基于神经网络的矿用通风机测试虚拟仪器性能研究
|
摘要
矿用通风机测试虚拟仪器系统的研究对保障矿山安全生产,实现固定设备性能综合测试,降低测试成本,简化测试工作具有重要的意义。本论文在实现了矿用通风机测试虚拟仪器软件和硬件的基础上,主要对矿用通风机测试虚拟仪器进行了静态和动态性能的研究。
在静态特性研究过程中,通过设计的静态特性实验,得到静态实验数据。再根据测试系统静态性能指标的算法,编写了LabVIEW静态特性数据分析程序,将所测试实验数据输入到静态特性数据分析程序中,得到了矿用通风机测试虚拟仪器的静态特性指标,包括灵敏度、非线性度和回程误差,以及精确度。通过实验分析,得出了该矿用通风机测试虚拟仪器拥有良好的静态特性。
在动态特性研究过程中,使用神经网络算法对矿用通风机测试虚拟仪器进行了数学模型的研究。首先通过实验的方法分析出该虚拟仪器系统的估计模型。再通过神经网络的自适应线性神经元算法对虚拟仪器系统的估计模型进行了辨识,从而得到了虚拟仪器的数学模型。根据系统的阶跃响应,设计实验验证了本虚拟仪器数学模型的正确性。通过辨识得到的数学模型分析了虚拟仪器的动态特性,包括其稳定性、响应时间和工作频带,并确定了本虚拟仪器的响应时间和工作频带,结果表明了矿用通风机测试虚拟仪器拥有良好的动态特性。本动态研究不仅对虚拟仪器测试系统的设计提供了理论依据,而且使神经网络辨识算法在虚拟仪器测试系统中的应用奠定了理论基础。
最后,对矿用通风机测试虚拟仪器进行了验证,验证了矿用通风机测试虚拟仪器在整个测试系统中应用的正确性。在实验中,通过改变节流挡板的角度来改变通风机运行工况,并记录风机实验数据,绘制出通风机的性能曲线。结果表明了基于虚拟仪器的通风机性能检测系统可以满足测试的要求,从实验和理论上说明该矿用通风机测试虚拟仪器可以用于现场测试。
Researching the mine fan virtual instrument test system is important to ensure mine safety production and to actualize mine fixed equipment synthesis testing, and to decrease the test cost. After finishing the design of virtual instrument system, this paper analyzes the static and dynamic characteristics of the mine fan test virtual instrument also.
In the course of the study to static characteristics, programming the LabVIEW data analysis procedures based on the static performance algorithm of testing system, and designing the static characteristic experiment to gain some static dates, and inputting those experimental data to the LabVIEW data analysis procedures, which may analyze the static characteristic parameters of the mine fan test virtual instrument, including sensitivity, nonlinearity, hysteretic error and accuracy. Through the experimental analysis, the mine fan test virtual instrument has excellent static characteristics.
In the course of the study to dynamic characteristics, using the neural network algorithm studies the mathematical model of the mine fan test virtual instrument. First of all, through the analysis of the experimental method, getting the virtual instrument system estimation model, and identifying the estimation model by neural network algorithm of the adaptive linear neuron, which can research the mathematical model of virtual instrument. Based on the step response method of system, designing experiment can verify that the virtual instrument system mathematical model is right. Through the analysis to mathematical model, it can obtain the dynamic characteristics of virtual instrument including the system stability, response time and bandwidth, and determine the virtual instrument system response time and bandwidth, and those results show that the mine fan test virtual instrument has good dynamic characteristics. Above all, the study of dynamic characteristics of the virtual instrument not only provides a theoretical basis for the design of test system, but also establishes a theoretical basis to the application of neural network algorithm in virtual instrument test system.
Finally, the paper had made some experiments to test the correctness of the mine fan test virtual instrument application to the entire test system. In the experiment, changing the angle of throttle baffle may change the running conditions of mine fan, and recording experimental data, and drawing out the fan performance curve. The results show that the fan test system based on the virtual instrument can meet the requirements of the test, and show that the mine fan test virtual instrument can be used for field testing.
在静态特性研究过程中,通过设计的静态特性实验,得到静态实验数据。再根据测试系统静态性能指标的算法,编写了LabVIEW静态特性数据分析程序,将所测试实验数据输入到静态特性数据分析程序中,得到了矿用通风机测试虚拟仪器的静态特性指标,包括灵敏度、非线性度和回程误差,以及精确度。通过实验分析,得出了该矿用通风机测试虚拟仪器拥有良好的静态特性。
在动态特性研究过程中,使用神经网络算法对矿用通风机测试虚拟仪器进行了数学模型的研究。首先通过实验的方法分析出该虚拟仪器系统的估计模型。再通过神经网络的自适应线性神经元算法对虚拟仪器系统的估计模型进行了辨识,从而得到了虚拟仪器的数学模型。根据系统的阶跃响应,设计实验验证了本虚拟仪器数学模型的正确性。通过辨识得到的数学模型分析了虚拟仪器的动态特性,包括其稳定性、响应时间和工作频带,并确定了本虚拟仪器的响应时间和工作频带,结果表明了矿用通风机测试虚拟仪器拥有良好的动态特性。本动态研究不仅对虚拟仪器测试系统的设计提供了理论依据,而且使神经网络辨识算法在虚拟仪器测试系统中的应用奠定了理论基础。
最后,对矿用通风机测试虚拟仪器进行了验证,验证了矿用通风机测试虚拟仪器在整个测试系统中应用的正确性。在实验中,通过改变节流挡板的角度来改变通风机运行工况,并记录风机实验数据,绘制出通风机的性能曲线。结果表明了基于虚拟仪器的通风机性能检测系统可以满足测试的要求,从实验和理论上说明该矿用通风机测试虚拟仪器可以用于现场测试。
Researching the mine fan virtual instrument test system is important to ensure mine safety production and to actualize mine fixed equipment synthesis testing, and to decrease the test cost. After finishing the design of virtual instrument system, this paper analyzes the static and dynamic characteristics of the mine fan test virtual instrument also.
In the course of the study to static characteristics, programming the LabVIEW data analysis procedures based on the static performance algorithm of testing system, and designing the static characteristic experiment to gain some static dates, and inputting those experimental data to the LabVIEW data analysis procedures, which may analyze the static characteristic parameters of the mine fan test virtual instrument, including sensitivity, nonlinearity, hysteretic error and accuracy. Through the experimental analysis, the mine fan test virtual instrument has excellent static characteristics.
In the course of the study to dynamic characteristics, using the neural network algorithm studies the mathematical model of the mine fan test virtual instrument. First of all, through the analysis of the experimental method, getting the virtual instrument system estimation model, and identifying the estimation model by neural network algorithm of the adaptive linear neuron, which can research the mathematical model of virtual instrument. Based on the step response method of system, designing experiment can verify that the virtual instrument system mathematical model is right. Through the analysis to mathematical model, it can obtain the dynamic characteristics of virtual instrument including the system stability, response time and bandwidth, and determine the virtual instrument system response time and bandwidth, and those results show that the mine fan test virtual instrument has good dynamic characteristics. Above all, the study of dynamic characteristics of the virtual instrument not only provides a theoretical basis for the design of test system, but also establishes a theoretical basis to the application of neural network algorithm in virtual instrument test system.
Finally, the paper had made some experiments to test the correctness of the mine fan test virtual instrument application to the entire test system. In the experiment, changing the angle of throttle baffle may change the running conditions of mine fan, and recording experimental data, and drawing out the fan performance curve. The results show that the fan test system based on the virtual instrument can meet the requirements of the test, and show that the mine fan test virtual instrument can be used for field testing.
引文
[1]廖丽,李翠华.我国矿井主通风机设备的现状及发展.煤炭工程,2004年第9期
[2]陈文礼.矿用BDK系列双级对旋轴流式通风机性能测定与评价.能源与环境,2005,86-88
[3]穆大耀,谢瑞靖,赵梓成.风机性能参数微机测试系统的设计研究.云南冶金,1995年第1期
[4]严俭祝,汤中於.风机性能测定计算机数据采集系统的研制.煤炭科学技术,2002年9月
[5]胡生清,幸国全.未来的仪器仪表—虚拟仪器.国外电子测量技术,2000(4)
[6]秦树人.虚拟仪器及其最新发展.振动、测试与诊断,2000(20)
[7] McGarry, Nicole (National Instruments), The move to virtual instrumentation, Electronic Products (Garden City, New York), v46, n2, July, 2003:33-34
[8] Cristaldi, Loredana, Ferrero, Alessandro, Piuri, Vincenzo Programmable instruments, virtual instruments, and distributed measurement systems: What is really useful, innovative and technically sound, IEEE Instrumentation and Measurement Magazine, v2, n3, Sep, 1999:20-27
[9] Van Halen, Paul , Redefining the virtual instrument: merging simulation and test & measurement, Midwest Symposium on Circuits and Systems, v1, 1995:322-325
[10] Campbell, H.S; Gupta, N.K. Measurements using virtual instruments, Electron, v20, n5, May, 2003:14-18
[11]戚新波,范峥,陈学广.基于虚拟仪器技术的风机性能测试系统.河南科技学院学报(自然科学版), 2005年第33卷第1期
[12]张福旺,杨江锋.HGFY22风机测定仪的研制与性能测试.中州煤炭,2001
[13]胡维颉.多功能风机全性能自动测试装置通过国家机械工业部鉴定.地下工程与隧道,1997年第2期
[14]陈维健,傅运刚等主编.矿山大型机电设备测试技术手册.1998年8月
[15]廖俊,罗晟,仲石廉,黄武雄.计算机辅助风机试验系统.流体机械,1999年8月
[16]宋玲,张山鹰,裴新民等.离心机性能测试系统的设计.新疆农机化,2004年第6期
[17]范云霄,刘桦.测试技术与信号处理.中国计量出版社,2002(4)第一版
[18]刘君华等编著.基于LabVIEW的虚拟仪器设计.北京:电子工业出版社,2003
[19]侯国屏,王坤,叶齐鑫编著. LabVIEW7.1编程与虚拟仪器设计.北京:清华大学出版社,2005.2
[20] (美)康威(Conway, J.)(美)瓦特(Watts, S).软件工程方法在LabVIEW中的应用.北京:清华大学出版社,2006.4
[21]杨乐平等编著.LabVIEW高级程序设计.北京:清华大学出版社,2003
[22]王平,怀其才.谈精密度、准确度和精确度.济南教育学院学报,2002,49-50
[23]邓善熙.测试信号分析与处理.中国计量出版社,2003.8
[24]马戎,周王民,陈明.气体传感器的建模及特性分析.测控技术,2004年第23卷第9期
[25]解同信.最小二乘法求作拟合直线.北京工业职业技术学院学报,2004年第5卷第3期
[26]李言俊,张科.系统辨识理论及应用.国防工业出版社,2006.7
[27]侯媛彬,汪梅,王立琦.系统辨识及其MATLAB仿真.科学出版社,2004.2
[28]黄睿.基于神经网络的飞行器系统辨识方法研究:[学位论文].西安:西北工业大学,2002
[29]侯媛彬,杜京义,汪梅.神经网络.西安电子科技大学出版社,2007.8
[30] Hang liqun. Artifical neural network theory design and application.Publishing company of chemistry industry, Bejing China,2002:120-127
[31] Jagannathan S. Adaptive critic neural network based controller for nonlinear systems. Proc of IEEE Int Symposium on Intelligent Control. Vancouver, 2002 :303-308
[32] Prokhorov D V, Wunsch D C. Adaptive critic designs. IEEE Trans on Neural Networks, 2002,8 (5) :997-1007
[33]廖晓峰,李传东.神经网络研究的发展趋势.国际学术动态,2006,5
[34] HUYBERECHTSG. Simultaneous quantification of carbon monoxide and methane in humid air using a sensor array and an artificial neural network. Sensor and Actuatoes,1997,B45 :123-130
[35] Sun K.T,Lee S.J,Wu P.Y. Neural network approaches to fractal image compression and decompression. Neurocomputing, 2001,41(1-4):91-107
[36]俞阿龙,黄惟.基于人工神经网络的数字式涡流传感器建模方法.工业仪表与自动化装置,2004.06
[37]蔡兵.基于RBF神经网络的湿度传感器建模方法.仪表技术与传感器,2005.10
[38]徐丽娜.神经网络控制.电子工业出版社,2003
[39]王秀峰,卢桂章.系统建模与辨识.电子工业出版社,2004.8
[40]王志贤.最优状态估计与系统辨识.西北工业大学出版社,2004.6
[41]张成乾,张国强.系统辨识与参数估计.机械工业出版社,1986.11
[42]朱骥北.机械控制工程基础.机械工业出版社,2004.1
[43] AQ 1011-2005煤矿在用通风机系统安全检测检验规范.
[44]李曼,杨富强,冯华光.矿用通风机性能测试分析虚拟仪器的研发.风机技术,2008.4:43-46
[45]中华人民共和国国家标准.GB10178-2006T工业通风机现场性能试验
[46]黄忠霖.自动控制原理的MATLAB实现.国防工业出版社,2007
[2]陈文礼.矿用BDK系列双级对旋轴流式通风机性能测定与评价.能源与环境,2005,86-88
[3]穆大耀,谢瑞靖,赵梓成.风机性能参数微机测试系统的设计研究.云南冶金,1995年第1期
[4]严俭祝,汤中於.风机性能测定计算机数据采集系统的研制.煤炭科学技术,2002年9月
[5]胡生清,幸国全.未来的仪器仪表—虚拟仪器.国外电子测量技术,2000(4)
[6]秦树人.虚拟仪器及其最新发展.振动、测试与诊断,2000(20)
[7] McGarry, Nicole (National Instruments), The move to virtual instrumentation, Electronic Products (Garden City, New York), v46, n2, July, 2003:33-34
[8] Cristaldi, Loredana, Ferrero, Alessandro, Piuri, Vincenzo Programmable instruments, virtual instruments, and distributed measurement systems: What is really useful, innovative and technically sound, IEEE Instrumentation and Measurement Magazine, v2, n3, Sep, 1999:20-27
[9] Van Halen, Paul , Redefining the virtual instrument: merging simulation and test & measurement, Midwest Symposium on Circuits and Systems, v1, 1995:322-325
[10] Campbell, H.S; Gupta, N.K. Measurements using virtual instruments, Electron, v20, n5, May, 2003:14-18
[11]戚新波,范峥,陈学广.基于虚拟仪器技术的风机性能测试系统.河南科技学院学报(自然科学版), 2005年第33卷第1期
[12]张福旺,杨江锋.HGFY22风机测定仪的研制与性能测试.中州煤炭,2001
[13]胡维颉.多功能风机全性能自动测试装置通过国家机械工业部鉴定.地下工程与隧道,1997年第2期
[14]陈维健,傅运刚等主编.矿山大型机电设备测试技术手册.1998年8月
[15]廖俊,罗晟,仲石廉,黄武雄.计算机辅助风机试验系统.流体机械,1999年8月
[16]宋玲,张山鹰,裴新民等.离心机性能测试系统的设计.新疆农机化,2004年第6期
[17]范云霄,刘桦.测试技术与信号处理.中国计量出版社,2002(4)第一版
[18]刘君华等编著.基于LabVIEW的虚拟仪器设计.北京:电子工业出版社,2003
[19]侯国屏,王坤,叶齐鑫编著. LabVIEW7.1编程与虚拟仪器设计.北京:清华大学出版社,2005.2
[20] (美)康威(Conway, J.)(美)瓦特(Watts, S).软件工程方法在LabVIEW中的应用.北京:清华大学出版社,2006.4
[21]杨乐平等编著.LabVIEW高级程序设计.北京:清华大学出版社,2003
[22]王平,怀其才.谈精密度、准确度和精确度.济南教育学院学报,2002,49-50
[23]邓善熙.测试信号分析与处理.中国计量出版社,2003.8
[24]马戎,周王民,陈明.气体传感器的建模及特性分析.测控技术,2004年第23卷第9期
[25]解同信.最小二乘法求作拟合直线.北京工业职业技术学院学报,2004年第5卷第3期
[26]李言俊,张科.系统辨识理论及应用.国防工业出版社,2006.7
[27]侯媛彬,汪梅,王立琦.系统辨识及其MATLAB仿真.科学出版社,2004.2
[28]黄睿.基于神经网络的飞行器系统辨识方法研究:[学位论文].西安:西北工业大学,2002
[29]侯媛彬,杜京义,汪梅.神经网络.西安电子科技大学出版社,2007.8
[30] Hang liqun. Artifical neural network theory design and application.Publishing company of chemistry industry, Bejing China,2002:120-127
[31] Jagannathan S. Adaptive critic neural network based controller for nonlinear systems. Proc of IEEE Int Symposium on Intelligent Control. Vancouver, 2002 :303-308
[32] Prokhorov D V, Wunsch D C. Adaptive critic designs. IEEE Trans on Neural Networks, 2002,8 (5) :997-1007
[33]廖晓峰,李传东.神经网络研究的发展趋势.国际学术动态,2006,5
[34] HUYBERECHTSG. Simultaneous quantification of carbon monoxide and methane in humid air using a sensor array and an artificial neural network. Sensor and Actuatoes,1997,B45 :123-130
[35] Sun K.T,Lee S.J,Wu P.Y. Neural network approaches to fractal image compression and decompression. Neurocomputing, 2001,41(1-4):91-107
[36]俞阿龙,黄惟.基于人工神经网络的数字式涡流传感器建模方法.工业仪表与自动化装置,2004.06
[37]蔡兵.基于RBF神经网络的湿度传感器建模方法.仪表技术与传感器,2005.10
[38]徐丽娜.神经网络控制.电子工业出版社,2003
[39]王秀峰,卢桂章.系统建模与辨识.电子工业出版社,2004.8
[40]王志贤.最优状态估计与系统辨识.西北工业大学出版社,2004.6
[41]张成乾,张国强.系统辨识与参数估计.机械工业出版社,1986.11
[42]朱骥北.机械控制工程基础.机械工业出版社,2004.1
[43] AQ 1011-2005煤矿在用通风机系统安全检测检验规范.
[44]李曼,杨富强,冯华光.矿用通风机性能测试分析虚拟仪器的研发.风机技术,2008.4:43-46
[45]中华人民共和国国家标准.GB10178-2006T工业通风机现场性能试验
[46]黄忠霖.自动控制原理的MATLAB实现.国防工业出版社,2007
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |