# US 2023/0023896 A1 · Method of Transfer Learning for a Specific Production Process of an Industrial Plant

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0023896 A1
- Document ID: US20230023896A1
- Status: Published application
- Kind: A1
- Application number: 17/957,592
- Filed: 2022-09-30
- Published: 2023-01-26
- Earliest claimed: 2020-03-31
- Assignees: ABB Schweiz AG
- Applicants: ABB Schweiz AG
- Inventors: Benedikt Schmidt; Ido Amihai; Arzam Muzaffar Kotriwala; Moncef Chioua; Dennis Janka; Felix Lenders; Jan Christoph Schlake; Martin Hollender; Hadil Abukwaik; Benjamin Kloepper
- Web page: https://patentgrep.com/patent/US20230023896A1

## CPC

- G05B 13/0265: {the criterion being a learning criterion}
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G05B 19/41835: {characterised by program execution}
- G06N 3/09: Supervised learning
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 20/00: Machine learning
- G05B 17/02: electric
- G05B 19/41885: {characterised by modeling, simulation of the manufacturing system}
- G05B 2219/32015: Optimize, process management, optimize production line
- G05B 2219/32352: Modular modeling, decompose large system in smaller systems to simulate
- G06N 3/045: Combinations of networks
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- Y02P 90/80: Management or planning
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

A method of transfer learning for a specific production process of an industrial plant includes providing data templates defining expected data for a production process, and providing plant data, wherein the data templates define groupings for the expected data according to their relation in the industrial plant; determining a process instance and defining a mapping with the plant data; determining historic process data; determining training data using the determined process instance and the determined historic process data, wherein the training data comprises a structured data matrix, wherein columns of the data matrix represent the sensor data that are grouped in accordance with the data template and wherein rows of the data matrix represent timestamps of obtaining the sensor data; providing a pre-trained machine learning model using the determined process instance; and training a new machine learning model using the provided pre-trained model and the determined training data.

## Claims

### Claim 1

A method of transfer learning for a specific production process of an industrial plant, comprising:
providing a plurality of data templates defining expected data for a production process;
providing plant data of the industrial plant, comprising data points of the specific production process, wherein the data points comprise information about input and output of the specific production process;
wherein the data template defines a grouping for the expected data according to their relation in the industrial plant;
determining a process instance of the specific production process, defining a mapping between the plant data (P) to the expected data of the specific production process;
determining historic process data, being historic sensor data relating to the specific production process using the determined process instance;
determining training data using the determined process instance and the determined historic process data, wherein the training data comprises a structured data matrix, wherein columns of the data matrix represent the sensor data that are grouped in accordance with the data template, and wherein rows of the data matrix represent timestamps of obtaining the sensor data;
providing a pre-trained machine learning model using the determined process instance; and
training a new machine learning model using the provided pre-trained model and the determined training data.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining the training data comprises preprocessing the historic process data, thereby standardizing a format of the training data.

### Claim 3 (depends on 2)

The method of claim 2, wherein preprocessing the historic process data comprises adapting a sampling frequency to a standardized data matrix format.

### Claim 4 (depends on 2)

The method of claim 2, wherein preprocessing the historic process data comprises scaling the historic process data to a 0-1 domain.

### Claim 5 (depends on 2)

The method of claim 2, wherein preprocessing the historic process data comprises fusing missing data points of the historic process data from available data points of the historic process data.

### Claim 6 (depends on 2)

The method of claim 2, wherein preprocessing the historic process data comprises removing outliers from the historic process data.

### Claim 7 (depends on 1)

The method of claim 1, wherein the pre-trained model comprises trained weights, and wherein training the new machine learning model comprises adjusting the trained weights.

### Claim 8 (depends on 1)

The method of claim 1, wherein the pre-trained machine learning model comprises at least one layer, and wherein training the new machine learning model comprises:
categorizing each layer using the determined process instance in one of the categories frozen or non-frozen; and
reusing the frozen layers of the pre-trained machine learning model and retraining the non-frozen layers of the pre-trained machine learning model.

### Claim 9 (depends on 1)

The method of claim 1, wherein the pre-trained machine learning model comprises at least one layer, and wherein training the new machine learning model comprises:
categorizing each layer using the determined process instance in one of the categories frozen or non-frozen; and
applying different learning rates on the at least one layer depending on the determination if the layer is a frozen layer or a non-frozen layer.

### Claim 10 (depends on 1)

The method of claim 1, wherein the data points comprise input/output names of the specific production process, and wherein the historic process data is determined using the input/output names.

### Claim 11 (depends on 1)

The method of claim 1, wherein training the new machine learning model comprises using the data matrix as input for the new machine learning model to obtain a prediction as output from the new machine learning model.
