Fluidic Network Forecast Control for Sewer Overflow Prevention
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Fluidic networks, such as sewerage systems, face challenges with spillage and overflow into the natural environment due to inadequate control, necessitating an efficient operational configuration to minimize investments while enhancing performance.
Innovation Solution
A dynamic control method for fluidic networks using a supervision module that generates operational forecasts based on hydraulic models, incorporating metrological and meteorological data, with online calibration and real-time regulation instructions to optimize network management, including the use of metrology equipment data and weather forecasts to select control strategies and transmit instructions to actuators.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a hydraulic model with online calibration is used for operational forecast, then the measurement precision and reliability of network state prediction is improved, but the computing time and processing complexity increases
Solution Approach 1:
The system performs preliminary calibration of the hydraulic model using historical data and meteorological forecasts before the operational forecast period begins. This pre-calibration establishes baseline parameters that reduce the computational burden during real-time forecasting, allowing the system to maintain high prediction accuracy while reducing processing time during critical decision-making windows.
Solution Approach 2:
The system dynamically adjusts the level of model calibration and forecast detail based on the operational context. During periods of stable conditions, simplified models are used for faster processing. During critical periods such as anticipated overflow events or extreme weather, the system automatically increases model fidelity and calibration depth, optimizing the balance between accuracy and computing time in real-time.
2Reliability
If real-time control strategies are implemented with frequent data processing, then the reliability of spillage prevention is improved, but the device complexity and processing requirements increase
Solution Approach 1:
The control system is segmented into multiple independent modules: meteorological data processing module, hydraulic model calibration module, forecast generation module, and control strategy execution module. Each module operates semi-independently with defined interfaces, allowing the system to maintain high reliability through modular fault isolation while reducing overall complexity by eliminating the need for a monolithic complex system.
Solution Approach 2:
The patent introduces an intermediary data validation and prioritization layer that filters and ranks incoming data before processing. This intermediary layer validates meteorological forecasts, prioritizes critical sensor data, and filters out redundant information, thereby reducing the complexity burden on downstream control modules while maintaining reliable spillage prevention through comprehensive data coverage.
3Measurement precision
If comprehensive metrological and meteorological data are collected and processed, then the operational forecast accuracy is improved, but the loss of time for data validation and processing increases
Solution Approach 1:
Meteorological data and model parameters are pre-validated and pre-processed before the operational forecast period begins. Historical meteorological patterns are pre-analyzed and stored in optimized formats, and sensor calibration data are pre-computed. This preliminary preparation significantly reduces the time required for data validation during real-time forecasting while maintaining comprehensive data quality for accurate predictions.
Solution Approach 2:
The system dynamically prioritizes data processing based on forecast urgency and data criticality. During normal operations, comprehensive data validation is performed to maximize accuracy. During time-critical situations such as approaching overflow thresholds or extreme weather events, the system automatically adjusts validation depth and processing speed, focusing computational resources on the most critical parameters while maintaining acceptable forecast accuracy.
Data Source
AI summary
Disclosed is a method for dynamically controlling a fluidic network with a supervising module, the method including: an operation-forecasting step that generates a forecast datum relating to operation of the fluidic network; a step of selecting a control strategy for the fluidic network on the basis of a metrological datum and/or a meteorological datum and/or the forecast datum; a step of generating setpoints intended for an actuator of a unit for regulating the fluidic network, on the basis of the selected control strategy, the metrological datum or the meteorological datum or the forecast datum; and transmitting the regulation setpoint to the actuator.