基于投票机制的暖通空调空气处理单元传感器故障诊断

严颖; 蔡骏; 吴奇; 张欣; 杨溢

doi:10.11999/JEIT221506

基于投票机制的暖通空调空气处理单元传感器故障诊断

doi: 10.11999/JEIT221506

严颖^{1, 2},
蔡骏^{1, 2, 3},
吴奇⁴,
张欣⁵,
杨溢^{1, 2, ,}

1.
南京信息工程大学自动化学院南京 210044
2.
南京信息工程大学大气环境与装备技术协同创新中心南京 210044
3.
中国民用航空飞行学院广汉 618307
4.
上海交通大学电子信息与电气工程学院上海 200240
5.
浙江大学电气工程学院杭州 310027

基金项目: 国家自然科学基金(52077105)，江苏省自然科学基金(BK20211285)

详细信息

作者简介:
严颖：男，博士，讲师，研究方向为故障诊断与智能运维、脑电分析等

蔡骏：男，教授，博士生导师，研究方向为电能变换与驱动控制、故障诊断与容错控制等

吴奇：男，教授，博士生导师，研究方向为状态监测、故障诊断等

张欣：男，教授，博士生导师，研究方向为电力电子、电力系统等

杨溢：男，博士，讲师，研究方向为多旋翼无人机容错控制及复杂环境导航、容错控制等

通讯作者:
杨溢　yangyi@nuist.edu.cn

中图分类号: TN911; TP183
计量
- 文章访问数: 503
- HTML全文浏览量: 226
- PDF下载量: 61
- 被引次数: 0
出版历程
- 收稿日期: 2022-12-05
- 修回日期: 2023-02-14
- 网络出版日期: 2023-02-19
- 刊出日期: 2024-01-17

Sensor Fault Diagnosis for Air Handling Unit of Heating Ventilation and Air Conditioning Based on Voting Mechanism

YAN Ying^{1, 2},
CAI Jun^{1, 2, 3},
WU Qi⁴,
ZHANG Xin⁵,
YANG Yi^{1, 2
, ,}

1.
School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China
2.
Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing 210044, China
3.
Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China, Guanghan 618307, China
4.
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
5.
College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China

Funds: The National Natural Science Foundation of China (52077105), The Natural Science Foundation of Jiangsu Province (BK20211285)

摘要

摘要: 现有暖通空调(HVAC)空气处理单元(AHU)的故障诊断研究往往是集中式的。少量的分布式方法大多需要求解大量耗时的优化问题，使得无法及时完成故障诊断。针对以上挑战，该文提出一种基于投票机制的分布式故障诊断方法。在该方法中，建立一个玻尔兹曼机来描述传感器网络，通过传感器之间的相互投票来确定玻尔兹曼机的边权值，基于边权值对玻尔兹曼机的状态也就是传感器的状态进行迭代，从而定位传感器的故障。设计了一种基于欧氏距离的投票策略确定投票值。开发了一种方法，通过在玻尔兹曼机中增加一个额外的节点来重置其权值矩阵，在将玻尔兹曼机对称化的同时，保持原来各传感器之间的投票关系，以保证玻尔兹曼机状态的迭代收敛。该方法不需要求解大量的优化问题，相较于当前的分布式方法计算量小。使用ASHRAE Project RP-1312提供的实际数据对所提方法进行验证。实验结果表明所提方法可以精确且高效地诊断出空气处理单元传感器的偏差故障和漂移故障。
- 故障诊断 /
- 投票机制 /
- 分布式 /
- 传感器 /
- 玻尔兹曼机
Abstract: Existing fault diagnosis methods developed for Air Handling Unit (AHU) of Heating Ventilation and Air Conditioning (HVAC) tend to be centralized. The few distributed methods usually require solving a large number of time-consuming optimization problems, making it impossible to complete fault diagnosis in a timely manner. In response to the above challenges, a distributed fault diagnosis method based on a novel voting mechanism is proposed. In this method, a novel voting mechanism is proposed to establish a Boltzmann machine to describe the sensor network, determine the edge weights of the Boltzmann machine through mutual voting among sensors, and iterate over the state of the Boltzmann machine, which is also the state of the sensors, based on the edge weights to locate the sensor faults. Moreover, a novel voting strategy based on Euclidean distance is designed to determine the voting values. Additionally, a method is developed to reset the Boltzmann machine’s weight matrix by adding a node to the Boltzmann machine, which maintains the original voting relationship among the sensors while symmetrizing the Boltzmann machine to ensure convergence of the iteration of the Boltzmann machine state. This method does not need solving many optimization problems, leading to lower computational requirements compared to existing distributed methods. The proposed method is validated using actual data provided by ASHRAE Project RP-1312. The experimental results show that the proposed method can accurately and efficiently diagnose bias and drift faults in AHU sensors.
- Fault diagnosis /
- Voting mechanism /
- Decentralized /
- Sensor /
- Boltzmann machine

HTML全文

图 1 基于投票机制的故障诊断方法的灵感来源

下载: 全尺寸图片幻灯片

图 2 用玻尔兹曼机描述传感器的拓扑结构

下载: 全尺寸图片幻灯片

图 3 基于新型投票机制的分布式故障诊断方法的框图

下载: 全尺寸图片幻灯片

图 4 温度传感器的真实状态和状态估计

下载: 全尺寸图片幻灯片

图 5 流量传感器的真实状态和状态估计

下载: 全尺寸图片幻灯片

图 6 不同算法对不同故障进行诊断的雷达图

下载: 全尺寸图片幻灯片

图 7 不同算法的诊断精度

下载: 全尺寸图片幻灯片

表 1 基于ASHRAE Project RP-1312数据来模拟传感器故障

传感器	故障类型	故障大小	故障日期(年/月/日)
T_a,mix	偏差	2 ^oC	2007/8/25
T_a,mix	漂移	0.3 ^oC/h	2007/8/20
T_a,sup	偏差	2 ^oC	2007/8/26
T_a,sup	漂移	0.3 ^oC/h	2007/8/21
${\dot m_{{\rm{a}},\sup } }$	偏差	0.3 kg/s	2007/8/27
${\dot m_{{\rm{a}},\sup } }$	漂移	0.03 kg/(s·h)	2007/8/22
${\dot m_{{\rm{a}},rn} }$	偏差	0.3 kg/s	2007/8/31
${\dot m_{{\rm{a}},rn} }$	漂移	0.03 kg/(s·h)	2007/8/23

下载: 导出CSV

参考文献(17)

[1]	KATIPAMULA S and BRAMBLEY M R. Methods for fault detection, diagnostics, and prognostics for building systems - a review, part I[J]. HVAC& R Research, 2005, 11(1): 3–25. doi: 10.1080/10789669.2005.10391123
[2]	LIAO Huanyue, CAI Wenjian, CHENG Fanyong, et al. An online data-driven fault diagnosis method for air handling units by rule and convolutional neural networks[J]. Sensors, 2021, 21(13): 4358. doi: 10.3390/s21134358
[3]	YAN Ying, CAI Jun, LI Tao, et al. Fault prognosis of HVAC air handling unit and its components using hidden-semi Markov model and statistical process control[J]. Energy and Buildings, 2021, 240: 110875. doi: 10.1016/j.enbuild.2021.110875
[4]	YAN Xiao’an and JIA Minping. Application of CSA-VMD and optimal scale morphological slice bispectrum in enhancing outer race fault detection of rolling element bearings[J]. Mechanical Systems and Signal Processing, 2019, 122: 56–86. doi: 10.1016/j.ymssp.2018.12.022
[5]	邵海东, 肖一鸣, 颜深. 仿真数据驱动的改进无监督域适应轴承故障诊断[J/OL]. 机械工程学报, 2022: 1–10. http://kns.cnki.net/kcms/detail/11.2187.TH.20220915.1441.002.html, 2022. SHAO Haidong, XIAO Yiming, and YAN Shen. Simulation data-driven enhanced unsupervised domain adaptation for bearing fault diagnosis[J/OL]. Journal of Mechanical Engineering, 2022: 1–10. http://kns.cnki.net/kcms/detail/11.2187.TH.20220915.1441.002.html, 2022.
[6]	王路瑶, 吴斌, 杜志敏, 等. 基于长短期记忆神经网络的数据中心空调系统传感器故障诊断[J]. 化工学报, 2018, 69(S2): 252–259. doi: 10.11949/j.issn.0438-1157.20181084 WANG Luyao, WU Bin, DU Zhimin, et al. Sensor fault detection and diagnosis for data center air conditioning system based on LSTM neural network[J]. CIESC Journal, 2018, 69(S2): 252–259. doi: 10.11949/j.issn.0438-1157.20181084
[7]	邵海东, 颜深, 肖一鸣. 时变转速下基于改进图注意力网络的轴承半监督故障诊断[J/OL]. 电子与信息学报, 2022: 1–9. https://jeit.ac.cn/cn/article/doi/10.11999/JEIT220303, 2022. SHAO Haidong, YAN Shen, and XIAO Yiming. Semi-supervised bearing fault diagnosis using improved graph attention network under time-varying speeds[J/OL]. Journal of Electronics & Information Technology, 2022: 1–9. https://jeit.ac.cn/cn/article/doi/10.11999/JEIT220303, 2022.
[8]	LIU Jingjing, ZHANG Min, WANG Hai, et al. Sensor fault detection and diagnosis method for AHU using 1-D CNN and clustering analysis[J]. Computational Intelligence and Neuroscience, 2019, 2019: 5367217. doi: 10.1155/2019/5367217
[9]	WANG Zhuozheng, DONG Yingjie, LIU Wei, et al. A novel fault diagnosis approach for chillers based on 1-D convolutional neural network and gated recurrent unit[J]. Sensors, 2020, 20(9): 2458. doi: 10.3390/s20092458
[10]	REPPA V, PAPADOPOULOS P, POLYCARPOU M M, et al. A distributed architecture for HVAC sensor fault detection and isolation[J]. IEEE Transactions on Control Systems Technology, 2015, 23(4): 1323–1337. doi: 10.1109/TCST.2014.2363629
[11]	SHAHNAZARI H, MHASKAR P, HOUSE J M, et al. Modeling and fault diagnosis design for HVAC systems using recurrent neural networks[J]. Computers & Chemical Engineering, 2019, 126: 189–203. doi: 10.1016/j.compchemeng.2019.04.011
[12]	WANG Shiqiang, XING Jianchun, JIANG Ziyan, et al. A novel sensors fault detection and self-correction method for HVAC systems using decentralized swarm intelligence algorithm[J]. International Journal of Refrigeration, 2019, 106: 54–65. doi: 10.1016/j.ijrefrig.2019.06.007
[13]	WANG Shiqiang, XING Jianchun, JIANG Ziyan, et al. A decentralized sensor fault detection and self-repair method for HVAC systems[J]. Building Services Engineering Research and Technology, 2018, 39(6): 667–678. doi: 10.1177/0143624418775881
[14]	FENG Bpwei, ZHOU Qizhen, XING Jianchun, et al. A fully distributed voting strategy for AHU fault detection and diagnosis based on a decentralized structure[J]. Energy Reports, 2022, 8: 390–404. doi: 10.1016/J.EGYR.2021.11.281
[15]	YAN Ying, LUH P B, and PATTIPATI K R. Fault diagnosis of HVAC air-handling systems considering fault propagation impacts among components[J]. IEEE Transactions on Automation Science and Engineering, 2017, 14(2): 705–717. doi: 10.1109/TASE.2017.2669892
[16]	YAN Ying, CAI Jun, TANG Yun, et al. A decentralized Boltzmann-machine-based fault diagnosis method for sensors of air handling units in HVACs[J]. Journal of Building Engineering, 2022, 50: 104130. doi: 10.1016/j.jobe.2022.104130
[17]	ZHAO Xiaoli, YAO Jianyong, DENG Wenxiang, et al. Intelligent fault diagnosis of gearbox under variable working conditions with adaptive intraclass and interclass convolutional neural network[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022.