CRFormer: Complementary Reliability Perspective Transformer for Automotive Components Reliability Prediction Based on Claim Data
Reliability prediction has been studied in many industries for managing stocks and reducing quality assurance costs and production costs. Particularly, in the automotive industry, reliability prediction is performed based on two automobile reliability perspectives, time and mileage. To maximize cost...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9863836/ |
| _version_ | 1811282730980212736 |
|---|---|
| author | Hyun Joon Park Taehyeong Kim Young Seok Kim Jinhong Min Ki Woo Sung Sung Won Han |
| author_facet | Hyun Joon Park Taehyeong Kim Young Seok Kim Jinhong Min Ki Woo Sung Sung Won Han |
| author_sort | Hyun Joon Park |
| collection | DOAJ |
| description | Reliability prediction has been studied in many industries for managing stocks and reducing quality assurance costs and production costs. Particularly, in the automotive industry, reliability prediction is performed based on two automobile reliability perspectives, time and mileage. To maximize cost savings, researchers attempted reliability prediction with short-term inputs. However, limited information on short-term inputs resulted in unsatisfactory prediction results for the long warranty periods. Additionally, the overall evaluation metrics could not reflect the pattern-wise performance, such as the increasing failure patterns. This study proposes Complementary Reliability perspective Transformer (CRFormer) based on Transformer encoder to achieve enriched representations from a short-term input sequence. CRFormer fuses different automobile reliability perspective information and automobile features to compensate for the limited information on short-term input. The performance of CRFormer is evaluated based on automobile claim data accumulated over 16 years. Results showed that compared to previous methods in terms of overall, pattern-wise, and pattern similarity evaluation metrics, CRFormer achieved outstanding performance in time and mileage reliability prediction. Lastly, visualization results and survival analysis based on accurate model prediction can be used to support decision-making to reduce quality assurance costs and production costs. |
| first_indexed | 2024-04-13T01:57:50Z |
| format | Article |
| id | doaj.art-02f8041d8971418cb76c18abc53572d2 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-13T01:57:50Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-02f8041d8971418cb76c18abc53572d22022-12-22T03:07:42ZengIEEEIEEE Access2169-35362022-01-0110884578846810.1109/ACCESS.2022.32004729863836CRFormer: Complementary Reliability Perspective Transformer for Automotive Components Reliability Prediction Based on Claim DataHyun Joon Park0https://orcid.org/0000-0002-5308-6675Taehyeong Kim1https://orcid.org/0000-0002-3499-9444Young Seok Kim2Jinhong Min3https://orcid.org/0000-0002-9261-9235Ki Woo Sung4Sung Won Han5https://orcid.org/0000-0002-0040-3542School of Industrial and Management Engineering, Korea University, Seoul, Seongbuk-gu, Republic of KoreaSchool of Industrial and Management Engineering, Korea University, Seoul, Seongbuk-gu, Republic of KoreaSchool of Industrial and Management Engineering, Korea University, Seoul, Seongbuk-gu, Republic of KoreaSchool of Industrial and Management Engineering, Korea University, Seoul, Seongbuk-gu, Republic of KoreaAutomotive Research and Development Division, Hyundai Motor Group, Advanced Durability Development Team, Namyang, South KoreaSchool of Industrial and Management Engineering, Korea University, Seoul, Seongbuk-gu, Republic of KoreaReliability prediction has been studied in many industries for managing stocks and reducing quality assurance costs and production costs. Particularly, in the automotive industry, reliability prediction is performed based on two automobile reliability perspectives, time and mileage. To maximize cost savings, researchers attempted reliability prediction with short-term inputs. However, limited information on short-term inputs resulted in unsatisfactory prediction results for the long warranty periods. Additionally, the overall evaluation metrics could not reflect the pattern-wise performance, such as the increasing failure patterns. This study proposes Complementary Reliability perspective Transformer (CRFormer) based on Transformer encoder to achieve enriched representations from a short-term input sequence. CRFormer fuses different automobile reliability perspective information and automobile features to compensate for the limited information on short-term input. The performance of CRFormer is evaluated based on automobile claim data accumulated over 16 years. Results showed that compared to previous methods in terms of overall, pattern-wise, and pattern similarity evaluation metrics, CRFormer achieved outstanding performance in time and mileage reliability prediction. Lastly, visualization results and survival analysis based on accurate model prediction can be used to support decision-making to reduce quality assurance costs and production costs.https://ieeexplore.ieee.org/document/9863836/Attention mechanismautomobilereliability predictiontransformer |
| spellingShingle | Hyun Joon Park Taehyeong Kim Young Seok Kim Jinhong Min Ki Woo Sung Sung Won Han CRFormer: Complementary Reliability Perspective Transformer for Automotive Components Reliability Prediction Based on Claim Data IEEE Access Attention mechanism automobile reliability prediction transformer |
| title | CRFormer: Complementary Reliability Perspective Transformer for Automotive Components Reliability Prediction Based on Claim Data |
| title_full | CRFormer: Complementary Reliability Perspective Transformer for Automotive Components Reliability Prediction Based on Claim Data |
| title_fullStr | CRFormer: Complementary Reliability Perspective Transformer for Automotive Components Reliability Prediction Based on Claim Data |
| title_full_unstemmed | CRFormer: Complementary Reliability Perspective Transformer for Automotive Components Reliability Prediction Based on Claim Data |
| title_short | CRFormer: Complementary Reliability Perspective Transformer for Automotive Components Reliability Prediction Based on Claim Data |
| title_sort | crformer complementary reliability perspective transformer for automotive components reliability prediction based on claim data |
| topic | Attention mechanism automobile reliability prediction transformer |
| url | https://ieeexplore.ieee.org/document/9863836/ |
| work_keys_str_mv | AT hyunjoonpark crformercomplementaryreliabilityperspectivetransformerforautomotivecomponentsreliabilitypredictionbasedonclaimdata AT taehyeongkim crformercomplementaryreliabilityperspectivetransformerforautomotivecomponentsreliabilitypredictionbasedonclaimdata AT youngseokkim crformercomplementaryreliabilityperspectivetransformerforautomotivecomponentsreliabilitypredictionbasedonclaimdata AT jinhongmin crformercomplementaryreliabilityperspectivetransformerforautomotivecomponentsreliabilitypredictionbasedonclaimdata AT kiwoosung crformercomplementaryreliabilityperspectivetransformerforautomotivecomponentsreliabilitypredictionbasedonclaimdata AT sungwonhan crformercomplementaryreliabilityperspectivetransformerforautomotivecomponentsreliabilitypredictionbasedonclaimdata |