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

Dynamic tuning method of scheduling strategy parameters for dense library equipment based on machine learning

A scheduling strategy and machine learning technology, applied in machine learning, instrumentation, data processing applications, etc., can solve problems such as low efficiency, failure to achieve the set goal, and inability to automatically adapt parameters

Active Publication Date: 2021-09-21
南京音飞峰云科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Such schemes rely more on human experience and long-term manual correction, and the efficiency is low
And if the environment changes, and the parameters cannot automatically adapt to this change, the original adjusted strategy will no longer be the best, or even fail to achieve the set goal

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
  • Dynamic tuning method of scheduling strategy parameters for dense library equipment based on machine learning
  • Dynamic tuning method of scheduling strategy parameters for dense library equipment based on machine learning
  • Dynamic tuning method of scheduling strategy parameters for dense library equipment based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention provides a dynamic tuning method for a dense library device scheduling strategy parameter based on machine learning. This method is applied in a dense library job task pool in a modern intelligent storage system and optimizes.

[0021] The automated intensive warehouse system for the present invention is suitable for strategic tuning of various automation libraries, such as stacker, sub-female libraries, and four-way shuttle garages.

[0022] Various warehouses can set the scheduling target mainly contain four indicators:

[0023] Equipment Occupation OC

[0024]

[0025] Count represents the total number of devices, Time represents the statistical cycle length, DTI represents the total length of the i-th device in this statistics cycle.

[0026] Average task completion time TC

[0027]

[0028] Ti means that the i-th task is completed, n means the number of tasks

[0029] Task completion time standard deviation AC

[0030]

[0031] Ti means that...

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 discloses a machine learning-based dynamic optimization method for scheduling policy parameters of dense warehouse equipment. The invention performs topology diagram modeling for the physical pathways and equipment movement categories of the warehouse, and uses the model to quantify the actual operation of automated vehicles under specific policy parameters. Subdivide the indicators, and set the target value of the warehouse scheduling indicator under this model, and then use the main data analysis idea of ​​machine learning to reduce the dimension parameter model, and then discover the correlation model between the strategy parameters and the target indicators, so as to facilitate the continuous optimization of the strategy Parameters, to gradually approach the scheduling goal, so as to realize the automatic optimization parameter adjustment under the existing conditions of the warehouse.

Description

Technical field [0001] The present invention relates to the field of intelligent automated storage equipment control, especially an intelligent and efficient warehouse task coordinated planning method. Background technique [0002] Warehouse automation equipment is often very complicated, such as signal occlusion of different levels of goods in a dense library, resulting in different points in network signal coverage in the intensive library, and the wear between the devices can also cause the operating equipment There is a certain degree of slip, and the above environment is subjected to a large impact on the actual equipment operation, which in turn affects the work efficiency of the entire warehouse. [0003] In order to solve the above problems, most automated warehouse devices are configured to configure multiple policies and parameters used by the policy to adapt the warehouse environment, thereby safeguarding the equipment as stable as possible. For example, a common error...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/04G06Q10/06G06Q10/08G06N20/00
CPCG06Q10/04G06Q10/0631G06Q10/06393G06Q10/0875G06N20/00
Inventor 靳国泉石晟
Owner 南京音飞峰云科技有限公司