A comparative investigation of data-driven approaches based on one-class classifiers for condition monitoring of marine machinery system

Tan, Yulin; Tian, Hui; Jiang, Ruizheng; Lin, Yejin; Zhang, Jundong

doi:10.1016/j.oceaneng.2020.107174

Cited by 38 publications

(15 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A comparison of decision tree algorithms in [47] analysed the behaviour of a GT according to temperature evolution. Similarly, but using the oneclass approach, a comparative investigation of data-driven approaches based on one-class classifiers was proposed in [48]. One-class classifiers are common algorithms used in several fields in which the models learn to define the boundary of normal and abnormal samples.…”

Section: Health Statusmentioning

confidence: 99%

“…Yu Xhang et al [46] 2013 VBGMM Determine operational change between steadystate and transients Manjit Verma and Amit Kumar [56] 2014 PN Qualitative and quantitative analysis for modelling and analysing machine behaviour Hamid Asgari et al [49] 2016 NARX Gas turbine's start-up dynamics' assessment Cristiano Hora Fontes and Otacílio Pereira [50] 2016 SPCA + Fuzzy C-means Operational pattern recognition Nallamilli P. G. Bhavani et al [53] 2016 ANN Intelligent sensor to monitor and control combustion quality Pogorelov G.I et al [43] 2017 RNN Dynamic performance assessment Abshukirov Zhandos and Jian Guo [47] 2017 Decision tree Behaviour analysis based on temperature evolution Josué Enríquez-Zárate et al [51] 2017 GSGP Model parameters' estimation Maria Grazia De Giorgi et al [44] 2018 ANN, SVM Model comparison for health status monitoring Jiao Liu et al [52] 2018 CNN Abnormal operation detection Farzan Majdani et al [57] 2018 ANN Inferential sensor for machine status assessment K. Sujatha, G. et al [54] 2019 ANN + PSO Exhaust gas estimation Hossein Shahabadi Farahani et al [45] 2020 TL Improvement of health monitoring system Yanghui Tan et al [48] 2020 OCSVM, SVDD, GKNN, LOF, IForest, and ABOD…”

Section: Reference Year ML Model Applicationmentioning

confidence: 99%

See 1 more Smart Citation

Machine-Learning-Based Condition Assessment of Gas Turbines—A Review

2021

View full text Add to dashboard Cite

Condition monitoring, diagnostics, and prognostics are key factors in today’s competitive industrial sector. Equipment digitalisation has increased the amount of available data throughout the industrial process, and the development of new and more advanced techniques has significantly improved the performance of industrial machines. This publication focuses on surveying the last decade of evolution of condition monitoring, diagnostic, and prognostic techniques using machine-learning (ML)-based models for the improvement of the operational performance of gas turbines. A comprehensive review of the literature led to a performance assessment of ML models and their applications to gas turbines, as well as a discussion of the major challenges and opportunities for the research on these kind of engines. This paper further concludes that the combination of the available information captured through the collectors and the ML techniques shows promising results in increasing the accuracy, robustness, precision, and generalisation of industrial gas turbine equipment.

show abstract

Section: Health Statusmentioning

confidence: 99%

Section: Reference Year ML Model Applicationmentioning

confidence: 99%

Machine-Learning-Based Condition Assessment of Gas Turbines—A Review

2021

View full text Add to dashboard Cite

show abstract

“…Foram investigados os requisitos para aplicativos de engenharia e demonstrada uma implementação do algoritmo de Floresta de Isolamento. Tan et al (2020) compararam o desempenho de diversos classificadores para detecção de anomalias em máquinas de embarcações marítimas. A segurança e a confiabilidade da navegação dependem do desempenho dessas máquinas e o monitoramento inteligente de condiçõesé importante para as atividade de manutenção.…”

Section: Trabalhos Correlatosunclassified

Detecção de anomalias em poços produtores de petróleo usando aprendizado de máquina

Júnior

Vargas

Komati

et al. 2020

Anais Do Congresso Brasileiro De Automática 2020

View full text Add to dashboard Cite

Anomalias em poços produtores de petróleo podem provocar impactos financeiros significativos. O uso de aprendizado de máquina para detectar essas situações podem prevenir interrupções indesejadas de produção bem como custos de manutenção. Nesse contexto, este trabalho propõe a aplicação e comparação de classificadores para detecção de anomalias em poços de produção de petróleo e gás. Classificadores de classe única Floresta de Isolamento, \textit{One-class Support Vector Machine} (OCSVM), \textit{Local Outlier Factor} (LOF) e Envelope Elíptico foram aplicados em uma base de dados com casos reais, sendo o melhor desempenho obtido pelo LOF com medida F1 de 88,2\%, seguido da Floresta de Isolamento com 74,3\%. Os resultados obtidos apresentam melhoria em comparação ao \textit{benchmark} de referência e estimulam a continuação do trabalho com a experimentação de outras famílias de classificadores.

show abstract

“…Simple supervised regression models were then adopted to predict the decay coefficient given only the sensor dataset. Utilizing the same dataset, Cipollini et al [ 17 ] and Tan et al [ 18 ] proposed a classification-based approach and compared the accuracy of several competing classification algorithms. However, generating the simulated dataset is costly because it requires complex physical modeling of the system, which may be challenging to develop.…”

Section: Introductionmentioning

confidence: 99%

Explainable Anomaly Detection Framework for Maritime Main Engine Sensor Data

Kim¹,

Antariksa

Handayani

et al. 2021

Sensors

View full text Add to dashboard Cite

In this study, we proposed a data-driven approach to the condition monitoring of the marine engine. Although several unsupervised methods in the maritime industry have existed, the common limitation was the interpretation of the anomaly; they do not explain why the model classifies specific data instances as an anomaly. This study combines explainable AI techniques with anomaly detection algorithm to overcome the limitation above. As an explainable AI method, this study adopts Shapley Additive exPlanations (SHAP), which is theoretically solid and compatible with any kind of machine learning algorithm. SHAP enables us to measure the marginal contribution of each sensor variable to an anomaly. Thus, one can easily specify which sensor is responsible for the specific anomaly. To illustrate our framework, the actual sensor stream obtained from the cargo vessel collected over 10 months was analyzed. In this analysis, we performed hierarchical clustering analysis with transformed SHAP values to interpret and group common anomaly patterns. We showed that anomaly interpretation and segmentation using SHAP value provides more useful interpretation compared to the case without using SHAP value.

show abstract

A comparative investigation of data-driven approaches based on one-class classifiers for condition monitoring of marine machinery system

Cited by 38 publications

References 31 publications

Machine-Learning-Based Condition Assessment of Gas Turbines—A Review

Machine-Learning-Based Condition Assessment of Gas Turbines—A Review

Detecção de anomalias em poços produtores de petróleo usando aprendizado de máquina

Explainable Anomaly Detection Framework for Maritime Main Engine Sensor Data

Contact Info

Product

Resources

About