Yinping Gao

This study proposes a ship scheduling model that considers a comprehensive set of factors, such as ship types, ship routes, and berthing criteria. This study designs a customized heuristic algorithm based on the realistic scheduling rules to minimize all ships’ waiting time. This study develops an intelligent scheduling system to replace traditional manual scheduling method.

The steady growth of container volume and aggressive shipping alliances have intensified competition among terminals. With the rapid development and application of modern information and communication technology, automation is a great way to promote terminals’ sustainable development. The objectives of this study are to analyze the key factors influencing automation transformation and provide theoretical guidelines for implementing automation transformation. Based on the literature review, the main factors influencing the automation transformation of container terminals are characterized and analyzed. They are divided into four categories: technical feasibility, external promotion, self-constraints, and goals/demand. Thereafter, a novel multi-source data fusion method, the Dempster–Shafer evidence interval method (DSIM) based on Dempster–Shafer evidence theory and interval value, is proposed to fuse conflicting and uncertain opinions among experts. This method is effective for expert opinion elicitation. Using DSIM, the key factors’ relative importance and their relationship are examined based on the opinions of experts in China. The results show that technical feasibility is the most important factor category in the foundation of automation transformation. Finally, a generalized planning framework for constructing automation transformation schemes is established, providing references and suggestions for terminals’ decision-makers.

The dispatching of automated guided vehicles (AGVs) is essential for efficient horizontal transportation at automated container terminals. Effective planning of AGV transportation can reduce equipment energy consumption and shorten task completion time. Multiple AGVs transport containers between storage blocks and vessels, which can be regarded as the supply sides and demand points of containers. To meet the requirements of shipment in terms of timely and high-efficient delivery, multiple AGVs should be dispatched to deliver containers, which includes assigning tasks and selecting paths. A contract net protocol (CNP) is employed for task assignment in a multiagent system, while machine learning provides a logical alternative, such as Q-learning (QL), for complex path planning. In this study, mathematical models for multi-AGV dispatching are established, and a QL-CNP algorithm is proposed to tackle the multi-AGV dispatching problem (MADP). The distribution of traffic load is balanced for multiple AGVs performing tasks in the road network. The proposed model is validated using a Gurobi solver with a small experiment. Then, QL-CNP is used to conduct experiments with different sizes. The other algorithms, including Dijkstra, GA, and PSO, are also compared with the QL-CNP algorithm. The experimental results demonstrate the superiority of the proposed QL-CNP when addressing the MADP.

With the rapid growth of containers and scarce of land, the underground container logistics system (UCLS) presents a logical alternative for container terminals to better protect the environment and relieve traffic pressure. The operating efficiency of container terminals is one of the competitive edges over other terminals, which requires UCLS to be well integrated with the handling process of the storage yard. In UCLS, yard trucks (YTs) serve different handling points dynamically instead of one fixed handling point, and yard cranes (YCs) perform loading and unloading simultaneously. To minimize the total time of handling all containers in UCLS, the mixed integer programming problem is described and solved using an adaptive genetic algorithm (AGA). The convergence speed and accuracy of AGA are demonstrated by comparison with conventional genetic algorithm (GA). Additionally, AGA and CPLEX are compared with different scale cases. Experimental results show that the proposed algorithm is superior to CPLEX in resulted solutions and calculation time. A sensitivity analysis is provided to obtain reasonable numbers of YTs for scheduling between handling points and the storage yard in UCLS.

Digital twin (DT), machine learning, and industrial Internet of things (IIoT) provide great potential for the transformation of the container terminal from automation to intelligence. The production control in the loading and unloading process of automated container terminals (ACTs) involves complex situations, which puts forward high requirements for efficiency and safety. To realize the real-time optimization and security of the ACT, a framework integrating DT with the AdaBoost algorithm is proposed in this study. The framework is mainly composed of physical space, a data service platform, and virtual space, in which the twin space and service system constitute virtual space. In the proposed framework, a multidimensional and multiscale DT model in twin space is first built through a 3D MAX and U3D technology. Second, we introduce a random forest and XGBoost to compare with AdaBoost to select the best algorithm to train and optimize the DT mechanism model. Third, the experimental results show that the AdaBoost algorithm is better than others by comparing the performance indexes of model accuracy, root mean square error, interpretable variance, and fitting error. In addition, we implement empirical experiments by different scales to further evaluate the proposed framework. The experimental results show that the mode of the DT-based terminal operation has higher loading and unloading efficiency than that of the conventional terminal operation, increasing by 23.34% and 31.46% in small-scale and large-scale problems, respectively. Moreover, the visualization service provided by the DT system can monitor the status of automation equipment in real time to ensure the safety of operation.

The effective forecast of container volumes can provide decision support for port scheduling and operating. In this work, by deep learning the historical dataset, the long short-term memory (LSTM) recurrent neural network (RNN) is used to predict daily volumes of containers which will enter the storage yard. The raw dataset of daily container volumes in a certain port is chosen as the training set and preprocessed with box plot. Then the LSTM model is established with Python and Tensorflow framework. The comparison between LSTM and other prediction methods like ARIMA model and BP neural network is also provided in this study, and the prediction gap of LSTM is lower than other methods. It is promising that the proposed LSTM is helpful to predict the daily volumes of containers.

With the rapid development of world economy and trade and the continuous construction of green port, automated container terminal (ACT) has increasingly become the direction of future development. Layout design is the premise of ACT construction, which has an at least 50-year influence on the terminal. Therefore, this paper hopes to analyze and design the typical ACT layout to achieve sustainable development of the port. Firstly, a conceptual model is presented considering the interaction between different areas within the ACT when the width and length of the terminal are fixed. To select the optimal layout to achieve the goal of the green terminal, a novel mathematical model is established based on the energy consumption during cycle operation of various devices which can estimate the total carbon emission of an ACT over a period and is suitable for designing period. Then, with the developed model, an ACT in East China was taken as a case study. Finally, according to various analysis of the data results, the layout suggestion considering the sustainable development of the port is given.