Browsing by Author "Musharraf, Mashrura"
Now showing 1 - 19 of 19
- Results Per Page
- Sort Options
- Applications of Machine Learning in Winter Navigation
Insinööritieteiden korkeakoulu | Bachelor's thesis(2024-12-01) Pihlajamäki, OhtoThis literature review investigates the applications of machine learning to enhance maritime winter navigation in Arctic waters. Given the increasing accessibility of Arctic waters, navigating partially ice-covered Arctic regions presents significant challenges, including unpredictable environmental variables and especially ice-related hazards. This study explores how machine learning technologies can utilize various data sources to support navigational decisions, and what challenges are encountered when applying machine learning to winter navigation. Studies commonly emphasize satellite data (especially SAR data), AIS data, vessel-specific parameters, and accident records as important data sources and inputs for machine learning models in maritime and winter navigation applications. Supervised learning has proven effective in processing satellite images, particularly in identifying ice from them. Unsupervised learning has been used for anomaly detection, route analysis, ice classification, and monitoring other maritime traffic. Data quality and availability, environmental variability, and computational constraints in real-time data processing are key challenges. The literature reveals a gap in applying machine learning to real-time onboard systems. the use of machine learning in winter navigation can improve safety and efficiency when operating in Arctic sea areas. Further research is needed, especially in the development of real-time applications and in adapting models to existing navigation systems. Ultimately, this study provides a foundation for further research on the application and integration of machine learning in winter navigation to improve the safety and efficiency of Arctic maritime operations. - Big maritime data for intelligent winter navigation
Insinööritieteiden korkeakoulu | Bachelor's thesis(2022-04-15) Chu, Nam - Black-Box vs. White-Box Machine Learning Models in Ship Navigation — A Systematic Mapping of the Literature
Insinööritieteiden korkeakoulu | Bachelor's thesis(2023-05-05) Shahinas, Erald - A data mining method for automatic identification and analysis of icebreaker assistance operation in ice-covered waters
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä(2022-12-15) Liu, Cong; Musharraf, Mashrura; Li, Fang; Kujala, PenttiIcebreaker assistance is a common but complex operation in ice-infested regions. Currently, the operational decision-making and the decisions regarding the safety indicators are primarily based on expert knowledge, resulting in subjectivity and the ad hoc nature of icebreaker assistance. This can negatively impact both the navigational efficiency of icebreaker services and the productivity of port services. This paper proposes a data mining method to automatically identify icebreaker assistance cases from big data. The identified cases are then used to statistically analyze the safety indicators. The data used in the paper include navigational data obtained from the Automatic Identification System (AIS) and sea ice data in the Baltic Sea area. A multi-step clustering method is adopted to cluster similar trajectories of merchant vessels and icebreakers, identifying assistance events automatically. The results show that the proposed method can automatically identify icebreaker assistance cases with an accuracy of 99.6%, precision of 87%, and recall of 78.3%. The automatic identification along with the statistical analysis can assist in the development of an intelligent decision-making system for safe and efficient winter navigation. - Decarbonizing shipping in ice by intelligent icebreaking assistance: A case study of the Finnish-Swedish winter navigation system
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä(2023-10-15) Kondratenko, Aleksandr; Kulkarni, Ketki; Li, Fang; Musharraf, Mashrura; Hirdaris, Spyros; Kujala, PenttiIce often complicates shipping in extremely cold regions, leading to energy-consuming, expensive transportation. Ship performance can be significantly improved with icebreaking assistance that uses specialized ships called icebreakers to create navigable pathways in ice fields. Icebreakers are a critical and expensive resource with high energy consumption that must be judiciously utilized for efficient traffic flow. Optimizing icebreaker usage requires careful consideration of multiple factors related to weather, ships, and regulations. The existing decision support tools for icebreaker management primarily aim to minimize the total waiting time of ships, which may result in allocation of excess icebreakers. The paper presents a novel simulation-based approach for decarbonizing shipping in ice by intelligent icebreaking assistance. The proposed approach optimizes icebreaker assistance for both eco- and cost efficiency, allowing for more sustainable icebreaking policies. A case study representing a simplified configuration of the Finnish-Swedish Winter Navigation System demonstrates this approach to come up with alternate operating strategies that can significantly improve the emission and/or cost (e.g., up to 7 percent less greenhouse gas emission or up to 14.2% lower costs). Results show that the proposed approach is promising, for providing recommendations on environmental and economic policies to decarbonize the Finnish-Swedish icebreaking assistance. - Development of stress concentration factors for geared shafts
Insinööritieteiden korkeakoulu | Master's thesis(2024-01-22) Pandey, DurgeshThe presence of geometrical irregularities in shafts, such as shaft shoulders, grooves, and keyways, disrupts the homogeneity of stress distribution, creating areas with stress concentrations. This intricate connection between geometric complexities and stress gradients is crucial as it significantly impacts both the initiation and propagation of cracks in shafts. Consequently, the development of a precise and comprehensive calculation method for stress concentration is always imperative to ensure the integrity of mechanical design. By comprehending and unifying these interconnected factors, engineers can make well-informed design decisions that contribute to the enhanced reliability and durability of shaft-integrated systems. This thesis investigated modern techniques for assessing stress concentrations in shafts and introduced an Artificial Intelligence (AI) based approach to compute the Stress Concentration Factor (SCF) in geared shafts subjected to the combination of bending, axial, torsional, and shear stresses. The proposed calculation method employs Artificial Neural Network (ANN) models trained on stress datasets obtained from Finite Element Analysis (FEA) of industrial gearbox shafts. These models can predict SCFs for both familiar and unfamiliar geometric irregularities within the confines of the training dataset’s limits. Comparative analyses with results from conventional analytical approaches demonstrated that the stress concentration factors obtained through the proposed AI-based method are both valid and reliable. Notably, this method proves its validity for handling combined stresses and exhibits applicability to complex geometric conditions, including keyways with shaft shoulders, setting it apart from the underlined analytical methods. - Developments and research directions in maritime cybersecurity: A systematic literature review and bibliometric analysis
A2 Katsausartikkeli tieteellisessä aikakauslehdessä(2022-12) Bolbot, Victor; Kulkarni, Ketki; Brunou, Päivi; Banda, Osiris Valdez; Musharraf, MashruraShips and maritime infrastructure are becoming increasingly interconnected as the maritime industry is undergoing the industry 4.0 revolution. This development is associated with novel risk types such as the increased potential for successful cyberattacks. Several review studies have investigated the regulatory framework in connection to maritime cybersecurity, the vulnerabilities in maritime systems, potential cyberattack scenarios, and risk assessment techniques. None of them though, has implemented a systematic literature review and bibliometric analysis of the available academic research studies in the discipline of maritime cybersecurity. The aim of this review, therefore, is to offer a succinct description of the progress in academic research on the arising topic of maritime cybersecurity. To that end, we conducted a bibliometric analysis of maritime cybersecurity-related studies based on several metrics and analysis tools, identified the topics of academic research in this field, the employed methodologies and identified the main research challenges and directions in connection to maritime cybersecurity. To achieve the objectives, we employed principles from Preferred Reporting Items for Systematic reviews and Metanalysis (PRISMA) for systematic literature review and tailored keywords during a search in Scopus. The results demonstrated that Norway, the United Kingdom, France and the USA are the leading countries in maritime cybersecurity based on the weighted number of authors. The results also demonstrated that the main research focus in the area was on the development or application of cybersecurity risk assessment techniques and the design of monitoring and intrusion detection tools for cyberattacks in maritime systems. Based on the analysed literature, 53 challenges in various studies were identified and 73 topics for future research were suggested. - Estimation of propeller ice torque in preliminary design phase - Development of a numerical model
Insinööritieteiden korkeakoulu | Master's thesis(2024-06-10) Sevón, MikuPropeller-ice interaction crucially impacts ship's operational performance and safety in icy conditions. Ice torque, an essential design parameter for assessing a ship's propulsion system performance, refers to the additional rotational force applied to the propeller during interactions with ice. Estimating ice torque is challenging due to the randomness of ice loads. This thesis develops a method and a numerical model for the estimation of ice torque in preliminary design phase. The model, developed in MATLAB, utilizes a theoretical framework of propulsion system dynamics and full-scale propulsion data from existing reference ships to estimate ice torque for new designs. The model firstly calculates the reference ship ice torque inversely from propulsion motor torque and normalizes the result for a new design in preliminary design phase using scaling factors based on ice torque design regulations. Preliminary model assessment is conducted via comparative and sensitivity analyses. The model's maximum ice torque estimations matched the comparison data values with 84.3 to 93.3 % accuracy and qualitative similarities were found between the model estimates and the results of previous studies. Consistent performance was also proved with minimal sensitivity errors, ranging from -2.3 to 2.1 %, indicating low sensitivity. The numerical model was successful due to its comprehensive framework and usage of propulsion data. On the other hand, the accuracy of the model can be limited if the quality of the input propulsion data is insufficient. The main feature of the model is its ability to provide ice torque estimates, which can be used as key inputs for propulsion system simulations, enabling the optimization of the design. The model can be further developed through a broader validation process and by refining the normalization process. - Factor analysis of icebreaker assistance operation for ice-going ships in the Baltic Sea
A4 Artikkeli konferenssijulkaisussa(2023) Liu, Cong; Kulkarni, Ketki; Musharraf, Mashrura; Kujala, PenttiMerchant vessels navigating the Baltic Sea in winter often require assistance from icebreakers to create safe pathways and improve navigational efficiency. Given icebreaker resources are limited, assistance decision is important. The requirement for assistance depends on multiple factors, including ice conditions, weather, and ship characteristics. In this paper, we explore how data-driven techniques can enhance the current understanding of factors influencing the decision-making of icebreaker assistance. Firstly, the paper identifies multiple factors from previous winter navigation operations research. Then different data sources containing traffic data, environmental conditions, and ship characteristics are explored to find data about the identified factors. Finally, an integrated database containing these factors is established. Using a multi-step clustering method, data points in the database are classified as either assistance or independent navigation. Preliminary statistical analysis of the factors is performed to understand how they vary between independent navigation and assistance cases. Results show that weather and ship factors do not significantly vary compared to ice factors. Among the ice factors, ridge ice thickness and level ice concentration vary the most between independent navigation and assistance. These findings are aligned well with empirical knowledge and previous studies. The database and the empirical findings in this paper can provide insights for quantifying factor effects on the decision-making of icebreaker assistance and support the intelligent decision-support system for winter navigation. - A machine learning method for the prediction of ship motion trajectories in real operational conditions
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä(2023-09-01) Zhang, Mingyang; Kujala, Pentti; Musharraf, Mashrura; Zhang, Jinfen; Hirdaris, SpyrosThis paper presents a big data analytics method for the proactive mitigation of grounding risk. The model encompasses the dynamics of ship motion trajectories while accounting for kinematic uncertainties in real operational conditions. The approach combines K-means and DB-SCAN (Density-Based Spatial Clustering of Applications with Noise) big data clustering methods with Principal Component Analysis (PCA) to group environmental factors. A Multiple-Output Gaussian Process Regression (MOGPR) method is consequently used to predict selected ship motion dynamics. Ship sway is defined as the deviation between a ship and her motion trajectory centreline. Surge accelerations are used to idealise the time-varying manoeuvring of ships in various routes. Operational conditions are simulated by Automatic Identification System (AIS), General Bathymetric Chart of the Oceans (GEBCO), and nowcast hydro-meteorological data records. A Dynamic Time Warping (DTW) method is adopted to identify ship centre-line trajectories along selected paths. The machine learning algorithm is applied for ship motion predictions of Ro-Pax ships operating between two ports in the Gulf of Finland. Ship motion dynamics are visualised along the ship’s route using a Gaussian Progress Regression (GPR) flow method. Results indicate that the present methodology may assist with predicting the probabilistic distribution of ship dynamics (speed, sway distance, drift angle, and surge accelerations) and grounding risk along selected ship routes. - On the data-driven investigation of factors affecting the need for icebreaker assistance in ice-covered waters
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä(2024-05) Liu, Cong; Kulkarni, Ketki; Suominen, Mikko; Kujala, Pentti; Musharraf, MashruraMerchant vessels often require icebreaker (IB) assistance to create safe pathways and improve efficiency when navigating in the Baltic Sea. Since IB resources are limited, an accurate estimation on the need for IB assistance is important. Whether IB assistance is needed depends on multiple factors. While practical experience from captains is naturally a source of valuable information for the decision on the need for IB assistance, systematic analysis of the reasoning is limited. The primary aim of this paper is to holistically investigate the influencing factors and their effect on estimating the need for IB assistance through data-driven techniques. Based on a comprehensive list of potential factors, different of data such as traffic history, environmental conditions, and ship specifications are gathered to present complex navigational scenarios. Each scenario is labeled by different navigation modes (independent navigation or IB assistance), laying the foundation for influencing factor identification and effect quantification. Logistic regression is applied to evaluate the effect of the factors on the need for IB assistance. The results show that the impact of the factors is diverse, and ridged ice concentration has the most significant impact. The effectiveness of identified factors is measured by comparing it to that of the factors that have been implemented by the existing studies (e.g., the combination of ice concentration, thickness, and ship ice class, or only ship speed). By considering the factors in this study, the classification performance can be improved by at least 5.6%. The findings in this paper can provide insights for predicting IB workloads and optimizing IB resources and have the potential to support the development of an intelligent decision-support system for winter navigation. - Pathfinding and optimization for vessels in ice : A literature review
A2 Katsausartikkeli tieteellisessä aikakauslehdessä(2023-07) Tran, Trung Tien; Browne, Thomas; Musharraf, Mashrura; Veitch, BrianVoyages through ice-covered waters must maintain safety by adhering to maritime regulations. It is also important to optimize maritime shipping in terms of both economic and environmental factors. There has been much research on this topic. However, a systematic review has not been executed. Hence, this work summarizes systematically what has been done and indicates the current gaps. The present research aims to provide a comprehensive investigation of the following questions: (1) What are the objectives of route optimization in ice? (2) What are the ship performance models for vessels in ice operation? (3) What are the operational constraints in ice? (4) What kind of optimization techniques are used in the routing model? (5) Where do the ice data come from? (6) Is the dynamic changing ice environment considered in the model? (7) Is route validation executed? A review of 32 articles in the literature is performed. The results show that main objectives typically include travelled distance, voyage time, and/or fuel consumption, while wide ranges of ship performance models, constraints, optimization methods, and ice data are used. A few studies consider dynamic ice conditions and route validation. This review article is limited to online sources. Results of the current review suggest that future research in the area of pathfinding for vessels in ice should explore more operational constraints and solve the pathfinding in ice problem under uncertainties. It is also recommended that future work consider validation techniques to enhance the reliability and practicality of these routing tools. - Pilot Study Using Decision Trees to Diagnose the Efficacy of Virtual Offshore Egress Training
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä(2022-12-01) Smith, Jennifer; Musharraf, Mashrura; Veitch, Brian; Khan, FaisalFor the offshore energy industry, virtual environment technology can enhance conventional training by teaching basic offshore safety protocols such as onboard familiarization and emergency evacuation. Virtual environments have the added benefit of being used to investigate the impact of different training approaches on competence. This pilot study uses decision tree modeling to examine the efficacy of two pedagogical approaches, simulation-based mastery learning (SBML) and lecture-based training (LBT), in a virtual environment. Decision trees are an inductive reasoning approach that can be used to identify learners' egress strategies in offshore emergencies after training. The efficacy of the virtual training is evaluated in three ways: 1) analyzing participants' performance scores in test scenarios; 2) comparing the decision tree depiction of participant's understanding of emergency egress to the intended learning objectives; and 3) comparing the decision strategies developed under a different pedagogical approach. A comparison of the resulting decision trees from the SBML training with trees generated from the LBT showed that the different training methods influenced the participants' egress strategies. The SBML approach resulted in concise decision trees and better route selection strategies when compared to the LBT training. This pilot study demonstrates the diagnostic capabilities of decision trees as training assessment tools and recommends integrating decision trees into virtual training to better support the learning needs of individuals and deliver adaptive training scenarios. - The Role of Machine Learning for Vessel Speed and the Optimization of It-A Systematic Mapping
Perustieteiden korkeakoulu | Bachelor's thesis(2023-09-08) Ekblom, Crista - Route optimization for vessels in ice : Investigating operational implications of the carbon intensity indicator regulation
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä(2023-12) Tran, Trung Tien; Browne, Thomas; Veitch, Brian; Musharraf, Mashrura; Peters, DennisThe International Maritime Organization has adopted the Carbon Intensity Indicator (CII) regulation to promote decarbonization of shipping operations. The CII regulation includes specific treatment for vessels sailing in ice, which allows the time spent in ice, the associated emissions and transport work, to be excluded from the reported annual CII. The current study investigates the implications and possible side effects of this exemption in all ice-covered waters. A proposed model integrates the CII regulation into a route optimization tool for vessels in ice. The research decomposes the regulation from evaluating an annual CII value to monitoring an instantaneous CII value over a unit distance. A ship performance model is used to estimate resistance, powering, and fuel consumption. A graph-based pathfinding method is applied to find optimal routes and speeds for the vessel. A hypothetical bulk carrier with ice class 1A Super operating in the Canadian Arctic is considered as a case study. The Polar Operational Limit Assessment Risk Indexing System is applied to promote safe operations in ice. The demonstrations explore route optimization with and without CII considerations, including the exemption for ships sailing ice. The results show that the CII regulation promotes reduced speeds to curb fuel consumption and carbon emissions. The findings also indicate that the exemption for sailing in ice conditions influences routing decisions with results that are contrary to the intent of the regulation. This research provides a tool to support ship operators with voyage planning and policy-makers in evaluating the impact of the CII regulation. - Sensitivity analysis of a Baltic sea winter navigation simulation tool
School of Electrical Engineering | Master's thesis(2024-12-31) Kainulainen, AnttiThe Baltic Sea serves as a vital gateway to international trade, providing essential maritime access to countries bordering it. However, its unique environmental conditions present significant challenges, particularly during winter when extensive ice coverage impedes safe and efficient navigation. These challenges are most pronounced in the Bay of Bothnia, where prolonged ice coverage affects several important ports for Finland and Sweden. To support the decision-making processes of Finnish and Swedish authorities, Kulkarni et al. (2022) have developed a tool for simulating the Baltic Sea under various conditions, aimed at helping to ensure safe maritime operations in icy conditions. A recent validation analysis revealed discrepancies between the model’s outputs and observed real-world data, highlighting the need for further investigation. To address this, a comprehensive sensitivity analysis was conducted to evaluate the model’s responsiveness to its key input parameters. This analysis aims to guide future refinement efforts and enhance understanding of the model’s behavior. The sensitivity analysis was carried out in two parts using different analysis methods. The Elementary Effects method was employed to identify the most influential parameters, while the Sobol’ method provided quantitative insights into the model’s sensitivity. The results of these analyses are presented using graphical figures that represent the numerical findings. The analysis revealed that the model responds predictably to variations in input parameters, with no significant outliers detected. However, certain parameters exhibited lower-than-expected influence on the model’s outputs, suggesting areas for potential improvement. The implications of these findings for the model’s functionality and future development are discussed. - Simulation Tool for Winter Navigation Decision Support in the Baltic Sea
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä(2022-08) Kulkarni, Ketki; Kujala, Pentti; Musharraf, Mashrura; Rainio, IlariThis article presents a novel simulation tool for the analysis of winter navigation operations in the Baltic Sea in the context of the Finnish-Swedish Winter Navigation System (FSWNS). The aim of the tool is to simulate the performance of the FSWNS under various potential future operating scenarios and thereby support decision making in matters affecting the operation and development of the FSWNS, for instance, in terms of icebreaking resources and ice class regulations. To this end, the tool considers key performance factors and characteristics of the FSWNS, such as the prevailing ice conditions, the ice-going capability and other technical characteristics of the relevant merchant vessels, the availability of icebreaking resources, and the features of specific icebreaking operations (e.g., convoys). The tool would allow testing of several "what-if" scenarios, answering questions related to optimal engine power for safe, efficient, and environmentally friendly navigation and the optimal scheduling of icebreakers for effective and cost-efficient assistance missions. - Transparency and Intelligent ships -A Literature Review
Insinööritieteiden korkeakoulu | Bachelor's thesis(2022-04-18) Eriksson, Jesper - Validation of a computational simulation model of the Finnish-Swedish winter navigation system
Insinööritieteiden korkeakoulu | Master's thesis(2023-12-11) Winberg, CasperMaritime transportation plays a vital role in the global economy, with the maritime sector representing 90% of all material trading worldwide. The Baltic Sea, a significant maritime hub, faces unique challenges due to its substantial traffic and ice coverage during winter months. To aid decision-making in this challenging environment, simulation tools are being developed, allowing efficient simulations to be performed under different conditions. In this thesis, the latest winter navigation simulation tool developed by Kulkarni et al. (2022) is validated using historical data in order to find out its accuracy and trustworthiness. Rather than validating it only for one winter, the model is now studied on trip-level using three different historical winters, being 2011, 2018, and 2020. These represent the three different winter types of mild, average, and severe, classified by the Finnish Ice Service. A major part of the study includes the processing and filtration of both traffic flow-data and ice conditions-data, used in the model as inputs. This ensures the validation results to be as truthful as possible and allows the model’s performance to be studied without worrying about the error possibly being caused by the input data. The validation results are presented using common statistical measures, including mean, standard deviation, relative standard deviation, and confidence interval. For the purpose of finding error trends, numerical and graphical figures are presented in relation to different parameters. Finally, the results are discussed from a naval architect’s point of view, in order to find system-level deficiencies and incorrect assumptions that might have impacted the validation results.