Prediction of a Ship’s Operational Parameters Using Artificial Intelligence Techniques
نویسندگان
چکیده
The maritime industry is one of the most competitive industries today. However, there a tendency for profit margins shipping companies to reduce due an increase in operational costs, and it does not seem that this trend will change near future. important reason operating costs relates fuel prices. To compensate can either renew their fleet or try make use new technologies optimize performance existing one. software structure has changed now leaning towards Artificial Intelligence (AI) and, more specifically, Machine Learning (ML) calculating its scenarios as way reduction profit. While AI technology creating intelligent systems simulate human intelligence, ML subfield AI, which enables machines learn from past data without being explicitly programmed. been used other increasing both availability profitability, seems also great potential industry. In paper authors compares multiple regression algorithms like Neural Network (ANN), Tree Regressor (TRs), Random Forest (RFR), K-Nearest Neighbor (kNN), Linear Regression, AdaBoost, predicting output power Main Engines (M/E) ocean going vessel. These are selected because they commonly well supported by main developers area ML. For scope, measured values collected onboard Automated Data Logging & Monitoring (ADLM) system vessel period six months have used. study shows ML, with proper processing parameters based on fundamental knowledge naval architecture, achieve remarkable prediction results. With proposed method was vast computational needed calculations, maximum absolute error value prediction.
منابع مشابه
On Applying Artificial Intelligence Techniques to Building Sea-Going Ships
Sea-going ships are autonomous complex objects that are intensively automatized due to safety and economic factors. The issue is complicated enough to entail a need for powerful methods such as Artificial Intelligence techniques. This repon gives a brief description of several problems of ship-building for which Artificial Intelligence techniques seem to be particularly suitable. They include: ...
متن کاملSolar Flare M-class Prediction Using Artificial Intelligence Techniques
Currently, astronomical data have increased in terms of volume and complexity. To bring out the information in order to analyze and predict, the artificial intelligence techniques are required. This paper aims to apply artificial intelligence techniques to predict M-class solar flare. Artificial neural network, support vector machine and naïve bayes techniques are compared to define the best pr...
متن کاملOptimal Selection of Active Suspension Parameters Using Artificial Intelligence
In this paper, multi-objective uniform-diversity genetic algorithm (MUGA) with a diversity preserving mechanism called the ε-elimination algorithm is used for Pareto optimization of 5-degree of freedom vehicle vibration model considering the five conflicting functions simultaneously. The important conflicting objective functions that have been considered in this work are, namely, vertical accel...
متن کاملArtificial intelligence techniques for the prediction of bladder cancer progression
New techniques for the prediction of tumour behaviour are needed since statistical analysis has a poor accuracy and is not applicable to the individual. Artificial Intelligence (AI) may provide these suitable methods. We have compared the predictive accuracies of neuro-fuzzy modelling (NFM), artificial neural networks (ANN) and traditional statistical methods, for the behaviour of bladder cance...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Marine Science and Engineering
سال: 2021
ISSN: ['2077-1312']
DOI: https://doi.org/10.3390/jmse9060681