Research On Ship Operating Time Prediction Model In Container Port Berth Planning

Berths are an important resource for ports,and a reasonable and effective ship berthing plan is closely related to increasing the berth utilization rate,increasing port throughput,and thus improving the economic benefits of the port.Because the berth plan must be prior to the ship's arrival time and the ship's loading and unloading operation plan,and at the same time subject to the ship's arrival time and loading and unloading operation process,the formulation of an effective and reasonable berth plan needs to be based on the ship's arrival time and predict the loading andunloading The operation time is completed on the basis of the operation time.Therefore,the research on the container ship berth plan focusing on the prediction of the operation time of the container ship in port has very important practical significance and application value.This article first analyzes the influencing factors of container ship operations in port,and finds that the loading and unloading process is greatly affected by weather,ship type,the number of containers to be loaded and unloaded,the number of assigned shore bridges,the efficiency of shore bridge loading and unloading,and berthing time For example,the wind force will affect the swing amplitude of the shore bridge spreader,resulting in the reduction of the load and unload efficiency of the shore bridge.These influencing factors have a non-linear relationship with the operation time of ships and ports.Therefore,it is necessary to find an effective prediction method to predict the operation time of loading and unloading operations in ports.Then analyzes the research status and methods of related issues at home and abroad.The traditional method uses the amount of containers to be loaded and unloaded divided by the efficiency of shore bridge loading and' unloading to predict the operating time.This method has the disadvantages of low prediction accuracy and poor flexibility.In terms of solving nonlinear relationship problems,BP neural network has a strong modeling ability,so BP neural network is selected to build a container ship port operation time prediction model,and the factors that affect the operation time are used as the model input,and the container ship port operation Time is used as the output of the model.In the process of model construction,it is found that the BP neural network that uses the gradient descent method for training and learning has the problem of easy to fall into the local minimum and the convergence speed is slow.In order to overcome this problem of the BP neural network,this paper proposes to use genetic algorithm and The LM algorithm optimizes the BP neural network to obtain the GA-BP neural network container ship port operation time prediction model.Using Tianjin port ship and port operation data,train and learn on container ship port operation time prediction model based on BP neural network and GA-BP neural network container ship port operation time prediction model,and verify and analyze the model with verification data set.By comparing and analyzing the predicted values of loading and unloading operations using traditional operation time prediction methods,the prediction model based on BP neural network and the prediction model of GA-BP neural network,the average relative error between the predicted value and the actual value is 6.5%,3.4%,1.2%,which leads to the conclusion that the optimized GA-BP neural network container ship port operation time prediction model has higher prediction accuracy.The ship operation time predicted by the traditional method and GA-BP prediction model is applied to the berth plan.It is found that the berth plan model based on the predicted value of the traditional method has the phenomenon of the ship "pushing dynamics" and the berth resource idle time is long.The berth plan made by the prediction value of GA-BP neural network avoids the phenomenon of ship "pushing dynamics" and long idle time of berth resources,and achieves the effect of improving the berth utilization rate.The proposed method has important guidance for the formulation of berth plans significance.