# US 2023/0392846 A1 · Building system with automatic chiller anti-surge control

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

- Number: US 2023/0392846 A1
- Document ID: US20230392846A1
- Status: Published application
- Kind: A1
- Application number: 18/236,286
- Filed: 2023-08-21
- Published: 2023-12-07
- Earliest claimed: 2020-02-28
- Assignees: Johnson Controls Tyco IP Holdings LLP
- Applicants: Johnson Controls Tyco IP Holdings LLP
- Inventors: Liming Yang; Thomas M. Seneczko; Curtis C. Crane; Justin P. Kauffman
- Web page: https://patentgrep.com/patent/US20230392846A1

## CPC

- F25B 1/053: of turbine type
- F25B 49/022: {Compressor control arrangements}
- F04D 27/0246: {by varying geometry within the pumps, e.g. by adjusting vanes}
- F04D 27/0261: {by varying driving speed}
- F04D 27/0284: {Conjoint control of two or more different functions}
- F24F 11/64: using pre-stored data
- F25B 25/005: {using primary and secondary systems}
- F25B 49/02: for compression type machines, plants or systems
- F05B 2270/404: active, predictive, or anticipative
- F05B 2270/709: with neural networks
- F25B 2339/047: Water-cooled condensers
- F25B 2500/06: Damage
- F25B 2500/12: Sound
- F25B 2500/13: Vibrations
- F25B 2600/0253: with variable speed
- Y02B 30/70: Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
- F25B: REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
- F04D: NON-POSITIVE-DISPLACEMENT PUMPS (engine fuel-injection pumps F02M; ion pumps H01J41/12; electrodynamic pumps H02K44/02)
- F24F: AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING (removing dirt or fumes from areas where they are produced B08B15/00; vertical ducts for carrying away waste gases from buildings E04F17/02; tops for chimneys or ventilating shafts, terminals for flues F23L17/02)
- F05B: INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- Y02B: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS

## Abstract

A method of operating a chiller to avoid future surge events, the method comprises applying chiller operating data associated with a chiller as an input to one or more machine learning models; and generating a threshold for a controllable chiller variable to prevent a future chiller surge event from occurring based on an output of the one or more machine learning models, further comprising affecting operation of the chiller based on the threshold to prevent the future chiller surge event from occurring. The method enables automatic control of a chiller to avoid future chiller surge events.

## Claims

### Claim 1

A method of operating a chiller to avoid future surge events, the method comprising:
applying chiller operating data associated with a chiller as an input to one or more machine learning models; and
generating a threshold for a controllable chiller variable to prevent a future chiller surge event from occurring based on an output of the one or more machine learning models, further comprising affecting operation of the chiller based on the threshold to prevent the future chiller surge event from occurring.

### Claim 2 (depends on 1)

The method of claim 1, further comprising generating the one or more machine learning models by:
creating a set of training data by:
detecting a past surge event in historical chiller operating data, and
labeling a portion of the historical chiller operating data as surge chiller operating data associated with the past surge event; and
training the one or more machine learning models with the set of training data.

### Claim 3 (depends on 2)

The method of claim 2, wherein the surge chiller operating data comprise a timeseries including values of one or more variables of the historical chiller operating data associated with times before and during the past surge event.

### Claim 4 (depends on 1)

The method of claim 1, wherein affecting operation of the chiller comprises determining, based on the output of the one or more machine learning models, values of one or more controllable chiller variables that are predicted to prevent the future surge event, the one or more controllable chiller variables comprising at least one of:
a variable speed drive frequency;
a pre-rotational vane position; or
a variable geometry diffuser position.

### Claim 5 (depends on 1)

The method of claim 1, wherein the controllable chiller variable is a first controllable chiller variable and affecting operation of the chiller further comprises:
adjusting the first controllable chiller variable to affect a cooling capacity of the chiller until either:
the cooling capacity of the chiller reaches a desired cooling capacity; or
the first controllable chiller variable reaches the threshold; and
in response to the first controllable chiller variable reaching the threshold before the cooling capacity of the chiller reaches the desired cooling capacity, adjusting a second controllable chiller variable until the cooling capacity of the chiller reaches the desired cooling capacity.

### Claim 6 (depends on 1)

The method of claim 1, wherein the chiller operating data comprises at least one of a refrigerant type, a discharge pressure, a suction pressure, a stall voltage, an input current, a bearing position, a current variable speed drive frequency, a current pre-rotational vane position, or a current variable geometry diffuser position.

### Claim 7 (depends on 1)

The method of claim 1, wherein the input to the one or more machine learning models comprises a value of the controllable chiller variable and the output of the one or more machine learning models comprises a probability that the future chiller surge event will occur if the value of the controllable chiller variable is used to operate the chiller, and wherein generating the threshold for the controllable chiller variable comprises:
comparing the probability that the future chiller surge event will occur with a probability threshold; and
setting the threshold for the controllable chiller variable to the value of the controllable chiller variable in response to determining that the probability that the future chiller surge event will occur does not violate the probability threshold.

### Claim 8 (depends on 1)

The method of claim 1, wherein the input to the one or more machine learning models comprises a probability that the future chiller surge event will occur, and wherein the output of the one or more machine learning models comprises a value for the threshold for the controllable chiller variable.

### Claim 9 (depends on 1)

The method of claim 1, wherein the one or more machine learning models comprise at least one of a neural network, random forest, or a support vector machine.

### Claim 10 (depends on 1)

The method of claim 1, wherein the output of the one or more machine learning models comprises probabilities for a plurality of values for the controllable chiller variable, and wherein generating the threshold for the controllable chiller variable comprises selecting one of the plurality of values for the controllable chiller variable based on the probabilities for the plurality of values for the controllable chiller variable.

### Claim 11

A system comprising one or more memory devices storing instructions thereon that, when executed by one or more processors, cause the one or more processors to:
provide chiller operating data associated with a chiller as an input to one or more machine learning models; and
provide a threshold for a controllable chiller variable to prevent a future chiller surge event from occurring using the one or more machine learning models.

### Claim 12 (depends on 11)

The system of claim 11, wherein the instructions cause the one or more processors to generate the one or more machine learning models by:
creating a set of training data by:
detecting a past surge event in historical chiller operating data, and
labeling a portion of the historical chiller operating data as surge chiller operating data associated with the past surge event; and
training the one or more machine learning models with the set of training data.

### Claim 13 (depends on 11)

The system of claim 11, wherein the input to the one or more machine learning models comprises a value of the controllable chiller variable and an output of the one or more machine learning models comprises a probability that the future chiller surge event will occur if the value of the controllable chiller variable is used to operate the chiller, and wherein the instructions cause the one or more processors to generate the threshold for the controllable chiller variable by:
comparing the probability that the future chiller surge event will occur with a probability threshold; and
setting the threshold for the controllable chiller variable to the value of the controllable chiller variable in response to determining that the probability that the future chiller surge event will occur does not violate the probability threshold.

### Claim 14 (depends on 11)

The system of claim 11, wherein the instructions cause the one or more processors to affect operation of the chiller to avoid applying a control signal with a value that exceeds the threshold.

### Claim 15 (depends on 14)

The system of claim 14, wherein the controllable chiller variable is a first controllable chiller variable and wherein the instructions cause the one or more processors to affect operation of the chiller by:
adjusting the first controllable chiller variable to affect a cooling capacity of the chiller until either:
the cooling capacity of the chiller reaches a desired cooling capacity; or
the first controllable chiller variable reaches the threshold; and
in response to the first controllable chiller variable reaching the threshold before the cooling capacity of the chiller reaches the desired cooling capacity, adjusting a second controllable chiller variable until the cooling capacity of the chiller reaches the desired cooling capacity.

### Claim 16

A method of operating a chiller, the method comprising:
generating a first threshold for a first controllable chiller variable corresponding to a probability of a future chiller surge event occurring based on an output of one or more machine learning models;
determining whether a chiller can handle a cooling capacity based on the first threshold for the first controllable chiller variable;
based on determining that the chiller would not be able to handle the cooling capacity based on the first threshold for the first controllable chiller variable, generating a second threshold for a second controllable chiller variable corresponding to the probability of the future chiller surge event occurring based on a second output of the one or more machine learning models; and
affecting operation of the chiller based on the first threshold and the second threshold.

### Claim 17 (depends on 16)

The method of claim 16, wherein the first controllable chiller variable is a pre-rotational vane position or a variable geometry diffuser position and the first threshold is a first upper boundary corresponding to the probability of the future chiller surge event occurring, and wherein the second controllable chiller variable is a variable speed drive frequency and the second threshold is a second upper boundary corresponding to the probability of the future chiller surge event occurring.

### Claim 18 (depends on 16)

The method of claim 16, wherein the first controllable chiller variable is a variable speed drive frequency and the first threshold is a first lower boundary corresponding to the probability of the future chiller surge event occurring, and wherein the second controllable chiller variable is a pre-rotational vane position or a variable geometry diffuser position and the second threshold is a second lower boundary corresponding to the probability of the future chiller surge event occurring.

### Claim 19 (depends on 16)

The method of claim 16, wherein the probability is a first probability, and wherein generating the first threshold for the first controllable chiller variable corresponding to the probability of the future chiller surge event occurring comprises:
obtaining a first output from the one or more machine learning models indicating a second probability that a surge will occur;
based on a first difference between the second probability and the first probability exceeding a third threshold, updating a value for the first controllable chiller variable of a chiller operating data to obtain updated chiller operating data;
providing the updated chiller operating data to the one or more machine learning models to obtain a third probability; and
based on a second difference between the third probability and the first probability being less than the third threshold, generating the first threshold for the first controllable chiller variable based on the updated value.

### Claim 20 (depends on 16)

The method of claim 16, operation of the chiller further comprises:
adjusting the first controllable chiller variable to affect a cooling capacity of the chiller until either:
the cooling capacity of the chiller reaches a desired cooling capacity; or
the first controllable chiller variable reaches the first threshold; and
in response to the first controllable chiller variable reaching the first threshold before the cooling capacity of the chiller reaches the desired cooling capacity, adjusting the second controllable chiller variable until the cooling capacity of the chiller reaches the desired cooling capacity.
