Fluid Pressure Control Stations Using Demand Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fluid distribution networks face challenges in accurately controlling fluid pressure in response to changing environmental conditions, leading to inefficiencies such as excessive pressure that increases leakage and fails to meet statutory minimum requirements.
Innovation Solution
A computing device uses a machine learning algorithm to predict fluid demand based on environmental conditions, allowing pressure-control stations to adjust settings in advance to match anticipated demand, thereby optimizing fluid pressure conditions at predetermined points in the network.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If gas supply pressure is set high to prepare for worst case scenario, then consumer service levels are maintained, but gas leakage increases
Solution Approach 1:
The system performs preliminary action by predicting future gas demand based on environmental conditions (weather forecasts, historical data) and pre-adjusting the gas supply pressure before peak demand occurs. This allows the system to maintain consumer service levels during high demand without continuously operating at high pressure that would cause leakage during low demand periods.
Solution Approach 2:
The system implements dynamic pressure adjustment by continuously monitoring environmental conditions and demand patterns, then varying the gas supply pressure in real-time response to changing conditions. This replaces static high-pressure operation with dynamic pressure control that matches actual demand, reducing leakage while maintaining service levels.
2Loss of substance
If gas supply pressure is reduced to minimize leakage, then environmental impact decreases, but pressure may fall below statutory minimum requirement
Solution Approach 1:
The system predicts upcoming demand increases based on environmental conditions (e.g., forecasted cold weather indicating heating demand) and proactively increases pressure before demand peaks, ensuring statutory minimum pressure is maintained without needing to operate at high pressure continuously.
Solution Approach 2:
The system uses feedback from environmental condition monitoring and historical demand data to continuously adjust pressure control decisions. By incorporating real-time and forecasted environmental data into the control loop, the system can maintain pressure compliance while minimizing excess pressure that causes leakage.
3Device complexity
If manual pressure setting is used at governor stations, then system complexity is reduced, but responsiveness to changing environmental conditions deteriorates
Solution Approach 1:
The system implements self-service by using automated algorithms that independently analyze environmental conditions, predict demand patterns, and adjust pressure settings without manual intervention. This maintains the simplicity of centralized control while achieving adaptive responsiveness to changing conditions.
Solution Approach 2:
The system replaces manual mechanical pressure adjustment with automated computational algorithms that process environmental data and generate control signals. This substitution maintains operational simplicity while dramatically improving adaptability to environmental changes.
4Ease of operation
If clock-based automatic pressure change is implemented, then operational simplicity is improved, but accuracy in matching actual demand deteriorates
Solution Approach 1:
The system improves upon fixed clock-based schedules by dynamically changing pressure control parameters based on actual environmental conditions and learned demand patterns. Instead of following predetermined time-based profiles, the system adapts pressure settings to match actual demand drivers such as weather conditions, achieving both automation and accuracy.
Data Source
AI summary
A method performed by a computing device for controlling fluid pressure in a fluid distribution network (FDN) above a threshold pressure by communicating with a plurality of pressure control stations distributed throughout the FDN to independently control a fluid pressure at each of the plurality of pressure control stations is provided. The method comprises training a machine learning algorithm to establish one or more correspondences between a measured variation in fluid demand in the FDN for a first time period and measured environmental conditions for the first time period. The method comprises predicting a variation in fluid demand in the FDN for a second, later time period based on predicted environmental conditions for the second time period and the established one or more correspondences between the measured variation in fluid demand in the FDN for the first time period and the measured environmental conditions for the FDN for the first time period. The method comprises determining, based on the predicted variation in fluid demand for the second time period, a variation in fluid pressure to be applied at the plurality of pressure control stations for the second time period to satisfy a fluid pressure condition at one or more pre-determined points in the FDN downstream from the plurality of pressure control stations. The method comprises transmitting, to the plurality of pressure control stations, an indication of the determined variation in fluid pressure to be applied at the plurality of pressure-control stations for the second time period to satisfy the fluid pressure condition at the one or more pre-determined points in the FDN.