High‐Precision Data Fusion for Multisensor Weigh‐in‐Motion Using an Adaptive Backpropagation Neural Network.
Saved in:
| Title: | High‐Precision Data Fusion for Multisensor Weigh‐in‐Motion Using an Adaptive Backpropagation Neural Network. |
|---|---|
| Authors: | Liu, Xiaofeng1,2 (AUTHOR) 799544480@qq.com, Wang, Hui3 (AUTHOR), Wang, Xuejun1,2 (AUTHOR), Yuan, Yujie1,2 (AUTHOR), Makul, Natt (AUTHOR) natt@pnru.ac.th |
| Source: | Journal of Engineering (2314-4912). 6/27/2026, Vol. 2026, p1-15. 15p. |
| Subjects: | Multisensor data fusion, Artificial neural networks, Piezoelectric detectors, Genetic algorithms, Weighing instruments, Particle swarm optimization |
| Abstract: | To achieve higher data fusion accuracy of backpropagation neural networks (BPNN) in multisensor weigh‐in‐motion (MS‐WIM), this study proposes a novel algorithm termed adaptive adjustment of bias for backpropagation neural networks (AAB‐BPNN). The AAB‐BPNN can dynamically adjust the output layer biases during the testing phase by calculating the theoretical biases of the two closest training samples and employing linear interpolation. An MS‐WIM experimental platform equipped with four piezoelectric film sensors was established. Experiments were conducted within a specified range of vehicle speeds and temperatures, utilizing five vehicles with varying loads. Data fusion tests were performed for BPNN, genetic algorithm–optimized BPNN, particle swarm–optimized BPNN, and AAB‐BPNN, respectively. The results indicate that among the four algorithms, AAB‐BPNN achieves the highest fusion accuracy, reducing the weighing error to nearly zero while maintaining high computational efficiency. Therefore, AAB‐BPNN emerges as a superior and deployable solution for high‐precision data fusion in MS‐WIM systems. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Engineering (2314-4912) is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | To achieve higher data fusion accuracy of backpropagation neural networks (BPNN) in multisensor weigh‐in‐motion (MS‐WIM), this study proposes a novel algorithm termed adaptive adjustment of bias for backpropagation neural networks (AAB‐BPNN). The AAB‐BPNN can dynamically adjust the output layer biases during the testing phase by calculating the theoretical biases of the two closest training samples and employing linear interpolation. An MS‐WIM experimental platform equipped with four piezoelectric film sensors was established. Experiments were conducted within a specified range of vehicle speeds and temperatures, utilizing five vehicles with varying loads. Data fusion tests were performed for BPNN, genetic algorithm–optimized BPNN, particle swarm–optimized BPNN, and AAB‐BPNN, respectively. The results indicate that among the four algorithms, AAB‐BPNN achieves the highest fusion accuracy, reducing the weighing error to nearly zero while maintaining high computational efficiency. Therefore, AAB‐BPNN emerges as a superior and deployable solution for high‐precision data fusion in MS‐WIM systems. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 23144904 |
| DOI: | 10.1155/je/9914077 |
