| Presentation | 2017-01-20 Defect Causal Analysis in Solar Panel using Thermal Image : A Deep Learning Approach Seungho Lee, Makoto Suzuki, Hiroyuki Morikawa, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Deteriorated solar panels cause not only decreasing of power generation but also significantly safety concerns such as concentrated heat generation in a small area. Therefore, the deterioration diagnosis and the risk management are indispensable for solar power generation systems. However, conventional maintenance methods focusing on the power generation characteristics costs a lot of time and money since it is necessary to connect the measuring device to each solar module. Conventional maintenance methods using thermal images are mainly based on abnormality detection focusing on specifying the high temperature area, and specific diagnosis in abnormal solar cells has not yet been provided. In this paper, we design the thermal image classifier using deep learning for the state diagnosis of the bypass diode and the power generation circuit which are the main abnormal part of solar module. The validation based on 1400 thermal images of six solar modules collected over six months, shown to classification performance of f1-score 0.97. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Solar panel / Fault diagnosis / Thermal image / Convolutional neural network |
| Paper # | ASN2016-87 |
| Date of Issue | 2017-01-12 (ASN) |
| Conference Information | |
| Committee | ASN / MoNA / MICT |
|---|---|
| Conference Date | 2017/1/19(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Hiroshi Tohjo(NTT) / Hiroaki Morino(Shibaura Inst. of Tech.) / Masaru Sugimachi(National Cerebral and Cardiovascular Center) |
| Vice Chair | Hiroo Sekiya(Chiba Univ.) / Hiraku Okada(Nagoya Univ.) / Satoru Yamano(NEC) / Ryoichi Shinkuma(Kyoto Univ.) / Shinsuke Hara(Osaka City Univ.) / Takahiro Aoyagi(Tokyo Inst. of Tech.) |
| Secretary | Hiroo Sekiya(Kanagawa Inst. of Tech.) / Hiraku Okada(NTT) / Satoru Yamano(Univ. of Tokyo) / Ryoichi Shinkuma(NTT DoCoMo) / Shinsuke Hara(Niigata Univ.) / Takahiro Aoyagi(Saga Univ.) |
| Assistant | Yuichi Igarashi(Hitachi) / Katsuhiro Naito(Aichi Inst. of Tech.) / Kiyohiko Hattori(NICT) / Hiroshi Fujita(Fujitsu Labs.) / Takuro Yonezawa(Keio Univ.) / Shigemi Ishida(Kyushu Univ.) / Hisashi Kurasawa(NTT) / Koichi Nihei(NEC) / Kohei Ohno(Meiji Univ.) / Keisuke Shima(Yokohama National Univ.) / Tomoko Tateyama(Hiroshima Inst. of Tech.) / Ami Tanaka(Ritsumeikan Univ.) / Daisuke Anzai(Nagoya Inst. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Ambient intelligence and Sensor Networks / Technical Committee on Mobile Network and Applications / Technical Committee on Healthcare and Medical Information Communication Technology |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Defect Causal Analysis in Solar Panel using Thermal Image : A Deep Learning Approach |
| Sub Title (in English) | |
| Keyword(1) | Solar panel |
| Keyword(2) | Fault diagnosis |
| Keyword(3) | Thermal image |
| Keyword(4) | Convolutional neural network |
| 1st Author's Name | Seungho Lee |
| 1st Author's Affiliation | Research Center for Advanced Science and Technology, The University of Tokyo(UTokyo) |
| 2nd Author's Name | Makoto Suzuki |
| 2nd Author's Affiliation | Research Center for Advanced Science and Technology, The University of Tokyo(UTokyo) |
| 3rd Author's Name | Hiroyuki Morikawa |
| 3rd Author's Affiliation | Research Center for Advanced Science and Technology, The University of Tokyo(UTokyo) |
| Date | 2017-01-20 |
| Paper # | ASN2016-87 |
| Volume (vol) | vol.116 |
| Number (no) | ASN-407 |
| Page | pp.pp.95-100(ASN), |
| #Pages | 6 |
| Date of Issue | 2017-01-12 (ASN) |