Multispectral radiation temperature inversion based on Transformer-LSTM-SVM
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912283977842688 |
|---|---|
| author | Cui, Ying Qiu, Kongxin Gao, Shan Liu, Hailong Gao, Rongyan Chen, Liwei Zhang, Zezhan Jiang, Jing Niu, Yi Wang, Chao |
| author_facet | Cui, Ying Qiu, Kongxin Gao, Shan Liu, Hailong Gao, Rongyan Chen, Liwei Zhang, Zezhan Jiang, Jing Niu, Yi Wang, Chao |
| contents | The key challenge in multispectral radiation thermometry is accurately measuring emissivity. Traditional constrained optimization methods often fail to meet practical requirements in terms of precision, efficiency, and noise resistance. However, the continuous advancement of neural networks in data processing offers a potential solution to this issue. This paper presents a multispectral radiation thermometry algorithm that combines Transformer, LSTM (Long Short-Term Memory), and SVM (Support Vector Machine) to mitigate the impact of emissivity, thereby enhancing accuracy and noise resistance. In simulations, compared to the BP neural network algorithm, GIM-LSTM, and Transformer-LSTM algorithms, the Transformer-LSTM-SVM algorithm demonstrates an improvement in accuracy of 1.23%, 0.46% and 0.13%, respectively, without noise. When 5% random noise is added, the accuracy increases by 1.39%, 0.51%, and 0.38%, respectively. Finally, experiments confirmed that the maximum temperature error using this method is less than 1%, indicating that the algorithm offers high accuracy, fast processing speed, and robust noise resistance. These characteristics make it well-suited for real-time high-temperature measurements with multi-wavelength thermometry equipment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15797 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multispectral radiation temperature inversion based on Transformer-LSTM-SVM Cui, Ying Qiu, Kongxin Gao, Shan Liu, Hailong Gao, Rongyan Chen, Liwei Zhang, Zezhan Jiang, Jing Niu, Yi Wang, Chao Optics The key challenge in multispectral radiation thermometry is accurately measuring emissivity. Traditional constrained optimization methods often fail to meet practical requirements in terms of precision, efficiency, and noise resistance. However, the continuous advancement of neural networks in data processing offers a potential solution to this issue. This paper presents a multispectral radiation thermometry algorithm that combines Transformer, LSTM (Long Short-Term Memory), and SVM (Support Vector Machine) to mitigate the impact of emissivity, thereby enhancing accuracy and noise resistance. In simulations, compared to the BP neural network algorithm, GIM-LSTM, and Transformer-LSTM algorithms, the Transformer-LSTM-SVM algorithm demonstrates an improvement in accuracy of 1.23%, 0.46% and 0.13%, respectively, without noise. When 5% random noise is added, the accuracy increases by 1.39%, 0.51%, and 0.38%, respectively. Finally, experiments confirmed that the maximum temperature error using this method is less than 1%, indicating that the algorithm offers high accuracy, fast processing speed, and robust noise resistance. These characteristics make it well-suited for real-time high-temperature measurements with multi-wavelength thermometry equipment. |
| title | Multispectral radiation temperature inversion based on Transformer-LSTM-SVM |
| topic | Optics |
| url | https://arxiv.org/abs/2503.15797 |