Unlock instant, AI-driven research and patent intelligence for your innovation.

Adaptive sequence sampling algorithm based on cross validation

A cross-validation and self-adaptive technology, applied in the direction of computing, special data processing applications, instruments, etc., can solve problems such as unbalanced, and achieve the effect of improving efficiency, improving prediction accuracy, and improving optimization efficiency

Inactive Publication Date: 2014-01-01
DALIAN UNIV OF TECH
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing adaptive sequence sampling algorithms are still unable to achieve a flexible balance between local mining and global exploration

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
  • Adaptive sequence sampling algorithm based on cross validation
  • Adaptive sequence sampling algorithm based on cross validation
  • Adaptive sequence sampling algorithm based on cross validation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] There are three key points in the whole algorithm: 1) segment the design space with Thiessen diagram method; 2) identify sensitive polygonal areas; 3) collect new test points in the obtained sensitive areas.

[0028] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described below in conjunction with the accompanying drawings and specific examples.

[0029] Assuming that in the current iteration step, there is already a set of sample points P, the specific implementation process of obtaining the next sample point is as follows:

[0030] Step1. Divide the design space with Thiessen diagram method.

[0031] Each Thiessen polygon area C i is the test point p i The adjacent area of ​​, the segmentation diagram is shown in figure 1 . Because the boundary of the Thiessen polygon area is irregular, the Monte Carlo method is used to approximate the Thiessen polygon area C i . Specifical...

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 belongs to the field of engineering design and optimization and relates to an adaptive sequence sampling algorithm based on cross validation. The algorithm is characterized by including the steps of cutting design space into a series of Thiessen polygons according to existing test points by a Thiessen graphic method, and describing each Thiessen polygon by the Monte Carlo method; estimating error characteristics of a Thiessen polygonal area by a cross validation method, and selecting the Thiessen polygonal area with the largest error as a sensitive area; selecting a next test point in the recognized sensitive area by a local filling method; checking whether the algorithm meets an end condition or not; if yes, ending sampling; if not, restarting. The algorithm is simple, efficient and widely applicable and is available for acquiring relatively accurate approximate models with few test points, so that the cost of computing engineering design and optimization problems is saved greatly and work efficiency is improved.

Description

technical field [0001] The present invention is in the field of engineering design and optimization. Specifically, it relates to an adaptive sequence sampling algorithm based on cross-validation. Background technique [0002] In recent years, approximate model (Surrogate models) technology has been widely used in engineering optimization design problems based on high-precision numerical simulation analysis. The approximate model can provide a good prediction function, reduce the number of numerical simulation analysis in the optimization design process, and greatly improve the design efficiency. [0003] For engineering optimization design problems based on approximate models, the prediction accuracy of the approximate models is very important. If the predicted value of the approximate model differs greatly from the real value, effective optimization design based on the approximate model cannot be carried out. Of course, the more test points used to construct the approxim...

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
IPC IPC(8): G06F17/50
Inventor 徐胜利刘海涛王晓放
Owner DALIAN UNIV OF TECH