Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in th...Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many areas.In this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,China.The two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural Network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural Network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction results.In addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.展开更多
Construction site layout planning(CSLP)involves strategically placing various facilities to optimize a project.However,real construction sites are complex,making it challenging to consider all construction activities ...Construction site layout planning(CSLP)involves strategically placing various facilities to optimize a project.However,real construction sites are complex,making it challenging to consider all construction activities and facilities comprehensively.Addressing multi-objective layout optimization is crucial for CSLP.Previous optimization results often lacked precision,imposed stringent boundary constraints,and had limited applications in prefabricated construction.Traditional heuristic algorithms still require improvements in region search strategies and computational efficiency when tackling multi-objective optimization problems.This paper optimizes the prefabricated component construction site layout planning(PCCSLP)by treating construction efficiency and safety risk as objectives within a multi-objective CSLP model.A novel heuristic algorithm,the Hybrid Multi-Strategy Improvement Dung Beetle Optimizer(HMSIDBO),was applied to solve the model due to its balanced capabilities in global exploration and local development.The practicality and effectiveness of this approach were validated through a case study in prefabricated residential construction.The research findings indicate that the HMSIDBO-PCCSLP optimization scheme improved each objective by 18%to 75%compared to the original layout.Compared to Genetic Algorithm(GA),the HMSIDBO demonstrates significantly faster computational speed and higher resolution accuracy.Additionally,in comparison with the Dung Beetle Optimizer(DBO),Particle Swarm Optimization(PSO),and Whale Optimization Algorithm(WOA),HMSIDBO exhibits superior iterative speed and an enhanced ability for global exploration.This paper completes the framework from data collection to multi-objective optimization in-site layout,laying the foundation for implementing intelligent construction site layout practices.展开更多
基金supported by the National Natural Science Foundation of China [grant numbers 42088101 and 42375048]。
文摘Due to the lack of accurate data and complex parameterization,the prediction of groundwater depth is a chal-lenge for numerical models.Machine learning can effectively solve this issue and has been proven useful in the prediction of groundwater depth in many areas.In this study,two new models are applied to the prediction of groundwater depth in the Ningxia area,China.The two models combine the improved dung beetle optimizer(DBO)algorithm with two deep learning models:The Multi-head Attention-Convolution Neural Network-Long Short Term Memory networks(MH-CNN-LSTM)and the Multi-head Attention-Convolution Neural Network-Gated Recurrent Unit(MH-CNN-GRU).The models with DBO show better prediction performance,with larger R(correlation coefficient),RPD(residual prediction deviation),and lower RMSE(root-mean-square error).Com-pared with the models with the original DBO,the R and RPD of models with the improved DBO increase by over 1.5%,and the RMSE decreases by over 1.8%,indicating better prediction results.In addition,compared with the multiple linear regression model,a traditional statistical model,deep learning models have better prediction performance.
基金supported by the National Key R&D projects(Grant No.2018YFC0704301)Science and Technology Project of Wuhan Urban and Rural Construction Bureau,China(201943)+2 种基金Research on theory and application of prefabricated building construction management(20201h0439)Wuhan Modou Construction Consulting Co.,Ltd.(20201h0414)Preliminary Study on the Preparation of the 14th Five-Year Plan for Housing and Urban-Rural Development in Hubei Province,China(20202s002).
文摘Construction site layout planning(CSLP)involves strategically placing various facilities to optimize a project.However,real construction sites are complex,making it challenging to consider all construction activities and facilities comprehensively.Addressing multi-objective layout optimization is crucial for CSLP.Previous optimization results often lacked precision,imposed stringent boundary constraints,and had limited applications in prefabricated construction.Traditional heuristic algorithms still require improvements in region search strategies and computational efficiency when tackling multi-objective optimization problems.This paper optimizes the prefabricated component construction site layout planning(PCCSLP)by treating construction efficiency and safety risk as objectives within a multi-objective CSLP model.A novel heuristic algorithm,the Hybrid Multi-Strategy Improvement Dung Beetle Optimizer(HMSIDBO),was applied to solve the model due to its balanced capabilities in global exploration and local development.The practicality and effectiveness of this approach were validated through a case study in prefabricated residential construction.The research findings indicate that the HMSIDBO-PCCSLP optimization scheme improved each objective by 18%to 75%compared to the original layout.Compared to Genetic Algorithm(GA),the HMSIDBO demonstrates significantly faster computational speed and higher resolution accuracy.Additionally,in comparison with the Dung Beetle Optimizer(DBO),Particle Swarm Optimization(PSO),and Whale Optimization Algorithm(WOA),HMSIDBO exhibits superior iterative speed and an enhanced ability for global exploration.This paper completes the framework from data collection to multi-objective optimization in-site layout,laying the foundation for implementing intelligent construction site layout practices.
