摘要
考虑到抗压强度对混凝土设计的重要影响,本文提出了改进麻雀搜索算法(ISSA)和门控循环单元(GRU)结合的ISSA-GRU预测模型,实现对高性能混凝土抗压强度的精准预测。对收集的数据集进行归一化处理后,利用基于光谱-理化值共生距离(SPXY)法对数据集进行训练集和测试集划分,采用GRU对高性能混凝土抗压强度进行回归预测,并通过引入动态惯性权重的ISSA,加强对GRU网络参数的寻优效率。结果表明,在使用相同数据样本的情况下,将ISSA-GRU模型与长短期记忆(LSTM)网络、核极限学习机(KELM)和支持向量回归(SVR)模型进行比较,其均方根误差RMSE分别降低了9.3%、37.5%、33.5%,平均绝对误差MAE分别降低了13.5%、38.5%、41.7%。同时,研究了训练集数据量和输入变量对模型预测性能的影响,研究结果表明,所提出的模型能高效寻找超参数,具有较高的预测精度和较好的适应性,为多样化原材料和混凝土特定性能的发展提供可行参考。
Considering the important influence of compressive strength on concrete design,an ISSA-GRU prediction model combining improved sparrow search algorithm(ISSA)and gate recurrent unit(GRU)was proposed to achieve accurate prediction of compressive strength of high-performance concrete.After normalizing the collected data set,the data set was divided into training set and testing set based on spectral-physicochemical value symbiotic distance(SPXY)method,GRU was used to predict the compressive strength of high-performance concrete,and enhances optimization efficiency of GRU network parameters by introducing ISSA with dynamic inertia weight.The results show that,in the case of using same data samples,the ISSA-GRU model is compared with the long short-term memory network(LSTM),kernel extreme learning machine(KELM)and support vector regression(SVR)models.The root mean square error(RMSE)is reduced by 9.3%,37.5%,and 33.5%,respectively,and the mean absolute error(MAE)is reduced by 13.5%,38.5%,and 41.7%,respectively.At the same time,the influences of the amount of training set data and input variables on prediction performance of the model were studied.The results show that the proposed model is efficient in finding GRU parameters,has high prediction accuracy and good adaptability,and provides a feasible reference for the development of diverse raw materials and specific properties of concrete.
作者
段妹玲
张单
袁锦虎
孙爱军
强晟
DUAN Meiling;ZHANG Dan;YUAN Jinhu;SUN Aijun;QIANG Sheng(College of Water Resources and Hydropower,Hohai University,Nanjing 210098,China;Power China Huadong Engineering Corporation Limited,Hangzhou 311122,China;Jiangxi Poyang Lake Water Conservancy Project Construction Office,Nanchang 330046,China;Yuyao Water Resources Bureau,Ningbo 315402,China)
出处
《硅酸盐通报》
CAS
北大核心
2023年第7期2392-2400,共9页
Bulletin of the Chinese Ceramic Society
基金
国家自然科学基金(52079049)
宁波市水利科技项目(NSKA202343)。
关键词
高性能混凝土
门控循环单元
动态惯性权重
麻雀搜索算法
深度学习
强度预测
high-performance concrete
gate recurrent unit
dynamic inertia weight
sparrow search algorithm
deep learning
strength prediction
