Scholarlink

<p>Shear walls are vital structural systems that provide lateral strength to buildings, effectively resisting seismic loads. These loads are transferred to the walls through diaphragm and collector members. Accurately predicting the shear capacity of concrete shear walls is essential for ensuring seismic safety. This study proposes a model using a Deep Belief Network (DBN) optimized by the Balanced Manta Ray Foraging Optimization Algorithm (BMRFOA) to predict the shear strength of these walls. The model incorporates several input parameters: wall thickness, vertical reinforcement ratio, wall length, transverse reinforcement percentage, concrete compressive strength, transverse reinforcement capacity, vertical reinforcement capacity, and dimension ratio. The output variable is the shear strength of the reinforced concrete shear wall. A dataset of 60 laboratory tests was analyzed to train the model. The results demonstrate that the optimized Deep Belief Network can reliably estimate shear capacity, with the γ ratio having the greatest impact on predictive accuracy. The model achieved an error margin of approximately 7%, which is considered satisfactory for this field. Overall, the findings underscore the effectiveness of the DBN-BMRFOA approach for predicting the shear strength of concrete shear walls.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Utilizing deep belief network optimized by balanced Manta ray foraging optimization algorithm for estimating the shear Wall’s shear strength

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月3日

查看全文
  • Feng Liu,
  • Zhigui Dong,
  • Bizhan Gorbani

摘要

Shear walls are vital structural systems that provide lateral strength to buildings, effectively resisting seismic loads. These loads are transferred to the walls through diaphragm and collector members. Accurately predicting the shear capacity of concrete shear walls is essential for ensuring seismic safety. This study proposes a model using a Deep Belief Network (DBN) optimized by the Balanced Manta Ray Foraging Optimization Algorithm (BMRFOA) to predict the shear strength of these walls. The model incorporates several input parameters: wall thickness, vertical reinforcement ratio, wall length, transverse reinforcement percentage, concrete compressive strength, transverse reinforcement capacity, vertical reinforcement capacity, and dimension ratio. The output variable is the shear strength of the reinforced concrete shear wall. A dataset of 60 laboratory tests was analyzed to train the model. The results demonstrate that the optimized Deep Belief Network can reliably estimate shear capacity, with the γ ratio having the greatest impact on predictive accuracy. The model achieved an error margin of approximately 7%, which is considered satisfactory for this field. Overall, the findings underscore the effectiveness of the DBN-BMRFOA approach for predicting the shear strength of concrete shear walls.