基于深度学习的空预器转子红外补光图像积灰状态识别

doi:10.12096/j.2096-4528.pgt.20122

发电技术 ›› 2022, Vol. 43 ›› Issue (3): 510-517.DOI: 10.12096/j.2096-4528.pgt.20122

基于深度学习的空预器转子红外补光图像积灰状态识别

刘君¹, 邓毅², 杨延西², 魏永贵¹, 薛燕辉¹, 史雯雯²

^1.东方电气集团东方锅炉股份有限公司, 四川省成都市 611731
^2.西安理工大学自动化与信息工程学院, 陕西省西安市 710048

收稿日期:2021-07-19 出版日期:2022-06-30 发布日期:2022-07-06
作者简介:刘君(1982)，男，硕士，高级工程师，研究方向为电站锅炉，793323814@qq.com；
邓毅(1975)，男，硕士，讲师，研究方向为复杂系统建模与控制，yideng@xaut.edu.cn；
杨延西(1975)，男，博士，教授，研究方向为复杂系统控制、机器视觉和智能机器人，本文通信作者，yangyanxi@xaut.edu.cn。
基金资助:
国家重点研发计划项目(2018YFB1703000);陕西省现代装备绿色制造协同创新中心研究计划项目(304-210891702)

Ash Accumulation State Identification for Infrared Compensation Images of Air Preheater Rotor Based on Deep Learning Method

Jun LIU¹, Yi DEND², Yanxi YANG², Yonggui WEI¹, Yanhui XUE¹, Wenwen SHI²

^1.Dongfang Electric Corporation Dongfang Boiler Group Co. , Ltd. , Chengdu 611731, Sichuan Province, China
^2.School of Automation and Information Engineering, Xi’an University of Technology, Xi’an 710048, Shaanxi Province, China

Received:2021-07-19 Published:2022-06-30 Online:2022-07-06
Supported by:
National Key Research & Development Program of China(2018YFB1703000);Research Program of Shaanxi Modern Equipment Green Manufacturing Co-innovation Center(304-210891702)

摘要/Abstract

摘要：

目前大型电站锅炉广泛采用的回转式空气预热器(简称“空预器”)普遍存在堵塞现象，严重时甚至会限制锅炉出力。针对这一问题，提出一种基于深度学习的空预器转子红外图像积灰演化分析方法。针对获取的空预器转子红外补光图像样本数据进行预处理，去噪后转化为灰度曲线图像，并采用高斯滤波方法进行图像增强。然后建立灰度共生矩阵(gray level co-occurrence matrix，GLCM)计算相关统计量，提取了角二阶矩(angular second moment，ASM)能量、对比度、熵、逆方差(inverse difference moment，IDM)和自相关性5类纹理特征参数。最后建立了深度信念网络(deep belief network，DBN)模型并进行训练与测试。结果表明：所提方法不但可以实现对空预器转子积灰程度的有效检测和监视，而且能够提前预测空预器堵塞可能性，从而指导运行人员优化运行吹灰系统，保证空预器正常运行。

关键词: 电站锅炉, 回转式空预器, 积灰, 红外补光成像, 纹理特征, 灰度共生矩阵(GLCM), 深度信念网络(DBN)

Abstract:

Ash plugging of the rotary air preheater widely used in large-scale power station often occurs and even reduces the efficiency of the boiler in sever cases. Therefore, a deep learning-based method was proposed for analyzing the evolution of ash accumulation for the infrared compensation images of the air preheater rotor. The sample data of the infrared compensation images of air preheater rotor was preprocessed, and the denoised image was transformed into the gray-level curve image, and the Gaussian filtering method was used for the image enhancement. Then, the gray-level co-occurrence matrix (GLCM) was established, the correlation statistics were calculated, and five different types of texture feature parameters of angular second moment (ASM) energy, contrast, entropy, inverse difference moment (IDM) and correlation were extracted. Finally, a deep belief network (DBN) model was established, which was trained with those preprocessed infrared images. The testing results show that the proposed method can not only detect effectively and monitor the ash accumulation of the air preheater rotor, but also predict the occurrence of ash blockage in advance, so as to guide the operators to optimize the operation of the ash blowing system and ensure the normal operation of the air preheater.

Key words: power station boiler, rotary air preheater, ash accumulation, infrared compensation imaging, texture feature, gray-level co-occurrence matrix (GLCM), deep belief network (DBN)

中图分类号:

TK 223.3⁺4

刘君, 邓毅, 杨延西, 魏永贵, 薛燕辉, 史雯雯. 基于深度学习的空预器转子红外补光图像积灰状态识别[J]. 发电技术, 2022, 43(3): 510-517.

Jun LIU, Yi DEND, Yanxi YANG, Yonggui WEI, Yanhui XUE, Wenwen SHI. Ash Accumulation State Identification for Infrared Compensation Images of Air Preheater Rotor Based on Deep Learning Method[J]. Power Generation Technology, 2022, 43(3): 510-517.

图/表 7

图1 电磁波谱图

Fig. 1 Electromagnetic spectrum

图2 DBN模型

Fig. 2 Model of DBN

图3 DBN模型分析流程图

Fig. 3 Analysis flow chart of DBN

图4 不同积灰状态图像的纹理特征对比

Fig. 4 Comparison of texture features of images in different ash states

图5 不同积灰状态下的转子受热面图像(工况1)

Fig. 5 Images of rotor heating surface under different ash accumulation states (working condition 1)

图6 不同积灰状态下的转子受热面图像(工况2)

Fig. 6 Images of rotor heating surface under different ash accumulation states (working condition 2)

图7 识别分类结果示例

Fig. 7 Examples of identifying classification results

参考文献 21

1	李允超，赵大周，刘博，等．火电厂烟气余热利用现状与展望[J]．发电技术，2019，40(3)：270-275． doi:10.12096/j.2096-4528.pgt.18043
	LI Y C， ZHAO D Z， LIU B，et al ．Status and prospect of waste heat utilization in power plant[J]．Power Generation Technology，2019，40(3)：270-275． doi:10.12096/j.2096-4528.pgt.18043
2	王学栋，姜明超，宋昂．低压省煤器性能评价试验与节能效果的修正计算方法[J]．发电技术，2021，42(2)：280-287． doi:10.12096/j.2096-4528.pgt.19101
	WANG X D， JIANG M C， SONG A ．Performance evaluation test of low-pressure economizer and corrected calculation method of energy saving effect[J]．Power Generation Technology，2021，42(2)：280-287． doi:10.12096/j.2096-4528.pgt.19101
3	洪志刚，张杨，刘永生，等．燃煤电厂烟气非常规污染物检测与协同控制技术研究综述[J]．发电技术，2020，41(5)：517-526． doi:10.12096/j.2096-4528.pgt.19145
	HONG Z G， ZHANG Y， LIU Y S，et al ．Research overview on unconventional pollutant detection and cooperative control technology of flue gas in coal-fired power plant[J]．Power Generation Technology，2020，41(5)：517-526． doi:10.12096/j.2096-4528.pgt.19145
4	章荣顶，沈利．660 MW超超临界机组引风机失速引起锅炉MFT的原因分析及对策[J]．浙江电力，2020，39(10)：98-104． doi:10.19585/j.zjdl.202010017
	ZHANG R D， SHEN L ．Cause analysis and countermeasures of MFT caused by stall of induced draft fan of 660 MW ultra-supercritical units[J]．Zhejiang Electric Power，2020，39(10)：98-104． doi:10.19585/j.zjdl.202010017
5	吴坡，段松涛，张江南，等．数据驱动型实时燃烧优化控制架构及应用[J]．电力工程技术，2021，40(2)：197-204． doi:10.12158/j.2096-3203.2021.02.028
	WU P， DUAN S T， ZHANG J N，et al ．Architecture and application of data-driven on-line combustion optimization control[J]．Electric Power Engineering Technology，2021，40(2)：197-204． doi:10.12158/j.2096-3203.2021.02.028
6	李建伟，王林，王红雨．某超临界锅炉结渣原因分析与对策[J]．热力发电，2019，48(12)：122-128． doi:10.4028/www.scientific.net/amm.713-715.1331
	LI J W， WANG L， WANG H Y ．Cause analysis and countermeasures of slagging in a supercritical boiler[J]．Thermal Power Generation，2019，48(12)：122-128． doi:10.4028/www.scientific.net/amm.713-715.1331
7	柴一占，杨震，段远源．燃煤积灰法向光谱发射率的测量[J]．发电技术，2019，40(4)：323-328． doi:10.12096/j.2096-4528.pgt.19070
	CHAI Y Z， YANG Z， DUAN Y Y ．Coal ash deposit normal spectral emissivity measurement[J]．Power Generation Technology，2019，40(4)：323-328． doi:10.12096/j.2096-4528.pgt.19070
8	邢军，何超，舒忠平．移动式声波吹灰器在660 MW机组锅炉省煤器的应用[J]．华电技术，2019，41(7)：73-76．
	XING J， HE C， SHU Z P ．Application of mobile sonic sootblower in boiler economizer of 660 MW unit[J]．Huadian Technology，2019，41(7)：73-76．
9	张良，刁云鹏，赵树龙，等．电站锅炉低负荷工况下水平烟道积灰治理[J]．锅炉制造，2020(5)：34-36． doi:10.3969/j.issn.1674-1005.2020.05.013
	ZHANG L， DIAO Y P， ZHAO S L，et al ．Treatment of fouling in horizontal flue of power station boiler under low load conditions[J]．Boiler Manufacturing，2020(5)：34-36． doi:10.3969/j.issn.1674-1005.2020.05.013
10	樊泉桂．锅炉原理[M]．北京：中国电力出版社，2008：31-50． doi:10.12783/dtetr/iceea2016/6679
	FAN Q G ．Principles of boiler[M]．Beijing：China Electric Power Press，2008：31-50． doi:10.12783/dtetr/iceea2016/6679
11	张国滨．排烟温度对空气预热器压差影响的试验[J]．华电技术，2016，38(7)：58-69． doi:10.3969/j.issn.1674-1951.2016.07.017
	ZHANG G B ．Test of the influence of exhaust gas temperature on air preheater pressure difference[J]．Huadian Technology，2016，38(7)：58-69． doi:10.3969/j.issn.1674-1951.2016.07.017
12	张广科，杨子海，史小刚．煤粉炉回转式空气预热器堵塞原因分析及解决措施[J]．大氮肥，2017，40(1)：34-35． doi:10.3969/j.issn.1002-5782.2017.01.010
	ZHANG G K， YANG Z H， SHI X G ．Cause analysis and solution of blockage of rotary air preheater of pulverized coal boiler[J]．Big Nitrogen Fertilizer，2017，40(1)：34-35． doi:10.3969/j.issn.1002-5782.2017.01.010
13	BU Y F， WANG L M， CHEN X，et al ．Numerical analysis of ABS deposition and corrosion on a rotary air preheater[J]．Applied Thermal Engineering，2018，131：669-677． doi:10.1016/j.applthermaleng.2017.11.082
14	MARCO L， HARTMUT S， JAAP K ．Ash deposition modeling using a visco-elastic approach[J]．Fuel，2012，102：145-155． doi:10.1016/j.fuel.2012.04.047
15	ARMIN H K， EBRAHIM H ．Three-dimensional simulation of rotary air preheater in steam power plant[J]．Applied Thermal Engineering，2014，73(1)：397-405． doi:10.1016/j.applthermaleng.2014.08.013
16	ROMAN W， MARCO M， NATALIA S M，et al ．On predicting the ash behaviour using computational fluid dynamics[J]．Fuel Processing Technology，2013，105：113-128． doi:10.1016/j.fuproc.2011.09.008
17	阎维平，陈宝康，梁秀俊，等．电站锅炉回转式空气预热器积灰监测模型的研究[J]．动力工程，2002，22(2)：1708-1710． doi:10.3321/j.issn:1000-6761.2002.02.011
	YAN W P， CHEN B K， LIANG X J，et al ．Investigation on ash monitoring model for rotary air heater in utility boiler[J]．Power Engineering，2002，22(2)：1708-1710． doi:10.3321/j.issn:1000-6761.2002.02.011
18	杨祥良，安连锁，孙鑫强，等．基于人工神经网络的电站锅炉积灰实时监测系统[J]．动力工程学报，2010，30(3)：206-209．
	YANG X L， AN L S， SUN X Q，et al ．A real-time monitoring system for fouling of power station boilers based on artificial neural networks[J]．Chinese Journal of Power Engineering，2010，30(3)：206-209．
19	赵勇纲，白杨，陈裕辉，等．基于支持向量机的低温受热面积灰监测研究[J]．热力发电，2018，47(11)：77-81． doi:10.19666/j.rlfd.201801025
	ZHAO Y G， BAI Y， CHEN Y H，et al ．Research on ash monitoring of low temperature heating area based on support vector machine[J]．Thermal Power Generation，2018，47(11)：77-81． doi:10.19666/j.rlfd.201801025
20	周俊波，陈晓文，高海东，等．燃煤电站锅炉受热面灰污监测与智能吹灰控制技术[J]．热力发电，2015，46(11)：11-17．
	ZHOU J B， CHEN X W， GAO H D，et al ．Coal-fired power station boiler heating surface ash pollution monitoring and intelligent soot blowing control technology[J]．Thermal Power Generation，2015，46(11)：11-17．
21	KAROL G， KATARZYNA P ．Diagnostic methods of detecting defects within the material with the use of active infrared the rmovision[J]．Archives of Mechanical Technology and Materials，2017，37(1)：41-44． doi:10.1515/amtm-2017-0006

[1]	梁中荣, 蓝茂蔚, 郑国, 何荣强, 屈可扬, 甘云华. 基于最小二乘支持向量机的电站锅炉高效率低NO _x 的多目标优化研究[J]. 发电技术, 2023, 44(6): 809-816.
[2]	张立峰, 李晶, 王智. 基于主成分分析和深度神经网络的声学层析成像温度分布重建[J]. 发电技术, 2023, 44(3): 399-406.
[3]	柴一占,杨震,段远源. 燃煤积灰法向光谱发射率的测量[J]. 发电技术, 2019, 40(4): 323-328.

基于深度学习的空预器转子红外补光图像积灰状态识别

Ash Accumulation State Identification for Infrared Compensation Images of Air Preheater Rotor Based on Deep Learning Method

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 21

相关文章 3

编辑推荐

Metrics

本文评价