# US 11,307,569 B2 · Adaptive sequential probability ratio test to facilitate a robust remaining useful life estimation for critical assets

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

- Number: US 11,307,569 B2
- Document ID: US11307569B2
- Status: Granted
- Kind: B2
- Application number: 16/282,087
- Filed: 2019-02-21
- Published: 2020-08-27
- Granted: 2022-04-19
- Earliest claimed: 2019-02-21
- Assignees: Oracle International Corporation
- Applicants: Oracle International Corporation
- Inventors: Kenny C. Gross; Ashin George; DeJun Li
- Web page: https://patentgrep.com/patent/US11307569B2

## CPC

- G06Q 10/0635: Risk analysis of enterprise or organisation activities
- G05B 23/0283: {Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] (preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06)}
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06N 5/04: Inference or reasoning models
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G05B 23/024: {Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks}
- G06F 2218/12: Classification; Matching
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The system receives a set of present time-series signals gathered from sensors in the asset. Next, the system uses an inferential model to generate estimated values for the set of present time-series signals, and performs a pairwise differencing operation between actual values and the estimated values for the set of present time-series signals to produce residuals. The system then performs a sequential probability ratio test (SPRT) on the residuals to produce SPRT alarms with associated tripping frequency (TF). While the TF exceeds a TF threshold, the system iteratively adjusts sensitivity parameters for the SPRT to reduce the TF, and performs the SPRT again on the residuals. The system then uses a logistic regression model to compute a risk index for the asset based on the TF. If the risk index exceeds a threshold, the system generates a notification indicating that the asset needs to be replaced.

## Claims

### Claim 1

A method for estimating a remaining useful life (RUL) of an asset, wherein during a surveillance mode, the method comprises:
receiving a set of present time-series signals gathered from sensors in the asset;
using an inferential model to generate estimated values for the set of present time-series signals;
performing a pairwise differencing operation between actual values and the estimated values for the set of present time-series signals to produce residuals;
performing a sequential probability ratio test (SPRT) on the residuals to produce SPRT alarms having an associated tripping frequency (TF);
while the TF exceeds a TF threshold, iteratively adjusting sensitivity parameters for the SPRT to reduce the TF, and performing the SPRT again on the residuals; and
when the TF for the SPRT alarms falls below the TF threshold,
using a logistic regression model to compute an RUL-based risk index for the asset based on the TF, and
when the risk index exceeds a risk-index threshold, generating a notification indicating that the asset needs to be replaced.

### Claim 2 (depends on 1)

The method of claim 1, wherein during an inferential-training mode, which precedes the surveillance mode, the method further comprises:
receiving an inferential training set of time-series signals gathered from sensors in the asset during normal fault-free operation; and
training the inferential model to predict values of the time-series signals based on the inferential training set.

### Claim 3 (depends on 2)

The method of claim 2, wherein during an RUL-training mode, which follows the inferential training mode and precedes the surveillance mode, the method further comprises:
receiving an RUL training set of historical time-series signals gathered from sensors in similar assets while the similar assets were run to failure;
using the inferential model to generate estimated values for the RUL training set of time-series signals;
performing a pairwise differencing operation between actual values and the estimated values for the RUL training set of time-series signals to produce residuals;
performing an SPRT on the residuals to produce SPRT alarms; and
training the logistic regression model to predict an RUL for the asset based on correlations between the SPRT alarms and associated failure times for the similar assets.

### Claim 4 (depends on 1)

The method of claim 1, wherein the sensitivity parameters for the SPRT include one or more of the following:
a false alarm probability parameter α;
a missed alarm probability parameter β;
a parameter M associated with a positive mean test and a negative mean test for the SPRT; and
a parameter V associated with a nominal variance test and an inverse variance test for the SPRT.

### Claim 5 (depends on 1)

The method of claim 1, wherein the TF is a windowed TF, which is associated with a preceding time window of SPRT alarms.

### Claim 6 (depends on 1)

The method of claim 1, wherein the asset comprises one of the following:
a component in a power generation system; and
a component in a power transmission system.

### Claim 7 (depends on 1)

The method of claim 1, wherein the inferential model comprises a Multivariate State Estimation Technique (MSET) model.

### Claim 8

A non-transitory, computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for estimating a remaining useful life (RUL) of an asset, wherein during a surveillance mode, the method comprises:
receiving a set of present time-series signals gathered from sensors in the asset;
using an inferential model to generate estimated values for the set of present time-series signals;
performing a pairwise differencing operation between actual values and the estimated values for the set of present time-series signals to produce residuals;
performing a sequential probability ratio test (SPRT) on the residuals to produce SPRT alarms having an associated tripping frequency (TF);
while the TF exceeds a TF threshold, iteratively adjusting sensitivity parameters for the SPRT to reduce the TF, and performing the SPRT again on the residuals; and
when the TF for the SPRT alarms falls below the TF threshold,
using a logistic regression model to compute an RUL-based risk index for the asset based on the TF, and
when the risk index exceeds a risk-index threshold, generating a notification indicating that the asset needs to be replaced.

### Claim 9 (depends on 8)

The non-transitory, computer-readable storage medium of claim 8, wherein during an inferential-training mode, which precedes the surveillance mode, the method further comprises:
receiving an inferential training set of time-series signals gathered from sensors in the asset during normal fault-free operation; and
training the inferential model to predict values of the time-series signals based on the inferential training set.

### Claim 10 (depends on 9)

The non-transitory, computer-readable storage medium of claim 9, wherein during an RUL-training mode, which follows the inferential training mode and precedes the surveillance mode, the method further comprises:
receiving an RUL training set of historical time-series signals gathered from sensors in similar assets while the similar assets were run to failure;
using the inferential model to generate estimated values for the RUL training set of time-series signals;
performing a pairwise differencing operation between actual values and the estimated values for the RUL training set of time-series signals to produce residuals;
performing an SPRT on the residuals to produce SPRT alarms; and
training the logistic regression model to predict an RUL for the asset based on correlations between the SPRT alarms and associated failure times for the similar assets.

### Claim 11 (depends on 8)

The non-transitory, computer-readable storage medium of claim 8, wherein the sensitivity parameters for the SPRT include one or more of the following:
a false alarm probability parameter α;
a missed alarm probability parameter β;
a parameter M associated with a positive mean test and a negative mean test for the SPRT; and
a parameter V associated with a nominal variance test and an inverse variance test for the SPRT.

### Claim 12 (depends on 8)

The non-transitory, computer-readable storage medium of claim 8, wherein the TF is a windowed TF, which is associated with a preceding time window of SPRT alarms.

### Claim 13 (depends on 8)

The non-transitory, computer-readable storage medium of claim 8, wherein the asset comprises one of the following:
a component in a power generation system; and
a component in a power transmission system.

### Claim 14 (depends on 8)

The non-transitory, computer-readable storage medium of claim 8, wherein the inferential model comprises a Multivariate State Estimation Technique (MSET) model.

### Claim 15

A system that estimates a remaining useful life (RUL) of an asset, comprising:
at least one processor and at least one associated memory; and
a notification mechanism that executes on the at least one processor, wherein during a surveillance mode, the notification mechanism:
receives a set of present time-series signals gathered from sensors in the asset;
uses an inferential model to generate estimated values for the set of present time-series signals;
performs a pairwise differencing operation between actual values and the estimated values for the set of present time-series signals to produce residuals;
performs a sequential probability ratio test (SPRT) on the residuals to produce SPRT alarms having an associated tripping frequency (TF);
while the TF exceeds a TF threshold, iteratively adjusts sensitivity parameters for the SPRT to reduce the TF, and performs the SPRT again on the residuals; and
when the TF for the SPRT alarms falls below the TF threshold,
uses a logistic regression model to compute an RUL-based risk index for the asset based on the TF, and
when the risk index exceeds a risk-index threshold, generates a notification indicating that the asset needs to be replaced.

### Claim 16 (depends on 15)

The system of claim 15, wherein during an inferential-training mode, which precedes the surveillance mode, the notification mechanism:
receives an inferential training set of time-series signals gathered from sensors in the asset during normal fault-free operation; and
trains the inferential model to predict values of the time-series signals based on the inferential training set.

### Claim 17 (depends on 16)

The system of claim 16, wherein during an RUL-training mode, which follows the inferential training mode and precedes the surveillance mode, the notification mechanism:
receives an RUL training set of historical time-series signals gathered from sensors in similar assets while the similar assets were run to failure;
uses the inferential model to generate estimated values for the RUL training set of time-series signals;
performs a pairwise differencing operation between actual values and the estimated values for the RUL training set of time-series signals to produce residuals;
performs an SPRT on the residuals to produce SPRT alarms; and
trains the logistic regression model to predict an RUL for the asset based on correlations between the SPRT alarms and associated failure times for the similar assets.

### Claim 18 (depends on 15)

The system of claim 15, wherein the sensitivity parameters for the SPRT include one or more of the following:
a false alarm probability parameter α;
a missed alarm probability parameter β;
a parameter M associated with a positive mean test and a negative mean test for the SPRT; and
a parameter V associated with a nominal variance test and an inverse variance test for the SPRT.

### Claim 19 (depends on 15)

The system of claim 15, wherein the TF is a windowed TF, which is associated with a preceding time window of SPRT alarms.

### Claim 20 (depends on 15)

The system of claim 15, wherein the asset comprises one of the following:
a component in a power generation system; and
a component in a power transmission system.