CN112413812A - Refrigerant leakage detection method and system and air conditioner - Google Patents

Refrigerant leakage detection method and system and air conditioner Download PDF

Info

Publication number
CN112413812A
CN112413812A CN202011381821.6A CN202011381821A CN112413812A CN 112413812 A CN112413812 A CN 112413812A CN 202011381821 A CN202011381821 A CN 202011381821A CN 112413812 A CN112413812 A CN 112413812A
Authority
CN
China
Prior art keywords
air conditioner
standard
judgment result
refrigerant
neural network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202011381821.6A
Other languages
Chinese (zh)
Other versions
CN112413812B (en
Inventor
王彬
李勋章
王炳忠
胡新生
张涛
范红军
谈秋宏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qingdao Campus of Naval Aviation University of PLA
Original Assignee
Qingdao Campus of Naval Aviation University of PLA
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Qingdao Campus of Naval Aviation University of PLA filed Critical Qingdao Campus of Naval Aviation University of PLA
Priority to CN202011381821.6A priority Critical patent/CN112413812B/en
Publication of CN112413812A publication Critical patent/CN112413812A/en
Application granted granted Critical
Publication of CN112413812B publication Critical patent/CN112413812B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
    • F24F11/32—Responding to malfunctions or emergencies
    • F24F11/36—Responding to malfunctions or emergencies to leakage of heat-exchange fluid
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
    • F24F11/63—Electronic processing
    • F24F11/64—Electronic processing using pre-stored data
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/70—Control systems characterised by their outputs; Constructional details thereof
    • F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
    • F24F11/83—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling the supply of heat-exchange fluids to heat-exchangers
    • F24F11/84—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling the supply of heat-exchange fluids to heat-exchangers using valves
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/70—Control systems characterised by their outputs; Constructional details thereof
    • F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
    • F24F11/86—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling compressors within refrigeration or heat pump circuits
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/70—Control systems characterised by their outputs; Constructional details thereof
    • F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
    • F24F11/87—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling absorption or discharge of heat in outdoor units
    • F24F11/871—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling absorption or discharge of heat in outdoor units by controlling outdoor fans
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2140/00—Control inputs relating to system states
    • F24F2140/10—Pressure
    • F24F2140/12—Heat-exchange fluid pressure

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Thermal Sciences (AREA)
  • Signal Processing (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

The invention discloses a refrigerant leakage detection method, a refrigerant leakage detection system and an air conditioner, wherein the refrigerant leakage detection method comprises the following steps: standard pressure parameter obtaining step: outputting a standard pressure parameter through a neural network model according to a working condition information parameter when the air conditioner operates; a detection step: detecting and obtaining actual measurement pressure parameters in real time when the air conditioner operates; a judging step: obtaining a judgment result of whether the refrigerant leaks or not according to the standard pressure parameter and the actual measurement pressure parameter; and a processing step of processing the air conditioner according to the judgment result. The invention provides a more accurate judgment result aiming at the problem of refrigerant leakage so as to facilitate subsequent processing.

Description

Refrigerant leakage detection method and system and air conditioner
Technical Field
The present invention relates to a refrigerant leakage detection method, a refrigerant leakage detection system, and an air conditioner, and more particularly, to a refrigerant leakage detection method, a refrigerant leakage detection system, and an air conditioner based on a neural network.
Background
During the long-term use of the air conditioner, refrigerant leakage may occur due to poor sealing performance, corrosion of pipelines and other ineffectiveness reasons. If the refrigerant leaks, the performance of the air conditioner is deteriorated. The user typically only perceives that maintenance is taking place when the performance of the air conditioner becomes extremely poor. Therefore, an accurate and punctual refrigerant leakage detection method is necessary, and when the refrigerant leaks, the air conditioner automatically prompts the user of the refrigerant leakage.
In recent years, many people have proposed the following methods for detecting the refrigerant:
in chinese patent application No. 201811108477.6, a refrigerant detection and determination method is proposed, which compares the refrigerant pressure with a refrigerant pressure threshold, wherein the refrigerant pressure threshold is obtained according to a refrigerant pressure threshold curve. The method has the disadvantages that the refrigerant pressure threshold value curve is easy to obtain under a specific working condition and is not suitable for the full working condition of air conditioner operation, so that the refrigerant pressure threshold value is adopted to have larger error.
For example, in the chinese patent application No. 201910702473.9, a method for detecting and determining a refrigerant is proposed, which mainly performs a comparison determination between a compressor return air pressure and a compressor return air pressure set value. The set value of the return air pressure is obtained according to an empirical formula through an indoor temperature value and an outdoor temperature value. In the method, the set value of the return air pressure is judged only by the indoor temperature and the outdoor temperature, and the error is large. The set value of the return air pressure is related to not only the indoor temperature and the outdoor temperature, but also the set temperature, the air volume and the like.
The refrigerant leakage detection has a difficulty in that, regardless of which parameter is used for the determination of refrigerant leakage, the basic idea is to determine whether the detected value of the parameter deviates from the normal range of the parameter, and determine refrigerant leakage when the detected value deviates from the normal range. The air conditioner is operated under multiple working conditions, and for any working condition, the normal value of the parameter is in what normal range, so that the judgment is relatively difficult, while the existing detection method is inaccurate, and the misjudgment condition of refrigerant leakage is easy to occur.
Therefore, it is urgently needed to develop a refrigerant leakage detection method, a refrigerant leakage detection system and an air conditioner based on a neural network, which overcome the above defects.
Disclosure of Invention
In view of the above problems, the present invention provides a refrigerant leakage detection method, which includes:
standard pressure parameter obtaining step: outputting a standard pressure parameter through a neural network model according to a working condition information parameter when the air conditioner operates;
a detection step: detecting and obtaining actual measurement pressure parameters in real time when the air conditioner operates;
a judging step: obtaining a judgment result of whether the refrigerant leaks or not according to the standard pressure parameter and the actual measurement pressure parameter;
and a processing step of processing the air conditioner according to the judgment result.
In the above refrigerant leakage detection method, the step of obtaining the standard pressure parameter includes:
test data input step: taking working condition information parameters under different working conditions as training samples, and dividing the training samples into a training set and a verification set;
model training: training the neural network model through the working condition information parameters of the training set;
a model verification step: verifying the neural network model through the working condition information parameters of the verification set;
A model embedding step: embedding the verified neural network model into a control unit of the air conditioner.
In the above refrigerant leakage detection method, the standard pressure parameter includes a standard condensation pressure value and/or a standard evaporation pressure value, and the actual measurement pressure parameter includes an actual measurement condensation pressure value and/or an actual measurement evaporation pressure value.
In the above refrigerant leakage detection method, the determining step includes:
when (P)k-P′k)/PkNot less than 15% or (P)0-P′0)/P0When the refrigerant leakage rate is more than or equal to 20 percent, outputting a first judgment result that the refrigerant leaks and the leakage grade is one grade;
when (P)k-P′k)/PkNot less than 10 percent and (P)0-P′0)/P0Not less than 15%, outputting a second judgment result of refrigerant leakage with a secondary leakage grade;
when (P)k-P′k)/PkNot less than 10% or (P)0-P′0)/P0When the heat degree is less than or equal to 15%, further judging the heat degree, and when the heat degree is more than or equal to a threshold value, outputting a third judgment result that the refrigerant leaks and the leakage grade is three-grade;
wherein, PkIs a standard value of the condensation pressure, P0Is a standard evaporation pressure value, P'kIs an actually measured condensation pressure value, P'0The measured evaporation pressure value is obtained.
In the above refrigerant leakage detection method, in the processing step, the compressor of the air conditioner is controlled to stop according to the first determination result and the second determination result, and the opening of the electronic expansion valve of the air conditioner is controlled to increase and/or the rotation speed of the external fan of the air conditioner is controlled to increase according to the third determination result.
The method for detecting refrigerant leakage further comprises a display step of displaying and outputting the judgment result.
The invention also provides a refrigerant leakage detection system, which comprises:
the standard pressure parameter obtaining unit is used for outputting standard pressure parameters through a neural network model according to working condition information parameters of the air conditioner during operation;
the detection unit detects and obtains actual measurement pressure parameters in real time when the air conditioner operates;
the control unit is used for obtaining a judgment result of whether the refrigerant leaks according to the standard pressure parameter and the actual measurement pressure parameter, and processing the air conditioner according to the judgment result;
and the display unit displays and outputs the judgment result.
The refrigerant leakage detecting system further includes a neural network model obtaining unit, including:
the test data input module takes working condition information parameters under different working conditions as training samples, and divides the training samples into a training set and a verification set;
the model training module is used for training the neural network model through the working condition information parameters of the training set;
the model verification module is used for verifying the neural network model through the working condition information parameters of the verification set;
And the model embedding module is used for embedding the verified neural network model into a control unit of the air conditioner.
In the above refrigerant leakage detecting system, the standard pressure parameter includes a standard condensing pressure value and/or a standard evaporating pressure value, the actual measurement pressure parameter includes an actual measurement condensing pressure value and/or an actual measurement evaporating pressure value,
wherein when (P)k-P′k)/PkNot less than 15% or (P)0-P′0)/P0When the refrigerant leakage rate is more than or equal to 20 percent, the control unit outputs a first judgment result that the refrigerant leaks and the leakage grade is first grade;
when (P)k-P′k)/PkNot less than 10 percent and (P)0-P′0)/P0The control unit outputs a second judgment result that the refrigerant leaks and the leakage grade is two-stage;
when (P)k-P′k)/PkNot less than 10% or (P)0-P′0)/P0When the heat degree is less than or equal to 15%, the control unit further judges the heat degree, and when the heat degree is greater than or equal to a threshold value, the control unit outputs a third judgment result that the refrigerant leaks and the leakage grade is three-grade;
wherein, PkIs a standard value of the condensation pressure, P0Is a standard evaporation pressure value, P'kIs an actually measured condensation pressure value, P'0In order to measure the evaporation pressure value actually,
the control unit controls the compressor of the air conditioner to stop according to the first judgment result and the second judgment result, and the control unit controls the opening of the electronic expansion valve of the air conditioner to be increased and/or the rotating speed of the external fan of the air conditioner to be increased according to the third judgment result.
The present invention also provides an air conditioner, comprising:
a compressor;
an outer fan;
an electronic expansion valve;
the refrigerant leakage detection system according to any one of the above.
In summary, compared with the prior art, the invention has the following effects: the invention utilizes the predictability of the neural network to accurately calculate the condensation pressure value and the evaporation pressure value under different working conditions, thereby solving the difficult point that the normal value range of the parameters under different working conditions is determined inaccurately; and by judging the deviation degree according to two parameters of the condensation pressure value and the evaporation pressure value, whether leakage exists or not and the leakage level are judged, so that a more accurate judgment result is provided, and the subsequent treatment is facilitated.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of a refrigerant leakage detection method according to the present invention;
FIG. 2 is a flowchart illustrating the substeps of step S1 in FIG. 1;
FIG. 3 is a flow chart illustrating an application of the refrigerant leakage detection method of the present invention;
FIG. 4 is a schematic structural diagram of a refrigerant leakage detection system according to the present invention;
fig. 5 is a schematic structural diagram of an air conditioner.
Wherein the reference numerals are:
a standard pressure parameter obtaining unit: 11;
a detection unit: 12;
a control unit: 13;
a display unit: 14;
a neural network model obtaining unit: 15
A test data input module: 151, and (b);
a model training module: 152;
a model verification module: 153;
a model embedding module: 154.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The exemplary embodiments and descriptions of the present invention are provided to explain the present invention and not to limit the present invention. Additionally, the same or similar numbered elements/components used in the drawings and the embodiments are used to represent the same or similar parts.
As used herein, the terms "first", "second", "S1", "S2", …, etc. do not particularly denote an order or sequential meaning, nor are they intended to limit the present invention, but merely distinguish between elements or operations described in the same technical terms.
With respect to directional terminology used herein, for example: up, down, left, right, front or rear, etc., are simply directions with reference to the drawings. Accordingly, the directional terminology used is intended to be illustrative and is not intended to be limiting of the present teachings.
As used herein, the terms "comprising," "including," "having," "containing," and the like are open-ended terms that mean including, but not limited to.
As used herein, "and/or" includes any and all combinations of the described items.
References to "plurality" herein include "two" and "more than two"; reference to "sets" herein includes "two sets" and "more than two sets".
As used herein, the terms "substantially", "about" and the like are used to modify any slight variation in quantity or error that does not alter the nature of the variation. Generally, the range of slight variations or errors modified by such terms may be 20% in some embodiments, 10% in some embodiments, 5% in some embodiments, or other values. It should be understood by those skilled in the art that the aforementioned values can be adjusted according to actual needs, and are not limited thereto.
Certain words used to describe the present application are discussed below or elsewhere in this specification to provide additional guidance to those skilled in the art in describing the present application.
The neural network is a technology for simulating the structure and function of human cranial nerves by using an engineering technology, and a technology for simulating the activity processes of information processing, storage, search and the like of the human cranial nerves by using an electronic computer. The artificial neural network is a computational model formed by extracting and simulating the biological neural network based on the structure and the basic principle of the biological neural network. Among them, the most applied and relatively mature artificial neural network is the BP neural network.
The BP neural network is a multilayer feedforward neural network, and the main characteristic of the neural network is that signals are transmitted from front to back, and errors are transmitted from back to front. The input signal passes from the input layer from front to back, the hidden layer processes the signal and passes to the next hidden layer until passing to the output layer. During transmission, the neuron state of the next layer is only affected by the neuron state of the previous layer. And judging the signal output by the output layer, if the error between the output signal and the expected value cannot reach the set error, transferring the error into reverse propagation, adjusting the network weight and the threshold according to error prediction, and performing next calculation until the error between the predicted output of the BP neural network and the actual value reaches the expected error.
The invention provides a refrigerant leakage detection method. By training the neural network model, the standard condensing pressure and evaporating pressure under the working condition are calculated based on the input working condition information parameters, and then compared with the detected condensing pressure and evaporating pressure to judge whether the refrigerant leaks, which is described in detail below.
Referring to fig. 1, fig. 1 is a flow chart of a refrigerant leakage detection method according to the present invention. As shown in fig. 1, the refrigerant leakage detection method of the present invention includes:
Standard pressure parameter obtaining step S1: outputting a standard pressure parameter through a neural network model according to a working condition information parameter when the air conditioner operates;
detection step S2: detecting and obtaining actual measurement pressure parameters in real time when the air conditioner operates;
determination step S3: obtaining a judgment result whether the refrigerant leaks or not according to the standard pressure parameter and the actual measurement pressure parameter;
a processing step S4, processing the air conditioner according to the judgment result;
and a display step S5, displaying and outputting the judgment result.
The invention aims to accurately calculate the standard pressure parameters of different working conditions by utilizing the predictability of the neural network, solve the problem of inaccurate determination of the normal value ranges of the parameters under different working conditions, judge whether to leak or not and judge the leakage level by judging the deviation degree according to the actually measured pressure parameters, and further improve the accuracy of the judgment result.
Further, referring to fig. 2, fig. 2 is a flowchart illustrating a substep of S1. As shown in fig. 2, the standard pressure parameter obtaining step S1 includes:
test data input step S11: taking working condition information parameters under different working conditions as training samples, and dividing the training samples into a training set and a verification set;
Model training step S12: training the neural network model according to the working condition information parameters of the training set;
model verification step S13: verifying the neural network model through the working condition information parameters of the verification set;
model embedding step S14: embedding the verified neural network model into a control unit of the air conditioner.
The standard pressure parameters comprise standard condensation pressure values and/or standard evaporation pressure values, and the actually measured pressure parameters comprise actually measured condensation pressure values and/or actually measured evaporation pressure values.
Specifically, when the air conditioner is in normal refrigerant quantity, the condensation pressure value and the evaporation pressure value are tested under different working conditions. The air conditioner is characterized in that different outdoor temperatures, outdoor humidity, indoor temperatures, indoor humidity, set temperatures and set air volume are used as a working condition. Then, test data under different working conditions are used as training samples, outdoor temperature, outdoor humidity, indoor temperature, indoor humidity, set temperature and set air volume are used as input quantities, condensing pressure and evaporating pressure are used as output quantities, one part of the samples are selected to be used for training the neural network model, and the rest part of the samples are used for verifying the accuracy of the neural network model. Then, the trained neural network model is embedded into the control And (4) units. In the actual operation process of the air conditioner, after the compressor operates for a certain time, the working condition parameters are detected and input into the neural network model as input quantity, and the neural network model calculates the standard condensation pressure value P under the working condition according to the input quantitykAnd a standard evaporation pressure value P0。
Still further, the determining step S3 includes:
when (P)k-P′k)/PkNot less than 15% or (P)0-P′0)/P0When the refrigerant leakage rate is more than or equal to 20 percent, outputting a first judgment result that the refrigerant leaks and the leakage grade is one grade;
when (P)k-P′k)/PkNot less than 10 percent and (P)0-P′0)/P0Not less than 15%, outputting a second judgment result of refrigerant leakage with a secondary leakage grade;
when (P)k-P′k)/PkNot less than 10% or (P)0-P′0)/P0When the heat degree is less than or equal to 15%, further judging the heat degree, and when the heat degree is more than or equal to a threshold value, outputting a third judgment result that the refrigerant leaks and the leakage grade is three-grade;
wherein, PkIs a standard value of the condensation pressure, P0Is a standard evaporation pressure value, P'kIs an actually measured condensation pressure value, P'0The measured evaporation pressure value is obtained.
Further, in the processing step S4, the stop of the compressor of the air conditioner is controlled according to the first determination result and the second determination result, and the increase of the opening degree of the electronic expansion valve of the air conditioner and/or the increase of the rotation speed of the external fan of the air conditioner is controlled according to the third determination result.
Specifically, the actually measured condensation pressure value P 'obtained by detection'kAnd an actually measured evaporation pressure value P'0Making a comparison when (P)k-P′k)/PkNot less than 15% or (P)0-P′0)/P0And when the refrigerant leakage rate is more than or equal to 20%, judging that the refrigerant is certainly leaked, and controlling the compressor to be protected and shut down at the moment, wherein the leakage level is a first judgment result A of one stage. When the condition is not satisfied, judging whether the condition is satisfied(Pk-P′k)/PkNot less than 10 percent and (P)0-P′0)/P0And if the refrigerant leakage is more than or equal to 15 percent, judging a second judgment result B with a second grade, and controlling the compressor to stop in a protection mode. When the condition is not satisfied, it is judged whether or not (P) is satisfiedk-P′k)/PkNot less than 10% or (P)0-P′0)/P0And when the superheat degree lambda is less than or equal to 15%, refrigerant leakage may exist, at the moment, whether the superheat degree lambda is more than or equal to 5 is further judged, if yes, the refrigerant leakage is judged, and the leakage grade is a third judgment result C with three levels. Because the leakage quantity is less this moment, control electron expansion valve aperture and increase, control outer fan rotational speed and increase, reduce the superheat degree, reduce exhaust temperature, the reinforcing heat transfer improves air conditioner performance, otherwise the refrigerant leakage does not take place. The superheat is the return air temperature minus the inner disk temperature of the compressor. When the reduction percentage of the condensing pressure and the evaporating pressure is small, the refrigerant may leak, when the refrigerant leaks, the superheat degree may increase, and when the superheat degree is greater than 5, the refrigerant is determined to leak. In the leakage classification A, B, C, the degree of leakage A > B > C.
The invention aims to accurately calculate the standard condensation pressure values and the standard evaporation pressure values under different working conditions by utilizing the predictability of the neural network, solve the problem of inaccurate difficult point determination of the normal value range of the parameters under different working conditions, judge whether leakage exists or not and judge the leakage level by judging the deviation degree according to two parameters of the actually-measured condensation pressure value and the actually-measured evaporation pressure value, and further improve the accuracy of the judgment result.
Referring to fig. 3, fig. 3 is a flow chart illustrating an application of the refrigerant leakage detection method of the present invention. The refrigerant leakage detection method of the present invention is described as follows with reference to fig. 3.
In a laboratory, the outdoor temperature is from 20 ℃ to 53 ℃, test points are arranged at intervals of 6 ℃, and 7 test points are taken in total; taking a test point every 40% from 10% -100% of outdoor relative humidity, and taking 3 test points in total; the outdoor working condition comprises 21 test points consisting of outdoor temperature and outdoor relative humidity. In a similar way, the indoor temperature is from 19 ℃ to 46 ℃, each test point is at an interval of 6 ℃, and 6 test points are taken in total; taking a test point every 40% from 10% -100% of indoor relative humidity, and taking 3 test points in total; the indoor working condition comprises 18 test points of indoor temperature and indoor relative humidity. In addition, the temperature is set to be 16-30 ℃, one point is taken every 4 ℃, 5 points are used totally, the wind speed is set to be 300m3/h-900m3/h, one test point is taken every 300m3/h, and 3 test points are taken totally.
The indoor working condition, the outdoor working condition and the air volume form an actual operating working condition of the air conditioner, 21 operating points 18 operating points 3 operating points 5 operating points 5670 operating points are counted, the condensation pressure and the evaporation pressure of the operating points are respectively tested, the working condition parameters, the condensation pressure and the evaporation pressure under each operating condition are used as sample points, and 5670 sample points are counted.
4000 sample points are selected as a training set, and 1670 sample points are selected as a verification set. Training the neural network model through a training set, and then verifying whether the trained neural network model is accurate through a verification set sample point. And after the verification is accurate and reliable, embedding the model into a control unit. The above work is completed in a laboratory as a development stage. The user use phase is as follows.
When a user uses the air conditioner, the air conditioner acquires outdoor temperature, outdoor humidity, indoor temperature, indoor humidity, set temperature and set air volume as actual working condition parameters, inputs the actual working condition parameters into a neural network model of the control unit, and acquires standard pressure parameters. For example, when the user is at 35 ℃ outdoors, 50% outdoor relative humidity, 27% indoor temperature and 50% indoor relative humidity, the temperature is set to be 20 ℃, the air conditioner is turned on, the air volume is 800m 3/h: and then inputting the 6 parameters into a neural network model, wherein the neural network model gives standard working condition parameters according to the input parameters, the standard condensing pressure is 1.85MPa, the standard evaporating pressure is 0.9MPa, the actually measured condensing pressure is 1.5MPa, the evaporating pressure is 0.65MPa, then the (1.85-1.5)/1.85 × 100% is 18.9%, and the (0.9-0.65)/0.9 × 100% is 27.8%, and when the condition A is met, the control unit prompts that the refrigerant leaks, and the air-conditioning compressor is protected to stop.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a refrigerant leakage detection system according to the present invention. As shown in fig. 4, the refrigerant leakage detecting system of the present invention includes:
the standard pressure parameter obtaining unit 11 outputs a standard pressure parameter through the neural network model according to a working condition information parameter when the air conditioner operates;
the detection unit 12 is used for detecting and obtaining actual measurement pressure parameters in real time when the air conditioner runs;
the control unit 13 is used for obtaining a judgment result of whether the refrigerant leaks or not according to the standard pressure parameter and the actual measurement pressure parameter, and the control unit is also used for processing the air conditioner according to the judgment result;
and a display unit 14 for displaying and outputting the judgment result.
Further, the refrigerant leakage detecting system further includes a neural network model obtaining unit 15 including:
the test data input module 151 takes working condition information parameters under different working conditions as training samples, and divides the training samples into a training set and a verification set;
a model training module 152, which trains the neural network model according to the working condition information parameters of the training set;
the model verification module 153 is used for verifying the neural network model through the working condition information parameters of the verification set;
A model embedding module 154 embedding the neural network model that passes the verification into a control unit of the air conditioner.
It should be noted that, in this embodiment, the neural network model obtaining unit 15 is externally disposed and is independent from the refrigerant leakage detecting system, that is, when the refrigerant leakage detecting system is disposed in the air conditioner, the neural network model obtaining unit may be disposed on a host computer in a laboratory, and the neural network model obtaining unit 15 obtains the verified neural network model and embeds the verified neural network model into the control unit 13, but the present invention is not limited thereto, and in other embodiments, the neural network model obtaining unit 15 may also be disposed on the air conditioner.
Wherein the standard pressure parameter comprises a standard condensation pressure value and/or a standard evaporation pressure value, the actually measured pressure parameter comprises an actually measured condensation pressure value and/or an actually measured evaporation pressure value,
wherein when (P)k-P′k)/PkNot less than 15% or (P)0-P′0)/P0When the refrigerant leakage rate is more than or equal to 20 percent, the control unit outputs a first judgment result that the refrigerant leaks and the leakage grade is first grade;
when (P)k-P′k)/PkNot less than 10 percent and (P)0-P′0)/P0The control unit outputs a second judgment result that the refrigerant leaks and the leakage grade is two-stage;
When (P)k-P′k)/PkNot less than 10% or (P)0-P′0)/P0When the heat degree is less than or equal to 15%, the control unit further judges the heat degree, and when the heat degree is greater than or equal to a threshold value, the control unit outputs a third judgment result that the refrigerant leaks and the leakage grade is three-grade;
wherein, PkIs a standard value of the condensation pressure, P0Is a standard evaporation pressure value, P'kIs an actually measured condensation pressure value, P'0In order to measure the evaporation pressure value actually,
the control unit 13 controls the compressor of the air conditioner to stop according to the first determination result and the second determination result, and the control unit 13 controls the opening of the electronic expansion valve of the air conditioner to increase and/or the rotation speed of the external fan of the air conditioner to increase according to the third determination result.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an air conditioner. As shown in fig. 5, the air conditioner of the present invention includes: the refrigerant leakage detection system comprises a compressor, an external fan, an electronic expansion valve and any one of the above components, and controls the compressor, the external fan and the electronic expansion valve to perform corresponding actions according to a judgment result of whether the refrigerant leaks or not, wherein the judgment result is obtained by the refrigerant leakage detection system.
In conclusion, the invention utilizes the predictability of the neural network to accurately calculate the condensation pressure value and the evaporation pressure value under different working conditions, thereby solving the difficulty that the normal value range of the parameters under different working conditions is inaccurately determined; and whether leakage and leakage level are judged by judging the deviation degree according to two parameters of the condensation pressure value and the evaporation pressure value, so that a more accurate judgment result is provided for subsequent processing.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A refrigerant leakage detection method is characterized by comprising the following steps:
standard pressure parameter obtaining step: outputting a standard pressure parameter through a neural network model according to a working condition information parameter when the air conditioner operates;
a detection step: detecting and obtaining actual measurement pressure parameters in real time when the air conditioner operates;
a judging step: obtaining a judgment result of whether the refrigerant leaks or not according to the standard pressure parameter and the actual measurement pressure parameter;
and a processing step of processing the air conditioner according to the judgment result.
2. The refrigerant leakage detection method as claimed in claim 1, wherein the standard pressure parameter obtaining step includes:
test data input step: taking working condition information parameters under different working conditions as training samples, and dividing the training samples into a training set and a verification set;
Model training: training the neural network model through the working condition information parameters of the training set;
a model verification step: verifying the neural network model through the working condition information parameters of the verification set;
a model embedding step: embedding the verified neural network model into a control unit of the air conditioner.
3. The refrigerant leakage detection method as claimed in claim 1, wherein the standard pressure parameter includes a standard condensing pressure value and/or a standard evaporating pressure value, and the measured pressure parameter includes a measured condensing pressure value and/or a measured evaporating pressure value.
4. The refrigerant leakage detection method according to claim 3, wherein the determining step includes:
when (P)k-P′k)/PkNot less than 15% or (P)0-P′0)/P0When the refrigerant leakage rate is more than or equal to 20 percent, outputting a first judgment result that the refrigerant leaks and the leakage grade is first grade;
when (P)k-P′k)/PkNot less than 10 percent and (P)0-P′0)/P0Not less than 15%, outputting a second judgment result of refrigerant leakage with a secondary leakage grade;
when (P)k-P′k)/PkNot less than 10% or (P)0-P′0)/P0When the heat degree is less than or equal to 15%, further judging the heat degree, and when the heat degree is more than or equal to a threshold value, outputting a third judgment result that the refrigerant leaks and the leakage grade is three-grade;
wherein, PkIs a standard value of the condensation pressure, P 0Is a standard evaporation pressure value, P'kIs actually measured condensation pressure value, P'0The measured evaporation pressure value is obtained.
5. The refrigerant leakage detection method according to claim 4, wherein in the processing step, a compressor of the air conditioner is controlled to be stopped according to the first determination result and the second determination result, and an opening degree of an electronic expansion valve of the air conditioner is controlled to be increased and/or a rotation speed of an external fan of the air conditioner is controlled to be increased according to the third determination result.
6. The refrigerant leakage detection method according to claim 1, further comprising a display step of displaying and outputting the determination result.
7. A refrigerant leak detection system, comprising:
the standard pressure parameter obtaining unit is used for outputting standard pressure parameters through a neural network model according to working condition information parameters of the air conditioner during operation;
the detection unit detects and obtains actual measurement pressure parameters in real time when the air conditioner operates;
the control unit is used for obtaining a judgment result of whether the refrigerant leaks according to the standard pressure parameter and the actual measurement pressure parameter, and processing the air conditioner according to the judgment result;
and the display unit displays and outputs the judgment result.
8. The refrigerant leak detection system as claimed in claim 7, further comprising a neural network model obtaining unit comprising:
the test data input module takes working condition information parameters under different working conditions as training samples, and divides the training samples into a training set and a verification set;
the model training module is used for training the neural network model through the working condition information parameters of the training set;
the model verification module is used for verifying the neural network model through the working condition information parameters of the verification set;
and the model embedding module is used for embedding the verified neural network model into a control unit of the air conditioner.
9. The refrigerant leakage detection system according to claim 7, wherein the standard pressure parameter includes a standard condensing pressure value and/or a standard evaporating pressure value, the measured pressure parameter includes a measured condensing pressure value and/or a measured evaporating pressure value,
wherein when (P)k-P′k)/PkNot less than 15% or (P)0-P′0)/P0When the content is more than or equal to 20 percent, the control unitOutputting a first judgment result of refrigerant leakage with a first-grade leakage grade;
when (P)k-P′k)/PkNot less than 10 percent and (P)0-P′0)/P0The control unit outputs a second judgment result that the refrigerant leaks and the leakage grade is two-stage;
When (P)k-P′k)/PkNot less than 10% or (P)0-P′0)/P0When the heat degree is less than or equal to 15%, the control unit further judges the heat degree, and when the heat degree is greater than or equal to a threshold value, the control unit outputs a third judgment result that the refrigerant leaks and the leakage grade is three-grade;
wherein, PkIs a standard value of the condensation pressure, P0Is a standard evaporation pressure value, P'kIs actually measured condensation pressure value, P'0In order to measure the evaporation pressure value actually,
the control unit controls the compressor of the air conditioner to stop according to the first judgment result and the second judgment result, and the control unit controls the opening of the electronic expansion valve of the air conditioner to be increased and/or the rotating speed of the external fan of the air conditioner to be increased according to the third judgment result.
10. An air conditioner, comprising:
a compressor;
an outer fan;
an electronic expansion valve;
the refrigerant leak detection system according to any one of claims 7 to 9.
CN202011381821.6A 2020-12-01 2020-12-01 Refrigerant leakage detection method and system and air conditioner Active CN112413812B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011381821.6A CN112413812B (en) 2020-12-01 2020-12-01 Refrigerant leakage detection method and system and air conditioner

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011381821.6A CN112413812B (en) 2020-12-01 2020-12-01 Refrigerant leakage detection method and system and air conditioner

Publications (2)

Publication Number Publication Date
CN112413812A true CN112413812A (en) 2021-02-26
CN112413812B CN112413812B (en) 2021-11-05

Family

ID=74830746

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011381821.6A Active CN112413812B (en) 2020-12-01 2020-12-01 Refrigerant leakage detection method and system and air conditioner

Country Status (1)

Country Link
CN (1) CN112413812B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113654182A (en) * 2021-08-30 2021-11-16 海信（广东）空调有限公司 Method for detecting refrigerant leakage, computer readable storage medium and air conditioner
CN113669839A (en) * 2021-08-30 2021-11-19 海信（广东）空调有限公司 Method for detecting refrigerant leakage, computer readable storage medium and air conditioner
CN115200159A (en) * 2022-07-12 2022-10-18 珠海格力电器股份有限公司 Method, system and equipment for detecting fluorine deficiency of air conditioner
WO2023106890A1 (en) * 2021-12-10 2023-06-15 삼성전자주식회사 Electronic apparatus and control method thereof

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104596172A (en) * 2010-03-12 2015-05-06 三菱电机株式会社 Refrigeration air conditioning device
CN106705384A (en) * 2017-02-09 2017-05-24 美的集团股份有限公司 Refrigerant leakage reminding method and device and air conditioner
CN108981073A (en) * 2018-07-09 2018-12-11 珠海格力电器股份有限公司 Unit control method, control device and control system
CN110059801A (en) * 2019-03-20 2019-07-26 青岛海尔空调器有限总公司 Energy efficiency of air conditioner control method neural network based
CN110878985A (en) * 2018-09-06 2020-03-13 奥克斯空调股份有限公司 Method and device for detecting refrigerant leakage of air conditioner
CN110895022A (en) * 2018-09-12 2020-03-20 奥克斯空调股份有限公司 Method and device for detecting refrigerant leakage of air conditioner

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104596172A (en) * 2010-03-12 2015-05-06 三菱电机株式会社 Refrigeration air conditioning device
CN106705384A (en) * 2017-02-09 2017-05-24 美的集团股份有限公司 Refrigerant leakage reminding method and device and air conditioner
CN108981073A (en) * 2018-07-09 2018-12-11 珠海格力电器股份有限公司 Unit control method, control device and control system
CN110878985A (en) * 2018-09-06 2020-03-13 奥克斯空调股份有限公司 Method and device for detecting refrigerant leakage of air conditioner
CN110895022A (en) * 2018-09-12 2020-03-20 奥克斯空调股份有限公司 Method and device for detecting refrigerant leakage of air conditioner
CN110059801A (en) * 2019-03-20 2019-07-26 青岛海尔空调器有限总公司 Energy efficiency of air conditioner control method neural network based

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113654182A (en) * 2021-08-30 2021-11-16 海信（广东）空调有限公司 Method for detecting refrigerant leakage, computer readable storage medium and air conditioner
CN113669839A (en) * 2021-08-30 2021-11-19 海信（广东）空调有限公司 Method for detecting refrigerant leakage, computer readable storage medium and air conditioner
CN113669839B (en) * 2021-08-30 2022-11-25 海信（广东）空调有限公司 Method for detecting refrigerant leakage, computer readable storage medium and air conditioner
WO2023106890A1 (en) * 2021-12-10 2023-06-15 삼성전자주식회사 Electronic apparatus and control method thereof
CN115200159A (en) * 2022-07-12 2022-10-18 珠海格力电器股份有限公司 Method, system and equipment for detecting fluorine deficiency of air conditioner

Also Published As

Publication number Publication date
CN112413812B (en) 2021-11-05

Similar Documents

Publication Publication Date Title
CN112413812B (en) Refrigerant leakage detection method and system and air conditioner
US7444251B2 (en) Detecting and diagnosing faults in HVAC equipment
JP3165676B2 (en) How to monitor refrigerant charge
CN106642584B (en) Air conditioner operation control method and device
Kim et al. Development and evaluation of virtual refrigerant mass flow sensors for fault detection and diagnostics
WO2019052241A1 (en) Refrigerant leak detection method and device for air conditioner
CN109323363B (en) Refrigerant leakage fault detection method and system of air conditioner and air conditioner
US10941956B2 (en) Data processing method, refrigerant leakage detection method, system failure detection method and system performance detection method
JPH11148750A (en) Method of monitoring operation of expansion valve
CN114484731A (en) Method and device for diagnosing faults of central air conditioner based on stacking fusion algorithm
KR102279351B1 (en) A fault diagnosis method of based ai on optimization of air conditioner
CN113739348B (en) Refrigerant state detection method, air conditioner and storage medium
CN113654182A (en) Method for detecting refrigerant leakage, computer readable storage medium and air conditioner
WO2024119832A1 (en) Refrigerant leak detection method and apparatus, system, device and storage medium
CN112413820A (en) Air conditioner defrosting method and device, air conditioning equipment and computer readable storage medium
CN107015486A (en) A kind of air-conditioner water system regulating valve intelligent fault diagnosis method
CN107063663A (en) A kind of air-conditioner water system intelligent diagnostics regulating valve
CN114021461A (en) XGboost-based electronic expansion valve mass flow characteristic prediction method
Kim et al. Cooling mode fault detection and diagnosis method for a residential heat pump
CN113677972A (en) Gas network and method for simultaneous detection of leaks and blockages in a gas network under pressure or vacuum
CN114659583A (en) Liquid level detection method and device of gas-liquid separator, cloud server and medium
CN114061060B (en) Air conditioning apparatus, control method thereof, control device thereof, and computer storage medium
CN105090000A (en) Fault diagnosis method for rough vacuum pumping system of space environment simulator
JP7455667B2 (en) Sensor drift diagnosis device, sensor drift diagnosis method, and sensor drift diagnosis program
CN209726590U (en) Unit capable of detecting blockage

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant