- Number
- 20260228615
- Published
- 2026-08-06
- Filed
- 2025-02-06
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Paulsen; Amber E., Pagano; Sarah, Eaton; Jeremy
- CPC
- G06N20/00; G06N3/044; G06N3/045; G06N3/0464; G06N3/08; G06N3/088; G06N3/09; G06N20/10
- Verdict
- Set aside dropped in weekly review
- In edition
- 2026-W32
- Source
- Google Patents · FreePatentsOnline
The keeper's note
A system includes a hardware processor and a memory storing software code and a trained machine learning (ML) model.
Abstract
A system includes a hardware processor and a memory storing software code and a trained machine learning (ML) model. The hardware processor is configured to execute the software code to receive data describing an operation by an apparatus, generate, using the data, a first visual representation of the operation, and predict, using the trained ML model and the first visual representation, whether an operating state of the apparatus during the operation is anomalous. When predicting identifies an anomalous operating state by the apparatus, the hardware processor is further configured to execute the software code to obtain a second visual representation of an expected operation by the apparatus during a normal operating state of the apparatus, perform a comparison of the first visual representation with the second visual representation, and output an alert including a result of the comparison of the first visual representation with the second visual representation.
Background
BACKGROUND
Many industrial apparatuses are interconnected systems-of-systems having designs that are increasingly complicated and are susceptible to malfunction or failure for many different reasons. The larger a system-of-systems based apparatus is, the more difficult, costly and inefficient it can become to identify and troubleshoot the sources of anomalous apparatus operation. Conventional solutions for anticipating apparatus malfunctions and failures have relied upon the deep knowledge base of highly experienced system engineers, which, due to the heavy reliance of those solutions on the expertise of particular individuals, are brittle and ultimately untenable. Consequently, there is a need in the art for a solution enabling system engineers of varying degrees of experience to readily diagnose the operational states of complex apparatuses, and to accurately anticipate situations in which those system are likely to malfunction or fail.
Claims
1. A system comprising: a hardware processor; and a memory storing a software code and a trained machine learning (ML) model; the hardware processor configured to execute the software code to: receive data describing an operation by an apparatus; generate, using the data, a first visual representation of the operation; predict, using the trained ML and the first visual representation of the operation, whether an operating state of the apparatus during the operation is anomalous; obtain, when predicting identifies an anomalous operating state by the apparatus, a second visual representation of an expected operation by the apparatus during a normal operating state of the apparatus; perform a comparison of the first visual representation with the second visual representation; and output an alert including a result of the comparison of the first visual representation with the second visual representation. ||
9. A method for use by a system including a hardware processor and a memory storing a software code and a trained machine learning (ML) model, the method comprising: receiving, by the software code executed by the hardware processor, data describing an operation by an apparatus; generating, by the software code executed by the hardware processor and using the data, a first visual representation of the operation; predicting, by the software code executed by the hardware processor and using the trained ML model and the first visual representation of the operation, whether an operating state of the apparatus during the operation is anomalous; obtaining, by the software code executed by the hardware processor when predicting identifies an anomalous operating state by the apparatus, a second visual representation of an expected operation by the apparatus during a normal operating state of the apparatus; performing, by the software code executed by the hardware processor, a comparison of the first visual representation with the second visual representation; and outputting, by the software code executed by the hardware processor, an alert including a result of the comparison of the first visual representation with the second visual representation. ||
17. A computer-readable non-transitory medium having stored thereon instructions and a trained machine learning (ML) model, which when executed by a hardware processor, instantiate a method comprising: receiving data describing an operation by an apparatus; generating, using the data, a first visual representation of the operation; predicting, using the trained ML model and the first visual representation of the operation, whether an operating state of the apparatus during the operation is anomalous; obtaining, when predicting identifies an anomalous operating state by the apparatus, a second visual representation of an expected operation by the apparatus during a normal operating state of the apparatus; performing a comparison of the first visual representation with the second visual representation; and outputting an alert including the comparison of the first visual representation with the second visual representation.