A HVAC fault handling recommendation method based on operating data

Abstract

The present invention provides a HVAC fault handling recommendation method based on operating data, which belongs to the field of data processing technology, and specifically includes: determining a reference data group in a valid data group based on the degree of data similarity in different operating stages, determining the correlation coefficients between operating data in different operating stages and different fault types based on the analysis results of the operating data of the reference data group, and determining the associated fault type and comprehensive correlation coefficient of the reference data group through the correlation coefficients with different fault types, obtaining the difficulty of troubleshooting different associated fault types, and combining the associated fault types and comprehensive correlation coefficients of different reference data groups to determine the fault types that need to be troubleshooted and the troubleshooting sequence, thereby improving the efficiency of fault handling.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a HVAC fault handling recommendation method based on operating data. Background Art

[0002] During the installation process of HVAC, due to problems with the installation or the HVAC equipment itself, there will inevitably be operational failures. Therefore, in order to solve the above technical problems, in the invention patent application CN202410107439.8 "HVAC Fault Identification and Measures Recommendation Method and System Based on Knowledge Graph", the nodes with the highest ranking of the user's search and the keywords and intentions are checked, and the matching HVAC fault causes and recommended measures are output, thereby improving the troubleshooting time of the operation and maintenance personnel. However, the above technical solution has the following technical problems:

[0003] Different types of faults often manifest themselves differently in different operating stages of the HVAC, such as startup, cooling, and temperature control. Therefore, if the analysis results of the operating data of different operating stages cannot be combined to output fault handling recommendations, the efficiency of fault troubleshooting cannot be guaranteed.

[0004] In view of the above technical problems, the present invention provides a HVAC fault handling recommendation method based on operation data. Summary of the invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] According to one aspect of the present invention, a method for recommending HVAC fault handling based on operating data is provided.

[0007] A recommended method for handling HVAC faults based on operating data, specifically comprising:

[0008] S1: determining weather data corresponding to HVAC operation data, dividing the operation data into different operation data groups according to the similarity of the weather data, and screening valid data groups in the operation data groups based on the similarity and the amount of the operation data;

[0009] S2: obtaining data similarity of operation data in different valid data groups at different operation stages, and determining a reference data group in the valid data group based on the data similarity at different operation stages;

[0010] S3, based on the analysis result of the operation data of the reference data group, determining the correlation coefficients between the operation data of different operation stages and different fault types, and determining the associated fault type and the comprehensive correlation coefficient of the reference data group through the correlation coefficients with the different fault types;

[0011] S4 obtains the difficulty of troubleshooting different associated fault types, and combines the associated fault types and comprehensive correlation coefficients of different reference data groups to determine the fault types that need to be troubleshooted and the troubleshooting sequence.

[0012] The beneficial effects of the present invention are:

[0013] 1. The reference data group in the valid data group is determined based on the data similarity at different operation stages, thereby realizing the screening of valid data groups with low data quality from the perspective of data similarity, improving the recognition accuracy of fault types that need to be eliminated, and avoiding the impact of data quality issues.

[0014] 2. The troubleshooting order of the fault types that need to be troubleshooted is determined by utilizing the troubleshooting difficulty of the associated fault types, the associated fault types of the reference data group, and the comprehensive correlation coefficient. This not only takes into account the impact of the troubleshooting difficulty of different fault types that need to be troubleshooted on the troubleshooting efficiency, but also takes into account the comprehensive correlation coefficients with different reference data groups. It also achieves priority troubleshooting of fault types with a higher probability of occurrence, thereby improving the overall identification and processing efficiency.

[0015] A further technical solution is that the weather data corresponding to the operating data is determined based on the weather data at a corresponding moment of the operating data.

[0016] A further technical solution is that the weather data includes weather type, temperature, wind speed and precipitation data.

[0017] A further technical solution is to divide the operation data into different operation data groups, specifically including:

[0018] Determine the weather data similarity coefficient between different operation data by using the deviation of weather data in different dimensions;

[0019] The operating data whose weather data similarity coefficient meets the requirements are divided into the same operating data group.

[0020] A further technical solution is that the method for determining the troubleshooting order is:

[0021] The fault types that need to be checked and processed are taken as the fault types to be checked, and the fault occurrence probabilities of different fault types to be checked are determined according to the comprehensive correlation coefficients between different fault types to be checked and different reference data groups;

[0022] The troubleshooting priority coefficients of different fault types to be troubleshooted are determined according to the fault occurrence probabilities and troubleshooting difficulties of different fault types to be troubleshooted, and the troubleshooting order of different fault types to be troubleshooted is determined based on the troubleshooting priority coefficients.

[0023] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0024] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0026] Figure 1 It is a flow chart of the recommended method for handling HVAC faults based on operating data;

[0027] Figure 2 is a flow chart of a method for screening a valid data group in a running data group;

[0028] Figure 3 is a flow chart of a method for determining a reference data group in a valid data group;

[0029] Figure 4 is a flow chart of a method for determining an associated fault type of a reference data group;

[0030] Figure 5 The present invention is a flowchart of a method for determining a troubleshooting processing sequence. DETAILED DESCRIPTION

[0031] In order to enable those 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 specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0032] Different types of faults often manifest themselves differently in different operating stages of the HVAC, such as startup, cooling, and temperature control. Therefore, it is necessary to combine the analysis results of the operating data of different operating stages to output fault handling recommendations.

[0033] Specifically, the present application determines the troubleshooting sequence of different fault types according to the correlation coefficients between the operation data of different operation stages and the different fault types, thereby realizing troubleshooting of the faults.

[0034] Including the following technical solutions:

[0035] Valid data group: The valid data group in the operating data group is screened based on the similarity of the weather data and the operating data. The operating data group with a temperature deviation within 5% corresponding to the weather data and a deviation within 10% corresponding to the operating data is taken as a valid data group.

[0036] Reference data group: The valid data group whose operating data deviations in different operating stages are all within 3% is used as the reference data group.

[0037] Associated fault type: The fault types whose correlation coefficients with different operation stages are all greater than 0.7 are taken as associated fault types, and the comprehensive correlation coefficient between the reference data group and the associated fault type is determined using the average value of the correlation coefficients with different stages.

[0038] Fault types to be investigated and processed: Using the average value of the comprehensive correlation coefficients with different reference data groups and combining the difficulty of investigation and processing, the order of investigation and processing for different associated fault types is determined from large to small.

[0039] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, a recommended method for handling HVAC faults based on operating data is provided, which specifically includes:

[0040] S1: determining weather data corresponding to HVAC operation data, dividing the operation data into different operation data groups according to the similarity of the weather data, and screening valid data groups in the operation data groups based on the similarity and the amount of the operation data;

[0041] Furthermore, the weather data corresponding to the operating data is determined based on the weather data at a corresponding moment of the operating data.

[0042] It should be noted that the weather data includes weather type, temperature, wind speed and precipitation data.

[0043] It is understandable that the operation data is divided into different operation data groups, specifically including:

[0044] Determine the weather data similarity coefficient between different operation data by using the deviation of weather data in different dimensions;

[0045] The operating data whose weather data similarity coefficient meets the requirements are divided into the same operating data group.

[0046] Specifically, Figure 2 As shown, the method for screening the valid data group in the running data group is:

[0047] Determining data reliability of the operation data in the operation data group according to the data amount of the operation data in the operation data group;

[0048] Determining an average value of weather data similarity coefficients between different operating data in the operating data group based on the similarity of weather data corresponding to different operating data in the operating data group, and determining the weather data similarity of the operating data in the operating data group using the average value of the weather data similarity coefficients;

[0049] The comprehensive reliability of the valid data group is determined based on the data reliability and weather data similarity, and the comprehensive reliability is used to screen the valid data group in the operation data group.

[0050] It should also be noted that when the comprehensive reliability of the operating data group meets the requirements, the operating data group is determined to be a valid data group.

[0051] Furthermore, the data reliability of the operating data is determined according to a preset data volume interval corresponding to the data volume of the operating data, and specifically, the preset data reliability matched by the corresponding preset data volume interval is used as the data reliability of the operating data.

[0052] In another embodiment, the method for screening the valid data group in the running data group is:

[0053] S11: obtaining the data volume of the operation data in the operation data group, and determining whether the data volume of the operation data in the operation data group is less than a preset data volume; if so, determining that the operation data group does not belong to a valid data group; if not, proceeding to the next step;

[0054] S12 determines whether the amount of data in the operation data group is greater than the data volume limit value, and if so, proceeds to the next step, if not, proceeds to step S15;

[0055] S13: determining an average value of weather data similarity coefficients between different operating data in the operating data group based on the similarity of weather data corresponding to different operating data in the operating data group, and judging whether the average value of weather data similarity coefficients meets the requirement; if so, determining that the operating data group belongs to a valid data group; if not, proceeding to the next step;

[0056] S14: using the weather data similarity coefficient to determine the similar operation data in the operation data, and judging whether the amount of the similar operation data is greater than the preset similar data amount; if so, determining that the operation data group belongs to the valid data group; if not, proceeding to the next step;

[0057] S15: determining the weather data similarity of the operation data in the operation data group by using the average value of the weather data similarity coefficient, and determining the data reliability of the operation data in the operation data group according to the data volume of the operation data in the operation data group;

[0058] S16 determines the comprehensive reliability of the valid data group based on the data reliability and weather data similarity, and uses the comprehensive reliability to screen the valid data group in the operating data group.

[0059] S2: obtaining data similarity of operation data in different valid data groups at different operation stages, and determining a reference data group in the valid data group based on the data similarity at different operation stages;

[0060] Specifically, Figure 3 As shown, the method for determining the reference data group in the valid data group is:

[0061] Determining an average value of data similarity of operation data at different operation stages in the valid data group according to data similarity at different operation stages, and determining similarity coefficients of operation data at different operation stages using the average value of data similarity;

[0062] The data reference value of the valid data group is determined by using the average value of the similarity coefficients of the operation data in different operation stages, and the reference data group in the valid data group is determined by using the data reference value.

[0063] Furthermore, when the data reference value of the valid data group is greater than a preset reference threshold, it is determined that the valid data group belongs to the reference data group.

[0064] In another embodiment, the method for determining the reference data group in the valid data group is:

[0065] Determine an average value of data similarity of operation data of different operation stages in the valid data group according to the data similarity in different operation stages, and determine whether there is an operation stage in the valid data group whose data similarity does not meet the requirement by using the average value of the data similarity; if so, determine that the valid data group does not belong to the reference data group; if not, proceed to the next step;

[0066] Determine the deviation operation data of different operation stages based on the data similarity of the operation data of different operation stages, and judge whether there is an operation stage in which the data amount of the deviation operation data does not meet the requirement in the valid data group. If so, determine that the valid data group does not belong to the reference data group. If not, proceed to the next step.

[0067] Determine the data deviation evaluation amount of different operation stages according to the data amount of the deviation operation data of different operation stages and the data similarity degree of the deviation operation data, and judge whether there is an operation stage in the valid data group whose data deviation evaluation amount does not meet the requirements, if so, determine that the valid data group does not belong to the reference data group, if not, proceed to the next step;

[0068] The operating data similarity coefficients of different operating stages are determined using the average value of the data similarity and the data deviation assessment value, the data reference value of the valid data group is determined using the average value of the operating data similarity coefficients of different operating stages, and the reference data group in the valid data group is determined using the data reference value.

[0069] S3, based on the analysis result of the operation data of the reference data group, determining the correlation coefficients between the operation data of different operation stages and different fault types, and determining the associated fault type and the comprehensive correlation coefficient of the reference data group through the correlation coefficients with the different fault types;

[0070] Furthermore, the correlation coefficients between the operating data and different fault types are determined based on the matching conditions between the operating data feature quantities of the operating data and the different fault types, and specifically determined based on the number of matching operating data feature quantities.

[0071] It is understandable that if Figure 4 As shown, the method for determining the associated fault type of the reference data group is:

[0072] Based on the correlation coefficients between the operation data at different operation stages and the fault type, the operation data at different operation stages whose correlation coefficients are greater than a preset correlation threshold are determined and used as the strongly correlated operation data;

[0073] Determine the data correlation coefficient between different operating stages and the fault type according to the data volume proportion of strongly correlated operating data in different operating stages;

[0074] Determine the weight values ​​of different operation stages based on the data amounts of different operation stages, and determine the comprehensive correlation coefficient between the reference data group and the fault type in combination with the data correlation coefficient between the different operation stages and the fault type;

[0075] The associated fault types among the fault types are determined by using the comprehensive correlation coefficient.

[0076] Furthermore, the value range of the comprehensive correlation coefficient is between 0 and 1, wherein the larger the comprehensive correlation coefficient of the fault type is, the higher the degree of correlation between the reference data group and the fault type is.

[0077] It should also be noted that the method for determining the associated fault type of the reference data group is:

[0078] Based on the correlation coefficients between the operation data of different operation stages and the fault types, an average value of the correlation coefficients between the operation data of different operation stages and the fault types is determined, and the associated operation stages in the operation stages are determined according to the average value of the correlation coefficients;

[0079] Determine weight values ​​of different associated operation stages based on data amounts of different associated operation stages, and determine a comprehensive correlation coefficient between the reference data group and the fault type according to the sum of the weight values ​​of the associated operation stages;

[0080] The associated fault types among the fault types are determined by using the comprehensive correlation coefficient.

[0081] It should be further explained that the method for determining the associated fault type of the reference data group is:

[0082] Based on the correlation coefficients between the operation data of different operation stages and the fault type, determining whether there is operation data with a correlation coefficient greater than a preset correlation threshold in the reference data group, if so, proceeding to the next step, if not, determining that the fault type does not belong to the associated fault type of the reference data group;

[0083] Based on the correlation coefficients between the operation data of different operation stages and the fault types, an average value of the correlation coefficients between the operation data of different operation stages and the fault types is determined, and whether there is an associated operation stage in the operation stage according to the average value of the correlation coefficients, if yes, proceeding to the next step, if not, determining that the fault type does not belong to the associated fault type of the reference data group;

[0084] Determine the operation data whose correlation coefficients of different operation stages are greater than a preset correlation threshold, and use them as strongly correlated operation data; determine the data correlation coefficients of different operation stages and the fault type according to the data volume and data volume proportion of the strongly correlated operation data of different operation stages; judge whether there is an operation stage whose data correlation coefficient is greater than the preset correlation coefficient; if so, proceed to the next step; if not, determine that the fault type does not belong to the associated fault type of the reference data group;

[0085] Determine the weight values ​​of different operation stages based on the data amounts of different operation stages, and determine the comprehensive correlation coefficient between the reference data group and the fault type in combination with the data correlation coefficient between the different operation stages and the fault type;

[0086] The associated fault types among the fault types are determined by using the comprehensive correlation coefficient.

[0087] S4 obtains the difficulty of troubleshooting different associated fault types, and combines the associated fault types and comprehensive correlation coefficients of different reference data groups to determine the fault types that need to be troubleshooted and the troubleshooting sequence.

[0088] Specifically, it should be noted that the method for determining the type of fault that needs to be troubleshooted is:

[0089] Taking the associated fault types of different reference data groups as the fault types for alternative troubleshooting, and determining the associated reference data group of the fault type for alternative deviation processing according to whether the fault type for alternative troubleshooting belongs to the associated fault type in the reference data group;

[0090] Determining basic weight values ​​of different associated reference data groups according to comprehensive correlation coefficients of different associated reference data groups, and determining occurrence probabilities of different fault types for alternative troubleshooting based on the sum of the basic weight values ​​of different associated reference data groups;

[0091] The occurrence probability is used to determine the fault type that needs to be troubleshooted among the candidate fault types for troubleshooting.

[0092] Furthermore, the candidate troubleshooting fault types whose occurrence probability is greater than a preset probability threshold are taken as the fault types that need to be troubleshooted.

[0093] It can be understood that the troubleshooting difficulty is determined according to the preset troubleshooting difficulty corresponding to the associated fault type.

[0094] Specifically, Figure 5 As shown, the method for determining the troubleshooting processing order is:

[0095] The fault types that need to be checked and processed are taken as the fault types to be checked, and the fault occurrence probabilities of different fault types to be checked are determined according to the comprehensive correlation coefficients between different fault types to be checked and different reference data groups;

[0096] The troubleshooting priority coefficients of different fault types to be troubleshooted are determined according to the fault occurrence probabilities and troubleshooting difficulties of different fault types to be troubleshooted, and the troubleshooting order of different fault types to be troubleshooted is determined based on the troubleshooting priority coefficients.

[0097] Based on the above embodiments, the present invention achieves the following beneficial effects:

[0098] 1. The reference data group in the valid data group is determined based on the data similarity at different operation stages, thereby realizing the screening of valid data groups with low data quality from the perspective of data similarity, improving the recognition accuracy of fault types that need to be eliminated, and avoiding the impact of data quality issues.

[0099] 2. The troubleshooting order of the fault types that need to be troubleshooted is determined by utilizing the troubleshooting difficulty of the associated fault types, the associated fault types of the reference data group, and the comprehensive correlation coefficient. This not only takes into account the impact of the troubleshooting difficulty of different fault types that need to be troubleshooted on the troubleshooting efficiency, but also takes into account the comprehensive correlation coefficients with different reference data groups. It also achieves priority troubleshooting of fault types with a higher probability of occurrence, thereby improving the overall identification and processing efficiency.

[0100] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0101] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0102] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A method for recommending HVAC fault handling based on operating data, characterized in that: Specifically include: Determine weather data corresponding to HVAC operation data, divide the operation data into different operation data groups according to the similarity of the weather data, and screen valid data groups in the operation data groups based on the similarity and the data volume of the operation data; Acquire data similarity of operation data in different valid data groups at different operation stages, and determine a reference data group in the valid data group based on the data similarity at different operation stages; Based on the analysis results of the operation data of the reference data group, determining the correlation coefficients between the operation data of different operation stages and different fault types, and determining the associated fault type and the comprehensive correlation coefficient of the reference data group through the correlation coefficients with the different fault types; Obtain the troubleshooting difficulty of different associated fault types, and determine the fault types and troubleshooting sequence that need to be troubleshooted based on the associated fault types and comprehensive correlation coefficients of different reference data groups; The method for screening the valid data group in the running data group is: Determining data reliability of the operation data in the operation data group according to the data amount of the operation data in the operation data group; Determining an average value of weather data similarity coefficients between different operating data in the operating data group based on the similarity of weather data corresponding to different operating data in the operating data group, and determining the weather data similarity of the operating data in the operating data group using the average value of the weather data similarity coefficients; Determining the comprehensive reliability of the valid data group based on the data reliability and weather data similarity, and screening the valid data group in the operation data group using the comprehensive reliability; The method for determining the reference data group in the valid data group is: Determining an average value of data similarity of operation data at different operation stages in the valid data group according to data similarity at different operation stages, and determining similarity coefficients of operation data at different operation stages using the average value of data similarity; Determining the data reference value of the valid data group by using the average value of the similarity coefficient of the operation data in different operation stages, and determining the reference data group in the valid data group by using the data reference value; The correlation coefficients between the operating data and different fault types are determined according to the matching conditions between the operating data feature quantities of the operating data and the different fault types, and specifically determined according to the number of matching operating data feature quantities.

2. The HVAC fault handling recommendation method based on operating data according to claim 1, characterized in that: The weather data corresponding to the operating data is determined according to the weather data at a time corresponding to the operating data.

3. The HVAC fault handling recommendation method based on operation data according to claim 1, characterized in that: The weather data includes weather type, temperature, wind speed and precipitation data.

4. The HVAC fault handling recommendation method based on operation data according to claim 1, characterized in that: When the comprehensive reliability of the operating data group meets the requirement, the operating data group is determined to be a valid data group.

5. The HVAC fault handling recommendation method based on operation data according to claim 1, characterized in that: The method for determining the associated fault type of the reference data group is: Based on the correlation coefficients between the operation data at different operation stages and the fault type, the operation data at different operation stages whose correlation coefficients are greater than a preset correlation threshold are determined and used as the strongly correlated operation data; Determine the data correlation coefficient between different operating stages and the fault type according to the data volume proportion of strongly correlated operating data in different operating stages; Determine the weight values ​​of different operation stages based on the data amounts of different operation stages, and determine the comprehensive correlation coefficient between the reference data group and the fault type in combination with the data correlation coefficient between the different operation stages and the fault type; The associated fault types among the fault types are determined by using the comprehensive correlation coefficient.

6. The HVAC fault handling recommendation method based on operation data according to claim 1, characterized in that: The troubleshooting difficulty is determined according to a preset troubleshooting difficulty corresponding to the associated fault type.

7. The HVAC fault handling recommendation method based on operation data according to claim 1, characterized in that: The method for determining the troubleshooting order is: The fault types that need to be checked and processed are taken as the fault types to be checked, and the fault occurrence probabilities of different fault types to be checked are determined according to the comprehensive correlation coefficients between different fault types to be checked and different reference data groups; The troubleshooting priority coefficients of different fault types to be troubleshooted are determined according to the fault occurrence probabilities and troubleshooting difficulties of different fault types to be troubleshooted, and the troubleshooting order of different fault types to be troubleshooted is determined based on the troubleshooting priority coefficients.

Images