Data monitoring method and system used for boiling sugar crystallization process
A data monitoring and crystallization technology, which is applied in the direction of electrical digital data processing, special data processing applications, instruments, etc., can solve the problem that some parameters that cannot be boiled and crystallized cannot be directly measured, and achieve strong expansion capabilities and openness, and improve stability Sexuality and reliability, the effect of a high degree of intelligence
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0065] Example 1
[0066] like figure 1 As shown, the method includes:
[0067] Step S101: obtaining real-time process data and historical process data of the sugar-boiled crystallization process;
[0068] Obtaining historical process data is the process of selecting auxiliary variables for constructing the soft-sensor data-driven model in the process of boiling sugar and crystallization, and the historical process data is auxiliary variables, and the auxiliary variables are state parameters directly measured online in the process of boiling sugar and crystallization;
[0069] The state parameters directly measured online can include any one or more of the following: vacuum degree, massecuite temperature, massecuite liquid level, steam pressure, steam temperature, feed flow, massecuite hammer.
[0070] Step S102: normalize the historical process data, and randomly divide it into a training set and a test set, and use a twin support vector regression machine to construct a da...
Example Embodiment
[0136] Embodiment 2
[0137] The present invention also proposes a data monitoring system for cooking sugar crystallization, such as figure 2 shown, including:
[0138] A data acquisition module 010 is used to acquire real-time process data and historical process data of the sugar-boiled crystallization process;
[0139] The processing and building module 020 is used to normalize the historical process data, and randomly divide it into a training set and a test set, and use the twin support vector regression machine to construct the data on the supersaturation of the mother liquor and the purity of the mother liquor in the process of sugar boiling and crystallization drive model;
[0140] The model optimization module 030 is used to iteratively search the data-driven model according to the particle swarm optimization algorithm and the 10-fold cross-validation method, and obtain the optimized data-driven model;
[0141] A model testing module 040, configured to perform perf...
Example Embodiment
[0156] Embodiment 3
[0157] like image 3 As shown, the data measurement method for boiled sugar crystallization of the present invention includes:
[0158] Step S301: Select an auxiliary variable for constructing a soft-sensor data-driven model in the process of boiling sugar and crystallization, and the auxiliary variable is a state parameter directly measured online in the process of boiling sugar and crystallization;
[0159] The state parameters directly measured online can include any one or more of the following: vacuum degree, massecuite temperature, massecuite liquid level, steam pressure, steam temperature, feed flow, massecuite hammer.
[0160] Step S302: using the auxiliary variable as the input of the data-driven model, using the mother liquor supersaturation and the mother liquor purity as the output of the data-driven model, and constructing a data-driven model of the sugar boiling crystallization process based on the twin support vector regression machine;
...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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