Systems and methods for controlling equipment based on chiller efficiency assessments

Patent metadata

Field	Value
Publication number	US-2024337421-A1
Application number	US-202318297240-A
Country	US
Kind code	A1
Filing date	Apr 7, 2023
Priority date	Apr 7, 2023
Publication date	Oct 10, 2024
Grant date	—

Abstract

A method for assessing an efficiency of a chiller. The method includes: performing, using a processor of a computer system, an energy balance check on operational data of a chiller in a chiller group; selecting, using the processor and based on the energy balance check, a reference chiller from one or more other chillers in the chiller group, wherein an energy flow of the reference chiller has a best energy balance amongst the one or more other chillers; determining, using the processor and reference operational data from the reference chiller, the efficiency of the chiller; and performing, based on the determined efficiency of the chiller, an action with respect to a chiller plant containing the chiller. Other aspects are described and claimed.

First claim

What is claimed is:

1 . A computer-implemented method for controlling equipment based on assessing efficiency of a chiller, the computer-implemented method comprising operations including:
performing, using a processor of a computer system, an energy balance check on operational data of a chiller in a chiller group; selecting, using the processor and based on the energy balance check, a reference chiller from one or more other chillers in the chiller group, wherein an energy flow of the reference chiller has a best energy balance amongst the one or more other chillers; determining the efficiency of the chiller by using the processor to perform a coefficient of performance (COP) determination using a machine learning model trained on energy flow of the selected reference chiller; and controlling equipment including or impacted by the chiller, based on the determined efficiency of the chiller.

2 . The method of claim 1 , wherein the operational data is received from one or more sensors associated with a plurality of components of the chiller and wherein the plurality of components include: an evaporator, a compressor, and a condenser.

3 . The method of claim 2 , wherein the performing the energy balance check comprises identifying whether a first energy flow metric associated with the evaporator combined with a second energy flow metric associated with the compressor matches a third energy flow metric associated with the condenser.

4 . The method of claim 3 , wherein the selecting the reference chiller comprises:
determining, based on the energy balance check, whether an energy flow of the chiller is balanced or imbalanced; identifying, using the processor and responsive to determining that the energy flow of the chiller is imbalanced, the one or more other chillers in the chiller group for which the energy flow is balanced.

5 . The method of claim 4 , wherein the determining whether the energy flow of the chiller is balanced or imbalanced comprises:
determining that the energy flow is balanced responsive to identifying that the first energy flow metric combined with the second energy flow metric matches the third energy flow metric; and determining that the energy flow is imbalanced responsive to identifying that the first energy flow metric combined with the second energy flow metric does not match the third energy flow metric.

6 . The method of claim 1 , wherein using the machine learning model trained on energy flow of the selected reference chiller comprises:
training, using the reference operational data from the reference chiller, a machine learning model to identify energy flow metrics when the energy flow is balanced; receiving, upon applying the operational data of the chiller to the trained machine learning model, an output result from the trained machine learning model that identifies a balanced energy flow metric from the operational data; and performing, using the processor, a coefficient of performance (COP) determination for the chiller utilizing the balanced energy flow metric.

7 . The method of claim 6 , wherein the chiller group is operating under a conditional state and wherein the training the machine learning model comprises training the machine learning model to identify the energy flow metrics when the energy flow is balanced under the conditional state.

8 . The method of claim 6 , wherein the COP determination for the chiller utilizing the balanced energy flow metric deviates from another COP determination for the reference chiller by an expected amount.

9 . The method of claim 1 , wherein the controlling the equipment comprises managing a position of the chiller in a chiller schedule based on the determined efficiency.

10 . The method of claim 1 , wherein the controlling the equipment comprises transmitting a notification to a user that identifies a chiller component responsible for an imbalanced flow metric in the operational data.

11 . A computer system for controlling equipment based on assessing efficiency of a chiller, the computer system comprising:
a computer server; one or more computer processors; and a non-transitory computer-readable storage medium storing instructions executable by the one or more computer processors, the instructions when executed by the one or more computer processors causing the one or more computer processors to perform operations including: performing, using a processor of a computer system, an energy balance check on operational data of a chiller in a chiller group; selecting, using the processor and based on the energy balance check, a reference chiller from one or more other chillers in the chiller group, wherein an energy flow of the reference chiller has a best energy balance amongst the one or more other chillers; determining the efficiency of the chiller by using the processor to perform a coefficient of performance (COP) determination using a machine learning model trained on energy flow of the selected reference chiller; and controlling equipment including or impacted by the chiller based on the determined efficiency of the chiller.

12 . The computer system of claim 11 , wherein the operational data is received from one or more sensors associated with a plurality of components of the chiller and wherein the plurality of components include: an evaporator, a compressor, and a condenser.

13 . The computer system of claim 12 , wherein the performing the energy balance check comprises identifying whether a first energy flow metric associated with the evaporator combined with a second energy flow metric associated with the compressor matches a third energy flow metric associated with the condenser.

14 . The computer system of claim 13 , wherein the selecting the reference chiller comprises:
determining, based on the energy balance check, whether an energy flow of the chiller is balanced or imbalanced; identifying, using the processor and responsive to determining that the energy flow of the chiller is imbalanced, the one or more other chillers in the chiller group for which the energy flow is balanced.

15 . The computer system of claim 14 , wherein the determining whether the energy flow of the chiller is balanced or imbalanced comprises:
determining that the energy flow is balanced responsive to identifying that the first energy flow metric combined with the second energy flow metric matches the third energy flow metric; and determining that the energy flow is imbalanced responsive to identifying that the first energy flow metric combined with the second energy flow metric does not match the third energy flow metric.

16 . The computer system of claim 11 , wherein using the machine learning model trained on energy flow of the selected reference chiller comprises:
training, using the reference operational data from the reference chiller, a machine learning model to identify energy flow metrics when the energy flow is balanced; receiving, upon applying the operational data of the chiller to the trained machine learning model, an output result from the trained machine learning model that identifies a balanced energy flow metric from the operational data; and performing, using the processor, a coefficient of performance (COP) determination for the chiller utilizing the balanced energy flow metric.

17 . The computer system of claim 11 , wherein the chiller group is operating under a conditional state and wherein the training the machine learning model comprises training the machine learning model to identify the energy flow metrics when the energy flow is balan

Assignees

• Honeywell Int Inc

Inventors

• Schindler Zdenek
• Rojicek Jiri
• Malanik Jakub

Classifications

• G06N20/00

  Machine learning · CPC title

• F25B2339/047

  Water-cooled condensers · CPC title

• F25B25/005

  using primary and secondary systems · CPC title

• F25B2700/00

  Sensing or detecting of parameters; Sensors therefor · CPC title

• F25B2500/19

  Calculation of parameters · CPC title