基于主元分析的温室物联网空气温湿度传感器故障诊断

doi:10.13733/j.jcam.issn.2095-5553.2024.05.011

摘要/Abstract

摘要： 针对温室物联网测控系统中空气温湿度传感器受恶劣环境影响易发生故障的问题，研究温室物联网测控系统中空气温湿度传感器的故障诊断，保障温室物联网测控系统整体工作的稳定可靠性，提出一种基于主元分析的空气温湿度传感器故障诊断方法。首先对空气温湿度传感器数据进行主元分析，通过监控平方预测误差统计量的变化实现传感器的故障检测；再针对检测出的空气温湿度传感器故障数据，利用加权后的平方预测误差统计量来计算传感器的累积贡献率，并将其作为传感器故障识别的指标，识别出现故障的空气温湿度传感器。利用空气温湿度传感器数据在不同故障条件下进行传感器故障诊断方法验证，验证结果表明：所提方法可用于温室物联网测控系统中空气温湿度传感器偏差故障和漂移故障的检测，偏差故障的检测效果要好于漂移故障，偏差故障综合检测率为100%，漂移故障综合检测率为51.25%；同时所提方法能够正确识别出故障传感器，有效提高温室物联网测控系统中空气温湿度传感器故障诊断结果的准确性。

关键词: 温室, 物联网, 空气温湿度传感器, 故障诊断, 主元分析, 测控系统

Abstract: Aiming at the problem that the air temperature and humidity sensor in the greenhouse IoT measurement and control system is prone to failure due to the harsh environment, the fault diagnosis of the air temperature and humidity sensor in the greenhouse IoT measurement and control system is studied to ensure the stability and reliability of the overall work of the greenhouse IoT measurement and control system. A fault diagnosis method of air temperature and humidity sensor based on principal component analysis is proposed. Firstly, the principal component analysis of the air temperature and humidity sensor data is carried out, and the fault detection of the sensor is realized by monitoring the change of the square prediction error statistics. Then, for the detected air temperature and humidity sensor fault data, the weighted squared prediction error statistics are used to calculate the cumulative contribution rate of the sensor, and it is used as an indicator of sensor fault identification to identify the faulty air temperature and humidity sensor. The sensor fault diagnosis method is verified by using the data of air temperature and humidity sensor under different fault conditions. The verification results show that the proposed method can be used to detect the deviation fault and drift fault of air temperature and humidity sensor in the measurement and control system of greenhouse IoT. The detection effect of deviation fault is better than that of drift fault. The comprehensive detection rate of deviation fault is 100 %, and the comprehensive detection rate of drift fault is 51.25 %. At the same time, the proposed method can correctly identify the fault sensor, and effectively improve the accuracy of the fault diagnosis results of the air temperature and humidity sensor in the greenhouse IoT measurement and control system.

Key words: greenhouse, IoT, air temperature and humidity sensors, fault diagnosis, principal components analysis, measurement and control system

中图分类号:

S625: TP212.9

范卫强, , , 柳平增, , , 朱珂, , , 孟宪勇, , , 刘力宁, , . 基于主元分析的温室物联网空气温湿度传感器故障诊断[J]. 中国农机化学报, 2024, 45(5): 69-78.

Fan Weiqiang, , , Liu Pingzeng, , , Zhu Ke, , , Meng Xianyong, , , Liu Lining, , . Fault diagnosis of greenhouse IoT air temperature and humidity sensors based on principal components analysis [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(5): 69-78.

参考文献

［1］　郑钊. 基于物联网技术的智慧农业发展模式研究［J］. 农业经济, 2022(2): 13-15.
［2］　赵继春, 孙素芬, 郭建鑫, 等. 基于无线传感器网络的设施农业环境智能监测系统设计［J］. 中国农机化学报, 2020, 41(4): 146-151.
Zhao Jichun, Sun Sufen, Guo Jianxin, et al. Design of intelligent monitoring system for facility agriculture environment based on wireless sensor network ［J］. Journal of Chinese Agricultural Mechanization, 2020, 41(4): 146-151.
［3］　贾敬敦, 鲁相洁, 黄峰, 等. 远程控制与无线通信技术在农业中的应用分析与展望［J］. 农业机械学报, 2021, 52(S1): 351-359.
Jia Jingdun, Lu Xiangjie, Huang Feng, et al. Review of remote control and wireless communication technology in agriculture applications ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(S1): 351-359.
［4］　邹彬, 董军堂, 杨延宁, 等. 基于云平台的温室大棚管理系统［J］. 传感器与微系统, 2021, 40(12): 112-114, 118.
Zou Bin, Dong Juntang, Yang Yanning, et al. Greenhouse management system based on cloud platform ［J］. Transducer and Microsystem Technologies, 2021, 40(12): 112-114, 118.
［5］　张宝峰, 陈枭, 朱均超, 等. 基于物联网的水肥一体化系统设计与试验［J］. 中国农机化学报, 2021, 42(3): 98-104.
Zhang Baofeng, Chen Xiao, Zhu Junchao, et al. Design and experiment of integrated water and fertilizer system based on Internet of Things ［J］. Journal of Chinese Agricultural Mechanization, 2021, 42(3): 98-104.
［6］　Chamarajnagar R, Ashok A. Integrity threat identification for distributed IoT in precision agriculture ［C］. 2019 16th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON). IEEE, 2019: 1-9.
［7］　Commault C, Dion J M, Trinh D H, et al. Sensor classification for the fault detection and isolation, a structural approach ［J］. International Journal of Adaptive Control and Signal Processing, 2011, 25(1): 1-17.
［8］　王纪章, 贺通, 周金生, 等. 基于时空信息比较的温室环境传感器故障识别［J］. 农业机械学报, 2018, 49(2): 319-326.
Wang Jizhang, He Tong, Zhou Jinsheng, et al. Sensor fault identification in greenhouse environment based on comparison of spatialtemporal information ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(2): 319-326.
［9］　Yi T H, Huang H B, Li H N. Development of sensor validation methodologies for structural health monitoring: A comprehensive review ［J］. Measurement, 2017, 109: 200-214.
［10］　Ni K, Ramanathan N, Chehade M N H, et al. Sensor network data fault types ［J］. ACM Transactions on Sensor Networks (TOSN), 2009, 5(3): 1-29.
［11］　张娅玲, 陈伟民，章鹏, 等. 传感器故障诊断技术概述［J］. 传感器与微系统, 2009, 28(1): 4-6, 12.
Zhang Yaling, Chen Weimin, Zhang Peng, et al. Overview on sensor fault diagnosis technology ［J］. Transducer and Microsystem Technologies, 2009, 28(1): 4-6, 12.
［12］　Li D, Wang Y, Wang J, et al. Recent advances in sensor fault diagnosis: A review ［J］. Sensors and Actuators A: Physical, 2020, 309: 111990.
［13］　Raychaudhuri S, Stuart J M, Altman R B. Principal components analysis to summarize microarray experiments: Application to sporulation time series ［M］. Biocomputing 2000, 1999: 455-466.
［14］　顾炳斌, 熊伟丽. 基于多块信息提取的PCA故障诊断方法［J］. 化工学报, 2019, 70(2): 736-749.
Gu Bingbin, Xiong Weili. Fault diagnosis based on PCA method with multiblock information extraction ［J］. CIESC Journal, 2019, 70(2): 736-749.
［15］　李立力, 刘纲, 张亮亮, 等. 加权PCA残差子空间的加速度传感器故障诊断［J］. 振动·测试与诊断, 2021, 41(5): 1007-1013, 1039-1040.
Li Lili, Liu Gang, Zhang Liangliang, et al. Accelerometer fault diagnosis with weighted PCA residual space ［J］. Journal of Vibration, Measurement & Diagnosis, 2021, 41(5): 1007-1013, 1039-1040.
［16］　Huang H B, Yi T H, Li H N. Bayesian combination of weighted principalcomponent analysis for diagnosing sensor faults in structural monitoring systems ［J］. Journal of Engineering Mechanics, 2017, 143(9): 04017088.
［17］　Wang S, Xiao F. AHU sensor fault diagnosis using principal component analysis method ［J］. Energy and Buildings, 2004, 36(2): 147-160.
［18］　Chen H, Jiang B, Lu N, et al. Deep PCA based realtime incipient fault detection and diagnosis methodology for electrical drive in highspeed trains ［J］. IEEE Transactions on Vehicular Technology, 2018, 67(6): 4819-4830.
［19］　Li W, Peng M, Liu Y, et al. Fault detection, identification and reconstruction of sensors in nuclear power plant with optimized PCA method ［J］. Annals of Nuclear Energy, 2018, 113: 105-117.
［20］　苑进, 胡敏, Kesheng Wang, 等. 基于高斯过程建模的物联网数据不确定性度量与预测［J］. 农业机械学报, 2015, 46(5): 265-272.
Yuan Jin, Hu Min, Kesheng Wang, et al. Uncertainty measurement and prediction of IoT data based on Gaussian process modeling ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(5): 265-272.
［21］　Li S, Wen J. A modelbased fault detection and diagnostic methodology based on PCA method and wavelet transform ［J］. Energy and Buildings, 2014, 68: 63-71.
［22］　李伟. 核电厂传感器状态监测方法研究［D］. 哈尔滨: 哈尔滨工程大学, 2018.
Li Wei. Research on the techniques of sensor condition monitoring for a nuclear power plant ［D］. Harbin: Harbin Engineering University, 2018.
［23］　MacGregor J F, Kourti T. Statistical process control of multivariate processes ［J］. Control Engineering Practice, 1995, 3(3): 403-414.
［24］　Zhu T, Huang J, Yan X. Process monitoring based on entropy weight for a subspace containing probabilistic principal components and faultrelevant noise factors ［J］. Journal of Chemometrics, 2017, 31(6): e2890.
［25］　Zhang C, Gao X, Xu T, et al. Fault detection and diagnosis strategy based on a weighted and combined index in the residual subspace associated with PCA ［J］. Journal of Chemometrics, 2018, 32(11): e2981.

[1]	焦宁, , 朱德兰, , 荆宇鹏, , 刘孟阳, , 柳昌新. 基于数值模拟的温室湿帘—风机运行参数确定方法研究[J]. 中国农机化学报, 2024, 45(5): 79-84.
[2]	邢清桂, 吴凯, 周洪斌. 基于分层特征注意力解耦的农机轴承故障诊断[J]. 中国农机化学报, 2024, 45(5): 140-146.
[3]	伏俊伟, , 贺小伟, , 王旭峰, , 刘金秀, , 朱冠三, , 李敏, . 温室环境控制方法现状分析及发展研究[J]. 中国农机化学报, 2024, 45(4): 58-65.
[4]	胡玲艳, 邱绍航, 李国强, 许巍, 刘艳, 汪祖民. 融合GA-Attention-LSTM算法的温室樱桃环境参数预测与裂果预警[J]. 中国农机化学报, 2024, 45(1): 169-176.
[5]	侯炳法, 李小敏, 牟向伟, 姚华平. 圣女果温室巡检机器人系统设计与试验[J]. 中国农机化学报, 2024, 45(1): 285-294.
[6]	杨冬艳, 王丹, 桑婷, 赵云霞, 宋卫堂. 日光温室番茄东西垄向模式下群体光环境及产量分布特征[J]. 中国农机化学报, 2023, 44(9): 51-58.
[7]	张莉, 刘京蕊, 李震, 李传友, 滕飞, 赵景文. 温室草莓不同喷药方式作业质量研究[J]. 中国农机化学报, 2023, 44(7): 63-68.
[8]	郎秀丹, 史宇亮, 黄新平, 李天华, 王东伟, 陈明东. 日光温室藤蔓类作物整体落蔓装置设计[J]. 中国农机化学报, 2023, 44(7): 78-84.
[9]	杨承磊, 兰玉彬, 王庆雨, 别晓婷, 单常峰, 王国宾, . 神经网络在温室小气候预测中的应用[J]. 中国农机化学报, 2023, 44(5): 89-99.
[10]	霍如周, 奚小波, , 张翼夫, 张宝峰, 瞿济伟, 张瑞宏, . 碳中和背景下中国农业碳排放现状与发展趋势[J]. 中国农机化学报, 2023, 44(12): 151-161.
[11]	毛晓娟, 鲍彤, 荀广连, 李德翠, 王宝佳, 任妮. 基于GWO-LSTM的设施蔬菜温室温度预测[J]. 中国农机化学报, 2023, 44(1): 116-123.
[12]	李洪兵, 罗洋, 张颖, 王雨凝, 欧俊, 崔浩. 基于模糊PID控制的NB-IoT果蔬农业物联网系统设计与试验[J]. 中国农机化学报, 2023, 44(1): 162-171.
[13]	代志伟, 程曼, 袁洪波, 蔡振江. 温室灌溉控制策略研究进展[J]. 中国农机化学报, 2022, 43(9): 63-72.
[14]	卞东超, 杨发展, 赵国栋, 郑凯瑞, 林海波. 蓝莓温室智能水肥一体化系统构建[J]. 中国农机化学报, 2022, 43(8): 55-61.
[15]	杨学坤, 郑士朝. 气雾栽培式家庭植物工厂设计[J]. 中国农机化学报, 2022, 43(4): 38-45.