基于BP神经网络的散装铁精矿液化风险评估模型

BP Neural Network Model for Evaluating the Liquefaction Risk of Iron Ore Concentrates

在海上运输过程中,散装铁精矿等固体散货物存在液化可能性,需对此进行有效评估。引入加速度作为影响散装铁精矿液化形成的参量,利用MATLAB程序构建基于BP神经网络算法的散装铁精矿液化风险等级多因素综合评判模型,预测细粒含量为4.8%的铁精矿在不同含水率和加速度条件下的液化风险等级,并与铁精矿室内模型进行对比实验。结果表明:铁精矿液化风险评估等级均处于Ⅳ及以上,预测结果与实验结果一致。该液化风险评估模型能够有效预测散装铁精矿在海上运输过程中液化的可能性,为确保固体散货物的海运安全提供参考。

To effectively evaluate the possibility of liquefaction of iron ore concentrates during marine transportation,the acceleration parameter was introduced to characterize the comprehensive influence of external marine environmental changes on the formation of solid bulk cargoes liquefaction,and the multi-factor comprehensive evaluation model for the liquefaction risk level of iron ore concentrates is constructed based on the MATLAB program using the BP neural network algorithm.The proposed method is used to predict the iron ore concentrates with the fine particles content was 4.8%under different moisture content and acceleration conditions.The model results are compared to the experimental results from the laboratory model test of iron ore concentrates.The results show that the model prediction results are consistent with the laboratory model test results.For iron ore concentrates that undergoing liquefaction,the model evaluation results are all at zone Ⅳ and above.This liquefaction risk assessment model could effectively predict the possibility of liquefaction of iron ore concentrates during ocean shipping,which could provide a reference for the water traffic management department to ensure the transportation safety of solid bulk cargoes.