Deep Learning Inspection for Photovoltaic Cell Image Sequence

doi:10.3901/JME.2021.08.098

Abstract

Abstract: In order to realize intelligent factory inspection of photovoltaic cell, the defects of photovoltaic cell are detected by using thermal infrared camera acquiring electro-thermography(ET) and short-wave infrared camera acquiring electroluminescence(EL). A thermal image sequence analysis method based on optical flow method to deal with the thermal flow field of photovoltaic cells is proposed to find the abnormal heat source accurately. The database of photovoltaic cell detection is established by fusing the abnormal light source found by short-wave infrared imaging. The deep convolution neural network is used to effectively identify the artificial defects and internal defects of photovoltaic cells, such as scratches, covers, cracks and defects. The experimental results show that the deep learning method based on optical flow is superior to principal component analysis(PCA) and independent component analysis(ICA) in mean square error, average gradient and information entropy index, and make the network converge faster in the training of convolution network.

Key words: photovoltaic cell, non-destructive testing, image fusion, deep learning

CLC Number:

TM914

DENG Baoyuan, HE Yunze, WANG Hongjin, ZHANG Hong, YANG Yuan, MA Minmin, MU Xinying, YANG Ruizhen. Deep Learning Inspection for Photovoltaic Cell Image Sequence[J]. Journal of Mechanical Engineering, 2021, 57(8): 98-106.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://www.cjmenet.com.cn/EN/10.3901/JME.2021.08.098

http://www.cjmenet.com.cn/EN/Y2021/V57/I8/98

References

[1] 杨瑞珍，杜博伦，何赟泽. 晶体硅光伏电池电磁感应激励红外热辐射缺陷检测与成像技术[J]. 电工技术学报，2018，33(2)：321-330. YANG Ruizhen，DU Bolun，HE Yunze. Infrared radiation defect detection and imaging technique under active electromagnetic induction excitation for crystalline silicon photovoltaic cells[J]. Transactions of China Electrotechnical Society，2018，33(2)：321-330.
[2] BELYAEV A，POLUPAN O，OSTAPENKO S，et al. Resonance ultrasonic vibration diagnostics of elastic stress in full-size silicon wafers[J]. Semiconductorence &; Technology，2006，21(3)：254-260.
[3] HE Y，DU B，HUANG S. Non-contact electromagnetic induction excited infrared thermography for photovoltaic cells and modules inspection[J]. IEEE Transactions on Industrial Informatics，2018，14(12)：5585-5593.
[4] COTFAS D T，COTFAS P A，KAPLANIS S. Methods to determine the dc parameters of solar cells：A critical review[J]. Renewable &; Sustainable Energy Reviews，2013，28(8)：588-596.
[5] COTFAS D T，COTFAS P A，KAPLANIS S. Methods and techniques to determine the dynamic parameters of solar cells：Review[J]. Renewable &; Sustainable Energy Reviews，2016，61：213-221.
[6] HUANG Z，SONG X，ZHONG S，et al. 20.0% efficiency Si nano/microstructures based solar cells with excellent broadband spectral response[J]. Advanced Functional Materials，2016，26(12)：1892-1898.
[7] 陈文志，张凤燕，张然，等. 基于电致发光成像的太阳能电池缺陷检测[J]. 发光学报，2013，34(8)：1028-1034. CHEN Wenzhi，ZHANG Fengyan，ZHANG Ran，et al. Defect detection of solar cells based on electroluminescence imaging[J]. Chinese Journal of Luminescence，2013，34(8)：1028-1034.
[8] CHUNG T Y，WANG C H，CHANG K J，et al. Evaluation of the spatial distribution of series and shunt resistance of a solar cell using dark lock-in thermography[J]. Journal of Applied Physics，2014，115(3)：271-282.
[9] RILAND S，MICARD G，BREITENSTEIN O，et al. Comparison of the recombination velocity at grain boundaries gained by lock-in thermography and light beam induced current measurements[C]//28th European Photovoltaics Solar Energy Conference and Exhibition， 2013：1659-1664.
[10] RIBLAND S，PLETZER T M，WINDGASSEN H，et al. Local thermographic efficiency analysis of multicrystalline and cast-mono silicon solar cells[J]. IEEE Journal of Photovoltaics，2013，3(4)：1192-1199.
[11] KIM D，YOUN J，KIM C. Automatic fault recognition of photovoltaic modules based on statistical analysis of UAV thermography[C/CD]//International Conference on Unmanned Aerial Vehicles in Geomatics，4-7 September 2017，Bonn，Germany，2017.
[12] AGHAEI M，GRIMACCIA F，GONANO C A，et al. Innovative automated control system for PV fields inspection and remote control[J]. IEEE Transactions on Industrial Electronics，2015，62(11)：7287-7296.
[13] NAKANISHI H，FUJIWARA S，TAKAYAMA K，et al. Imaging of a polycrystalline silicon solar cell using a laser terahertz emission microscope[J]. Applied Physics Express，2012，5(11)：2301.
[14] REN W，LIU J，TIAN G Y，et al. Quantitative non-destructive evaluation method for impact damage using eddy current pulsed thermography[J]. Composites Part B：Engineering，2013，54：169-179.
[15] HAUSSECKER H W. Simultaneous estimation of optical flow and heat transport in infrared image sequences [C/CD]//Proceedings of the IEEE Workshop on Computer Vision Beyond the Visible Spectrum：Methods and Applications (Cat No PR00640)，F，2000.
[16] SIMONYAN K，ZISSERMAN A. Two-stream convolutional networks for action recognition in videos [C]//Proceedings of the 27th International Conference on Neural Information Processing Systems，2014：568-576.
[17] WANG L，XIONG Y，WANG Z，et al. Temporal segment networks：Towards good practices for deep action recognition[C]//Proceedings of the European Conference on Computer Vision，2016：20-36.
[18] QIU Z，YAO T，MEI T. Learning spatio-temporal representation with pseudo-3d residual networks[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：5534-5542.
[19] CARREIRA J，ZISSERMAN A. Quo vadis，action recognition? A new model and the kinetics dataset[C/CD]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017.
[20] FEICHTENHOFER C，FAN H，MALIK J，et al. SlowFast networks for video recognition[C]//International Conference on Computer Vision，2018：6201-6210.