Model-Free Online Recursive Optimization for Batch Processes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for optimizing batch processes in industrial production are laborious, time-consuming, and lack effective real-time online optimization strategies, making it difficult to adapt to uncertainties and changes in feedstock or products, especially in batch reactors, rectifying towers, and fermentation processes.
Innovation Solution
A data-driven online recursive optimization method that decomposes batch process data into variable periods, integrates optimization actions through principal component analysis, and implements online recursive error correction without requiring prior knowledge or a process model, forming a global optimization strategy adaptable to real-time changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If model-based offline optimization method is used, then optimal operation curve can be obtained under ideal conditions, but it cannot adapt to uncertainties and disturbances in real-time operation
Solution Approach 1:
The batch process is divided into multiple periods based on time-domain characteristics. Each period is optimized independently using recursive least squares estimation, allowing the system to adapt to local changes while maintaining overall optimization goals. This segmentation enables real-time adaptation without requiring complete remodelling of the entire process.
Solution Approach 2:
The optimization method transitions from static offline optimization to dynamic online optimization by continuously updating parameter estimates during batch operation. The recursive least squares algorithm dynamically adjusts the operation curve based on real-time deviation measurements, making the system adaptive to uncertainties and disturbances.
2Adaptability or versatility
If experience-based operation curve method is used, then operational knowledge can be utilized, but the method is laborious, time-consuming and difficult to standardize
Solution Approach 1:
The system implements feedback by measuring actual process deviations from the reference operation curve and using these measurements to recursively update parameter estimates. This automated feedback loop replaces manual experience-based adjustments with systematic, standardized optimization that can be efficiently replicated across different batches.
Solution Approach 2:
The optimization system performs self-adjustment by automatically updating its own parameters based on real-time process data. The recursive least squares algorithm enables the system to learn from past performance and autonomously optimize future batches without requiring external expert intervention, thereby standardizing and accelerating the optimization process.
3Adaptability or versatility
If online real-time optimization is implemented, then adaptability to feedstock changes and process conditions is improved, but device complexity and computational requirements increase
Solution Approach 1:
The system performs preliminary estimation of optimal parameters offline before actual batch operation begins. These pre-computed parameters serve as initial values for the online recursive optimization, reducing the computational burden during real-time operation while maintaining adaptability to process changes.
Solution Approach 2:
The method replaces complex mechanical or manual optimization systems with a computational approach based on recursive least squares estimation. This substitution uses simple mathematical relationships and linear algebra operations that can be efficiently implemented on standard computers, achieving real-time optimization without requiring complex hardware systems.
Data Source
AI summary
The present invention discloses a model-free online recursive optimization method for a batch process based on variable period decomposition. Variable operation data closely related to product quality is acquired, optimization action on each subset is integrated on the basis of time domain variable division on the process by utilizing a data driving method and a global optimization strategy is formed, based on which an online recursive error correction optimization strategy is implemented. According to the method, the online optimization strategy is formed completely based on the operation data of the batch process without needing prior knowledge or a model of a process mechanism. Meanwhile, the optimized operation locus line has better adaptability by using the online recursive correction strategy, and thus the anti-interference requirement of the actual industrial production is better met.