Abstract
The booming computational thinking and deep learning make it possible to construct agile, efficient, and robust deep learning-driven decision-making support engine for the operation of container terminal handling systems (CTHSs). Within the conceptual framework of computational logistics, an attention mechanism oriented hybrid convolutional neural network and recurrent neural network deep learning architecture (AMO-HCR-DLA) is proposed technically to predict the container terminal liner handling conditions that mainly include liner handling time (LHT) and total working time of quay crane farm (TWT-QCF) for a calling liner. Consequently, the container terminal oriented logistics generalized computation (CTO-LGC) automation and intelligence are established tentatively by AMO-HCR-DLA. A typical regional container terminal hub of China is selected to design, implement, execute, and evaluate the AMO-HCR-DLA with the actual production data. In the case of severe vibration of LHT and TWT-QCF, while forecasting the handling conditions of 210 ships based on the CTO-LGC running log of four years, the forecasting error of LHT within one hour is more than 97% and that of TWT-QCF within six hours accounts for 89.405%. When predicting the operating conditions of 300 liners by the log of five years, the forecasting deviation of LHT within one hour is more than striking 99% and that of TWT-QCF within six hours reaches up to 94.010% as well. All are far superior to the predicting outcomes by the classical algorithms of machine learning and deep learning. Hence, the AMO-HCR-DLA shows excellent performance for the prediction of CTHS with the low and stable computational consuming. It also demonstrates the feasibility, credibility, and realizability of the computing architecture and design paradigm of AMO-HCR-DLA preliminarily.
Highlights
Deep learning has obtained vigorous development based on the promotion of big data, computing capacity, artificial neural network (ANN), and deep neural network (DNN), especially in the field of computer vision [1,2,3], image classification [4, 5], speech recognition [6, 7], natural language processing [8, 9], clinical decision support [10, 11], smart manufacturing [12, 13], and so on
E container terminals are the backbone and branch hubs of the global transportation network and modern intelligent logistics, which make a crucial effect on the operation and improvement of e-commerce and supply chain all over the world [16]. e container terminal handling systems (CTHS) are the typical representation of complex logistics systems (CLS), and its job planning, task scheduling, and resource allocation all are of representative nondeterministic polynomial complete problems [17]. ose are the big challenges for the traditional methods of operations research, such as mathematical programming [18], intelligent optimization [19], and system simulation [20]
A regional and traditional container terminal hub in China is the target object for the demonstration of the AMO-HCR-DLA. ere are five deep water berths along terminal quayside, and ten quay cranes with the four different activation parameters and handling specifications are deployed along terminal quayside. e annual container throughput of terminal is about two million twenty-foot equivalent units (TEUs)
Summary
Deep learning has obtained vigorous development based on the promotion of big data, computing capacity, artificial neural network (ANN), and deep neural network (DNN), especially in the field of computer vision [1,2,3], image classification [4, 5], speech recognition [6, 7], natural language processing [8, 9], clinical decision support [10, 11], smart manufacturing [12, 13], and so on. An attention mechanism oriented hybrid CNN-RNN deep learning architecture (AMO-HCR-DLA) is proposed tentatively to predict the container terminal liner handling conditions that mainly include two aspects: liner handling time (LHT) and total working time of quay crane farm for a calling liner (TWT-QCF) Both are expected to establish a service target time-consuming baseline preliminary sketch for the guidance of the job planning, task scheduling, and resource allocation at container terminals. The container terminal oriented logistics generalized computing engine farms microarchitecture (CTO-LGC-EFM) makes a crucial effect on the design, implementation, planning, scheduling, execution, upgrading, and reconstruction of CTHS. The QC, YC, CRS, and ECFL construct a hybrid CTO-LGC architecture, which is very similar to the collaborative computing architecture of central processing unit (CPU), general purpose graphics processing unit (GPGPU), and synergistic processing element (SPE) in computer science and engineering It is the combination of serial and parallel and is the hybrid of asynchronous and synchronous as well. The preemption is usually not possible in the berth scheduler, but the LGCCPU preemption is feasible and frequent during the CTOLGC. e above CTO-LGC rules affect two operational indicators of LHT and TWT-QCF in turn
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
