US 12,013,690 B2Granted

Method and system for controlling a process in a process plant

AssigneeABB Schweiz AG

InventorShrikant Bhat

Life of this patent

Estimating the term…

Loading patent…

Abstract

The present invention relates to a method and a system for controlling a process of a process plant. Hie system is configured to control a process in the process plant by recommending control operations and perform the control operations. The system obtains the control operations and detects availability of control room operators using historical data related to actions performed by the control room operators, sensory parameters of the control room operators and a status associated with the process. The system provides queries related to the control operations, the plant parameters, status of the process to the control room operators upon detecting the availability. Hie queries are validated by the control room operators. The system thereafter autonomously controls tire control room based on the validated data.

Claims13

Dependent claims

A method of controlling a process with a distributed control system (DCS) of a process plant, wherein the DCS is configured to operate in at least a control room in the process plant, for controlling a plurality of plant parameters associated with at least one process, wherein the DCS is trained to monitor one or more control room operators and one or more actions performed by the one or more control room operators on the plurality of plant parameters, for providing recommendations and performing one or more control operations to control the at least one process in the process plant, wherein the method is performed by the DCS, the method comprising:

obtaining the recommended one or more control operations to be performed to control the at least one process based on an artificial intelligence (AI) model;
detecting availability of the one or more control room operators based on historical data related to the one or more actions performed by the one or more control room operators, one or more sensory parameters of the one or more control room operators and a status associated with the at least one process;
providing one or more queries to the one or more control room operators upon detecting the availability of the one or more control room operators, wherein the one or more queries are related to at least one plant parameter from the plurality of plant parameters being at least one of, observed and modified by the one or more control room operators, the recommended control operations, and the status of the at least one process;
receiving one or more inputs from the one or more control room operators for validating the recommended one or more control operations, wherein a training set for the DCS to control the at least one process comprises the validated one or more control operations;
and
training the AI model based on the training set.

3 more elements

A Distributed Control System (DCS) for controlling a process in a process plant, wherein the DCS is configured to operate in at least a control room in the process plant, for controlling a plurality of plant parameters of at least one process, wherein the DCS is configured to monitor one or more control room operators and one or more actions performed by the one or more control room operators, recommend one or more control operations to control the at least one process in the process plant, and perform the one or more control operations for controlling the at least one process, wherein the DCS comprises:

a historian configured to store historical data related to the one or more actions performed by the one or more control room operators;
a computing unit configured to:
receive the historical data and one or more sensory parameters;
obtain the recommended one or more control operations based on an artificial intelligence (AI) model;
detect an availability of the one or more control room operators based on the historical data, the one or more sensory parameters of the one or more control room operators and a status associated with the at least one process;
train the AI model based on a training set and a User Interface (UI) configured to:
provide one or more queries to the one or more control room operators upon receiving instructions from the computing unit, wherein the computing unit provides the instructions upon detecting the availability of the one or more control room operators, wherein the one or more queries are related to at least one plant parameter from the plurality of plant parameters being at least one of, observed and modified by the one or more control room operators, the recommended control operations, and the status of the at least one process;
and
receive one or more inputs from the one or more control room operators, wherein the computing unit receives the one or more inputs from the one UI for validating the recommended control operations, wherein the training set for the DCS to control the at least one process comprises the validated control operations.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/418,830Filed 26 Dec 2019
Priority: IN 20184104970228 Dec 2018
Published: US 2022/0066425 A13 Mar 2022
Granted: 18 Jun 2024
Term ends: Not estimatedThe source records don’t support an estimate.

Classification8 codes

G05B 19/418
Electric: total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible…
G05B 19/4188
Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible…:…
G05B 2219/32007
Operator till task planning: operator is assisted by expert system for advice and delegation of tasks
G05B 2219/33034
Director till display: online learning, training