CN111765676A - Multi-split refrigerant charge capacity fault diagnosis method and device - Google Patents
Multi-split refrigerant charge capacity fault diagnosis method and device Download PDFInfo
- Publication number
- CN111765676A CN111765676A CN201910256845.XA CN201910256845A CN111765676A CN 111765676 A CN111765676 A CN 111765676A CN 201910256845 A CN201910256845 A CN 201910256845A CN 111765676 A CN111765676 A CN 111765676A
- Authority
- CN
- China
- Prior art keywords
- refrigerant charge
- operation data
- split air
- neural network
- data
- 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
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25B—REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
- F25B49/00—Arrangement or mounting of control or safety devices
- F25B49/02—Arrangement or mounting of control or safety devices for compression type machines, plants or systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Thermal Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses a refrigerant charge capacity fault diagnosis method and a refrigerant charge capacity fault diagnosis device for a multi-split air conditioner, wherein the method comprises the following steps: s1: collecting operation data of the multi-split air conditioner under different refrigerant charging amounts; s2: processing the collected operation data through Principal Component Analysis (PCA) to obtain characteristic operation data; s3: training a BP neural network by using the characteristic operation data to obtain a refrigerant charge capacity fault detection model; s4: and judging whether the refrigerant charge quantity of the multi-split air conditioner meets a preset standard or not by using the fault detection model. The invention can remove the redundant part in the original data, reduce the dimension of the input data, exert the nonlinear modeling capability of the BP neural network, improve the generalization capability and the learning stability of the model and greatly improve the convergence of the neural network.
Description
Technical Field
The invention relates to the technical field of energy, in particular to a refrigerant charge capacity fault diagnosis method and device of a multi-split air conditioner.
Background
Nowadays, energy resources are gradually exhausted, and how to improve energy efficiency and reduce energy consumption becomes a research topic with important significance. At present, the proportion of the refrigeration air-conditioning system to the total energy consumption of the building system is up to 30% -45%, the energy consumption of the air-conditioning is effectively reduced, the working efficiency of the refrigeration air-conditioning is improved, the energy consumption can be reduced, and the energy utilization rate is improved. The refrigerant charge is one of the important parameters affecting the performance of the refrigeration system, and if a fault occurs and the fault is not removed in time, the energy consumption of the system is increased, the service life of equipment is shortened, and the normal work is affected even if the personnel feel uncomfortable.
At present, the fault diagnosis method basically excavates effective information from a large amount of data, and a data excavation algorithm for finding a rule is a fault diagnosis method which is widely applied at present. The multi-layer feedforward (BP) neural network is one of the well-developed data mining algorithms used at present, the reasoning process of the BP neural network is essentially a numerical calculation process by simulating a brain thinking structure, and the problems of matching conflict, infinite recursion and the like in the diagnostic process of an expert system are avoided.
However, the direct utilization of the BP neural network for fault diagnosis has the defects that the network weight is difficult to understand, the network weight is easy to fall into a local minimum value, the network stability is poor, the convergence rate is slow, the generalization capability is weak, and the like.
Disclosure of Invention
The embodiment of the invention provides a refrigerant charge capacity fault diagnosis method and device of a multi-split air conditioner, which can remove redundant parts in original data, reduce the dimension of input data, exert the nonlinear modeling capacity of a BP (back propagation) neural network, improve the generalization capacity and learning stability of the model and greatly improve the convergence of the neural network.
In a first aspect, an embodiment of the present invention provides a refrigerant charge fault diagnosis method for a multi-split air conditioning system, where the method includes:
s1: collecting operation data of the multi-split air conditioner under different refrigerant charging amounts;
s2: processing the collected operation data through Principal Component Analysis (PCA) to obtain characteristic operation data;
s3: training a BP neural network by using the characteristic operation data to obtain a refrigerant charge capacity fault detection model;
s4: and judging whether the refrigerant charge quantity of the multi-split air conditioner meets a preset standard or not by using the fault detection model.
Preferably, the first and second electrodes are formed of a metal,
before step S2, the method further includes:
preprocessing the collected operation data;
the preprocessing includes rejecting dead variables in the operating data whose values remain unchanged, measured values in the measured temperature values that are outside the normal range, and measured values in the measured pressure values that are outside the normal range.
Preferably, the first and second electrodes are formed of a metal,
the specific process of step S2 includes:
obtaining the contribution rate and the accumulated contribution rate of each principal component by PCA analysis;
and determining characteristic operation data meeting the preset requirements according to the contribution rate and the accumulated contribution rate of each principal element.
Preferably, the first and second electrodes are formed of a metal,
the specific process of step S3 includes:
constructing a BP neural network by taking the characteristic operation data as input data of the BP neural network and taking the refrigerant charge as output data of the BP neural network;
and training the constructed BP neural network by using the characteristic operation data to obtain a refrigerant charge capacity fault detection model.
In a second aspect, an embodiment of the present invention provides a refrigerant charge fault diagnosis apparatus for a multi-split air conditioning system, including: a data acquisition module, a principal component analysis module, a model training module and a detection judgment module, wherein,
the data acquisition module is used for acquiring the operation data of the multi-split air conditioner under different refrigerant charging amounts;
the principal component analysis module is used for processing the collected operation data through Principal Component Analysis (PCA) to obtain characteristic operation data;
the model training module is used for training the BP neural network by using the characteristic operation data to obtain a refrigerant charge capacity fault detection model;
and the detection and judgment module is used for judging whether the refrigerant charge quantity of the multi-split air conditioner meets the preset standard or not by using the fault detection model.
Preferably, the first and second electrodes are formed of a metal,
the device also includes: the data processing module is used for preprocessing the acquired operation data;
the preprocessing includes rejecting dead variables in the operating data whose values remain unchanged, measured values in the measured temperature values that are outside the normal range, and measured values in the measured pressure values that are outside the normal range.
Preferably, the first and second electrodes are formed of a metal,
the principal component analysis module is specifically used for obtaining the contribution rate and the accumulated contribution rate of each principal component by utilizing PCA analysis, and determining the characteristic operation data meeting the preset requirements according to the contribution rate and the accumulated contribution rate of each principal component.
Preferably, the first and second electrodes are formed of a metal,
the detection judgment module is specifically used for constructing the BP neural network by taking the characteristic operation data as input data of the BP neural network and taking the refrigerant charge as output data of the BP neural network, and training the constructed BP neural network by utilizing the characteristic operation data to obtain a refrigerant charge fault detection model.
In a third aspect, the embodiment of the present invention provides a readable medium, which includes execution instructions, and when a processor of an electronic device executes the execution instructions, the electronic device executes a refrigerant charge fault diagnosis method of a multi-split air conditioner according to any one of the first aspect.
In a fourth aspect, an embodiment of the present invention provides an electronic device, including: a processor, a memory, and a bus; the storage is used for storing execution instructions, the processor is connected with the storage through the bus, and when the electronic device runs, the processor executes the execution instructions stored in the storage, so that the processor executes the refrigerant charge fault diagnosis method of the multi-split air conditioner according to any one of claims 1 to 4.
Compared with the prior art, the invention has at least the following beneficial effects:
the invention firstly adopts PCA to reduce the dimension of the input vector to improve the BP neural network, so that the linear combination of the input layer of the neural network can be well completed, the network is greatly simplified and the training time is shortened. The method has good diagnosis precision on the refrigerant charge fault and certain generalization capability, and can be popularized to the diagnosis of other faults of the multi-split air conditioner.
The invention introduces PCA to carry out dimension reduction processing on the sample, eliminates the correlation among characteristics, can remove redundant parts in original data, reduces the dimension of input data, can exert the nonlinear modeling capability of the BP neural network, greatly accelerates the convergence speed of the neural network, improves the generalization capability and the learning stability of the model, and obviously improves the fault diagnosis precision.
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 introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flow chart illustrating a refrigerant charge fault diagnosis method for a multi-split air conditioning system according to an embodiment of the present invention;
fig. 2 is a flow chart illustrating a refrigerant charge fault diagnosis method for a multi-split air conditioning system according to an embodiment of the present invention;
fig. 3 is a block diagram of a refrigerant charge fault diagnosis apparatus of a multi-split air conditioning system according to an embodiment of the present invention;
fig. 4 is an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be 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, and based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts belong to the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a refrigerant charge fault diagnosis method of a multi-split air conditioner, which may include the following steps:
s1: collecting operation data of the multi-split air conditioner under different refrigerant charging amounts;
s2: processing the collected operation data through Principal Component Analysis (PCA) to obtain characteristic operation data;
s3: training a BP neural network by using the characteristic operation data to obtain a refrigerant charge capacity fault detection model;
s4: and judging whether the refrigerant charge quantity of the multi-split air conditioner meets a preset standard or not by using the fault detection model.
In an embodiment of the present invention, as shown in fig. 2, before step S2, the method further includes:
n1: preprocessing the collected operation data;
the preprocessing includes rejecting dead variables in the operating data whose values remain unchanged, measured values in the measured temperature values that are outside the normal range, and measured values in the measured pressure values that are outside the normal range. The dead variable comprises the maximum displacement of the compressor, the model of the compressor, the pipe diameter of the piping and the like. The normal range of the measured temperature value is preset according to the actual situation and can be-15 ℃ to 45 ℃. The normal range of the pressure measurement value is preset according to the actual situation, and can be-0.1 MPa-4.15 MPa.
In an embodiment of the present invention, the specific process of step S2 includes:
analyzing by PCA (Principal Component Analysis) to obtain contribution rate and accumulated contribution rate of each Principal element;
and determining characteristic operation data meeting the preset requirements according to the contribution rate and the accumulated contribution rate of each principal element.
In an embodiment of the present invention, the specific process of step S3 includes:
constructing a BP neural network by taking the characteristic operation data as input data of the BP neural network and taking the refrigerant charge as output data of the BP neural network;
and training the constructed BP neural network by using the characteristic operation data to obtain a refrigerant charge capacity fault detection model.
In this example, the experimental data was derived from a multi-split refrigeration charge experiment, which consists of 8 indoor units and 2 indoor units. As shown in table 1, there were 9 different refrigerant charge levels, and when the refrigerant charge was 65% to 80%, it was judged that the refrigerant charge was insufficient; when the refrigerant charge is 85% -110%, judging that the refrigerant charge is normal; when the refrigerant charge is 120-130%, the refrigerant charge is excessive.
TABLE 1
| Serial number | Refrigerant charge/%) | Determination |
| 1 | 65 | Deficiency of |
| 2 | 76 | Deficiency of |
| 3 | 80 | Deficiency of |
| 4 | 85 | Is normal |
| 5 | 95 | Is normal |
| 6 | 105 | Is normal |
| 7 | 110 | Is normal |
| 8 | 120 | Excess of |
| 9 | 130 | Excess of |
In the process of sampling actual data of the multi-split air conditioner, due to the influences of factors such as short sampling interval, long time, more measuring points, large data volume and the like, missing values and unchanged values exist in data concentration, so that the later algorithm has long running time and low efficiency. In order to ensure the data quality and avoid the occurrence of the phenomena, the data preprocessing is carried out on the original data. The process comprises the following steps: and eliminating dead value variables with unchanged values in the data and measured values which exceed normal ranges in the variables such as temperature, pressure and the like. Finally, the 22 characteristic variables in table 2 are selected for subsequent operation and the additional refrigerant charge is taken as its label column.
FIG. 2
Firstly, PCA is utilized to carry out dimensionality reduction processing on original refrigerant charge experimental data to obtain data after dimensionality reduction, then a BP neural network is utilized to train, and fault detection and diagnosis are carried out on the network data after dimensionality reduction. The contribution rates and the cumulative contribution rates of the 23 principal elements obtained by the principal element analysis method are shown in table 3, and therefore, the first 8 principal elements with the cumulative contribution rate of 89.85% (the preset requirement in this embodiment is greater than 85%) are selected as principal components to perform the fault detection operation.
TABLE 3
And according to the PCA principal component analysis result, the selected first 8 eigenvectors are used as an input layer, and the output layer is the refrigerant filling amount (the variables of insufficient refrigerant filling, normal refrigerant filling and excessive refrigerant filling are used as outputs). For example, the numbers a1, a2, and A3 can be assigned respectively, and the neural network outputs are (100), (010), (001). I.e. there are 3 types of labels in total, and the output layer has 3 node numbers (see table 4).
Because the complexity of the problem is not too large, in order to ensure the stability of the system, the learning rate is selected to be 0.01; the maximum training times are set to be 1,000, the minimum mean square error of the training samples is set to be 0.00004, and other parameters are selected from default values to train and predict the samples.
TABLE 4
| Fault numbering | Neural network output | Label (R) |
| A1 (refrigerant insufficient filling) | A(1 0 0) | -1 |
| A2 (refrigerant filling normal) | A(0 1 0) | 0 |
| A3 (refrigerant overdischarging) | A(0 0 1) | 1 |
Compared with the traditional BP neural network method, the invention has unique superiority. Under the condition that all parameters are unchanged, the training and testing time can be greatly shortened, meanwhile, the good accuracy of the BP neural network on refrigerant charge fault diagnosis is also kept, and the refrigerant charge fault diagnosis precision is greatly improved.
As shown in fig. 3, an embodiment of the present invention provides a refrigerant charge quantity fault diagnosis apparatus of a multi-split air conditioner, including: a data acquisition module, a principal component analysis module, a model training module and a detection judgment module, wherein,
the data acquisition module is used for acquiring the operation data of the multi-split air conditioner under different refrigerant charging amounts;
the principal component analysis module is used for processing the collected operation data through Principal Component Analysis (PCA) to obtain characteristic operation data;
the model training module is used for training the BP neural network by using the characteristic operation data to obtain a refrigerant charge capacity fault detection model;
and the detection and judgment module is used for judging whether the refrigerant charge quantity of the multi-split air conditioner meets the preset standard or not by using the fault detection model.
In one embodiment of the invention, the apparatus further comprises: the data processing module is used for preprocessing the acquired operation data;
the preprocessing includes rejecting dead variables in the operating data whose values remain unchanged, measured values in the measured temperature values that are outside the normal range, and measured values in the measured pressure values that are outside the normal range.
In an embodiment of the present invention, the principal component analysis module is specifically configured to obtain the contribution rate and the cumulative contribution rate of each principal component by using PCA analysis, and determine the characteristic operation data meeting the preset requirement according to the contribution rate and the cumulative contribution rate of each principal component.
In an embodiment of the present invention, the detection and judgment module is specifically configured to use the characteristic operation data as input data of a BP neural network, use the refrigerant charge as output data of the BP neural network, construct the BP neural network, and train the constructed BP neural network by using the characteristic operation data to obtain a refrigerant charge fault detection model.
Because the content of information interaction, execution process, and the like among the modules in the device is based on the same concept as the method embodiment of the present invention, specific content can be referred to the description in the method embodiment of the present invention, and is not described herein again.
As shown in fig. 4, one embodiment of the present invention provides an electronic device. On the hardware level, the electronic device comprises a processor and optionally an internal bus, a network interface and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (peripheral component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 4, but that does not indicate only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor. In a possible implementation manner, the processor reads a corresponding computer program from the nonvolatile memory into the memory and then runs the computer program, and the corresponding computer program can also be obtained from other equipment so as to form the refrigerant charge fault diagnosis device of the multi-split air-conditioning system on a logic level. And the processor executes the program stored in the memory so as to realize the refrigerant charge fault diagnosis method of the multi-split air conditioning system provided by any embodiment of the invention through the executed program.
The method executed by the refrigerant charge fault diagnosis device of the multi-split air conditioner according to the embodiment of the invention shown in fig. 3 can be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
Embodiments of the present invention also provide a computer-readable storage medium storing one or more programs, the one or more programs including instructions, which when executed by an electronic device including a plurality of application programs, enable the electronic device to perform a refrigerant charge fault diagnosis method of a multi-split air-conditioning system provided in any embodiment of the present invention.
The apparatuses, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or implemented by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units or modules by function, respectively. Of course, the functionality of the units or modules may be implemented in the same one or more software and/or hardware when implementing the invention.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a" does not exclude the presence of other similar elements in a process, method, article, or apparatus that comprises the element.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it is to be noted that: the above description is only a preferred embodiment of the present invention, and is only used to illustrate the technical solutions of the present invention, and not to limit the protection scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (10)
1. A refrigerant charge amount failure diagnosis method of a multi-split air conditioner, characterized by comprising:
s1: collecting operation data of the multi-split air conditioner under different refrigerant charging amounts;
s2: processing the collected operation data through Principal Component Analysis (PCA) to obtain characteristic operation data;
s3: training a BP neural network by using the characteristic operation data to obtain a refrigerant charge capacity fault detection model;
s4: and judging whether the refrigerant charge quantity of the multi-split air conditioner meets a preset standard or not by using the fault detection model.
2. The refrigerant charge quantity failure diagnosis method of a multi-split air conditioning system according to claim 1, further comprising, before step S2:
preprocessing the collected operation data;
the preprocessing includes rejecting dead variables in the operating data whose values remain unchanged, measured values in the measured temperature values that are outside the normal range, and measured values in the measured pressure values that are outside the normal range.
3. The refrigerant charge quantity failure diagnosis method of a multi-split air conditioning system according to claim 1, wherein the specific process of step S2 includes:
obtaining the contribution rate and the accumulated contribution rate of each principal component by PCA analysis;
and determining characteristic operation data meeting the preset requirements according to the contribution rate and the accumulated contribution rate of each principal element.
4. The refrigerant charge quantity failure diagnosis method of a multi-split air conditioning system according to claim 3, wherein the specific process of step S3 includes:
constructing a BP neural network by taking the characteristic operation data as input data of the BP neural network and taking the refrigerant charge as output data of the BP neural network;
and training the constructed BP neural network by using the characteristic operation data to obtain a refrigerant charge capacity fault detection model.
5. A refrigerant charge quantity failure diagnosis apparatus of a multi-split air conditioner, characterized by comprising: a data acquisition module, a principal component analysis module, a model training module and a detection judgment module, wherein,
the data acquisition module is used for acquiring the operation data of the multi-split air conditioner under different refrigerant charging amounts;
the principal component analysis module is used for processing the collected operation data through Principal Component Analysis (PCA) to obtain characteristic operation data;
the model training module is used for training the BP neural network by using the characteristic operation data to obtain a refrigerant charge capacity fault detection model;
and the detection and judgment module is used for judging whether the refrigerant charge quantity of the multi-split air conditioner meets the preset standard or not by using the fault detection model.
6. The refrigerant charge quantity failure diagnosis device of a multi-split air conditioner according to claim 5, further comprising: the data processing module is used for preprocessing the acquired operation data;
the preprocessing includes rejecting dead variables in the operating data whose values remain unchanged, measured values in the measured temperature values that are outside the normal range, and measured values in the measured pressure values that are outside the normal range.
7. The refrigerant charge capacity fault diagnosis apparatus of a multi-split air-conditioning system as claimed in claim 5, wherein the principal component analysis module is specifically configured to obtain the contribution rate and the cumulative contribution rate of each principal component by using PCA analysis, and determine the characteristic operation data meeting the preset requirement according to the contribution rate and the cumulative contribution rate of each principal component.
8. The refrigerant charge capacity fault diagnosis device of the multi-split air-fuel ratio system according to claim 7, wherein the detection and judgment module is specifically configured to use the characteristic operation data as input data of a BP neural network, use the refrigerant charge capacity as output data of the BP neural network, construct the BP neural network, and train the constructed BP neural network by using the characteristic operation data to obtain a refrigerant charge capacity fault detection model.
9. A readable medium, characterized in that the readable medium comprises an execution instruction, when the execution instruction is executed by a processor of an electronic device, the electronic device executes the refrigerant charge fault diagnosis method of the multi-split air-conditioning system according to any one of claims 1 to 4.
10. An electronic device, comprising: a processor, a memory, and a bus; the storage is used for storing execution instructions, the processor is connected with the storage through the bus, and when the electronic device runs, the processor executes the execution instructions stored in the storage, so that the processor executes the refrigerant charge fault diagnosis method of the multi-split air conditioner according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910256845.XA CN111765676A (en) | 2019-04-01 | 2019-04-01 | Multi-split refrigerant charge capacity fault diagnosis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910256845.XA CN111765676A (en) | 2019-04-01 | 2019-04-01 | Multi-split refrigerant charge capacity fault diagnosis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111765676A true CN111765676A (en) | 2020-10-13 |
Family
ID=72718195
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910256845.XA Pending CN111765676A (en) | 2019-04-01 | 2019-04-01 | Multi-split refrigerant charge capacity fault diagnosis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111765676A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114413410A (en) * | 2022-03-11 | 2022-04-29 | 青岛海信日立空调系统有限公司 | Fault-tolerant control method for refrigerant improper charging of multi-split air-conditioning system and multi-split air-conditioning system |
| WO2023056617A1 (en) * | 2021-10-09 | 2023-04-13 | Johnson Controls Tyco IP Holdings LLP | Systems and methods for controlling variable refrigerant flow systems using artificial intelligence |
| WO2023169519A1 (en) * | 2022-03-11 | 2023-09-14 | 青岛海信日立空调系统有限公司 | Multi-split air conditioning system and fault-tolerant control method therefor |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060089376A (en) * | 2005-02-04 | 2006-08-09 | 오병주 | A method of face recognition using pca and back-propagation algorithms |
| CN104865827A (en) * | 2015-03-23 | 2015-08-26 | 中国石油天然气股份有限公司 | Oil pumping unit oil extraction optimization method based on multi-working-condition model |
| CN109376794A (en) * | 2018-11-12 | 2019-02-22 | 武汉科技大学 | A kind of intelligent failure diagnosis method and system of molten iron desulphurization stirring device |
| CN109447236A (en) * | 2018-09-28 | 2019-03-08 | 重庆邮电大学 | A kind of method for diagnosing faults of hybrid vehicle heat management system |
-
2019
- 2019-04-01 CN CN201910256845.XA patent/CN111765676A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060089376A (en) * | 2005-02-04 | 2006-08-09 | 오병주 | A method of face recognition using pca and back-propagation algorithms |
| CN104865827A (en) * | 2015-03-23 | 2015-08-26 | 中国石油天然气股份有限公司 | Oil pumping unit oil extraction optimization method based on multi-working-condition model |
| CN109447236A (en) * | 2018-09-28 | 2019-03-08 | 重庆邮电大学 | A kind of method for diagnosing faults of hybrid vehicle heat management system |
| CN109376794A (en) * | 2018-11-12 | 2019-02-22 | 武汉科技大学 | A kind of intelligent failure diagnosis method and system of molten iron desulphurization stirring device |
Non-Patent Citations (1)
| Title |
|---|
| 袁玥等人: "基于主成分分析和神经网络相结合的制冷剂充注量故障诊断", 《制冷技术》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023056617A1 (en) * | 2021-10-09 | 2023-04-13 | Johnson Controls Tyco IP Holdings LLP | Systems and methods for controlling variable refrigerant flow systems using artificial intelligence |
| CN114413410A (en) * | 2022-03-11 | 2022-04-29 | 青岛海信日立空调系统有限公司 | Fault-tolerant control method for refrigerant improper charging of multi-split air-conditioning system and multi-split air-conditioning system |
| WO2023169519A1 (en) * | 2022-03-11 | 2023-09-14 | 青岛海信日立空调系统有限公司 | Multi-split air conditioning system and fault-tolerant control method therefor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017157203A1 (en) | Reference test method and device for supervised learning algorithm in distributed environment | |
| CN111765676A (en) | Multi-split refrigerant charge capacity fault diagnosis method and device | |
| CN109711440B (en) | Data anomaly detection method and device | |
| TW201928841A (en) | Method, apparatus, and device for training risk control model and risk control | |
| CN109857984B (en) | Regression method and device of boiler load rate-efficiency curve | |
| CN111104438A (en) | Method and device for determining periodicity of time sequence and electronic equipment | |
| CN110909826A (en) | Diagnosis monitoring method and device for energy equipment and electronic equipment | |
| CN111506731B (en) | Method, device and equipment for training field classification model | |
| CN112433139B (en) | Method and device for prolonging cycle life of super capacitor | |
| CN111353850A (en) | Risk identification strategy updating method and device and risk merchant identification method and device | |
| CN111310784A (en) | Resource data processing method and device | |
| CN112926636A (en) | Method and device for detecting abnormal temperature of traction converter cabinet body | |
| CN110189178B (en) | Abnormal transaction monitoring method and device and electronic equipment | |
| CN117216529A (en) | Online monitoring method, system and product for molten salt energy storage system equipment | |
| CN112749035B (en) | Abnormality detection method, abnormality detection device, and computer-readable medium | |
| CN115129791A (en) | Data compression storage method, device and equipment | |
| CN111046909A (en) | Load prediction method and device | |
| CN116560968A (en) | Simulation calculation time prediction method, system and equipment based on machine learning | |
| CN108446213A (en) | A kind of static code mass analysis method and device | |
| CN116246787A (en) | Risk prediction method and device for non-recurrent death | |
| CN116204522A (en) | Data auditing method and device, electronic equipment and storage medium | |
| CN111578463A (en) | Method and device for adjusting fresh air valve of variable air volume air conditioning system | |
| CN109145996B (en) | Index data generation method and device under abnormal environment and electronic equipment | |
| CN117454563A (en) | Leakage detection coverage rate detection method and device based on risk frequency | |
| CN113076451B (en) | Abnormal behavior identification and risk model library establishment method and device and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201013 |
|
| RJ01 | Rejection of invention patent application after publication |