High‐Precision Data Fusion for Multisensor Weigh‐in‐Motion Using an Adaptive Backpropagation Neural Network
Year: 2026
Type: article
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.
Source: Journal of Engineering
DOI: 10.1155/je/9914077
Authors: Xiaofeng Liu, Hui Wang, Xuejun Wang, Yujie Yuan
Language: English
Subfield: Civil and Structural Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,400
OpenAlex ID: W7166325086
