[vc_empty_space][vc_empty_space]
Partial Discharge Waveform Identification using Image with Convolutional Neural Network
Puspitasari N.a,b, Khayam U.b, Suwarnob, Kakimoto Y.c, Yoshikawa H.c, Kozako M.c, Hikita M.c
a PT PLN (Persero), Jakarta, Indonesia
b Institut Teknologi Bandung, School of Electrical Engineering and Informatics, Bandung, Indonesia
c Kyushu Institute of Technology, Department of Electrical and Electronics Engineering, Kitakyushu, Japan
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2019 IEEE.The use of Neural Network as a tool for Partial Discharge (PD) Identification has been used since the 1990s, where Backpropagation Neural Network (BPNN) with input in the form of data values was the most widely used method. However, for the past five years, Convolutional Neural Network (CNN) has been used to identify Partial Discharge with input in the form of images. Pattern Recognition of Partial Discharge Image Based on One-dimensional Convolutional Neural reported by Wan et al. in CMD 2018 was using images of 5 cycles repeated waveform pattern images as input. In our research, we used two-dimensional images of time domain single PD waveform obtained from experiments using three sensors (High-Frequency Current Transformer (HFCT), Surface Current Sensor (SCS), and Transient Earth Voltage (TEV) sensor) for input to CNN. The images were extracted using Gaussian Filter on the Convolutional layer, then searched the maximum value for each group of pixels to make computing easier on the Pooling Layer, and finally identified on the Fully Connected Layer. The purpose of this study is to develop a PD diagnostic technique that could simplify the identification of PD sources by using a signal waveform image for identification. The experimental results show that the proposed method has sufficient accuracy in identifying Partial Discharge, and it may be possible to identify Partial Discharge in HV voltage equipment by comparing field data.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Back-propagation neural networks,Convolutional neural network,HFCT,High frequency current transformers,Image,Partial discharge identifications,Partial discharge waveforms,Wave forms[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]CNN,HFCT,Image,Partial Discharge,SCS,TEV,Waveform[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text]The authors would like to give special acknowledgment to Tokyo Densetsu Service Co., Ltd. (Japan) for providing research facility.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.1109/UPEC.2019.8893577[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]