Air conditioning system and control method therefor

Abstract

The present application relates to an air conditioning system and a control method therefor. The air conditioning system comprises: at least one processor; and at least one computer memory, which is operably connected to the at least one processor and stores instructions, wherein when the instructions are executed by the at least one processor, the at least one processor executes the following operations: acquiring real-time operating data, historical normal data and a first abnormality threshold value of an air conditioning system, wherein the first abnormality threshold value is used for identifying whether the air conditioning system is abnormal; on the basis of the real-time operating data and the historical normal data, determining the abnormality degree of the real-time operating data; and when the abnormality degree of the real-time operating data is above the first abnormality threshold value, determining, on the basis of a magnitude relationship between the abnormality degree of the real-time operating data and a plurality of abnormality threshold value intervals, an abnormality level corresponding to the abnormality threshold value interval to which the abnormality degree of the real-time operating data belongs, so as to obtain the abnormality level of the air conditioning system.

Description

Air conditioning systems and their control methods

[0001] Related applications

[0002] This application claims priority to Chinese patent application No. 2024115493537, filed on October 31, 2024, entitled "An Air Conditioning System and Control Method Thereof", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of electrical equipment technology, and in particular to an air conditioning system and its control method. Background Technology

[0004] During air conditioning operation, it is usually necessary to detect faults in the air conditioning system so that they can be dealt with in a timely manner, thereby effectively reducing the energy consumption of the air conditioning system and extending its service life. Summary of the Invention

[0005] This application provides an air conditioning system and its control method to improve the accuracy of air conditioning system fault pre-diagnosis.

[0006] In a first aspect, embodiments of this application provide an air conditioning system, the air conditioning system comprising: at least one processor; and at least one computer memory operatively connected to the at least one processor and storing instructions, wherein when the instructions are executed by the at least one processor, the at least one processor performs the following operations:

[0007] Acquire real-time operating data, historical normal data, and a first anomaly threshold of the air conditioning system; the first anomaly threshold is used to identify whether the air conditioning system is abnormal.

[0008] The degree of anomaly in real-time operational data is determined based on the relationship between real-time operational data and historical normal data.

[0009] If the anomaly level of the real-time operating data is above the first anomaly threshold, the anomaly level corresponding to the anomaly threshold interval to which the anomaly level of the real-time operating data belongs is determined based on the relationship between the anomaly level of the real-time operating data and multiple anomaly threshold intervals, thus obtaining the anomaly level of the air conditioning system.

[0010] In the aforementioned technical solution, if the anomaly level of the real-time operating data of the air conditioning system exceeds the first anomaly threshold, it indicates that the anomaly level of the real-time operating data exceeds the maximum allowable anomaly level under normal operating conditions. Therefore, the real-time operating data can be identified as anomalous data. Furthermore, by analyzing the relationship between the anomaly level of the real-time operating data and multiple anomaly threshold intervals, the specific anomaly level of the real-time operating data can be determined. This method of classifying real-time operating data into different anomaly levels facilitates the selection of appropriate handling measures based on these different anomaly levels. It avoids the resource waste caused by requiring maintenance for minor anomalies such as short-term pressure fluctuations and also improves the accuracy of air conditioning system fault prediction and diagnosis.

[0011] Secondly, embodiments of this application provide a control method for an air conditioning system. The method includes: acquiring real-time operating data, historical normal data, and a first abnormal threshold of the air conditioning system; the first abnormal threshold is used to identify whether the air conditioning system is abnormal; determining the degree of abnormality of the real-time operating data based on the relationship between the real-time operating data and the historical normal data; and, if the degree of abnormality of the real-time operating data is above the first abnormal threshold, determining the abnormal level corresponding to the abnormal threshold interval to which the degree of abnormality of the real-time operating data belongs based on the size relationship between the degree of abnormality of the real-time operating data and multiple abnormal threshold intervals, thereby obtaining the abnormal level of the air conditioning system.

[0012] Thirdly, embodiments of this application provide a controller, including: one or more processors; one or more memories; wherein the one or more memories are used to store computer program code, the computer program code including computer instructions, and when the one or more processors execute the computer instructions, the controller executes any of the air conditioning system control methods provided in the second aspect.

[0013] Fourthly, embodiments of this application provide a computer-readable storage medium including computer instructions that, when executed on a computer, cause the computer to perform any of the air conditioning system control methods provided in the second aspect.

[0014] Fifthly, embodiments of the present invention provide a computer program product that can be directly loaded into a memory and contains software code. After being loaded and executed by a computer, the computer program product can realize any of the air conditioning system control methods provided in the second aspect.

[0015] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the controller's processor, or it may be packaged separately from the controller's processor; this application does not impose any limitations on this.

[0016] Details of one or more embodiments of this application are set forth in the following drawings and description. Other features, objects, and advantages of this application will become apparent from the specification, drawings, and claims. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the published drawings without creative effort.

[0018] Figure 1 is a schematic diagram of the composition of an air conditioning system provided in an embodiment of this application;

[0019] Figure 2 is a flowchart of a control method for an air conditioning system provided in an embodiment of this application;

[0020] Figure 3 is a schematic diagram of the distribution of historical normal data before data standardization processing provided in an embodiment of this application;

[0021] Figure 4 is a schematic diagram of the distribution of historical normal data after data standardization processing, provided in an embodiment of this application.

[0022] Figure 5 is a schematic diagram showing the distribution of a first abnormal threshold and a second abnormal threshold provided in an embodiment of this application;

[0023] Figure 6 is a schematic diagram showing the distribution of another first abnormal threshold and second abnormal threshold provided in an embodiment of this application;

[0024] Figure 7 is a schematic diagram of the display interface of a display device provided in an embodiment of this application;

[0025] Figure 8 is a flowchart of another air conditioning system control method provided in an embodiment of this application;

[0026] Figure 9 is a flowchart of another air conditioning system control method provided in an embodiment of this application;

[0027] Figure 10 is a flowchart of another air conditioning system control method provided in an embodiment of this application. Detailed Implementation

[0028] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0029] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0030] 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 technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0031] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "connected" and "linked" should be interpreted broadly, for example, as a fixed connection, a detachable connection, or an integral connection. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances. Furthermore, when describing pipelines, the terms "connected" and "linked" as used in this application have the meaning of establishing electrical connection. The specific meaning needs to be understood in conjunction with the context.

[0032] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0033] In related technologies, when diagnosing faults in air conditioning systems, predefined thresholds are typically used to determine whether the system is in an abnormal state. While this method can quickly identify abnormal states in air conditioning systems, it cannot achieve a finer determination of these abnormal states, resulting in an inability to perform more accurate testing of the air conditioning system.

[0034] To improve the accuracy of fault prediction in air conditioning systems, this application provides a control method for an air conditioning system. If the anomaly level of the real-time operating data of the air conditioning system exceeds a first anomaly threshold, it indicates that the anomaly level of the real-time operating data exceeds the maximum allowable anomaly level under normal operating conditions. Therefore, the real-time operating data can be identified as abnormal data. Furthermore, by analyzing the relationship between the anomaly level of the real-time operating data and multiple anomaly threshold intervals, the specific anomaly level of the real-time operating data can be determined. This method of classifying real-time operating data into different anomaly levels facilitates the selection of appropriate handling measures based on these different anomaly levels. It avoids the resource waste caused by requiring maintenance for minor anomalies such as short-term pressure fluctuations and also improves the accuracy of fault prediction in air conditioning systems.

[0035] The basic operating principle of the air conditioning system in this application is as follows:

[0036] In this application, the air conditioning system executes a refrigeration cycle using a compressor, condenser, expansion valve, and evaporator. The refrigeration cycle includes a series of processes involving compression, condensation, expansion, and evaporation, and supplies refrigerant to the conditioned and heat-exchanged air.

[0037] The compressor compresses refrigerant gas under high temperature and pressure and discharges the compressed refrigerant gas. The discharged refrigerant gas flows into the condenser. The condenser condenses the compressed refrigerant into a liquid phase, and the heat is released to the surrounding environment through the condensation process.

[0038] The expansion valve expands the high-temperature, high-pressure liquid refrigerant condensed in the condenser into a low-pressure liquid refrigerant. The evaporator evaporates the expanded refrigerant in the expansion valve, returning the low-temperature, low-pressure refrigerant gas to the compressor. The evaporator achieves its cooling effect by utilizing the latent heat of refrigerant evaporation to exchange heat with the material being cooled. Throughout the cycle, the air conditioning system regulates the temperature of the indoor space.

[0039] The outdoor unit of an air conditioning system refers to the part of the refrigeration cycle that includes the compressor and the outdoor heat exchanger. The indoor unit of an air conditioning system includes the indoor heat exchanger, and the expansion valve can be provided in either the indoor or outdoor unit.

[0040] Indoor and outdoor heat exchangers function as either condensers or evaporators. When the indoor heat exchanger is used as a condenser, the air conditioning system functions as a heater in heating mode; when the indoor heat exchanger is used as an evaporator, the air conditioning system functions as a cooler in cooling mode.

[0041] Figure 1 is a schematic diagram of an air conditioning system provided by this application according to an exemplary embodiment. As shown in Figure 1, the air conditioning system may include an outdoor unit 101. The outdoor unit 101 is typically installed outdoors and is used for heat exchange in the indoor environment.

[0042] In some embodiments, the air conditioning system may include an indoor unit 102. The indoor unit 102 is typically installed indoors.

[0043] In some embodiments, the air conditioning system may include at least one processor 103 (not shown in FIG. 1). Processor 103 refers to a device that can generate operation control signals according to instruction opcodes and timing signals, instructing the air conditioning system to execute control commands. Exemplarily, processor 103 may be a central processing unit (CPU), a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The controller may also be other devices with processing functions, such as circuits, devices, or software modules; this application embodiment does not impose any limitations on this.

[0044] In addition, the processor 103 can be used to control the operation of various components inside the air conditioning system so that the operation of each component of the air conditioning system can realize the predetermined functions of the air conditioning system.

[0045] In some embodiments, the air conditioning system may include at least one computer memory 104 (not shown in FIG. 1). The computer memory 104 can be used to store software programs and data. At least one processor 103 performs various functions of the air conditioning system and data processing by running the software programs or data stored in the computer memory 104. The computer memory 104 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 computer memory 104 stores an operating system that enables the air conditioning system to run. In this application, the computer memory 104 may store the operating system and various application programs, and may also store code that executes the control method of the air conditioning system provided in the embodiments of this application.

[0046] Understandably, if an air conditioning system malfunctions, it will not only reduce its capacity but also shorten its lifespan. Therefore, it is necessary to promptly and accurately detect any abnormalities in the air conditioning system and conduct preliminary fault diagnosis so that measures can be taken in a timely manner when an abnormality is identified, thereby reducing the adverse effects of the malfunction.

[0047] Based on this, this application provides a control method for an air conditioning system according to an exemplary embodiment. As shown in FIG2, at least one computer memory 104 is operatively connected to at least one processor 103 and stores instructions. When the instructions are executed by at least one processor 103, at least one processor 103 can perform the following operations to perform anomaly detection and fault pre-diagnosis of the air conditioning system.

[0048] S101. Obtain real-time operating data, historical normal data, and the first abnormal threshold of the air conditioning system.

[0049] Real-time operating data of an air conditioning system refers to data collected by various sensors, controllers, and monitoring devices during the operation of the system, reflecting its current operating status. For example, real-time operating data includes the compressor's operating frequency, the fan's speed, and the opening degree of the electronic expansion valve.

[0050] The first abnormal threshold is used to identify whether the air conditioning system is abnormal.

[0051] In some possible embodiments, the air conditioning system is equipped with a database, in which historical normal data of the air conditioning system can be stored, and the processor can retrieve historical normal data from the database.

[0052] In one example, the accumulated operating data of the air conditioning system from installation to a preset period after commissioning can be considered historical normal data. That is, the operating data of the air conditioning system within the past preset period is considered normal data; in other words, the obtained historical normal data can be the operating data of the air conditioning system within the past preset period. It should be noted that the preset period can be one year.

[0053] In another example, if the cumulative running time of the air conditioning system exceeds the preset time, anomaly detection can be performed on the running data obtained after the cumulative running time of the air conditioning system exceeds the preset time. After determining that the running data is normal data, the running data is stored in the database. In other words, the obtained historical normal data includes the running data of the air conditioning system within the past preset time, or the normal data obtained after the cumulative running time of the air conditioning system reaches the preset time.

[0054] Normal data refers to the operating parameters of an air conditioning system when it is running under design conditions and the system reaches preset standards. For example, preset standards may include energy efficiency ratio and set power.

[0055] In some possible embodiments, the first abnormal threshold may be stored in a database of the air conditioning system, and the processor may retrieve the first abnormal threshold and the second abnormal threshold from the database.

[0056] In other possible embodiments, the first anomaly threshold may be determined based on the anomaly degree of multiple historical normal data, the anomaly degree of the historical normal data may reflect the anomaly degree allowed by the air conditioning system under normal operating conditions, and the first anomaly threshold may reflect the maximum anomaly degree allowed by the air conditioning system under normal operating conditions.

[0057] Furthermore, the process for determining the first abnormal threshold can be referred to in the specific descriptions in S501-S503 below, which will not be repeated here.

[0058] S102. Determine the degree of anomaly in the real-time operating data based on real-time operating data and historical normal data.

[0059] In some possible embodiments, the Mahalanobis distance between real-time running data and historical normal data can be determined based on real-time running data and historical normal data, and then the anomaly degree of real-time running data can be determined based on the Mahalanobis distance between real-time running data and historical normal data.

[0060] In one example, the target similarity between real-time running data and historical normal data can be determined, and then the anomaly of the real-time running data corresponding to the target similarity can be determined based on the correspondence between similarity and anomaly.

[0061] In another example, there is a positive correlation between the Mahalanobis distance between real-time running data and historical normal data and the degree of anomalousness; that is, the larger the Mahalanobis distance, the higher the degree of anomalousness of the real-time running data. Therefore, the degree of anomalousness of real-time running data can be determined based on the Mahalanobis distance between real-time running data and historical normal data, and the positive correlation between the Mahalanobis distance between real-time running data and historical normal data and the degree of anomalousness.

[0062] In other possible embodiments, the local outlier factor of the real-time running data can be determined based on the real-time running data and historical normal data. The local outlier factor can characterize the degree of outlier of the real-time running data in the historical normal data. Thus, the degree of anomaly of the real-time running data can be determined based on the local outlier factor of the real-time running data.

[0063] In one example, the local outlier factor of the real-time running data can be determined as the anomaly degree corresponding to the real-time running data.

[0064] In another example, the anomaly degree of the real-time running data corresponding to the local outlier can be determined based on the correspondence between the local outlier and the anomaly degree of the real-time running data.

[0065] The following example illustrates the process of determining the Mahalanobis distance between real-time running data and historical normal data.

[0066] In some possible embodiments, there are multiple historical normal data sets. The Mahalanobis distance between the real-time running data and the expected centers of the multiple historical normal data sets can be determined as the Mahalanobis distance between the real-time running data and the historical normal data sets. For example, the Mahalanobis distance between the real-time running data and the expected centers of the multiple historical normal data sets can be determined based on the following steps a1-a3.

[0067] Step a1: Perform data standardization processing on real-time running data and multiple historical normal data.

[0068] In one example, z-score standardization can be applied to real-time running data and multiple historical normal data to transform each of the M feature variables included in each data point into data that conforms to a standard normal distribution, thereby eliminating dimensional differences between each feature variable.

[0069] For example, the historical normal data before data standardization is shown in Figure 3, and the historical normal data after data standardization is shown in Figure 4.

[0070] Step a2: Determine the expected center of multiple historical normal data after data standardization.

[0071] In one example, each historical normal data point includes M feature variables. The mean of each feature variable in the historical normal data can be calculated. Then, the mean of each feature variable can form an M-dimensional mean vector. This M-dimensional mean vector is the expected center of multiple historical normal data points, which can reflect the distribution trend of the historical normal data on each feature variable.

[0072] Step a3: Determine the covariance matrix and the inverse of the covariance matrix corresponding to the center of expectation.

[0073] Step a4: Determine the Mahalanobis distance between the real-time running data and the expected center based on the inverse of the covariance matrix.

[0074] In some possible implementations, the Mahalanobis distance between the real-time running data and the desired center can be determined based on the following formula (1).

[0075] Where D is the Mahalanobis distance; x is the real-time running data; μ is the desired center; S -1 is the inverse of the covariance matrix; T denotes the transpose.

[0076] In other possible embodiments, there are multiple historical normal data sets. The Mahalanobis distance between the real-time running data and each of the multiple historical normal data sets can be determined first, resulting in multiple Mahalanobis distances. Then, based on these multiple Mahalanobis distances, the Mahalanobis distance between the real-time running data and the historical normal data can be determined. For example, the average of these multiple Mahalanobis distances can be used as the Mahalanobis distance between the real-time running data and the historical normal data.

[0077] Furthermore, the Mahalanobis distance between the real-time running data and each of the multiple historical normal data can be found in the description of steps a1-a4 above, and will not be repeated here.

[0078] S103. When the anomaly degree of the real-time operating data is above the first anomaly threshold, the anomaly level corresponding to the anomaly threshold interval to which the anomaly degree of the real-time operating data belongs is determined according to the relationship between the anomaly degree of the real-time operating data and multiple anomaly threshold intervals, so as to obtain the anomaly level of the air conditioning system.

[0079] Among them, each of the multiple abnormal threshold intervals corresponds to an abnormality level, and the abnormality level is a classification of the degree of abnormality.

[0080] Understandably, if the anomaly level of the real-time operating data is above the first anomaly threshold, it means that the anomaly level of the real-time operating data exceeds the maximum anomaly level allowed by the air conditioning system under normal operating conditions. Therefore, the real-time operating data can be identified as abnormal data.

[0081] Furthermore, the specific anomaly level of real-time operational data can be determined by the relationship between the anomaly degree of the real-time operational data and multiple anomaly threshold intervals. This method of classifying real-time operational data into different anomaly levels facilitates the selection of appropriate handling measures based on these different anomaly levels. It avoids the waste of resources caused by requiring maintenance for minor anomalies such as short-term pressure fluctuations, and also improves the accuracy of pre-diagnosis of air conditioning system faults.

[0082] In some possible implementations, multiple abnormal threshold ranges can be preset based on industry experience.

[0083] In other possible embodiments, multiple anomaly threshold intervals are determined based on a second anomaly threshold. This second anomaly threshold can identify data with low anomaly levels.

[0084] The first and second anomaly thresholds are illustrated below. When the data includes feature variable 1 and feature variable 2, the first and second anomaly thresholds can be the anomaly levels of the data, as shown in Figure 5 or Figure 6. It can be understood that the anomaly level corresponding to the first anomaly threshold is the maximum allowable anomaly level for the air conditioning system under normal operating conditions; data with anomalies below the first threshold are considered normal data. The anomaly level corresponding to the second anomaly threshold is the critical value between anomalous data with low anomaly levels and data with high anomalies in the air conditioning system.

[0085] In one example, a first threshold interval and a second threshold interval can be determined based on a second anomaly threshold. The first threshold interval corresponds to a sub-health level, and the second threshold interval corresponds to an anomaly level. The sub-health level indicates that the anomaly degree of the real-time running data is not zero, but the anomaly degree is low, indicating that the air conditioning system is in a sub-healthy state. The anomaly level indicates that the anomaly degree of the real-time running data is not zero, but the anomaly degree is high, indicating that the air conditioning system is in an abnormal state.

[0086] Understandably, not all data anomalies indicate a serious malfunction in the air conditioning system. In some cases, data anomalies may simply be due to changes in the external environment or improper human operation, and in such cases, the degree of anomaly is usually low. If the air conditioning system is misdiagnosed as abnormal in these situations and corresponding alerts are issued, it could lead to unnecessary waste of resources. Therefore, a second anomaly threshold can be set to differentiate data with low anomaly levels. When the anomaly level of real-time operating data is determined to be low, the air conditioning system's anomaly level should be marked as sub-healthy rather than abnormal, thus reducing resource waste caused by false alarms and improving the accuracy of air conditioning system fault prediction.

[0087] For example, the set of anomalies that reach the first anomaly threshold but do not reach the second anomaly threshold can be used as the aforementioned first threshold interval. It should be noted that the anomaly degree reaching the first anomaly threshold but not reaching the second anomaly threshold can refer to an anomaly degree greater than the first anomaly threshold and less than the second anomaly threshold, or an anomaly degree greater than or equal to the first anomaly threshold and less than the second threshold, or an anomaly degree greater than or equal to the first anomaly threshold and less than or equal to the second anomaly threshold; this application does not specifically limit this.

[0088] The set of anomalies that reach the second anomaly threshold can be used as the aforementioned second threshold interval. It should be noted that the anomaly that reaches the second anomaly threshold can refer to an anomaly that is greater than the second anomaly threshold, or it can refer to an anomaly that is greater than or equal to the second anomaly threshold; this application does not make a specific limitation in this regard.

[0089] For example, based on the above embodiments, the first threshold interval can be represented as (first abnormal threshold, second abnormal threshold) and the second threshold interval can be represented as (second abnormal threshold, +∞).

[0090] In another example, to more accurately identify anomalies in the air conditioning system, multiple threshold intervals can be defined based on a second anomaly threshold. Each of these threshold intervals corresponds to an anomaly level, and each anomaly level reflects the degree of capacity degradation of the air conditioning system. Different relationships between the degree of capacity degradation and the anomaly level can be set according to actual needs; this application does not impose specific limitations on this. In this way, multiple anomaly levels can be defined according to the degree of anomaly to achieve pre-diagnosis of air conditioning system faults.

[0091] For example, based on the second anomaly threshold, a third threshold interval and a fourth threshold interval can also be determined. The third threshold interval corresponds to a mild anomaly level, and the fourth threshold interval corresponds to a severe anomaly level. In other words, based on the second anomaly threshold, a first threshold interval, a third threshold interval, and a fourth threshold interval can be determined. The specific description of the first threshold interval can be found in the example above, and will not be repeated here. For example, the capability attenuation level corresponding to the first threshold interval is 5%, the capability attenuation level corresponding to the third threshold interval is 10%, and the capability attenuation level corresponding to the fourth threshold interval is 25%.

[0092] For example, the set of abnormalities that reach the second abnormality threshold but are not more than twice the second abnormality threshold can be defined as the third threshold interval, and the set of abnormalities that reach the second abnormality threshold but are not more than three times the second abnormality threshold can be defined as the fourth threshold interval.

[0093] For example, based on the above example, the third threshold interval can be represented as (the second abnormal threshold, twice the second abnormal threshold) and the fourth threshold interval can be represented as (twice the second abnormal threshold, three times the second abnormal threshold).

[0094] Furthermore, regarding the abnormality level that reaches the second abnormality threshold but is less than twice the second abnormality threshold, and the abnormality level that reaches twice the second abnormality threshold but is less than three times the second abnormality threshold, please refer to the specific description of the abnormality level that reaches the first abnormality threshold but is less than the second abnormality threshold in the above embodiments, which will not be repeated here.

[0095] In some embodiments, based on the above example, if the anomaly of the real-time operating data exceeds the fourth threshold range corresponding to severe anomaly, it indicates that the current air conditioning system has crashed and a corresponding alarm reminder needs to be issued to remind the user to repair it in time.

[0096] In some embodiments, after determining the abnormality level of the air conditioning system, the abnormality level of the air conditioning system can be displayed through a display device to facilitate users or manufacturers to intuitively understand the operating status of the air conditioning system.

[0097] In some embodiments, the display device may be installed in the air conditioning system, for example, in the indoor unit, so that users can view it at any time.

[0098] In other embodiments, the display device may also be a terminal device that communicates with the air conditioning system, such as a mobile phone. For example, after determining the anomaly level of the air conditioning system, the processor sends the anomaly level to the terminal device, which then displays the anomaly level in an application that controls the air conditioning system.

[0099] In one example, as shown in Figure 7, different anomaly levels can be identified using different colors. As the anomaly level increases, the color displayed by the display device becomes darker, thereby improving the user's ability to identify different anomaly levels in the air conditioning system.

[0100] In addition, based on the display interface shown in Figure 7, in some embodiments, after determining the abnormality level of the air conditioning system, the display interface can also display the degree of capacity attenuation corresponding to the abnormality level, thereby more intuitively prompting the user about the impact of air conditioning abnormalities on system performance.

[0101] In another example, different anomaly levels can use different display methods. For instance, when the air conditioning system's anomaly level is "minor," the display device can show an exclamation mark. When the air conditioning system's anomaly level is also "minor," the display device can show a stop sign.

[0102] In some embodiments, after determining the abnormality level of the air conditioning system, a specific percentage value corresponding to the current abnormality level of the air conditioning system can be determined. This percentage value can more accurately reflect the degree of abnormality of the air conditioning system.

[0103] Based on S101-S103 above, if the anomaly level of the real-time operating data exceeds the first anomaly threshold, it indicates that the anomaly level of the real-time operating data exceeds the maximum allowable anomaly level under normal operating conditions of the air conditioning system. Therefore, the real-time operating data can be identified as abnormal data. Furthermore, by analyzing the relationship between the anomaly level of the real-time operating data and multiple anomaly threshold intervals, the specific anomaly level of the real-time operating data can be determined. This method of classifying real-time operating data into different anomaly levels facilitates the selection of appropriate handling measures based on these different anomaly levels. It avoids the resource waste caused by requiring maintenance for minor anomalies such as short-term pressure fluctuations and also improves the accuracy of air conditioning system fault prediction.

[0104] In some embodiments, in order to determine the second anomaly threshold, as shown in FIG8, at least one processor 103 may also perform the following operations:

[0105] S201. Obtain the fitting relationship corresponding to the basic model to which the air conditioning system belongs.

[0106] The fitting relationship is used to characterize the relationship between the abnormal baseline value of the air conditioning system corresponding to the base model and external influencing factors. The abnormal baseline value is determined based on multiple abnormal data of the air conditioning system corresponding to the base model.

[0107] The basic model refers to the model of the air conditioning system used in the modeling phase. Understandably, the model of the air conditioning system used in the modeling phase usually differs from the model of the air conditioning system in the actual application scenario. If the first abnormal baseline value determined in the modeling phase (for a description of the first abnormal baseline value, refer to S202 below) is directly used as the second abnormal threshold, the second abnormal threshold will be inaccurate, thereby affecting the accuracy of fault pre-diagnosis of the air conditioning system.

[0108] Therefore, in order to improve the accuracy of air conditioning system fault pre-diagnosis, the fitting relationship corresponding to the basic model to which the air conditioning system belongs can be obtained, and the fitting relationship corresponding to the basic model can be transferred to the current air conditioning system. Thus, the second abnormal threshold can be accurately determined based on the following steps.

[0109] External influencing factors refer to parameters existing outside the air conditioning system that can affect it. These parameters may originate from human operation or changes in the external environment. For example, external influencing factors may include any of the following: outdoor ambient temperature, indoor set temperature, indoor fan speed coefficient, and load factor. The load factor is the ratio of the total capacity of the indoor units currently in operation to the total capacity of all indoor units in the air conditioning system. The indoor fan speed coefficient is the ratio of the speed of the indoor fan at its current setting to the speed at its maximum setting.

[0110] Understandably, since the speeds of indoor fans at different settings vary across different air conditioning models, directly determining the fitting relationship based on the speed of a basic model's indoor unit would lead to incompatibility when transferring the fitting relationship to the current air conditioning system, thus affecting the accuracy of the second anomaly threshold. Therefore, fitting the relationship using the ratio between the indoor fan's speed at the current setting and the speed at the maximum setting allows for comparison of the indoor fan speeds across different models on the same scale, making it more applicable to various models and improving the accuracy of the second anomaly threshold for the current air conditioning system. In some possible embodiments, this fitting relationship can be stored in a database, which could be a database on a cloud server, allowing the processor to obtain the fitting relationship through a communication connection between the air conditioning system and the cloud server. Alternatively, the database could be the air conditioning system's own database, allowing the processor to obtain the fitting relationship through the air conditioning system's own communicator.

[0111] S202. Based on the fitting relationship, determine the first abnormal baseline value corresponding to the external influence factor in the first abnormal data of the air conditioning system.

[0112] In some possible embodiments, since the fitting relationship characterizes the relationship between the abnormal baseline value of the air conditioning system corresponding to the modeling model and the external influencing factors, the external influencing factors of the first abnormal data of the air conditioning system can be input into the fitting relationship to obtain the corresponding first abnormal baseline value.

[0113] For example, this fitting relationship can be expressed as the following formula (2): Y=Ax+By+Cz+Dm+n. Formula (2)

[0114] Where Y is the abnormal baseline value of the air conditioning system corresponding to the basic model; x, y, z, and m are external influencing factors; A, B, C, and D are the fitting coefficients corresponding to the external influencing factors; and n is the intercept of the fitting relationship.

[0115] Substitute the external influence factor of the first abnormal data of the air conditioning system into the above formula (2) to obtain the Y value, which is the first abnormal baseline value.

[0116] S203. Determine the second abnormal threshold based on the first abnormal baseline value.

[0117] In some possible embodiments, there is a correspondence between the first abnormal benchmark value and the second abnormal threshold value, and the second abnormal threshold value corresponding to the first abnormal benchmark value can be determined based on the correspondence between the first abnormal benchmark value and the second abnormal threshold value.

[0118] Based on S201-S203, by transferring the fitting relationship of the basic model to the current air conditioning system, the second anomaly threshold can be quickly and accurately determined for air conditioning systems of different models, thereby improving the sensitivity and versatility of air conditioning system fault pre-diagnosis. Furthermore, since the fitting relationship reflects the relationship between external influencing factors and the anomaly baseline value, the air conditioning system can accurately distinguish whether the anomaly is caused by normal fluctuations in the external environment or human operation, or by a genuine abnormal situation. This distinction improves the accuracy of the second anomaly threshold, thus enhancing the accuracy of air conditioning system fault pre-diagnosis.

[0119] In some embodiments, in order to determine a second abnormal threshold based on a first abnormal reference value, as shown in FIG9, at least one processor may perform the following operation, that is, the above S203 may be implemented as the following steps.

[0120] S301. Obtain the first degree of anomaly of the normal data of the basic model and the second degree of anomaly of the normal data of the air conditioning system.

[0121] The following example illustrates the process of obtaining the first anomaly level of normal data for a basic model.

[0122] Step b1: Obtain abnormal data and multiple normal data for the basic model.

[0123] Step b2: Perform data standardization processing on the abnormal and normal data of the basic model.

[0124] Step b3: Determine the Mahalanobis distance between each normal data point and the abnormal data point in the multiple normal data points of the base model.

[0125] Furthermore, regarding the determination of the Mahalanobis distance between each normal and abnormal data point, please refer to the specific description of steps a1-a4 above, which will not be repeated here.

[0126] Step b4: Determine the anomalousness of each normal data point based on the Mahalanobis distance between each normal data point and the abnormal data point, thus obtaining the anomalousness of multiple normal data points.

[0127] Furthermore, regarding the determination of the anomaly degree of multiple normal data, please refer to the specific description of determining the anomaly degree of real-time running data in S102 above, which will not be repeated here.

[0128] Step b5: Determine the first anomaly based on the anomaly degree of multiple normal data.

[0129] In some possible embodiments, the anomaly degree corresponding to the first preset quantile of the anomaly degree of multiple normal data can be determined as the first anomaly degree. The anomaly degree corresponding to the first preset quantile can reflect the critical value between normal data and anomalous data. It should be noted that the first preset quantile can be the 98.5th percentile, and the specific first preset quantile can be set according to the actual situation.

[0130] Similarly, a second degree of anomaly in the normal data of the air conditioning system can be determined based on the abnormal data and multiple historical normal data. For details, please refer to the description of obtaining the first degree of anomaly above; this application will not repeat it here.

[0131] It should be noted that the determination of the first and second outliers is based on the characteristic variables in each data set, excluding external influencing factors.

[0132] S302. The first abnormality benchmark value is corrected based on the first abnormality and the second abnormality to obtain the second abnormality threshold.

[0133] In some possible embodiments, there is a preset relationship between the first anomaly degree, the second anomaly degree, the first anomaly benchmark value, and the second anomaly threshold. Therefore, the second anomaly threshold can be determined based on the preset relationship, the first anomaly degree, the second anomaly degree, and the first anomaly benchmark value.

[0134] For example, the preset relationship includes: the ratio of a first anomaly baseline value to a first anomaly degree is equal to the ratio of a second anomaly threshold to a second anomaly degree. Based on this preset relationship, the ratio of the first anomaly baseline value to the first anomaly degree can be multiplied by the second anomaly degree to obtain the second anomaly threshold.

[0135] In some embodiments, as shown in FIG10, at least one processor may also perform the following operations.

[0136] S401. Obtain multiple second abnormal data of the basic model to which the air conditioning system belongs.

[0137] In some embodiments, the RobustScaler function from the Scikit-learn library can be used to standardize multiple second outlier data. Because the RobustScaler function scales features using the median and interquartile range (IQR), it is more robust to outliers and is therefore suitable for datasets containing outliers, i.e., for multiple second outliers that deviate from the normal data.

[0138] S402. Determine the operating condition and degree of abnormality corresponding to each second abnormal data.

[0139] Operating conditions refer to the environmental conditions in which the air conditioning system operates. For example, operating conditions may include ambient temperature and ambient humidity.

[0140] In some possible embodiments, there is a correspondence between external influencing factors and operating conditions, and the operating conditions corresponding to each second abnormal data can be determined based on the external influencing factors of the second abnormal data.

[0141] In some possible embodiments, under each operating condition corresponding to the second abnormal data, the Mahalanobis distance between the second abnormal data and the normal data is determined based on the other characteristic variables of each second abnormal data besides external influencing factors, and then the abnormality degree corresponding to the second abnormal data is determined according to the Mahalanobis distance. Furthermore, the process of determining the Mahalanobis distance between the second abnormal data and the normal data can be referred to the specific description of steps a1-a4 above, and will not be repeated here.

[0142] Understandably, when determining the degree of anomaly corresponding to the second abnormal data based on characteristic variables other than external influencing factors, the accuracy of the calculated degree of anomaly is relatively low due to the limited number of characteristic variables used. This is suitable for distinguishing data with low degree of anomaly, which helps to identify whether the abnormality of the air conditioning system is caused by normal fluctuations such as external environment and human operation, thereby improving the accuracy of fault pre-diagnosis.

[0143] S403. Based on the degree of abnormality of the second abnormal data corresponding to each working condition, determine the abnormal baseline value corresponding to the working condition.

[0144] In some possible embodiments, the average value of the abnormality of multiple second abnormal data corresponding to each working condition can be determined as the abnormality baseline value corresponding to the working condition.

[0145] In some possible embodiments, the anomaly degree corresponding to the second preset quantile among the anomaly degrees of multiple second anomaly data corresponding to each working condition can be determined as the anomaly baseline value corresponding to the working condition. The second preset quantile, corresponding to the anomaly degree, can reflect the critical value between anomaly data with low anomaly degree and anomaly data with high anomaly degree. It should be noted that the second preset quantile can be the 1% quantile, and the specific second preset quantile can be set according to the actual situation.

[0146] Understandably, since the anomaly degree of the second abnormal data has relatively low discrimination accuracy, it is suitable for distinguishing data with low anomaly degree. The anomaly benchmark value determined based on the anomaly degree of the second abnormal data is also suitable for distinguishing data with low anomaly degree, thereby helping to identify whether the abnormality of the air conditioning system is caused by normal fluctuations such as external environment and human operation, thus improving the accuracy of fault pre-diagnosis.

[0147] S404. Based on the external influencing factors in the second abnormal data corresponding to the current operating condition of the air conditioning system, and the abnormal baseline value corresponding to the current operating condition of the air conditioning system, determine the fitting relationship corresponding to the basic model to which the air conditioning system belongs.

[0148] In some possible embodiments, a linear regression is performed between the abnormal baseline value corresponding to the current operating condition of the air conditioning system and the external influencing factors in the second abnormal data corresponding to the current operating condition of the air conditioning system to obtain a fitting formula. For example, the fitting formula is shown in formula (1) above.

[0149] Based on S401-S404, abnormal conditions in the air conditioning system can be fitted with external influencing factors. Since abnormal states in the air conditioning system may be caused by normal fluctuations in the external environment or human operation, rather than by a genuine malfunction in the system itself, the fitting relationship obtained by combining these factors allows the system to accurately distinguish between abnormalities caused by normal fluctuations in the external environment or human operation and those caused by a true malfunction. This improves the accuracy of determining the second abnormality threshold and enhances the accuracy of pre-diagnosis of air conditioning system faults.

[0150] In some embodiments, in order to determine the first anomaly threshold, at least one processor 103 may also perform the following operations:

[0151] S501. Determine the mathematical expectation of multiple historical normal data of the air conditioning system.

[0152] In some embodiments, the StandardScalerr function from the Scikit-learn library can be used to standardize the multiple historical normal data before determining the mathematical expectation of the multiple historical normal data of the air conditioning system.

[0153] In some embodiments, before determining the mathematical expectation of multiple historical normal data of the air conditioning system, the number of features for each historical normal data can be reduced based on the principal component analysis (PCA) method to avoid overfitting of each feature variable when determining the first threshold.

[0154] Furthermore, the process for determining the mathematical expectation of multiple historical normal data of the air conditioning system can be found in the detailed description of determining the expectation center of multiple historical normal data in step a2 above, which will not be repeated here.

[0155] S502, Determine the distance between each historical normal data point and the mathematical expectation.

[0156] The process of determining the distance between each historical normal data point and the mathematical expectation can be found in the detailed descriptions of steps a3 and a4 above, and will not be repeated here.

[0157] S503. Determine the target distance corresponding to the third preset quantile from the distances corresponding to multiple historical normal data, and determine the first abnormal threshold based on the target distance.

[0158] The target distance corresponding to the third preset percentile can be the maximum distance allowed by the air conditioning system under normal operating conditions. This maximum distance reflects the maximum degree of abnormality allowed by the air conditioning system under normal operating conditions. For example, the third preset percentile can be the 98.5th percentile, and different third preset percentiles can be set according to actual needs.

[0159] In some possible implementations, the target distance can be used as the first anomaly threshold.

[0160] It should be noted that in S501-S503 above, the first anomaly threshold is determined based on multiple feature variables, including external influencing factors, from historical normal data. Because a relatively large number of feature variables are used, the calculated anomaly degree has relatively high discrimination accuracy, making it suitable for distinguishing between normal and anomalous data.

[0161] Based on S501-S503, a first anomaly threshold is determined by the target distance between the mathematical expectation of historical normal data and the target distance between historical normal data. Since this target distance reflects the maximum allowable anomaly degree of the air conditioning system under normal operating conditions, the determined first anomaly threshold can effectively distinguish between normal and abnormal data of the air conditioning system, making the fault pre-diagnosis of the air conditioning system based on the first anomaly threshold more accurate.

[0162] The following describes a control method for an air conditioning system according to an embodiment of this application. The control method for the air conditioning system includes at least the following:

[0163] S601. Obtain real-time operating data, historical normal data, and a first abnormal threshold of the air conditioning system; the first abnormal threshold is used to identify whether the air conditioning system is abnormal.

[0164] S602. Determine the anomaly level of real-time operating data based on the relationship between real-time operating data and historical normal data.

[0165] S603. When the anomaly degree of the real-time operating data is above the first anomaly threshold, the anomaly level corresponding to the anomaly threshold interval to which the anomaly degree of the real-time operating data belongs is determined according to the relationship between the anomaly degree of the real-time operating data and multiple anomaly threshold intervals, so as to obtain the anomaly level of the air conditioning system.

[0166] In summary, the air conditioning system control method provided by this application, according to an exemplary embodiment, can determine real-time operating data as abnormal data when the anomaly level of the real-time operating data exceeds a first anomaly threshold. Furthermore, it determines the specific anomaly level of the real-time operating data by analyzing the relationship between the anomaly level determined by the real-time operating data and multiple anomaly threshold intervals. This method of classifying real-time operating data into different anomaly levels facilitates the subsequent selection of appropriate handling measures based on these different anomaly levels. It avoids the resource waste caused by requiring maintenance for minor anomalies such as short-term pressure fluctuations and also improves the accuracy of air conditioning system fault pre-diagnosis.

[0167] In some embodiments, multiple abnormal threshold intervals are determined based on a second abnormal threshold, which is obtained based on the following steps: obtaining the fitting relationship corresponding to the base model to which the air conditioning system belongs, the fitting relationship being used to characterize the relationship between the abnormal baseline value of the air conditioning system corresponding to the base model and external influencing factors; the abnormal baseline value is determined based on multiple abnormal data of the air conditioning system corresponding to the base model; determining the first abnormal baseline value corresponding to the external influencing factors in the first abnormal data of the air conditioning system based on the fitting relationship; and determining the second abnormal threshold based on the first abnormal baseline value.

[0168] In some embodiments, determining a second anomaly threshold based on a first outlier includes: obtaining a first degree of anomaly in normal data of a basic model and a second degree of anomaly in normal data of an air conditioning system; and correcting a first anomaly baseline value based on the first degree of anomaly and the second degree of anomaly to obtain a second anomaly threshold.

[0169] It is understood that the steps in the control method of the air conditioning system provided in this application can refer to the steps in the previous air conditioning system, and will not be repeated here.

[0170] Some embodiments of this application also provide a controller, including at least one processor and at least one memory. The memory stores computer program code, which includes computer instructions. When the at least one processor executes the computer instructions, it performs the control method for the air conditioning system.

[0171] Some embodiments of this application also provide a computer-readable storage medium including computer instructions. When the computer instructions are executed by at least one processor, the processor performs a control method for the air conditioning system.

[0172] Some embodiments of this application also provide a computer program product that can be directly loaded into a memory and contains software code. After being loaded and executed by a processor, the computer program product can realize the control method of the air conditioning system.

[0173] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this invention can be implemented using hardware, software, firmware, or any combination thereof. When implemented in software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transfer of a computer program from one place to another. Storage media can be any available medium accessible to a general-purpose or special-purpose computer.

[0174] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An air conditioning system, comprising: At least one processor; and at least one computer memory operatively connected to and storing instructions, which, when executed by the at least one processor, cause the at least one processor to perform the following operations: The system acquires real-time operating data, historical normal data, and a first anomaly threshold for the air conditioning system; the first anomaly threshold is used to identify whether the air conditioning system is abnormal. Based on the real-time operating data and the historical normal data, the degree of anomaly of the real-time operating data is determined; If the anomaly level of the real-time operating data is above the first anomaly threshold, the anomaly level corresponding to the anomaly threshold interval to which the anomaly level of the real-time operating data belongs is determined according to the relationship between the anomaly level of the real-time operating data and multiple anomaly threshold intervals, thereby obtaining the anomaly level of the air conditioning system.

2. The air conditioning system according to claim 1, wherein, The plurality of abnormal threshold intervals are determined based on a second abnormal threshold, and the at least one processor further performs the following operations: Obtain the fitting relationship corresponding to the basic model to which the air conditioning system belongs; the fitting relationship is used to characterize the relationship between the abnormal benchmark value of the air conditioning system corresponding to the basic model and external influencing factors. The abnormal baseline value is determined based on multiple abnormal data from the air conditioning system corresponding to the basic model; Based on the fitting relationship, determine the first abnormal baseline value corresponding to the external influencing factor in the first abnormal data of the air conditioning system; The second abnormal threshold is determined based on the first abnormal baseline value.

3. The air conditioning system according to claim 2, wherein, The at least one processor performing the step of determining the second anomaly threshold based on the first anomaly benchmark value includes: Obtain the first degree of anomaly of the normal data of the basic model and the second degree of anomaly of the normal data of the air conditioning system; The first abnormality benchmark value is corrected based on the first abnormality and the second abnormality to obtain the second abnormality threshold.

4. The air conditioning system according to claim 2, wherein, The at least one processor executes the process of obtaining the fitting relationship corresponding to the base model to which the air conditioning system belongs, including: Obtain multiple second abnormal data points for the basic model to which the air conditioning system belongs; Determine the operating condition and degree of abnormality corresponding to each of the second abnormal data; Based on the degree of abnormality of the second abnormal data corresponding to each operating condition, the abnormal baseline value corresponding to the operating condition is determined. Based on the external influencing factors in the second abnormal data corresponding to the current operating condition of the air conditioning system, and the abnormal baseline value corresponding to the current operating condition of the air conditioning system, the fitting relationship corresponding to the basic model to which the air conditioning system belongs is determined.

5. The air conditioning system according to any one of claims 2-4, wherein, The external influencing factors include at least one of the following: outdoor ambient temperature, indoor set temperature, indoor windshield coefficient, and load rate.

6. The air conditioning system according to any one of claims 1-4, wherein, The at least one processor also performs the following operations: Determine the mathematical expectation of multiple historical normal data of the air conditioning system; Determine the distance between each of the historical normal data points and the mathematical expectation; The target distance corresponding to the preset quantile is determined from the distances corresponding to multiple historical normal data, and the first abnormal threshold is determined based on the target distance.

7. The air conditioning system according to any one of claims 1-4, wherein, The anomaly degree of the real-time running data is determined based on the Mahalanobis distance between the real-time running data and the historical normal data.

8. The air conditioning system according to claim 1, wherein, The at least one processor also performs the following operations: The abnormality level of the air conditioning system is displayed via a display device.

9. A control method for an air conditioning system, the method comprising: Acquire the real-time operating data, historical normal data, and first abnormal threshold of the air conditioning system; The first abnormal threshold is used to identify whether the air conditioning system is abnormal; Based on the relationship between the real-time operating data and the historical normal data, the anomaly degree of the real-time operating data is determined; If the anomaly level of the real-time operating data is above the first anomaly threshold, the anomaly level corresponding to the anomaly threshold interval to which the anomaly level of the real-time operating data belongs is determined according to the relationship between the anomaly level of the real-time operating data and multiple anomaly threshold intervals, thereby obtaining the anomaly level of the air conditioning system.

10. The method according to claim 9, wherein, The plurality of abnormal threshold intervals are determined based on a second abnormal threshold, which is obtained based on the following steps: Obtain the fitting relationship corresponding to the basic model to which the air conditioning system belongs; the fitting relationship is used to characterize the relationship between the abnormal benchmark value of the air conditioning system corresponding to the basic model and external influencing factors. The abnormal baseline value is determined based on multiple abnormal data from the air conditioning system corresponding to the basic model; Based on the fitting relationship, determine the first abnormal baseline value corresponding to the external influencing factor in the first abnormal data of the air conditioning system; The second abnormal threshold is determined based on the first abnormal baseline value.

11. The method according to claim 9, wherein, Determining the second abnormal threshold based on the first abnormal benchmark value includes: Obtain the first degree of anomaly of the normal data of the basic model and the second degree of anomaly of the normal data of the air conditioning system; The first abnormality benchmark value is corrected based on the first abnormality and the second abnormality to obtain the second abnormality threshold.

Images