System and method for optimal drive configuration using machine learning

Patent metadata

Field	Value
Publication number	US-12437234-B2
Application number	US-202117499917-A
Country	US
Kind code	B2
Filing date	Oct 13, 2021
Priority date	Oct 14, 2020
Publication date	Oct 7, 2025
Grant date	Oct 7, 2025

Abstract

A system for optimal drive configuration using machine learning; the system includes: a data collector configured to collect data and establish correlations among the collected data; a training data set generator configured to compute configuration sets based on the collected data and based on the established correlations, further configured to compute measured success values for the configuration sets, further configured to generate training data sets that include the configuration sets together with corresponding measured success values; a machine learning module, configured to predict predicted success values for calculated configuration sets using the training data sets provided by the training data set generator using machine learning algorithm; and an optimization module, configured to order the calculated configuration sets, including a simulation module, configured to simulate the calculated configuration sets.

First claim

What is claimed is:

1. A system for optimal drive configuration using machine learning, the system comprising;
a non-transitory computer-readable medium comprising:
a data collector configured to collect data and establish correlations among the collected data, wherein the data collector is configured to collect the data by adopting text processing approaches or text mining approaches to extract features from customer documents and technical requirements of an industrial application associated with the drive;
a training data set generator configured to compute configuration sets for the drive based on the collected data and based on the established correlations, further configured to compute measured success values for the computed configuration sets, further configured to generate training data sets comprising the computed configuration sets together with corresponding measured success values;
a machine learning module, configured to predict predicted success values for the computed configuration sets using the training data sets provided by the training data set generator using a machine learning algorithm;
an optimization module, configured to order the computed configuration sets that has the predicted success values above a certain threshold, comprising a simulation module, configured to simulate the ordered configuration sets and evaluate results for convergence; and
a user interface module configured to present a graphical user interface with the computed configuration sets for which the results are converged, and initiate a feedback mechanism for a user to provide feedback regarding the presented configuration sets such that the feedback is used to tune the machine learning algorithm to achieve the optimal drive configuration.

2. The system according to claim 1 ,
wherein the user interface module is configured to provide configuration of the system and to provide a visualization of a machine learning process performed by the machine learning module.

3. The system according to claim 1 ,
wherein the user interface module is configured to offer alternatives of machine learning algorithms to the user.

4. The system according to claim 1 ,
wherein the optimization module is configured to collect real-time-series data, which are used by the simulation module to simulate the computed configuration sets.

5. The system according to claim 1 , wherein engineering data collected over a lifecycle of a drive system installation is collected and used to generate the training data sets.

6. The system according to claim 1 , wherein simulation results of simulating the ordered configurations sets by means of the simulation module are provided as a history of changes of configuration parameters from tools of the system.

7. A method for optimal drive configuration for a system using machine learning, the method comprising:
collecting data and establishing correlations among the collected data, wherein the data is collected by adopting text processing approaches or text mining approaches to extract features from customer documents and technical requirements of an industrial application associated with the drive;
computing configuration sets for the drive based on the collected data and based on the established correlations, computing measured success values for the computed configuration sets, generating training data sets comprising the computed configuration sets together with corresponding measured success values;
predicting predicted success values for the computed configuration sets using the training data sets using a machine learning algorithm;
ordering the computed configuration sets that has the predicted success values above a certain threshold and simulating the ordered configuration sets to evaluate results for convergence; and
presenting a graphical user interface with the computed configuration sets for which the results are converged, and initiate a feedback mechanism for a user to provide feedback regarding the presented configuration sets such that the feedback is used to tune the machine learning algorithm to achieve the optimal drive configuration.

8. The method according to claim 7 ,
wherein the method further comprises providing a configuration of the system and providing a visualization of a machine learning process performed based on the machine learning algorithm.

9. A computer program element stored on a non-transitory computer-readable medium, which when executed by the system according to claim 1 , is configured to carry out a method comprising:
collecting data and establishing correlations among the collected data, wherein the data is collected by adopting text processing approaches or text mining approaches to extract features from customer documents and technical requirements of an industrial application associated with the drive;
computing configuration sets for the drive based on the collected data and based on the established correlations, computing measured success values for the computed configuration sets, generating training data sets comprising the computed configuration sets together with corresponding measured success values;
predicting predicted success values for the computed configuration sets using the training data sets using a machine learning algorithm;
ordering the computed configuration sets that has the predicted success values above a certain threshold and simulating the ordered configuration sets to evaluate results for convergence; and
presenting a graphical user interface with the computed configuration sets for which the results are converged, and initiate a feedback mechanism for a user to provide feedback regarding the presented configuration sets such that the feedback is used to tune the machine learning algorithm to achieve the optimal drive configuration.

Assignees

• Abb Schweiz Ag

Inventors

• Rodriguez Pablo
• Juhlin Prerna
• Doppelhamer Jens
• Stark Katharina
• Malakuti Somayeh

Classifications

• G06F18/217

  Validation; Performance evaluation; Active pattern learning techniques · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06F18/40

  Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor · CPC title

• G06F30/27

  using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model · CPC title

• G06F30/15

  Vehicle, aircraft or watercraft design · CPC title