Fig 4 - available via license: Creative Commons Attribution-NonCommercial 4.0 International
Content may be subject to copyright.
Source publication
The use of condition monitoring and fault diagnosis (CMFD) in marine power systems significantly influences ship safety. This study divides the development of CMFD for marine power systems into three periods and reviews the content, state and limitations of CMFD research for each period. According to the research achievements and engineering experi...
Context in source publication
Context 1
... magneto-electric sensor was used to collect the instantaneous angular speed signals. Fig. 4 shows the installation positions of the sensors and the measurement principle for the instantaneous angular speed. As shown in Fig. 3, a TDC sensor was installed on the wedge opposite to the head face of an engine flywheel, and the instantaneous angular speed sensor was installed above the flywheel. The signals collected by the two ...
Similar publications
![Fig. 6. Transfer functions computed with closed-form expression [13].](profile/Raphael-Mounet/publication/351747806/figure/fig4/AS:1025842704576512@1621591368284/Transfer-functions-computed-with-closed-form-expression-13_Q320.jpg)
Transfer functions are often used together with a wave spectrum for analysis of wave-ship interactions, where one application addresses the prediction of wave-induced motions or other types of global responses. This paper presents a simple and practical method which can be used to tune the transfer function of such responses to facilitate improved...
Citations
... Also, periodic maintenance, overhauls, and regulations of necessary replacement parts on board enable a ship to maintain long-term operation and maintenance [18]. However, most Unmanned Surface Vehicles (USVs) follow scheduled maintenance and reactive strategies, and most fault-related research is heavily focused on commercial-class surface vessels [19][20][21][22]. ...
Among unmanned surface vehicle (USV) components, underwater thrusters are pivotal in their mission execution integrity. Yet, these thrusters directly interact with marine environments, making them perpetually susceptible to malfunctions. To diagnose thruster faults, a non-invasive and cost-effective vibration-based methodology that does not require altering existing systems is employed. However, the vibration data collected within the hull is influenced by propeller-fluid interactions, hull damping, and structural resonant frequencies, resulting in noise and unpredictability. Furthermore, to differentiate faults not only at fixed rotational speeds but also over the entire range of a thruster’s rotational speeds, traditional frequency analysis based on the Fourier transform cannot be utilized. Hence, Continuous Wavelet Transform (CWT), known for attributions encapsulating physical characteristics in both time-frequency domain nuances, was applied to address these complications and transform vibration data into a scalogram. CWT results are diagnosed using a Vision Transformer (ViT) classifier known for its global context awareness in image processing. The effectiveness of this diagnosis approach was verified through experiments using a USV designed for field experiments. Seven cases with different fault types and severity were diagnosed and yielded average accuracy of 0.9855 and 0.9908 at different vibration points, respectively.
... Diesel engines are widely used in various shipping for their excellent performance [1,2]. According to previous studies, mechanical friction in diesel engines takes up roughly 4%-15% of the total fuel energy [3]. ...
... Specifically, 28% of these claims stem from marine diesel engine failures, causing losses of approximately $13 million [3]. Research indicates that electrical faults in ships not only compromise navigation safety, but also contribute to severe maritime accidents, leading to significant personal and property losses [4]. Therefore, the development of motor fault diagnosis algorithms holds great significance for the safe operation and maintenance of ships and marine machinery equipment. ...
Electric motors play a crucial role in ship systems. Detecting potential issues with electric motors is a critical aspect of ship fault diagnosis. Fault diagnosis in motors is often challenging due to limited and noisy vibration signals. Existing deep learning methods struggle to extract the underlying correlation between samples while being susceptible to noise interference during the feature extraction process. To overcome these issues, this study proposes an intelligent bimodal fusion attention residual model. Firstly, the vibration signal to be encoded undergoes demodulation and is divided into high and low frequencies using the IEEMD (Improved Ensemble Empirical Mode Decomposition) composed of the EEMD (Ensemble Empirical Mode Decomposition) and the MASM (the Mean of the Standardized Accumulated Modes). Subsequently, the high-frequency component is effectively denoised using the wavelet packet threshold method. Secondly, current data and vibration signals are transformed into two-dimensional images using the Gramian Angular Summation Field (GASF) and aggregated into a bimodal Gramian Angle Field diagram. Finally, the proposed model incorporates the Self-Attention Squeeze-and-Excitation Networks (SE) mechanism with the Swish activation function and utilizes the ResNeXt architecture with a Dropout layer to identify and diagnose faults in the multi-mode fusion dataset of motors under various working conditions. Based on the experimental results, a comprehensive discussion and analysis were conducted to evaluate the performance of the proposed intelligent bimodal fusion attention residual model. The results demonstrated that, in comparison to traditional methods and other deep learning models, the proposed model effectively utilized multimodal data, thereby enhancing the accuracy and robustness of fault diagnosis. The introduction of attention mechanisms and residual learning enable the model to focus more effectively on crucial modal data and learn the correlations between modalities, thus improving the overall performance of fault diagnosis.
... Almost 90% of global trade is carried out by 90,000 commercial ships, and despite the international trend for intelligent and eco-friendly power systems, diesel engines are still the primary power source for over 99% of commercial ships [1,2]. However, the main reasons for operating diesel engines on ships are the unpredictable changing conditions and the need for a highly flexible system that can cover all of the complicated, weather-related, and unstable conditions. ...
Prognostic and health management (PHM) methods focus on improving the performance and reliability of systems with a high degree of complexity and criticality. These systems include engines, turbines, and robotic systems. PHM methods involve managing technical processes, such as condition monitoring, fault diagnosis, health prognosis, and maintenance decision-making. Various software and applications deal with the processes mentioned above independently. We can also observe different development levels, making connecting all of the machine’s technical processes in one health management system with the best possible output a challenging task. This study’s objective was to outline the scope of PHM methods in real-time conditions and propose new directions to develop a decision support tool for marine diesel engines. In this paper, we illustrate PHM processes and the state of the art in the marine industry for each technical process. Then, we review PHM methods and limitations for marine diesel engines. Finally, we analyze future research opportunities for the marine industry and their role in developing systems’ performance and reliability. The main added value of the research is that a research gap was found in this research field, which is that new advanced PHM methods have to be implemented for marine diesel engines. Our suggestions to improve marine diesel engines’ operation and maintenance include implementing advanced PHM methods and utilizing predictive analytics and machine learning.
... Consequently, to the best of the authors' knowledge, there is no evidence that they have performed an analysis of 1) the data pre-processing steps applied and the data quality challenges, 2) the identification of the trends with regards to the utilisation of deep learning and machine learning methodologies for fault diagnosis and prognosis, 3) the metrics, comparative studies and processes applied to validate the data-driven methodologies, and 4) the opportunities that the sector is providing to accelerate the application of smart maintenance within the sector. Xu et al. (2021) analysed the utilisation of Condition Monitoring and Fault Diagnosis (CMFD) in marine power systems in a very comprehensive manner. Data-driven methodologies for fault diagnosis based on statistical analysis, machine learning, and information fusion were analysed. ...
... • There is no evidence that data preprocessing methods have been considered in the analysis. Xu et al. (2021) Review of the utilisation of CMFD in marine power systems. ...
In recent years, there has been an interest increase in smart maintenance within the shipping sector due to the benefits and opportunities associated with its implementation. Consequently, an increase in maintenance analytics studies for marine systems has been perceived. Due to the lack of reviews that encompass the body of knowledge of data-driven methodologies for the data pre-processing, fault diagnosis and prognosis of marine systems, this study aims to introduce the findings of a systematic literature review conducted on data-driven methodologies for three critical domains: 1) data pre-processing, 2) fault diagnosis, and 3) fault prognosis of marine systems. To determine the current state-of-the-art, a total of 88 primary studies published from 2016 to 2022 have been analysed and five research questions have been proposed. Examples of key findings are the advancements in the analysis of deep learning approaches, the quality of the data pre-processing methods, and the availability of fault data. Results of the systematic review indicate that advancements in Prognostics and Health Management (PHM), advancements in AI, and advancements in the creation of open-fault datasets are the main future work recommendations to be addressed in the upcoming years.
... The reliability of the power system, which often consists of diesel engines, gear transmissions, and propellers, plays a vital role in ensuring operational safety and expected performance. However, the extreme working conditions and increasing efficiency demands make the power systems susceptible to malfunctions and faults [1][2][3], such as blockage, component wear, and lubrication failure. These factors cause severe economic losses and further reduce the life expectancy of ships. ...
The engine system is critical for a marine vehicle, and its performance significantly affects the efficiency and safety of the whole ship. Due to the harsh working environment and the complex system structure, a marine system is prone to have many kinds of novelties and faults. Timely detection of faults via effective condition monitoring is vital for such systems, avoiding serious damage and economic loss. However, it is difficult to realize online monitoring because of the limitations of measurement and health monitoring methods. In this paper, a marine engine system simulator is set up with enhanced sensory placement for static and dynamic data collection. The test rig and processing for static and dynamic data are described. Then, a physics-based multivariate modeling method is proposed for the health monitoring of the system. Case studies are carried out considering the misfire fault and the exhaust valve leakage fault. In the misfire fault test, the exhaust gas temperature of the misfired cylinder dropped from the confidence interval 100-150 C to 70-80 C and the head vibration features decreased from the confidence interval 900-1300 m/s 2 to around 200-300 m/s 2. For the exhaust valve leakage fault, the engine body vibration main bearing impact RMS increased nearly 10 times. Comparisons between the model-predicted confidence interval and measured data reveal that the proposed model based on the fault-related static and dynamic features successfully identified the two faults and their positions, proving the effectiveness of the proposed framework.
... Artificial intelligence, cloud computing, the internet of things and big data promote the development of smart ships, which brings opportunities and challenges to CMFD for marine power systems simultaneously. The paper also proposes the research trends and challenges of CMFD, focusing more on how to serve smart ships, ensuring their security and reliability [1]. ...
... There are more developments on offshore monitoring systems, seen in inventions and publications in various areas that were earlier discussed in Sections 6 and 7. However, another aspect of sensor application is presented in recent reviews on condition monitoring and fault diagnosis (CMFD) on offshore structures which include state-of-the-art applications and limitations of CMFD [121,364]. Some other reviews have been presented on structural health monitoring (SHM) systems for offshore platforms [171,[365][366][367][368]. Different field monitoring projects can be seen in offshore platforms [368,369]. ...
Recent activities in the oil and gas industry have shown an increasing need for monitoring engagements, such as in shipping, logistics, exploration, drilling, or production. Hence, there is a need to have asset management of these offshore assets (or facilities). Much of the offshore infrastructure is currently approaching or past its operational life expectancy. The study presents an overview on asset management of offshore facilities towards monitoring, safe practices, maintenance, and sustainability. This study outlines the major considerations and the steps to take when evaluating asset life extensions for an aging offshore structure (or asset). The design and construction of offshore structures require some materials that are used to make the structural units, such as offshore platform rigs, ships, and boats. Maintaining existing assets in the field and developing new platforms that are capable of extracting future oil and gas resources are the two key issues facing the offshore sector. This paper also discusses fault diagnosis using sensors in the offshore facilities. The ocean environment is constantly corrosive, and the production activities demand extremely high levels of safety and reliability. Due to the limited space and remote location of most offshore operations, producing cost-effective, efficient, and long-lasting equipment necessitates a high level of competence. This paper presents the guidelines on asset monitoring, sustainable maintenance, and safety practices for offshore structures. In this study, the management of offshore structures were also presented with some discussions on fault monitoring using sensors. It also proposes sustainable asset management approaches as guidelines that are advised, with policy implications.
... Because of their effectiveness and easy implementation, scholars frequently make use of multivariate statistical analysis methods in feature extraction, such as principal component analysis, independent component analysis, and linear discriminant analysis [25]. These methods reduce the data dimension as much as possible on the premise of retaining sufficient fault information, thereby reducing the complexity of the model. ...
Grid-connected inverters are the core equipment for connecting marine energy power generation systems to the public electric utility. The variation of current sensor fault severity will make fault samples multimodal. However, linear discriminant analysis assumes that the same fault is independent and identically distributed. To solve this problem, this paper proposes a layering linear discriminant analysis method based on traditional linear discriminant analysis. The proposed method divides the historical fault data based on the sensor fault severity layer-by-layer until the distribution of the same fault category in each subset is very close. Linear discriminant analysis is used to analyze historical fault data in each subgroup, and the kappa coefficient is applied as the basis for ending the training process. A BP neural network is employed to estimate the fault severity during the testing process, and the fault diagnosis sub-model is selected. The proposed method enables the accurate diagnosis of faults with different distributions in the same category and provides an accurate estimate of the sensor’s fault severity degree. The estimated value of the sensor’s fault degree can provide critical information for the maintenance of the equipment and can be used to correct the sensor’s output.
... For onboard machinery systems, risk-based approaches are not widely adopted. However, if examined from the perspective of predictive maintenance for marine machinery, which is inextricably linked to condition monitoring framework and techniques [12][13][14], risk-based methods can be combined with condition monitoring. In fact, there is a growing interest in developing such prediction methods from this combination [15,16]. ...
... In addition, it can be used as evidence at a certain time-step, to alter the prediction in later time-steps. Besides inserting evidence into the model, updated features with on-going analyses are not integrated into current work, though they could be added with minor modifications, in the sense that the review from X. Xu et al. [14] introduces, regarding condition monitoring and fault diagnosis, focusing on oil monitoring in marine power systems. ...
This paper focuses on the creation of a dynamic probabilistic model which simulates deterioration trends of marine engine lubrication system. The approach is based on risk and the implementation is achieved through a dynamic Bayesian network (dBN). Risk can be useful for decision making, while dBNs are a powerful tool for risk modelling and prediction models. The model takes into account deterioration of engine components, oil degradation, and the off-line condition monitoring technique of oil analysis, in the context of predictive maintenance. The paper aims to efficiently predict probability evolution for main engine lubrication failure and to decide upon most beneficial schemes from a variety of lubrication oil analysis interval schemes by introducing monetary costs and producing the risk model. Real data and respective analysis, along with expert elicitation are utilized for achieving model quantification, while the model is materialised through a code in Matlab environment. Results from the probabilistic model show a realistic simulation for the system and indicate the obvious, that with more frequent oil analyses and respective maintenance or repairs, the probability of failure drops significantly. However, the results from risk model highlight that the costs can redefine scheme suggestions, as they can correspond to low probabilities of failure but also to higher costs. Two-month interval scheme is suggested, in contrast to the most preferred practice among shipping companies, that of threemonth interval. The developed model is in general identified as a failure prediction tool focusing on marine engine lubrication failure.
