System and method for controlling a production plant consisting of a plurality of plant parts, in particular a production plant for producing industrial goods such as metallic semi-finished products

Patent metadata

Field	Value
Publication number	US-12596352-B2
Application number	US-202117924788-A
Country	US
Kind code	B2
Filing date	May 12, 2021
Priority date	May 14, 2020
Publication date	Apr 7, 2026
Grant date	Apr 7, 2026

Abstract

A system for controlling a production plant includes a plant automation unit for monitoring and control of the production process within the production plant. A production planning system has information concerning the products to be produced. A model generator generates at least one prediction model for products produced in the production plant. The model generator takes into account the results of the monitoring of the production plant when generating the at least one prediction model. A production optimizer determines an optimized production process within the production plant on the basis of data from the plant automation unit, the production planning system, and the prediction model generated by the model generator. The production optimizer takes into account the production-related specifications of the individual plant parts. A production plant control unit generates target specifications for the plant automation unit on the basis of the optimized production process determined by the production optimizer.

First claim

The invention claimed is:

1 . A system ( 1 ) for controlling a production plant ( 2 ) having a plurality of plant parts ( 3 ) for producing metallic semi-finished products, comprising:
a plant automation unit ( 4 ) for monitoring and for open-loop and/or closed-loop control of a production process within the production plant ( 2 ), including monitoring and open-loop and/or closed-loop control of the plant parts ( 3 ); a production planning system ( 5 ) having information concerning products to be produced in the production plant ( 2 ), including target criteria for the products to be produced; a model generator ( 6 ) for generating at least one prediction model ( 7 ) for a product currently being produced in the production plant ( 2 ) and/or for the products to be produced in the future in accordance with the production planning system ( 5 ), in compliance with the target criteria for the product currently being produced or the products to be produced in the future,
wherein the model generator ( 6 ) takes into account results of the monitoring of the production plant ( 2 ), including the plurality of plant parts ( 3 ), when generating the at least one prediction model ( 7 ), and
wherein the at least one prediction model ( 7 ) is configured to predict compliance of the product with the target criteria, including predicting at least one of
(i) an expected value of a target criterion or
(ii) a probability that the target criterion lies within a defined range;

a production optimizer ( 8 ) for determining an optimized production process within the production plant ( 2 ) including target specifications for control commands based on data from the plant automation unit ( 4 ), the production planning system ( 5 ), and the compliance with the target criteria predicted by the prediction model ( 7 ) generated by the model generator ( 6 ),
wherein the production optimizer ( 8 ) takes into account production-related specifications of the plant parts ( 3 ) in determining the optimized production process within the production plant ( 2 ); and
a production plant control unit ( 9 ) for executing the target specifications for the plant automation unit ( 4 ) based on the optimized production process determined by the production optimizer ( 8 ).

2 . The system ( 1 ) according to claim 1 ,
wherein each plant part ( 3 ) of the plurality of plant parts ( 3 ) comprises sensors ( 10 ) for detecting product properties, process parameters, and/or operating states within the respective plant part ( 3 ).

3 . The system ( 1 ) according to claim 1 ,
further comprising a central data storage unit ( 14 ) for individual components of the system ( 1 ), wherein the individual components of the system ( 1 ) can access the data and can adapt the data.

4 . The system ( 1 ) according to claim 1 ,
wherein the target criteria are selected from the group consisting of thickness, width, length, weight, tensile strength, yield strength, Young's modulus, elongation at break, corrosion resistance, presence or number of surface defects of various types, number of cracks on a surface or within a material, DWTT results, Charpy results, transition temperatures from ductile to brittle fractures, layer thickness of a zinc layer, tube wall thickness, eccentricity, connecting bar height, flange height, flange thickness, profile, and flatness, and wherein the at least one prediction model ( 7 ) is configured to predict the probability that the target criterion lies within the defined range.

5 . The system ( 1 ) according to claim 1 ,
wherein the model generator ( 6 ) generates multiple different prediction models ( 7 ), wherein the different prediction models ( 7 ) differ with regard to a creation method, original data and/or learning algorithms, and wherein the multiple different prediction models do not predict the control variables.

6 . The system ( 1 ) according to claim 5 ,
wherein the production optimizer ( 8 ) takes into account the prediction model ( 7 ) that provides currently best prediction for the product currently being produced in the production plant ( 2 ) and/or for the products to be produced in the future in accordance with the production planning system ( 5 ), including taking into account the target criteria.

7 . The system ( 1 ) according to claim 1 ,
wherein the production optimizer ( 8 ) executes an evaluation with regard to the target criteria when determining the optimized production process within the production plant ( 2 ).

8 . The system ( 1 ) according to claim 1 ,
wherein the production optimizer ( 8 ) determines effects of target value changes on objective specifications of the product currently being produced in the production plant ( 2 ) and/or of the product to be produced in the future in accordance with the production planning system ( 5 ).

9 . The system ( 1 ) according to claim 8 ,
wherein the production optimizer ( 8 ) comprises information on possible target value changes of the production plant ( 2 ), including the plant parts ( 3 ), including target value changes that can be implemented by the production plant ( 2 ), including the plant parts ( 3 ), and wherein the possible target value changes are maximum rates of change of actuator activity and/or dependencies of an adjustable variable on other variables that can also be adjusted.

10 . The system ( 1 ) according to claim 1 ,
wherein the production optimizer ( 8 ) optimizes the production process within the production plant ( 2 ) for a plurality of product sections.

11 . A method for controlling a production plant ( 2 ) having of a plurality of plant parts ( 3 ) for producing metallic semi-finished products, comprising:
acquiring information concerning products to be produced in the production plant ( 2 ), including target criteria for the products to be produced; monitoring a production process within the production plant ( 2 ), including within the plant parts ( 3 ); generating at least one prediction model ( 7 ) for a product currently being produced in the production plant ( 2 ) and/or for the products to be produced in the future, in compliance with target criteria for the product currently being produced or the products to be produced in the future,
wherein the acquired information of the production plant ( 2 ), including the plurality of plant parts ( 3 ), is taken into account in generating the at least one prediction model ( 7 ), and
wherein the at least one prediction model ( 7 ) is configured to predict compliance of the product with the target criteria, including predicting at least one of
(i) an expected value of a target criterion or
(ii) a probability that the target criterion lies within a defined range;

determining an optimized production process within the production plant ( 2 ) including target specifications for control commands based on
the acquired information concerning the products to be produced in the production plant ( 2 ),
the monitoring of the production process within the production plant ( 2 ), including the plant parts ( 3 ),
the compliance with the target criteria predicted by the at least one prediction model ( 7 ), and
production-related parameters of the production plant ( 2 ), including production-related parameters of the plant parts ( 3 ); and
executing the target specifications for an open-loop and/or closed-loop control of the production process within the production plant ( 2 ), including an open-loop and/or closed-loop control of processes within the plant parts ( 3 ).

12 . The method according to claim 11 ,
wherein the monitoring of the production process within the production plant ( 2 ), including within the plant p

Assignees

• Sms Group Gmbh

Inventors

• Klein Carsten Andreas

Classifications

• G05B2219/31395

  Process management, specification, process and production data, middle level · CPC title

• Y02P90/02

  Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS] · CPC title

• G06N20/00

  Machine learning · CPC title

• G05B13/027

  using neural networks only · CPC title

• G05B19/41875

  characterised by quality surveillance of production · CPC title