# US 10,120,374 B2 · Intelligent condition monitoring and fault diagnostic system for preventative maintenance

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

- Number: US 10,120,374 B2
- Document ID: US10120374B2
- Status: Granted
- Kind: B2
- Application number: 14/822,310
- Filed: 2015-08-10
- Published: 2015-12-03
- Granted: 2018-11-06
- Earliest claimed: 2005-07-11
- Assignees: Brooks Automation, Inc.
- Applicants: Brooks Automation, Inc.
- Inventors: Martin Hosek; Jay Krishnasamy; Jan Prochazka
- Web page: https://patentgrep.com/patent/US10120374B2

## CPC

- 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)}
- B25J 9/1674: {characterised by safety, monitoring, diagnostic}
- G05B 19/41875: {characterised by quality surveillance of production}
- G05B 23/0221: {Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods}
- G06F 11/2257: {using expert systems}
- 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)
- B25J: MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES ({manipulators specially adapted for use in surgery A61B34/70; manipulators used in cleaning hollow articles B08B9/04}; manipulators associated with rolling mills B21B39/20; manipulators associated with forging machines B21J13/10; {manipulators associated with picking-up and placing mechanisms B23P19/007}; means for holding wheels or parts thereof B60B30/00; {vehicles with ground-engaging propulsion means, e.g. walking members B62D57/02, B62D57/032; devices for picking-up and depositing articles or materials between conveyors B65G47/90, B65G47/91; manipulators with gripping or holding means for transferring packages B65H67/065}; cranes B66C; {manipulators used in the protection or supervision of pipe-line installations F17D5/00; walking equipment adapted for nuclear steam-generators F22B37/006}; manipulators specially adapted for, or associated with, nuclear reactors G21C; {apparatus used for handling wafers during manufacture or treatment of semiconductor H10P72/50})
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A system for condition monitoring and fault diagnosis includes a data collection function that acquires time histories of selected variables for one or more of the components, a pre-processing function that calculates specified characteristics of the time histories, an analysis function for evaluating the characteristics to produce one or more hypotheses of a condition of the one or more components, and a reasoning function for determining the condition of the one or more components from the one or more hypotheses.

## Claims

### Claim 1

A continuous health monitoring system comprising:
a controller including
a non-transitory data collection function that acquires unparametrized time histories of one or more component energy dissipation values during component operations;
a non-transitory pre-processing function that characterizes each unparametrized time history of the one more component energy dissipation values independently and computes metrics from characteristics of each independently characterized unparametrized time history of the one or more component energy dissipation values using an operational energy dissipation from the time histories and a baseline energy dissipation;
a non-transitory analysis function for evaluating whether the computed metrics exceed predetermined threshold values to produce one or more hypotheses of a condition of one or more components corresponding to the one or more component energy dissipation values; and
a non-transitory reasoning function for determining the condition of the one or more components from the one or more hypotheses,
wherein the data collection, pre-processing, and analysis functions operate in parallel with the component operations.

### Claim 2 (depends on 1)

The system of claim 1, wherein the data collection function acquires unparametrized time histories of mechanical energy dissipation values.

### Claim 3 (depends on 1)

The system of claim 1, wherein the data collection function acquires unparametrized time histories of electrical energy dissipation values.

### Claim 4 (depends on 1)

The system of claim 1, wherein the data collection function acquires unparametrized time histories of energy dissipation values of a robotic joint.

### Claim 5 (depends on 1)

The system of claim 1, wherein the data collection function acquires unparametrized time histories for a predefined sequence of component moves.

### Claim 6 (depends on 1)

The continuous health monitoring system of claim 1, wherein the pre-processing function computes a difference between the operational energy dissipation and the baseline energy dissipation as a first metric and an exponentially weighted moving average of the difference as a second metric.

### Claim 7 (depends on 1)

The system of claim 1, wherein the pre-processing function computes the predetermined threshold values using a confidence coefficient for predicting a change in the metrics.

### Claim 8 (depends on 1)

The system of claim 1, wherein the baseline energy dissipation used by the pre-processing function is acquired from data obtained from a selected move sequence.

### Claim 9 (depends on 1)

The system of claim 1, wherein the baseline energy dissipation used by the pre-processing function is acquired from a component model.

### Claim 10

A method of continuously monitoring system health comprising:
acquiring unparametrized time histories of one or more component energy dissipation values during component operations;
characterizing each unparametrized time history of the one or more component energy dissipation values independently and computing metrics, during the component operations, from characteristics of each independently characterized unparametrized time history of the one or more component energy dissipation values using an operational energy dissipation from the time histories and a baseline energy dissipation;
in parallel with the component operations, evaluating whether the computed metrics exceed predetermined threshold values to produce one or more hypotheses of a condition of one or more components corresponding to the one or more component energy dissipation values; and
determining the condition of the one or more components from the one or more hypotheses.

### Claim 11 (depends on 10)

The method of claim 10, further comprising acquiring unparametrized time histories of mechanical energy dissipation values.

### Claim 12 (depends on 10)

The method of claim 10, further comprising acquiring unparametrized time histories of electrical energy dissipation values.

### Claim 13 (depends on 10)

The method of claim 10, further comprising acquiring unparametrized time histories of energy dissipation values of a robotic joint.

### Claim 14 (depends on 10)

The method of claim 10, further comprising acquiring unparametrized time histories for a predefined sequence of component moves.

### Claim 15 (depends on 10)

The method of claim 10, further comprising computing a difference between the operational energy dissipation and the baseline energy dissipation as a first metric and an exponentially weighted moving average of the difference as a second metric.

### Claim 16 (depends on 10)

The method of claim 10, further comprising computing the predetermined threshold values using a confidence coefficient for predicting a change in the metrics.

### Claim 17 (depends on 10)

The method of claim 10, further comprising acquiring the baseline energy dissipation from data obtained from a selected move sequence.

### Claim 18 (depends on 10)

The method of claim 10, further comprising acquiring the baseline energy dissipation from data obtained from a component model.

### Claim 19

A continuous heath monitoring system comprising:
a controller including
a non-transitory data collection function that acquires unparametrized time histories of one or more values related to power consumption by a component during operation;
a non-transitory pre-processing function that characterizes each unparametrized time history of the one or more values related to power consumption independently and computes metrics from characteristics of each independently characterized unparametrized time history of the one or more values related to power consumption using an operational power consumption computed from the time histories and a power consumption baseline;
a non-transitory analysis function for evaluating whether the computed metrics exceed predetermined threshold values to produce one or more hypotheses of a condition of the component; and
a non-transitory reasoning function for determining the condition of the component from the one or more hypotheses,
wherein the data collection, pre-processing, and analysis functions operate in parallel with the component operations.

### Claim 20 (depends on 19)

The system of claim 19, wherein the one or more values related to power consumption by a component include component current consumption.

### Claim 21 (depends on 19)

The system of claim 19, wherein the one or more values related to power consumption by a component include or more of component position, velocity, or acceleration.

### Claim 22 (depends on 19)

The system of claim 19, wherein the power consumption baseline used by the pre-processing function is acquired from a component model.

### Claim 23 (depends on 19)

The system of claim 19, wherein the pre-processing function computes a difference between the operational power consumption and the baseline power consumption as a first metric and an exponentially weighted moving average of the difference as a second metric.

### Claim 24 (depends on 23)

The system of claim 23, wherein the data collection function acquires the unparametrized time histories for a predefined set of component locations and the pre-processing function computes difference between the operational power consumption and he baseline power consumption those predetermined locations as the first metric.

### Claim 25 (depends on 23)

The system of claim 23, wherein the data collection function acquires the unparametrized time histories for a predefined sequence of component moves and the pre-processing function computes an integral of the absolute value of the difference between the operational power consumption and the baseline power consumption over the predefined sequence of component moves as the first metric.

### Claim 26 (depends on 19)

The system of claim 19, wherein the pre-processing function computes a fast Fourier transform on portions of the unparametrized time histories and on portions of the baseline power consumption, and wherein the analysis function monitors peaks emerging or shifting in a frequency spectrum from the transform.

### Claim 27

A method of continuously monitoring system health comprising:
acquiring unparametrized time histories of one or more power consumption related values of a component during operation;
characterizing each unparametrized time history of the one or more power consumption related values independently and computing metrics from characteristics of each independently characterized unparametrized time history of the one or more power consumption related values during the component operations using an operational power consumption computed from the unparametrized time histories and a power consumption baseline;
in parallel with the component operations, evaluating whether the computed metrics exceed predetermined threshold values to produce one or more hypotheses of a condition of the component; and
determining the condition of the component from the one or more hypotheses.

### Claim 28 (depends on 27)

The method of claim 27, wherein the one or more power consumption related values include component current consumption.

### Claim 29 (depends on 27)

The method of claim 27, wherein the one or more power consumption related values include one or more of component position, velocity, or acceleration.

### Claim 30 (depends on 27)

The method of claim 27, further comprising determining the baseline energy dissipation from a component model.

### Claim 31 (depends on 27)

The method of claim 27, further comprising computing a difference between the operational power consumption and the baseline power consumption as a first metric and an exponentially weighted moving average of the difference as a second metric.

### Claim 32 (depends on 31)

The method of claim 31, further comprising acquiring time histories for a predefined set of component locations and computing a difference between the operational power consumption and the baseline power consumption at those predetermined locations as the first metric.

### Claim 33 (depends on 31)

The method of claim 31, further comprising acquiring unparametrized time histories a predefined sequence of component moves and computing an integral of the absolute value of the difference between the operational power consumption and the baseline power consumption over the predefined sequence of component moves as the first metric.

### Claim 34 (depends on 27)

The method of claim 27, further comprising computing a fast Fourier transform on portions of the unparametrized time histories and on portions of the baseline power consumption, and monitoring peaks emerging or shifting in a frequency spectrum from the transform.

### Claim 35

system for automatic fault diagnosis comprising:
a controller including
a non-transitory data collection function that acquires unparametrized time histories of selected power consumption related values for one or more components of a device in response to deterioration in the operation of the device;
a non-transitory pre-processing function that characterizes each unparametrized time history of the selected power consumption related values independently by calculating specified characteristics of the unparametrized time stories including a range and a minimum variance and requests additional unparametrized time history acquisition if certain thresholds are not met for the range and minimum variance;
a non-transitory analysis function for evaluating the characteristics to produce one or more hypotheses of a condition of the one or more components; and
a non-transitory reasoning function for determining faults of the one or more components or of the device from the one or more hypotheses.

### Claim 36 (depends on 35)

The system of claim 35, wherein the selected power consumption related values for the one or more components include component current consumption.

### Claim 37 (depends on 35)

The system of claim 35, wherein the selected power consumption related values for the one or more components include one or more of component position, velocity, or acceleration.

### Claim 38 (depends on 35)

The system of claim 35, wherein the power consumption baseline used by the pre-processing function is acquired from a component model.

### Claim 39

A method for automatic fault diagnosis comprising:
acquiring time unparametrized histories of selected power consumption related values for one or more components of a device in response to deterioration in the operation of the device;
characterizing each unparametrized time history of the selected power consumption related values independently by calculating specified characteristics of the unparametrized time histories including a range and a minimum variance and requests additional unparametrized time history acquisition if certain thresholds are not met for t e range and minimum variance;
evaluating the characteristics to produce one or more hypotheses of a condition of the one or more components; and
determining faults of the one or more components or of the device from the one or more hypotheses.

### Claim 40 (depends on 39)

The method of claim 39, wherein the selected power consumption related values for the one or more components include component current consumption.

### Claim 41 (depends on 39)

The method of claim 39, wherein the selected power consumption related values for the one or more components include one or more of component position, velocity, or acceleration.

### Claim 42 (depends on 39)

The method of claim 39, wherein the power consumption baseline used by the pre processing function is acquired from a component model.