| It is the key to ensure the safe and stable operation of the rockfill dam to control the rolling construction quality during the rolling process.At present,the methods to control the rolling quality at the construction site include: controlling the rolling parameters in the event and sampling inspection in the test pit afterwards.The former determines rolling parameters through rolling test,which is time-consuming and laborious;The latter will not only destroy the dam materials after compaction,but also have hysteresis and randomness in the test results.In view of the shortcomings of the above methods,this thesis establishes the compaction process model of rockfill dam materials through the particle flow code PFC(Particle Flow Code)based on the Discrete Element Method(DEM),and studies and analyzes the vibration compaction mechanism of rockfill dam materials and the impact of compaction parameters on the compaction effect of rockfill dam materials;At the same time,based on the improved neural network algorithm,the compaction quality evaluation model of the concrete faced rockfill dam is established,which provides a theoretical basis for the compaction quality control during the rolling construction of the rockfill dam.The main research results of this thesis are as follows:(1)The modeling method of rockfill dam material rolling process based on PFC is proposed.Firstly,irregular polygon dam materials are generated by randomly generating polygon algorithm to approximate the irregular shape of rockfill dam materials;Secondly,based on the theory of compaction capacity coefficient,the calculation formula and simulation method of rolling load of roller in two-dimensional environment are determined;Finally,based on the discrete element simulation software PFC,the vibration compaction model of concrete faced rockfill dam material is established to study and analyze the vibration compaction mechanism and the change rule of microstructure of dam material.(2)In view of the layering phenomenon of rockfill dam materials during unloading at the construction site,the gravity settlement method is adopted to simulate the unloading process of dam materials through PFC,and a meso simulation model of the rolling process of rockfill dam materials is established by comprehensively considering the layering characteristics of rockfill materials.Based on this method,combined with the actual rolling test,the influence of rolling parameters on the compaction effect of dam materials is studied and analyzed.The results show that the faster the rolling speed is,the worse the compaction effect of dam materials is;The compaction quality of dam materials will be better if the rolling load is appropriately increased.(3)The evaluation model of compaction quality of rockfill dam is established based on artificial neural network algorithm and actual project site data.At the same time,in order to improve the performance of the model,intelligent optimization algorithm is introduced to optimize the neural network model.Compared with the other three commonly used models,the results show that the proposed model has higher prediction accuracy and generalization performance. |