Cloud server, first multi-split air conditioning system and control method of first multi-split air conditioning system

Abstract

The embodiment of the invention provides a cloud server, a first multi-split air conditioning system and a control method of the first multi-split air conditioning system, relates to the field of air conditioners, and is used for expanding the application range of fault detection of the multi-split air conditioning system and realizing cross-system fault detection. The cloud server comprises a processor configured to obtain real-time performance parameters and real-time condition parameters of a first multi-split air conditioning system; based on the real-time condition parameters, a target mode matched with the first multi-split air-conditioning system is determined from multiple modes of the second multi-split air-conditioning system, and first performance parameters of the first multi-split air-conditioning system in the normal operation state and second performance parameters of the second multi-split air-conditioning system in the normal operation state in the target mode are obtained; based on the first performance parameter and the second performance parameter in the target mode, converting the real-time performance parameter to obtain a third performance parameter; and inputting the third performance parameter into a fault detection model of the second multi-split air-conditioning system to obtain a fault detection result of the first multi-split air-conditioning system.

Description

Technical Field

[0001] The present application relates to the field of air-conditioning technology, and in particular to a cloud server, a first multi-split air-conditioning system and a control method thereof. Background Art

[0002] With the development of the economy and society, air conditioners are becoming more and more widely used in various places such as entertainment, home and work.

[0003] In recent years, with the continuous changes in air conditioner structures and application scenarios, the types of air conditioner failures have become increasingly diverse. To improve the accuracy and efficiency of air conditioner fault diagnosis, researchers have used machine learning, data mining, and other methods to build fault detection models, which has become a current research hotspot.

[0004] However, in practical applications, current data-driven fault detection models are mostly applicable only to specific types of air conditioners. Given the diversity of factors such as the number of indoor and outdoor units, and installation scenarios, data-driven fault detection methods cannot accurately detect faults in all types of air conditioners. Therefore, expanding the scope of air conditioner fault detection and enabling cross-system fault detection has become a pressing technical challenge. Summary of the Invention

[0005] The present application provides a cloud server, a first multi-split air-conditioning system and a control method thereof, which are used to expand the scope of application of fault detection of the multi-split air-conditioning system and realize cross-system fault detection.

[0006] In order to achieve the above objectives, this application adopts the following technical solutions.

[0007] In a first aspect, an embodiment of the present application provides a cloud server, which includes: a communicator for communicating with a first multi-split air-conditioning system; a processor, configured to: obtain real-time performance parameters, real-time condition parameters and first performance parameters of the first multi-split air-conditioning system under normal operating conditions, the real-time condition parameters are used to characterize the operating conditions of the first multi-split air-conditioning system, and the first performance parameters are used to characterize the performance of the first multi-split air-conditioning system; based on the real-time condition parameters, determine a target mode matching the first multi-split air-conditioning system from multiple modes of a second multi-split air-conditioning system, and obtain second performance parameters of the second multi-split air-conditioning system under normal operating conditions under the target mode, and the second performance parameters are used to characterize the performance of the second multi-split air-conditioning system; based on the first performance parameters and the second performance parameters under the target mode, convert the real-time performance parameters to obtain third performance parameters; input the third performance parameters into a fault detection model of the second multi-split air-conditioning system to obtain a fault detection result of the first multi-split air-conditioning system.

[0008] The technical solution provided by the embodiment of the present application provides at least the following beneficial effects: Due to the difference in the data distribution of the operating data of the first multi-split air-conditioning system and the data distribution of the operating data of the second multi-split air-conditioning system, the fault detection model of the second multi-split air-conditioning system is not applicable to the first multi-split air-conditioning system. However, the embodiment of the present application provides a cloud server that can, using the first performance parameters of the first multi-split air-conditioning system in normal operation and the first performance parameters of the second multi-split air-conditioning system in normal operation in a target mode, approximately convert the data distribution of the real-time performance parameters to be consistent with the data distribution of the operating data of the second multi-split air-conditioning system, that is, convert the real-time performance parameters into third performance parameters.

[0009] In this way, the converted third performance parameter meets the requirements of the fault detection model of the second multi-split air-conditioning system for input data, and can be input into the fault detection model of the second multi-split air-conditioning system as input data, thereby realizing the fault detection of the first multi-split air-conditioning system by the fault detection model of the second multi-split air-conditioning system.

[0010] This method effectively solves the challenges brought by the diversity of parameters of multi-split air-conditioning systems (such as the number of indoor units, the number of outdoor units, and the ratio of indoor and outdoor unit capacities), realizes the universality of fault detection models among different multi-split air-conditioning systems, and also realizes cross-system fault detection. It improves the problem of insufficient generalization ability of fault detection models in related technologies for multi-split air-conditioning systems, thereby expanding the scope of application of fault detection in multi-split air-conditioning systems and alleviating the difficulty in obtaining fault operation data of multi-split air-conditioning systems.

[0011] In some embodiments, the processor is configured to determine a target mode that matches the first multi-split air-conditioning system from multiple modes of the second multi-split air-conditioning system based on real-time condition parameters, including: determining the distance between the real-time condition parameters and the cluster centers corresponding to each of the multiple modes; wherein the cluster centers corresponding to each of the multiple modes are obtained by clustering calculation of the second condition parameters of the second multi-split air-conditioning system under different test environments, and the second condition parameters are used to characterize the operating conditions of the second multi-split air-conditioning system; and the mode corresponding to the cluster center closest to the first multi-split air-conditioning system is used as the target mode.

[0012] In some embodiments, the processor is configured to determine the distance between the real-time condition parameter and the cluster center corresponding to each of the multiple patterns, including: performing dimensionality reduction processing on the real-time condition parameter to obtain the processed real-time condition parameter; determining the distance between the processed real-time condition parameter and the cluster center corresponding to each of the multiple patterns.

[0013] In some embodiments, the processor is configured to convert the real-time performance parameter based on the second performance parameter of the second multi-split air-conditioning system in normal operating state under the target mode to obtain a third performance parameter, including: determining the deviation value between the first performance parameter and the second performance parameter under the target mode; based on the deviation value, converting the real-time performance parameter to obtain the third performance parameter.

[0014] In some embodiments, the processor is further configured to: send the fault detection result to the first multi-split air conditioning system via the communicator.

[0015] In some embodiments, the fault detection result is used to characterize whether there is a refrigerant leak in the first multi-split air-conditioning system; the first condition parameter includes at least one of the following: ambient temperature, speed gear of the outdoor fan, set temperature, actual operating frequency of the compressor and opening of the electronic expansion valve; the first performance parameter includes at least one of the following: compressor exhaust pressure, compressor suction temperature, compressor exhaust temperature, condensing pressure, evaporating pressure, compressor current, compressor suction superheat, compressor exhaust superheat, evaporating temperature and condensing temperature.

[0016] In a second aspect, an embodiment of the present application provides a first multi-split air-conditioning system, including: a communicator for communicating with a cloud server; a controller, configured to: obtain real-time performance parameters and real-time condition parameters of the first multi-split air-conditioning system, the real-time condition parameters being used to characterize the operating conditions of the first multi-split air-conditioning system; based on the real-time condition parameters, determine a target mode matching the first multi-split air-conditioning system from multiple modes of the second multi-split air-conditioning system, and obtain first performance parameters of the first multi-split air-conditioning system in normal operating conditions and second performance parameters of the second multi-split air-conditioning system in normal operating conditions under the target mode from the cloud server, the first performance parameters being used to characterize the performance of the first multi-split air-conditioning system, and the second performance parameters being used to characterize the performance of the second multi-split air-conditioning system; based on the first performance parameters and the second performance parameters under the target mode, convert the real-time performance parameters to obtain third performance parameters; input the third performance parameters into a fault detection model of the second multi-split air-conditioning system to obtain a fault detection result of the first multi-split air-conditioning system.

[0017] On the third aspect, an embodiment of the present application provides a control method for a multi-split air-conditioning system, which is applied to a cloud server. The method includes: obtaining real-time performance parameters, real-time condition parameters and first performance parameters of the first multi-split air-conditioning system under normal operating conditions, the real-time condition parameters are used to characterize the operating conditions of the first multi-split air-conditioning system, and the first performance parameters are used to characterize the performance of the first multi-split air-conditioning system; based on the real-time condition parameters, determining a target mode matching the first multi-split air-conditioning system from multiple modes of the second multi-split air-conditioning system, and obtaining the second performance parameters of the second multi-split air-conditioning system under normal operating conditions under the target mode, and the second performance parameters are used to characterize the performance of the second multi-split air-conditioning system; based on the first performance parameters and the second performance parameters under the target mode, converting the real-time performance parameters to obtain third performance parameters; inputting the third performance parameters into the fault detection model of the second multi-split air-conditioning system to obtain the fault detection results of the first multi-split air-conditioning system.

[0018] In a fourth aspect, an embodiment of the present application provides a control method for a multi-split air-conditioning system, which is applied to a first multi-split air-conditioning system, the method comprising: obtaining real-time performance parameters and real-time condition parameters of the first multi-split air-conditioning system, the real-time condition parameters being used to characterize the operating conditions of the first multi-split air-conditioning system; based on the real-time condition parameters, determining a target mode matching the first multi-split air-conditioning system from multiple modes of the second multi-split air-conditioning system, and obtaining first performance parameters of the first multi-split air-conditioning system in normal operating conditions and second performance parameters of the second multi-split air-conditioning system in normal operating conditions from a cloud server under the target mode, the first performance parameters being used to characterize the performance of the first multi-split air-conditioning system, and the second performance parameters being used to characterize the performance of the second multi-split air-conditioning system; based on the first performance parameters and the second performance parameters under the target mode, converting the real-time performance parameters to obtain third performance parameters; inputting the third performance parameters into a fault detection model of the second multi-split air-conditioning system to obtain a fault detection result of the first multi-split air-conditioning system.

[0019] In a fifth aspect, an embodiment of the present application provides a controller comprising: one or more processors; one or more memories; wherein the one or more memories are used to store computer program codes, the computer program codes comprising computer instructions, and when the one or more processors execute the computer instructions, the controller executes any one of the control methods for the multi-split air-conditioning system provided in the second aspect.

[0020] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, which includes computer instructions. When the computer instructions are executed on a computer, the computer executes any one of the control methods for the multi-split air-conditioning system provided in the second aspect.

[0021] In the seventh aspect, an embodiment of the present invention provides a computer program product, which can be directly loaded into a memory and contains software code. After being loaded and executed by a computer, the computer program product can implement any control method of a multi-split air-conditioning system provided in the second aspect.

[0022] It should be noted that the above-mentioned computer instructions may be stored in whole or in part on a computer-readable storage medium. The computer-readable storage medium may be packaged together with the processor of the controller or separately from the processor of the controller, and this application does not limit this.

[0023] The beneficial effects described in the second to seventh aspects of this application can be referred to the analysis of the beneficial effects of the first aspect and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0025] Figure 1 A schematic diagram of an application scenario provided in an embodiment of the present application;

[0026] Figure 2 A schematic diagram of the hardware structure of a cloud server provided in an embodiment of the present application;

[0027] Figure 3 A schematic diagram of the hardware structure of a multi-split air conditioning system provided in an embodiment of the present application;

[0028] Figure 4 A flow chart of a control method for a multi-split air conditioning system provided in an embodiment of the present application;

[0029] Figure 5 A flowchart of fault detection for a first multi-split air conditioning system provided in an embodiment of the present application;

[0030] Figure 6 A flow chart of another method for controlling a multi-split air conditioning system provided in an embodiment of the present application;

[0031] Figure 7 A schematic diagram of how the sum of squared errors varies with the number of clusters provided in an embodiment of the present application;

[0032] Figure 8 A schematic diagram showing how the cumulative contribution rate varies with the number of principal components provided in an embodiment of the present application;

[0033] Figure 9A flowchart of matching a target mode of a first multi-split air conditioning system provided in an embodiment of the present application;

[0034] Figure 10 A flow chart of another method for controlling a multi-split air conditioning system provided in an embodiment of the present application;

[0035] Figure 11 A schematic diagram of converting a first performance parameter of a first multi-split air conditioning system provided in an embodiment of the present application;

[0036] Figure 12 A schematic diagram of the composition of a first multi-split air conditioning system provided in an embodiment of the present application;

[0037] Figure 13 A schematic diagram of the composition of a second multi-split air conditioning system provided in an embodiment of the present application;

[0038] Figure 14 A schematic diagram of the detection accuracy of a fault detection model provided in an embodiment of the present application;

[0039] Figure 15 A flow chart of another method for controlling a multi-split air conditioning system provided in an embodiment of the present application;

[0040] Figure 16 A flowchart of another method for controlling a multi-split air conditioning system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0042] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0043] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0044] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "connected" and "connect" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances. Furthermore, when describing pipelines, the terms "connected" and "connected" used in this application have the meaning of conducting electricity. The specific meanings need to be understood in the context.

[0045] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0046] Currently, there are three main approaches to fault detection in VRF systems. The first is a rule-based approach, which establishes a rule table to determine whether the VRF system's historical operating data deviates from normal operating data. However, this approach is only effective when the parameters deviate significantly from normal operation and is ineffective for detecting minor faults. The second is a physical model-based approach, which establishes a physical model of the VRF system's circulation and compares the model's results with the VRF system's historical operating data. However, this approach suffers from complex system modeling and difficulty meeting the model's accuracy requirements in diverse scenarios. The third is a data-driven approach, which uses machine learning models (such as support vector machines, decision trees, and deep learning) to train historical data to learn the VRF system's operating patterns and predict faults such as refrigerant leaks based on real-time data. Although this approach has good diagnostic performance within a given system, due to the diversity of VRF systems in terms of the number of indoor and outdoor units, the capacity ratio of indoor and outdoor units, and installation scenarios, current data-driven approaches face challenges in generalization and cross-system detection portability, and cannot effectively address this diversity.

[0047] Based on this, an embodiment of the present application provides a control method for a multi-split air conditioning system. Because the data distribution of the operating data of a first multi-split air conditioning system differs from the data distribution of the operating data of a second multi-split air conditioning system, the fault detection model of the second multi-split air conditioning system is not applicable to the first multi-split air conditioning system. However, the method provided in the embodiment of the present application can use the first performance parameter of the first multi-split air conditioning system in normal operation under the target mode and the first performance parameter of the second multi-split air conditioning system in normal operation under the target mode to approximately convert the data distribution of the real-time performance parameter to be consistent with the data distribution of the operating data of the second multi-split air conditioning system, that is, to convert the real-time performance parameter into a third performance parameter.

[0048] In this way, the converted third performance parameter meets the requirements of the fault detection model of the second multi-split air-conditioning system for input data, and can be input into the fault detection model of the second multi-split air-conditioning system as input data, thereby realizing the fault detection of the first multi-split air-conditioning system by the fault detection model of the second multi-split air-conditioning system.

[0049] This method effectively solves the challenges brought by the diversity of parameters of multi-split air-conditioning systems (such as the number of indoor units, the number of outdoor units, and the ratio of indoor and outdoor unit capacities), realizes the universality of fault detection models among different multi-split air-conditioning systems, and also realizes cross-system fault detection. It improves the problem of insufficient generalization ability of fault detection models in related technologies for multi-split air-conditioning systems, thereby expanding the scope of application of fault detection in multi-split air-conditioning systems and alleviating the difficulty in obtaining fault operation data of multi-split air-conditioning systems.

[0050] In this application, the air conditioner performs a refrigeration cycle of the air conditioner by using a compressor, a condenser, an electronic expansion valve, an evaporator, and a four-way valve as a refrigerant circulation circuit. 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.

[0051] The compressor compresses low-temperature, low-pressure refrigerant gas and discharges the compressed, high-temperature, high-pressure refrigerant gas. The discharged refrigerant gas flows into the condenser. The condenser condenses the compressed refrigerant into a liquid phase, releasing heat into the surrounding environment through the condensation process.

[0052] The electronic expansion valve throttles the high-temperature, high-pressure liquid refrigerant condensed in the condenser to a low-pressure, two-phase refrigerant. The evaporator evaporates the refrigerant throttled by the electronic expansion valve and returns the low-temperature, low-pressure refrigerant gas to the compressor. The evaporator achieves cooling by utilizing the latent heat of evaporation to exchange heat with the medium being cooled. Throughout this cycle, the air conditioner regulates the indoor temperature.

[0053] The outdoor unit of the air conditioner refers to a portion of a refrigeration cycle including a compressor and an outdoor heat exchanger, the indoor unit of the air conditioner includes an indoor heat exchanger, and an expansion valve may be provided in the indoor unit or the outdoor unit.

[0054] The indoor heat exchanger and the outdoor heat exchanger function as a condenser or an evaporator. When the indoor heat exchanger functions as a condenser, the air conditioner functions as a heater in heating mode, and when the indoor heat exchanger functions as an evaporator, the air conditioner functions as a cooler in cooling mode.

[0055] Figure 1 This is a schematic diagram of an application scenario provided by this application according to an exemplary embodiment. Figure 1 As shown, the application scenario includes multiple multi-split air-conditioning systems, such as a first multi-split air-conditioning system 101 and a second multi-split air-conditioning system 102 , and a cloud server 103 .

[0056] There is a communication connection between the cloud server 103 and multiple multi-split air-conditioning systems.

[0057] In some embodiments, a multi-split air conditioning system is a device that regulates and controls parameters such as the temperature, humidity, and flow rate of the ambient air in a building or structure.

[0058] In some embodiments, the cloud server 103 can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, big data servers, etc. This application does not impose any special restrictions on the specific form of the cloud server 103.

[0059] In some embodiments, the multi-split air-conditioning system may send its own operating data to a cloud server so that the cloud server can detect faults of the multi-split air-conditioning system based on the operating data of the multi-split air-conditioning system.

[0060] Figure 2 This is a hardware structure diagram of a cloud server provided by this application according to an exemplary embodiment. Figure 2 As shown, the cloud server 103 includes a communicator 201 , a memory 202 and a processor 203 .

[0061] In some embodiments, the communicator 201 is used to establish a communication connection with other network entities, for example, to establish a communication connection with the first multi-split air conditioning system 101. The communicator 201 may include a radio frequency (RF) module, a cellular module, a wireless fidelity (WIFI) module, and a GPS module, etc. Taking the RF module as an example, the RF module can be used to receive and send signals, in particular, to send the received information to the processor 203 for processing; in addition, the signal generated by the processor 203 is sent out. Typically, the RF circuit may include but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, etc.

[0062] In some embodiments, the memory 202 can be used to store software programs and data. The processor 203 executes various functions and data processing of the cloud server 103 by running the software programs or data stored in the memory 202. The memory 202 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. The memory 202 stores an operating system that enables the processor 203 to run. In the present application, the memory 202 can store the operating system and various application programs, and may also store code for executing the control method of the multi-split air conditioning system provided in the embodiments of the present application.

[0063] In some embodiments, the processor 203 can be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present disclosure, such as one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs).

[0064] Those skilled in the art will understand that Figure 2 The hardware structure shown in the figure does not constitute a limitation on the cloud server. The cloud server may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0065] Figure 3This is a hardware structure diagram of a multi-split air conditioning system provided by this application according to an exemplary embodiment. It should be noted that the multi-split air conditioning systems of different models involved in the embodiments of this application are all based on Figure 1 The structural diagram of the multi-split air-conditioning system shown in FIG.

[0066] like Figure 3 As shown, the multi-split air conditioning system includes multiple indoor units 301 , outdoor units 302 and a controller 303 .

[0067] Indoor unit 301, taking indoor unit 301 as an indoor hanging unit as an example, indoor hanging units are usually installed on indoor walls, etc. For another example, indoor cabinet units are also a type of indoor unit form of indoor units.

[0068] The outdoor unit 302 is usually arranged outdoors and can be connected to a plurality of indoor units 101 for indoor heat exchange. In addition, the outdoor unit 302 is usually located outdoors on the opposite side of the indoor unit 301 across a wall.

[0069] In some embodiments, the controller 303 is a device that can generate an operation control signal based on an instruction opcode and a timing signal to instruct the multi-split air conditioning system to execute the control instruction. For example, the controller can be a central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The controller can also be other devices with processing functions, such as circuits, devices, or software modules, and the embodiments of the present application do not impose any limitations on this.

[0070] In addition, both the outdoor unit 302 and the indoor unit 301 are in communication with the controller 303 and perform related operations according to instructions of the controller 303 .

[0071] The following is a detailed introduction to the embodiments provided in this application in conjunction with the accompanying drawings.

[0072] like Figure 4 As shown, an embodiment of the present application provides a control method for a multi-split air conditioning system, which is applied to a cloud server. The method includes the following steps:

[0073] S101. The cloud server obtains real-time performance parameters and real-time condition parameters of a first multi-split air-conditioning system.

[0074] The real-time condition parameter is used to characterize the operating condition of the first multi-split air-conditioning system, and the real-time performance parameter is used to characterize the performance of the first multi-split air-conditioning system.

[0075] In some embodiments, the real-time condition parameter may include at least one of the following: ambient temperature, speed level of the outdoor fan, set temperature, actual operating frequency of the compressor, and opening of the electronic expansion valve. The first performance parameter may include at least one of the following: compressor discharge pressure, compressor suction temperature, compressor discharge temperature, condensing pressure, evaporating pressure, compressor current, compressor suction superheat, compressor discharge superheat, evaporating temperature, and condensing temperature.

[0076] In some embodiments, real-time condition parameters and real-time performance parameters are determined based on the real-time operating data of the first multi-split air-conditioning system, and real-time fault detection can be performed on the first multi-split air-conditioning system so that faults can be detected in the early stages of the first multi-split air-conditioning system, thereby preventing system operation from deteriorating and reducing energy waste.

[0077] Exemplarily, the acquisition of real-time performance parameters and real-time condition parameters can be implemented as follows:

[0078] Step a1: The cloud server obtains real-time operating data of the first multi-split air-conditioning system from the memory.

[0079] In some embodiments, the real-time operating data of the first multi-split air-conditioning system is operating data in an unknown operating state (faulty operating state or normal operating state).

[0080] Step a2: extracting steady-state operation data from the real-time operation data.

[0081] It is understandable that since a large amount of transient data exists in the real-time operating data obtained for the first multi-split air-conditioning system, such as the operating data during the start-up and shutdown process of the first multi-split air-conditioning system and the operating data during the four-way valve reversing process, the existence of transient data increases the difficulty of adapting the fault detection model of the second multi-split air-conditioning system to the first multi-split air-conditioning system. Therefore, it is necessary to perform steady-state screening on the real-time operating data of the first multi-split air-conditioning system to remove transient data.

[0082] In some embodiments, the cloud server may determine whether the first multi-split air-conditioning system has reached a stable operating state based on the operating frequency of the compressor and the exhaust pressure of the compressor.

[0083] Furthermore, when the first multi-split air conditioning system is in a stable operating state, the real-time operating data of the first multi-split air conditioning system is steady-state operating data. In this way, the steady-state operating data can be extracted from the real-time operating data of the first multi-split air conditioning system.

[0084] Optionally, the cloud server can use a sliding window algorithm to calculate the slope of the operating frequency of the compressor and the slope of the exhaust pressure of the compressor within the sliding window according to a preset window length to measure the rate of change of the real-time operating data of the first multi-split air-conditioning system.

[0085] Furthermore, when the rate of change is within a preset range, it is determined that the first multi-split air-conditioning system has reached a stable operating state, and the real-time operating data of the first multi-split air-conditioning system within the sliding window can be determined as steady-state operating data.

[0086] When the absolute value of the change rate is outside the preset range, it is determined that the first multi-split air-conditioning system has not reached a stable operating state, and the real-time operating data of the first multi-split air-conditioning system within the sliding window can be deleted.

[0087] Optionally, the default range is [0, k].

[0088] For example, the step size of each sliding operation is set to the preset sliding window length L. Initially, the cloud server can use the least squares method or other linear regression method to fit the linear relationship between the real-time operating data in the current sliding window, such as the equation y = kx + b. The slope k is the rate of change of the real-time operating data within the sliding window. Next, based on the absolute value of this rate of change, it is determined whether the real-time operating data of the first multi-split air conditioning system within the sliding window should be deleted.

[0089] Next, the sliding window is slid backward by a step length, and the above steps are repeated until all the real-time operation data of the first multi-split air-conditioning system are processed to obtain steady-state data.

[0090] Step a3: extracting multiple characteristic parameters of the first multi-split air-conditioning system from the steady-state operation data.

[0091] Step a4: Divide the multiple characteristic parameters of the first multi-split air-conditioning system into real-time condition parameters and real-time performance parameters.

[0092] It can be understood that dividing the multiple characteristic parameters of the first multi-split air-conditioning system into condition parameters and performance parameters can better control the operation of the first multi-split air-conditioning system.

[0093] In some embodiments, since the capacities of different indoor units in the first multi-split air-conditioning system are different, the real-time condition parameters and real-time performance parameters of the first multi-split air-conditioning system can also be weighted averaged based on the capacity of the indoor units to better consider the performance of the entire multi-split air-conditioning system, rather than considering the performance of each indoor unit individually.

[0094] Similarly, the first condition parameters and performance parameters of the first multi-split air-conditioning system under different test environments can also be weighted averaged, and the first condition parameters and performance parameters of the second multi-split air-conditioning system under different test environments also need to be weighted averaged.

[0095] Exemplarily, the cloud server may perform weighted averaging of the real-time performance parameters and the real-time condition parameters of the first multi-split air-conditioning system based on the following formula (1).

[0096]

[0097] Among them, m avg is the real-time condition parameter or real-time performance parameter of the first multi-split air-conditioning system after weighted average; n is the total number of indoor units in the first multi-split air-conditioning system; m i is the value of the real-time condition parameter or real-time performance parameter of the i-th indoor unit in the first multi-split air-conditioning system; status i is the on state of the i-th indoor unit in the first multi-split air-conditioning system; capacity is the rated capacity of the i-th indoor unit in the first multi-split air-conditioning system.

[0098] S102: The cloud server determines, based on the real-time condition parameter, a target mode that matches the first multi-split air conditioning system from the multiple modes of the second multi-split air conditioning system, and obtains a first performance parameter of the first multi-split air conditioning system under normal operation and a second performance parameter of the second multi-split air conditioning system under normal operation under the target mode. The first performance parameter is used to characterize the performance of the first multi-split air conditioning system, and the second performance parameter is used to characterize the performance of the second multi-split air conditioning system.

[0099] In some embodiments, different operating conditions may correspond to different modes, and further, a target mode matching the first multi-split air-conditioning system may be determined based on real-time condition parameters.

[0100] In some embodiments, the mode of the second multi-split air conditioning system is determined by multiple parameters, such as set temperature, indoor and outdoor temperature, number of indoor units on, etc. Changes in these parameters may result in different modes of the second multi-split air conditioning system.

[0101] For example, the second multi-split air conditioning system is a one-to-five (i.e., one outdoor unit connected to five indoor units) multi-split air conditioning system. The second multi-split air conditioning system was tested under six experimental operating conditions with refrigerant charge levels of 60%, 70%, 80%, 90%, and 100%. During the experiments, the number of indoor units operating was 1, 3, and 5, respectively. Table 1 below lists 90 different operating modes of the second multi-split air conditioning system under these experiments.

[0102] Table 1

[0103]

[0104] Similarly, the mode of the first multi-split air conditioning system is also determined by multiple parameters.

[0105] For example, the first multi-split air conditioning system is a one-to-three (i.e., one outdoor unit connected to three indoor units) multi-split air conditioning system. The first multi-split air conditioning system was tested under six experimental operating conditions with refrigerant charge levels of 70% and 100%. During the experiments, the number of indoor units operating was 1, 2, and 3, respectively. Table 2 below lists the 36 different operating modes of the first multi-split air conditioning system under these experiments.

[0106] Table 2

[0107]

[0108] In some embodiments, the cloud server may cluster the real-time condition parameters based on a clustering algorithm to determine a target mode that matches the first multi-split air-conditioning system.

[0109] In one example, the cloud server may determine a target mode that matches the first multi-split air-conditioning system based on the distance between the real-time condition parameters and the cluster centers corresponding to the multiple modes of the second multi-split air-conditioning system.

[0110] Among them, the cluster centers corresponding to the multiple modes of the second multi-split air-conditioning system are obtained by clustering calculation of the second conditional parameters of the second multi-split air-conditioning system under different test environments, and the second conditional parameters are used to characterize the operating conditions of the second multi-split air-conditioning system.

[0111] Similarly, the cloud server can also perform cluster calculation based on the first conditional parameters of the first multi-split air-conditioning system under different test environments to obtain multiple modes of the first multi-split air-conditioning system, and the first conditional parameters are used to characterize the operating conditions of the first multi-split air-conditioning system.

[0112] For example, the specific process of determining the target mode that matches the first multi-split air conditioning system can refer to the following Figure 6 The embodiments shown are not described in detail here.

[0113] In some embodiments, after determining the target mode that matches the first multi-split air-conditioning system, the cloud server can obtain the first performance parameters of the first multi-split air-conditioning system under normal operating conditions and the second performance parameters of the second multi-split air-conditioning system under normal operating conditions under the target mode.

[0114] Exemplarily, taking obtaining the second performance parameter as an example, the cloud server may obtain the cluster to which the cluster center corresponding to the target mode belongs, and the cluster includes at least one second condition parameter of the second multi-split air-conditioning system.

[0115] Furthermore, the cloud server may select any second conditional parameter of a second multi-split air-conditioning system from the cluster as the second conditional parameter in the target mode.

[0116] Then, based on the second condition parameter, the cloud server may use the second performance parameter corresponding to the second condition parameter as the second performance parameter of the second multi-split air-conditioning system in normal operation under the target mode.

[0117] It is understandable that within a given mode, a multi-split air conditioning system can operate in both a normal operating state and a faulty operating state. Therefore, each conditional parameter can correspond to a performance parameter of the multi-split air conditioning system in both a faulty operating state and a normal operating state. In other words, a conditional parameter corresponds to both a performance parameter of the multi-split air conditioning system in both a faulty state and a normal operating state. Similarly, the specific process for obtaining the second performance parameter described above can also be referred to for obtaining the first performance parameter, which is not detailed in this application.

[0118] S103: The cloud server converts the real-time performance parameter based on the first performance parameter and the second performance parameter in the target mode to obtain a third performance parameter.

[0119] It is understandable that the third performance parameter is derived through processing and analysis, rather than collected by a cloud server. Since faulty operating data is difficult to obtain, the difference between the operating data of the first multi-split air conditioning system in normal operation and the operating data of the second multi-split air conditioning system in normal operation under the target mode can be used to infer the operating data of the first multi-split air conditioning system in faulty operation based on the operating data of the second multi-split air conditioning system in faulty operation, thereby alleviating the difficulty in obtaining faulty data.

[0120] Furthermore, since the data distribution of the operating data of the first multi-split air conditioning system differs from that of the second multi-split air conditioning system, the fault detection model for the second multi-split air conditioning system is not applicable to the first multi-split air conditioning system. By using the data difference between the first performance parameter of the first multi-split air conditioning system in normal operation under the target mode and the first performance parameter of the second multi-split air conditioning system in normal operation, the data distribution of the real-time performance parameter can be approximately transformed to be consistent with the data distribution of the operating data of the second multi-split air conditioning system, that is, the real-time performance parameter can be converted into a third performance parameter.

[0121] In this way, the converted third performance parameter can be input as input data into the fault detection model of the second multi-split air-conditioning system, realizing the fault detection of the first multi-split air-conditioning system by the fault detection model of the second multi-split air-conditioning system, that is, fault detection across multi-split air-conditioning systems, broadening the scope of application of the fault detection model of the multi-split air-conditioning system.

[0122] In some embodiments, the cloud server may convert the real-time performance parameter based on a preset relationship to obtain a third performance parameter.

[0123] Among them, the preset relationship includes, in the target mode, the relationship between the second performance parameters of the second multi-split air-conditioning system in a fault state, the second performance parameters of the second multi-split air-conditioning system in a normal operating state, the first performance parameters of the first multi-split air-conditioning system in a normal operating state, and the first performance parameters of the first multi-split air-conditioning system in a fault operating state.

[0124] Optionally, the preset relationship may be: in the target mode, the deviation value between the second performance parameter of the second multi-split air-conditioning system under normal operating conditions and the first performance parameter of the first multi-split air-conditioning system under normal operating conditions is approximately equal to the deviation value between the second performance parameter of the second multi-split air-conditioning system under fault conditions and the first performance parameter of the first multi-split air-conditioning system under fault operating conditions.

[0125] Moreover, when the first multi-split air-conditioning system is in a faulty operating state and the second multi-split air-conditioning system is in a faulty operating state, the product of the deviation value between the second performance parameter of the second multi-split air-conditioning system in a normal operating state and the second performance parameter of the second multi-split air-conditioning system in a faulty operating state and the deviation value between the first performance parameter of the first multi-split air-conditioning system in a normal operating state and the first performance parameter of the first multi-split air-conditioning system in a faulty operating state is a positive number.

[0126] Exemplarily, the preset relationship may satisfy the following formula (2) and formula (3).

[0127]

[0128]

[0129] Where f(x, y) is the deviation function, which is used to return the deviation value between x and y; is the average value of the first performance parameter of the first multi-split air-conditioning system under normal operating conditions; is the mean value of the second performance parameter of the second multi-split air-conditioning system in the faulty operating state; is the mean value of the first performance parameter of the first multi-split air-conditioning system in a faulty operating state; is the average value of the second performance parameter of the second multi-split air-conditioning system under normal operating conditions.

[0130] Exemplarily, the cloud server can combine the preset relationship and convert the real-time performance parameters according to the deviation between the second performance parameters of the second multi-split air-conditioning system under normal operating conditions in the target mode and the first performance parameters of the first multi-split air-conditioning system under normal operating conditions to obtain the third performance parameters.

[0131] In addition, regarding the specific conversion process of the first performance parameter of the first multi-split air conditioning system under normal operating conditions, please refer to the following Figure 10 The embodiments shown in this application will not be described in detail here.

[0132] S104. The cloud server inputs the third performance parameter into the fault detection model of the second multi-split air-conditioning system to obtain a fault detection result of the first multi-split air-conditioning system.

[0133] Optionally, the fault detection result may be used to indicate whether there is a refrigerant leak in the first multi-split air-conditioning system.

[0134] It is understood that the performance parameter reflects the actual working condition of the multi-split air conditioning system, which helps to detect faults and guide the optimization and maintenance of the multi-split air conditioning system. Therefore, the fault detection result of the first multi-split air conditioning system can be determined based on the third performance parameter.

[0135] In some embodiments, before inputting the third performance parameter into the fault detection model of the second multi-split air-conditioning system, the cloud server may normalize the third performance parameter to eliminate the dimensional differences between different variables in the third performance parameter, so that the third performance parameter is at the same order of magnitude, so as to improve the convergence speed of the fault detection model.

[0136] Optionally, the cloud server may normalize the third performance parameter based on the following formula (4).

[0137]

[0138] Among them, x new is the third performance parameter after normalization; x min is the minimum value of the third performance parameter; x max is the maximum value of the third performance parameter; x is the third performance parameter before normalization.

[0139] In some embodiments, after obtaining the fault detection result of the first multi-split air-conditioning system, the cloud server may also send the fault detection result to the first multi-split air-conditioning system through the communicator.

[0140] In some embodiments, the training process of the fault detection model of the second multi-split air-conditioning system can be implemented as follows.

[0141] Step b1: The cloud server trains a fault detection model based on the historical operating data of the second multi-split air-conditioning system to obtain a trained fault detection model.

[0142] In some embodiments, the cloud server may select a data-driven model such as a random forest, a support vector machine, or a convolutional neural network for training to establish a fault detection model for the first air conditioner.

[0143] Step b2: The cloud server optimizes the hyperparameters in the fault detection model based on the grid search method and the n-fold cross-validation method to obtain an optimized hyperparameter combination.

[0144] For example, taking the example that the hyperparameters a and b have three possible values, nine hyperparameter combinations can be obtained.

[0145] Next, the training sample set, constructed based on the historical operating data of the second multi-split air conditioning system, is divided into n subsets. For each hyperparameter combination, n-1 subsets of the n subsets are used as training sets to train the fault detection model determined based on the current hyperparameter combination. The remaining subset of the n subsets is used as a test set to evaluate the performance of the trained fault detection model. This process is repeated n times until every subset of the n subsets has been used as a test set.

[0146] Then, the results of n performance evaluations are averaged as the performance indicator for each hyperparameter combination.

[0147] Finally, the hyperparameter combination with the largest performance index is taken as the optimized hyperparameter combination.

[0148] Step b3: Adjust the trained fault detection model based on the optimized hyperparameter combination to obtain an adjusted fault detection model.

[0149] In some embodiments, the obtained optimized hyperparameter combination is applied to a fault detection model.

[0150] The complete fault detection process of the first multi-split air conditioning system is exemplarily described below.

[0151] like Figure 5 As shown, the historical operation data of the second multi-split air-conditioning system can be obtained, and after normalizing the historical operation data, the fault detection model is trained, and the hyperparameters of the fault detection model are optimized to obtain the optimized fault detection model.

[0152] Next, real-time performance parameters of the first multi-split air conditioning system can be obtained and converted to obtain third performance parameters. After normalization, the third performance parameters are input into the optimized fault detection model to obtain fault detection results. Based on the fault detection results, corresponding manual decisions can be made or control optimization of the first multi-split air conditioning system can be performed.

[0153] based on Figure 4 In the illustrated embodiment, due to the difference in the data distribution of the operating data of the first multi-split air conditioning system and the second multi-split air conditioning system, the fault detection model for the second multi-split air conditioning system is not applicable to the first multi-split air conditioning system. However, the method provided in the embodiment of the present application can use the first performance parameter of the first multi-split air conditioning system in normal operation under the target mode and the first performance parameter of the second multi-split air conditioning system in normal operation under the target mode to approximately convert the data distribution of the real-time performance parameter to be consistent with the data distribution of the operating data of the second multi-split air conditioning system, that is, to convert the real-time performance parameter into a third performance parameter.

[0154] In this way, the converted third performance parameter meets the requirements of the fault detection model of the second multi-split air-conditioning system for input data, and can be input into the fault detection model of the second multi-split air-conditioning system as input data, thereby realizing the fault detection of the first multi-split air-conditioning system by the fault detection model of the second multi-split air-conditioning system.

[0155] In some embodiments, in order to determine the mode of the first multi-split air conditioning system, such as Figure 6 As shown, step S102 can be implemented as follows.

[0156] S201. The cloud server determines the distance between the first condition parameter and the cluster centers corresponding to each of the multiple patterns.

[0157] In some embodiments, the cloud server may cluster the second conditional parameters of the second multi-split air-conditioning system under different test environments based on a clustering algorithm to obtain cluster centers corresponding to multiple modes of the second multi-split air-conditioning system.

[0158] Optionally, the clustering algorithm may be a k-means clustering algorithm, a k-means++ algorithm, a DBSCAN algorithm, or the like.

[0159] Exemplarily, based on the k-means clustering algorithm, the calculation of the cluster centers corresponding to the multiple patterns can be implemented as follows.

[0160] Step c1: Calculate the distances from each of the second conditional parameters of the second multi-split air-conditioning system under different test environments to k initial cluster centers.

[0161] In some embodiments, the number k of initial cluster centers may be determined based on the elbow rule.

[0162] It should be noted that the sum of squared errors (also known as the degree of distortion) is calculated by summing the squares of the distances between each first conditional parameter and the cluster center within a cluster. For each cluster, a lower sum of squared errors indicates a closer cluster, while a higher degree of distortion indicates a looser cluster. The sum of squared errors decreases as the number of cluster centers increases. However, for discriminative data, the sum of squared errors slowly decreases when it reaches a certain critical point. This critical point can be considered the point of good clustering performance, indicating a more appropriate number of cluster centers.

[0163] For example, Figure 7 As shown in the figure, after the number of cluster centers reaches 20, the sum of squared errors gradually stabilizes, so the number of cluster centers can be set to 20.

[0164] Step c2: Divide each second condition parameter into the cluster to which the cluster center closest to the second condition parameter belongs.

[0165] Step c3: Update the cluster center of each cluster.

[0166] In some embodiments, the mean of all second condition parameters in each cluster may be used as the updated cluster center.

[0167] Step c4: Repeat steps c2 and c3 until a preset stop condition is reached.

[0168] Optionally, the preset stopping condition includes any one of the following: the number of iterations reaches a preset maximum number; the sum of squared errors is less than a set error value.

[0169] In some embodiments, before clustering the second conditional parameters of the second multi-split air-conditioning system under different test environments, the cloud server may further perform dimensionality reduction processing on the second conditional parameters to reduce redundancy between parameters, thereby enabling better clustering.

[0170] Optionally, the cloud server may perform dimensionality reduction processing on the first conditional parameter based on a dimensionality reduction method such as principal component analysis, linear discriminant analysis, multidimensional scaling analysis, isometric mapping, or t-distributed random neighbor embedding.

[0171] For example, taking the first condition parameter including n pieces of m-dimensional data as an example, the dimensionality reduction processing of the first condition parameter based on the principal component analysis method can be implemented as follows:

[0172] Step d1: Arrange the first conditional parameters into a matrix X with n rows and m columns.

[0173] Step d2: Zero-mean each row of the matrix X, that is, subtract the mean of this row;

[0174] Step d3, calculate the covariance matrix C = (XXT) / m;

[0175] Step d4, finding the eigenvalues ​​and corresponding eigenvectors of the covariance matrix;

[0176] Step d5: Arrange the eigenvalues ​​in reverse order of size, and calculate the ratio of each eigenvalue to the total eigenvalue (ie, the variance contribution rate).

[0177] Step d6: Determine the number k of principal components to be retained so that the cumulative variance contribution rate is close to 1, that is, select the first k eigenvalues ​​so that the cumulative variance contribution rate reaches the set threshold.

[0178] In some embodiments, before determining the distance between the first conditional parameter and the cluster centers corresponding to each of the multiple modes, the cloud server may also perform dimensionality reduction processing on the first conditional parameter to obtain the processed first conditional parameter, so that the dimension of the processed first conditional parameter is the same as the dimension of the second conditional parameter of the second multi-split air-conditioning system under different test environments.

[0179] In addition, regarding the specific dimensionality reduction process of the first conditional parameter, reference can be made to the above-mentioned specific description of dimensionality reduction of the second conditional parameter of the second multi-split air-conditioning system under different test environments, which will not be elaborated in this application.

[0180] For example, Figure 8 As shown in Figure 2, when the number of principal components k=4, the cumulative variance contribution rate is close to 1.

[0181] Step d7: Arrange the eigenvectors into a matrix P by row from top to bottom according to the corresponding eigenvalues, and take the first k rows to form the matrix P_k.

[0182] Step d8: Calculate the data matrix after dimensionality reduction Y=PX_k, where Y is the first conditional parameter after dimensionality reduction to k dimensions.

[0183] In some embodiments, after performing dimensionality reduction processing on the first condition parameter, the cloud server may determine the distance between the processed first condition parameter and the cluster centers corresponding to each of the multiple patterns.

[0184] Optionally, the cloud server can select Euclidean distance, Manhattan distance, cosine similarity, etc. as the distance metric.

[0185] S202: The cloud server uses the pattern corresponding to the nearest cluster center as the target pattern.

[0186] It is understandable that the closer the distance is, the higher the similarity between the first condition parameter and other condition parameters in the cluster to which the cluster center belongs, and the cluster to which the cluster center belongs. Therefore, the pattern corresponding to the cluster center with the closest distance can be used as the target pattern.

[0187] The following is an exemplary description of the completion determination process of the mode of the first multi-split air conditioning system.

[0188] like Figure 9 As shown, the cloud server can determine the dimensionality reduction of the second conditional parameter (hereinafter referred to as the second conditional parameter for ease of description) of the second multi-split air-conditioning system under different test environments based on the cumulative variance contribution rate. Then, based on the dimensionality reduction algorithm, the second conditional parameter is subjected to dimensionality reduction processing. Next, based on the elbow rule, the number of clustering centers of the second conditional parameter is determined, and then based on the clustering algorithm, the second conditional parameter is clustered to obtain the patterns corresponding to the multiple clustering centers, and a pattern classification model is established based on the clustering results to perform pattern recognition on the first conditional parameter of the first multi-split air-conditioning system.

[0189] Similarly, the cloud server can also perform dimensionality reduction processing on the first conditional parameter of the first multi-split air-conditioning system, and determine the target mode that matches the first multi-split air-conditioning system from the multiple modes of the second multi-split air-conditioning system based on the distance between the first conditional parameter and the cluster centers corresponding to the multiple modes.

[0190] In some embodiments, to obtain a third performance parameter, such as Figure 10 As shown, the embodiment of the present application further provides a method for controlling a multi-split air-conditioning system, that is, step S103 can be implemented as the following steps.

[0191] S301. The cloud server determines a deviation value between a first performance parameter and a second performance parameter in a target mode.

[0192] For example, in the target mode, taking the first performance parameter of the first multi-split air-conditioning system under normal operating conditions as a compressor exhaust temperature of 60°C, and the second performance parameter of the second multi-split air-conditioning system under normal operating conditions as an exhaust temperature of 70°C as an example, in the target mode under normal operating conditions, the deviation value between the first performance parameter and the second performance parameter is 70°C-60°C=10°C.

[0193] S302. The cloud server converts the real-time performance parameter based on the deviation value to obtain a third performance parameter.

[0194] In some embodiments, the cloud server may substitute the deviation value and the real-time performance parameter into the above formula (2) to obtain a third performance parameter.

[0195] For example, in the target mode, taking the first performance parameter of the first multi-split air-conditioning system under normal operating conditions as a compressor exhaust temperature of 60°C, and the second performance parameter of the second multi-split air-conditioning system under normal operating conditions as an exhaust temperature of 70°C, and the second performance parameter of the first multi-split air-conditioning system under an unknown operating state (fault operating state or normal operating state) as an exhaust temperature of 90°C, the third performance parameter is 90°C+10°C=100°C.

[0196] It should be noted that the execution entity in the above steps S101 to S104, the above steps S201 to S202 and the above steps S301 to S302 may be a processor of the cloud server.

[0197] The specific process of determining the third performance parameter is exemplified below.

[0198] like Figure 11 As shown, the cloud server can calculate the deviation value between the first performance parameter and the second performance parameter in the target mode, and then transform the real-time performance parameter based on the deviation value to obtain the third performance parameter.

[0199] The feasibility of a control method for a multi-split air conditioning system provided in an embodiment of the present application is exemplarily described below.

[0200] For example, Figure 12 As shown in the figure, the first multi-split air conditioning system uses an 8kW (three-horsepower) outdoor unit and adopts a one-to-three connection scheme with a connection ratio of 107%. Figure 13 As shown in the figure, the second multi-split air conditioning system uses a 16kW (six-horsepower) outdoor unit, adopts a one-to-five connection scheme, and the connection ratio is 115%. Figure 14 As shown, using the methods described in the above embodiments, the fault detection models trained using data-driven models such as random forests, support vector machines, and convolutional neural networks achieved detection accuracy rates of 95.8%, 93.2%, and 85.6%, respectively. The fault detection model trained using the random forest data-driven model achieved a detection accuracy rate exceeding 95%, meeting practical application requirements and demonstrating the feasibility of the methods described in the above embodiments.

[0201] The following is an illustrative description of the complete process of a control method for a multi-split air conditioning system provided in an embodiment of the present application.

[0202] like Figure 15As shown, steady-state data extraction and weighted averaging are performed on the second performance parameters of the second multi-split air conditioning system under normal operation, the second performance parameters under faulty operation, and the second conditional parameters of the second multi-split air conditioning system under different test environments. Next, dimensionality reduction is performed on the processed second conditional parameters of the second multi-split air conditioning system under different test environments, and the reduced second conditional parameters are clustered to obtain multiple cluster centers.

[0203] Simultaneously, the real-time condition parameters and real-time performance parameters of the first multi-split air conditioning system are similarly subjected to steady-state data extraction and weighted averaging. Next, the real-time condition parameters are dimensionality reduced to align with the dimensions of the second condition parameters. Pattern matching is then performed based on the distances between the real-time condition parameters and multiple cluster centers to obtain a target pattern that matches the first multi-split air conditioning system. Within the same target pattern, the real-time performance parameters are transformed based on the deviation between the first and second performance parameters to obtain a third performance parameter.

[0204] Next, after normalizing the third performance parameter, the parameter is input into a fault detection model established and optimized based on historical operation data of the second multi-split air-conditioning system to obtain a target detection result.

[0205] In some embodiments, as Figure 16 As shown, an embodiment of the present application further provides a control method for a multi-split air-conditioning system, which is applied to a first multi-split air-conditioning system. The method can be implemented as follows.

[0206] S401: The first multi-split air-conditioning system obtains real-time performance parameters and real-time condition parameters of the first multi-split air-conditioning system.

[0207] The real-time condition parameter is used to characterize the operating condition of the first multi-split air-conditioning system, and the real-time performance parameter is used to characterize the performance of the first multi-split air-conditioning system.

[0208] S402. The first multi-split air-conditioning system determines a target mode that matches the first multi-split air-conditioning system from multiple modes of the second multi-split air-conditioning system based on real-time condition parameters, and obtains first performance parameters of the first multi-split air-conditioning system under normal operating conditions and second performance parameters of the second multi-split air-conditioning system under normal operating conditions under the target mode.

[0209] The first performance parameter is used to characterize the performance of the first multi-split air-conditioning system, and the second performance parameter is used to characterize the performance of the second multi-split air-conditioning system.

[0210] S403: The first multi-split air conditioning system converts the real-time performance parameter based on the first performance parameter and the second performance parameter in the target mode to obtain a third performance parameter.

[0211] S404. The first multi-split air-conditioning system sends the third performance parameter to the cloud server, so that the cloud server inputs the third performance parameter into the fault detection model of the second multi-split air-conditioning system to obtain the fault detection result of the first multi-split air-conditioning system.

[0212] In addition, regarding the above steps S401 to S404, reference may be made to the specific descriptions in the above steps S101 to S104, the above steps S201 to S202, and the above steps S301 to S302, and this application will not elaborate on them here.

[0213] It should be noted that the execution entity of the above steps S401 to S404 may be the controller of the first multi-split air-conditioning system.

[0214] Those skilled in the art will appreciate that in one or more of the above examples, the functions described herein can be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0215] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0216] The above is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or replacements within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A cloud server, characterized in that: include: a communicator, configured to communicate with the first multi-split air conditioning system; The processor is configured to: Acquire real-time performance parameters and real-time condition parameters of the first multi-split air-conditioning system, wherein the real-time condition parameters are used to characterize the operating conditions of the first multi-split air-conditioning system, and the real-time performance parameters are used to characterize the performance of the first multi-split air-conditioning system; Based on the real-time condition parameter, determining a target mode that matches the first multi-split air-conditioning system from multiple modes of the second multi-split air-conditioning system, and obtaining a first performance parameter of the first multi-split air-conditioning system in a normal operating state and a second performance parameter of the second multi-split air-conditioning system in a normal operating state under the target mode, the first performance parameter being used to characterize the performance of the first multi-split air-conditioning system, and the second performance parameter being used to characterize the performance of the second multi-split air-conditioning system; Converting the real-time performance parameter based on the first performance parameter and the second performance parameter in the target mode to obtain a third performance parameter; The third performance parameter is input into the fault detection model of the second multi-split air-conditioning system to obtain a fault detection result of the first multi-split air-conditioning system.

2. The cloud server according to claim 1, wherein: The processor is configured to determine, based on the real-time condition parameter, a target mode that matches the first multi-split air-conditioning system from a plurality of modes of the second multi-split air-conditioning system, including: determining a distance between the real-time condition parameter and the cluster centers corresponding to each of the multiple modes; wherein the cluster centers corresponding to each of the multiple modes are obtained by clustering and calculating second condition parameters of the second multi-split air conditioning system under different test environments, the second condition parameters being used to characterize the operating conditions of the second multi-split air conditioning system; The pattern corresponding to the nearest cluster center is used as the target pattern.

3. The cloud server according to claim 2, wherein: The processor is configured to determine the distance between the real-time condition parameter and the cluster centers corresponding to the plurality of patterns, including: Performing dimensionality reduction processing on the real-time condition parameters to obtain processed real-time condition parameters; Determine the distance between the processed real-time condition parameter and the cluster centers corresponding to each of the multiple patterns.

4. The cloud server according to claim 1, wherein: The processor is configured to convert the real-time performance parameter based on the second performance parameter of the second multi-split air-conditioning system in a normal operating state under the target mode to obtain a third performance parameter, including: determining a deviation value between the first performance parameter and the second performance parameter under the target mode; Based on the deviation value, the real-time performance parameter is converted to obtain the third performance parameter.

5. The cloud server according to claim 1, wherein: The processor is further configured to send the fault detection result to the first multi-split air conditioning system through the communicator.

6. The cloud server according to any one of claims 1 to 5, characterized in that: The fault detection result is used to characterize whether there is a refrigerant leak in the first multi-split air-conditioning system; the first condition parameter includes at least one of the following: ambient temperature, speed gear of the outdoor fan, set temperature, actual operating frequency of the compressor and opening of the electronic expansion valve; the first performance parameter includes at least one of the following: compressor exhaust pressure, compressor suction temperature, compressor exhaust temperature, condensing pressure, evaporating pressure, compressor current, compressor suction superheat, compressor exhaust superheat, evaporating temperature and condensing temperature.

7. A first multi-split air conditioning system, characterized in that: include: Communicator, used for communicating with the cloud server; The controller is configured as: Acquiring real-time performance parameters and real-time condition parameters of the first multi-split air-conditioning system, wherein the real-time condition parameters are used to characterize an operating condition of the first multi-split air-conditioning system; Based on the real-time condition parameter, determining a target mode that matches the first multi-split air-conditioning system from multiple modes of the second multi-split air-conditioning system, and obtaining from the cloud server a first performance parameter of the first multi-split air-conditioning system in a normal operating state under the target mode and a second performance parameter of the second multi-split air-conditioning system in a normal operating state, the first performance parameter being used to characterize the performance of the first multi-split air-conditioning system, and the second performance parameter being used to characterize the performance of the second multi-split air-conditioning system; Converting the real-time performance parameter based on the first performance parameter and the second performance parameter in the target mode to obtain a third performance parameter; The third performance parameter is input into the fault detection model of the second multi-split air-conditioning system to obtain a fault detection result of the first multi-split air-conditioning system.

8. A control method for a multi-split air conditioning system, characterized in that: Applicable to cloud servers, including: Acquiring real-time performance parameters and real-time condition parameters of the first multi-split air-conditioning system, wherein the real-time condition parameters are used to characterize an operating condition of the first multi-split air-conditioning system; Based on the real-time condition parameter, determining a target mode that matches the first multi-split air-conditioning system from multiple modes of the second multi-split air-conditioning system, and obtaining a first performance parameter of the first multi-split air-conditioning system in a normal operating state and a second performance parameter of the second multi-split air-conditioning system in a normal operating state under the target mode, the first performance parameter being used to characterize the performance of the first multi-split air-conditioning system, and the second performance parameter being used to characterize the performance of the second multi-split air-conditioning system; Converting the real-time performance parameter based on the first performance parameter and the second performance parameter in the target mode to obtain a third performance parameter; The third performance parameter is input into the fault detection model of the second multi-split air-conditioning system to obtain a fault detection result of the first multi-split air-conditioning system.

9. The method according to claim 8, characterized in that The determining, based on the real-time condition parameter, a target mode that matches the first multi-split air-conditioning system from a plurality of modes of the second multi-split air-conditioning system includes: determining a distance between the real-time condition parameter and the cluster centers corresponding to each of the multiple modes; wherein the cluster centers corresponding to each of the multiple modes are obtained by clustering and calculating second condition parameters of the second multi-split air conditioning system under different test environments, the second condition parameters being used to characterize the operating conditions of the second multi-split air conditioning system; The pattern corresponding to the nearest cluster center is used as the target pattern.

10. A control method for a multi-split air conditioning system, characterized in that: Applied to the first multi-split air conditioning system, including: Acquiring real-time performance parameters and real-time condition parameters of the first multi-split air-conditioning system, wherein the real-time condition parameters are used to characterize an operating condition of the first multi-split air-conditioning system; Based on the real-time condition parameter, determining a target mode that matches the first multi-split air-conditioning system from multiple modes of the second multi-split air-conditioning system, and obtaining from a cloud server a first performance parameter of the first multi-split air-conditioning system in a normal operating state under the target mode and a second performance parameter of the second multi-split air-conditioning system in a normal operating state, the first performance parameter being used to characterize the performance of the first multi-split air-conditioning system, and the second performance parameter being used to characterize the performance of the second multi-split air-conditioning system; Converting the real-time performance parameter based on the first performance parameter and the second performance parameter in the target mode to obtain a third performance parameter; The third performance parameter is input into the fault detection model of the second multi-split air-conditioning system to obtain a fault detection result of the first multi-split air-conditioning system.

Images