摘要
碾压质量评价是大坝智慧化施工的关键技术之一,对坝体安全稳定性具有重要影响,而目前对其评价模型和方法尚未达成一致认识。以新疆阿尔塔什面板堆石坝为依托工程,结合现场填筑碾压监测数据和试坑检测试验数据,提出基于遗传算法和粒子群算法混合优化的BP神经网络算法(GA-PSO-BP)的爆破料压实质量评价模型。通过与BP、GA-BP、PSO-BP 3种预测模型进行对比分析,证明该模型的精度和优越性。结果表明:提出的基于GA-PSO-BP模型收敛速度更快、性能更好,且基于GA-PSO混合优化后的BP神经网络爆破料压实质量评价模型精度相对较高,可用于与新疆阿尔塔什混凝土面板堆石坝类似工况的压实质量评价。
Compaction quality evaluation is one of the key technologies of dam intelligent construction,which has an important impact on the safety and stability of dam body.However,there is no consensus on its evaluation method at present.In this paper,based on the Artash concrete face rockfill dam in Xinjiang and combined with the results of field test,the BP neural network algorithm based on genetic algorithm and particle swarm optimization(GA-PSO-BP)was proposed.The accuracy and superiority of the model were proved by comparing with BP model,GA-BP model and PSO-BP model.The result shows that the GA-PSO-BP model,proposed by the paper,has faster convergence speed and better performance.And,the BP neural network compaction quality evaluation model,based on GA-PSO hybrid optimization,has relatively higher accuracy,which can be used to evaluate the compaction quality of Xinjiang Artash concrete face rockfill dam under similar working conditions.
作者
宿辉
孙熇远
赵宇飞
刘世伟
赵翠东
杨宇
SU Hui;SUN Heyuan;ZHAO Yufei;LIU Shiwei;ZHAO Cuidong;YANG Yu(Hebei Key Laboratory of Intelligent Water Conservancy,Handan 056006,China;School of Water Conservancy and Hydropower Hebei University of Engineering,Handan 056006,China;China Institute of Water Resources and Hydropower Research,Beijing 100044,China)
出处
《人民黄河》
CAS
北大核心
2023年第6期137-142,146,共7页
Yellow River
基金
河北省自然科学基金资助项目(E2020402087)
河北省高等学校科学技术研究项目(QN2021030)。
关键词
堆石坝
爆破料
压实质量
BP神经网络
粒子群算法
遗传算法
rockfill dam
blasting material
compaction quality
BP neural network
particle swarm algorithm
genetic algorithm
