Vessel Risk Advisory Using Variable Correlation to Cut False Alerts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Marine vessels face challenges in managing the overwhelming number of operating parameters, leading to reactionary rather than proactive maintenance, as operators struggle to track nominal levels and respond to potential issues before they become catastrophic failures due to the complexity of vessel systems and limited displayable indicators.
Innovation Solution
A conditional online-based risk advisory system (CORBAS) utilizing machine learning to continuously monitor vessel systems, reduce false notifications, and provide proactive alerts and optimizations by correlating variables and learning from operator interactions, enabling more efficient operation and reducing downtime.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional sensor-based monitoring systems are used to track vessel system parameters, then system safety is improved through detection of abnormal conditions, but operator workload and complexity increase due to the overwhelming number of parameters that must be monitored
Solution Approach 1:
The patent introduces an intermediary processing layer between the sensors and the operator. This layer includes a processor that receives sensor signals, correlates multiple parameters to identify root causes, and generates simplified diagnostic indicators. The intermediary translates complex sensor data into actionable insights, reducing the burden on operators while maintaining system safety.
Solution Approach 2:
The system performs self-diagnosis by automatically correlating parameters and identifying abnormal conditions without requiring operator intervention for each parameter. The processor autonomously analyzes sensor data, determines correlations between parameters, and generates notifications only when actual problems are detected, allowing the system to serve itself in monitoring its own health.
2Reliability
If operators manually monitor all vessel system parameters to detect potential failures early, then maintenance effectiveness is improved, but response time deteriorates due to the inability to track all indicators simultaneously
Solution Approach 1:
The system performs preliminary analysis of parameter correlations and identifies potential failure conditions before they manifest as actual problems. By pre-establishing correlation relationships between parameters and configuring alert thresholds, the system is prepared to immediately detect and notify operators of abnormal conditions, enabling proactive maintenance before failures occur.
Solution Approach 2:
The patent replaces manual operator monitoring with an automated electronic processing system. The processor continuously analyzes sensor data, calculates parameter correlations, and generates alerts automatically, substituting the mechanical process of manual observation and analysis with an electronic system that operates at much higher speeds and without fatigue.
3Reliability
If notification systems alert operators to all parameter abnormalities, then system reliability is improved through comprehensive monitoring, but false positive notifications increase causing operator desensitization
Solution Approach 1:
The system applies different notification strategies based on the specific characteristics of each parameter and its correlation context. Rather than using a uniform alert threshold for all parameters, the system adjusts notification behavior based on local conditions including parameter interrelationships, historical data, and operational context, reducing false positives while maintaining comprehensive monitoring.
Solution Approach 2:
The system incorporates feedback mechanisms where operator responses to notifications are used to refine future alert generation. When operators confirm or dismiss notifications, this information feeds back into the system to improve correlation algorithms and threshold settings, reducing false positives over time while maintaining reliable detection of actual problems.
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.