基于软测量的真空玻璃传热过程智能建模研究
发布时间：2021-12-21 20:19
表征真空玻璃热性能的最重要参数-传热系数很难在线测量,因为它会随着时间的推移而增加,从而降低隔热性能。确定真空的热传递需要详细了解它们不同元素的热特性,这一领域存在一系列标准和指南。总体的热性能既可以通过详细的二维数值方法确定,也可以通过符合欧洲或国际标准的测量来确定。首先,我们研究基于真空玻璃传热机理的软测量智能建模方法,以获取真空玻璃性能数据。该方法保证了智能建模的可行性,为基于软测量的智能建模预测真空玻璃隔热性能参数提供了理论依据。研究并开发了一种有效的方法来模拟通过真空玻璃的传热。基于先进的数值模拟技术,利用计算流体动力学软件对传热过程进行了分析,并将仿真结果用于指导和分析非稳态测试方法。这种方法保证了加热板的中心进行一维传热,非受热面中心的温度测量具有实际意义,对于研究智能化保温性能建模和预测是必要的。其次,我们应用神经网络方法对真空玻璃的传热系数进行了预测。基于MATLAB软件,建立了神经网络智能模型,并对传统的BP神经网络进行了优化。采用遗传算法对自变量进行降维。然后,利用思维进化计算算法对初始权值和阈值进行优化。利用优化后的BP神经网络智能模型对真空玻璃隔热层传热系数进...
【文章来源】：海南大学海南省 211工程院校
【文章页数】：183 页
【学位级别】：博士
【文章目录】：
摘要
Abstract
Nomenclature
Chapter 1 Introduction general
1.1 Introduction
1.2 Research Background
1.3 Research heat transfer coefficients of VG and development trends in China and abroad
1.3.1 Study performance prediction of vacuum glass insulation at Home and abroad
1.3.2 Main content of research of the heat transfer coefficients of vacuum glass insulation
1.4 Conclusion
Chapter 2 Mechanism of Vacuum Glass Heat Transfer by Soft Sensor Intelligent Modelling
2.1 Introduction
2.2 Data preprocessing
2.2.1 Implementation of a model of Soft Sensor intelligent modelling
2.2.2 Online correction of the smart sensor model intelligent modeling
2.2.3 Modeling methods
2.3 Selection of historical data
2.3.1 Pretreatment and transformation of data
2.3.2 Cleaning and reduction of data
2.4 Reduction of dimensionality
2.5 Model selection,training and validation of Prediction coefficient heat transfer VG
2.5.1 Model training soft sensor intelligent for heat transfer coefficient prediction
2.5.2 Validation of the model
2.6 Flexible sensor applications
2.6.1 Data for flexible sensor modeling
2.6.2 Modeling approaches
2.7 White box templates
2.8 Mathematical modeling equation white boxes on heat transfer coefficient vacuum glass
2.8.1 Vacuum glass heat transfer principle
2.8.2 Main factors affecting insulation performance parameters
2.8.3 Principles of Soft Sensor Intelligent Modeling Technology
2.8.4 Auxiliary variable selection
2.9 Gray Box Controller Model
2.9.1 Data-Driven Modeling Soft Sensor Intelligent Modeling
2.10 Black box model
2.11 Feasibility Analysis of the SS Intelligent Modeling of Vacuum Glass
2.12 Summary of this chapter
Chapter 3 Computational fluid-dynamics-based simulation of heat transfer through vacuum glass
3.1 Introduction
3.2 Application of vacuum glass
3.3 Heat transfer coefficient of vacuum glass
3.4 Research significance,main content,and innovation points
3.5 Method of heat transfer in vacuum glass
3.6 CFD-based vacuum glass heat transfer simulation
3.7 Discussion
3.7.1 Steady heat transfer
3.7.2 Unsteady heat transfer
3.8.Grid-independent modelling of heat transfer
3.8.1 Mathematical model
3.8.2 Numerical methods
3.9.Vacuum glass thermal property parameters non-steady-state test principle
3.9.1 Unsteady measuring device
3.9.2 Analysis of factors affecting the accuracy of non-steady-state measuring devices
3.9.3 Selection and design of hardware components for temperature measurement system
3.9.4 System software program
3.9.5 Physical system
3.10.Conclusion
Chapter 4 Intelligent modelling to predict heat transfer coefficient of vacuum glass insulation based on thinking evolutionary neural network
4.1 Introduction
4.2 Thermal formulation analytical modelling approach
4.3 Artificial NN(ANN)structure and methodology
4.4 BPNN model
4.4.1 BP algorithm
4.4.2 BPNN algorithm
4.4.3 Learning process of BPNN algorithms
4.5 Prediction model of Vacuum Glass insulation performance based on BPNN
4.5.1 Variable dimension reduction
4.5.2 Optimisation of initial weights and thresholds
4.5.3 Simulation results
4.5.4 Measurements and error analysis
4.6 Conclusions
Chapter 5 Performance Monitoring of Vacuum Glazing Based on LSSVM
5.1.Introduction and motivation
5.2 PCA-RBFNN and Establishing an RBF Neural Network Model
5.2.1 RBF Neural Network Design
5.2.2 Analysis of simulation results
5.2.3 Comparison of PCA and Non-PCA Neural Network Models
5.3 Vector machine supports least squares
5.3.1 Prediction modeling Based on LSSVM
5.3.2 Selection of modeling variables
5.3.3 Model establishment
5.3.4 Selecting the parameters of the LSSVM model
5.3.5 Comparison of modeling methods
5.4 Conclusion
Chapter 6 Predicting the lifetime of vacuum glass based on fuzzy
6.1 Introduction
6.2 Fuzzy Sets,Numbers and Operations
6.3 Determination of fuzzy regression parameter
6.3.1 Fuzzy linear regression
6.3.2 Direct estimation of the parameters
6.3.3 Fuzzy failure probabilities
6.3.4 Fuzzy degradation analysis
6.3.5 Parameter Estimation,Two-Stage Least-Squares
6.3.6 Maximum Likelihood
6.3.7 Bayesian Approach
6.3.8 Estimation of and Prediction from Failure Time Distributions
6.4 Predicting the lifetime service of vacuum glass based on fuzzy
6.4.1 Vacuum glass degradation analysis
6.4.2 Detecting Degraded Data
6.4.3 Application Fuzzy degradation analysis
6.5 Fuzzy set theory to predict the probability of lifetime Vacuum Glass
6.5.1 Failure Time Distribution
Chapter 7 Conclusions general
7.1 Conclusions
7.2 Future prospects
Reference
Acknowledgements
Research achievements during the Ph D
致谢
【参考文献】：
期刊论文
[1]Adoption of wide-bandgap microcrystalline silicon oxide and dual buffers for semitransparent solar cells in building-integrated photovoltaic window system[J]. Johwa Yang,Hyunjin Jo,Soo-Won Choi,Dong-Won Kang,Jung-Dae Kwon. Journal of Materials Science & Technology. 2019(08)
[2]基于模糊信息粒化和LSSVM真空玻璃保温性能预测研究[J]. 张亮,王磊,王元麒,李益红,谭毓银,宋浩. 广西大学学报(自然科学版). 2017(06)
[3]基于思维进化优化灰色神经网络在真空玻璃需求中的研究[J]. 杜萍,王磊,王元麒. 真空. 2016(05)
[4]基于多退化量的动量轮剩余寿命预测方法[J]. 刘胜南,陆宁云,程月华,姜斌,邢琰. 南京航空航天大学学报. 2015(03)
[5]基于LSSVM的真空玻璃传热过程建模[J]. 王元麒,王磊,李桂香. 真空. 2015(02)
[6]基于局部PLS的多输出过程自适应软测量建模方法（英文）[J]. 邵伟明,田学民,王平. Chinese Journal of Chemical Engineering. 2014(07)
[7]真空玻璃技术与应用分析[J]. 王元麒,王磊,李继定. 真空科学与技术学报. 2012(12)
[8]真空玻璃真空度在线检测技术与应用[J]. 刘小根,包亦望,宋一乐,庞世红,邱岩. 郑州大学学报(工学版). 2009(01)
[9]Matlab遗传算法优化工具箱（GAOT）的研究与应用[J]. 周正武,丁同梅,田毅红,王晓峰. 机械研究与应用. 2006(06)
[10]统计模式识别中的维数削减与低损降维[J]. 宋枫溪,高秀梅,刘树海,杨静宇. 计算机学报. 2005(11)
本文编号：3545113
【文章来源】：海南大学海南省 211工程院校
【文章页数】：183 页
【学位级别】：博士
【文章目录】：
摘要
Abstract
Nomenclature
Chapter 1 Introduction general
1.1 Introduction
1.2 Research Background
1.3 Research heat transfer coefficients of VG and development trends in China and abroad
1.3.1 Study performance prediction of vacuum glass insulation at Home and abroad
1.3.2 Main content of research of the heat transfer coefficients of vacuum glass insulation
1.4 Conclusion
Chapter 2 Mechanism of Vacuum Glass Heat Transfer by Soft Sensor Intelligent Modelling
2.1 Introduction
2.2 Data preprocessing
2.2.1 Implementation of a model of Soft Sensor intelligent modelling
2.2.2 Online correction of the smart sensor model intelligent modeling
2.2.3 Modeling methods
2.3 Selection of historical data
2.3.1 Pretreatment and transformation of data
2.3.2 Cleaning and reduction of data
2.4 Reduction of dimensionality
2.5 Model selection,training and validation of Prediction coefficient heat transfer VG
2.5.1 Model training soft sensor intelligent for heat transfer coefficient prediction
2.5.2 Validation of the model
2.6 Flexible sensor applications
2.6.1 Data for flexible sensor modeling
2.6.2 Modeling approaches
2.7 White box templates
2.8 Mathematical modeling equation white boxes on heat transfer coefficient vacuum glass
2.8.1 Vacuum glass heat transfer principle
2.8.2 Main factors affecting insulation performance parameters
2.8.3 Principles of Soft Sensor Intelligent Modeling Technology
2.8.4 Auxiliary variable selection
2.9 Gray Box Controller Model
2.9.1 Data-Driven Modeling Soft Sensor Intelligent Modeling
2.10 Black box model
2.11 Feasibility Analysis of the SS Intelligent Modeling of Vacuum Glass
2.12 Summary of this chapter
Chapter 3 Computational fluid-dynamics-based simulation of heat transfer through vacuum glass
3.1 Introduction
3.2 Application of vacuum glass
3.3 Heat transfer coefficient of vacuum glass
3.4 Research significance,main content,and innovation points
3.5 Method of heat transfer in vacuum glass
3.6 CFD-based vacuum glass heat transfer simulation
3.7 Discussion
3.7.1 Steady heat transfer
3.7.2 Unsteady heat transfer
3.8.Grid-independent modelling of heat transfer
3.8.1 Mathematical model
3.8.2 Numerical methods
3.9.Vacuum glass thermal property parameters non-steady-state test principle
3.9.1 Unsteady measuring device
3.9.2 Analysis of factors affecting the accuracy of non-steady-state measuring devices
3.9.3 Selection and design of hardware components for temperature measurement system
3.9.4 System software program
3.9.5 Physical system
3.10.Conclusion
Chapter 4 Intelligent modelling to predict heat transfer coefficient of vacuum glass insulation based on thinking evolutionary neural network
4.1 Introduction
4.2 Thermal formulation analytical modelling approach
4.3 Artificial NN(ANN)structure and methodology
4.4 BPNN model
4.4.1 BP algorithm
4.4.2 BPNN algorithm
4.4.3 Learning process of BPNN algorithms
4.5 Prediction model of Vacuum Glass insulation performance based on BPNN
4.5.1 Variable dimension reduction
4.5.2 Optimisation of initial weights and thresholds
4.5.3 Simulation results
4.5.4 Measurements and error analysis
4.6 Conclusions
Chapter 5 Performance Monitoring of Vacuum Glazing Based on LSSVM
5.1.Introduction and motivation
5.2 PCA-RBFNN and Establishing an RBF Neural Network Model
5.2.1 RBF Neural Network Design
5.2.2 Analysis of simulation results
5.2.3 Comparison of PCA and Non-PCA Neural Network Models
5.3 Vector machine supports least squares
5.3.1 Prediction modeling Based on LSSVM
5.3.2 Selection of modeling variables
5.3.3 Model establishment
5.3.4 Selecting the parameters of the LSSVM model
5.3.5 Comparison of modeling methods
5.4 Conclusion
Chapter 6 Predicting the lifetime of vacuum glass based on fuzzy
6.1 Introduction
6.2 Fuzzy Sets,Numbers and Operations
6.3 Determination of fuzzy regression parameter
6.3.1 Fuzzy linear regression
6.3.2 Direct estimation of the parameters
6.3.3 Fuzzy failure probabilities
6.3.4 Fuzzy degradation analysis
6.3.5 Parameter Estimation,Two-Stage Least-Squares
6.3.6 Maximum Likelihood
6.3.7 Bayesian Approach
6.3.8 Estimation of and Prediction from Failure Time Distributions
6.4 Predicting the lifetime service of vacuum glass based on fuzzy
6.4.1 Vacuum glass degradation analysis
6.4.2 Detecting Degraded Data
6.4.3 Application Fuzzy degradation analysis
6.5 Fuzzy set theory to predict the probability of lifetime Vacuum Glass
6.5.1 Failure Time Distribution
Chapter 7 Conclusions general
7.1 Conclusions
7.2 Future prospects
Reference
Acknowledgements
Research achievements during the Ph D
致谢
【参考文献】：
期刊论文
[1]Adoption of wide-bandgap microcrystalline silicon oxide and dual buffers for semitransparent solar cells in building-integrated photovoltaic window system[J]. Johwa Yang,Hyunjin Jo,Soo-Won Choi,Dong-Won Kang,Jung-Dae Kwon. Journal of Materials Science & Technology. 2019(08)
[2]基于模糊信息粒化和LSSVM真空玻璃保温性能预测研究[J]. 张亮,王磊,王元麒,李益红,谭毓银,宋浩. 广西大学学报(自然科学版). 2017(06)
[3]基于思维进化优化灰色神经网络在真空玻璃需求中的研究[J]. 杜萍,王磊,王元麒. 真空. 2016(05)
[4]基于多退化量的动量轮剩余寿命预测方法[J]. 刘胜南,陆宁云,程月华,姜斌,邢琰. 南京航空航天大学学报. 2015(03)
[5]基于LSSVM的真空玻璃传热过程建模[J]. 王元麒,王磊,李桂香. 真空. 2015(02)
[6]基于局部PLS的多输出过程自适应软测量建模方法（英文）[J]. 邵伟明,田学民,王平. Chinese Journal of Chemical Engineering. 2014(07)
[7]真空玻璃技术与应用分析[J]. 王元麒,王磊,李继定. 真空科学与技术学报. 2012(12)
[8]真空玻璃真空度在线检测技术与应用[J]. 刘小根,包亦望,宋一乐,庞世红,邱岩. 郑州大学学报(工学版). 2009(01)
[9]Matlab遗传算法优化工具箱（GAOT）的研究与应用[J]. 周正武,丁同梅,田毅红,王晓峰. 机械研究与应用. 2006(06)
[10]统计模式识别中的维数削减与低损降维[J]. 宋枫溪,高秀梅,刘树海,杨静宇. 计算机学报. 2005(11)
本文编号：3545113
本文链接：https://www.wllwen.com/shoufeilunwen/xxkjbs/3545113.html
