Simulation methods, electronic devices and storage media for air conditioner operation test data

Abstract

This invention discloses a simulation method for air conditioner operation detection data, comprising: conducting operational tests on an air conditioner prototype to obtain test data; dividing the test data into test data corresponding to state parameters and test data corresponding to control parameters, wherein the state parameters refer to parameters reflecting the operating state of the air conditioner, and the control parameters refer to parameters controlling the operation of the air conditioner; obtaining an initial model according to the design requirements of the air conditioner, setting the test data corresponding to the control parameters as input quantities, setting the test data corresponding to the state parameters as output quantities, training the initial model to obtain a simulation model; inputting the control parameters into the simulation model, and the simulation model outputting the simulation state parameters. This application can realize the operation simulation of the air conditioning system before the air conditioner is manufactured, simplifying the air conditioner development process and improving the development efficiency of the air conditioner.

Description

Technical Field

[0001] This invention relates to the field of air conditioning simulation, and more particularly to simulation methods, electronic devices, and storage media for air conditioning operation detection data. Background Technology

[0002] Currently, side-discharge multi-split air conditioning products are diverse and have complex system structures. Product function testing can only be carried out after the air conditioner has been developed and manufactured. With the increasing demands of market competition, the number of air conditioning products being developed is increasing year by year. According to the current development, manufacturing, and testing process, the R&D and testing cycle of air conditioners is significantly extended. Such a long R&D and testing cycle requires a huge investment of human and material resources to complete. Moreover, the testing after development is cumbersome, resulting in a long overall development and testing time and affecting product production efficiency. Summary of the Invention

[0003] This invention aims to at least partially address one of the problems in related technologies. Therefore, the purpose of this invention is to provide a simulation method, electronic device, and storage medium for air conditioner operation detection data, which can simulate the operation of the air conditioning system before air conditioner manufacturing, simplifying the air conditioner development process and improving air conditioner development efficiency.

[0004] To achieve the above objectives, this application adopts the following technical solution: a simulation method for air conditioner operation detection data, comprising:

[0005] The air conditioner prototype was tested to obtain test data. The test data was then divided into test data corresponding to state parameters and test data corresponding to control parameters. The state parameters refer to the parameters that reflect the operating state of the air conditioner, and the control parameters refer to the parameters that control the operation of the air conditioner.

[0006] The initial model is obtained according to the design requirements of the air conditioner. The test data corresponding to the control parameters are set as inputs, and the test data corresponding to the state parameters are set as outputs. The initial model is trained to obtain the simulation model.

[0007] The simulation model inputs control parameters and outputs simulation state parameters.

[0008] Furthermore, the test data includes a test set and a training set, wherein the training set is used to train the initial model and the test set is used to test the similarity of the simulation models.

[0009] Furthermore, it also includes: calculating the correlation between control parameters and state parameters based on test data to obtain a test correlation curve; and using the test set and correlation curve to determine the accuracy of the simulation model.

[0010] Furthermore, the accuracy of the simulation model is determined using the test set and correlation curves, specifically including:

[0011] After obtaining the simulation model, the test data corresponding to the control parameters in the test set are used as input, and the test data of the state parameters related to the control parameters in the test set are used as output. The simulation correlation curve is obtained using the simulation model.

[0012] The simulation correlation curve and the test correlation curve are calculated relative to each other. If the similarity between the simulation correlation curve and the test correlation curve is greater than the preset value, the simulation model is output. If it is less than or equal to the preset value, the simulation model is retrained using the training set until the similarity between the simulation correlation curve and the test correlation curve is greater than the preset value.

[0013] Furthermore, after acquiring the test data, the process also includes classifying the test data according to the model and acquiring a corresponding simulation model for each model.

[0014] Furthermore, the initial model and simulation model include neural networks.

[0015] Furthermore, after obtaining the simulation model, a tooling self-checking step is also included:

[0016] Establish standard formats for each control parameter;

[0017] The format for writing the control parameter input is compared with the standard format. If the format does not match the standard format, the input format is judged to be incorrect, and the reason for the error is output. If the format matches the standard format, the input format is judged to be correct.

[0018] Furthermore, after the simulation model outputs the simulation state parameters, it also includes a fault simulation step: inputting the simulation state parameters into the fault detection model, and the fault detection model outputs whether the simulation state parameters are abnormal and the cause of the abnormality.

[0019] An electronic device, comprising:

[0020] Processor; and

[0021] A memory that stores executable code, which, when executed by the processor, causes the processor to perform the method described above.

[0022] A non-transitory machine-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method described above.

[0023] Compared with the prior art, the technical solution provided in this application has the following advantages: This application obtains an initial model based on the design requirements of the air conditioner, and then obtains test data based on the operation of the air conditioner prototype. The initial model is trained based on the test data to obtain a simulation model. This application can simulate the operation of the air conditioner based solely on the design requirements and the prototype. Compared with the prior art method of manufacturing the air conditioner first and then conducting operation tests, this application can realize "physical" air conditioner operation simulation and obtain simulation results. This application can simplify the air conditioner development process and improve the air conditioner development efficiency. Attached Figure Description

[0024] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] In the attached image:

[0027] Figure 1 This is a flowchart of the simulation method for air conditioner operation detection data in Example 1;

[0028] Figure 2 This is a flowchart of the simulation method for air conditioner operation detection data in Example 2. Detailed Implementation

[0029] To provide a clearer understanding of the technical features, objectives, and effects of this invention, specific embodiments are now described in detail with reference to the accompanying drawings. In the following description, it should be understood that the orientations or positional relationships indicated by terms such as "front," "rear," "upper," "lower," "left," "right," "longitudinal," "horizontal," "vertical," "horizontal," "top," "bottom," "inner," "outer," "head," and "tail" are based on the orientations or positional relationships shown in the accompanying drawings, and are constructed and operated in a specific orientation. They are only for the convenience of describing this technical solution and do not indicate that the referred mechanism or element must have a specific orientation; therefore, they should not be construed as limitations on this invention.

[0030] It should also be noted that, unless otherwise explicitly specified and limited, terms such as "installation," "connection," "linking," "fixing," and "setting" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. When an component is referred to as being "on" or "below" another component, the component can be located "directly" or "indirectly" on the other component, or there may be one or more intermediary components. The terms "first," "second," "third," etc., are only for the convenience of describing this technical solution and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, features defined with "first," "second," "third," etc., may explicitly or implicitly include one or more of that feature. For those skilled in the art, the specific meaning of the above terms in this invention can be understood according to the specific circumstances.

[0031] In the following description, specific details such as particular system structures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, mechanisms, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0032] Example 1

[0033] Please see the appendix Figure 1 This application provides a simulation method for air conditioner operation detection data, comprising:

[0034] S1: Conduct operational tests on the air conditioner prototype and obtain test data; divide the test data into test data corresponding to state parameters and test data corresponding to control parameters. Among them, state parameters refer to parameters that reflect the operating state of the air conditioner, and control parameters refer to parameters that control the operation of the air conditioner.

[0035] S2: Obtain the initial model according to the design requirements of the air conditioner, set the test data corresponding to the control parameters as inputs, set the test data corresponding to the state parameters as outputs, train the initial model, and obtain the simulation model.

[0036] S3: Input control parameters into the simulation model, and the simulation model outputs simulation state parameters.

[0037] This application obtains an initial model based on the design requirements of the air conditioner, and then obtains test data based on the operation of the air conditioner prototype. The initial model is then trained based on the test data to obtain a simulation model. This application can simulate the operation of the air conditioner based solely on the design requirements and the prototype. Compared with the existing technology of manufacturing the air conditioner first and then conducting operation tests, this application can realize the simulation of air conditioner operation without physical objects and obtain simulation results. This application can simplify the air conditioner development process and improve the development efficiency of the air conditioner.

[0038] Example 2

[0039] Please see the appendix Figure 2 This application provides a simulation method for air conditioner operation detection data, comprising:

[0040] S1: Conduct operational tests on the air conditioner prototype and obtain test data; divide the test data into test data corresponding to state parameters and test data corresponding to control parameters; among them, state parameters refer to parameters that reflect the operating state of the air conditioner, such as temperature sensors, electrical parameters, etc.; control parameters refer to parameters that control the operation of the air conditioner, such as compressor frequency, fan frequency, electronic expansion valve opening, etc.

[0041] Test parameters refer to the set of test values ​​corresponding to key parameters within a test time. Key parameters include control parameters and state parameters. Test parameters are a set of test values ​​within a time period. For example, the opening of the electronic expansion valve. When the air conditioner prototype runs from time T0 to time T1, the test data corresponding to the control parameter electronic expansion valve opening refers to the set of multiple test data corresponding to time T0 to time T1.

[0042] After obtaining the test parameters, this application also needs to divide the test data according to the model. In actual operation, the test data is obtained from multiple air conditioner prototypes. It is necessary to divide the test data corresponding to each model together. When training the simulation model later, it is necessary to match according to the model, that is, to use the test data of the corresponding model to train the simulation model.

[0043] After obtaining the test data, this application also requires noise removal and null value imputation. Noise removal refers to removing test data that is considered noisy. Specifically, the "box plot method" can be used to process the test data for noise. Human experience is used to determine whether data is noisy; if so, it is removed. Null value imputation involves checking the processed test data for missing values. If missing values ​​are found, they need to be filled. The method is to calculate the average of the two values ​​before and after the missing value and fill the missing value with this average.

[0044] This application defines the test data as a test set and a training set. The training set is used to train the initial model, and the test set is used to test the similarity of the simulation models. Both the training set and the test set include test data corresponding to the control parameters and state parameters.

[0045] S2: Obtain the initial model according to the design requirements of the air conditioner, set the test data corresponding to the control parameters as inputs, set the test data corresponding to the state parameters as outputs, train the initial model, and obtain the simulation model.

[0046] The design requirements for an air conditioner refer to the functional and performance requirements to be achieved by the air conditioner before its development and manufacturing. Based on the design requirements, a suggested air conditioner prototype can be prepared. In step S1, the air conditioner prototype is designed and manufactured according to the design requirements. It should be noted that the preparation of an air conditioner prototype is much simpler than that of a complete air conditioner. With the help of the initial model obtained from the design requirements, this application can achieve functional testing of the air conditioner without a physical object, unlike the prior art, which requires the air conditioner to be officially manufactured before functional testing can be carried out.

[0047] In practice, designers first formulate an initial air conditioning system design plan based on the air conditioning design requirements. Then, based on this plan, they determine the model, type, and installation location of each piece of equipment in the air conditioning system. Finally, an initial model consistent with the design plan is created based on the model, type, and installation location of each piece of equipment.

[0048] There are certain differences between the initial model and the final air conditioner developed. This application requires training the initial model using a training set to ensure that its simulation results are as close as possible to the actual operating test data of the final air conditioner.

[0049] The initial model in this application can be a neural network model or other autonomous learning model.

[0050] During the initial model training process, the input is set to test data representing the control parameters, and the output is set to test data representing state parameters that are correlated with the control parameters. This allows the initial model to learn autonomously and adjust its internal model parameters.

[0051] S3: Calculate the correlation between control parameters and state parameters based on the test data to obtain the test correlation curve; use the test set and the correlation curve to determine the accuracy of the simulation model. The correlation reflects the degree of influence of control parameters on state parameters.

[0052] In this step, the correlation test can be the correlation between one control parameter and multiple state parameters, or the correlation between one control parameter and one state parameter. For example, the influence of the electronic expansion valve opening on the temperature sensing bulb and / or the temperature sensing bulb can be calculated. This influence is expressed using correlation. The specific correlation calculation can be performed using a correlation analysis model in the existing technology. Only the test data of two parameters need to be input, and the correlation analysis model can calculate the correlation between the two parameters.

[0053] The accuracy of the simulation model is determined using a test set and correlation curves, specifically including:

[0054] After obtaining the simulation model, the test data corresponding to the control parameters in the test set are used as input, and the test data of the state parameters related to the control parameters in the test set are used as output. The simulation correlation curve is obtained using the simulation model.

[0055] The simulation correlation curve and the test correlation curve are compared and their relative similarity is calculated. If the similarity between the simulation correlation curve and the test correlation curve is greater than a preset value, the simulation model is output; if it is less than or equal to the preset value, the simulation model is retrained using the training set until the similarity between the simulation correlation curve and the test correlation curve is greater than the preset value. The specific preset value can be set according to the model accuracy requirements, such as 75%.

[0056] When the similarity between the simulation correlation curve and the test correlation curve is greater than the preset value, it indicates that the accuracy of the simulation model has met the requirements. The data simulated by the simulation model is not much different from the data tested by the air conditioner prototype. Therefore, the data simulated by the simulation model can be used as the functional test data of the air conditioner.

[0057] S4: Input the control parameters into the simulation model, and the simulation model outputs the simulation state parameters. This step refers to using the trained simulation model to test the air conditioning function. Simply input the control parameters into the simulation model to obtain the simulated test values ​​of the state parameters.

[0058] Example 3

[0059] Based on Example 2, in order to further ensure the accuracy of the simulation results of the simulation model, after obtaining the trained simulation model, this application needs to write and check the control parameters input to the simulation model, and input them into the simulation model only after confirming that the writing format of the control parameters is correct.

[0060] It should be noted that after obtaining the simulation model in Example 2, the simulation model can be encapsulated to form an independent module. The encapsulated independent module then works together with the self-inspection model for tooling self-inspection in this example.

[0061] Specific tooling self-inspection steps:

[0062] Establish standard formats for each control parameter;

[0063] The format for writing the control parameter input is compared with the standard format. If the format does not match the standard format, the input format is judged to be incorrect, and the reason for the error is output. If the format matches the standard format, the input format is judged to be correct.

[0064] Example 4

[0065] Based on Example 2, in order to further ensure the accuracy of the simulation results of the simulation model, this application can also use a fault detection model to detect whether the air conditioner design has a fault after the simulation model outputs the simulation state parameters. The specific fault simulation steps include: inputting the simulation state parameters into the fault detection model, and the fault detection model outputting whether the simulation state parameters are abnormal and the cause of the abnormality.

[0066] It should be noted that after obtaining the simulation model in Example 2, the simulation model can be encapsulated to form an independent module. The encapsulated independent module then works together with the fault detection model used for fault detection in this example.

[0067] The fault detection model needs to be verified before use. Specifically, it can be verified using simulation state parameters obtained from the simulation model. The specific verification steps include:

[0068] S1: Select simulation data with simulation state parameters within a certain range, and swap the simulation data corresponding to the two sets of simulation state parameters; for example, swap the simulation data corresponding to the subcooler gas outlet temperature sensor and the subcooler liquid outlet temperature sensor.

[0069] S2: Input the swapped simulation state parameters into the fault detection model. If the fault detection model determines that the simulation state parameters are abnormal, it will pop up a fault message that "the temperature sensor bulbs of the subcooler gas outlet and the subcooler liquid outlet are reversed". This indicates that the fault detection model is effective and can be used to detect the simulation state parameters. If the fault detection model determines that the simulation state parameters are normal, or the fault message that pops up does not correspond, it indicates that the fault detection model is invalid and cannot be used to detect the simulation state parameters.

[0070] This application can replace manual debugging, improve the quality of air conditioner development, shorten the development cycle, and realize automatic detection of input parameter format, as well as fault simulation before air conditioner production, to verify and test the reliability of air conditioner design.

[0071] This application can construct corresponding simulation models based on test data of different models, realize the development of "physical-free" testing and visualization of simulation data; formulate a self-check judgment mechanism to automatically identify abnormal test formats and prompt abnormal items; set faults and automatically read or change the data of simulation status parameters to realize fault early warning.

[0072] Corresponding to the aforementioned application function implementation method embodiments, this application also provides an electronic device and corresponding embodiments for a simulation method of air conditioner operation detection data.

[0073] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated further here.

[0074] Electronic devices include memory and processors.

[0075] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, 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, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0076] Memory can include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM can store static data or instructions required by the processor or other modules of the computer. Permanent storage devices can be read-write storage devices. Permanent storage devices can be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices use high-capacity storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices can be removable storage devices (e.g., floppy disks, optical drives). System memory can be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. System memory can store some or all of the instructions and data required by the processor during operation. Furthermore, memory can include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks can also be used. In some implementations, the memory may include removable storage devices that are readable and / or writable, such as laser discs (CDs), read-only digital versatile optical discs (e.g., DVD-ROMs, dual-layer DVD-ROMs), read-only Blu-ray discs, ultra-high density optical discs, flash memory cards (e.g., SD cards, mini SD cards, Micro-SD cards, etc.), magnetic floppy disks, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.

[0077] The memory stores executable code, which, when processed by the processor, can cause the processor to execute some or all of the methods described above.

[0078] It is understood that the above embodiments only illustrate preferred embodiments of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can freely combine the above technical features without departing from the concept of the present invention, and can also make several modifications and improvements, all of which fall within the protection scope of the present invention. Therefore, all equivalent transformations and modifications made with respect to the scope of the claims of the present invention should fall within the scope of the claims of the present invention.

Claims

1. A simulation method for air conditioner operation detection data, characterized in that, include: Conduct operational tests on the air conditioner prototype and obtain test data; The test data is divided into test data corresponding to state parameters and test data corresponding to control parameters. The state parameters refer to parameters that reflect the operating state of the air conditioner, and the control parameters refer to parameters that control the operation of the air conditioner. An initial model is obtained based on the design requirements of the air conditioner. The test data corresponding to the control parameters are set as inputs, and the test data corresponding to the state parameters are set as outputs. The initial model is trained to obtain a simulation model. The design requirements of the air conditioner refer to the requirements for the functions and performance of the air conditioner before its development and manufacturing. A suggested air conditioner prototype is prepared based on the design requirements. Input control parameters into the simulation model, and the simulation model outputs simulation state parameters; After the simulation model outputs the simulation state parameters, the method further includes a fault simulation step: inputting the simulation state parameters into a fault detection model, which outputs whether the simulation state parameters are abnormal and the cause of the abnormality; wherein, the fault detection model needs to be verified before use, and the simulation state parameters obtained from the simulation model are used to verify it. The specific verification steps include: S1: Select simulation data with simulation state parameters within a certain range, and swap the simulation data corresponding to the two sets of simulation state parameters; swap the simulation data corresponding to the subcooler gas outlet temperature sensor and the subcooler liquid outlet temperature sensor. S2: Input the swapped simulation state parameters into the fault detection model. If the fault detection model determines that the simulation state parameters are abnormal and pops up a fault message "The temperature sensor bulbs of the subcooler gas outlet and the subcooler liquid outlet are reversed", it means that the fault detection model is effective and can be used to detect the simulation state parameters. If the fault detection model determines that the simulation state parameters are normal, or the pop-up fault message does not correspond, it means that the fault detection model is invalid and cannot be used to detect the simulation state parameters.

2. The simulation method for air conditioner operation detection data according to claim 1, characterized in that, The test data includes a test set and a training set. The training set is used to train the initial model, and the test set is used to test the similarity of the simulation models.

3. The simulation method for air conditioner operation detection data according to claim 2, characterized in that, Also includes: The correlation between control parameters and state parameters is calculated based on the test data, and the test correlation curve is obtained. The accuracy of the simulation model is determined by using the test set and correlation curves.

4. The simulation method for air conditioner operation detection data according to claim 3, characterized in that, The accuracy of the simulation model is determined using a test set and correlation curves, specifically including: After obtaining the simulation model, the test data corresponding to the control parameters in the test set are used as input, and the test data of the state parameters related to the control parameters in the test set are used as output. The simulation correlation curve is obtained using the simulation model. The simulation correlation curve and the test correlation curve are calculated relative to each other. If the similarity between the simulation correlation curve and the test correlation curve is greater than the preset value, the simulation model is output. If it is less than or equal to the preset value, the simulation model is retrained using the training set until the similarity between the simulation correlation curve and the test correlation curve is greater than the preset value.

5. The simulation method for air conditioner operation detection data according to claim 1, characterized in that, After acquiring the test data, the process also includes classifying the test data according to the model and obtaining a corresponding simulation model for each model.

6. The simulation method for air conditioner operation detection data according to claim 1, characterized in that, The initial model and simulation model include neural networks.

7. The simulation method for air conditioner operation detection data according to claim 1, characterized in that, After obtaining the simulation model, the tooling self-inspection step is also included: Establish standard formats for each control parameter; The format for writing the control parameter input is compared with the standard format. If the format does not match the standard format, the input format is judged to be incorrect, and the reason for the error is output. If the format matches the standard format, the input format is judged to be correct.

8. An electronic device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described in any one of claims 1-7.

9. A non-transitory machine-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method as described in any one of claims 1-7.

Images