面向真空玻璃真空度预测的智能检测系统

发布时间：2018-05-01 14:06

本文选题：真空玻璃 + 真空度　；参考：《海南大学》2017年硕士论文

【摘要】：作为新一代节能环保材料,真空玻璃由于具有比传统玻璃更好的性能而被广泛应用,具体体现在保温、防结露水、防结霜、隔音等方面的优良性能。真空度这一性能指标可用来表征真空玻璃的质量,当这一值越高时,表明其性能越好,反之性能越差。然而,多年以来对真空玻璃性能检测的研究表明,其性能表征参数的实际测量很难。并且随着时间积累,真空度这一指标也不断衰减,因此使得服役中真空玻璃真空度的测量成为高难度课题。针对目前真空玻璃性能检测的各种方式方法中,大都是采用的物理原理测量真空玻璃的相关参数,均未采用过基于智能算法建立各种可能因素与真空玻璃性能表征参数之间的智能模型,本文结合真空玻璃的传热过程,设计了面向真空度这一性能指标的智能检测系统。该智能检测系统主要包括无线温度检测、智能算法模型以及上位机管理软件等三部分。基于STM32F103微控制器、MLX90614红外测温模块以及nRF24L01无线射频模块,本文建立了一套无线温度检测系统。利用该无线测温系统测取实验中的温度数据,然后采用USB接口技术将获取到的温度数据传输到计算机端进行相关处理。设计实验测取温度,以恒定温度加热真空玻璃的一侧(热源侧或热板),在一段时间内分组测取真空玻璃另一侧(非热源侧或冷板)的温度数据以及各时段的室温数据。然后以MATLAB软件为平台,采用BP神经网络算法建立智能模型,以此来预测真空玻璃的真空度,预测结果较为理想。此外,以Visual Studio 2015为平台,使用C#语言、.NET Framework设计了基于WPF的上位机管理软件,选用SQL Server数据库存储数据,运用MATLAB的扩展功能MATLAB Builder for.NET将基于BP神经网络算法建立的智能模型封装打包成类的形式以便.NET上位机应用程序使用。
[Abstract]:As a new generation of energy saving and environmental protection materials, vacuum glass has been widely used because of its better performance than traditional glass. The vacuum degree can be used to characterize the quality of vacuum glass. The higher the vacuum degree is, the better the performance is and the worse the performance is. However, many years of research on the performance of vacuum glass shows that it is difficult to measure the properties of vacuum glass. With the accumulation of time, the index of vacuum degree is decaying, so it is difficult to measure the vacuum degree of vacuum glass in service. In view of the various methods of testing vacuum glass properties, most of them are based on the physical principles used to measure the relevant parameters of vacuum glass. The intelligent model between various possible factors and the performance parameters of vacuum glass has not been established based on intelligent algorithm. In this paper, an intelligent testing system for vacuum degree is designed based on the heat transfer process of vacuum glass. The intelligent detection system consists of three parts: wireless temperature detection, intelligent algorithm model and host computer management software. Based on STM32F103 microcontroller MLX90614 infrared temperature measurement module and nRF24L01 radio frequency module, a wireless temperature detection system is established in this paper. The temperature data in the experiment are obtained by using the wireless temperature measurement system, and then the temperature data obtained is transmitted to the computer for related processing by using USB interface technology. The temperature of one side of the vacuum glass (heat source side or hot plate) is heated at a constant temperature. The temperature data of the other side of the vacuum glass (non-heat source side or cold plate) and the room temperature data of each period of time are measured in groups within a period of time. Then the intelligent model is established by using BP neural network algorithm on the platform of MATLAB software to predict the vacuum degree of vacuum glass and the prediction result is ideal. In addition, based on Visual Studio 2015 and C # language. Net Framework, the upper computer management software based on WPF is designed. SQL Server database is used to store data. Using the extended function of MATLAB, MATLAB Builder for.NET, the intelligent model based on BP neural network algorithm is encapsulated and packaged into classes for the use of. Net PC applications.
【学位授予单位】：海南大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TQ171.12;TP274

【相似文献】