Abnormal data monitoring method, device, medium and equipment for central air conditioning cooling system

Abstract

The present application relates to a method, device, medium and equipment for monitoring abnormal data of a centralized air-conditioning and cooling system, and relates to the field of data monitoring technology, wherein the method includes: obtaining system operation data of at least one dimension of a centralized air-conditioning and cooling system; if the system operation data is not within the corresponding normal value range, then determining the corresponding system operation data as abnormal operation data, and based on at least one target fault type that is prone to occur in the centralized air-conditioning and cooling system and at least one corresponding target data abnormal dimension, determining whether to issue an early warning for the abnormal operation data, the target data abnormal dimension is a dimension in which operation data abnormalities are prone to occur when the corresponding target fault type occurs; if so, determining the system fault type corresponding to the abnormal operation data, and issuing a targeted early warning based on the system fault type. The present application has the effect of improving the accuracy of early warnings when abnormal operation data occurs.

Description

Technical Field

[0001] The present application relates to the field of data monitoring technology, and in particular to a method, device, medium and equipment for monitoring abnormal data of a centralized air-conditioning cooling system. Background Art

[0002] A centralized air-conditioning and cooling system refers to an efficient and energy-saving system that provides cooling services through a unified pipe network within a specific area. For building complexes with high building density and high cooling demand, centralized cooling uses large, advanced and efficient chillers, and its cooling energy efficiency is much higher than that of ordinary air-conditioning. At the same time, considering the staggered demand of different buildings, the total installed capacity and operating costs are lower than that of each building's separate air-conditioning system. In general, centralized air-conditioning and cooling systems have the characteristics of intensive land use, high efficiency and energy saving, staggered capacity reduction, and intelligent management and control. They are particularly suitable for promotion and application in areas with high density of commercial buildings. With the complexity and intelligence of modern buildings, centralized air-conditioning and cooling systems have become the core part of energy consumption management and comfort control in large buildings. Therefore, it is of great significance to effectively monitor the operating data of centralized air-conditioning and cooling systems to ensure their normal operation.

[0003] At present, the common method for monitoring the operating data of centralized air-conditioning and cooling systems is to collect the operating data of multiple dimensions of the centralized air-conditioning and cooling systems in real time through various sensors, and adopt an early warning mechanism with a fixed threshold. Once the operating data exceeds the corresponding fixed threshold, it indicates that the operating data is abnormal and an early warning is triggered. However, when the centralized air-conditioning and cooling system has normal load fluctuations, it may also cause abnormal operating data. Under this method, it is easy to mistrigger the early warning, resulting in poor accuracy of early warning when the operating data is abnormal. Summary of the Invention

[0004] In order to improve the accuracy of early warning when abnormal operating data occurs, the present application provides a method, device, medium and equipment for monitoring abnormal data of a centralized air-conditioning and cooling system.

[0005] In a first aspect of the present application, a method for monitoring abnormal data of a centralized air-conditioning and cooling system is provided, specifically comprising:

[0006] Obtain system operation data of at least one dimension of the central air conditioning and cooling system;

[0007] If the system operation data is not within the corresponding normal value range, the corresponding system operation data is determined to be abnormal operation data, and based on at least one target fault type that is prone to occur in the centralized air-conditioning and cooling system and at least one corresponding target data abnormality dimension, it is determined whether to issue an early warning for the abnormal operation data, where the target data abnormality dimension is a dimension in which operation data abnormality is likely to occur when the corresponding target fault type occurs;

[0008] If so, the system fault type corresponding to the abnormal operation data is determined, and a targeted warning is issued based on the system fault type.

[0009] By adopting the above technical solution, after obtaining system operation data of at least one dimension, if the system operation data is not within the corresponding normal value range, it means that the centralized air-conditioning and cooling system currently has abnormal operation data, indicating that the centralized air-conditioning and cooling system may have a fault that causes abnormal operation, or it may not have a fault but is only affected by normal load fluctuations. In order to improve the accuracy of the abnormal operation data warning, based on the target fault type that is prone to occur in the centralized air-conditioning and cooling system and the corresponding target data abnormality dimension, combined with the current abnormal operation data, the risk of failure of the centralized air-conditioning and cooling system is analyzed, and then it is accurately determined whether to issue a targeted warning. If it is determined to issue a warning, then the warning is issued based on the system fault type, thereby avoiding false triggering of the warning and improving the accuracy of the warning when the operation data is abnormal.

[0010] Optionally, the determining whether to issue an early warning for the abnormal operating data based on at least one target fault type that is prone to occur in the centralized air conditioning and cooling system and at least one corresponding target data abnormality dimension specifically includes:

[0011] Obtaining historical fault types that have occurred in the centralized air conditioning and cooling system, counting the first occurrence count of each of the historical fault types, and selecting the first occurrence count of each of the historical fault types in descending order as the target fault type;

[0012] Obtaining a first historical dimension in which an operating data anomaly occurs when each target fault type occurs, counting the number of second occurrences of each first historical dimension, and selecting the first historical dimension with the second number from each first historical dimension in descending order of the number of second occurrences as the target data anomaly dimension for the corresponding target fault type;

[0013] Calculating a first weight for each target fault type and a second weight for each corresponding target data anomaly dimension, where the first weight is a ratio of a first occurrence count for each target fault type to a sum of first occurrence counts for all target fault types, and the second weight is a ratio of a second occurrence count for a single target data anomaly dimension corresponding to a target fault type to a sum of second occurrence counts for all corresponding target data anomaly dimensions;

[0014] It is determined whether to issue an early warning for the abnormal operating data according to at least one abnormal operating data, the first weight and the corresponding second weights.

[0015] By adopting the above technical solution, the greater the number of occurrences of the first fault type, the more likely the central air conditioning and cooling system is to experience the corresponding historical fault type, thereby determining the target fault type. The greater the number of occurrences of the second fault type, the more likely the corresponding first historical dimension of operating data will be abnormal when the target fault type occurs, thereby determining the target data abnormality dimension corresponding to the target fault type. Finally, combining the abnormal operating data, the first weight, and the corresponding second weights, the overall probability of a fault occurring in the target data abnormality dimension of the target fault type based on the current abnormal operating data is analyzed, thereby accurately determining whether to issue an early warning when abnormal operating data occurs, thereby avoiding false alarms.

[0016] Optionally, determining whether to issue an early warning for the at least one abnormal operating data according to the at least one abnormal operating data, the first weight, and the corresponding second weights specifically includes:

[0017] Determine a target abnormal dimension corresponding to each of the abnormal operation data, and determine a target fault type having the target abnormal dimension in each corresponding target data abnormal dimension as a key fault type;

[0018] Calculating a first product of a first weight of each key fault type and a second weight of each corresponding target abnormality dimension and summing the results to obtain a corresponding sum of the first products;

[0019] Summing the sums of the first products to obtain a final product sum, and if the final product sum is greater than a preset first product sum threshold, determining to issue an early warning for the abnormal operating data;

[0020] If the final sum of the products is not greater than the first product sum threshold, it is determined that no warning is issued for the abnormal operation data.

[0021] By adopting the above technical solution, the sum of each first product is re-summed to obtain the final product sum. The larger the final product sum, the greater the overall probability of a failure in the centralized air conditioning and cooling system, combined with the currently detected abnormal operating data. If the final product sum is greater than the preset first product sum threshold, it indicates a high probability that a system failure has caused the abnormal operating data, and a warning is determined to be issued for this abnormal operating data. Conversely, if the final product sum is not greater than the first product sum threshold, a warning is determined not to be issued for the abnormal operating data, thereby effectively avoiding misjudgments of the issued warning.

[0022] Optionally, determining the system fault type corresponding to the abnormal operation data specifically includes:

[0023] Selecting the maximum first product from the first products corresponding to the same target abnormal dimension;

[0024] Determining the key fault type corresponding to each of the maximum first products as a hidden danger fault type, and determining whether the hidden danger fault types are the same;

[0025] If the hidden danger fault types are all the same, summing the maximum first products corresponding to the hidden danger fault types to obtain the sum of the second products;

[0026] If the sum of the second products is greater than a preset threshold value of the sum of the first products, the hidden danger fault type is determined to be the system fault type corresponding to the abnormal operation data;

[0027] The target abnormal dimension corresponding to each of the maximum first products is determined as a set of associated dimensions of the hidden danger fault type, and a mapping relationship is established between the hidden danger fault type and the set of associated dimensions.

[0028] By adopting the above technical solution, if the hidden danger fault types are all the same, it means that when abnormal operating data in each target abnormal dimension appears, the same fault type is likely to occur. This further indicates that for this hidden danger fault type, the abnormal operating data in the target abnormal dimension corresponding to each of the largest first products is strongly correlated with abnormal operating data at the time of the fault. If the sum of the second products is greater than the threshold for the sum of the first products, it indicates that the probability of a fault occurring when strongly correlated abnormal operating data appears is high. This not only further verifies that a fault exists in the centralized air conditioning and cooling system, but also accurately determines the type of fault, namely, the hidden danger fault type is used as the system fault type.

[0029] Optionally, the method further includes:

[0030] Obtaining a second historical dimension in which abnormal operating data of the centralized air conditioning and cooling system occurs under a historical fault of the system fault type, counting the first occurrence frequency of each second historical dimension, and selecting the second historical dimension with the third number from each second historical dimension in descending order of the first occurrence frequency to determine as a dimension prone to abnormality;

[0031] Obtaining associated historical dimensions where abnormal data fluctuations occur when an abnormal operation data of a single abnormality-prone dimension occurs, counting the second occurrence frequency of each associated historical dimension, and selecting the associated historical dimension with the fourth number from each associated historical dimension in descending order of the second occurrence frequency as the easily fluctuating dimension of the corresponding abnormality-prone dimension;

[0032] Calculating the third weight of each dimension prone to anomaly and the corresponding fourth weight of each dimension prone to fluctuation;

[0033] Obtaining a first actual fluctuation dimension of abnormal fluctuations in operating data of the centralized air-conditioning cooling system, and performing a rationality check on the system fault type based on the first actual fluctuation dimension, the third weight, and the corresponding fourth weights;

[0034] The issuing of a targeted warning based on the system fault type specifically includes:

[0035] After the rationality check is passed, a targeted warning is issued based on the system fault type.

[0036] By adopting the above technical solution, the greater the first occurrence frequency, the more likely the operating data in the corresponding second historical dimension will be abnormal when this system fault type occurs, thereby determining the dimension prone to abnormality. The occurrence of abnormal operating data in the dimension prone to abnormality is more likely to cause abnormal fluctuations in the operating data in the corresponding associated historical dimension, thereby determining the dimension prone to fluctuations corresponding to the dimension prone to abnormality. Finally, combining the dimensions of the actual fluctuation abnormalities of the centralized air conditioning and cooling system, namely the first actual fluctuation dimension, the third weight, and the corresponding fourth weight, the possibility of a system fault type being present in the current situation of abnormal operating data in the centralized air conditioning and cooling system is analyzed and determined. The determined system fault type is then re-verified, thereby more accurately determining the fault type of the centralized air conditioning and cooling system.

[0037] Optionally, performing rationality checking on the system fault type according to the first actual fluctuation dimension, the third weight, and the corresponding fourth weights specifically includes:

[0038] Determine the abnormal dimension in each corresponding easily fluctuating dimension where the first actual fluctuation dimension exists as a key abnormal dimension, and determine the target abnormal dimension corresponding to each abnormal operation data;

[0039] Calculating a second product of the third weight of the key abnormal dimension in each of the target abnormal dimensions and the fourth weight of the corresponding first actual fluctuation dimension;

[0040] The second products are summed to obtain a sum of third products. If the sum of the third products is greater than a preset threshold value of the sum of the second products, it is determined that the rationality check of the system fault type has passed.

[0041] By adopting the above technical solution, the larger the second product, the more likely the central air conditioning and cooling system is to have a system fault type when the corresponding operating data fluctuations in the first actual fluctuation dimension and the operating data in the key abnormal dimension are abnormal. Then, the sum of the third products is obtained by summing the second products. The larger the sum of the third products, the greater the likelihood that the central air conditioning and cooling system will have a system fault type, combined with the current abnormal operating data and the first actual fluctuation dimension where the abnormal fluctuation occurs. Finally, if the sum of the third products is greater than the preset second product sum threshold, then the system fault type rationality check is determined to have passed, re-verifying that the current central air conditioning and cooling system has a system fault type.

[0042] Optionally, the method further includes:

[0043] If there is no abnormal operation data in the centralized air-conditioning and cooling system, obtaining a second actual fluctuation dimension of abnormal fluctuation of the operation data in the centralized air-conditioning and cooling system;

[0044] Determine the easily abnormal dimension in each corresponding easily abnormal dimension that has the second actual fluctuation dimension as an important abnormal dimension, and calculate and sum the third product of the third weight of each important abnormal dimension and the fourth weight of each corresponding second actual fluctuation dimension to obtain the corresponding sum of the fourth products;

[0045] selecting a maximum sum of the fourth products from the sums of the fourth products, and issuing a fault risk alert of the system fault type if the maximum sum of the fourth products is greater than a preset third product sum threshold;

[0046] The normal value range of the important abnormal dimension corresponding to the sum of the largest fourth products is adjusted and optimized.

[0047] By adopting the above technical solution, the larger the sum of the fourth products, the greater the possibility of abnormal operation data in the corresponding important abnormal dimension, and the greater the risk of overall system failure type. If the maximum sum of the fourth products is greater than the preset third product sum threshold, it means that the possibility of abnormal data in the important abnormal dimension corresponding to the maximum fourth product sum and the risk of overall system failure type are both greater. In this case, a system failure type failure risk reminder is issued to the terminal, reminding personnel to go for timely maintenance. At the same time, it also means that the abnormal operation data of the important abnormal dimension corresponding to the maximum fourth product sum has not been identified, indicating that the normal value range of the important abnormal dimension corresponding to the maximum fourth product sum is not reasonable and needs to be adjusted and optimized to make the normal value range corresponding to this important abnormal dimension more reasonable and accurate.

[0048] In a second aspect of the present application, a device for monitoring abnormal data of a centralized air-conditioning and cooling system is provided, specifically comprising:

[0049] A data acquisition module, used to acquire system operation data of at least one dimension of a central air-conditioning and cooling system;

[0050] an abnormality verification module, configured to determine the corresponding system operation data as abnormal operation data if the system operation data is not within the corresponding normal value range, and determine whether to issue an early warning for the abnormal operation data based on at least one target fault type that is prone to occur in the centralized air-conditioning and cooling system and at least one corresponding target data abnormality dimension, wherein the target data abnormality dimension is a dimension in which the operation data abnormality is likely to occur when the corresponding target fault type occurs;

[0051] The abnormal warning module is used to determine the system fault type corresponding to the abnormal operation data and issue a targeted warning based on the system fault type.

[0052] By adopting the above technical solution, the data acquisition module obtains system operation data of at least one dimension. When the system operation data is determined to be abnormal operation data, the abnormality verification module determines whether to issue a targeted warning based on the target fault type and the corresponding at least one target data abnormal dimension. Finally, when the abnormal warning module determines to issue a warning, it determines the system fault type corresponding to the abnormal operation data and issues a targeted warning based on the system fault type.

[0053] In a third aspect of the present application, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is loaded and executed by a processor, the method steps as described in any one of the first aspects are performed.

[0054] In a fourth aspect of the present application, an electronic device is provided, specifically comprising:

[0055] A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the processor is used to load and execute the computer program stored in the memory so that the electronic device performs the method as described in any one of the first aspects.

[0056] In summary, the present application includes at least one of the following beneficial technical effects: If the system operation data is not within the corresponding normal value range, it means that the centralized air-conditioning and cooling system currently has abnormal operation data, indicating that the centralized air-conditioning and cooling system may have a fault that causes abnormal operation, or it may not have a fault but is only affected by normal load fluctuations. In order to improve the accuracy of abnormal data warnings, based on the target fault types that are prone to occur in the centralized air-conditioning and cooling system and the corresponding target data abnormality dimensions, combined with the currently occurring abnormal operation data, the risk of failure of the centralized air-conditioning and cooling system is analyzed, and then it is accurately determined whether to issue a targeted warning. If it is determined to issue a warning, then a warning is issued based on the system fault type, thereby avoiding false triggering of the warning and improving the accuracy of abnormal data warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a flow chart of a method for monitoring abnormal data in a centralized air-conditioning and cooling system provided by an embodiment of the present application;

[0058] Figure 2 This is a flow chart of another method for monitoring abnormal data of a centralized air-conditioning and cooling system provided by an embodiment of the present application;

[0059] Figure 3 This is a schematic structural diagram of an abnormal data monitoring device for a centralized air-conditioning cooling system provided by an embodiment of the present application;

[0060] Figure 4 It is a structural diagram of another abnormal data monitoring device for a centralized air-conditioning and cooling system provided in an embodiment of the present application.

[0061] Explanation of the accompanying symbols: 11. Data acquisition module; 12. Abnormality verification module; 13. Abnormality warning module; 14. Fault verification module; 15. Range adjustment module. DETAILED DESCRIPTION

[0062] In order to enable people skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0063] In the description of the embodiments of this application, words such as "exemplary," "for example," or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary," "for example," or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "for example," or "for example" is intended to present the relevant concepts in a concrete manner.

[0064] In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, B exists alone, and A and B exist at the same time. In addition, unless otherwise specified, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0065] See also Figure 1 The present application discloses a flowchart of a method for monitoring abnormal data in a centralized air conditioning and cooling system. This method can be implemented using a computer program or run on a centralized air conditioning and cooling system abnormal data monitoring device based on the von Neumann architecture. The computer program can be integrated into an application or run as a standalone tool application, specifically including:

[0066] S101: Obtain system operation data of at least one dimension of a central air-conditioning cooling system.

[0067] Specifically, in an embodiment of the present application, the application scenario of the centralized air-conditioning cooling system can be a commercial building or a data center. In other embodiments, the application scenario can also be a hospital or a large venue. The system operation data are various key parameters and performance indicators collected during the operation of the system. These data are used to monitor, analyze and maintain the normal operation of the system. The dimensions of the system operation data include but are not limited to temperature dimension, flow dimension, pressure dimension and equipment status dimension. Among them, the temperature includes the chilled water supply temperature, return water temperature, cooling water inlet temperature and outlet temperature, etc., which reflect the cooling effect and heat exchange efficiency of the system. The flow rate includes the flow rate of chilled water and cooling water, which directly affects the cooling capacity and energy consumption level of the system. The pressure includes the water supply pressure and return water pressure of the system. By monitoring the pressure, it can be determined whether the system is blocked or leaking. The equipment parameters include the operating status of the main equipment such as the chiller, water pump, cooling tower, etc. in the system.

[0068] Exemplarily, the pressure value of the pressure dimension can be obtained through a preset pressure sensor, and the operating data of the flow dimension can be obtained through a preset flow sensor, etc., and the operating data of some dimensions can be determined as the system operating data. In other embodiments, more other relevant sensors can also be used to obtain the operating data of all dimensions as the system operating data. In addition, the execution subject of the abnormal data monitoring of a centralized air-conditioning and cooling system of the present application is a server, and the server is wirelessly connected to various sensors such as pressure sensors, flow sensors, and terminals. A client or applet related to data monitoring is installed in the terminal. The server is the background server of the client or applet, which can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. Furthermore, when personnel need to monitor the operating data of the centralized air-conditioning and cooling system and issue an abnormal warning, a monitoring start instruction is sent through the client or applet in the terminal. After receiving the instruction, the server obtains the system operating data of at least one dimension through the corresponding sensor.

[0069] S102: If the system operation data is not within the corresponding normal value range, the corresponding system operation data is determined as abnormal operation data, and based on at least one target fault type that is prone to occur in the centralized air-conditioning and cooling system and at least one corresponding target data abnormality dimension, it is determined whether to issue an early warning for the abnormal operation data.

[0070] Specifically, after the system operation data is acquired, the system operation data of each dimension is compared with the normal value range of the corresponding dimension, wherein the normal value range is the value range of the operation data of the corresponding dimension when the centralized air conditioning and cooling system is operating normally. If the system operation data is not within the corresponding normal value range, it means that there is an abnormality in the system operation data of the corresponding dimension, and then it is determined to be abnormal operation data. At this time, the centralized air conditioning and cooling system may have a fault that causes abnormal operation, or it may not have a fault but is only affected by normal load fluctuations. In order to improve the accuracy of the abnormal data warning, it is necessary to further verify whether there is a fault risk, so as to accurately determine whether to issue an early warning. In an embodiment of the present application, a feasible implementation method is: based on the historical fault inspection and maintenance records of the centralized air conditioning and cooling system, the historical fault inspection and maintenance records include but are not limited to the historical fault types that need to be repaired and the corresponding historical operation data with abnormalities, determine the historical fault types that have occurred, and then count the first occurrence number of each historical fault type. The larger the first occurrence number, the more likely the centralized air conditioning and cooling system is to have the corresponding historical fault type. Then, according to the order of the first occurrence number from large to small, select the historical fault type with the preset first number from each historical fault type to determine it as the target fault type, that is, the fault type that is likely to occur.

[0071] Furthermore, based on the above-mentioned historical fault repair records, the first historical dimension of the historical operating data with abnormalities when a single target fault type occurs in the central air-conditioning cooling system is determined, and then the second occurrence number of each first historical dimension is counted, wherein the larger the second occurrence number, the more likely the operating data of the corresponding first historical dimension is to be abnormal when the target fault type occurs, and in descending order of the second occurrence number, the first historical dimension with the second number is selected from each first historical dimension to be determined as the target data abnormality dimension of the corresponding target fault type, that is, the dimension in which the operating data is more likely to be abnormal when the target fault type occurs.

[0072] Furthermore, the first weight of each target fault type and the second weight of each corresponding target data anomaly dimension are calculated, the first weight being the ratio of the first occurrence number of each target fault type to the sum of the first occurrence numbers of all target fault types, and the second weight being the ratio of the second occurrence number of a single target data anomaly dimension corresponding to the target fault type to the sum of the second occurrence numbers of all corresponding target data anomaly dimensions.

[0073] Finally, the abnormal operation data of each dimension, each first weight and the corresponding second weight are used to determine whether it is enough to issue an early warning for the abnormal operation data. A feasible determination method is: determine the corresponding target abnormal dimension through the properties of the sensor collected by the abnormal operation data of each dimension. For example, if the abnormal operation data is collected by a temperature sensor, then the corresponding target abnormal dimension is the temperature dimension. Then, the target fault type with the target abnormal dimension in the corresponding target data abnormal dimension is determined as the key fault type, and the first product of the first weight of each key fault type and the second weight of the corresponding target abnormal dimension is calculated. The larger the first product, the greater the possibility of the corresponding key fault type appearing when the abnormal operation data of the target abnormal dimension appears. Then, sum up the first products to obtain the corresponding sum of the first products, and sum up the sum of the first products again to obtain the final sum of the products. The larger the final sum of the products, the greater the overall possibility of the centralized air conditioning and cooling system failing in combination with the currently detected abnormal operation data. If the sum of the final products is greater than the preset threshold of the sum of the first products, it means that there is a high possibility that the abnormal operating data is caused by a system failure, and then an early warning is issued for these abnormal operating data; conversely, if the sum of the final products is not greater than the threshold of the sum of the first products, then it is determined that no early warning is issued for the abnormal operating data, so as to better avoid misjudgment of the issued data.

[0074] S103: If yes, determine the system fault type corresponding to the abnormal operation data, and issue a targeted warning based on the system fault type.

[0075] Specifically, if it is determined that an early warning is issued, then the system fault type that causes the abnormal operation data is determined. A feasible determination method is: from each first product corresponding to each key fault type, the first product corresponding to the same target abnormal dimension is screened out, and the maximum first product corresponding to this target abnormal dimension is selected. The key fault type corresponding to the maximum first product is the fault type that is most likely to exist when the abnormal operation data of this single target abnormal dimension appears, that is, the hidden danger fault type. By analogy, the hidden danger fault types corresponding to multiple target abnormal dimensions can be determined. Furthermore, if the hidden danger fault types are all the same, it means that when the abnormal operation data of each target abnormal dimension appears, the same fault type is more likely to appear, which further indicates that for this hidden danger fault type, the abnormal operation data of the target abnormal dimension corresponding to each maximum first product is the strongly correlated abnormal operation data when the fault occurs. Furthermore, the sum of each maximum first product is calculated to obtain the sum of the second products. If the sum of the second products is greater than the threshold of the sum of the first products, it indicates that the possibility of a fault occurring when strongly correlated abnormal operating data appears is high. This not only further verifies that the centralized air-conditioning cooling system does have a fault and the result of issuing the early warning determined in step S102 is correct, but also accurately determines the type of fault that has occurred, that is, the hidden danger fault type is used as the system fault type. Furthermore, the target abnormal dimension corresponding to each maximum first product is determined as the associated dimension set of this hidden danger fault type, and a mapping relationship is established between this hidden danger fault type and this associated dimension set. This facilitates subsequent personnel to quickly determine the risk of system failure and accurately lock the corresponding fault type once the operating data of each dimension in this associated dimension set are abnormal. Finally, the early warning information related to this system fault type is sent to the terminal of the maintenance personnel, thereby assisting the maintenance personnel to promptly and accurately resolve the hidden fault that causes abnormal operating data.

[0076] See also Figure 2 The present application discloses a flowchart of another method for monitoring abnormal data in a centralized air conditioning and cooling system. This method can be implemented using a computer program or run on a centralized air conditioning and cooling system abnormal data monitoring device based on the von Neumann architecture. The computer program can be integrated into an application or run as a standalone tool application, specifically including:

[0077] S201: Obtain system operation data of at least one dimension of a central air-conditioning cooling system.

[0078] S202: If the system operation data is not within the corresponding normal value range, the corresponding system operation data is determined as abnormal operation data, and based on at least one target fault type that is prone to occur in the centralized air-conditioning and cooling system and at least one corresponding target data abnormal dimension, it is determined whether to issue an early warning for the abnormal operation data.

[0079] S203: If yes, determine the system fault type corresponding to the abnormal operation data.

[0080] For details, please refer to steps S101-103, which will not be described in detail here.

[0081] S204: Obtain the second historical dimensions of abnormal operation data of the central air-conditioning and cooling system under historical faults of the system fault type, count the first occurrence frequency of each second historical dimension, and select the third second historical dimension from each second historical dimension in descending order of the first occurrence frequency to determine it as a dimension prone to abnormality.

[0082] S205: Obtain associated historical dimensions that cause abnormal data fluctuations when an abnormal operation data of a single abnormality-prone dimension occurs, count the second occurrence frequency of each associated historical dimension, and select the fourth associated historical dimension from each associated historical dimension in descending order of the second occurrence frequency to determine it as the easily fluctuating dimension of the corresponding abnormality-prone dimension.

[0083] Specifically, after determining the system fault type with a high probability of existing in the centralized air-conditioning and cooling system, based on the above-mentioned historical fault inspection and repair records, the second historical dimension in which the operating data of the centralized air-conditioning and cooling system is abnormal when the historical fault type is a system fault type, that is, when a historical fault of the system fault type occurs, is screened, and the first occurrence frequency of the second historical dimension is counted. The greater the first occurrence frequency, the more likely the operating number of the corresponding second historical dimension is to be abnormal when this system fault type occurs. Then, in order of the first occurrence frequency from large to small, the third number of the second historical dimension is selected from each second historical dimension, and it is determined as the dimension prone to abnormality, that is, the dimension in which the operating data is more likely to be abnormal when the system fault type occurs.

[0084] Furthermore, under the premise of the existence of a system fault type, when the operating data of a single dimension prone to abnormality is abnormal, the abnormal historical time node is determined through the corresponding sensor, and then the operating data of the remaining dimensions in the centralized air-conditioning and cooling system at this historical time node and the operating data before this historical time node are obtained from the historical data collection records of other sensors. Then, the corresponding historical operating data change curve is drawn through the MATLAB tool, and this historical operating data change curve is fitted with the corresponding normal operating data change curve. If the fitting rate is lower than the preset fitting rate threshold, it means that the operating data fluctuation of this remaining dimension is abnormal, and then the corresponding remaining dimension is determined as the associated historical dimension of the abnormal data fluctuation. Furthermore, the second occurrence frequency of each associated historical dimension is counted. The larger the second occurrence frequency, the more likely it is that abnormal operating data of the dimension prone to abnormality occurs, which will cause abnormal fluctuation of the operating data of the corresponding associated historical dimension. Finally, the fourth number of associated historical dimensions is selected from each associated historical dimension in descending order of the second occurrence frequency, and determined as the easily fluctuating dimension of the corresponding dimension prone to abnormality.

[0085] S206: Calculate the third weight of each dimension prone to anomaly and the corresponding fourth weight of each dimension prone to fluctuation.

[0086] S207: Obtain a first actual fluctuation dimension of abnormal fluctuations in operating data in the centralized air-conditioning cooling system, and perform a rationality check on the system fault type based on the first actual fluctuation dimension, the third weight, and the corresponding fourth weights.

[0087] Specifically, in the embodiment of the present application, the third weight is the ratio of the first occurrence frequency of each dimension prone to anomaly to the sum of the first occurrence frequencies of all dimensions prone to anomaly, and the fourth weight is the ratio of the second occurrence frequency of a single dimension prone to fluctuation corresponding to the dimension prone to anomaly to the sum of the second occurrence frequencies of all corresponding dimensions prone to fluctuation. Furthermore, the operating data of the dimensions other than the abnormal operating data at the current time and before the current time are obtained through the corresponding sensors, and then the operating data of each dimension are fitted through MATLAB to obtain the actual fluctuation curve, and fit it with the corresponding normal fluctuation curve. If the fitting rate does not exceed the preset fitting rate threshold, it means that the operating data fluctuation of the corresponding dimension is abnormal, and then the corresponding dimension is determined as the first actual fluctuation dimension.

[0088] Furthermore, the easily abnormal dimension with the first actual fluctuation dimension in the corresponding easily fluctuating dimensions is determined as the key abnormal dimension, and the target abnormal dimension corresponding to each abnormal operation data is determined. Then, the second product of the third weight of the key abnormal dimension in each target abnormal temperature and the fourth weight of the corresponding first actual fluctuation dimension is calculated. The larger the second product, the more likely the centralized air-conditioning and cooling system is to have a system fault type when the operation data fluctuation of the corresponding first actual fluctuation dimension and the operation data of the key abnormal dimension are abnormal. Then, the sum of each second product is summed to obtain the sum of the third products. The larger the sum of the third products, the greater the possibility of the centralized air-conditioning and cooling system having a system fault type in combination with the current abnormal operation data and the first actual fluctuation dimension where the abnormal fluctuation occurs. Finally, if the sum of the third products is greater than the preset second product sum threshold, then it is determined that the rationality check of the system fault type has passed, and it is verified again that the current centralized air-conditioning and cooling system has a system fault type.

[0089] S208: After the rationality check is passed, a targeted warning is issued based on the system fault type.

[0090] Specifically, please refer to step S103, which will not be described in detail here. In other embodiments, if there is no abnormal operation data in the system operation data of all dimensions obtained, then the second actual fluctuation dimension in which the operation data in the current centralized air-conditioning cooling system fluctuates abnormally is obtained. Then, the easily abnormal dimension with the second actual fluctuation dimension in the corresponding easily abnormal dimensions is determined as the important abnormal dimension, and the third weight of each important abnormal dimension and the third product of the fourth weight of each corresponding second actual fluctuation dimension are calculated and summed to obtain the corresponding sum of the fourth products. The larger the sum of the fourth products, the greater the possibility of abnormal operation data in the corresponding important abnormal dimension, and the greater the risk of overall system failure type. Further, the maximum sum of the fourth products is selected from the sums of the fourth products. If the maximum sum of the fourth products is greater than the preset third product sum threshold, it means that the possibility of abnormal important abnormal dimension data corresponding to the maximum sum of the fourth products and the risk of overall system failure type are both greater. Then, a fault risk reminder of the system failure type is issued to the terminal to remind personnel to go for timely maintenance. At the same time, it also shows that the operating data of the important abnormal dimension corresponding to the sum of the largest fourth products is abnormal but not identified, indicating that the normal numerical range of the important abnormal dimension corresponding to the sum of the largest fourth products is not reasonable and needs to be adjusted and optimized to make the normal numerical range corresponding to this important abnormal dimension more reasonable and accurate, thereby avoiding the problem of missed judgment of subsequent abnormalities. In an embodiment of the present application, a feasible adjustment and optimization method is: receiving the target normal numerical range sent by the terminal, so that the current operating data of the important abnormal dimension corresponding to the sum of the largest fourth products is not within this target normal numerical range.

[0091] The implementation principle of the abnormal data monitoring method for a centralized air-conditioning and cooling system in the embodiment of the present application is as follows: if the system operation data is not within the corresponding normal value range, it means that the centralized air-conditioning and cooling system currently has abnormal operation data, indicating that the centralized air-conditioning and cooling system may have a fault that causes abnormal operation, or it may not have a fault but is just affected by normal load fluctuations. In order to improve the accuracy of abnormal data warnings, based on the target fault types that are prone to occur in the centralized air-conditioning and cooling system and the corresponding target data abnormality dimensions, combined with the currently occurring abnormal operation data, the risk of failure of the centralized air-conditioning and cooling system is analyzed, and then it is accurately determined whether to issue a targeted warning. If it is determined to issue a warning, then a warning is issued based on the system fault type, thereby avoiding false triggering of the warning and improving the accuracy of abnormal data warnings.

[0092] The following are device embodiments of the present application, which can be used to implement the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0093] See Figure 3 , which is a schematic diagram of the structure of a device for monitoring abnormal data in a centralized air conditioning and cooling system according to an embodiment of the present application. This device for monitoring abnormal data in a centralized air conditioning and cooling system can be implemented as all or part of a device using software, hardware, or a combination of both. The device includes a data acquisition module 11, an abnormality verification module 12, and an abnormality warning module 13.

[0094] The data acquisition module 11 is used to obtain system operation data of at least one dimension of the central air conditioning and cooling system;

[0095] The abnormality verification module 12 is configured to determine that the system operation data is abnormal operation data if the system operation data is not within the corresponding normal value range, and determine whether to issue an early warning for the abnormal operation data based on at least one target fault type that is prone to occur in the centralized air conditioning and cooling system and at least one corresponding target data abnormality dimension, where the target data abnormality dimension is a dimension in which the operation data is prone to abnormality when the corresponding target fault type occurs;

[0096] The abnormal warning module 13 is used to determine the system fault type corresponding to the abnormal operation data and issue a targeted warning based on the system fault type.

[0097] Optionally, the abnormality verification module 12 is specifically configured to:

[0098] Obtain historical fault types that have occurred in the central air conditioning and cooling system, count the first occurrence times of each historical fault type, and select the first historical fault type from each historical fault type in descending order of the first occurrence times as the target fault type;

[0099] Obtain the first historical dimension where the operating data anomaly occurs when each target fault type occurs, count the number of second occurrences of each first historical dimension, and select the first historical dimension with the second number from each first historical dimension in descending order of the number of second occurrences to determine it as the target data anomaly dimension for the corresponding target fault type;

[0100] Calculate the first weight of each target fault type and the second weight of each corresponding target data anomaly dimension, where the first weight is the ratio of the first occurrence count of each target fault type to the sum of the first occurrence counts of all target fault types, and the second weight is the ratio of the second occurrence count of a single target data anomaly dimension corresponding to the target fault type to the sum of the second occurrence counts of all corresponding target data anomaly dimensions;

[0101] Whether to issue an early warning for the abnormal operating data is determined according to at least one abnormal operating data, the first weight, and the corresponding second weights.

[0102] Optionally, the abnormality verification module 12 is specifically configured to:

[0103] Determine the target abnormal dimension corresponding to each abnormal operation data, and determine the target fault type that has the target abnormal dimension in the corresponding target data abnormal dimension as the key fault type;

[0104] Calculate the first product of the first weight of each key fault type and the second weight of each corresponding target abnormality dimension and sum them to obtain the corresponding sum of the first products;

[0105] Summing the sums of the first products to obtain a final product sum, and if the final product sum is greater than a preset first product sum threshold, determining to issue an early warning for abnormal operating data;

[0106] If the final product sum is not greater than the first product sum threshold, it is determined that no warning is issued for the abnormal operation data.

[0107] Optionally, the abnormality warning module 13 is specifically used to:

[0108] Select the largest first product from the first products corresponding to the same target anomaly dimension;

[0109] Determine the key fault type corresponding to each largest first product as the hidden fault type, and determine whether the hidden fault types are the same;

[0110] If the hidden danger fault types are all the same, then sum the maximum first products corresponding to the hidden danger fault types to obtain the sum of the second products;

[0111] If the sum of the second products is greater than a preset threshold value of the sum of the first products, the hidden danger fault type is determined to be the system fault type corresponding to the abnormal operation data;

[0112] The target abnormal dimension corresponding to each largest first product is determined as a correlation dimension set of the hidden danger fault type, and a mapping relationship is established between the hidden danger fault type and the correlation dimension set.

[0113] Optional, such as Figure 4 As shown, the device further includes a fault checking module 14, which is specifically configured to:

[0114] Obtain the second historical dimension of abnormal operating data of the central air conditioning and cooling system under historical faults of the system fault type, count the first occurrence frequency of each second historical dimension, and select the second historical dimension with the third number from each second historical dimension in descending order of first occurrence frequency to determine it as the dimension prone to abnormality;

[0115] Obtain the associated historical dimensions that cause abnormal data fluctuations when a single abnormality-prone dimension's operating data anomaly occurs, count the second occurrence frequency of each associated historical dimension, and select the fourth associated historical dimension from each associated historical dimension in descending order of second occurrence frequency to determine it as the easily fluctuating dimension of the corresponding abnormality-prone dimension;

[0116] Calculate the third weight of each dimension prone to anomalies and the corresponding fourth weight of each dimension prone to fluctuations;

[0117] Obtain a first actual fluctuation dimension of abnormal fluctuations in operating data in a centralized air-conditioning cooling system, and perform a rationality check on a system fault type based on the first actual fluctuation dimension, the third weight, and corresponding fourth weights.

[0118] Optionally, the abnormality warning module 13 is further configured to:

[0119] After the rationality check is passed, a targeted warning is issued based on the system fault type.

[0120] Optionally, the fault checking module 14 is specifically configured to:

[0121] Determine the abnormal dimension with the first actual fluctuation dimension among the corresponding easily fluctuating dimensions as the key abnormal dimension, and determine the target abnormal dimension corresponding to each abnormal operation data;

[0122] Calculate the second product of the third weight of the key abnormal dimension in each target abnormal dimension and the fourth weight of the corresponding first actual fluctuation dimension;

[0123] The second products are summed to obtain the sum of the third products. If the sum of the third products is greater than a preset threshold value of the sum of the second products, it is determined that the rationality check of the system fault type has passed.

[0124] Optional, such as Figure 4 As shown, the device further includes a range adjustment module 15, which is specifically configured to:

[0125] If there is no abnormal operation data in the central air-conditioning cooling system, obtaining a second actual fluctuation dimension in which abnormal fluctuations occur in the operation data in the central air-conditioning cooling system;

[0126] Determine the easily abnormal dimension with the second actual fluctuation dimension among the corresponding easily abnormal dimensions as the important abnormal dimension, and calculate the third product of the third weight of each important abnormal dimension and the fourth weight of the corresponding second actual fluctuation dimension and sum them to obtain the corresponding sum of the fourth products;

[0127] Selecting a maximum sum of the fourth products from the sums of the fourth products, and issuing a fault risk alert of a system fault type if the maximum sum of the fourth products is greater than a preset threshold value of the sum of the third products;

[0128] The normal value range of the important abnormal dimension corresponding to the sum of the largest fourth product is adjusted and optimized.

[0129] It should be noted that the above embodiment provides a centralized air-conditioning and cooling system abnormal data monitoring device, when executing the centralized air-conditioning and cooling system abnormal data monitoring method, only uses the division of the above functional modules as an example. In actual applications, the above 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. In addition, the above embodiment provides a centralized air-conditioning and cooling system abnormal data monitoring device and a centralized air-conditioning and cooling system abnormal data monitoring method embodiment, which belong to the same concept. The implementation process is detailed in the method embodiment and will not be repeated here.

[0130] An embodiment of the present application further discloses a computer-readable storage medium, and the computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, a method for monitoring abnormal data of a centralized air-conditioning cooling system according to the above embodiment is adopted.

[0131] Among them, the computer program can be stored in a computer-readable medium, the computer program includes computer program code, the computer program code can be in the form of source code, object code, executable file or certain middleware, etc. The computer-readable medium includes any entity or device that can carry computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that computer-readable medium includes but is not limited to the above-mentioned components.

[0132] Among them, through this computer-readable storage medium, a centralized air-conditioning and cooling system abnormal data monitoring method of the above embodiment is stored in a computer-readable storage medium, and is loaded and executed on a processor to facilitate the storage and application of the above method.

[0133] An embodiment of the present application also discloses an electronic device, in which a computer program is stored in a computer-readable storage medium. When the computer program is loaded and executed by a processor, the above-mentioned method for monitoring abnormal data of a centralized air-conditioning and cooling system is adopted.

[0134] Among them, the electronic device can be an electronic device such as a desktop computer, a laptop computer or a cloud server, and the electronic device includes but is not limited to a processor and a memory. For example, the electronic device can also include input and output devices, network access devices and buses, etc.

[0135] Among them, the processor can adopt a central processing unit (CPU). Of course, according to actual usage, other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. can also be adopted. The general-purpose processor can adopt a microprocessor or any conventional processor, etc., and this application does not impose any restrictions on this.

[0136] Among them, the memory can be an internal storage unit of the electronic device, such as the hard disk or memory of the electronic device, or it can be an external storage device of the electronic device, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD) or flash memory card (FC) equipped on the electronic device. In addition, the memory can also be a combination of an internal storage unit and an external storage device of the electronic device. The memory is used to store computer programs and other programs and data required by the electronic device. The memory can also be used to temporarily store data that has been output or is to be output. This application does not impose any restrictions on this.

[0137] Among them, through this electronic device, the abnormal data monitoring method of a centralized air-conditioning and cooling system of the above embodiment is stored in the memory of the electronic device, and is loaded and executed on the processor of the electronic device for easy use.

[0138] The above description is merely an exemplary embodiment of the present disclosure and is not intended to limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. This application is intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for monitoring abnormal data of a central air conditioning cooling system, characterized in that: The method comprises: Obtain system operation data of at least one dimension of the central air conditioning and cooling system; If the system operation data is not within the corresponding normal value range, the corresponding system operation data is determined to be abnormal operation data, and based on at least one target fault type that is prone to occur in the centralized air-conditioning and cooling system and at least one corresponding target data abnormality dimension, it is determined whether to issue an early warning for the abnormal operation data, including: obtaining historical fault types that have occurred in the history of the centralized air-conditioning and cooling system, counting the first occurrence number of each of the historical fault types, and selecting the historical fault type with the first occurrence number from each of the historical fault types in descending order of the first occurrence number to determine it as the target fault type; Obtaining a first historical dimension in which an operating data anomaly occurs when each target fault type occurs, counting the number of second occurrences of each first historical dimension, and selecting the first historical dimension with the second number from each first historical dimension in descending order of the number of second occurrences as the target data anomaly dimension for the corresponding target fault type; Calculating a first weight for each target fault type and a second weight for each corresponding target data anomaly dimension, where the first weight is a ratio of a first occurrence count for each target fault type to a sum of first occurrence counts for all target fault types, and the second weight is a ratio of a second occurrence count for a single target data anomaly dimension corresponding to a target fault type to a sum of second occurrence counts for all corresponding target data anomaly dimensions; determining, based on at least one abnormal operating data, the first weight, and the corresponding second weights, whether to issue an early warning for the abnormal operating data, wherein the target data abnormality dimension is a dimension in which operating data abnormality is likely to occur when a corresponding target fault type occurs; If so, the system fault type corresponding to the abnormal operation data is determined, and a targeted warning is issued based on the system fault type.

2. The method for monitoring abnormal data of a centralized air-conditioning cooling system according to claim 1, characterized in that: The determining, based on the at least one abnormal operation data, the first weight, and the corresponding second weights, whether to issue an early warning for the abnormal operation data specifically includes: Determine a target abnormal dimension corresponding to each of the abnormal operation data, and determine a target fault type having the target abnormal dimension in each corresponding target data abnormal dimension as a key fault type; Calculating a first product of a first weight of each key fault type and a second weight of each corresponding target abnormality dimension and summing the results to obtain a corresponding sum of the first products; Summing the sums of the first products to obtain a final product sum, and if the final product sum is greater than a preset first product sum threshold, determining to issue an early warning for the abnormal operating data; If the final sum of the products is not greater than the first product sum threshold, it is determined that no warning is issued for the abnormal operation data.

3. The abnormal data monitoring method for a centralized air conditioning cooling system according to claim 2, characterized in that: Determining the system fault type corresponding to the abnormal operation data specifically includes: Selecting the maximum first product from the first products corresponding to the same target abnormal dimension; Determining the key fault type corresponding to each of the maximum first products as a hidden danger fault type, and determining whether the hidden danger fault types are the same; If the hidden danger fault types are all the same, summing the maximum first products corresponding to the hidden danger fault types to obtain the sum of the second products; If the sum of the second products is greater than a preset threshold value of the sum of the first products, the hidden danger fault type is determined to be the system fault type corresponding to the abnormal operation data; The target abnormal dimension corresponding to each of the maximum first products is determined as a set of associated dimensions of the hidden danger fault type, and a mapping relationship is established between the hidden danger fault type and the set of associated dimensions.

4. The method for monitoring abnormal data of a centralized air conditioning and cooling system according to claim 1, characterized in that: The method further comprises: Obtaining a second historical dimension in which abnormal operating data of the centralized air conditioning and cooling system occurs under a historical fault of the system fault type, counting the first occurrence frequency of each second historical dimension, and selecting the second historical dimension with the third number from each second historical dimension in descending order of the first occurrence frequency to determine as a dimension prone to abnormality; Obtaining associated historical dimensions where abnormal data fluctuations occur when an abnormal operation data of a single abnormality-prone dimension occurs, counting the second occurrence frequency of each associated historical dimension, and selecting the associated historical dimension with the fourth number from each associated historical dimension in descending order of the second occurrence frequency as the easily fluctuating dimension of the corresponding abnormality-prone dimension; Calculating the third weight of each dimension prone to anomaly and the corresponding fourth weight of each dimension prone to fluctuation; Obtaining a first actual fluctuation dimension of abnormal fluctuations in operating data of the centralized air-conditioning cooling system, and performing a rationality check on the system fault type based on the first actual fluctuation dimension, the third weight, and the corresponding fourth weights; The issuing of a targeted warning based on the system fault type specifically includes: After the rationality check is passed, a targeted warning is issued based on the system fault type.

5. The method for monitoring abnormal data of a centralized air-conditioning cooling system according to claim 4, characterized in that: The performing rationality check on the system fault type according to the first actual fluctuation dimension, the third weight, and the corresponding fourth weights specifically includes: Determine the abnormal dimension in each corresponding easily fluctuating dimension where the first actual fluctuation dimension exists as a key abnormal dimension, and determine the target abnormal dimension corresponding to each abnormal operation data; Calculating a second product of the third weight of the key abnormal dimension in each of the target abnormal dimensions and the fourth weight of the corresponding first actual fluctuation dimension; The second products are summed to obtain a sum of third products. If the sum of the third products is greater than a preset threshold value of the sum of the second products, it is determined that the rationality check of the system fault type has passed.

6. The method for monitoring abnormal data of a centralized air-conditioning cooling system according to claim 4, characterized in that: The method further comprises: If there is no abnormal operation data in the centralized air-conditioning and cooling system, obtaining a second actual fluctuation dimension of abnormal fluctuation of the operation data in the centralized air-conditioning and cooling system; Determine the easily abnormal dimension in each corresponding easily abnormal dimension that has the second actual fluctuation dimension as an important abnormal dimension, and calculate and sum the third product of the third weight of each important abnormal dimension and the fourth weight of each corresponding second actual fluctuation dimension to obtain the corresponding sum of the fourth products; selecting a maximum sum of the fourth products from the sums of the fourth products, and issuing a fault risk alert of the system fault type if the maximum sum of the fourth products is greater than a preset third product sum threshold; The normal value range of the important abnormal dimension corresponding to the sum of the largest fourth products is adjusted and optimized.

7. A device for monitoring abnormal data of a centralized air-conditioning and cooling system, used to implement the method for monitoring abnormal data of a centralized air-conditioning and cooling system according to any one of claims 1 to 6, characterized in that: include: A data acquisition module (11) is used to acquire system operation data of at least one dimension of a centralized air conditioning and cooling system; An abnormality verification module (12) is used to determine the corresponding system operation data as abnormal operation data if the system operation data is not within the corresponding normal value range, and determine whether to issue an early warning for the abnormal operation data based on at least one target fault type that is prone to occur in the centralized air-conditioning and cooling system and at least one corresponding target data abnormality dimension, wherein the target data abnormality dimension is a dimension in which the operation data abnormality is prone to occur when the corresponding target fault type occurs; The abnormal warning module (13) is used to determine the system fault type corresponding to the abnormal operation data and issue a targeted warning based on the system fault type.

8. A computer-readable storage medium storing a computer program, wherein: When the computer program is loaded and executed by a processor, the method according to any one of claims 1 to 6 is adopted.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor loads and executes the computer program, the method according to any one of claims 1 to 6 is adopted.

Images