AI Berthing Capacity Prediction Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current maritime vessel traffic control technologies lack objective criteria for deciding whether to berth ships at onshore and offshore structures, especially under adverse weather conditions, leading to subjective decision-making and inefficiencies.
Innovation Solution
The use of artificial intelligence (AI) techniques, specifically machine learning algorithms and statistical models integrated with historical meteorological and operational data, to predict the berthing capacity of ships through an artificial neural network (ANN) model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If subjective interpretation of meteorological variables is used for berthing decisions, then operational flexibility is maintained, but decision-making objectivity and reliability deteriorate
Solution Approach 1:
The patent replaces subjective human interpretation of meteorological data with an objective AI-based system that uses neural networks and machine learning algorithms to automatically assess berthing capacity. The system processes meteorological variables through computational models rather than human judgment, eliminating subjectivity while maintaining operational flexibility through automated decision-support capabilities.
Solution Approach 2:
The patent introduces an intermediary AI system that mediates between meteorological data and berthing decisions. This intermediary layer processes raw meteorological information through neural networks and statistical models to produce objective berthing capacity predictions, serving as a bridge between data collection and decision-making without requiring direct human interpretation of complex weather patterns.
2Measurement precision
If AI-based prediction models are implemented, then berthing capacity prediction accuracy is improved, but system complexity and data requirements increase
Solution Approach 1:
The patent applies preliminary action by pre-training neural network models and statistical algorithms using historical meteorological and operational data before actual berthing decisions need to be made. The system prepares prediction models in advance, allowing rapid and accurate berthing capacity assessment during operational periods without requiring complex real-time computations, thus reducing operational system complexity.
Solution Approach 2:
The patent utilizes parameter changes by transforming raw meteorological data into standardized input parameters for the AI models. The system processes various meteorological variables (wind speed, wave height, sea state) and converts them into normalized parameters that the neural networks can process efficiently, improving prediction accuracy while managing data complexity through standardization.
3Productivity
If historical data processing and AI model training are performed, then operational efficiency is improved, but computational resources and time consumption increase
Solution Approach 1:
The patent implements preliminary action by conducting extensive historical data processing and model training during off-peak periods or in advance, rather than performing these computationally intensive tasks in real-time during operational periods. The system pre-processes historical meteorological data and trains neural networks beforehand, so that during actual operations, only lightweight prediction inference is required, significantly reducing real-time computational resource consumption while maintaining high operational efficiency.
Data Source
AI summary
The present invention relates to methods using artificial intelligence, AI, techniques to predict the berthing capacity of ships in onshore and offshore structures and comprises embodiments of a method for training an artificial neural network, ANN, model to predict the berthing capacity of ships, a method for predicting the berthing capacity of ships, and a non-transitory computer-readable medium.