- Number
- 20260244550
- Published
- 2026-08-20
- Filed
- 2025-02-14
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Onofre; Thiago Borba, Tschanz; Michael
- CPC
- G06F11/3447; G06F11/324
- Verdict
- Set aside cpc prior 0.14
- In edition
- 2026-W36
- Source
- Google Patents · FreePatentsOnline
The keeper's note
A system includes a processor and a memory storing software code and a trained machine learning (ML) model.
Abstract
A system includes a processor and a memory storing software code and a trained machine learning (ML) model. The software code is executed to receive global sensor data generated by sensors used to monitor a plurality of apparatuses and, for a first apparatus, extract from the global sensor data, data generated by a first subset of sensors associated with the first apparatus. The software code is further executed to identify, using the global sensor data, other data generated within a respective predetermined time interval of the expected timing of at least one of the first subset of sensors, process the data and the other data to provide performance data for the first apparatus, predict, using the trained ML model and the performance data, whether the first apparatus is operating anomalously, and output, when the first apparatus is operating anomalously, a notification including a visual representation of the performance data.
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. Moreover, as the amount of monitoring data required to adequately profile the operating state of a system-of-systems based apparatus grows with the increasing complexity of such an apparatus, human review and interpretation of that data becomes ever more impracticable. Consequently, there is a need in the art for an automated solution for diagnosing the operational states of complex apparatuses and accurately predicting situations in which those apparatuses are likely to malfunction or fail.
Claims
1. A system comprising: a hardware processor; and a memory storing a software code, a trained machine learning (ML) model, and a sensor database including a plurality of database entries each associating a respective subset of a plurality of sensors with one of a plurality of apparatuses; the hardware processor configured to execute the software code to: receive a global sensor data including data generated by all active sensors of the plurality of sensors; for a first apparatus of the plurality of apparatuses: extract from the global sensor data, based on a first database entry for the first apparatus, a first sensor data generated by a first subset of the plurality of sensors associated with the first apparatus; identify, using the global sensor data, a first other sensor data generated by a sensor of the plurality of sensors not included in the first subset of the plurality of sensors within a respective predetermined time interval of an expected timing of at least one sensor of the first subset of the plurality of sensors; process the first sensor data and the first other sensor data to provide a first performance data for the first apparatus; predict, using the trained ML model and the first performance data, whether the first apparatus is operating anomalously; and output, when predicting identifies the first apparatus as operating anomalously, a notification including a visual representation of the first performance data. ||
11. A method for use by a system including a hardware processor and a memory storing a software code, a trained machine learning (ML) model, and a sensor database including a plurality of database entries each associating a respective subset of a plurality of sensors with one of a plurality of apparatuses, the method comprising: receiving, by the software code executed by the hardware processor, a global sensor data including data generated by all active sensors of the plurality of sensors; for a first apparatus of the plurality of apparatuses: extracting from the global sensor data,, by the software code executed by the hardware processor based on a first database entry for the first apparatus, a first sensor data generated by a first subset of the plurality of sensors associated with the first apparatus; identifying,, by the software code executed by the hardware processor and using the global sensor data, a first other sensor data generated by a sensor of the plurality of sensors not included in the first subset of the plurality of sensors within a respective predetermined time interval of an expected timing of at least one sensor of the first subset of the plurality of sensors; processing the first sensor data and the first other sensor data, by the software code executed by the hardware processor, to provide a first performance data for the first apparatus; predicting,, by the software code executed by the hardware processor using the trained ML model and the first performance data, whether the first apparatus is operating anomalously; and outputting, by the software code executed by the hardware processor when predicting identifies the first apparatus as operating anomalously, a notification including a visual representation of the first performance data.