Unlock instant, AI-driven research and patent intelligence for your innovation.
A Batch Process Model Building Method
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A model building and batch processing technology, applied in the direction of program control, electrical program control, comprehensive factory control, etc., to achieve the effect of conveniently establishing accurate analysis models
Active Publication Date: 2020-09-15
点睛数据科技(杭州)有限责任公司
View PDF10 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
Through the real multivariate analysis method, the batch process model is determined based on the characteristics, so that the shortcomings of the existing batch process model can be solved, and a stable model can be provided for the monitoring of the batch process
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0021] Refer below figure 1 Detailed description.
[0022] Such as figure 1 As shown, the basic process is:
[0023] Step S110, selecting several sets of high-quality batch process data by evaluating the response effect on the existing batch process monitoring data;
[0024] Step S120, for all samples, adopt multivariate analysis method to obtain PCA (Principal Component Analysis) principal components;
[0025] Step S130, selecting an appropriate number of principal components according to the scores;
[0026] Step S140, draw all the samples on the same score map according to the determined principal component scores;
[0027] Step S150, through the search algorithm, determine the relative positioning points of each development process of different batches;
[0028] In step S160, the upper and lower limits are composed of the average value of multiple batches and a certain amount of standard deviation, and the development channel of the batch process is established;
[0...
Embodiment 2
[0031] Embodiment 2: This embodiment is a further description of Embodiment 1.
[0032] In steps S120 and S130, the original monitoring variables are transformed into several principal components by PCA principal component analysis method through multivariate analysis method, and then the final number of principal components is determined according to the scores of each principal component. Usually, one or two or three principal components are selected, and of course there is no limit to the number of principal components selected. Through the conversion of this step method, the batch process model established by the conventional method based on the concept of 'time' is transformed into a model based on the principal component score, so that the shortcomings of the conventional method such as uneven batches and inconsistent time can be solved.
[0033] In step S140, the scores corresponding to the principal component scores of all samples are plotted on the same score map. Al...
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 model establishing method for a batch processing process, and relates to a modeling method for a batch processing production process. The method can adapt to a non-uniform batch length, an unknown real starting time point, the phase change and the non-uniform reaction time. The method comprises the following steps of: collecting a plurality of batches of high-quality normal operation condition data, obtaining principal components of each batch by adopting a multivariable analysis method, selecting a proper number of principal components according to scores of the principal components, and drawing a trajectory diagram; determining a common relative starting point and a common relative terminal point of different batches in the trajectory diagram through adoption ofa search algorithm; determining an average track of the whole batch processing process on the basis of calculation of all high-quality samples; and finally, forming the development track of the batchprocess by taking the average track as a center and adding a certain standard deviation. According to the method, the defect that the sample set trajectory is artificially and subjectively searched by a conventional method is eliminated. Batch process modeling of various batch lengths and uneven process development can also be processed.
Description
technical field [0001] The invention relates to a modeling method for batch production processes. Background technique [0002] Batch production processes widely exist in the production processes of various industries, such as pharmaceutical, food processing and chemical production industries. In the usual batch production process, various raw materials are mixed in corresponding containers before chemical, physical or biological transformation reactions occur, and then the final product is produced through certain processes and steps. In many cases, the control of a batch process is determined by the recipe. In the production process, the reaction conditions of the batch process are adjusted according to the detected parameter changes to achieve the best product quality, that is, the production is pushed to the desired state through the control mechanism. Through the analysis of the high-quality process (HQP, High Quality Process) data set of the known batch, the model de...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More