Explore the vast range of titles available.

The application of machine vision in identifying various types of instruments holds significant research value in enhancing the intelligence level of ship engine rooms. This paper presents the development of a SE-MIXUP YOLO model based on the YOLOv5 algorithm, capable of recognizing different types of instruments in complex ship engine room environments. First, instrument images of different types from different ship engine rooms were collected as a self-built data set, and the image data set was enhanced according to the actual situation of the engine room. In this study, the YOLOv5 model was trained based on the PyTorch framework in the Anaconda virtual environment. The analysis shows that the model achieves an average precision (mAP) of 1.00 when the confidence threshold is 0.970; the average F1 score is 0.84 when the confidence threshold is 0.596. The model can effectively identify various instruments such as pressure gauges, thermometers, and level gauges in complex ship engine room environments, verifying its good environmental adaptability and robustness.

The impact of digitalization on the maritime industry is increasing day by day. In this sense, realistic engine room simulators (ERS), which fulfill the requirements of the International Maritime Organization, are getting more important and frequently used in the field of maritime education and training. Besides, it is observed that there is an increase in ERS usage in experimental academic studies because opportunities for realizing critical and risky operations on real marine vessels in the ERS and determining the effects of failures through simulations encourage researchers. However, there is uncertainty about the method followed in ERS-based studies since the use of the ERS varies at the discretion of each author. In this study, a novel methodology is proposed to eliminate the uncertainty and provide standardization of engine simulators as a tool in academic studies. Real ship machinery operations, simulator specifications, scientific methods, instructor and operator interventions are utilized in this methodology framework. To prove the effectiveness of the methodology, a two-stroke MAN B&W 6S50 MC-C marine diesel engine turbocharger (TC) exhaust side fouling effects are analyzed. In addition, the validation of the application conducted by the proposed methodology is carried out by consulting experts with marine experience during the design and evaluation of the application. Thus, it is aimed to obtain more realistic and reliable data through a systematically designed simulation process.

This paper presents a risk assessment method for a ship’s power system under the conditions of an engine room fire based on the expert comprehensive evaluation (ECE) method combined with the fuzzy fault tree analysis (FFTA) method. The composition of the main engine system in the engine room and the failure logic of each subsystem were analyzed, and the fuzzy fault tree of a ship engine room fire was constructed. The probability of system failure and the importance of basic events were calculated. The fire safety risk assessment model was established using the safety risk matrix. The risk assessment of a ship engine room fire was implemented. The results demonstrated that the fire frequency of the ship engine room was 5.232 × 10−6 h−1. The fire risk of the main engine fuel system was the highest. Fuel leakages from diesel supply tanks and heavy fuel oil tanks are the main cause of accidents. The proposed method eliminated the influence of incomplete statistics in the risk assessment process and improved the accuracy and credibility of the reassessment results.

In order to make up for the shortage of scientific research experiments and teaching in land-based engine room laboratory, a simulation system is designed and developed using B/S mode to simulate scientific research experiments, teaching and operation processes, and designed algorithms to simulate the propulsion characteristics of the main propulsion diesel engine. A large number of experiments were carried out, and the relationship curve between output power and fuel consumption rate of the main engine was obtained in the laboratory. Apache JMeter was used to test the pressure of the simulation system deployed in Dalian Maritime University Cloud. It is found that under the test conditions, the average response time of sample request is 330 ms, which is far superior the design standard of 2 s. There is no abnormal response to all requests, and all indicators fully meet the requirements of the project team. The simulation system fills the gap in the application of panoramic interactive technology in Marine engineering education, and provides a reference for the exploration of \"intelligent +\" experiment and teaching mode in maritime university laboratories.

Large-scale experiments were carried out in an engine room platform to investigate the mass burning rate and smoke temperature under mechanical ventilation. Four air inlet heights ranged from 0.1 m to 1.0 m and six ventilation rates ranged from 38 h−1 to 126 h−1 were explored. The mass burning rates of pool fire and temperature distributions in the engine room were obtained. The average and maximum temperature values of the entire engine room were calculated to analyze the temperature characteristics of the engine room under various mechanical ventilation conditions. Results showed that the mass burning rates were slightly affected by ventilation rates. The vertical temperature distribution of ship engine room fires under mechanical ventilation presented to be a single-zone distribution. The average temperature of the entire engine room decreased with the increase of ventilation rate. On the basis of thermal balance analysis, a prediction model was proposed to calculate the average temperature of the entire engine room, which was consistent with the temperature trend measured in the experiments within 20% error.

This paper proposes a dynamic evolutionary model to quantify the domino effect of ship engine room fires. Based on the spatial and temporal characteristics of fire accidents, the dynamic probability of the domino effect of multiple accident units is calculated using matrix calculation and Monte Carlo simulation. The uncertainties of shipboard personnel, automatic detection systems, sprinkler systems, and the synergistic effects of multiple escalation vectors from different units are addressed. The dynamic probability of the domino effect of multiple accident units is calculated, and a risk assessment of complex fire scenarios in ship engine rooms is implemented. This study also presents the model feasibility in terms of fire risk assessment in cabins with numerous pieces of equipment. The results indicate that 2 min and 4 min are vital time nodes for the development and spread of fires. The extinguishing work on key equipment in the path of the fire's spread can effectively restrain its further expansion. The results can provide critical references for ship fire prevention, fire suppression, and fire protection design.

In comparison to onshore facilities, ships, and their machinery are subjected to challenging external influences such as rolling, vibration, and continually changing air & cooling water temperatures in the marine environment. However, these factors are typically neglected, or their consequences are deemed to have little effect on machinery, the environment, or human life. In this study, seasonal air & seawater temperature effects on marine diesel engine performance parameters and emissions are investigated by using a full-mission engine room simulator. A tanker ship two-stroke main engine MAN B&W 6S50 MC-C with a power output of 8 600 kW is employed during the simulation process. Furthermore, due to its diverse risks, the Marmara Region is chosen as the application area for real-time average temperature data. Based on the research findings, even minor variations in seasonal temperatures have a significant influence on certain key parameters of a ship’s main engine including scavenge pressure, exhaust temperatures, compression and combustion pressures, fuel consumption, power, and NO x −SO x −CO x emissions. For instance, during the winter season, the cylinder compression pressure ( p c ) is recorded at 94 bar, while the maximum pressure ( p z ) reaches 110 bar. In the summer, p c experiences a decrease of 81 bar, while p z is measured at 101 bar. The emission of nitrogen oxides (NO x ) exhibits a measurement of 784 parts per million (ppm) during winter and 744 in summer. The concentration of sulfur oxides (SO x ) is recorded at 46 ppm in winter and 53 in summer. Given the current state of global warming and climate change, it is an undeniable fact that the impact of these phenomena will inevitably escalate.

With the development of intelligentization in maritime vessels, the pursuit of an organized and scalable knowledge storage approach for marine engine room systems has become one of the current research hotspots. This study addressed the foundational named entity recognition (NER) task in constructing a knowledge graph for marine engine rooms. It proposed an entity recognition algorithm for Chinese semantics in marine engine rooms that integrates language models. Firstly, the bidirectional encoder representation from transformers (BERT) language model is used to extract text features and obtain word-level granularity vector matrices. Secondly, the trained word embeddings are fed into a bidirectional long short-term memory network (BiLSTM) to extract contextual information. It considers the surrounding words and their sequential relationships, enabling a better understanding of the context. Additionally, the conditional random field (CRF) model was used to extract the globally optimal sequence of named entities in the marine engine room semantic. The CRF model considered the dependencies between adjacent entities that ensured a coherent and consistent final result for entity recognition in marine engine room semantics. The experiment results demonstrate that the proposed algorithm achieves superior F1 scores for all three entity types. Compared with BERT, the overall precision, recall, and F1 score of the entity recognition are improved by 1.36%, 1.41%, and 1.38%, respectively. Future research will be carried out on named entity recognition of a small sample set to provide basic support for more efficient entity relationship extraction and construction of a marine engine room knowledge graph.

To ensure the safe protection of marine engine systems, it is necessary to explore the hot surface ignition (HSI) characteristics of marine diesel in ship environments. However, an accurate model describing these complex characteristics is still not available. In this work, a new experimental method is proposed in order to enhance prediction performance by integrating testing data of the characteristics of HSI of marine diesel. The sensitivity of HSI is determined by various factors such as surface parameters, flow state, and the ship’s environment. According to variations in the HSI status of marine diesel in an engine room, the HSI probability is distributed in three phases. It is essential to determine whether the presence of marine diesel or surrounding items can intensify the risk of an initial fire beginning in the engine room. A vapor plume model was developed to describe the relationship between HSI height and initial specific buoyancy flux in vertical space. Further, field distribution revealed significant variation in the increase in temperature between 200 and 300 mm of vertical height, indicating a region of initial HSI. In addition, increasing surface temperature did not result in a significant change in ignition delay time. After reaching a temperature of 773 K, the ignition delay time remained around 0.48 s, regardless of how much the hot surface temperature increased. This study reveals the HSI evolution of marine diesel in a ship engine room and develops data-based predictive models for evaluating the safety of HSI parameters during initial accident assessments. The results show that the goodness of fit of the predictive models reached above 0.964. On the basis of the predicted results, the HSI characteristics of marine diesel in engine rooms could be gleaned by actively determining the parameters of risk.

The engine room is the core area of a ship, critical to its operation, safety, and efficiency. Currently, many researchers merely address the ship engine room layout design (SERLD) problem using optimization algorithms and independent layout strategies. However, the engine room environment is complex, involving two significantly different challenges: equipment layout and pipe layout. Traditional methods fail to achieve optimal collaborative layout objectives. To address this research gap, this paper proposes a collaborative layout method that combines improved reinforcement learning and heuristic algorithms. For equipment layout, the engine room space is first discretized into a grid, and a Markov decision process (MDP) framework suitable for equipment layout is proposed, including state space, action space, and reward mechanisms suitable for equipment layout. An improved adaptive guided multi-agent Q-learning (AGMAQL) algorithm is employed to train the layout model in a centralized manner, with enhancements made to the agent’s exploration state, exploration action, and learning strategy. For pipe layout, this paper proposes an improved adaptive trajectory artificial fish swarm algorithm (ATAFSA). This algorithm incorporates a hybrid encoding method, adaptive strategy, scouting strategy, and parallel optimization strategy, resulting in enhanced stability, accuracy, and problem adaptability. Subsequently, by comprehensively considering layout objectives and engine room attributes, a collaborative layout method incorporating hierarchical and adaptive weight strategies is proposed. This method optimizes in phases according to the layout objectives and priorities of different stages, achieving multi-level optimal layouts and providing designers with various reference schemes with different focuses. Finally, based on a typical real-world engine room engineering case, various leading algorithms and strategies are tested and compared. The results show that the proposed AGMAQL-ATAFSA (AGMAQL-ATA) exhibits robustness, efficiency, and engineering practicality. Compared to previous research methods and algorithms, the final layout quality improved overall: equipment layout effectiveness increased by over 4.0%, pipe optimization efficiency improved by over 40.4%, and collaborative layout effectiveness enhanced by over 2.2%.