# US 12,762,462 B2 · Monte Carlo simulation framework that produces anomaly-free training data to support ML-based prognostic surveillance

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

- Number: US 12,762,462 B2
- Document ID: US12762462B2
- Status: Granted
- Kind: B2
- Application number: 17/370,388
- Filed: 2021-07-08
- Published: 2022-12-08
- Granted: 2026-10-13
- Earliest claimed: 2021-06-03
- Assignees: Oracle International Corporation
- Applicants: Oracle International Corporation
- Inventors: Beiwen Guo; Matthew T. Gerdes; Guang C. Wang; Hariharan Balasubramanian; Kenny C. Gross
- Web page: https://patentgrep.com/patent/US12762462B2

## CPC

- G06N 20/00: Machine learning
- G06N 5/04: Inference or reasoning models
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The disclosed embodiments relate to a system that produces anomaly-free training data to facilitate ML-based prognostic surveillance operations. During operation, the system receives a dataset comprising time-series signals obtained from a monitored system during normal, but not necessarily fault-free operation of the monitored system. Next, the system divides the dataset into subsets. The system then identifies subsets that contain anomalies by training one or more inferential models using combinations of the subsets, and using the one or more trained inferential models to detect anomalies in other target subsets of the dataset. Finally, the system removes any identified subsets from the dataset to produce anomaly-free training data.

## Claims

### Claim 1

A method for producing anomaly-free training data to facilitate machine learning (ML)-based prognostic surveillance operations, comprising:
receiving a dataset comprising time-series signals obtained from a monitored system during operation of the monitored system;
dividing the dataset into a plurality of subsets;
identifying subsets that contain anomalies from target subsets of the dataset by:
training one or more inferential models using combinations of subsets of the plurality of subsets, and
using the one or more trained inferential models to detect anomalies in the target subsets of the dataset; and
removing one or more subsets of the target subsets having the detected anomalies from the dataset, wherein the dividing the dataset into subsets and identifying the subsets that contain anomalies is an iterative process, which starts with fewer larger subsets and progresses to a larger number of smaller subsets.

### Claim 2 (depends on 1)

The method of claim 1, wherein removing identified subsets from the dataset comprises:
confirming that the identified subsets contain anomalies; and
removing the identified subsets that are confirmed to contain anomalies.

### Claim 3 (depends on 1)

The method of claim 1, wherein training the one or more inferential models using combinations of the subsets comprises training an inferential model for every possible combination of the subsets.

### Claim 4 (depends on 1)

The method of claim 1, wherein using the one or more trained inferential models to detect anomalies in the target subsets of the dataset comprises:
using the one or more trained inferential models to perform prognostic-surveillance operations on the target subsets; and
identifying target subsets that contain anomalies based on a number of alerts produced during the prognostic-surveillance operations.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the identifying the subsets that contain anomalies from target subsets of the dataset, further comprises, prior to the training, receiving one or more of the subsets comprising anomalies and one or more of the subsets that do not contain anomalies.

### Claim 6 (depends on 1)

The method of claim 1, wherein the method further comprises:
during a training mode, using the anomaly-free training data to train an inferential model; and
during a surveillance mode,
using a trained inferential model of the one or more trained inferential models to generate estimated values for the time-series signals received from the monitored system based on cross-correlations between the time-series signals,
performing pairwise differencing operations between actual values and the estimated values for the time-series signals set to produce residuals, and
analyzing the residuals to detect incipient anomalies in the monitored system.

### Claim 7 (depends on 6)

The method of claim 6, wherein analyzing the residuals comprises:
performing a sequential probability ratio test (SPRT) on the residuals to produce SPRT alarms; and
detecting the incipient anomalies based on the SPRT alarms.

### Claim 8 (depends on 1)

The method of claim 1, wherein an inferential model of the one or more inferential models comprises a multivariate state estimation technique (MSET) model.

### Claim 9

A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for producing anomaly-free training data to facilitate machine learning (ML)-based prognostic surveillance operations, the method comprising:
receiving a dataset comprising time-series signals obtained from a monitored system during operation of the monitored system;
dividing the dataset into a plurality of subsets;
identifying subsets that contain anomalies from target subsets of the dataset by:
training one or more inferential models using combinations of subsets of the plurality of subsets, and
using the one or more trained inferential models to detect anomalies in target subsets of the dataset; and
removing one or more subsets of the target subsets having the detected anomalies from the dataset, wherein the dividing the dataset into subsets and identifying the subsets that contain anomalies is an iterative process, which starts with fewer larger subsets and progresses to a larger number of smaller subsets.

### Claim 10 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein removing identified subsets from the dataset comprises:
confirming that the identified subsets contain anomalies; and
removing the identified subsets that are confirmed to contain anomalies.

### Claim 11 (depends on 9)

The non-transitory computer-readable storage medium of claim 9,
wherein training the one or more inferential models using combinations of the subsets comprises training an inferential model for every possible combination of the subsets, and
wherein the inferential model of the one or more inferential models comprises a multivariate state estimation technique (MSET) model.

### Claim 12 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein using the one or more trained inferential models to detect anomalies in the target subsets of the dataset comprises:
using the one or more trained inferential models to perform prognostic-surveillance operations on the target subsets; and
identifying target subsets that contain anomalies based on a number of alerts produced during the prognostic-surveillance operations.

### Claim 13 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein the method further comprises:
during a training mode, using the anomaly-free training data to train an inferential model; and
during a surveillance mode,
using a trained inferential model of the one or more trained inferential models to generate estimated values for the time-series signals received from the monitored system based on cross-correlations between the time-series signals,
performing pairwise differencing operations between actual values and the estimated values for the time-series signals set to produce residuals, and
analyzing the residuals to detect incipient anomalies in the monitored system.

### Claim 14 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, wherein analyzing the residuals comprises:
performing a sequential probability ratio test (SPRT) on the residuals to produce SPRT alarms; and
detecting the incipient anomalies based on the SPRT alarms.

### Claim 15

A system that produces anomaly-free training data to facilitate machine learning (ML)-based prognostic surveillance operations, comprising:
a computing system with one or more processors and one or more associated memories; and
an execution mechanism that executes on the computing system, wherein during operation, the execution mechanism:
receives a dataset comprising time-series signals obtained from a monitored system during operation of the monitored system,
divides the dataset into a plurality of subsets,
identifies subsets that contain anomalies from target subsets of the dataset, wherein while identifying subsets that contain anomalies, the execution mechanism trains one or more inferential models using combinations of subsets of the plurality of subsets, and uses the one or more trained inferential models to detect anomalies in target subsets of the dataset, and
removes one or more subsets of the target subsets having the detected anomalies from the dataset, wherein while dividing the dataset into subsets and identifying the subsets that contain anomalies, the execution mechanism performs an iterative process, which starts with fewer larger subsets and progresses to a larger number of smaller subsets.

### Claim 16 (depends on 15)

The system of claim 15, wherein while removing identified subsets from the dataset, the execution mechanism:
confirming that the identified subsets contain anomalies; and
removes the identified subsets that are confirmed to contain anomalies.

### Claim 17 (depends on 15)

The system of claim 15, wherein while using the one or more trained inferential models to detect anomalies in the target subsets, the execution mechanism:
uses the one or more trained inferential models to perform prognostic-surveillance operations on the target subsets; and
identifies target subsets that contain anomalies based on a number of alerts produced during the prognostic-surveillance operations.