US 7,680,751 B2 · Neural network based refrigerant charge detection algorithm for vapor compression systems

Abstract

Methods and apparatus are provided for determining refrigerant charge in a vapor compressor system (VCS) of an aircraft. The methods and apparatus comprise the following steps of, and/or means for, generating a data set from historical data representative of a plurality of VCS operating conditions over time, identifying one or more steady-state data points in the generated data set, forming a revised data set that includes at least the steady-state data points, using principal components analysis (PCA) to derive values for a plurality of minimally correlated input variables, supplying the derived values for the plurality of minimally correlated input variables and the corresponding values for the VCS refrigerant charge in the revised data set to a nonlinear neural network model, and deriving a simulator model characterizing a relationship between the plurality of minimally correlated input variables and the VCS refrigerant charge.

Drawings

Drawings are temporarily unavailable. Open the PDF at USPTO

Drawings

Claims17

Dependent claims

A method of developing a model for determining refrigerant charge in a vapor compressor system (VCS) of an aircraft, the method comprising the steps of:

(a) receiving, in a processor, a data set generated from historical data representative of a plurality of VCS operating conditions over time, the generated data set comprising a plurality of data points, each data point comprising:
(i) one or more values for a plurality of VCS operating variables reflecting operation of the VCS over a specific time period and corresponding to a specific set of operating conditions;
and
(ii) corresponding values for VCS refrigerant charge over the same time period;
and
(b) the processor processing the data to:
(i) identify one or more steady-state data points in the generated data set, each steady-state data point corresponding to steady-state operation of the VCS;
(ii) form a revised data set that includes at least the steady-state data points;
(iii) use principal components analysis (PCA) to derive values for a plurality of minimally correlated input variables from the values for the plurality of VCS operating variables in the revised data set;
(iv) supply the derived values for the plurality of minimally correlated input variables, and the corresponding values for the VCS refrigerant charge in the revised data set, to a nonlinear neural network model;
and
(v) derive a simulator model characterizing a relationship between the plurality of minimally correlated input variables and the VCS refrigerant charge using the nonlinear neural network model.

9 more elements

A method for developing a model for determining refrigerant charge in a vapor compressor system (VCS) of an aircraft, the method comprising the steps of:

(a) receiving, in a processor, a data set generated from historical data representative of a plurality of VCS operating conditions over time, the generated data set comprising a plurality of data points, each data point comprising:
(i) one or more values for a plurality of VCS operating variables reflecting operation of the VCS over a specific time period and corresponding to a specific set of operating conditions;
and
(ii) corresponding values for VCS refrigerant charge over the same time period;
and
(b) the processor processing the data to:
(i) identify one or more steady-state data points in the generated data set, each steady-state data point corresponding to steady-state operation of the VCS;
(ii) form a revised data set that includes at least the steady-state data points;
(iii) divide the steady-state data points according to particular ranges of VCS operating conditions, thereby creating a revised data subset for each range of VCS operating conditions;
(iv) calculate average values for the plurality of VCS operating variables for each data subset;
(v) supply the average values for the plurality of VCS operating variables to a nonlinear neural network model;
(vi) derive a simulator model characterizing a relationship between the plurality of VCS operating variables and the VCS refrigerant charge using the nonlinear neural network model;
(vii) use principal components analysis (PCA) to derive values for a plurality of minimally correlated input variables from the average values for the plurality of VCS operating variables in the revised data set;
and
(viii) supply the derived values for the plurality of minimally correlated input variables, and corresponding values for the VCS refrigerant charge in the revised data set, to a nonlinear neural network model.

12 more elements

Dependencies are inferred from the claim text.

Description6,720 words

Summary1,273 words

#The present invention generally relates to vapor compression systems for aircraft, and more particularly relates to a method and apparatus for determining refrigerant charge in a vapor compression system.

#Vapor compression systems (VCS) in aircraft are used to supply refrigerant cooled air, which is used primarily for cooling avionic systems. The VCS is generally a closed-loop system, and may include a ram-air cooled condenser, an evaporator with a draw through fan, a centrifugal compressor driven by an electric motor, and a flash subcooler heat exchanger to improve overall system efficiency.

#A low refrigerant charge level can result in decreased VCS system performance, particularly at higher heat loads. It may thus be appreciated that it is generally desirable to determine refrigerant charge level. However, the determination of refrigerant charge level can be difficult. This difficulty arises because the VCS operation is typically complex, with many interacting control loops. Generally the refrigerant charge level in the VCS is determined by indirect methods, such as inference from various system operating parameters. However, such methods to date have provided less than optimal results, for example due to a lack of a sufficient number of input variables, and/or due to substantial collinearity among input variables.

Brief description of the drawings13 figures

#The present invention will hereinafter be described in conjunction with the following drawing figures, wherein like numerals denote like elements, and

#FIG. 1 is a schematic representation of an embodiment of an exemplary vapor compression system (VCS) for aircraft from the prior art;

#FIG. 2 is a flowchart depicting an embodiment of a process for generating a simulator model for determining refrigerant charge level in a VCS, and for validating and using the simulator model in determining refrigerant charge level;

Detailed description5,079 words

#The following detailed description of the invention is merely exemplary in nature and is not intended to limit the invention or the application and uses of the invention. Furthermore, there is no intention to be bound by any theory presented in the preceding background of the invention or the following detailed description of the invention.

#FIG. 1 depicts an embodiment of a known vapor compression system (VCS) 10 for aircraft. The depicted VCS 10 has an evaporator 12, a compressor 14, a flash subcooler 16, a condenser 18, refrigerant lines 20, a surge valve 22, a thermal expansion valve 24, and a refrigerant expansion valve 26. The VCS 10 components are operated by a motor 28 and a controller 30.

#In conditions requiring maximum cooling, refrigerant enters the evaporator 12 as a low-temperature mixture of liquid and vapor, and flows through the evaporator 12. In this section of the VCS 10, which is generally referred to as the low-pressure side, the pressure remains essentially constant. While in the evaporator 12, the liquid portion of the refrigerant evaporates as it absorbs heat from return air. The refrigerant exits the evaporator 12 as a superheated vapor, and then flows to the compressor 14. Flow of the superheated vapor is regulated by the surge valve 22, in order to prevent a surge with the compressor 14.

Facts

Application

11/444,092Filed 31 May 2006

Published

US 2007/0277537 A16 Dec 2007

Granted

16 Mar 2010

Term ends

2 Jan 2029

Estimated · how

20 years from earliest known nonprovisional domestic filing plus recorded patent term adjustment, including 947 days of adjustment. Maintenance-fee lapses, terminal disclaimers and statutory extensions have not been checked. The continuity chain may be incomplete; this is not an enforceability determination.

Classification11 codes

F25B 49/005
Arrangement or mounting of control or safety devices: of safety devices
B64D 13/06
Arrangements or adaptations of air-treatment apparatus for aircraft crew or passengers, or freight space: the air being conditioned
B64D 2013/0614
Environmental Control Systems: with subsystems for cooling avionics
B64D 2013/0644
Environmental Control Systems: including electric motors or generators

Timeline

31 May 2006Application filedUS 11/444,092
31 May 2006Assigned to Honeywell International, Inc.assignment of assignor's interest
6 Dec 2007PublishedUS 2007/0277537 A1
16 Mar 2010GrantedUS 7,680,751 B2
12 Oct 2026TodayWithin its term
2 Jan 2029Term endsEstimated, includes 947 days of adjustment

Neural network based refrigerant charge detection algorithm for vapor compression systems

Life of this patent

Neural network based refrigerant charge detection algorithm for vapor compression systems

Life of this patent

Life of this patent

Abstract

Drawings

Drawings

Claims17

Description6,720 words

Drawings

Description6,720 words

Classification11 codes

Life of this patent