期刊文献+

基于红外阵列传感器的数据融合技术 被引量:2

The Data Fusion Technology Based on the Infrared Array Sensor
下载PDF
导出
摘要 电站锅炉空气预热器存在二次燃烧现象,现有检测技术还存在一些问题。针对这些问题,本设计采用基于红外阵列的多个红外传感器同时检测空气预热器温度,根据空气预热器的温度分布规律以及运用数据融合技术来判定火灾。首先根据多传感器的检测值,自动建立空气预热器内部的温度分布规律模型,并在运行过程中对温度分布模型进行自我调节与修正。最后运用D-S证据理论进行判警,检测出火灾发生部位及火灾程度。其克服了阈值判断容易出现漏报警和误报警的缺点,克服了移动式检测装置不断往返运动容易卡死的问题。不仅如此,本系统还具有自诊断和自适应能力,当某个传感器出现故障时,会发出相应的报警信号,并根据故障调整具体融合方法。 Power plant boiler air preheater exists secondary burning phenomenon,but the existing detection technology is still not without some problems.To solve these problems,the design uses a number of infrared sensors to construct an infrared sensor array and detect an air pre-heater ' s temperature at the same time.In accordance with its temperature distribution fire points can be determined by using the data fusion theory.Firstly,according to the detecting values of the multi-sensor the system was enabled to automatically find the rules of the temperature distributions of the air pre-heater.And it can automatically adjust the temperature distribution model in the testing process.Finally,the D-S evidence theory was used to detect the fire location and extent.With fast response and high reliability,the threshold alarm ' s shortcomings and mobile device ' s problem had been overcome.The system also has self-diagnosis and self-adaptive capabilities.When a sensor fails,it will give the corresponding alarm signal,and adjust the specific fusion method according to the failure.
出处 《传感技术学报》 CAS CSCD 北大核心 2011年第4期548-553,共6页 Chinese Journal of Sensors and Actuators
关键词 空气预热器 D-S证据理论 数据融合. Air preheater D-S evidential theory Data fusion
  • 相关文献

参考文献11

二级参考文献29

  • 1Jiang Lin Qu Liangsheng Chen Tao Institute of Diagnostics & Cybernetics Xi′an Jiaotong University, Xi′an, 710049, P.R.China.The Influence of Training Quality on the Performance of Neural Networks[J].International Journal of Plant Engineering and Management,1996,1(1):29-37. 被引量:1
  • 2罗发龙,李衍达.神经网络信号处理研究评述[J].电子瞭望,1993(9):5-10. 被引量:13
  • 3陈仁文.小波变换在输油管道漏油实时监测中的应用[J].仪器仪表学报,2005,26(3):242-245. 被引量:24
  • 4Chilukuri M V, Dash P K. Multiresolution S-transform-based fuzzy recognition system for power quality events[J]. IEEE Tran. On Power Delivery, 2004, 19(1): 323-330.
  • 5Abde-Gali T K, El-Saadany E F, Youssef A M et al. On-line disturbance recognition utilizing vector quantization based fast match[C]. Pro. IEEE Power Eng. Soc. Summer Meeting, Chicago,IL, July21-25, 2002.
  • 6Youssef A M, Abde-Gali T K, El-Saadany E F et al. Disturbance classification utilizing dynamic time warping classifier[J]. IEEE Trans.on Power Delivery, 2004, 19(1): 272-278.
  • 7ChungJ, Powers E J, GradyWMetal. Power disturbance classifier utilizing a ruled-based method and wavelet packet-based hidden markov model[J]. IEEE Trans. on Power Delivery, 2002, 17(1):738-743.
  • 8Santoso S, Powers E J, Grady W M. Power quality disturbance identification using wavelet transforms and arfficial neural networks[C]. Proceedings of IEEE ICHQP Ⅶ Lasvegas: 1996,615-618.
  • 9Chung J, Powers E J, Grady W M et al. Power disturbance classifier using a rule based method and wavelet packet-based hidden Markov model[J]. IEEETran. Power Delivery, 2002, 17(1): 233-241.
  • 10Kezunovic M, Liao Y. A novel software implementation concept for power quality study[J]. IEEE Tran. on Power Delivery, 2002, 17(2):998-1001.

共引文献140

同被引文献13

引证文献2

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部