A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Multi-performance control concrete mix proportion optimization method
The invention belongs to the technical field of concrete mix proportion optimization, and particularly discloses a multi-performance control concrete mix proportion optimization method. Comprising the following steps: collecting a plurality of groups of concrete mix proportion actual production data, respectively establishing deep learning prediction models of concrete strength, workability and durability according to the data, and on the basis of the strength, workability and durability prediction models, establishing a prediction model with minimum cost as a target, and the mathematical optimization model of the concrete mix proportion is constrained by meeting various performance requirements. According to the method disclosed by the invention, the deep learning prediction model is constructed on the basis of the use amount of the existing concrete raw materials, the performance of the raw materials and the corresponding strength, workability and durability by combining the characteristics of the concrete mix proportion and the corresponding concrete strength, workability and durability characteristics, and the influence of the raw material properties on the concrete performance is fully considered; and besides the strength, the workability and durability of the concrete are considered as constraints, so that the method is more suitable for practical application.
本发明属于混凝土配合比优化技术领域，并具体公开了一种多性能控制的混凝土配合比优化方法。包括：收集若干组混凝土配合比实际生产数据，根据上述数据分别建立混凝土强度、工作性和耐久性的深度学习预测模型，在上述强度、工作性、耐久性预测模型的基础上，建立以成本最小为目标，以满足各项性能要求为约束的混凝土配合比数学优化模型。本发明本结合混凝土配合比自身的特征及其对应混凝土强度、工作性、耐久性特点，基于现有混凝土原料的用量、原料的性能以及其对应的强度、工作性、耐久性去构建深度学习预测模型，充分考虑原料性质对混凝土性能的影响，预测结果更准确，除强度外，还考虑混凝土的工作性和耐久性作为约束，更贴合实际应用。
Multi-performance control concrete mix proportion optimization method
The invention belongs to the technical field of concrete mix proportion optimization, and particularly discloses a multi-performance control concrete mix proportion optimization method. Comprising the following steps: collecting a plurality of groups of concrete mix proportion actual production data, respectively establishing deep learning prediction models of concrete strength, workability and durability according to the data, and on the basis of the strength, workability and durability prediction models, establishing a prediction model with minimum cost as a target, and the mathematical optimization model of the concrete mix proportion is constrained by meeting various performance requirements. According to the method disclosed by the invention, the deep learning prediction model is constructed on the basis of the use amount of the existing concrete raw materials, the performance of the raw materials and the corresponding strength, workability and durability by combining the characteristics of the concrete mix proportion and the corresponding concrete strength, workability and durability characteristics, and the influence of the raw material properties on the concrete performance is fully considered; and besides the strength, the workability and durability of the concrete are considered as constraints, so that the method is more suitable for practical application.
本发明属于混凝土配合比优化技术领域，并具体公开了一种多性能控制的混凝土配合比优化方法。包括：收集若干组混凝土配合比实际生产数据，根据上述数据分别建立混凝土强度、工作性和耐久性的深度学习预测模型，在上述强度、工作性、耐久性预测模型的基础上，建立以成本最小为目标，以满足各项性能要求为约束的混凝土配合比数学优化模型。本发明本结合混凝土配合比自身的特征及其对应混凝土强度、工作性、耐久性特点，基于现有混凝土原料的用量、原料的性能以及其对应的强度、工作性、耐久性去构建深度学习预测模型，充分考虑原料性质对混凝土性能的影响，预测结果更准确，除强度外，还考虑混凝土的工作性和耐久性作为约束，更贴合实际应用。
Multi-performance control concrete mix proportion optimization method
一种多性能控制的混凝土配合比优化方法
ZHOU LI (author) / CHEN GUOHUI (author) / YAN LIEXIANG (author) / FAN YANGCHUN (author)
2022-04-22
Patent
Electronic Resource
Chinese
Multi-target control special concrete mix proportion design method
| European Patent Office | 2023
Anti-crack concrete and proportion optimization method thereof
| European Patent Office | 2024
| British Library Conference Proceedings | 1997