A Method for Predicting the Mechanical Properties of Strips
A technology of performance prediction and mechanics, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as unstable prediction accuracy and poor generalization ability, and achieve improved prediction accuracy, good application prospects, and improved prediction The effect of stability and generalization ability
Active Publication Date: 2021-04-02
UNIV OF SCI & TECH BEIJING
View PDF8 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The technical problem to be solved by the present invention is to provide a method for predicting the mechanical properties of strips to solve the problems of unstable prediction accuracy, poor generalization ability and lack of accuracy evaluation of prediction results in the prediction models existing in the prior art
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
[0051] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will describe in detail with reference to the drawings and specific embodiments.
[0052] The invention provides a method for predicting the mechanical properties of strips, aiming at the problems of unstable prediction accuracy, poor generalization ability and lack of accuracy evaluation of prediction results in the existing prediction models.
[0053] like figure 1 As shown, the method for predicting the mechanical properties of strips provided by the embodiments of the present invention includes:
[0054] S101, collect data related to the mechanical properties of the strip, and use the collected data to train multiple mechanical performance prediction sub-models describing the differences between samples; wherein, different mechanical performance prediction sub-models have the same structure, but each mechanical performance prediction...
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 provides a plate strip mechanical property prediction method, which realizes accuracy evaluation of a mechanical property prediction result while improving model prediction precision andgeneralization ability. The method comprises the following steps: collecting plate strip mechanical property related data, and training a plurality of mechanical property prediction sub-models for describing differences among samples by utilizing the collected data; wherein the structures of different mechanical property prediction sub-models are the same, and each mechanical property predictionsub-model has independent model parameters; obtaining a to-be-tested sample, and predicting the mechanical properties of the to-be-tested sample by adopting the plurality of mechanical property prediction sub-models; evaluating the accuracy of the prediction result of each mechanical property prediction sub-model, and selecting the mechanical property prediction sub-model with the highest accuracyvalue as a target sub-model; and outputting a prediction result of the target sub-model as a final mechanical property prediction value, and evaluating the final mechanical property prediction valueby utilizing the accuracy value of the target sub-model. The invention relates to the field of strip mechanical property prediction.
Description
technical field [0001] The invention relates to the field of predicting the mechanical properties of strips, in particular to a method for predicting the mechanical properties of strips. Background technique [0002] The prediction of mechanical properties of the strip refers to the use of the chemical composition and process parameters of the strip to predict the mechanical properties of the strip after rolling. It has high application value in actual production, such as mechanical property prediction, sampling reduction, and production optimization. Technology and development of new steel grades, etc. [0003] The current mechanical performance prediction models are mainly divided into two types: mechanism model and data model. Most of the mechanism models are established on the basis of laboratory research. Due to the large errors in the actual field production data, the data quality is difficult to guarantee, resulting in poor application effects; and the data model ove...
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): G06F30/20G06N3/08G06F119/14
CPCG06N3/08
Inventor 宋勇李飞飞
Owner UNIV OF SCI & TECH BEIJING