Bulk Port Research Articles

Hourly PM2.5 concentration prediction for dry bulk port clusters considering spatiotemporal correlation: A novel deep learning blending ensemble model

Accurate prediction of PM2.5 concentrations in ports is crucial for authorities to combat ambient air pollution effectively and protect the health of port staff. However, in port clusters formed by multiple neighboring ports, we encountered several challenges owing to the impact of unique meteorological conditions, potential correlation between PM2.5 levels in neighboring ports, and coupling influence of background pollutants in city zones. Therefore, considering the spatiotemporal correlation among the factors influencing PM2.5 concentration variations within the harbor cluster, we developed a novel blending ensemble deep learning model. The proposed model combined the strengths of four deep learning architectures: graph convolutional networks (GCN), long short-term memory networks (LSTM), residual neural networks (ResNet), and convolutional neural networks (CNN). GCN, LSTM, and ResNet served as the base models aimed at capturing the spatial correlation of PM2.5 concentrations in neighboring ports, the potential long-term dependence of meteorological factors and PM2.5 concentrations, and the effects of urban ambient air pollutants, respectively. Following the blending ensemble technique, the prediction outcomes of three base models were used as the input data for the meta-model CNN, which employs the blending ensemble technique to produce the final prediction results. Based on actual data obtained from 18 ports in Nanjing, the proposed model was compared and analyzed for its prediction performance against six state-of-the-art models. The findings revealed that the proposed model provided more accurate predictions. It reduced mean absolute error (MAE) by 10.59 %–20.00 %, reduced root mean square error (RMSE) by 13.22 %–17.11 %, improved coefficient of determination (R2) by 10 %–35.38 %, and improved accuracy (ACC) by 3.48 %–7.08 %. Additionally, the contribution of each component to the prediction performance of the proposed model was measured using a systematic ablation study. The results demonstrated that the GCN model exerted the most substantial influence on the prediction performance of the GCN-LSTM-ResNet model, followed by the LSTM model. The influence of urban background pollutants can significantly enhance the generalizability of the complete model. Moreover, a comparison with three blended ensemble models incorporating any two base models demonstrated that the GCN-LSTM-ResNet model exhibited superior prediction performance and was particularly excellent in predicting the occurrence of high-concentration events. Specifically, the GCN-LSTM-ResNet model improved MAE and RMSE by at least 12.3% and 9.2%, respectively, but reduced R2 and ACC by 26.1% and 6.8%, respectively. The proposed model provided reliable PM2.5 concentration prediction outcomes and decision support for air quality management strategies in dry bulk port clusters.

High-Level Feature Fusion Deep Learning Model for Fault Detection in Handling Equipment in Dry Bulk Ports

The flexibility of handling equipment in dry bulk ports is poor, and frequent equipment fault induced by the high-load and high-power working conditions greatly impacts the overall port handling operations, making accurate fault detection play an important role in improving the efficiency and stability of dry bulk port operations. However, as we know, most fault detection methods for port handling equipment depend heavily on monitoring sensor data, which is not applicable in the dry bulk port due to high configuration and maintenance cost, as well as the high false alarm rate of monitoring sensors caused by strong background noise. To solve the problem, this study proposes a High-Level Feature Fusion Deep Learning Model, which uses different deep learning sub-models to extract features of structured and unstructured data. It fuses the extracted feature vectors to achieve fault detection in the handling equipment, establishing the mapping relationship between the fault (e.g., waiting for the pre-loading process, equipment fault, and others) and multi-source heterogeneous operation and maintenance data for the handling equipment, including reclaimers, belt conveyors, dumpers, and ship loaders. To verify the effectiveness of the proposed method, the actual data of a coal port in Northern China is employed as an example. The results show the deep learning model can achieve high prediction accuracy (over 86%) with high efficiency (0.5 s for each sample), which provides decision support for the fault detection in dry bulk port handling equipment.

Predicting dust pollution from dry bulk ports in coastal cities: A hybrid approach based on data decomposition and deep learning

Dust pollution from storage and handling of materials in dry bulk ports seriously affects air quality and public health in coastal cities. Accurate prediction of dust pollution helps identify risks early and take preventive measures. However, there remain challenges in solving non-stationary time series and selecting relevant features. Besides, existing studies rarely consider impacts of port operations on dust pollution. Therefore, a hybrid approach based on data decomposition and deep learning is proposed to predict dust pollution from dry bulk ports. Port operational data is specially integrated into input features. A secondary decomposition and recombination (SDR) strategy is presented to reduce data non-stationarity. A dual-stage attention-based sequence-to-sequence (DA-Seq2Seq) model is employed to adaptively select the most relevant features at each time step, as well as capture long-term temporal dependencies. This approach is compared with baseline models on a dataset from a dry bulk port in northern China. The results reveal the advantages of SDR strategy and integrating operational data and show that this approach has higher accuracy than baseline models. The proposed approach can mitigate adverse effects of dust pollution from dry bulk ports on urban residents and help port authorities control dust pollution.

A model-driven decision support system for the storage location assignment problem in bulk ports

Yard storage management involves tactical and operational decisions affecting bulk port productivity. The main challenge is to ensure that bulk materials are available and stored according to physical and managerial constraints while minimizing storage space utilization. This article studies a new variant of the storage location assignment problem by considering contamination constraints for bulk materials. The problem is inspired by a real case study of Africa's largest fertilizer hub port. To tackle the problem, a model-driven decision support system, optimizing the storage space while satisfying vessels' demands and avoiding contamination from overlapping bulk materials, is developed. A mixed-integer linear programming model is formulated, and an efficient rolling-horizon heuristic is investigated as a solution approach. Extensive numerical experiments are performed, and the results confirm the efficiency of this model-driven support system from both theoretical and practical points of view.

The Role of Digital Transformation On The Performance of Indonesia's Biggest Dry Bulk Port

This study aims to analyze the successful implementation of digital transformation in management and organizational performance and how Information Technology integrates organizations to provide professional services with added value for customers and has competitiveness compared to competitors—analysis using quantitative methods. By distributing questionnaires to 135 respondents from a total population of 204 employees working at the company, the data collected was then processed with PLS-SEM to establish a causal relationship. The research findings explain that digital competency positively and significantly influences organizational performance. Management support has a positive and significant influence on organizational performance. Management support has a positive and considerable effect on digital strategy, and digital strategy has a positive and significant impact on organizational performance. The implications of the findings prove that the better the digital competency, the higher the management support, and the better the digital strategy can improve organizational performance. This research cannot only analyze and calculate the impact of digital competency, management support, and organizational performance at Krakatau International Port.

An improved deep reinforcement learning approach: A case study for optimisation of berth and yard scheduling for bulk cargo terminal

The cornerstone of port production operations is ship handling, necessitating judicious allocation of diverse production resources to enhance the efficiency of loading and unloading operations. This paper introduces an optimisation method based on deep reinforcement learning to schedule berths and yards at a bulk cargo terminal. A Markov Decision Process model is formulated by analysing scheduling processes and unloading operations in bulk port imports business. The study presents an enhanced reinforcement learning algorithm called PS-D3QN (Prioritised Experience Replay and Softmax strategy-based Dueling Double Deep Q-Network), amalgamating the strengths of the Double DQN and Dueling DQN algorithms. The proposed solution is evaluated using actual port data and benchmarked against the other two algorithms mentioned in this paper. The numerical experiments and comparative analysis substantiate that the PS-D3QN algorithm significantly enhances the efficiency of berth and yard scheduling in bulk terminals, reduces the cost of port operation, and eliminates errors associated with manual scheduling. The algorithm presented in this paper can be tailored to address scheduling issues in the fields of production and manufacturing with suitable adjustments, including problems like the job shop scheduling problem and its extensions.

Integrated laycan and berth allocation problem with ship stability and conveyor routing constraints in bulk ports

In this paper, we study the integrated Laycan and Berth Allocation Problem (LBAP) in the context of bulk ports, which considers two problems in an integrated way: the tactical Laycan Allocation Problem and the dynamic hybrid case of the operational Berth Allocation Problem. To make the LBAP closer to reality, we consider tidal bulk ports with conveyor routing constraints between storage hangars and berthing positions, preventive maintenance activities, multiple quays with different water depths and fixed heterogeneous bulk-handling cranes, navigation channel restrictions, vessels with multiple cargo types, charter party clauses, non-working periods, and ship stability considerations during loading operations. The proposed integer programming model aims to define an efficient schedule for berthing chartered vessels and new vessels to charter. The model is formulated with predicates that guarantee maximum flexibility in the implementation and greatly improve the computational performance. Finally, the model is tested and validated through a set of relevant case studies inspired by the operations of OCP Group at the bulk port of Jorf Lasfar in Morocco in very reasonable computational time using commercial Software.

Joint scheduling of barges and tugboats for river–sea intermodal transport

In this paper, we study a barge and tugboat joint scheduling problem arising from a river–sea intermodal transport system, where non-self-propelled barges travel with the help of tugboats between an inland river bulk port and sea transshipment platforms to transport cargo. Due to limited channels and the sequential scheduling among ships, transit inefficiency and resource under-utilization often occur, thus it is essential to design barge timetables and tugboat paths. This paper jointly schedules barges and tugboats in a river–sea transshipment port with a tidally influenced channel, and focuses on barge round trips with multiple legs. We construct a state-space–time network from the perspective of tugboats, in which the state implies whether a barge is served by a tugboat. The problem is formulated as an integer programming model based on the network to minimize time taken for bulk cargo transshipment. A tailored variable neighborhood search algorithm is designed and its efficiency, effectiveness, and stability are demonstrated by numerical experiments, which are based on real data from the Boffa port. It is demonstrated that, by joint scheduling barges and tugboats, transfer efficiency can be significantly improved under limited tugboat resources and shorter tidal windows. The results also provide managerial insights on schedule and valuable conclusions about the resource allocation in the port.

BTEX profile and health risk at the largest bulk port in Latin America, Paranaguá Port

Port-related activities have a detrimental impact on the air quality both at the point of source and for considerable distances beyond. These activities include, but are not limited to, heavy cargo traffic, onboard, and at-berth emissions. Due to differences in construction, operation, location, and policies at ports, the site-specific air pollution cocktail could result in different human health risks. Thus, monitoring and evaluating such emissions are essential to predict the risk to the community. Environmental agencies often monitor key pollutants (PM2.5, PM10, NO2, SO2), but the volatile organic carbons (VOCs) most often are not, due to its analytical challenging. This study intends to fill that gap and evaluate the VOC emissions caused by activities related to the port of Paranaguá - one of the largest bulk ports in Latin America - by characterizing BTEX concentrations at the port and its surroundings. At seven different sites, passive samplers were used to measure the dispersion of BTEX concentrations throughout the port and around the city at weekly intervals from November 2018 to January 2019. The average and uncertainty of BTEX concentrations (µg m-3) were 0.60 ± 0.43, 5.58 ± 3.80, 3.30 ± 2.41, 4.66 ± 3.67, and 2.82 ± 1.95 for benzene, toluene, ethylbenzene, m- and p-xylene, and o-xylene, respectively. Relationships between toluene and benzene and health risk analysis were used to establish the potential effects of BTEX emissions on the population of the city of Paranaguá. Ratio analysis (T/B, B/T, m,p X/Et, and m,p X/B) indicate that the BTEX levels are mainly from fresh emission sources and that photochemical ageing was at minimum. The cancer risk varied across the sampling trajectory, whereas ethylbenzene represented a moderate cancer risk development for the exposed population in some of the locations. This study provided the necessary baseline data to support policymakers on how to change the circumstances of those currently at risk, putting in place a sustainable operation.

Modeling the Bulk Port Belt-Conveyor Routing Problem Considering Interactions With Storage Spaces and Loading Operations

Modeling the Bulk Port Belt-Conveyor Routing Problem Considering Interactions With Storage Spaces and Loading Operations

An integrated Decision Support System for planning production, storage and bulk port operations in a fertilizer supply chain

Effective and efficient management of resources plays a crucial role in supply chains. This paper presents the bases of an integrated Decision Support System (DSS) for planning the operations of three successive echelons in the fertilizer part of a phosphate supply chain working in pull mode: production, vessel loading and storage where storage cannot constitute a decoupling point. Considering the whole perimeter of these planning operations within a monolithic optimization problem is much too huge to be solvable. Thus, the proposed DSS encapsulates an existing production scheduling model, an existing berth scheduling model, and a new model for the Storage Space Allocation Problem (SSAP). The latter provides a precise allocation of storage spaces for the fertilizers entering and leaving the hangars. Therefore, the proposed DSS aims to align production and storage decisions with vessel demands in a lean perspective, ensuring consistency in decision-making and keeping, if possible, the optimal solutions of production and port models. This approach is illustrated by several tests inspired by actual data provided by OCP Group on its operations at the Jorf Lasfar chemical platform in Morocco, but it is also valid for any other phosphate fertilizer producer that ships fertilizers in large batches from storage spaces directly linked to a fertilizer plant. This research yields several academic contributions in lean supply chain management and provides an original approach for modeling time in the SSAP.

IMPACT OF COVID-19 ON MALAYSIAN DRY BULK BUSINESS

During the COVID-19 pandemic, international cross-border restrictions were implemented worldwide. In Malaysia, it was anticipated that the Movement Control Order (MCO) would negatively impact the maritime business as badly as it would on most other economic activities in the country. However, the lockdown in Malaysia, which aimed to “restrict movement”, “reduce contact” and further “isolate the virus”, did not impact maritime business as much as other industries. In fact, the maritime waterways remained the main artery to transport essential goods nationwide during the pandemic. This paper analyses the impact of the pandemic on the maritime business in Malaysia by studying the commercial and technical aspects. Primarily, the paper focuses on dry bulk trade, container business, port infrastructure, and parties involved in the maritime supply chains. It finds that the impact of the pandemic was minimal, and certainly not as prominent as anticipated; in fact, the Baltic Dry index touched a new high during this period. This paper uses secondary data and draws on the analyses of the Baltic Dry Index, Platts Report by S&P, and Review of Maritime Transport by the United Nations Conference on Trade and Development. The paper is divided into three sections: The changes in selected maritime sectors before and during the pandemic, the factors affecting dry bulk market growth in Malaysia, and the lessons learnt and corresponding recommendations to improve Malaysian maritime business post-pandemic.

Business process redesign towards IoT-enabled context-awareness: the case of a Chinese bulk port

PurposeThe purpose of this paper is to contribute to the extant literature about the co-evolvement of Business Process Management (BPM) and the Internet of Things (IoT) by proposing the IoT-enabled Context-aware BPM (IoT-CaBPM) framework to bridge from the IoT infrastructure to context-aware business processes.Design/methodology/approachMotivated by the “Three Waves” of BPM research, IoT-enabled context-awareness is, therefore, expected to be achieved for enhancing the business process design, which pilots a new wave of BPR (Business Process Redesign/Reengineering) to enable the business process coevolve with IoT and analytics. This paper reports an illustrative case study of BPR in a Chinese bulk port, one of the hub seaports that widely adopted IoT technologies over the last few years.FindingsThe IoT implementation and data analytics has increased the efficiency and improve the monitoring effectively. The proposed IoT-CaBPM framework availably helps to identify and match nodes of IoT devices, business decisions and analytic models in order to redesign a business process towards context-aware variability. As IoT is rapidly becoming the new dominant IT paradigm is moving towards mature implementation in various industries, the corresponding BPR must be planned and executed strategically for achieving better benefits.Originality/valueDespite some research extend BPM standard by integrating IoT devices as a sort of resources or report generically that the ports operations are affected by IoT, there is still a lack of layers from the IoT infrastructure to context-aware business processes. An industrial BPR case with business models in detail is also a lack for presenting the specific implications and effectiveness of the adoption of such technologies. This paper fills in this gap.

Trend analysis of the productivity of Nigerian seaports

This paper assessed the trend of productivity of the existing six Nigerian ports. Secondary data was extracted from National Bureau of Statistics (NBS) Annual Reports, Nigeria Port Authority (NPA) Annual Reports, and Central Bank of Nigeria (CBN) Annual reports. Using the Data Envelopment Analysis technique, it was discovered that Calabar Port had been under-utilized towards the achievement of the required results. On the contrary, Rivers Port requires technical touches in her operations. As a liquid bulk port, the time of loading and discharging of commodities are often more than any other type of port and the turnaround time at this port are often more. Scale optimization is also required in Rivers Port. Inferentially, Lagos Port has been operating on optimal scale size but fluctuating managerial efficiency was experienced in the operation years. As a matter of findings, Tin Can Island has a similar trend to that of Onne Port with low productivities in the pre-concession period which improved consistently in the post-concession year of 2010 till the year 2015. It was also observed that Tin Can Island Port operated on under-utilization of inputs resources in the pre-concession periods till the post-concession year 2010. This reflects the element of wastefulness concerning both inputs and outputs quantities. Delta Port experienced fluctuating scale and technical efficiency trends in both pre and post concession years. Hence, it is observed that productivities' trends vary among the concessioned Nigerian Ports. These could be as a result of the influence of varied exogenous and endogenous factors on individual Port.

An Analysis on the Importance of Port Competitiveness Factors in the Integrated Operation of Bulk Port - Focusing on Incheon Port -

TOC (Terminal Operating Company) 제도는 1997년 1월 인천항과 부산항을 시작으로 도입⋅확대되어 2018년 기준 전국 10개 항만 44개 TOC 제도 부두를 41개 부두운영회사(TOC)가 운영하였다. 인천항 중 내항을 운영하던 10개의 TOC 운영사는 지속적인 물동량 감소, 타 항만으로의 물동량 이전, 내항재개발에 따른 부두면적 축소, TOC 운영사의 경영수지 악화 등 여러 가지 문제들로 인해 해양수산부 주도의 ‘내항 TOC 통합’이 2018년 5월 이루어졌다. 인천 내항 TOC 운영사 통합은 정부 주도의 우리나라 최초 대형화 및 단일화 통합으로서 10개 운영사가 합쳐지는 국내 최대 규모 TOC 결합이라는 점에서 의미를 갖는다. 본 연구는 AHP기법을 활용하여 TOC 운영사 통합시 항만경쟁력을 결정하는 주요 요인을 도출하고, 상대적 중요도를 정량화하여 실증분석을 시도하였다. 이는 우리나라 최초 벌크항만 TOC 운영사의 대형 통합 사례로서 통합 이후 항만경쟁력 영향요인을 도출했다는 점에서 기존 연구들과 차별성을 가진다. 본 연구는 인천 내항 10개 TOC 운영사가 운영하던 통합 이전의 환경과 내항 통합법인 출범 이후 환경을 분석하고, 하역사, 고객사, 공공기관 및 학계 전문가를 대상으로 벌크항만 TOC 통합시 항만경쟁력 요인의 상대적 중요도를 분석하였다. AHP 분석결과 ‘항만입지’0.304, ‘항만비용’0.224, ‘항만시설’0.204, ‘항만물동량’0.144, ‘항만서비스’0.124 순으로 중요하게 인식되는 것으로 나타났다. 본 연구는 벌크항만 TOC 통합 또는 유사 항만 통합 사례시 참고할 수 있는 유용한 정보를 제공하고, 항만경쟁력 증대를 위한 정책수립시 활용할 수 있는 자료를 제시하였다는 점에서 의의가 있다.

A reduced VNS based approach for the dynamic continuous berth allocation problem in bulk terminals with tidal constraints

This paper deals with the problem of allocating berth positions for vessels in export bulk port terminals considering tidal constraints and was first formulated by Ernst et al., (2017). This study investigates the dynamic and continuous berth allocation problem (BAP) with respect to tidal constraints (BAP_TC), and seeks to minimize the total service time of berthed vessels. Since the BAP problem is NP-hard the BAP_TC is also NP-hard. A reduced variable neighborhood search (RVNS) based approach is developed to solve the problem. For parameters tuning a machine learning algorithm is developed and used. Problem instances are benchmarked with CPLEX and the numerical experiments proved that the proposed algorithm is capable of generating high-quality solutions in rather short time. Both small and large-scale instances in the literature are tested to evaluate the metaheuristic effectiveness using other solution approaches from the literature. The computational experiment proves that the proposed algorithm provides state of the art results.

Fine Dust and Sustainable Supply Chain Management in Port Operations: Focus on the Major Cargo Handled at the Dry Bulk Port

Local residents living adjacent to ports are directly affected by the fine dust generated from the port operations. There is a need to prepare detailed measures according to cargo type given the high correlation between the types of dust-producing cargo primarily managed at ports and local industries. This study attempts to establish the attributes of the cargo handled at ports and the relationship between supply chains built for local key industries and the air quality of the local community. It aims to ascertain which cargo needs managing preemptively at the local level, based on the major cargo types handled in a port. A correlation analysis and Granger causality test were performed to investigate the causality between the factor of cargo and fine dust concentrations. The results in this study indicate the necessity for intensive management of scrap metal cargo among the major cargo handled at the target port, which confirms the large effect of management on fine dust reduction, as well as on reduction efficiency. The results suggest requirements to expand the regulations on the emissions of supply chains by cargo type, not by industry type. Additionally, it is required to minimize the blind spots of management and form an eco-friendly supply chain by introducing green technology. The preparation of emission control measures is also necessary. The findings provide useful insights for the sustainable operations of the local supply chain around the target port and will help the strategic agenda for future improvement.

Modelling and solving the multi-quays berth allocation and crane assignment problem with availability constraints

In this work, we are interested in the multi-quays berth allocation and crane assignment problem under availability restrictions. Availability restrictions may arise due weather conditions, or when, for example, cranes must undergo planned maintenance in order to stay in good performance. This problem was inspired by a real-case of a bulk port in Morocco. To solve the problem we propose at first a mixed-integer programming model. Then, in view of the limitations of the proposed model, we investigate a set of heuristics based on general variable neighborhood search with three variants of variable neighborhood descent as a local search. To validate the proposed model and the proposed heuristic approach, real-world instances are used. The computational results reveal that CPLEX MIP solver consumes a lot of CPU time to solve this model, even sometimes failing to guarantee the optimality of the provided solution. On the other hand, the proposed GVNS heuristic turns out to be very efficient in solving the considered problem.

The storage space allocation problem in a dry bulk terminal: a heuristic solution

Abstract The bulk port operations are given a growing attention for their important role in the global supply chain in different industries (mining, energy ...). To guarantee their competitiveness, the efficient management of port logistics, including yard side management is crucial. In this paper, we consider a real-word storage space allocation problem at an export bulk terminal. We formulate the problem as a mixed integer linear program and we propose a heuristic method to solve large scale data sets. Both the model and the heuristic can help the yard planner to test different scenarios and provide better stock yard plan, which is a first step toward improving the management of port operation in the bulk terminal under study.

Vertical Distribution of Particulates within the Near-Surface Layer of Dry Bulk Port and Influence Mechanism: A Case Study in China

Knowing the vertical distribution of ambient particulate matter (PM) will help port authorities choose the optimal dust-suppression measures to reduce PM concentrations. In this study, we used an unmanned aerial vehicle (UAV) to assess the vertical distribution (0–120 m altitude) of PM in a dry bulk port along the Yangtze River, China. Total suspended particulates (TSP), PM10, and PM2.5 concentrations at different altitudes were measured at seven sites representing different cargo-handling sites and a background site. Variations in results across sites make it not suitable to characterize the vertical distribution of PM concentration at this port using simple representative distributions. Bulk cargo particle size, fog cannon use, and porous fence all affected the vertical distribution of TSP concentrations but had only minor impacts on PM10 and PM2.5 concentrations. Optimizing porous fence layout according to weather conditions and cargo demand at port have the most potential for mitigating PM pollution related to port operation. As ground-based stations cannot fully measure vertical PM distributions, our methods and results represent an advance in assessing the impact of port activities on air quality and can be used to determine optimal dust-suppression measures for dry bulk ports.