Coagulant Dosing Control During Manual-to-Automatic Handover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing water treatment systems face challenges in accurately determining coagulant dosage due to model instability and overfitting, particularly during transitions from manual to automatic control, leading to potential inaccuracies and model instability.
Innovation Solution
A control system at the water treatment plant operates with a computing system executing model predictive control models, incorporating dynamic models and feedback from manual overrides to synchronize and adjust coagulant dosage, ensuring accurate predictions and synchronization during mode transitions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If model predictive control is used to determine coagulant dosage, then coagulation efficiency is improved, but model instability occurs during transitions from manual to automatic control
Solution Approach 1:
The system incorporates feedback mechanisms where the dynamic model continuously receives actual process data and adjusts predictions accordingly. During transitions between manual and automatic control modes, feedback ensures the model adapts to changing conditions, maintaining stability while preserving predictive accuracy for coagulant dosage optimization.
Solution Approach 2:
The control system employs a dynamic model that adapts to changing operational conditions in real-time. During mode transitions, the model dynamically adjusts its parameters and predictions based on current process states, allowing the system to maintain both high coagulation efficiency and model stability despite transitions between control modes.
2Measurement precision
If automated control model is used, then dosing accuracy is improved, but overfitting occurs leading to model instability
Solution Approach 1:
The system dynamically adjusts model parameters based on operating conditions and data quality. By changing parameters adaptively rather than using fixed values, the model maintains dosing accuracy across different scenarios while avoiding overfitting to specific conditions, thus preserving model stability.
Solution Approach 2:
The control system applies partial automation where the dynamic model provides predictions and recommendations, but final dosing decisions can incorporate manual oversight or adjusted parameters. This partial application of automated control maintains accuracy benefits while reducing the risk of overfitting and model instability.
3Ease of operation
If manual override is allowed, then operational flexibility is improved, but model synchronization is disrupted
Solution Approach 1:
When manual overrides occur, the system implements feedback mechanisms where actual manual dosing actions are fed back to the dynamic model. This allows the model to learn from and adapt to manual interventions, maintaining synchronization and predictive accuracy while preserving operational flexibility for manual control when needed.
Data Source
AI summary
Systems and methods for coagulation optimization may include a control system deployed at the water treatment plant operating with a computing system executing various control model(s). The computing system may receive data including one or more water quality metrics and a settled turbidity setpoint of output water. The computing system may also receive a manual input corresponding to a dose of coagulant received during a manual override (e.g., at a first time instance). The control model(s) may determine the recommended dose of coagulant, while accounting for the manual input and the one or more metrics. When the control system has a handover from manual mode to automatic mode, the computing system may determine a recommended dose of coagulant based on the input data and the manual input. The computing system may transmit data corresponding to the recommended dose of coagulant to the control system of the water treatment plant.