相关实验视频

Updated: Jul 7, 2025

Surrogate Model Development for Digital Experiments in Welding

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

在RAC的压力强度的预测准确性上的ANN超参数的影响

Talita Andrade da Costa Almeida¹, Emerson Felipe Felix¹, Carlos Manuel Andrade de Sousa¹

¹Department of Civil Engineering, School of Science and Engineering, São Paulo State University (UNESP), Guaratinguetá 12516-410, Brazil.

Materials (Basel, Switzerland)

|December 23, 2023

概括

人工神经网络 (ANN) 准确地预测回收聚合物的混凝土强度. 最好的模型使用了28个神经元,莱文伯格-马奎特训练,以及一个超标触函数,避免过于复杂的设计可靠的预测.

科学领域:

土木工程土木工程是指土木工程.
材料科学材料科学材料科学
计算智能是一种计算智能.

背景情况:

人工神经网络 (ANN) 对于预测混凝土压力强度至关重要.
优化ANN有助于开发可持续建筑材料,如回收聚合混凝土混凝土.
减少建筑对环境的影响需要高效的材料预测模型.

研究的目的:

调查训练算法,网络拓和激活函数对回收聚合物混凝土强度ANN预测精度的影响.
为了确定最佳的ANN配置来预测回收聚合混凝土的压力强度.
为避免模型过拟合和确保强大的预测性能提供见解.

主要方法:

从现有的文献中编制了721个回收聚合混凝土压力强度样本的实验数据库.
240个人工神经网络 (ANN) 被训练和验证,不同的训练算法 (3种类型),激活函数 (2种类型) 和隐藏层神经元数量 (1-40).
使用确定系数 (R2) 和平均绝对百分比误差 (MAPE) 评估模型性能.

主要成果:

最优的ANN模型采用了28个神经元的单一隐藏层,利用莱文伯格-马奎特训练算法和过度触角激活函数.
这种优化模型实现了0.909的高确定系数 (R2) 和6.81%的低平均绝对百分比误差 (MAPE).
结果表明,尽管训练表现良好,但过度复杂的模型与过多的神经元导致测试阶段的预测准确性较差.

结论:

该研究成功地确定了一个最佳的ANN配置,用于准确预测回收聚合物混凝土的压力强度.
这些发现强调了选择适当的训练算法,激活函数和网络拓对于可靠的混凝土强度预测的重要性.
避免过于复杂的ANN模型至关重要,以防止过度拟合,并确保在回收聚合物混凝土应用中对未见的数据进行有效的概括.

关键词:

人工神经网络的人工神经网络压力强度预测压力强度预测机器学习是机器学习.回收聚合混凝土混凝土的回收混凝土混凝土

更多相关视频

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

相关概念视频

Relation Between Tensile Strength and Compressive Strength of Concrete

Relation Between Tensile Strength and Compressive Strength of Concrete

Concrete is a fundamental building material, and understanding its strengths is crucial for construction projects. The relationship between its tensile and compressive strengths is intricate, showing that while these strengths are related, they do not increase at the same rate. Tensile strength's growth is slower and is affected by various factors such as the methods used for testing, the size and shape of the specimen, the texture of the aggregate used, and the moisture content of the...

Fatigue Strength of Concrete

Fatigue Strength of Concrete

Fatigue, in the context of materials science and engineering, refers to the weakening or failure of a material caused by repeatedly applied loads, even if these loads are below the strength limit of the material. Fatigue strength in concrete is a critical property that influences its durability and longevity. Concrete can fail in two ways due to fatigue. Static fatigue or creep rupture occurs under a constant load or one that increases slowly. The other failure mode is due to cyclical or...

Impact Strength of Concrete

Impact Strength of Concrete

Impact strength in concrete is a critical measure that reflects the material's capability to endure the forces applied during pile driving and when supporting machinery foundations that experience impulsive loads. It is also essential when handling precast concrete components to prevent accidental damage. The impact strength is assessed by observing the concrete's resistance to repeated impacts and energy absorption capacity. A key indicator of significant damage to concrete is when it...