Pump Tripping Risk Prediction for LNG Carrier Tanks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Sealed and thermally insulating tanks on ships transporting liquefied gases face challenges with pump tripping due to sloshing phenomena, which can lead to cavitation and damage, as the pump-head may become uncovered when the tank is nearly empty, especially during ship movements.
Innovation Solution
A monitoring method that estimates a tripping risk parameter for the pump using computational fluid dynamics or supervised machine learning, considering the net positive suction head, tank filling level, and ship movement, providing users with an indication to take necessary measures to prevent pump tripping, such as adjusting ship course or speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the pump-head is arranged in proximity to a lower wall of the tank to maximize liquid suction, then the useful volume of liquid cargo is optimized, but the pump-head may become uncovered during sloshing when the tank is nearly empty, causing cavitation and pump tripping
Solution Approach 1:
The system performs preliminary assessment of sloshing conditions using CFD simulations and machine learning models to predict pump tripping risk before it occurs. By evaluating parameters such as tank filling level, ship motion, and liquid properties in advance, the system enables proactive intervention through warnings and automated responses, preventing pump tripping while maintaining optimal pump-head positioning for maximum cargo volume
Solution Approach 2:
The monitoring system continuously tracks operating parameters including tank filling level, ship motion, and pump performance, feeding this data back to the risk assessment algorithms. This real-time feedback loop allows the system to dynamically adjust warnings and control signals to the pump and ship operations, maintaining reliable pump operation while optimizing cargo discharge efficiency
2Productivity
If the tank filling level is reduced to maximize cargo discharge efficiency, then productivity increases, but the risk of pump-head uncovering due to sloshing increases, leading to cavitation and damage
Solution Approach 1:
The system performs preliminary assessment of sloshing conditions using CFD simulations and machine learning models to predict pump tripping risk before it occurs. By evaluating parameters such as tank filling level, ship motion, and liquid properties in advance, the system enables proactive intervention through warnings and automated responses, preventing pump tripping while maintaining optimal pump positioning for maximum cargo volume
Solution Approach 2:
The system dynamically adjusts operational parameters including pump speed, discharge rate, and ship motion based on real-time risk assessment. By changing these parameters in response to predicted tripping risk, the system maintains safe operation at lower filling levels, thereby preserving cargo discharge efficiency without increasing pump tripping risk
3Measurement precision
If computational fluid dynamics simulations are used to predict liquid-gas interface position and tripping risk, then prediction accuracy is improved, but computational time and complexity increase
Solution Approach 1:
CFD simulations are performed in advance to establish baseline sloshing behavior and tripping risk characteristics for different tank filling levels and ship motion conditions. These pre-computed results are stored and used to train machine learning models, enabling rapid real-time predictions without requiring extensive CFD computations during actual pump operations
Solution Approach 2:
Machine learning models serve as an intermediary between complex CFD simulations and real-time operational decision-making. The ML models are trained on CFD data to capture the essential relationships between tank filling level, ship motion, and tripping risk, enabling fast predictions during operations without requiring direct CFD computation
4Reliability
If a monitoring system with real-time prediction is implemented to prevent pump tripping, then pump reliability is improved, but system complexity and cost increase
Solution Approach 1:
The monitoring system leverages existing sensors and data infrastructure on LNG carriers, using the same sensors that monitor tank filling levels and ship motion for additional tripping risk assessment functions. By reusing existing data sources and integrating with existing control systems, the solution improves pump reliability without requiring a completely new complex system
Solution Approach 2:
The system uses automatically collected operational data and algorithmic risk assessment to generate warnings and control signals without requiring continuous manual monitoring or intervention. The automated nature of the system reduces operational complexity while maintaining high reliability through continuous real-time assessment
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The method significantly reduces the risk of pump tripping and associated damage by allowing timely interventions based on accurate predictions of the tripping risk, ensuring the pump operates safely and efficiently even in challenging sea conditions.
Implementation Method 1
estimating the tripping risk parameter either on the basis of a simulation of the evolution of the position of the liquid-gas interface inside the tank by a method of computational fluid dynamics (CFD)
Implementation Method 2
or with the aid of a predictive model trained by a supervised machine learning method
Implementation Method 3
such uncovering of the pump-head may cause the occurrence of cavitation phenomena in the pump
Data Source
AI summary
The invention relates to monitoring and predicting the operation of a pump (30) arranged in a tank (3) for transporting a liquid product on board a ship (1), the pump (30) having a pump-head (31) arranged in the tank (3). A tripping risk parameter of the pump (30) is estimated at least as a function of a required net positive suction head of the pump (30), of the current filling level of the tank and of a current state of movement, which is a current sea state and/or a current state of movement of the ship, and a user is provided with an indication as a function of said tripping risk parameter.A particular application to ships for transporting a cold liquid product, more particularly to ships for transporting LNG of the type which consume the boil-off gas for their propulsion.