Vessel Risk Advisory Using Variable Correlation and Operator Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Marine vessel operators face challenges in managing the overwhelming number of parameters from various systems, leading to reactionary rather than proactive maintenance, with limited ability to track nominal levels and environmental impacts, resulting in potential catastrophic failures.
Innovation Solution
A conditional online-based risk advisory system (CORBAS) utilizing machine learning to monitor vessel systems, reduce false notifications, and provide proactive alerts and optimizations by continuously monitoring variables, calculating dependencies, and learning from human interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If operators monitor all vessel system parameters manually, then system reliability improves, but operator workload and complexity increase significantly
Solution Approach 1:
The patent introduces an intermediary system (the advisory system with machine learning model) that mediates between the complex vessel system sensors and the operator. This intermediary automatically processes sensor data, identifies correlations between parameters, and presents simplified insights to operators, reducing the complexity burden while maintaining reliability monitoring.
Solution Approach 2:
The advisory system performs self-service by automatically learning from historical data, identifying parameter correlations, and generating alerts without continuous operator intervention. The system improves its performance over time through machine learning, reducing the need for complex manual monitoring configurations while maintaining high reliability standards.
2Productivity
If operators react to sensor alerts, then immediate problems are addressed, but proactive maintenance capability is lost
Solution Approach 1:
The system performs preliminary actions by proactively identifying potential failures before they occur. The machine learning model analyzes trends and correlations in real-time data to predict future failures, allowing maintenance to be scheduled in advance rather than reacting to actual failures, thus reducing downtime and improving maintenance efficiency.
Solution Approach 2:
The system implements continuous feedback loops where operator responses to alerts are fed back into the machine learning model. This feedback mechanism allows the system to learn from actual outcomes and improve its predictive accuracy over time, enhancing both proactive maintenance capability and maintenance efficiency while minimizing downtime.
3Adaptability or versatility
If environmental conditions are monitored, then operational optimizations improve, but false positive alerts increase
Solution Approach 1:
The system applies counter-weight by balancing environmental factor monitoring with correlation analysis. When environmental conditions cause parameter variations, the system checks whether these variations correlate with actual system issues or are merely environmental effects. This counter-balancing approach maintains operational adaptability while filtering out false positives caused by environmental factors.
Data Source
AI summary
An advisory system of a vessel that monitors variables of a vessel system inclusive of systems and subsystems that are used to operate the vessel. The advisory system may use machine-learning to learn from an operator (i) whether or not two variables are related to one another, and (ii) likelihood that a variable will reach a threshold, and, optionally, time until reaching the threshold. The system may receive operator feedback (i) to indicate whether the two variables are related to one another, and (ii) whether a behavior of the variable is normal or not normal. Thereafter, if a determination that the same two variables are related to one another and behaving in a similar manner, provide notification to the operator of the behavior. In response to determining that the variable is behaving (e.g., trending) in a similar manner that is not normal, providing a notification to the operator.