US-20260127056-A1 - DETERMINING PERIOD OF NORMAL OPERATING PERFORMANCE FOR TRAINING AN ANOMALY DETECTION MODEL

US20260127056A1US 20260127056 A1US20260127056 A1US 20260127056A1US-20260127056-A1

Abstract

Determining a period of normal operating performance for training an anomaly detection model is described herein. One embodiment includes receiving, by a computing device, operating data of equipment at a site over a period of time, filtering, by the computing device, the received operating data of the equipment, determining, by the computing device based on the filtered operating data of the equipment, a period of normal operating performance of the equipment during the period of time, training, by the computing device, an anomaly detection model for the equipment using the filtered operating data of the equipment during the determined period of normal operating performance of the equipment, and detecting, by the computing device using the trained anomaly detection model for the equipment, an anomaly occurring in the equipment.

Inventors

Praveen Tayal
ILANGOVAN R

Assignees

HONEYWELL INTERNATIONAL INC.

Dates

Publication Date: 20260507
Application Date: 20241105

Claims (20)

1 . A method, comprising: receiving, by a computing device, operating data of equipment at a site over a period of time; filtering, by the computing device, the received operating data of the equipment; determining, by the computing device based on the filtered operating data of the equipment, a period of normal operating performance of the equipment during the period of time; training, by the computing device, an anomaly detection model for the equipment using the filtered operating data of the equipment during the determined period of normal operating performance of the equipment; and detecting, by the computing device using the trained anomaly detection model for the equipment, an anomaly occurring in the equipment.
2 . The method of claim 1 , wherein determining the period of normal operating performance of the equipment during the period of time includes: determining scores for the filtered operating data of the equipment; and determining the period of normal operating performance of the equipment based on the determined scores.
3 . The method of claim 2 , wherein: determining the period of normal operating performance of the equipment based on the determined scores includes determining which operating data of the equipment has a score that meets or exceeds a particular threshold; and the anomaly detection model is trained using the filtered operating data of the equipment determined to have a score that meets or exceeds the particular threshold.
4 . The method of claim 1 , wherein determining the period of normal operating performance of the equipment during the period of time includes: determining interactions between the filtered operating data of the equipment during the period of time; and determining the period of normal operating performance of the equipment based on the determined interactions between the filtered operating data.
5 . The method of claim 4 , wherein the interactions include a collinearity between the filtered operating data of the equipment during the period of time.
6 . The method of claim 1 , wherein the method includes providing, by the computing device, the filtered operating data of the equipment during the determined period of normal operating performance of the equipment to a user.
7 . The method of claim 6 , wherein the method includes receiving, by the computing device, a validation of the determined period of normal operating performance of the equipment from the user.
8 . A computing device, comprising: an anomaly detection model for equipment at a site; a processor; and a memory storing non-transitory machine-readable instructions to cause the processor to: receive operating data of equipment at a site over a period of time; determine scores for the operating data of the equipment; determine a period of normal operating performance of the equipment during the period of time based on the determined scores for the operating data of the equipment; train the anomaly detection model using the operating data of the equipment during the determined period of normal operating performance of the equipment; and detect an anomaly occurring in the equipment using the trained anomaly detection model.
9 . The computing device of claim 8 , wherein the instructions cause the processor to provide an alert upon detecting the anomaly occurring in the equipment.
10 . The computing device of claim 8 , wherein the instructions cause the processor to remove the operating data of the equipment that is from outside the determined period of normal operating performance of the equipment prior to training the anomaly detection model.
11 . The computing device of claim 8 , wherein the instructions cause the processor to determine the period of normal operating performance of the equipment based on the determined scores for the operating data for a single operating variable of the equipment.
12 . The computing device of claim 8 , wherein the instructions cause the processor to determine the period of normal operating performance of the equipment based on the determined scores for the operating data for a plurality of operating variables of the equipment.
13 . The computing device of claim 8 , wherein the instructions cause the processor to detect an anomaly occurring in the equipment using the trained anomaly detection model by: receiving operating data of the equipment after the period of time; and determining, by the trained anomaly detection model, a deviation of the operating data of the equipment after the period of time from the operating data of the equipment during the determined period of normal operating performance of the equipment.
14 . The computing device of claim 8 , wherein the anomaly detection model is for at least one of: a lube oil system of the equipment; a flow performance of the equipment; a bearing of the equipment; a motor of the equipment; and a seal of the equipment.
15 . A non-transitory computer readable medium storing instructions executable by a processing resource to cause the processing resource to: receive operating data of equipment at a site over a period of time; determine a period of normal operating performance of the equipment during the period of time based on the operating data of the equipment; remove the operating data of the equipment that is from outside the determined period of normal operating performance of the equipment; train an anomaly detection model for the equipment using only the operating data of the equipment during the determined period of normal operating performance of the equipment; and detect an anomaly occurring in the equipment using the trained anomaly detection model.
16 . The computer readable medium of claim 15 , wherein training the anomaly detection model using only the operating data of the equipment during the determined period of normal operating performance of the equipment comprises training the anomaly detection model without using the operating data of the equipment that is from outside the determined period of normal operating performance of the equipment.
17 . The computer readable medium of claim 15 , wherein the instructions are executable to train an additional anomaly detection model for the equipment using only the operating data of the equipment during the determined period of normal operating performance of the equipment.
18 . The computer readable medium of claim 15 , wherein the instructions are executable to: receive operating data of additional equipment at the site over the period of time; determine a period of normal operating performance of the additional equipment during the period of time based on the operating data of the additional equipment; remove the operating data of the additional equipment that is from outside the determined period of normal operating performance of the additional equipment; and train an anomaly detection model for the additional equipment using only the operating data of the additional equipment during the determined period of normal operating performance of the additional equipment.
19 . The computer readable medium of claim 15 , wherein the operating data of the equipment includes at least one of: a temperature of the equipment; a pressure of the equipment; a flow of the equipment; a speed of the equipment; a vibration of the equipment; and an oscillation of the equipment.
20 . The computer readable medium of claim 15 , wherein the equipment at the site includes at least one of: a pump; a compressor; and an exchanger.

Description

TECHNICAL FIELD The present disclosure relates generally to devices, methods, and systems for determining a period of normal operating performance for training an anomaly detection model. BACKGROUND Anomaly detection models can be used to detect when an anomaly may be occurring in equipment (e.g., pumps, compressors, exchangers, etc.) at an industrial plant, manufacturing plant, or other site. For instance, an anomaly detection model can be used to determine whether the operating data of the equipment deviates from the operating data that would be expected from normal operating performance of the equipment. To train an anomaly detection model, the normal operating performance of the equipment needs to be established to provide a performance baseline for the equipment. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 illustrates a block diagram of an example of a system for determining a period of normal operating performance for training an anomaly detection model in accordance with one or more embodiments of the present disclosure. FIG. 2 illustrates an example of a method for determining a period of normal operating performance for training an anomaly detection model in accordance with one or more embodiments of the present disclosure. FIGS. 3A-3B are graphs illustrating conceptual examples of determining a period of normal operating performance for training an anomaly detection model in accordance with one or more embodiments of the present disclosure. FIG. 4 is a block diagram of an example of a computing device for determining a period of normal operating performance for training an anomaly detection model in accordance with one or more embodiments of the present disclosure. DETAILED DESCRIPTION Devices, methods, and systems for determining a period of normal operating performance for training an anomaly detection model are described herein. One embodiment includes receiving, by a computing device, operating data of equipment at a site over a period of time, filtering, by the computing device, the received operating data of the equipment, determining, by the computing device based on the filtered operating data of the equipment, a period of normal operating performance of the equipment during the period of time, training, by the computing device, an anomaly detection model for the equipment using the filtered operating data of the equipment during the determined period of normal operating performance of the equipment, and detecting, by the computing device using the trained anomaly detection model for the equipment, an anomaly occurring in the equipment. Anomaly detection models can be used to detect when an anomaly may be occurring in equipment, such as, for instance, pumps, compressors, exchanges, etc., at an industrial plant, manufacturing plant, or other type site. For instance, an anomaly detection model can be used to determine whether the operating data of the equipment, such as, for instance, temperature, pressure, flow, speed, vibration, and/or oscillation, deviates from the operating data that would be expected from normal operating performance of the equipment. To train an anomaly detection model, the normal operating performance of the equipment needs to be established to provide a performance baseline for the equipment. In previous approaches, an engineer, technician, field operator, or other type of subject matter expert may need to visually examine and manually select the normal operating performance for the equipment. However, such a process can be difficult and time consuming, especially when there are hundreds or thousands of equipment items across a site for which a normal operating performance needs to be established. Embodiments of the present disclosure, however, can instead utilize the operating data of the equipment to determine a period of normal operating performance of the equipment for use in training an anomaly detection model. For instance, embodiments of the present disclosure can select the normal (e.g., golden) operating period of the equipment, automatically remove outliers in the operating data, and provide filtered data that can be directly used to train the anomaly detection model. Such an approach can be quicker, easier, and/or more accurate, especially across a large scale (e.g., hundreds or thousands) of equipment items at a site, than previous approaches in which a subject matter expert manually selects the normal operating performance. Further, such an approach can be device agnostic. For instance, such an approach can be used for any type of equipment at the site. As an example, operating data of equipment at a site over a period of time can be received. The site can be, for instance, an industrial plant or manufacturing plant, the equipment can include, for instance, pumps, compressors, and/or exchangers, and the operating data can include, for instance, temperature, pressure, flow, speed, vibration, and/or oscillation. A period of normal operating performance of the