常規(guī)的基于BP神經(jīng)網(wǎng)絡(luò)的校正模型不能充分利用氣體傳感器監(jiān)測濃度的變化信息,以致校正模型的校正精度受限,并提出融合了長短期記憶(LSTM)神經(jīng)網(wǎng)絡(luò)和BP神經(jīng)網(wǎng)絡(luò)的改進校正模型。該改進模型首先利用氣體濃度變化在時間上連續(xù)的特點,通過LSTM網(wǎng)絡(luò)消除了環(huán)境中未知雜氣對氣體傳感器的影響,然后級聯(lián)BP神經(jīng)網(wǎng)絡(luò),實現(xiàn)改進模型的構(gòu)建,提高了校正模型的工作性能。論文最后從數(shù)據(jù)驗證的角度,結(jié)合仿真建模得到的實驗數(shù)據(jù),進一步分析證明了文中提出的優(yōu)化算法較之BP算法在校正模型訓(xùn)練過程中的優(yōu)越性,以及改進的校正模型在實際應(yīng)用環(huán)境中比常規(guī)校正模型擁有更高的校正精度。
[Abstract]:In recent years, the increasingly serious air pollution, improve air quality is urgently looking forward to the public, so the construction of air quality monitoring system has become the focus of the field of environmental protection and Environmental Protection Bureau around many of the concerns of the enterprise. Firstly, the construction of air quality monitoring system should be located in the monitoring of the gas sensor, and then all the gas sensor connection a sensor network. Because of the characteristics of the gas sensors, gas sensors will be cross interference in the monitoring of mixed gas pollutants, resulting in inaccurate monitoring. This paper mainly studies the concrete correction method for electrochemical gas sensor cross interference in the industrial park around the problem of monitoring of inorganic gas pollutants. At present, the mainstream correction method the network is based on gas sensor clusters, using neural network to upload the number According to the learning and training, build the sensor calibration model. Therefore, this paper based on back propagation (BP) neural network sensor calibration model, the optimization algorithm and the model is improved. The main work includes: firstly, the conventional BP neural network calibration models using BP algorithm based on the analysis, pointed out that the BP algorithm because of the defects in the training theory, correction model is easy to fall into local optimum phase errors, and puts forward the particle swarm optimization (PSO) algorithm and BP algorithm. The optimization algorithm in optimizing the initial weights of the network perspective, give full play to the advantages of global optimization PSO algorithm, combined with the characteristics of BP local optimal algorithm, effective to avoid the calibration model in the process of training into the local minimum, and speed up the convergence correction model training. Then the correction model works and actual gas The monitoring data of the sensor is analyzed from the practical application of the model and the correction of information using the environment point of view, pointed out that the conventional BP neural network model based on the correction cannot make full use of the change information monitoring the concentration of gas sensors, so that the correction model correction accuracy is limited, and puts forward the integration of long short term memory (LSTM) neural network and improved BP neural network calibration model. The improved model using gas concentration change in time is continuous, the influence of environment on the unknown impurity gas gas sensor is eliminated by LSTM network, and then cascaded BP neural network, realize the construction of the improved model, improve the working performance of calibration model. Finally, from the data validation point of view, combined with the experimental data obtained by simulation modeling, further analysis shows that the optimization algorithm proposed in this paper is compared with the BP algorithm in training model The superiority of the process and the improved correction model have higher correction precision in the practical application environment than the conventional correction model.

【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP212;TP391.44;TN929.5

【參考文獻】

相關(guān)期刊論文 前10條

1 邵婷婷;亓宏濤;雷文禮;;基于BP神經(jīng)網(wǎng)絡(luò)的測斜儀方位角誤差補償研究[J];信息技術(shù);2016年10期

2 朱明晨;趙平;陳偉榮;;基于BP神經(jīng)網(wǎng)絡(luò)的霍普菲爾德模型改進研究[J];測繪工程;2016年09期

3 翁瑩晶;馮慧斌;;基于BP神經(jīng)網(wǎng)絡(luò)的網(wǎng)店銷售預(yù)測模型研究[J];閩江學(xué)院學(xué)報;2016年05期

4 崔寶才;;基于GA改進BP神經(jīng)網(wǎng)絡(luò)網(wǎng)絡(luò)異常檢測方法[J];現(xiàn)代電子技術(shù);2016年03期

5 劉姝敏;劉海龍;;基于LabVIEW實現(xiàn)的BP神經(jīng)網(wǎng)絡(luò)[J];電子技術(shù);2015年01期

6 張雙巖;余雋;唐禎安;魏廣芬;陳毅;申寧;;二元混合氣體識別中傳感器陣列優(yōu)化方法研究[J];儀表技術(shù)與傳感器;2010年07期

7 張愉;齊美星;童敏明;;基于RBF神經(jīng)網(wǎng)絡(luò)的單一催化傳感器檢測混合氣體研究[J];傳感技術(shù)學(xué)報;2009年05期

8 楊盛春;賈林祥;;神經(jīng)網(wǎng)絡(luò)內(nèi)監(jiān)督學(xué)習(xí)和無監(jiān)督學(xué)習(xí)之比較[J];徐州建筑職業(yè)技術(shù)學(xué)院學(xué)報;2006年03期

9 太惠玲;謝光忠;蔣亞東;;基于氣體傳感器陣列的混合氣體定量分析[J];儀器儀表學(xué)報;2006年07期

10 姚智慧;徐保港;郝博;;基于氣體傳感器陣列的電子鼻對混合氣體定量識別的研究[J];電子工業(yè)專用設(shè)備;2006年06期

相關(guān)會議論文 前1條

1 蔣學(xué)悟;劉海韜;魏海明;;電化學(xué)氣體傳感器測量干擾排除的探討[A];中國土木工程學(xué)會城市燃氣分會應(yīng)用專業(yè)委員會2010年年會論文集[C];2010年

相關(guān)碩士學(xué)位論文 前6條

1 顧子玲;面向工業(yè)園區(qū)的污染氣體排放監(jiān)測系統(tǒng)設(shè)計[D];北京交通大學(xué);2016年

2 蔡貝貝;氣體傳感器陣列模式識別算法及硬件實現(xiàn)[D];電子科技大學(xué);2013年

3 呂先濤;基于BP網(wǎng)絡(luò)混合氣體濃度識別的研究[D];武漢理工大學(xué);2010年

4 王坤;盲信號分離技術(shù)在氣體濃度分析中的應(yīng)用研究[D];沈陽理工大學(xué);2009年

5 郭萌;電化學(xué)傳感器的研究[D];天津大學(xué);2005年

6 王瑋;基于氣體傳感器陣列的混合氣體檢測系統(tǒng)[D];西北工業(yè)大學(xué);2002年

，

本文編號：1748944