The maritime industry is displaying notable interest in the adoption of cutting-edge technologies within the scope of Industry 4.0, aiming to digitalize both companies and processes. At the core of data science lies machine learning, which serves as the focal point of this article. This study seeks to accomplish two main objectives: firstly, an exploration of various machine learning algorithms, and subsequently, the application of these techniques to analyze predictions within the propulsion system of a 9500 TEU container ship. The outcomes of the study reveal that utilizing distinct machine learning algorithms for predicting braking performance yields a lower mean square error (MSE) when compared to the discrepancy introduced by the J. Mau formula, as evident in the container ship database. The selection of propulsion engines was based on predictions for a 9500 TEU container ship. Similarly, promising outcomes were achieved in predicting propeller diameter in comparison to conventional methods. Thus, these predictions can also effectively guide the appropriate choice of propeller diameter.
The maritime industry is displaying notable interest in the adoption of cutting-edge technologies within the scope of Industry 4.0, aiming to digitalize both companies and processes. At the core of data science lies machine learning, which serves as the focal point of this article. This study seeks to accomplish two main objectives: firstly, an exploration of various machine learning algorithms, and subsequently, the application of these techniques to analyze predictions within the propulsion system of a 9500 TEU container ship. The outcomes of the study reveal that utilizing distinct machine learning algorithms for predicting braking performance yields a lower mean square error (MSE) when compared to the discrepancy introduced by the J. Mau formula, as evident in the container ship database. The selection of propulsion engines was based on predictions for a 9500 TEU container ship. Similarly, promising outcomes were achieved in predicting propeller diameter in comparison to conventional methods. Thus, these predictions can also effectively guide the appropriate choice of propeller diameter. Read More
Related posts:
Prediction of air traffic complexity through a dynamic complexity indicator and machine learning models
Machine learning based methods for ratemaking health care insurance
Monteloeder Launches BeRelief Botanical Ingredient
Red Hat acquires tech to lower the cost of machine learning
Linking Developing Country Firms’ Relational Capital to Their Export Performance in Global Value Chains: The Moderating Role of Technological Turbulence
Network anomaly detection using Machine Learning techniques