Fault Diagnosis for Photovoltaic Power Station by Multi-Scale Features Fusion

doi:10.3778/j.issn.1002-8331.2111-0095

Abstract

Abstract: To diagnose faulty equipments in time and save the cost of maintenance, a deep learning model of fault diagnosis based on multi-scale time serial features fusion is proposed for the operation and maintenance of photovoltaic power station. To take advantage of the different abilities of convolutional layers with different scales, the model implements the multi-scale neighborhood feature extraction, which can help the network filter the noise in input data while keep the important information. Then, considering the long time series and high dimension of monitoring data, a long short-term memory unit with attention mechanism is used to extract sequential features. Finally, to improve the discernment of the network, metric learning loss function is applied to assist training. In addition, a data normalization algorithm is designed out. It can be used to rectify the impact of devices and weather on monitoring data through comparison between data from different devices and different days. Experiments prove that the proposed model can diagnose faults of equipment more accurately compared with other time series analysis algorithms, which can achieve 95% accuracy on real monitoring data of photovoltaic power station.

Key words: fault diagnosis, deep learning, time series data analysis, photovoltaic power station

摘要： 为了高效率、低成本地发现光伏电站设备故障，提出了一种多尺度时序特征融合的故障诊断深度学习模型。组合多种尺度的卷积操作，实现了多尺度时序特征提取，能够使网络过滤输入数据的噪点，同时又不丢失数据的关键信息；针对光伏电站监测数据长序列、多维度的特点，采用带有注意力机制的长短时记忆循环网络提取数据中的序列特征；使用了度量学习的损失函数辅助训练，进一步提升模型辨别能力。另外，设计了一种数据规范化算法，能够通过不同设备之间的横向比较和不同日期之间的纵向比较，将监测数据转化为相对度量值，从而矫正设备、天气等因素对监测数据的干扰。实验表明，配合数据规范化算法，该模型在真实的电站监测数据上能够达到95%以上的诊断准确率，明显优于已有的诊断算法，能够满足实际应用场景的故障诊断需求。

关键词: 故障检测, 深度学习, 时序数据分析, 光伏电站

NA Zhixiong, SUN Tao, LAI Guangzhi, WANG Dong, ZHANG Changzhi. Fault Diagnosis for Photovoltaic Power Station by Multi-Scale Features Fusion[J]. Computer Engineering and Applications, 2022, 58(10): 300-308.

那峙雄, 孙涛, 来广志, 王栋, 张长志. 多尺度特征融合的光伏电站故障诊断[J]. 计算机工程与应用, 2022, 58(10): 300-308.

References

[1] HOCHREITER S，SCHMIDHUBER J.Long short-term memory[J].Neural Computation，1997，9（8）：1735-1780.
[2] ALAJMI M，ABDEL-QADER I.Fault detection and localization in solar photovoltaic arrays using the current-voltage sensing framework[C]//2016 IEEE International Conference on Electro Information Technology，2016：307-312.
[3] OOZEKI T，YAMADA T，KATO K.On-site measurements of photovoltaic systems for detection of failure modules[C]//2008 33rd IEEE Photovoltaic Specialists Conference，2008：1-6.
[4] 刘恒.基于I-V曲线的热斑光伏组件故障诊断及状态评估综合研究[D].合肥：合肥工业大学，2020.
LIU H.Comprehensive research on fault diagnosis and condition assessment of PV module with hot spot based on I-V curve[D].Hefei：Hefei University of Technology，2020.
[5] 丁坤，陈富东，翁帅，等.基于I-V特性灰色关联分析的光伏阵列健康状态评估[J].电网技术，2021，45（8）：3087-3095.
DING K，CHEN F D，WONG S，et al.Health state evaluation of photovoltaic array based on I-V characteristics and grey relational analysis[J].Power System Technology，2021，45（8）：3087-3095.
[6] 刘强，郭珂，毛明轩，等.一种基于串联等效电阻的光伏故障检测方法[J].太阳能学报，2020，41（10）：119-126.
LIU Q，GUO K，MAO M X，et al.A photovoltaic fault detection method based on series equivalent resistance[J].Acta Energiae Solaris Sinica，2020，41（10）：119-126.
[7] 林培杰，陈志聪，吴丽君，等.一种PSO-SVM的光伏阵列故障检测与分类[J].福州大学学报（自然科学版），2017，45（5）：652-658.
LIN P J，CHEN Z C，WU L J，et al.Fault detection and classification for photovoltaic arrays based on PSO-SVM[J].Journal of Fuzhou University（Science Edition），2017，45（5）：652-658.
[8] 叶进，卢泉，王钰淞，等.基于级联随机森林的光伏故障诊断模型研究[J].太阳能学报，2021，42（3）：358-362.
YE J，LU Q，WANG Y S，et al.Research on PV fault diagnosis model based on cascaded random forest[J].Acta Energiae Solaries Sinica，2020，42（3）：358-362.
[9] 朱健.基于关联规则改进聚类算法的光伏电站故障检测方法研究[D].南宁：广西大学，2019.
ZHU J.Research on PV station fault detection based on improved clustering algorithm and association rules[D].Nanning：Guangxi University，2019.
[10] 陆灵骍.基于数据驱动的光伏阵列故障诊断研究与应用[D].北京：华北电力大学（北京），2019.
LU L X.Research and application of photovoltaic array fault diagnosis based on data driven[D].Beijing：North China Electric Power University（Beijing），2019.
[11] 张国豪，刘波.采用CNN和Bidirectional GRU的时间序列分类研究[J].计算机科学与探索，2019，13（6）：916-927.
ZHANG G H，LIU B.Research on time series classification using CNN and Bidirectional GRU[J].Journal of Frontiers of Computer Science and Technology，2019，13（6）：916-927.
[12] 吴擎.基于深度学习的光伏发电系统故障诊断方法研究[D].济南：山东大学，2019.
WU Q.Research on fault diagnosis methods of photovoltaic power systems based on deep learning[D].Jinan：Shandong University，2019.
[13] BAYDOGAN M G，RUNGER G，TUV E.A bag-of-features framework to classify time series[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2013，35（11）：2796-2802.
[14] YE L，KEOGH E.Time series shapelets：a new primitive for data mining[C]//15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，2009：947-956.
[15] SUTSKEVER I，VINYALS O，LE Q V.Sequence to sequence learning with neural networks[C]//Advances in Neural Information Processing Systems，2014：3104-3112.
[16] BAHDANAU D，CHO K，BENGIO Y.Neural machine translation by jointly learning to align and translate[J].arXiv：1409.0473，2014.
[17] LIU W，WEN Y，YU Z，et al.SphereFace：deep hypersphere embedding for face recognition[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：212-220.
[18] WANG H，WANG Y，ZHOU Z，et al.CosFace：large margin cosine loss for deep face recognition[C]//2018 IEEE Conference on Computer Vision and Pattern Recognition，2018：5265-5274.
[19] DENG J，GUO J，XUE N，et al.ArcFace：additive angular margin loss for deep face recognition[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：4690-4699.
[20] 宋丽丽，李彬，赵俊雅，等.正态重采样的改进行人再识别度量学习算法[J].计算机工程与应用，2020，56（8）：158-165.
SONG L L，LI B，ZHAO J Y，et al.Normality resampling of improved metric learning method for person re-identification[J].Computer Engineering and Applications，2020，56（8）：158-165.
[21] HADSELL R，CHOPRA S，LECUN Y.Dimensionality reduction by learning an invariant mapping[C]//2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition，2006：1735-1742.
[22] SCHROFF F，KALENICHENKO D，PHILBIN J.FaceNet：a unified embedding for face recognition and clustering[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition，2015：815-823.
[23] 冯磊，蒋磊，许华，等.基于网络度量的三分支孪生网络调制识别算法[J].计算机工程与应用，2021，57（19）：135-141.
FENG L，JIANG L，XU H，et al.Triplet siamese network modulation recognition algorithm based on network measurement[J].Computer Engineering and Applications，2021，57（19）：135-141.
[24] KINGMA D P，BA J.Adam：a method for stochastic optimization[J].arXiv：1412.6980，2014.
[25] GRABOCKA J，SCHILLING N，WISTUBA M，et al.Learning time-series shapelets[C]//20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，2014：392-401.
[26] ZHANG W，ZHANG F，CHEN W，et al.Fault state recognition of rolling bearing based fully convolutional network[J].Computing in Science & Engineering，2018，21（5）：55-63.
[27] WU J，LIU B，ZHANG H，et al.Fault detection based on fully convolutional networks（FCN）[J].Journal of Marine Science and Engineering，2021，9（3）：259.