Improved Classification Models to Distinguish Natural from Anthropic Oil Slicks in the Gulf of Mexico: Seasonality and Radarsat-2 Beam Mode Effects under a Machine Learning Approach

Distinguishing between natural and anthropic oil slicks is a challenging task, especially in the Gulf of Mexico, where these events can be simultaneously observed and recognized as seeps or spills. In this study, a powerful data analysis provided by machine learning (ML) methods was employed to develop, test, and implement a classification model (CM) to distinguish an oil slick source (OSS) as natural or anthropic. A robust database containing 4916 validated oil samples, detected using synthetic aperture radar (SAR), was employed for this task. Six ML algorithms were evaluated, including artificial neural networks (ANN), random forest (RF), decision trees (DT), naive Bayes (NB), linear discriminant analysis (LDA), and logistic regression (LR). Using RF, the global CM achieved a maximum accuracy value of 73.15. An innovative approach evaluated how external factors, such as seasonality, satellite configurations, and the synergy between them, limit or improve OSS predictions. To accomplish this, specific classification models (SCMs) were derived from the global ones (CMs), tuning the best algorithms and parameters according to different scenarios. Median accuracies revealed winter and spring to be the best seasons and ScanSAR Narrow B (SCNB) as the best beam mode. The maximum median accuracy to distinguish seeps from spills was achieved in winter using SCNB (83.05). Among the tested algorithms, RF was the most robust, with a better performance in 81% of the investigated scenarios. The accuracy increment provided by the well-fitted models may minimize the confusion between seeps and spills. This represents a concrete contribution to reducing economic and geologic risks derived from exploration activities in offshore areas. Additionally, from an operational standpoint, specific models support specialists to select the best SAR products and seasons for new acquisitions, as well as to optimize performances according to the available data.

Safety performance assessment of a marine dual fuel engine by integrating failure mode, effects and criticality analysis with simulation tools

Marine Dual Fuel engines have been proved an attractive solution to improve the shipping industry sustainability and environmental footprint. Compared to the conventional diesel engines, the use of additional components to accommodate the natural gas feeding is associated with several safety implications. To ensure the engine safe operation, appropriate engine control and safety systems are of vital importance, whilst potential safety implications due to sensors and actuators faults or failures must be considered. This study aims at investigating the safety issues of a marine dual fuel (DF) engine considering critical operating scenarios, which are identified by employing a Failure Mode, Effects and Criticality Analysis. An existing verified digital twin (DT) of the investigated DF engine, capable of predicting the engine response at steady state and transient conditions with sufficient accuracy is employed to simulate the engine operation for the identified scenarios. The simulated scenarios results analysis is used to support the risk priority number assessment and identify the potential safety implications by considering the manufacturer alarm limits. Appropriate measures are recommended for the investigated DF engine safety performance improvement. This study demonstrates a methodology integrating existing safety methods with state-of-the-art simulation tools for facilitating and enhancing the safety assessment process of marine DF engines considering both steady state conditions and transient operation with main focus on switching operating modes.

Improving the Overall Equipment Effectiveness (OEE) of Drum Testing Machine in Laboratory of Tire Manufacturing Using FMEA and PFMEA

Drum testing is equipment to test tire capability in the highway prototype in the tire company. Overall Equipment Effectiveness (OEE) is used to measure the productivity of the equipment. OEE has declined and has not achieved the target from Jun 2019 until June 2020. The objectives of this research are to determine the fixed parameter in the OEE calculation at the Drum Testing and to increase the OEE for achieving the company target. Process Failure Mode Effects Analysis (PFMEA) and Failure Mode Effects Analysis (FMEA) help to identify potential failure mode and its consequences, and formulate a solution to achieve the OEE target by improving the drum testing machine. Furthermore, an ideal target should be customized based on the manufacturing year and brand of the machine. This research showed PFMEA and FMEA successfully improve the OEE efficiency for five machines increases the average OEE from 53.6% to 67.2%.