Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A self-learning dynamic optimization method for batch processes driven by data differences

A dynamic optimization and data difference technology, applied in machine learning, program control, adaptive control, etc., can solve problems such as optimization performance limitations

Active Publication Date: 2017-10-27
JIANGNAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when optimizing the operation of a batch production process, if only one optimization is performed, the optimization performance is limited

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A self-learning dynamic optimization method for batch processes driven by data differences
  • A self-learning dynamic optimization method for batch processes driven by data differences
  • A self-learning dynamic optimization method for batch processes driven by data differences

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] This example takes a batch crystallization process as an example, and the method does not constitute a limitation of the scope of the present invention.

[0048] This method is divided into three parts. The first part is data collection and preprocessing. The second part is to calculate the initial optimization strategy. The third part is to calculate the recursive optimization strategy based on the updated batch data.

[0049]The block diagram of the implementation steps of this method is as follows: Image 6 As shown, the specific implementation steps and algorithms are as follows:

[0050] Step 1: For the complete batch crystallization process, select the temperature operating curve closely related to the product yield as the variable to be optimized, and collect 35 sets of temperature variable and final yield index data in batches. The data collection interval is 1 minute. figure 1 is an example of a temperature profile (partial) for a batch crystallization pro...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a dynamic optimization method for intermittent process self-learning driven by data difference, including off-line collection of production process data, PCA operation to eliminate singular batches, constructing period and index variance matrix to perform PLS operation to generate initial optimization strategy, and collecting new batches Secondary data, running recursive algorithm, updating optimization strategy and other steps. The present invention utilizes perturbation method to establish an initial optimization strategy for optimizing variable setting curves. On this basis, the self-learning iterative update of the mean and standard deviation is carried out based on the statistical difference of the data, and the continuous improvement of the optimization index is realized, which provides a new method for the batch process optimization strategy to solve practical industrial problems. The present invention is entirely based on the operating data of the production process, and does not require prior knowledge and mechanism models of the process mechanism. It is suitable for the dynamic optimization of the operating trajectory of batch reactors, batch rectification towers, batch drying, batch fermentation, batch crystallization and other processes and systems that operate in batch mode.

Description

technical field [0001] The invention belongs to the field of chemical process manufacturing industry, and relates to a model-free intermittent process self-learning dynamic optimization method driven by data differences. The method is suitable for the dynamic optimization of the operating trajectory of batch reactors, batch rectification towers, batch drying, batch fermentation, batch crystallization and other processes and systems operated in batch mode. Background technique [0002] Batch processes are widely used in the production and preparation of various products such as food, polymers, and pharmaceuticals, and play an important role in chemical production and process industries. With the continuous development of computer technology, process control and optimization technology, the quality control and optimization of batch process has become one of the current research hotspots in industry and academia, which is of great significance to the development of batch proces...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G05B13/02G06N20/00
CPCG05B13/0205G06N20/00G05B13/0265G05B2219/32077G05B19/042G05B13/02
Inventor 栾小丽王志国刘飞
Owner JIANGNAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products