# US 2021/0041383 A1 · Steam trap monitoring devices, systems, and related techniques

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

- Number: US 2021/0041383 A1
- Document ID: US20210041383A1
- Status: Published application
- Kind: A1
- Application number: 16/534,945
- Filed: 2019-08-07
- Published: 2021-02-11
- Earliest claimed: 2019-08-07
- Assignees: Everactive, Inc.
- Applicants: Everactive, Inc.
- Inventors: David D. Wentzloff; Benton H. Calhoun; Nathan E. Roberts; Tom O'Brien; Sean P. Mahnken
- Web page: https://patentgrep.com/patent/US20210041383A1

## CPC

- F16T 1/48: Monitoring arrangements for inspecting, e.g. flow of steam and steam condensate
- G01N 25/72: Investigating presence of flaws
- 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}
- 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}
- F22B 37/38: Determining or indicating operating conditions in steam boilers, e.g. monitoring direction or rate of water flow through water tubes
- G05D 23/123: {the sensing element being placed within a regulating fluid flow}
- F16T: STEAM TRAPS OR LIKE APPARATUS FOR DRAINING-OFF LIQUIDS FROM ENCLOSURES PREDOMINANTLY CONTAINING GASES OR VAPOURS
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- 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)
- F22B: METHODS OF STEAM GENERATION; STEAM BOILERS
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES

## Abstract

Devices, systems, and techniques relating to steam trap monitoring are described. These include battery-less steam trap monitors that run on power harvested from their environments, systems for acquiring steam trap monitor data for the traps in a facility or across multiple facilities, and techniques for processing steam trap monitor data to reliably determine the status of individual steam traps and potentially other system parameters.

## Claims

### Claim 1

A computer-implemented method, comprising:
receiving steam trap data for a steam trap, the steam trap data comprising time series data representing one or both of steam temperature and condensate temperature;
determining normal baseline operation of the steam trap based on a first range of the time series data; and
determining a change in operation of the steam trap based on one or more data points of the time series data.

### Claim 2 (depends on 1)

The method of claim 1, wherein the time series data include first time series data representing the steam temperature and second time series data representing the condensate temperature, and wherein determining the normal baseline operation of the steam trap includes:
generating a plurality of vectors using the steam trap data, the plurality of vectors including one or more steam temperature envelope vectors based on the first time series data, and one or more condensate temperature envelope vectors based on the second time series data;
determining one or more periods during which live steam is flowing at the steam trap based on the first time series data; and
based on determining the one or more periods and the normal baseline operation of the steam trap, processing a first subset of the vectors to determine a state of the steam trap during at least one of the periods.

### Claim 3 (depends on 2)

The method of claim 2, wherein the state of the steam trap includes one of normal, failed open, modulating, or failed closed.

### Claim 4 (depends on 2)

The method of claim 2, wherein determining the one or more periods includes:
using a plurality of methods to determine a plurality of on states and a plurality of off states based on the first time series data using each of the methods, each of the on states and each off states having a confidence value associated therewith; and
using the confidence values, combining or selecting from among the on and off states for the plurality of methods to define the one or more periods.

### Claim 5 (depends on 2)

The method of claim 2, wherein determining the one or more periods includes determining a set of floating thresholds based on the one or more steam temperature envelope vectors, and determining points at which the first time series data are above or below corresponding floating thresholds.

### Claim 6 (depends on 2)

The method of claim 2, wherein determining the one or more periods includes determining points at which the first time series data are above or below a fixed threshold using a range of hysteresis around the fixed threshold.

### Claim 7 (depends on 2)

The method of claim 2, wherein determining the one or more periods includes determining a first point at which the first time series data is below a threshold, and identifying a second point in the first time series data earlier than the first point as corresponding to a steam off event.

### Claim 8 (depends on 7)

The method of claim 7, wherein the second point is identified using a sample time interval vector based on either or both of the first and second time series data.

### Claim 9 (depends on 2)

The method of claim 2, wherein determining the one or more periods includes determining a threshold based on a ground truth event representing a baseline for normal operation of the steam trap, and determining points at which the first time series data are above or below the threshold.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
determining that the steam trap is in a modulated steam application based on the time series data;
wherein determining the normal baseline operation of the steam trap is based, at least in part, on determining that the steam trap is in a modulated steam application.

### Claim 11 (depends on 10)

The method of claim 10, wherein determining that the steam trap is in a modulated steam application includes applying a fast Fourier transform to at least a portion of the time series data, or applying an autocorrelation function to at least a portion of the time series data.

### Claim 12 (depends on 1)

The method of claim 1, wherein the time series data include first time series data representing the steam temperature and second time series data representing the condensate temperature, and wherein determining the normal baseline operation of the steam trap includes:
generating a plurality of vectors using the steam trap data, the plurality of vectors including one or more steam temperature envelope vectors based on the first time series data, and one or more condensate temperature envelope vectors based on the second time series data; and
determining a centroid of a set of data points using the one or more steam temperature envelope vectors or the one or more condensate temperature envelope vectors, each data point representing corresponding values of the first or second time series data;
and wherein determining a change in operation of the steam trap includes:
tracking deviations of the data points relative to the centroid of the data points; and
identifying a subset of the deviations having corresponding magnitudes larger than a threshold and corresponding angles within a specified angle range.

### Claim 13 (depends on 12)

The method of claim 12, wherein the threshold is based on a variance of the data points.

### Claim 14 (depends on 13)

The method of claim 13, wherein the threshold is defined based on a specific number of standard deviations of the variance.

### Claim 15 (depends on 12)

The method of claim 12, further comprising receiving steam trap metadata, the steam trap metadata representing a steam trap type of the steam trap and a steam trap application of the steam trap, wherein the threshold and specified angle range are based on the steam trap type and the steam trap application.

### Claim 16 (depends on 1)

The method of claim 1, further comprising receiving steam trap metadata, the steam trap metadata representing a steam trap type of the steam trap and a steam trap application of the steam trap, wherein determining the normal baseline operation of the steam trap is based on the steam trap type and the steam trap application.

### Claim 17

A system, comprising one or more computing devices configured to:
receive steam trap data for a steam trap, the steam trap data including first time series data representing steam temperature and second time series data representing condensate temperature;
generate a plurality of vectors using the steam trap data, the plurality of vectors including a sample time interval vector based on either or both of the first and second time series data, one or more steam temperature envelope vectors based on the first time series data, and one or more condensate temperature envelope vectors based on the second time series data;
determine one or more periods during which live steam is flowing at the steam trap; and
based on determining the one or more periods, process a first subset of the vectors to determine a state of the steam trap during at least one of the periods.

### Claim 18 (depends on 17)

The system of claim 17, wherein the state of the steam trap includes one of normal, failed open, modulating, or failed closed.

### Claim 19 (depends on 17)

The system of claim 17, wherein the one or more computing devices are configured to determine the one or more periods by:
using a plurality of methods to determine a plurality of on states and a plurality of off states using each of the methods, each of the on states and each off states having a confidence value associated therewith; and
using the confidence values, combining or selecting from among the on and off states for the plurality of methods to define the one or more periods.

### Claim 20 (depends on 17)

The system of claim 17, wherein the one or more computing devices are configured to determine the one or more periods by determining a set of floating thresholds based on the one or more steam temperature envelope vectors, and determining points at which the first time series data are above or below corresponding floating thresholds.

### Claim 21 (depends on 17)

The system of claim 17, wherein the one or more computing devices are configured to determine the one or more periods by determining points at which the first time series data are above or below a fixed threshold using a range of hysteresis around the fixed threshold.

### Claim 22 (depends on 17)

The system of claim 17, wherein the one or more computing devices are configured to determine the one or more periods by determining a first point at which the first time series data is below a threshold, and identifying a second point in the first time series data earlier than the first point as corresponding to a steam off event.

### Claim 23 (depends on 22)

The system of claim 22, wherein the second point is identified using the sample time interval vector.

### Claim 24 (depends on 17)

The system of claim 17, wherein the one or more computing devices are configured to determine the one or more periods by determining a threshold based on a ground truth event representing a baseline for normal operation of the steam trap, and determining points at which the first time series data are above or below the threshold.

### Claim 25 (depends on 17)

The system of claim 17, wherein the one or more computing devices are further configured to:
determine that the steam trap is in a modulated steam application based on the first time series data; and
wherein the one or more computing devices are configured to determine the state of the steam trap, at least in part, by determining that the steam trap is in a modulated steam application.

### Claim 26 (depends on 25)

The system of claim 25, wherein the one or more computing devices are configured to determine that the steam trap is in a modulated steam application by applying a fast Fourier transform to the first time series data, or applying an autocorrelation function to the first time series data.

### Claim 27 (depends on 17)

The system of claim 17, wherein the one or more computing devices are configured to process the first subset of the vectors to determine the state of the steam trap by:
determining a centroid of a set of data points using the one or more steam temperature envelope vectors and the one or more condensate temperature envelope vectors, each data point representing corresponding values of the first and second time series data;
tracking deviations of short-term averages of the data points relative to the centroid of the data points; and
identifying a subset of the deviations having corresponding magnitudes larger than a threshold and corresponding angles within a specified angle range.

### Claim 28 (depends on 27)

The system of claim 27, wherein the threshold is based on a variance of the data points.

### Claim 29 (depends on 28)

The system of claim 28, wherein the threshold is based on a specific number of standard deviations of the variance.

### Claim 30 (depends on 27)

The system of claim 27, wherein the one or more computing devices are further configured to receive steam trap metadata, the steam trap metadata representing a steam trap type of the steam trap and a steam trap application of the steam trap, and wherein the threshold and specified angle range are based on the steam trap type and the steam trap application.

### Claim 31 (depends on 17)

The system of claim 17, wherein the one or more computing devices are configured to receive steam trap metadata, the steam trap metadata representing a steam trap type of the steam trap and a steam trap application of the steam trap, and wherein the one or more computing devices are configured to determine the one or more periods and process the first subset of the vectors based on the steam trap type and the steam trap application.

### Claim at position 32

32-51. (canceled)
