LNG Storage Pressure Forecasting With IoT Anomaly Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing LNG storage devices lack automatic and intelligent monitoring, data transmission has security risks, and pseudo data in abnormal data cannot be effectively removed, leading to inadequate prediction of pressure changes and potential safety issues.
Innovation Solution
A method using a distributed energy management platform with multiple sensors to monitor LNG storage, employing a machine learning model for real-time data analysis, pseudo data verification, and anomaly prediction to send timely alerts for maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional monitoring methods are used for LNG storage devices, then device complexity is reduced, but measurement precision and reliability of monitoring data deteriorate
Solution Approach 1:
The system segments monitoring functions into multiple specialized sensors (temperature, pressure, level, flow sensors) distributed throughout the LNG storage facility. Each sensor targets specific parameters, allowing high measurement precision for each individual parameter while keeping individual sensor complexity low. The segmentation of monitoring tasks across multiple simple components resolves the contradiction between overall system precision and individual component complexity.
Solution Approach 2:
The platform serves as an intermediary that collects, transmits, and processes data from multiple simple sensors. It mediates between the simple sensing elements and the complex analysis requirements, enabling high measurement precision through centralized processing while allowing individual sensors to remain simple. The platform handles data purification and pseudo-data removal, resolving the contradiction by centralizing complexity in the mediation layer rather than in individual sensing components.
2Reliability
If multiple sensors and real-time monitoring are implemented, then reliability of safety monitoring is improved, but use of energy and device complexity increase
Solution Approach 1:
The system implements periodic monitoring at strategically selected time points rather than continuous monitoring. The platform determines optimal monitoring time points based on LNG storage characteristics and risk factors, performing measurements periodically at these critical moments. This periodic approach maintains safety monitoring reliability by focusing resources on high-risk periods while significantly reducing overall energy consumption compared to continuous monitoring.
Solution Approach 2:
The system applies monitoring intensity selectively - using multiple sensors and frequent monitoring only when and where needed (partial action), rather than uniformly across all times and locations. The platform identifies critical monitoring zones and periods, concentrating monitoring resources on these areas to achieve high reliability where it matters most while minimizing energy consumption in low-risk areas. This selective application of monitoring resolves the contradiction between reliability and energy use.
3Productivity
If real-time data analysis and prediction models are used, then productivity of anomaly detection is improved, but device complexity and computational requirements increase
Solution Approach 1:
The platform performs self-service through automated anomaly detection and prediction algorithms that operate without constant human intervention. The system automatically collects data, applies prediction models, identifies anomalies, and generates alerts. This self-service capability improves productivity by enabling continuous automated monitoring and rapid anomaly detection, while the automation itself manages the complexity rather than requiring proportionally complex human-operated systems.
Solution Approach 2:
The system changes monitoring parameters dynamically based on storage conditions, risk levels, and historical data patterns. The platform adjusts monitoring frequency, threshold values, and prediction model parameters in response to changing conditions. This parameter adaptability improves productivity by focusing computational resources on high-risk scenarios while reducing analysis intensity during normal operations, effectively managing the complexity-productivity trade-off through flexible parameter adjustment.
Data Source
AI summary
The present disclosure discloses a method for monitoring operation of liquefied natural gas (LNG) storage, comprising: acquiring operating data of an LNG storage device, physical and chemical parameters of LNG and historical pressure change data in the LNG storage device; determining pseudo data information based on the historical pressure change data; determining at least one set of pressure change data at at least one future time point through a pressure model based on the operating data, the physical and chemical parameters, the historical pressure change data, and the pseudo data information, wherein the pressure model is a machine learning model, the pressure model includes a feature extracting layer and a pressure layer; and determining a pressure adjusting time point and preparing for a pressure adjustment based on the at least one set of pressure change data at the at least one future time point.