A Batch Process Mode Identification Method Based on Bayesian Statistical Analysis

A technology of modal recognition and statistical analysis, applied in character and pattern recognition, computing, computer components, etc., can solve problems such as difficulty in parameter selection, large time complexity of iterative process, ignoring time sequence constraints of intermittent process data, etc., to achieve improved The effect of accuracy

Active Publication Date: 2021-10-01
BEIJING UNIV OF CHEM TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Data-driven clustering analysis methods are widely used in batch process modal identification, such as K-means clustering method, fuzzy C-means clustering method, affine propagation clustering method, etc. During modal identification, the modal identification results are greatly affected by outliers in the process data, the iterative process has a large time complexity, and the timing constraints of intermittent process data are ignored, and parameter selection is difficult

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 Batch Process Mode Identification Method Based on Bayesian Statistical Analysis
  • A Batch Process Mode Identification Method Based on Bayesian Statistical Analysis
  • A Batch Process Mode Identification Method Based on Bayesian Statistical Analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0073] Penicillin fermentation is a typical batch process. Pensim v2.0 was used to simulate the penicillin fermentation process, and the substrate flow acceleration (L h -1 ), substrate concentration (g L -1 ), dissolved oxygen concentration (g L -1 ), biomass concentration (g L -1 ), penicillin concentration (g L -1 ), heat production (kcal·h -1 ) 6 process variables for data collection, as shown in Table 1. The sampling period is selected as 1h, and 20 batches of data are collected, each containing 400 data points. 15 batches are randomly selected as training batches, and the remaining 5 batches are used as test batches.

[0074] Table 1 Batch Process Variables

[0075]

[0076] Apply the method of the present invention to the modal recognition of the above-mentioned penicillin fermentation process, specifically implement according to the following steps:

[0077] Step 1: The three-dimensional process data of 20 batches of penicillin fermentation process Expand a...

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 batch process mode recognition method based on Bayesian statistical analysis, which belongs to the technical field of batch process monitoring. This method first expands the 3D historical process data of the batch process into 2D data along the batch method and standardizes the expanded data; secondly uses the fuzzy C-means clustering algorithm to perform cluster analysis on the standardized process data, setting The membership rules of the fixed mode rough division are obtained to obtain the results of the rough division of the mode; finally, the Bayesian network classifier is used to analyze the results of the rough division of the mode, and the mode inference coefficient of the time sequence constraint is introduced, and the minimum risk criterion is inferred according to the mode, Determine the final attribution of the mode and realize the mode recognition of the intermittent process. This method fully considers the time series constraints of the batch process data, and uses Bayesian statistical analysis to realize the effective division of the stable mode and the transition mode of the batch process, and has high mode recognition accuracy.

Description

technical field [0001] The invention relates to a batch process mode recognition method, which belongs to the technical field of batch process monitoring, in particular to a batch process mode recognition method based on Bayesian statistical analysis. Background technique [0002] As an important production mode in industrial production, batch process has multiple operating states and multi-modal characteristics, which makes the process characteristics of batch process different in different modes, and the correlation of variables is also significantly different. If the process data of different modes are modeled with the same model, it will lead to large modeling errors, which limits the application of the built model in the batch process. Therefore, it is necessary to accurately identify multiple modes with obvious differences in the batch process, so as to provide a basis for the monitoring and control optimization of the batch process. [0003] The existing 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): G06K9/62
CPCG06F18/23213G06F18/29
Inventor 王建林熊欢邱科鹏韩锐于涛
Owner BEIJING UNIV OF CHEM TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap