<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Tunnel sand layer grouting reinforcement is a major difficulty in the current development of underground space. Finding a suitable method strategy for grouting reinforcement of the road sand layer to ensure the smooth implementation of the construction is imminent. In this paper, by building a BP neural network model, using signal forward propagation algorithm and error back propagation algorithm, back propagation of the error signal through the implied layer to the input layer, increased accuracy of calculations. To prove that BP neural network based on can effectively enhance the effect of tunnel grouting reinforcement, propose strategies for tunnel sand layer grouting reinforcement. Proven by simulation experiments: the effect of grouting reinforcement is influenced by the grouting material, grouting pressure, and the condition of the injected medium. The grouting parameters, grouting compressive strength and grouting age are the three major factors affecting the grouting reinforcement effect as deduced from the BP neural network input layer and implicit layer, a BP neural network model can be built to derive the parameters of these three major influencing factors. The calculation shows that, BP neural networks can provide specific data that can be relied upon for grout reinforcement, its effect prediction accuracy can reach 98%. It can be seen that BP neural network has practical application in tunnel sand layer grouting reinforcement strategy.</p>
</abstract>

Tunnel sand layer grouting reinforcement is a major difficulty in the current development of underground space. Finding a suitable method strategy for grouting reinforcement of the road sand layer to ensure the smooth implementation of the construction is imminent. In this paper, by building a BP neural network model, using signal forward propagation algorithm and error back propagation algorithm, back propagation of the error signal through the implied layer to the input layer, increased accuracy of calculations. To prove that BP neural network based on can effectively enhance the effect of tunnel grouting reinforcement, propose strategies for tunnel sand layer grouting reinforcement. Proven by simulation experiments: the effect of grouting reinforcement is influenced by the grouting material, grouting pressure, and the condition of the injected medium. The grouting parameters, grouting compressive strength and grouting age are the three major factors affecting the grouting reinforcement effect as deduced from the BP neural network input layer and implicit layer, a BP neural network model can be built to derive the parameters of these three major influencing factors. The calculation shows that, BP neural networks can provide specific data that can be relied upon for grout reinforcement, its effect prediction accuracy can reach 98%. It can be seen that BP neural network has practical application in tunnel sand layer grouting reinforcement strategy.

Grouting reinforcement strategy for tunnel sand layer based on BP neural network

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

{"article-title":"Grouting reinforcement strategy for tunnel sand layer based on BP neural network"}

Tunnel sand layer grouting reinforcement is a major difficulty in the current development of underground space. Finding a suitable method strategy for grouting...

Grouting reinforcement strategy for tunnel sand layer based on BP neural network

Pubblicato online: 02 giu 2023

Pagine: -

Ricevuto: 08 lug 2022

Accettato: 21 ott 2022

DOI: https://doi.org/10.2478/amns.2023.1.00186

Parole chiave
BP Neural Network, Artificial Neural Networks, Tunnel Construction, Tunnel sand layer, Grouting reinforcement

© 2023 Qinglei Wang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Grouting reinforcement strategy for tunnel sand layer based on BP neural network

Pubblicato online: 02 giu 2023

Pagine: -

Ricevuto: 08 lug 2022

Accettato: 21 ott 2022

DOI: https://doi.org/10.2478/amns.2023.1.00186

Parole chiaveBP Neural Network, Artificial Neural Networks, Tunnel Construction, Tunnel sand layer, Grouting reinforcement

© 2023 Qinglei Wang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Parole chiave
BP Neural Network, Artificial Neural Networks, Tunnel Construction, Tunnel sand layer, Grouting reinforcement