An Incremental Regularization Kernel Randomized Neural Network for Electrical Energy Output Prediction in Combined Cycle Power Plant
Incremental randomized neural networks have been widely applied in industrial data modeling. However, incremental randomized neural networks may generate redundant hidden nodes. These nodes may lead to weak performance in real world data modeling tasks. An important factor is that the neural nodes c...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10792436/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533415627685888 |
|---|---|
| author | Xinlei Li Henggong Yue Fei Li Zerui Yun Zhenzhou Li Yongjie Liu Wei Shi Yang Liu |
| author_facet | Xinlei Li Henggong Yue Fei Li Zerui Yun Zhenzhou Li Yongjie Liu Wei Shi Yang Liu |
| author_sort | Xinlei Li |
| collection | DOAJ |
| description | Incremental randomized neural networks have been widely applied in industrial data modeling. However, incremental randomized neural networks may generate redundant hidden nodes. These nodes may lead to weak performance in real world data modeling tasks. An important factor is that the neural nodes constructed in the early stages may influence the quality of subsequently generated nodes. To resolve this drawback, an incremental regularization kernel randomized neural network (IRKRNN) is proposed in this work. IRKRNN adopts a kernel learning method to enhance the feature expression during the parameter-learning. Meanwhile, the uncertainty of random mapping is reduced. Each randomly generated node is projected into kernel space. When new nodes are generated, the kernel space is constantly updated. Moreover, the number of nodes and the expected tolerance are used as criteria for terminating the kernel-based incremental learning process to achieve a compact network structure. Finally, IRKRNN is compared with state-of-the-art randomized neural networks on six real world regression datasets and the electrical energy output prediction task of the combined cycle power plant. Experimental results indicate that the proposed IRKRNN achieves satisfactory generalization performance, and it has good potential for industrial data modeling tasks. |
| format | Article |
| id | doaj-art-775542dff3f44858b5cf3187878142bb |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-775542dff3f44858b5cf3187878142bb2025-01-16T00:01:27ZengIEEEIEEE Access2169-35362024-01-011219043419044410.1109/ACCESS.2024.351548110792436An Incremental Regularization Kernel Randomized Neural Network for Electrical Energy Output Prediction in Combined Cycle Power PlantXinlei Li0https://orcid.org/0009-0008-6242-9749Henggong Yue1Fei Li2https://orcid.org/0009-0007-1242-1477Zerui Yun3Zhenzhou Li4Yongjie Liu5Wei Shi6Yang Liu7Dalat Power Plant, Northern United Power Company Ltd., Ordos, ChinaDalat Power Plant, Northern United Power Company Ltd., Ordos, ChinaDalat Power Plant, Northern United Power Company Ltd., Ordos, ChinaDalat Power Plant, Northern United Power Company Ltd., Ordos, ChinaDalat Power Plant, Northern United Power Company Ltd., Ordos, ChinaDalat Power Plant, Northern United Power Company Ltd., Ordos, ChinaDalat Power Plant, Northern United Power Company Ltd., Ordos, ChinaDalat Power Plant, Northern United Power Company Ltd., Ordos, ChinaIncremental randomized neural networks have been widely applied in industrial data modeling. However, incremental randomized neural networks may generate redundant hidden nodes. These nodes may lead to weak performance in real world data modeling tasks. An important factor is that the neural nodes constructed in the early stages may influence the quality of subsequently generated nodes. To resolve this drawback, an incremental regularization kernel randomized neural network (IRKRNN) is proposed in this work. IRKRNN adopts a kernel learning method to enhance the feature expression during the parameter-learning. Meanwhile, the uncertainty of random mapping is reduced. Each randomly generated node is projected into kernel space. When new nodes are generated, the kernel space is constantly updated. Moreover, the number of nodes and the expected tolerance are used as criteria for terminating the kernel-based incremental learning process to achieve a compact network structure. Finally, IRKRNN is compared with state-of-the-art randomized neural networks on six real world regression datasets and the electrical energy output prediction task of the combined cycle power plant. Experimental results indicate that the proposed IRKRNN achieves satisfactory generalization performance, and it has good potential for industrial data modeling tasks.https://ieeexplore.ieee.org/document/10792436/Incremental learningrandomized neural networkskernel learningelectrical energy output prediction |
| spellingShingle | Xinlei Li Henggong Yue Fei Li Zerui Yun Zhenzhou Li Yongjie Liu Wei Shi Yang Liu An Incremental Regularization Kernel Randomized Neural Network for Electrical Energy Output Prediction in Combined Cycle Power Plant IEEE Access Incremental learning randomized neural networks kernel learning electrical energy output prediction |
| title | An Incremental Regularization Kernel Randomized Neural Network for Electrical Energy Output Prediction in Combined Cycle Power Plant |
| title_full | An Incremental Regularization Kernel Randomized Neural Network for Electrical Energy Output Prediction in Combined Cycle Power Plant |
| title_fullStr | An Incremental Regularization Kernel Randomized Neural Network for Electrical Energy Output Prediction in Combined Cycle Power Plant |
| title_full_unstemmed | An Incremental Regularization Kernel Randomized Neural Network for Electrical Energy Output Prediction in Combined Cycle Power Plant |
| title_short | An Incremental Regularization Kernel Randomized Neural Network for Electrical Energy Output Prediction in Combined Cycle Power Plant |
| title_sort | incremental regularization kernel randomized neural network for electrical energy output prediction in combined cycle power plant |
| topic | Incremental learning randomized neural networks kernel learning electrical energy output prediction |
| url | https://ieeexplore.ieee.org/document/10792436/ |
| work_keys_str_mv | AT xinleili anincrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT henggongyue anincrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT feili anincrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT zeruiyun anincrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT zhenzhouli anincrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT yongjieliu anincrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT weishi anincrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT yangliu anincrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT xinleili incrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT henggongyue incrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT feili incrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT zeruiyun incrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT zhenzhouli incrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT yongjieliu incrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT weishi incrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant AT yangliu incrementalregularizationkernelrandomizedneuralnetworkforelectricalenergyoutputpredictionincombinedcyclepowerplant |