Hybrid Process Simulation Correction for Nonlinear Operating Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional process simulation systems rely on fixed gain and bias to correct model predictions, which fail to account for non-linear behavior in industrial processes, leading to inaccuracies and inefficiencies.
Innovation Solution
A hybrid process simulation model combining a first principles model with a data-driven model, such as a neural network, to generate error predictions and correct model predictions as a function of operating conditions, improving prediction accuracy and enabling offline simulation studies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If conventional process simulation systems use fixed gain and bias to correct model predictions, then the correction method is simple and easy to implement, but the prediction accuracy deteriorates due to inability to account for non-linear behavior
Solution Approach 1:
The patent transforms the static correction parameters (fixed gain and bias) into dynamic parameters that vary with operating conditions. The neural network learns optimal correction parameters as functions of process variables, enabling the system to adapt to non-linear behavior while maintaining implementation feasibility through automated parameter adjustment.
Solution Approach 2:
The patent introduces dynamics into the correction system by using a neural network that continuously adapts correction parameters based on current operating conditions. This dynamic approach replaces static fixed gain and bias with living parameters that evolve with process state, capturing non-linear relationships without requiring complex manual tuning.
2Measurement precision
If multiple simulations are performed to achieve accurate predictions, then prediction accuracy improves, but computing time and resource consumption increase
Solution Approach 1:
The patent performs preliminary action by training the neural network offline using historical simulation data and ground truth measurements. This pre-training phase captures complex non-linear relationships in advance, so that during online operation, the system only needs to apply the learned correction function rather than running multiple simulations, dramatically reducing computing time while maintaining accuracy.
Solution Approach 2:
The patent introduces a neural network as an intermediary between the process simulation model and the final prediction. This intermediary learns the discrepancy patterns from multiple simulations during training, then applies learned corrections in real-time without requiring actual multiple simulations, thus achieving accuracy benefits while avoiding time costs during operation.
Data Source
AI summary
Embodiments of the disclosure provide for generating optimal model prediction for process simulation. Some embodiments receive input dataset associated with the operation of an industrial plant, generates one or more predictions based on the input dataset and using a hybrid process simulation model. The one or more predictions may include FP model-predicted data indicative of predicted value for each of one or more process variables and error prediction indicative of a discrepancy between the FP model-predicted data and ground-truth data for the one or more process variables. Optimal model-predicted data may be generated based on the FP model-predicted data and the error prediction the optimal model-predicted data may be indicative of optimal process simulation output. Performance of one or more prediction-based actions may be initiated based on the optimal model-predicted data.