CN115638507A - Air conditioning system - Google Patents
Air conditioning system Download PDFInfo
- Publication number
- CN115638507A CN115638507A CN202211305064.3A CN202211305064A CN115638507A CN 115638507 A CN115638507 A CN 115638507A CN 202211305064 A CN202211305064 A CN 202211305064A CN 115638507 A CN115638507 A CN 115638507A
- Authority
- CN
- China
- Prior art keywords
- mathematical model
- value
- detection
- training
- air conditioning
- 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.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Air Conditioning Control Device (AREA)
Abstract
The application discloses air conditioning system includes: an outdoor unit; an air pipe and a liquid pipe are connected between the indoor unit and the outdoor unit; a controller configured to: training: acquiring detection data sets of a plurality of associated operating parameters as training sets; training a mathematical model according to the training set, taking any one of the operation parameters as the output quantity of the mathematical model, and taking other operation parameters except the output quantity as the input quantity of the mathematical model for training; an online fault diagnosis step: a failure state of a detection element for detecting an output quantity is judged. The air conditioning system trains the mathematical model through the detection data set of the associated operating parameters, and adopts a statistical hypothesis testing method to judge the fault state, so that the influence caused by factors such as actual application occasions, working conditions, pipe lengths, online schemes and the like can be eliminated, after the field data is added, the mathematical model can be more accurate, the fault of the detection element can be detected on line, the detection element with the fault can be accurately judged, and the maintenance of personnel is facilitated.
Description
Technical Field
The application relates to the technical field of air conditioners, in particular to an air conditioning system.
Background
Various optimization control strategies for air conditioning systems have become increasingly complex for the purpose of energy conservation and improved indoor air quality, but the implementation of these optimization strategies must have a premise: accuracy and reliability of the sensor. The temperature sensor of the air conditioner is likely to generate resistance drift in the using process, so that the control of the air conditioner according to the data collected by the sensor is invalid. Measurement faults necessarily mislead the control system, resulting in the inability to achieve the goals of advanced control strategies. In addition, when the temperature deviation measured by the temperature sensor is too large, malfunction of the air conditioner may occur.
The Chinese patent application with the application number of CN200410017182.X discloses an online fault diagnosis system of a central air-conditioning water system temperature and flow sensor. The on-line fault diagnosis system for the temperature and flow sensor of the water system of the central air conditioner mainly comprises a data acquisition module, a noise filtering module, a steady-state data judgment module, a fault detection module, a storage module, a fault diagnosis module, a confidence judgment module of a diagnosis result and a data recovery and output module. And (3) carrying out online fault diagnosis on the drift faults of the temperature and flow sensors of the air-conditioning water system by adopting a statistical mathematical method according to the energy conservation and the mass conservation of the system. The patent uses different algorithms based on energy balance to determine that there has been a large deviation in the measurements from a group of sensors, but cannot identify which sensor is having a problem.
Disclosure of Invention
For the technical problem who can't detect and fix a position when solving the detecting element trouble among the air conditioning system among the prior art, this application provides an air conditioning system, can solve above-mentioned problem.
An air conditioning system comprising:
an outdoor unit;
an air pipe and a liquid pipe are connected between the indoor unit and the outdoor unit;
a controller configured to:
training:
acquiring detection data sets of a plurality of associated operating parameters as training sets;
training a mathematical model according to the training set, taking any one of the operation parameters as the output quantity of the mathematical model, and taking other operation parameters except the output quantity as the input quantity of the mathematical model for training;
an online fault diagnosis step:
acquiring detection values of all operation parameters on line;
inputting the detected value of the input quantity acquired on line into a mathematical model, and calculating and outputting the predicted value of the output quantity by the mathematical model;
adopting a statistical hypothesis testing method to judge the fault state, comprising the following steps:
constructing a test statistic according to the predicted value of the output quantity and the detected value of the output quantity;
determining a critical value of the test statistic;
and judging the fault state of the detection element for detecting the output quantity according to the critical value and the test statistic.
In some embodiments, the method further comprises a step of obtaining an air conditioner operation mode corresponding to the operation parameter,
in the training step, an air conditioner operation mode is input into the mathematical model for training;
in the online fault diagnosis step, when the detection values of all the operation parameters are acquired online, the air conditioner operation modes corresponding to the detection values are acquired simultaneously and input to the mathematical model together with the input quantity to obtain the predicted value of the output quantity, the air conditioner operation modes comprise a heating mode and a refrigerating mode, and the refrigerating mode comprises a single refrigerating mode and/or a dehumidifying mode.
In some embodiments, in the training step, each operating parameter is used as an output quantity to train a mathematical model, so as to obtain a plurality of mathematical models;
in the online fault diagnosis step, the input quantity is respectively input into each mathematical model, and the fault state of the detection element corresponding to the corresponding output quantity is judged, so that the fault state of all the detection elements for detecting each operation parameter is obtained.
In some embodiments, in the online fault diagnosis step, the method of detecting the fault state of all the detection elements includes:
selecting a mathematical model, and determining the current mathematical model according to a set sequence or a random selection mode;
determining the input quantity and the output quantity of the selected mathematical model, executing a step of judging the fault state by adopting a statistical hypothesis test method, judging the fault state of the detection element for detecting the current output quantity, and when the fault state is normal, continuously selecting other mathematical models until the fault states of the detection elements of the output quantities of all the mathematical models are judged;
when the failure state is abnormal, in the step of selecting another mathematical model, the detection value of the detection element determined to be abnormal is no longer input to the other mathematical model as the detection value of the input amount.
In some embodiments, when the failure state is abnormal, in the step of selecting another mathematical model, the predicted value of the detection element determined to be abnormal is input as the detected value of the input amount to the other mathematical model.
In some embodiments, in the training step, the trained mathematical model is a neural network model, and the training set is detection data during normal operation within a set time after the air conditioner is installed.
In some embodiments, before the online fault diagnosis step, the method further includes the steps of setting a detection period and determining a detection number, and in the online fault diagnosis step, when the detection values of all the operating parameters are obtained online, the method includes:
and acquiring detection values of all the operation parameters within set time after startup and shutdown on line according to the detection period, and not judging the fault state when the detected number does not meet the detection number or the operation time does not reach the set time.
In some embodiments, the step of determining the fault state by using a statistical hypothesis test further includes, before constructing the test statistic:
determine null hypothesis, H0: μ 1= μ 2, assuming that the mean value of the predicted values of the output quantities is equal to the mean value of the detected values of the output quantities;
in the step of constructing test statistics:
where t is the test statistic, X 1 Is the mean value of the detected values of the input quantity, X 2 The average value of the predicted values of the input quantity is shown, n1 is the sample size of the detected value of the input quantity, and n2 is the sample size of the predicted value of the input quantity;
is a sample variance of the detected value of the input quantity,is the sample variance of the predicted value of the input quantity.
In some embodiments, in the step of determining the fault state of the detection element for detecting the output quantity according to the critical value and the test statistic, the test statistic t is compared with the critical value of the test statistic, if the absolute value of the test statistic t is greater than the critical value, a null hypothesis H0 is rejected, that is, the fault state of the corresponding detection element is an abnormal state, otherwise, the null hypothesis H0 is accepted, that is, the fault state of the corresponding detection element is a normal state;
or acquiring a P value corresponding to the observed value of the test statistic t, comparing the P value with the set significance level alpha, and judging the fault state of the detection element according to the comparison result.
In some embodiments, in the training step, the obtaining of the associated operating parameters is: the air outlet temperature To, the air return temperature Ti, the liquid pipe temperature Tl and the air pipe temperature Tg.
The application provides an air conditioning system, this air conditioning system trains mathematical model through the detection data set of a plurality of operating parameter that is correlated with, adopt statistics hypothesis test method to carry out the fault status judgement, can get rid of because of practical application's occasion, the influence that factors such as operating mode, pipe length and online scheme caused, after adding the field data, mathematical model can be more accurate, not only can the fault of on-line measuring detecting element, can also accurately judge the detecting element who breaks down, the personnel of being convenient for maintain.
Drawings
FIG. 1 is a system schematic of one embodiment of an air conditioning system in accordance with the present invention;
FIG. 2 is a schematic diagram of a refrigerant cycle for a cooling mode of the proposed air conditioning system;
fig. 3 is a schematic diagram of a heating agent cycle in a cooling mode of the air conditioning system according to the present invention;
FIG. 4 is a schematic diagram of a mathematical model of an embodiment of the air conditioning system of the present invention;
FIG. 5 is a schematic diagram of a mathematical model of another embodiment of the air conditioning system of the present invention;
FIG. 6 is a control flow diagram of an embodiment of the air conditioning system of the present invention;
FIG. 7 is a flow chart illustrating a fault condition determination of a sensing element in an embodiment of an air conditioning system according to the present invention;
fig. 8 is a schematic view of a mathematical model of still another embodiment of the air conditioning system according to the present invention;
fig. 9 is a flowchart of a method for detecting a fault state of all detecting elements of still another embodiment of an air conditioning system according to the present invention;
fig. 10 is a schematic view of the internal structure of an indoor unit of an air conditioning system according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. 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 application.
In the description of the present invention, it is to be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used only for convenience of description and simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus are not to be considered as limiting.
The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or otherwise implying any addition or subtraction of the indicated technical features. Thus, a feature defined as "first" or "second" may include one or more of that feature either explicitly or implicitly. In the description of the present application, "a plurality" means two or more unless otherwise specified.
Throughout the description of the present application, it is to be noted that the terms "connected" and "connected" are to be construed broadly and, for example, may be fixedly connected, detachably connected, or integrally connected, unless expressly stated or limited otherwise. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art. In addition, when a pipeline is described, the terms "connected" and "connected" are used in this application to have the meaning of conducting. The specific meaning is to be understood in conjunction with the context.
In the embodiments of the present application, the words "exemplary" or "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the terms "exemplary" or "such as" are intended to present relevant concepts in a concrete fashion.
For the sake of understanding, the basic concepts of some terms or techniques related to the embodiments of the present invention will be briefly described and explained.
A refrigeration mode: the compressor of the air conditioning system sucks the low-temperature and low-pressure gaseous refrigerant evaporated by the evaporator into a compressor cavity, compresses the low-temperature and low-pressure gaseous refrigerant into high-temperature and high-pressure gaseous refrigerant, and then enters the condenser. The high-temperature high-pressure gas refrigerant is condensed into a high-temperature high-pressure liquid refrigerant in the condenser, then the high-temperature high-pressure liquid refrigerant is throttled by a throttling element such as a capillary tube to be changed into a low-temperature low-pressure liquid refrigerant, the low-temperature low-pressure liquid refrigerant enters the evaporator to be evaporated, and finally the low-temperature low-pressure liquid refrigerant returns to the compressor, so that the whole refrigeration cycle is completed. The outdoor heat exchanger in the cooling mode is used as a condenser, and the indoor heat exchanger is used as an evaporator.
Refrigerant: a substance which is easily changed into gas by heat absorption and liquid by heat release. In an air conditioning system, heat energy is transferred through evaporation and condensation of a refrigerant, and a refrigeration effect is generated.
An expansion valve: the valve consists of a valve body and a coil and is used for throttling, reducing pressure and regulating flow. An expansion valve in the air conditioning system can enable a medium-temperature high-pressure liquid refrigerant to be throttled into low-temperature low-pressure wet steam, then the refrigerant absorbs heat in an evaporator to achieve a refrigeration effect, and the flow of a valve is controlled through the change of the superheat degree of an outlet of the evaporator.
A temperature sensor: the temperature sensor is a core part of the temperature measuring instrument, can sense temperature and convert the temperature into a sensor capable of outputting signals, and sends detection signals to the controller, and the controller can control other parts to act according to the detection signals. The number of the temperature sensors in the multi-connected machine room is 4, and the temperature sensors are respectively the outlet air temperature To, the return air temperature Ti, the liquid pipe temperature Tl and the air pipe temperature Tg.
A pressure sensor: the pressure sensor is generally installed on a pipeline of an air conditioner outdoor unit to detect pressure and send a detection signal to a controller, and the controller controls the actions of other parts.
Various optimization control strategies for air conditioning systems have become increasingly complex, but the implementation of these optimization strategies must have a premise: accuracy and reliability of the sensor. For example, the temperature sensor of the air conditioner may have resistance drift during use, so that the control of the air conditioner according to the data collected by the sensor is disabled. Measurement faults necessarily mislead the control system, resulting in the inability to achieve the goals of advanced control strategies. In addition, when the temperature deviation measured by the temperature sensor is too large, malfunction of the air conditioner may occur.
At present, after various detection element faults occur in an air conditioning system, the element fault can be diagnosed, but the fault of which detection element in the air conditioning system occurs cannot be located, especially when a plurality of temperature sensors are arranged, the temperature detection fault can only be known, the temperature sensor fault of which position cannot be located, manual observation and analysis of workers are needed, the workload of the workers is large, the detection element which fails to be located quickly is not needed, and the use experience of a user is influenced while the maintenance cost is increased.
Based on this, the embodiment of the application provides training mathematical models through the detection data sets of a plurality of associated operating parameters, and the statistical hypothesis testing method is adopted to judge the fault state, so that the influence caused by factors such as actual application occasions, working conditions, pipe lengths, online schemes and the like can be eliminated.
To further describe the solution of the present application, reference may be made to fig. 1, where fig. 1 is a schematic structural diagram of an air conditioning system provided in the present application according to an exemplary embodiment.
In some embodiments, as shown in fig. 1, the air conditioning system includes an outdoor unit 11, an indoor unit 12, an expansion valve 13, a four-way valve 14, a compressor 15, an indoor heat exchanger 16, an outdoor heat exchanger 17, and a controller (not shown). During the refrigerant cycle, one of the indoor heat exchanger 16 and the outdoor heat exchanger 17 functions as an evaporator, and the other functions as a condenser.
The refrigeration cycle of the air conditioner is performed by using the compressor 15, the condenser, the expansion valve 13, and the evaporator. The refrigeration cycle includes a series of processes involving compression, condensation, expansion, and evaporation, and supplies refrigerant to the air that has been conditioned and heat-exchanged.
The compressor 15 compresses the refrigerant gas in a high-temperature and high-pressure state and discharges the compressed refrigerant gas. The discharged refrigerant gas flows into the condenser. The condenser condenses the compressed refrigerant into a liquid phase, and heat is released to the surrounding environment through the condensation process.
The expansion valve 13 expands the liquid-phase refrigerant in a high-temperature and high-pressure state condensed in the condenser into a low-pressure liquid-phase refrigerant. The evaporator evaporates the refrigerant expanded in the expansion valve 13, and returns the refrigerant gas in a low-temperature and low-pressure state to the compressor 15. The evaporator can achieve a cooling effect by heat-exchanging with a material to be cooled using latent heat of evaporation of a refrigerant. The air conditioner can adjust the temperature of the indoor space throughout the cycle.
As shown in fig. 2 and 3, the cooling cycle or the heating cycle of the indoor unit 12 is realized by controlling the communication direction of the four-way valve 14.
The outdoor unit of the air conditioner refers to a portion of a refrigeration cycle including a compressor 15 and an outdoor heat exchanger 17, the indoor unit 12 of the air conditioner includes an indoor heat exchanger 16, and an expansion valve 13 may be provided in the indoor unit 12 or the outdoor unit 11.
The indoor heat exchanger 16 and the outdoor heat exchanger 17 function as a condenser or an evaporator. When the indoor heat exchanger 16 is used as a condenser, the air conditioner is used as a heater in a heating mode, and when the indoor heat exchanger 16 is used as an evaporator, the air conditioner is used as a cooler in a cooling mode.
The indoor unit 12 may be provided therein with an air tube 19 and a liquid tube 18 for guiding a flow of refrigerant. The air pipe 19 and the liquid pipe 18 are connected to the indoor heat exchanger 16 so as to extend to the outside of the casing through the inner space of the casing for connection with the outdoor unit 11.
The indoor unit 12 may be a wall-mounted indoor unit 12 installed on a wall of an indoor space, or may be a cabinet-type indoor unit 12.
The indoor unit 12 includes a casing in which a plurality of components constituting a refrigeration cycle are mounted. The housing includes an at least partially open front surface, a rear surface mounted on a wall of the indoor space and provided with a mounting plate, a bottom surface defining a bottom configuration, side surfaces disposed at both sides of the bottom surface, and a top surface defining a top appearance.
An air return opening and an air outlet opening are formed in the indoor unit 12, and air flow enters the indoor unit 12 from the air return opening, exchanges heat through the indoor heat exchanger 16 and then is discharged to an indoor space through the air outlet opening. As shown in fig. 1, a return air temperature sensor 20 is provided at the return air inlet, and the return air temperature sensor 20 is used for detecting the return air temperature. An air outlet temperature sensor 21 is arranged at the air outlet and used for detecting the air outlet temperature.
As shown in fig. 10, a gas pipe temperature sensor 22 is provided in the gas pipe 19 for detecting the temperature of the refrigerant in the gas pipe 19, and a liquid pipe temperature sensor 23 is provided in the liquid pipe 18 for detecting the temperature of the refrigerant in the liquid pipe 18.
A controller configured, as shown in FIG. 6, to include:
training:
acquiring detection data sets of a plurality of associated operating parameters as training sets;
training a mathematical model according to a training set, taking any one operation parameter as the output quantity of the mathematical model, and taking other operation parameters except the output quantity as the input quantity of the mathematical model for training;
an online fault diagnosis step:
acquiring detection values of all operation parameters on line;
inputting the detected value of the input quantity acquired on line into a mathematical model, and calculating and outputting the predicted value of the output quantity by the mathematical model;
adopting a statistical hypothesis testing method to judge the fault state, comprising the following steps:
constructing a test statistic according to the predicted value of the output quantity and the detected value of the output quantity;
determining a critical value of the test statistic;
a failure state of a detection element for detecting an output quantity is judged based on the critical value and the test statistic.
The air conditioning system trains the mathematical model through the detection data set of the associated operating parameters and adopts a statistical hypothesis testing method to judge the fault state, so that the influence caused by factors such as actual application occasions, working conditions, pipe lengths, online schemes and the like can be eliminated.
During the operation of the air conditioner, some operation parameters are changed according to certain rules, and generally, the regular changes of the refrigeration and the heating are different. Based on this, in some embodiments, the method further includes a step of obtaining an air conditioner operation mode corresponding to the operation parameter, so as to associate the operation parameter with the air conditioner operation mode, so that the trained mathematical model has higher accuracy.
In some embodiments, in the training step, the air conditioner operation mode is input to the mathematical model for training;
accordingly, since the trained mathematical model is added with the air conditioner operation mode, in the online fault diagnosis step, as shown in fig. 8, when the detection values of all the operation parameters are acquired online, the air conditioner operation mode corresponding to the detection values is acquired at the same time, and is input to the trained mathematical model together with the input quantity, so as to obtain the predicted value of the output quantity.
The air conditioner operation mode comprises a heating mode and a cooling mode, and the cooling mode comprises a single cooling mode and/or a dehumidifying mode. That is, through training mathematical model respectively for each air conditioner operation mode to make this mathematical model accord with actual operation mode more, the output prediction value of training is closer to actual value.
In some embodiments, in the training step, the mathematical model is trained using each of the operating parameters as an output quantity, so as to obtain a plurality of mathematical models.
In some embodiments, as shown in fig. 4, the training set has n operating parameters, i.e., a parameter 1 and a parameter 2.. The parameter n, and the parameter 1 is used as an output quantity of the mathematical model, other parameters are used as input quantities of the mathematical model, a mathematical model is trained, the parameter 2 is used as an output quantity of the mathematical model, other parameters are used as input quantities of the mathematical model, a mathematical model is trained, i.e., the parameter n is used as an output quantity of the mathematical model, and other parameters are used as input quantities of the mathematical model, a mathematical model is trained, and n mathematical models are obtained through co-training.
Although it is only known that the operating parameters have a certain correlation, the correlation coefficient between each operating parameter and other operating parameters is different, and therefore, as shown in fig. 4 and 5, it is necessary to train each operating parameter as an output to obtain a mathematical model reflecting the relationship between each operating parameter and other operating parameters.
In the online fault diagnosis step, the input quantity is respectively input into each mathematical model, and the fault state of the detection element corresponding to the corresponding output quantity is judged, so that the fault state of all the detection elements for detecting each operation parameter is obtained.
In some embodiments, the trained mathematical model uses a regression function of a neural network machine learning algorithm, and the value of any one operating parameter can be accurately inferred from the values of the other three operating parameters.
In some embodiments, in the online fault diagnosis step, the method of detecting the fault state of all the detection elements includes:
and selecting a mathematical model, and determining the current mathematical model according to a set sequence or a random selection mode. As mentioned above, when there are n associated operating parameters, n mathematical models are trained accordingly, and therefore, the fault state of each detecting element needs to be determined separately in a certain order or manner in the online fault diagnosis step.
In some embodiments, as shown in fig. 9, the input quantity and the output quantity of the selected mathematical model are determined, a step of judging the fault state of the detecting element for detecting the current output quantity by using a statistical hypothesis test is performed, and when the fault state is normal, other mathematical models are selected continuously until the fault states of the detecting elements of the output quantities of all the mathematical models are judged.
As can be seen from the foregoing, the input and output quantities of each trained mathematical model are uniquely determined after training, and therefore, the input and output quantities of the selected mathematical model can be determined. The fault diagnosis method in the scheme can be used for diagnosing faults of the detection elements for detecting the output quantity of the mathematical model by utilizing the mathematical model.
When the failure state is abnormal, in the step of selecting another mathematical model, the detection value of the detection element determined to be abnormal is no longer input to the other mathematical model as the detection value of the input amount.
If the fault state of a certain detection element is judged to be abnormal, the detection result of the detection element is seriously deviated from the actual value, so that the detection element is not suitable to be input into other mathematical models as an input quantity to be used for carrying out fault judgment on the operation parameters of the gas, and otherwise, the detection result of other operation parameters is influenced.
In order to avoid erroneous judgment in diagnosing other elements which have not been subjected to fault diagnosis, in some embodiments, when the fault state is abnormal, in the step of selecting another mathematical model, the predicted value of the detection element which is judged to be abnormal is input to the other mathematical model as the detected value of the input quantity.
That is, since the mathematical model is obtained by training according to the actual data on site, the output predicted value and the actual value should be very close to each other, and it can be understood that if the detecting element is normal, the predicted value, the detected value and the actual value should be very close to each other. If the detection element is abnormal, the detection value deviates from the predicted value and the actual value, and the predicted value is still close to the actual value, so that the scheme can improve the diagnosis accuracy of other operation parameters by inputting the predicted value of the detection element which is judged to be abnormal as the detection value of the input quantity into other mathematical models in the step of selecting other mathematical models when the fault state is abnormal.
In some embodiments, in the training step, the trained mathematical model is a neural network model, and the training set is detection data during normal operation within a set time after the air conditioner is installed.
For example, data of normal operation of the air conditioner installation application in the first year can be recorded, and a training set database is added to revise the neural network model. Because the actual application occasion, the working condition, the pipe length, the online scheme and the like are different from those of a laboratory, and after field data are added, the model regression value is more accurate.
In some embodiments, before the step of online fault diagnosis, the method further includes the steps of setting a detection period and determining a detection number, and in the step of online fault diagnosis, when the detection values of all the operating parameters are obtained online, the method includes:
and acquiring detection values of all operation parameters within set time after startup and shutdown on line according to a detection period, and not judging the fault state when the detected number does not meet the detection number or the operation time does not reach the set time.
In some embodiments, the step of determining the fault state by using a statistical hypothesis test further includes, before constructing the test statistic:
determine null hypothesis, H0: μ 1= μ 2, assuming that the mean value of the predicted values of the output quantities is equal to the mean value of the detected values of the output quantities;
the task of hypothesis testing is to confirm whether the original hypothesis is true, and the method comprises the following steps: the original hypothesis is assumed to be established, and then the sample is used for judging the authenticity, and because the information contained in the sample is scattered, a statistic is required to be constructed for judgment, and the statistic is called as a test statistic.
In the step of constructing test statistics:
where t is the test statistic, X 1 Is the mean value of the detected values of the input quantity, X 2 The average value of the predicted values of the input quantity is shown, n1 is the sample size of the detected value of the input quantity, and n2 is the sample size of the predicted value of the input quantity;
is a sample variance of the detected value of the input quantity,is the sample variance of the predicted value of the input quantity.
Prior to the step of determining the cutoff value for the test statistic, determining a significance level α comprises:
there is a risk that an error may be made when trying to make a decision as to whether the original hypothesis H0 is true. To control this risk, it is first necessary to represent the risk with a probability that event "H0 is true but rejected", which is the level of significance that needs to be determined. Because of the randomness of the sample, it is impossible to avoid "false positives" completely, so the probability of this event occurring can only be controlled to a small range, typically 1%,5% and 10% alpha.
In some embodiments, as shown in fig. 7, in the step of determining the fault state of the detection element for detecting the output quantity according to the critical value and the test statistic, the test statistic t is compared with the critical value of the test statistic, if the absolute value of the test statistic t is greater than the critical value, the zero hypothesis H0 is rejected, that is, the fault state of the corresponding detection element is an abnormal state, otherwise, the zero hypothesis H0 is accepted, that is, the fault state of the corresponding detection element is a normal state;
or acquiring a P value corresponding to the observed value of the test statistic t, comparing the P value with the set significance level alpha, and judging the fault state of the detection element according to the comparison result.
That is, the statistical quantity calculated using the samples is compared with a threshold value at a given significance level, and if the absolute value calculated by the statistical quantity is greater than the threshold value, the original hypothesis H0 is rejected, otherwise only the original hypothesis can be accepted.
For example: p value =0.21484> α =0.05; therefore, the null hypothesis H0 is not rejected and the difference is not statistically significant. There is not sufficient reason to say that the average values of the two populations are not equal, i.e. the sensor is not faulty, otherwise it is decided that the indoor sensor is faulty.
In some embodiments, in the training step, the obtaining of the associated operating parameters is: the air outlet temperature To, the air return temperature Ti, the liquid pipe temperature Tl and the air pipe temperature Tg. In the air conditioner operation process, the four temperatures are changed according to a certain rule, so that the four temperature values can be used as associated operation parameters for training.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should 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 or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.
The foregoing description, for purposes of explanation, has been presented in conjunction with specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or to limit the embodiments to the precise forms disclosed above. Many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles and the practical application, to thereby enable others skilled in the art to best utilize the embodiments and various embodiments with various modifications as are suited to the particular use contemplated.
Claims (10)
1. An air conditioning system, comprising:
an outdoor unit;
an air pipe and a liquid pipe are connected between the indoor unit and the outdoor unit;
a controller configured to:
training:
acquiring detection data sets of a plurality of associated operating parameters as training sets;
training a mathematical model according to the training set, taking any one of the operation parameters as the output quantity of the mathematical model, and taking other operation parameters except the output quantity as the input quantity of the mathematical model for training;
an online fault diagnosis step:
acquiring detection values of all operation parameters on line;
inputting the detected value of the input quantity acquired on line into a mathematical model, and calculating and outputting the predicted value of the output quantity by the mathematical model;
adopting a statistical hypothesis testing method to judge the fault state, comprising the following steps:
constructing a test statistic according to the predicted value of the output quantity and the detected value of the output quantity;
determining a critical value of the test statistic;
and judging the fault state of the detection element for detecting the output quantity according to the critical value and the test statistic.
2. The air conditioning system of claim 1, further comprising a step of obtaining an air conditioning operation mode corresponding to the operation parameter,
in the training step, an air conditioner operation mode is input into the mathematical model for training;
in the online fault diagnosis step, when the detection values of all the operation parameters are acquired online, the air conditioner operation modes corresponding to the detection values are acquired simultaneously and input to the mathematical model together with the input quantity to obtain the predicted value of the output quantity, the air conditioner operation modes comprise a heating mode and a refrigerating mode, and the refrigerating mode comprises a single refrigerating mode and/or a dehumidifying mode.
3. The air conditioning system of claim 1, wherein in the training step, the mathematical model is trained by using each operation parameter as an output quantity to obtain a plurality of mathematical models;
in the online fault diagnosis step, the input quantity is respectively input into each mathematical model, and the fault state of the detection element corresponding to the corresponding output quantity is judged, so that the fault state of all the detection elements for detecting each operation parameter is obtained.
4. The air conditioning system as claimed in claim 3, wherein the method of detecting the fault state of all the detecting elements in the online fault diagnosing step includes:
selecting a mathematical model, and determining the current mathematical model according to a set sequence or a random selection mode;
determining the input quantity and the output quantity of the selected mathematical model, executing a step of judging the fault state by adopting a statistical hypothesis test method, judging the fault state of the detection element for detecting the current output quantity, and when the fault state is normal, continuously selecting other mathematical models until the fault states of the detection elements of the output quantities of all the mathematical models are judged;
when the failure state is abnormal, in the step of selecting another mathematical model, the detection value of the detection element determined to be abnormal is no longer input to the other mathematical model as the detection value of the input amount.
5. The air conditioning system according to claim 4, wherein when the failure state is abnormal, in the step of selecting another mathematical model, the predicted value of the detection element determined to be abnormal is input to the other mathematical model as the detected value of the input amount.
6. The air conditioning system as claimed in any one of claims 1 to 5, wherein in the training step, the trained mathematical model is a neural network model, and the training set is detection data of normal operation within a set time after installation of the air conditioner.
7. The air conditioning system according to any one of claims 1 to 5, further comprising a step of setting a detection period and determining the number of detections before the online fault diagnosis step, wherein the online fault diagnosis step, when acquiring the detected values of all the operation parameters online, comprises:
and acquiring detection values of all the operation parameters within set time after startup and shutdown on line according to the detection period, and not judging the fault state when the detected number does not meet the detection number or the operation time does not reach the set time.
8. The air conditioning system as claimed in any one of claims 1 to 5, wherein the step of determining the fault state by using the statistical hypothesis test further comprises, before constructing the test statistic:
determine null hypothesis, H0: μ 1= μ 2, assuming that the mean value of the predicted values of the output quantities is equal to the mean value of the detected values of the output quantities;
in the step of constructing test statistics:
where t is the test statistic, X 1 Is the mean value of the detected values of the input quantity, X 2 The average value of the predicted values of the input quantity is shown, n1 is the sample size of the detected value of the input quantity, and n2 is the sample size of the predicted value of the input quantity;
9. The air conditioning system according to claim 8, wherein in the step of determining the failure state of the detecting element for detecting the output quantity based on the critical value and the test statistic, the test statistic t is compared with the critical value of the test statistic, and if the absolute value of the test statistic t is greater than the critical value, the zero hypothesis H0 is rejected, that is, the failure state of the corresponding detecting element is an abnormal state, otherwise, the zero hypothesis H0 is accepted, that is, the failure state of the corresponding detecting element is a normal state;
or acquiring a P value corresponding to the observed value of the test statistic t, comparing the P value with the set significance level alpha, and judging the fault state of the detection element according to the comparison result.
10. The air conditioning system as claimed in any one of claims 1 to 5, wherein in the training step, the associated operating parameters are obtained as: the air outlet temperature To, the air return temperature Ti, the liquid pipe temperature Tl and the air pipe temperature Tg.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211305064.3A CN115638507A (en) | 2022-10-24 | 2022-10-24 | Air conditioning system |
PCT/CN2023/085943 WO2023226595A1 (en) | 2022-05-23 | 2023-04-03 | Air conditioning system and filth blockage determination method for air conditioning system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211305064.3A CN115638507A (en) | 2022-10-24 | 2022-10-24 | Air conditioning system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115638507A true CN115638507A (en) | 2023-01-24 |
Family
ID=84944119
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211305064.3A Pending CN115638507A (en) | 2022-05-23 | 2022-10-24 | Air conditioning system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115638507A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023226595A1 (en) * | 2022-05-23 | 2023-11-30 | 青岛海信日立空调***有限公司 | Air conditioning system and filth blockage determination method for air conditioning system |
-
2022
- 2022-10-24 CN CN202211305064.3A patent/CN115638507A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023226595A1 (en) * | 2022-05-23 | 2023-11-30 | 青岛海信日立空调***有限公司 | Air conditioning system and filth blockage determination method for air conditioning system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Breuker et al. | Evaluating the performance of a fault detection and diagnostic system for vapor compression equipment | |
CN107166638B (en) | Fault detection method and device of temperature sensor and multi-connected air conditioning system | |
Rossi et al. | A statistical, rule-based fault detection and diagnostic method for vapor compression air conditioners | |
CN107084494B (en) | Fault detection method and device for electronic expansion valve and multi-connected air conditioning system | |
Li et al. | Decoupling features and virtual sensors for diagnosis of faults in vapor compression air conditioners | |
US7987679B2 (en) | Air conditioning apparatus | |
Wang et al. | A robust fault detection and diagnosis strategy for centrifugal chillers | |
Chen et al. | Simple rule-based methods for fault detection and diagnostics applied to packaged air conditioners/Discussion | |
US20080033674A1 (en) | Detecting and diagnosing faults in HVAC equipment | |
Kim et al. | Development and evaluation of virtual refrigerant mass flow sensors for fault detection and diagnostics | |
CN108278715A (en) | A kind of air conditioner lacks fluorine guard method and the air conditioner with scarce fluorine defencive function | |
CN105509241B (en) | The method, apparatus and air conditioner that whether temperature sensing package falls off in condenser tube judged | |
JPH11148750A (en) | Method of monitoring operation of expansion valve | |
CN113654182A (en) | Method for detecting refrigerant leakage, computer readable storage medium and air conditioner | |
Li et al. | Virtual refrigerant pressure sensors for use in monitoring and fault diagnosis of vapor-compression equipment | |
KR20070017269A (en) | Pipe inspection operation and method of Multi air conditioner | |
CN115638507A (en) | Air conditioning system | |
CN110296499A (en) | A kind of electric expansion valve abnormal cause judgment method, device and air conditioner | |
JP2005301582A (en) | Process management device | |
Wichman et al. | Fault detection and diagnostics for commercial coolers and freezers | |
Hu | Development and demonstration of a method to determine residential air-conditioning system fault prevalence | |
Rueda et al. | Fault detection and diagnosis in liquid chillers | |
KR20230126044A (en) | Air conditioner | |
CN110926544B (en) | Detection equipment for heat exchanger unit and online automatic detection method thereof | |
EP2256423B1 (en) | Multi-type air conditioner and a method for checking operation of indoor electronic expansion valves of indoor units |
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 |