# US 12,007,753 B2 · System and method for predicting industrial equipment motor behavior

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

- Number: US 12,007,753 B2
- Document ID: US12007753B2
- Status: Granted
- Kind: B2
- Application number: 16/442,250
- Filed: 2019-06-14
- Published: 2020-12-17
- Granted: 2024-06-11
- Earliest claimed: 2019-06-14
- Assignees: One Tech LLC
- Applicants: One Tech, Inc.
- Inventors: Yandong Zhang; Yasser Khan
- Web page: https://patentgrep.com/patent/US12007753B2

## CPC

- G05B 19/4184: {characterised by fault tolerance, reliability of production system}
- 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}
- G05B 19/4183: {characterised by data acquisition, e.g. workpiece identification}
- G05B 23/027: {Alarm generation, e.g. communication protocol; Forms of alarm}
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- 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)}
- 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

A computer implemented method and system for predicting motor failure. The system and method employ artificial intelligence to train machine learning models to predict failure mechanisms within a machine. The system features at least one database configured to store machine performance indicator data. At least one server is configured to receive the indicator data and train machine learning models which are used by a processor to predict motor failure. The method for predicting motor failure is iterative, allowing the machine learning model to become more skilled at predicting machine performance outcomes in real-time.

## Claims

### Claim 1

A non-transitory computer-readable medium with instructions stored thereon, wherein the medium is configured to predict a behavior of a motor, that when executed by a processor, performs the steps comprising: determining a plurality of predictive machine learning models; receiving input values from at least one sensor, said at least one sensor is configured to receive operational data from the motor; updating a probability of a plurality of operational outcome of the motor for each of a unit time stamp within a predetermined time period, comprising: calculating a percentage of input values that are correct; removing, at random, a plurality of input values corresponding to the percentage that are incorrect; calculating a mean square prediction error value from the input values not removed; calculating a weight of each of the plurality of predictive machine learning models; determining an upper bound and a lower bound of the input values not removed; calculating a counter value for each of the plurality of predictive machine learning models; updating the weight of each of the plurality of predictive machine learning models; calculating a normal probability; updating the upper bound and lower bound of the input values not removed; updating the normal probability based on the updated upper bound and updated lower bound of the input values not removed; calculating the probability of a plurality of operational outcomes of the motor; predicting the behavior of the motor for said unit time stamp; and transferring data respecting the predicted behavior of the motor to at least one of a personal computer (PC) and a smart phone.

### Claim 2 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein calculating the weight comprises calculation of the weighted average contribution of each of the plurality of predictive machine learning models to a total of the plurality of predictive machine learning model.

### Claim 3 (depends on 2)

The non-transitory computer-readable medium of claim 2, wherein updating the weight of each of the plurality of predictive machine learning models comprises updating said weight in every time stamp period.

### Claim 4 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the method is used to predict thermal runaway.

### Claim 5 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the method is used to generate a range of temperature range predictions.

### Claim 6 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the processor generates an urgent alert signal if thermal runaway is predicted.

### Claim 7

A system comprising: a non-transitory computer-readable medium with instructions encoded thereon, wherein the medium is configured to predict a behavior of a motor; and one or more processors configured to, when executing the instructions, perform operations of: determining a plurality of predictive machine learning models; receiving input values from at least one sensor, said at least one sensor is configured to receive operational data from the motor; updating a probability of a plurality of operational outcome of the motor for each of a unit time stamp within a predetermined time period, comprising: calculating a percentage of input values that are correct; removing, at random, a plurality of input values corresponding to the percentage that are incorrect; calculating a mean square prediction error value from the input values not removed; calculating a weight of each of the plurality of predictive machine learning models; determining an upper bound and a lower bound of the input values not removed; calculating a counter value for each of the plurality of predictive machine learning models; updating the weight of each of the plurality of predictive machine learning models; calculating a normal probability; updating the upper bound and lower bound of the input values not removed; updating the normal probability based on the updated upper bound and updated lower bound of the input values not removed; calculating the probability of a plurality of operational outcomes of the motor; predicting the behavior of the motor for said unit time stamp; and transferring data respecting the predicted behavior of the motor to at least one of a personal computer (PC) and a smart phone.

### Claim 8 (depends on 7)

The system of claim 7, wherein calculating the weight comprises calculation of the weighted average contribution of each of the plurality of predictive machine learning models to a total of the plurality of predictive machine learning model.

### Claim 9 (depends on 7)

The system of claim 7, wherein updating the weight of each of the plurality of predictive machine learning models comprises updating said weight in every time stamp period.

### Claim 10 (depends on 7)

The system of claim 7, wherein the method is used to predict thermal runaway.

### Claim 11 (depends on 7)

The system of claim 7, wherein the method is used to generate a range of temperature range predictions.

### Claim 12 (depends on 7)

The system of claim 7, wherein the processor generates an urgent alert signal if thermal runaway is predicted.