Early warning of safety risks in construction of recycling and utilization of reinforced concrete shelving structure plant
The purpose of this paper is to ensure structural safety during the construction of a reinforced concrete shelving structure plant.Based on sorting out the main influencing factors and controlling essentials of the construction safety risk of the regeneration of reinforced concrete shelving structure plant,this paper constructed the early warning index system of the construction safety risk of regeneration through the analysis of the construction safety simulation and monitoring content.The index system includes 5 first-level indicators,16 second-level indicators,and 45 quantitative indicators.After a comparison of early warning methods,this paper constructed a safety risk early warning model for the recycling and utilization of reinforced concrete shelving structure plants based on the improved Generalized Regression Neural Network(GRNN)and took several engineering projects as examples.First,we reduced the dimension of the sample data(data standardization processing)and analyzed the accuracy of the model.Through the iterative analysis of Quantum Particle Swarm Optimization(QPSO),we determined the optimal smoothing factor=0.08(the corresponding RMSE=0.0397,and the best Spread reference value was 0.8)and the optimal model.Finally,the sample data was imported into MATLAB R2014b,and then the trained network was used to give early warning to the test samples.The constructed model in this paper obtains single-factor risk and multi-factor risk early warning after data dimensionality reduction(feature principal element extraction).Compared with the actual situation,we can see that the single-factor security risk early warning process and results are consistent with the multi-factor security risk early warning process and results.Both of them are consistent with the actual safety risk state of the site,thus verifying the reliability of the model.The results show that the model is an organic combination of Kernel Principal Component Analysis(KPCA)-QPSO-GRNN,which provides a new way for quantitative research on the construction safety risk warning of the regeneration of reinforced concrete shelving structure plants.
safety engineeringshelving structureregeneration and utilizationconstruction safetyrisk early warning
万方数据
维普
