Parameter manager, central device and method of adapting operational parameters in a textile machine

Patent metadata

Field	Value
Publication number	US-12124229-B2
Application number	US-201917293986-A
Country	US
Kind code	B2
Filing date	Nov 15, 2019
Priority date	Nov 16, 2018
Publication date	Oct 22, 2024
Grant date	Oct 22, 2024

Abstract

A textile mill system and associated method include a plurality of spinning mills each having textile machines. A computer system determines adapted machine parameters for the textile machines and processes within the spinning mills. The computer system includes a receiving and transmitting section configured to receive operational information from the spinning mills and the textile machines, and a first database configured to store the received operational information. A processing section includes an optimizer section with a neural network, wherein the neural network uses the operational information stored in the first database with processes for or derived from supervised or unsupervised machine or deep learning to determine the adapted machine parameters.

First claim

The invention claimed is:

1. A textile mill system, comprising:
a plurality of spinning mills, each of the spinning mills comprising a plurality of textile machines;
a computer system configured to determine adapted machine parameters for the textile machines and processes within the spinning mills for one or more of the following: production quality, usage of raw material, reduced waste, conversion costs including one or more of costs of energy, labor costs, maintenance costs and consumables costs, increase of production volume, and ideal batch allocation to different ones of the textile machines within the spinning mills, the computer system comprising:
a receiving and transmitting section comprising network interfaces, memory, and processors executing programs such that the receiving and transmitting section receives operational information from the spinning mills and the textile machines;
a first database configured to store the received operational information;
a processing section comprising an optimizer section with a neural network, wherein the neural network uses the operational information stored in the first database with processes for or derived from supervised or unsupervised machine or deep learning to determine the adapted machine parameters, wherein the optimizer section further comprises one or both of a Case-Based Reasoning system and a mathematical control and filtering section configured to check the adapted machine parameters by assigning a probability value to a difference between the adapted machine parameters and information derived from the Case-Based Reasoning system and the mathematical control and filtering section.

2. The textile mill system according to claim 1 , wherein the adapted machine parameters define one or more of one of the following:
raw material input;
allocations of spinning machines to individual batch mixes of raw material qualities;
specific allocation of bales in a blow room;
optimal use of textile machines;
operation of the textile machines;
specific components of the textile machines;
process settings and definitions;
settings of auxiliary systems;
definition of material flow within the spinning mills;
coordination of operators and their tasks with the spinning mills;
coordination and allocation of human resources to different process steps;
preventive or predictive maintenance of the textile machines.

3. The textile mill system according to claim 1 , wherein the operational information received from the spinning mills and the textile machines includes one or more of the following:
plant identification information to identify the spinning mills;
machine identification information to identify each of the textile machines;
unit identification information to identify individual machine units of the textile machines;
information from sensors and auxiliary spinning devices.

4. The textile mill system according to claim 1 , wherein the computer system is further configured to implement training the neural network based on training data relating to production tests and trials, wherein the training data is adjusted beforehand using information from the Case-Based Reasoning system or the mathematical control and filtering section applying mathematical models.

5. The textile mill system according to claim 1 , wherein the computer system further comprises:
a second database having stored reference data regarding production tests and trials;
a third database having stored empirical data collected from textile specialists of spinning mills or from textile technologists; and
a fourth database having stored adapted machine parameters; and
wherein the optimizer section and the neural network are further configured to determine the adapted machine parameters using data stored in one or more of the second, third, or fourth databases.

6. The textile mill system according to claim 5 , wherein at least a part of one or more of the first, second, third, and fourth databases is configured as an unstructured database or as a structured database.

7. The textile mill system according to claim 1 , wherein the computer system further comprises a transmission section configured to transmit the adapted machine parameters to the spinning mills and the textile machines.

8. The textile mill system according to claim 1 , wherein the processing section further includes a validity check section configured to check validity of the adapted machine parameters.

9. A computerized method of determining adapted machine parameters for textile machines and processes within spinning mills with respect to one or more of the following: production quality, usage of raw material, reduced waste, conversion costs including one or more of costs of energy, labor costs, maintenance costs and consumables costs, increase of production volume, and ideal batch allocation to different ones of the textile machines within the spinning mills, the method comprising:
receiving operational information from the spinning mills and the textile machines in a receiving and transmitting section of a computer system, the computer system having a processing section with an optimizer section;
storing the received operational information in a first database of the computer system;
using a neural network in the optimizer section to determine the adapted machine parameters, wherein the neural network uses the operational information stored in the first database and processes for or derived from supervised or unsupervised, machine or deep learning; and
checking the adapted machine parameters by assigning a probability value to a difference between the adapted machine parameters and information derived from one or both of a Case-Based Reasoning system and a mathematical control and filtering section.

10. The method according to claim 9 , wherein the adapted machine parameters define one or more of one of the following:
raw material input;
allocations of spinning machines to individual batch mixes of raw material qualities;
specific allocation of bales in a blow room;
optimal use of textile machines;
operation of the textile machines;
specific components of the textile machines;
process settings and definitions;
settings of auxiliary systems;
definition of material flow within the spinning mills;
coordination of operators and their tasks with the spinning mills;
coordination and allocation of human resources to different process steps;
preventive or predictive maintenance of the textile machines.

11. The method according to claim 9 , wherein the operational information received from the spinning mills and the textile machines includes one or more of the following:
plant identification information to identify the spinning mills;
machine identification information to identify each of the textile machines;
unit identification information to identify individual machine units of the textile machines;
information from sensors and auxiliary spinning devices.

12. The method according to claim 9 , further comprising training the neural network based on training data relating to production tests and trials, wherein the training data is adjusted beforehand using information from the Case-Based Reasoning system or the mathematical control and filtering section applying mathematical models.

13. The method according to claim 9 , further comprising determining the adapted machine parameters using one or more of:
a second database having stored reference data regarding production tests and trials;
a third database having stored empirical data collected from textile specialists of spinning mills or from textile technologists; and
a fou

Assignees

• Rieter Ag Maschf

Inventors

• Blaser Niklaus
• Griesshammer Christian

Classifications

• G05B13/027 Primary

  using neural networks only · CPC title

• G05B13/024

  in which a parameter or coefficient is automatically adjusted to optimise the performance · CPC title

• G05B13/042

  in which a parameter or coefficient is automatically adjusted to optimise the performance · CPC title

• D01H13/32

  Counting, measuring, recording or registering devices · CPC title

• D01G21/00

  Combinations of machines, apparatus, or processes, e.g. for continuous processing (D01G1/06, D01G9/12, D01G15/46, D01G15/94 take precedence) · CPC title