Systems and methods for evaluation of chiller plant operation economy

Patent metadata

Field	Value
Publication number	US-2025305696-A1
Application number	US-202418619218-A
Country	US
Kind code	A1
Filing date	Mar 28, 2024
Priority date	Mar 28, 2024
Publication date	Oct 2, 2025
Grant date	—

Abstract

A method for evaluation of chiller plant operation economy is disclosed. The method comprises receiving a first set of data associated with each chiller over a training interval; generating a ML model for each chiller; deploying the generated ML model to a model of each chiller over a ranking interval; receiving a second set of data associated with each chiller, from the sensors; averaging second set of data for each type of sensor across chillers; determining a power consumption of the ML model of each chiller and comparing it over the ranking interval to determine a best ML model; deploying the ML models to an non-degraded chiller plant model and the best ML model to an ideal chiller plant model; comparing the sum of measured actual power consumptions of chillers with calculated consumptions of a non-degraded chiller plant model and ideal chiller plant model to determine estimated potential of savings.

First claim

What is claimed is:

1 . A method comprising:
receiving, via at least one processor, a first set of data associated with each of a plurality of chillers of a chiller plant, from one or more sensors, over a training interval; generating, via the at least one processor, a machine learning (ML) model for each of the plurality of chillers of the chiller plant based at least on the received first set of data; deploying, via the at least one processor, the generated at least one ML model to a model of each of the plurality of chillers of the chiller plant over a ranking interval; receiving, via the at least one processor, a second set of data associated with each of the plurality of chillers of the chiller plant, from the one or more sensors, over the ranking interval; averaging, via the at least one processor, the second set of data associated with each of the plurality of chillers of the chiller plant; determining, via the at least one processor, a power consumption of each of the plurality of chillers of the chiller plant based at least on the averaged second set of data, using the at least one ML model; and comparing, via the at least one processor, the power consumption of each model of a chiller of the plurality of chillers over the ranking interval to determine a best ML model.

2 . The method of claim 1 , wherein the one or more sensors comprises at least one of a temperature sensor, a humidity sensor, calorimeter, and a power meter.

3 . The method of claim 1 , wherein the first set of data and the second set of data comprises at least one of chilled water temperature, cooling water temperature, and cooling demand.

4 . The method of claim 1 , wherein the training interval and the ranking interval correspond to at least one of hours, days, months, quarters, or years in which the first set of data and the second set of data are received.

5 . The method of claim 1 , wherein the second set of data is averaged across each of the plurality of chillers to standardize and allow consistent input data for the at least one ML model for each of the plurality of chillers of the chiller plant.

6 . The method of claim 1 further comprising deploying, via the at least one processor, the best ML model to the model of the each chiller of the chiller plant to form an ideal chiller plant ML model.

7 . The method of claim 6 further comprising comparing, via the at least one processor, power consumption of each of the plurality of chillers of the chiller plant with the ideal chiller plant ML model to determine real time efficiency of each of the plurality of chillers of the chiller plant.

8 . The method of claim 1 , wherein the best ML model corresponds to a model of the chiller among the plurality of chillers having minimum electricity consumption.

9 . A system comprising:
a memory; and at least one processor communicatively coupled to the memory, wherein the at least one processor is configured to:
receive a first set of data associated with each of a plurality of chillers of a chiller plant, from one or more sensors, over a training interval;
generate a machine learning (ML) model for each of the plurality of chillers of the chiller plant based at least on the received first set of data;
deploy the generated at least one ML model to model of each of the plurality of chillers of the chiller plant over a ranking interval;
receive a second set of data associated with each of the plurality of chillers of the chiller plant, from the one or more sensors, over the ranking interval;
average the second set of data associated with each of the plurality of chillers of the chiller plant;
determine a power consumption of each of the plurality of chillers of the chiller plant based at least on the averaged second set of data, using the at least one ML model; and
compare the power consumption of each model of a chiller of the plurality of chillers over the ranking interval to determine a best ML model.

10 . The system of claim 9 , wherein the one or more sensors comprises at least one of a temperature sensor, a humidity sensor, and a power meter.

11 . The system of claim 9 , wherein the first set of data and the second set of data comprises at least one of chilled water temperature, cooling water temperature, and cooling demand.

12 . The system of claim 9 , wherein the training interval and the ranking interval correspond to at least one of hours, days, months, quarters, or years in which the first set of data and the second set of data are received.

13 . The system of claim 9 , wherein the second set of data is averaged to standardize and allow consistent input data for the at least one ML model for each of the plurality of chillers of the chiller plant.

14 . The system of claim 9 , wherein the at least one processor is further configured to deploy the best ML model to the model of the each chiller of the chiller plant to form an ideal chiller plant ML model.

15 . The system of claim 14 , wherein the at least one processor is further configured to compare power consumption of each model of the chiller of the plurality of chillers of the chiller plant with the ideal chiller plant ML model to determine real time efficiency of each of the plurality of chillers of the chiller plant.

16 . The system of claim 9 , wherein the best ML model corresponds to a model of the chiller among the plurality of chiller models having minimum electricity consumption.

17 . A non-transitory machine-readable information storage medium comprising one or more instructions which when executed by at least one processor to perform operations comprising:
receiving a first set of data associated with each of a plurality of chillers of a chiller plant, from one or more sensors, over a training interval; generating a machine learning (ML) model for each of the plurality of chillers of the chiller plant based at least on the received first set of data; deploying the generated at least one ML model to a model of each chiller of the plurality of chillers of the chiller plant over a ranking interval; receiving a second set of data associated with each of the plurality of chillers of the chiller plant, from the one or more sensors, over the ranking interval; averaging the second set of data associated with each of the plurality of chillers of the chiller plant; determining a power consumption of each of the plurality of chillers of the chiller plant based at least on the averaged second set of data, using the at least one ML model; and comparing the power consumption of each of the plurality of chillers over the ranking interval to determine a best ML model.

18 . The non-transitory machine-readable information storage medium of claim 17 , wherein the one or more sensors comprises at least one of a temperature sensor, a humidity sensor, calorimeter, and a power meter, and wherein the first set of data and the second set of data comprises chiller water temperature, cooling water temperature, and cooling demand, and wherein the second set of data is averaged to standardize and allow consistent input data for the at least one ML model for each of the plurality of chillers of the chiller plant.

19 . The non-transitory machine-readable information storage medium of claim 17 , wherein the at least one processor is further configured to:
deploy the best ML model to the model of the each chiller of the chiller plant to form an ideal chiller plant ML model; and compare power consumption of each model of chiller of each of the plurality of chillers of the

Assignees

• Honeywell Int Inc

Inventors

• Schindler Zdenek

Classifications

• G06N20/20

  Ensemble learning · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06Q50/06

  Energy or water supply · CPC title

• G06N20/00

  Machine learning · CPC title

• F24F11/64

  using pre-stored data · CPC title