Dynamic Time Delay Identification Method for Industrial Production Process Based on Improved Sliding Time Window
A sliding time window, industrial process technology, applied in program control, comprehensive factory control, electrical program control, etc., can solve problems such as affecting prediction accuracy, difficult to determine dynamic delay, etc., to ensure estimation accuracy and good dynamic delay characteristics. , the effect of low algorithm complexity
Active Publication Date: 2022-05-10
CENT SOUTH UNIV
View PDF10 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] Based on the above problems, the present invention provides a dynamic time-delay identification method for industrial production processes based on improved sliding time windows, based on the strategy of static demarcation-dynamic update estimation to mine the dynamic time-delay characteristics between industrial process variables, and realize input and output variables Accurate time registration between variables solves the problem that the dynamic time delay of variables is difficult to determine and thus affects the prediction accuracy
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0049] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.
[0050] A dynamic time-delay identification method for industrial processes based on improved sliding time windows, such as figure 1 As shown, this embodiment takes the actual industrial process—the debutanizer process as an example. The debutanizer process is an important part of the desulfurization and naphtha decomposition device. One of the main tasks in this process is to reduce the butane concentration at the bottom of the debutanizer. The simplified process flow diagram of the whole process is as follows: figure 2 shown. The method includes the following steps:
[0051] S1. Obtain the input variable and output variable data of the debutanizer industrial process ...
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
Login to View More Abstract
The invention discloses a dynamic time delay identification method of an industrial process based on an improved sliding time window. The method adopts a strategy of static demarcation-dynamic update to estimate the dynamic time delay. Firstly, the static FCA method is used to estimate the overall time delay to determine the dynamic time delay. Then, based on the improved sliding time window, the delay estimation for each time window is performed to mine the dynamic delay characteristics between variables. The present invention further excavates the time delay characteristics between variables, realizes more accurate time registration between variables, and is beneficial to improving the prediction accuracy of output variables.
Description
technical field [0001] The invention relates to the technical field of complex industrial process modeling and control, in particular to a dynamic time delay identification method of an industrial production process based on an improved sliding time window. Background technique [0002] The key quality variable in the complex industrial process is an important variable to measure the production effect of the product, and its accurate prediction and control is the basis for the optimal operation of the industrial process. However, these variables often have the characteristics of high difficulty in measurement and long measurement period, so data-driven soft-sensing methods are often used to realize their prediction and control. However, in the actual industrial process, because the transmission of signals and raw materials takes time, the input and output variable data of the production process do not match in time, and the output often lags behind the input. At this time, ...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G05B19/418
CPCG05B19/41875G05B2219/32368Y02P90/02
Inventor 阳春华王威李勇刚韩洁蓝丽娟李文婷张凤雪
Owner CENT SOUTH UNIV