Fault detection method and device, air conditioning system, computer equipment and storage medium

Abstract

The application discloses a fault detection method, a fault detection device, an air conditioning system, computer equipment and a storage medium. The method comprises the following steps: counting the total data amount of project running data in a slow data distribution recorder; in the case that the total data amount is less than a preset data amount, calculating the average value and the standard deviation of the project running data in the slow data distribution recorder, and determining the current alarm threshold according to the average value and the standard deviation; in the case that the total data amount is greater than the preset data amount, obtaining the effective percentage of the valid project running data in the slow data distribution recorder in all project running data in the slow data distribution recorder, arranging all project running data in the slow data distribution recorder from small to large to obtain sorted data, and determining the current alarm threshold from the sorted data according to the effective percentage; and determining whether a fault occurs according to the current alarm threshold. In this way, the alarm threshold is determined by using the project running data, the credibility of the alarm threshold is ensured, and the fault detection accuracy is improved.

Description

Technical Field

[0001] This application relates to the field of fault detection technology, and in particular to a fault detection method, a fault detection device, an air conditioning system, a computer device, and a storage medium. Background Technology

[0002] When performing fault detection on certain systems (such as chiller systems), rule-based methods can be used. In this method, it is necessary to determine the threshold for fault alarms. Summary of the Invention

[0003] This application provides a fault detection method, a fault detection device, an air conditioning system, a computer device, and a storage medium.

[0004] The fault detection method of this application includes: counting the total amount of project operation data in a slow data distribution recorder; if the total amount of data is less than a preset amount of data, calculating the average value and standard deviation of the project operation data in the slow data distribution recorder, and determining a current alarm threshold based on the average value and the standard deviation; if the total amount of data is greater than the preset amount of data, obtaining the percentage of valid project operation data in the slow data distribution recorder relative to the valid percentage of all project operation data in the slow data distribution recorder, arranging all project operation data in the slow data distribution recorder from smallest to largest to obtain sorted data, determining the current alarm threshold from the sorted data based on the valid percentage; and determining whether a fault has occurred based on the current alarm threshold.

[0005] In some implementations, the current alarm threshold includes an upper limit threshold and a lower limit threshold; determining the current alarm threshold based on the average value and the standard deviation includes: determining an adjustment value based on the standard deviation and a preset multiple; summing the average value and the adjustment value to obtain the upper limit threshold; and subtracting the average value and the adjustment value to obtain the lower limit threshold.

[0006] In some implementations, the current alarm threshold includes an upper limit threshold and a lower limit threshold. Determining the current alarm threshold from the sorted data based on the effective percentage includes: determining the upper limit selection position and the lower limit selection position based on the effective percentage; determining the project operation data corresponding to the upper limit selection position from the sorted data as the upper limit threshold; and determining the project operation data corresponding to the lower limit selection position from the sorted data as the lower limit threshold.

[0007] In some implementations, the fault detection method includes: deploying an adaptive expert rule base, the adaptive expert rule base including an initial alarm threshold; initializing a fast data distribution recorder and a slow data distribution recorder, both of which are used to record the project operation data; accessing the project operation data; updating the project operation data to the fast data distribution recorder; determining a first statistical value of the project operation data in the fast data distribution recorder; determining a second statistical value of the project operation data in the slow data distribution recorder; determining the deviation between the first statistical value and the second statistical value; if the deviation is greater than a preset deviation, updating the project operation data in the fast data distribution recorder to the slow data distribution recorder; updating the initial alarm threshold using the current alarm threshold; and determining whether a fault has occurred based on the alarm threshold of the adaptive expert rule base, wherein the alarm threshold is the initial alarm threshold or the current alarm threshold.

[0008] In some implementations, the first statistical value includes a first mean and a first standard deviation, and the second statistical value includes a second mean and a second standard deviation. Determining the deviation between the first statistical value and the second statistical value includes: determining the mean deviation between the first mean and the second mean; determining the standard deviation deviation between the first standard deviation and the second standard deviation. Updating the project running data in the fast data distribution recorder to the slow data distribution recorder when the deviation is greater than a preset deviation includes: updating the project running data in the fast data distribution recorder to the slow data distribution recorder when the mean deviation is greater than a preset mean deviation and the standard deviation deviation is greater than a preset standard deviation deviation.

[0009] In some implementations, the fault detection method includes: continuing to access the project operation data if the deviation is less than a preset deviation.

[0010] In some implementations, after updating the initial alarm threshold using the current alarm threshold, the fault detection method includes: continuing to access the project operation data.

[0011] The fault detection device according to this application includes a statistics module, a calculation module, an acquisition module, and a determination module. The statistics module is used to count the total amount of project operation data in the slow data distribution recorder. The calculation module is used to calculate the average value and standard deviation of the project operation data in the slow data distribution recorder when the total data amount is less than a preset data amount, and determine the current alarm threshold based on the average value and the standard deviation. The acquisition module is used to acquire the percentage of valid project operation data in the slow data distribution recorder relative to the valid data of all project operation data in the slow data distribution recorder when the total data amount is greater than the preset data amount, arrange all project operation data in the slow data distribution recorder from smallest to largest to obtain sorted data, and determine the current alarm threshold from the sorted data based on the valid percentage. The determination module is used to determine whether a fault has occurred based on the current alarm threshold.

[0012] An air conditioning system according to an embodiment of this application includes a processor, the processor being configured to: count the total amount of project operation data in a slow data distribution recorder; if the total amount of data is less than a preset amount of data, calculate the average value and standard deviation of the project operation data in the slow data distribution recorder, and determine a current alarm threshold based on the average value and the standard deviation; if the total amount of data is greater than the preset amount of data, obtain the percentage of valid project operation data in the slow data distribution recorder relative to the valid percentage of all project operation data in the slow data distribution recorder, arrange all project operation data in the slow data distribution recorder from smallest to largest to obtain sorted data, determine the current alarm threshold from the sorted data based on the valid percentage; and determine whether a fault has occurred based on the current alarm threshold.

[0013] The computer device according to embodiments of this application includes a memory and a processor. The memory stores computer-readable instructions, which, when executed by the processor, cause the processor to perform the fault detection method as described above.

[0014] The non-volatile computer-readable storage medium of embodiments of this application contains computer-executable instructions. When the computer-executable instructions are executed by one or more processors, the processors perform the fault detection method as described above.

[0015] The fault detection method, fault detection device, air conditioning system, computer equipment, and storage medium of this application realize the determination of alarm thresholds using project operation data, which can ensure the reliability of the output alarm thresholds and thus improve the accuracy of fault detection.

[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, wherein:

[0018] Figures 1 to 7 This is a flowchart illustrating the fault detection method according to an embodiment of this application;

[0019] Figure 8 This is a schematic diagram of the access project operation data of the fault detection method according to the embodiments of this application;

[0020] Figure 9 This is a flowchart illustrating the fault detection method according to an embodiment of this application;

[0021] Figure 10 This is a schematic diagram of a fault detection device according to an embodiment of this application;

[0022] Figure 11 This is a schematic diagram of a computer device according to an embodiment of this application; and

[0023] Figure 12 This is a schematic diagram showing the connection between the computer device and the computer-readable storage medium according to an embodiment of this application. Detailed Implementation

[0024] The embodiments of this application are described in detail below. These embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0025] Please refer to the following: Figure 1 and Figure 2 This application provides a fault detection method.

[0026] Fault detection methods include:

[0027] Step S11: Calculate the total amount of project running data in the slow data distribution recorder;

[0028] Step S12: If the total data volume is less than the preset data volume, calculate the average value and standard deviation of the project running data in the slow data distribution recorder, and determine the current alarm threshold based on the average value and standard deviation;

[0029] Step S13: When the total data volume is greater than the preset data volume, obtain the percentage of valid project running data in the slow data distribution recorder relative to the valid project running data in all project running data in the slow data distribution recorder, arrange all project running data in the slow data distribution recorder from smallest to largest to obtain sorted data, and determine the current alarm threshold from the sorted data based on the valid percentage.

[0030] Step S14: Determine whether a fault has occurred based on the current alarm threshold.

[0031] In related technologies, fault alarms in some devices or systems mainly originate from their own reported faults and the analysis results of relevant detection modules in the Building Management System (BMS). However, fault reporting by the device itself is limited by the data source and cannot effectively pinpoint the root cause; while the effectiveness of alarms based on the analysis results of relevant detection modules depends on the accuracy of the corresponding fault detection method. Fault detection methods can be broadly classified into three categories: the first is rule-based methods, which are relatively simple but require adjusting alarm thresholds for different projects, lacking project universality; the second is model-based methods, which rely on the constructed mathematical model, but building high-precision models is costly; and the third is data-based methods, which require a large amount of data support, and due to their black-box nature, the output alarms lack interpretability and have questionable reliability. Therefore, fault detection requires a highly reliable, universal method that can automatically adjust alarm thresholds.

[0032] The fault detection method of this application realizes the determination of alarm thresholds using project operation data, which can ensure the reliability of the output alarm thresholds and thus improve the accuracy of fault detection.

[0033] It is worth mentioning that the fault detection method of this application can be used to detect faults in various systems. The embodiments of this application are illustrated using a chiller plant system as an example. This example is provided for ease of understanding and should not be construed as limiting the scope of this application. Thus, the fault detection method of this application can detect faults in different aspects of a chiller plant system.

[0034] Specifically, a chiller plant system can be understood as a control system used to monitor the chiller plant. A chiller plant can be understood as a location where refrigeration facilities are centrally installed, such as large shopping malls, office buildings, factories, etc., requiring large-scale cooling. A chiller plant system facilitates data analysis and real-time monitoring of the chiller plant. The fault detection method of this application can detect faults in different aspects of the chiller plant system. These fault detection aspects include, but are not limited to, cooling water temperature detection, high-pressure protection detection, low-pressure protection detection, chilled water flow interruption detection, and chiller outlet water temperature detection, etc., and are not limited here. This application uses cooling water temperature detection in a chiller plant system as an example for illustration.

[0035] Specifically, the total amount of project execution data in the slow data distribution logger is calculated. This allows for the determination of the total data volume for the next calculation, and then the current alarm threshold is determined based on the total data volume and the project execution data in the slow data distribution logger. This facilitates the selection of an algorithm to process the project execution data in the slow data distribution logger based on the total data volume. It ensures computational efficiency, guarantees the reliability of the output alarm threshold, and thus improves the accuracy of fault detection.

[0036] The preset data volume can be a set value. The preset data volume can be equivalent to the minimum data volume; that is, if the total data volume is less than the minimum data volume, it means that the total amount of project operation data in the slow data distribution logger is relatively small, and the average and standard deviation of the project operation data in the slow data distribution logger can be calculated in a shorter time. After obtaining the average and standard deviation of the project operation data in the slow data distribution logger, the current alarm threshold is determined using these values.

[0037] In one embodiment, the total amount of project operation data in the slow data distribution logger can be 1000 cooling water temperature data points, and the preset data amount can be 5000 cooling water temperature data points. Therefore, since the total data amount is less than the preset data amount, the average and standard deviation of the 1000 cooling water temperature data points in the slow data distribution logger can be calculated, and the alarm threshold for the current cooling water temperature can be determined based on the average and standard deviation of the cooling water temperature data. Thus, because the total amount of project operation data in the slow data distribution logger is relatively small, calculating the average and standard deviation of all data can improve the accuracy of the current alarm threshold, thereby improving the accuracy of cooling water temperature fault detection.

[0038] The preset data volume can be a set value. The preset data volume can be equivalent to the minimum data volume; that is, if the total data volume is greater than the minimum data volume, it indicates that the total amount of project execution data in the slow data distribution logger is relatively large. Using the average and standard deviation of the project execution data in the slow data distribution logger to calculate the current alarm threshold would result in excessive computation, long calculation time, and high computational resource consumption. Therefore, it is possible to obtain the percentage of valid project execution data in the slow data distribution logger out of all valid project execution data. All project execution data in the slow data distribution logger are then sorted from smallest to largest, and the current alarm threshold is determined from the sorted data using the valid percentage.

[0039] It is worth mentioning that the effective percentage of all project operation data can be obtained through data filtering, setting an invalid percentage, etc., and there are no restrictions here.

[0040] In one embodiment, the distribution of all project running data in the slow data distribution recorder can be plotted, and then invalid project data can be observed and statistically analyzed. Invalid project data can be removed to obtain the amount of valid project running data, thus obtaining the effective percentage.

[0041] In another embodiment, the invalid percentage can be preset, for example, 2%, 5%, etc. This allows the valid percentage to be obtained.

[0042] Determining the current alarm threshold from sorted data using the effective percentage allows for a quick determination of the current alarm threshold, while reducing computational load and ensuring the reliability of the current alarm threshold.

[0043] The current alarm threshold can be used to determine whether a fault has occurred. For example, if the calculated current alarm threshold is 35°C, the system can determine whether a cooling water temperature fault has occurred based on this threshold.

[0044] Please refer to the following: Figure 2 and Figure 3 In some implementations, the current alarm threshold includes an upper limit threshold and a lower limit threshold. Step S12, "determining the current alarm threshold based on the average value and standard deviation," includes:

[0045] Step S121: Determine the adjustment value based on the standard deviation and the preset multiple;

[0046] Step S122: Summing the average and adjusted values ​​to obtain the upper limit threshold;

[0047] Step S123: Obtain the lower limit threshold by subtracting the average value from the adjusted value.

[0048] Specifically, the preset multiplier can be a set value. In one embodiment, the preset multiplier can be 3, and the adjustment value can be the preset multiplier multiplied by the standard deviation (i.e., adjustment value = 3 × standard deviation). The upper threshold can be the average value plus the preset multiplier multiplied by the standard deviation (i.e., upper threshold = average value + 3 × standard deviation). The lower threshold can be the average value minus the preset multiplier multiplied by the standard deviation (i.e., lower threshold = average value - 3 × standard deviation). In this way, the upper and lower thresholds of the current alarm threshold can be calculated.

[0049] In one embodiment, the upper limit of the current alarm threshold for cooling water temperature is calculated to be 38.15°C, and the lower limit of the current alarm threshold for cooling water temperature is calculated to be 34.25°C. A fault can be determined and an alarm will be triggered when the cooling water temperature is higher than 38.15°C or lower than 34.25°C.

[0050] Please refer to the following: Figure 2 and Figure 4 In some implementations, the current alarm threshold includes an upper threshold and a lower threshold. Step S13, "determining the current alarm threshold from the sorted data based on the effective percentage," includes:

[0051] Step S131: Determine the upper limit selection position and the lower limit selection position based on the effective percentage;

[0052] Step S132: Determine the project running data corresponding to the upper limit selection position from the sorted data as the upper limit threshold;

[0053] Step S133: Determine the lower limit selection position from the sorted data and use the corresponding project running data as the lower limit threshold.

[0054] In one embodiment, the effective percentage can be 95%, the upper limit can be selected as 1 - (1 - x) / 2, and the lower limit can be selected as (1 - x) / 2, where x is the effective percentage: 95%. Thus, the upper limit can be selected as 97.5%, and the lower limit can be selected as 2.5%. The project running data corresponding to 97.5% is determined from the sorted data as the upper limit threshold, and the project running data corresponding to 2.5% is determined from the sorted data as the lower limit threshold.

[0055] It is worth mentioning that the fault detection method of this application can be used to determine the alarm threshold for the chiller outlet water temperature of a chiller plant system. For example, in summer, users prefer to lower the temperature; for instance, the chiller outlet water temperature in summer is generally distributed between 6.5℃ and 7.5℃. Therefore, the average value can be 7.0℃, and the standard deviation can be 0.5℃. Thus, the upper alarm threshold for the chiller outlet water temperature can be 8.5℃, and the lower alarm threshold can be 5.5℃.

[0056] However, the chiller outlet water temperature in winter is approximately 7.0℃ to 12℃. Furthermore, considering the annual chiller outlet water temperature data, the total data volume and standard deviation are large. Therefore, the upper limit threshold can be determined by selecting the upper limit position from the sorted data, and the lower limit threshold can be determined by selecting the lower limit position from the sorted data. For example, the upper limit alarm threshold for chiller outlet water temperature could be 15.5℃, and the lower limit alarm threshold could be 6.5℃.

[0057] It should be noted that the examples and specific figures mentioned above are for the purpose of illustrating the implementation of this application and should not be construed as limiting the scope of protection of this application.

[0058] Please refer to the following: Figure 5 , Figure 6 and Figure 7 In some implementations, the fault detection method includes:

[0059] Step S15: Deploy the adaptive expert rule base, which includes the initial alarm threshold;

[0060] Step S16: Initialize the fast data distribution recorder and the slow data distribution recorder. Both the fast data distribution recorder and the slow data distribution recorder are used to record project running data.

[0061] Step S17: Access project runtime data;

[0062] Step S18: Update the project running data to the fast data distribution recorder;

[0063] Step S19: Determine the first statistical value of the project running data in the fast data distribution recorder;

[0064] Step S21: Determine the second statistic of the project running data in the slow data distribution recorder;

[0065] Step S22: Determine the deviation between the first statistical value and the second statistical value;

[0066] Step S23: If the deviation is greater than the preset deviation, update the project running data in the fast data distribution recorder to the slow data distribution recorder;

[0067] Step S24: Update the initial alarm threshold using the current alarm threshold;

[0068] Step S25: Determine whether a fault has occurred based on the alarm threshold of the adaptive expert rule base. The alarm threshold is either the initial alarm threshold or the current alarm threshold.

[0069] Thus, based on an adaptive expert rule base, alarm thresholds can be determined using project operation data, ensuring the reliability of the output alarm thresholds and improving the accuracy of fault detection. The fault detection method is universal, capable of determining when alarm thresholds need to be updated in different projects and automatically adjusting alarm thresholds.

[0070] First, an adaptive expert rule base is deployed. The adaptive expert rule base can be constructed from various rules. The fault detection method of this application is an adaptive method, possessing versatility, capable of determining when alarm thresholds need to be updated under different projects, and automatically adjusting alarm thresholds. Combining the adaptive method with the expert rule base constitutes the adaptive expert rule base. The adaptive expert rule base includes an initial alarm threshold, such as an initial alarm threshold for cooling water temperature fault detection. This initial alarm threshold can be a historical alarm threshold or a predicted alarm threshold; no limitation is made here. The fault detection method of this application can recalculate the alarm threshold of the adaptive expert rule base based on cooling water temperature data to determine whether a cooling water temperature fault has occurred.

[0071] In one embodiment, the initial alarm threshold for cooling water temperature fault detection can be 37°C, which is an alarm threshold predicted by an adaptive expert rule base. After accessing project operation data, the initial alarm threshold can be used to determine whether a fault has occurred; this is not limited here.

[0072] After accessing the project's operational data, initialize the fast data distribution logger and the slow data distribution logger. This ensures the accuracy of the alarm thresholds obtained for this project. Both the fast and slow data distribution loggers record project operational data, which can be the cooling water temperature detected at regular intervals. The fast data distribution logger records the cooling water temperature more frequently than the slow data distribution logger, resulting in a more realistic reading of the cooling water temperature.

[0073] Please see Figure 8 , Figure 8 This is a schematic diagram illustrating the integration of project runtime data. In one embodiment, ti can be 36℃, and the acquired real-time data is t, where t = ti. Therefore, 36℃ occurs 64 + 1 times. ti-1 can be 35℃, occurring 32 times. ti+1 can be 37℃, occurring 28 times.

[0074] It should be noted that the examples and specific figures mentioned above are for the purpose of illustrating the implementation of this application and should not be construed as limiting the scope of protection of this application.

[0075] Project operation data can be updated in real time to the fast data distribution recorder to determine the first statistical value of the project operation data in the fast data distribution recorder. A second statistical value of the project operation data in the slow data distribution recorder is then determined. Because the fast data distribution recorder records cooling water temperature more frequently than the slow data distribution recorder, there may be a discrepancy between the first and second statistical values.

[0076] If the deviation exceeds the preset deviation, the project operation data in the fast data distribution recorder is updated to the slow data distribution recorder. At this time, the multiple cooling water temperature data recorded in the fast data distribution recorder are the same as the multiple cooling water temperature data recorded in the slow data distribution recorder. Thus, the current alarm threshold can be determined based on the project operation data in the slow data distribution recorder.

[0077] Specifically, after updating the project operation data in the fast data distribution recorder to the slow data distribution recorder, the total amount of project operation data in the slow data distribution recorder is counted, and then the current alarm threshold is determined based on the total amount of data and the project operation data in the slow data distribution recorder.

[0078] The initial alarm threshold can be updated using the current alarm threshold. For example, the calculated current alarm threshold could be 35℃, and the initial alarm threshold could be 37℃. Thus, the alarm threshold in the adaptive expert rule base is the current alarm threshold, which is 35℃. Based on the alarm threshold of 35℃, it is determined whether a cooling water temperature malfunction has occurred.

[0079] The alarm threshold can be an initial alarm threshold. For example, the calculated current alarm threshold could be 37°C, and the initial alarm threshold could also be 37°C. Thus, the alarm threshold in the adaptive expert rule base is the initial alarm threshold, which is 37°C. The system determines whether a cooling water temperature malfunction has occurred based on the alarm threshold of 37°C.

[0080] Thus, based on an adaptive expert rule base, alarm thresholds can be determined using project operation data. This ensures the reliability of the output alarm thresholds, thereby improving the accuracy of fault detection.

[0081] Please see Figure 9 In some embodiments, the first statistical value includes a first mean and a first standard deviation, and the second statistical value includes a second mean and a second standard deviation. Step S22 includes:

[0082] Step S221: Determine the mean deviation between the first mean and the second mean;

[0083] Step S222: Determine the standard deviation of the first standard deviation and the second standard deviation;

[0084] Step S23 includes:

[0085] Step S231: If the average deviation is greater than the preset average deviation and the standard deviation is greater than the preset standard deviation, update the project running data in the fast data distribution recorder to the slow data distribution recorder.

[0086] Specifically, the first statistical value includes a first average value, which can be calculated by averaging the project operation data in the fast data distribution recorder. For example, the project operation data in the fast data distribution recorder includes multiple cooling water temperature data at different times: 35.1℃, 35.7℃, 36.2℃, 36.3℃, 36.5℃, 37.0℃, 37.1℃, etc. Averaging multiple cooling water temperature data yields a first average value of 36.2℃.

[0087] The second statistical value includes a second average value, which can be calculated by averaging the project operation data in the slow data distribution logger. For example, the project operation data in the slow data distribution logger includes multiple cooling water temperature data at different times: 35.1℃, 35.7℃, 36.2℃, 36.3℃, 36.5℃, etc. Averaging multiple cooling water temperature data yields a second average value of 35.8℃.

[0088] The first statistical value also includes the first standard deviation, which can be the overall standard deviation of the project operation data in the fast data distribution recorder. The project operation data in the fast data distribution recorder includes multiple cooling water temperature data at different times: 35.1℃, 35.7℃, 36.2℃, 36.3℃, 36.5℃, 37.0℃, 37.1℃, etc. The overall standard deviation of multiple cooling water temperature data is calculated, and the first standard deviation is found to be 0.65℃.

[0089] The second statistical value also includes the second standard deviation, which can be the overall standard deviation of the project operation data in the slow data distribution recorder. The project operation data in the slow data distribution recorder includes multiple cooling water temperature data at different times: 35.1℃, 35.7℃, 36.2℃, 36.3℃, 36.5℃, etc. The overall standard deviation of multiple cooling water temperature data is calculated, and the second standard deviation is found to be 0.50℃.

[0090] Using the first average value of 36.2℃ and the second average value of 35.8℃, the deviation of the average value can be determined to be 0.40℃; using the first standard deviation of 0.65℃ and the second standard deviation of 0.50℃, the deviation of the standard deviation can be determined to be 0.15℃.

[0091] Both the preset average deviation and the preset standard deviation are set values. The preset average deviation can be 0.30℃, and the preset standard deviation can be 0.10℃; there are no restrictions here. If the average deviation of 0.40℃ is greater than the preset average deviation of 0.30℃, and the standard deviation of 0.15℃ is greater than the preset standard deviation of 0.10℃, then the project running data in the fast data distribution recorder will be updated to the slow data distribution recorder.

[0092] Understandably, in some implementations, the fast data distribution recorder updates itself as soon as it acquires a cooling water temperature data point; that is, it updates the recorder promptly upon receiving each new cooling water temperature data point. Therefore, the cooling water temperature recorded by the fast data distribution recorder is closer to real-time conditions. The slow data distribution recorder, on the other hand, only updates itself after certain conditions are met. Therefore, if the average deviation is greater than a preset average deviation and the standard deviation is greater than a preset standard deviation, it indicates a significant difference between the project operation data in the fast data distribution recorder and the project operation data in the slow data distribution recorder. In this case, the project operation data in the fast data distribution recorder will be updated to match the project operation data in the slow data distribution recorder.

[0093] Please refer to it again. Figure 7 In some implementations, the fault detection method includes:

[0094] If the deviation is less than the preset deviation, continue to input project running data.

[0095] Specifically, if the deviation between the first and second statistical values ​​is less than a preset deviation, it indicates that the project operation data in the fast data distribution recorder and the project operation data in the slow data distribution recorder are not significantly different. Therefore, it is not necessary to update the project operation data in the fast data distribution recorder to the slow data distribution recorder, and project operation data can continue to be input. If the input of project operation data causes the deviation to exceed the preset deviation, then the project operation data in the fast data distribution recorder will be updated to the slow data distribution recorder.

[0096] In some implementations, project operation data in the fast data distribution recorder is only updated to the slow data distribution recorder if both the average deviation and standard deviation are greater than a preset average deviation. That is, if the average deviation is greater than a preset average deviation but the standard deviation is not greater than a preset standard deviation, then project operation data continues to be received; if the average deviation is not greater than a preset average deviation but the standard deviation is greater than a preset standard deviation, then project operation data continues to be received; if the average deviation is neither greater than a preset average deviation nor a preset standard deviation, then project operation data continues to be received. This ensures the reliability of the calculated alarm threshold, effectively reducing the number of data calculations and thus reducing the computational load.

[0097] In some implementations, after step S24, the fault detection method includes:

[0098] Continue to access project runtime data.

[0099] Specifically, after updating the initial alarm threshold using the current alarm threshold, the project operation data continues to be accessed.

[0100] In this way, the current alarm threshold can be dynamically updated, making the latest calculated alarm threshold more consistent with the current operating status of the chiller plant system. In one embodiment, the alarm threshold for detecting cooling water temperature faults in the chiller plant system may differ at different times of the same day. For example, due to environmental influences at noon, the alarm threshold for cooling water temperature may be 37°C; while due to environmental influences at night, the alarm threshold for cooling water temperature may be 35°C. Thus, after updating the initial alarm threshold using the current alarm threshold, continued access to project operation data can dynamically update the current alarm threshold, making the fault detection method more intelligent.

[0101] Please see Figure 11This application also provides a fault detection device 100. The fault detection device 100 includes a statistics module 11, a calculation module 12, an acquisition module 13, and a determination module 14. The fault detection method of this application can be implemented by the fault detection device 100 of this application, wherein step S11 can be implemented by the statistics module 11, step S12 can be implemented by the calculation module 12, step S13 can be implemented by the data acquisition module 13, and step S14 can be implemented by the determination module 14. That is, the statistics module 11 is used to count the total amount of project operation data in the slow data distribution recorder. The calculation module 12 is used to calculate the average value and standard deviation of the project operation data in the slow data distribution recorder when the total amount of data is less than a preset amount of data, and determine the current alarm threshold based on the average value and standard deviation. The acquisition module 13 is used to acquire the percentage of valid project operation data in the slow data distribution recorder relative to the total valid project operation data in the slow data distribution recorder when the total data volume exceeds the preset data volume. It then sorts all project operation data in the slow data distribution recorder from smallest to largest to obtain sorted data, and determines the current alarm threshold based on the valid percentage from the sorted data. The determination module 14 is used to determine whether a fault has occurred based on the current alarm threshold.

[0102] The fault detection device 100 of this application realizes the determination of alarm thresholds using project operation data. This ensures the reliability of the output alarm thresholds, thereby improving the accuracy of fault detection.

[0103] The explanations and descriptions of the fault detection method in any of the above embodiments also apply to the fault detection device 100 of this embodiment, and will not be repeated here. In some embodiments, corresponding modules or units can be added to the fault detection device 100 to implement the corresponding fault detection method. For example, the fault detection device 100 may also include a processing module for deploying an adaptive expert rule base; or, for example, the fault detection device 100 may also include an initialization module for initializing the fast data distribution recorder and the slow data distribution recorder, etc., without specific limitations here.

[0104] This application also provides an air conditioning system (not shown in the figures), which includes a processor for implementing the steps of the fault detection method in any of the above embodiments. For example, the processor is used to: count the total amount of project operation data in the slow data distribution recorder; if the total amount of data is less than a preset amount of data, calculate the average value and standard deviation of the project operation data in the slow data distribution recorder, and determine the current alarm threshold based on the average value and standard deviation; if the total amount of data is greater than the preset amount of data, obtain the percentage of valid project operation data in the slow data distribution recorder relative to the valid percentage of all project operation data in the slow data distribution recorder, arrange all project operation data in the slow data distribution recorder from smallest to largest to obtain sorted data, determine the current alarm threshold from the sorted data based on the valid percentage, and determine whether a fault has occurred based on the current alarm threshold. The air conditioning system in this embodiment can be the chiller plant system described in the above embodiments, and is not specifically limited thereto.

[0105] Please see Figure 11 This application also provides a computer device 200. The computer device 200 includes a memory 220 and a processor 240. The memory 220 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 240, the processor 240 performs the steps of the fault detection method of any of the above embodiments.

[0106] The computer device 200 of this application implements the method of determining alarm thresholds using project operation data. This ensures the reliability of the output alarm thresholds, thereby improving the accuracy of fault detection.

[0107] Please see Figure 12 This application also provides a non-volatile computer-readable storage medium 300 containing computer-executable instructions, which, when executed by one or more processors 240, causes the processors 240 to perform the steps of the fault detection method of any of the above embodiments.

[0108] For example, when the program is executed by processor 240, the following steps are implemented for the fault detection method:

[0109] Step S11: Calculate the total amount of project running data in the slow data distribution recorder;

[0110] Step S12: If the total data volume is less than the preset data volume, calculate the average value and standard deviation of the project running data in the slow data distribution recorder, and determine the current alarm threshold based on the average value and standard deviation;

[0111] Step S13: When the total data volume is greater than the preset data volume, obtain the percentage of valid project running data in the slow data distribution recorder relative to the valid project running data in all project running data in the slow data distribution recorder, arrange all project running data in the slow data distribution recorder from smallest to largest to obtain sorted data, and determine the current alarm threshold from the sorted data based on the valid percentage.

[0112] Step S14: Determine whether a fault has occurred based on the current alarm threshold.

[0113] It is understood that a computer program includes computer program code. Computer program code can be in the form of source code, object code, executable files, or some intermediate form. Computer-readable storage media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, external hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc.

[0114] Processor 240 can be a microcontroller chip that integrates a processor, memory, communication module, etc. The processor can refer to the processor included in the controller. The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0115] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0116] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the function involved, as will be understood by those skilled in the art to which embodiments of this application pertain.

[0117] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processing module, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0118] It should be understood that various parts of the embodiments of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0119] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0120] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0121] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0122] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A fault detection method, characterized in that, The fault detection method includes: The total amount of project runtime data in the statistical slow data distribution recorder; If the total data volume is less than the preset data volume, calculate the average value and standard deviation of the project running data in the slow data distribution recorder, and determine the current alarm threshold based on the average value and the standard deviation. When the total data volume is greater than the preset data volume, the percentage of valid project operation data in the slow data distribution recorder relative to the valid project operation data in all project operation data in the slow data distribution recorder is obtained, and all project operation data in the slow data distribution recorder are arranged from smallest to largest to obtain sorted data. The current alarm threshold is determined from the sorted data based on the valid percentage. Determine whether a fault has occurred based on the current alarm threshold; The current alarm threshold includes an upper limit threshold and a lower limit threshold; determining the current alarm threshold based on the average value and the standard deviation includes: The adjustment value is determined based on the standard deviation and the preset multiple; The upper limit threshold is obtained by summing the average value and the adjustment value. The lower limit threshold is obtained by subtracting the average value from the adjusted value. The fault detection method includes: Deploy an adaptive expert rule base, which includes an initial alarm threshold; Initialize the fast data distribution recorder and the slow data distribution recorder, both of which are used to record the project's running data; Access the project's runtime data; Update the project's runtime data to the fast data distribution recorder; Determine the first statistical value of the project running data in the fast data distribution recorder; Determine a second statistical value for the project running data in the slow data distribution recorder; Determine the deviation between the first statistical value and the second statistical value; If the deviation is greater than the preset deviation, the project running data in the fast data distribution recorder will be updated to the slow data distribution recorder; Update the initial alarm threshold using the current alarm threshold; Whether a fault has occurred is determined based on the alarm threshold of the adaptive expert rule base, wherein the alarm threshold is the initial alarm threshold or the current alarm threshold.

2. The fault detection method according to claim 1, characterized in that, The current alarm threshold includes an upper threshold and a lower threshold. Determining the current alarm threshold from the sorted data based on the effective percentage includes: The upper limit selection position and the lower limit selection position are determined based on the effective percentage. The project running data corresponding to the upper limit selection position is determined from the sorted data and used as the upper limit threshold. The project running data corresponding to the lower limit selection position is determined from the sorted data and used as the lower limit threshold.

3. The fault detection method according to claim 1, characterized in that, The first statistical value includes a first mean and a first standard deviation, and the second statistical value includes a second mean and a second standard deviation. Determining the deviation between the first statistical value and the second statistical value includes: Determine the average deviation between the first average value and the second average value; Determine the standard deviation of the first standard deviation and the second standard deviation; The step of updating the project running data in the fast data distribution recorder to the slow data distribution recorder when the deviation is greater than a preset deviation includes: If the average deviation is greater than the preset average deviation and the standard deviation is greater than the preset standard deviation, the project running data in the fast data distribution recorder will be updated to the slow data distribution recorder.

4. The fault detection method according to claim 1, characterized in that, The fault detection method includes: If the deviation is less than the preset deviation, the project operation data will continue to be accessed.

5. The fault detection method according to claim 1, characterized in that, After updating the initial alarm threshold using the current alarm threshold, the fault detection method includes: Continue to access the project's runtime data.

6. A fault detection device, implementing the fault detection method as described in claim 1, characterized in that, The fault detection device includes: The statistics module is used to count the total amount of project running data in the slow data distribution recorder; The calculation module is used to calculate the average value and standard deviation of the project running data in the slow data distribution recorder when the total data volume is less than the preset data volume, and to determine the current alarm threshold based on the average value and the standard deviation. The acquisition module is used to acquire, when the total data volume is greater than the preset data volume, the percentage of valid project operation data in the slow data distribution recorder relative to the valid project operation data in all project operation data in the slow data distribution recorder, arrange all project operation data in the slow data distribution recorder from smallest to largest to obtain sorted data, and determine the current alarm threshold from the sorted data based on the valid percentage. The determination module is used to determine whether a fault has occurred based on the current alarm threshold.

7. An air conditioning system that implements the fault detection method as described in claim 1, characterized in that, The air conditioning system includes a processor, the processor being used for: The total amount of project runtime data in the statistical slow data distribution recorder; If the total data volume is less than the preset data volume, calculate the average value and standard deviation of the project running data in the slow data distribution recorder, and determine the current alarm threshold based on the average value and the standard deviation. When the total data volume is greater than the preset data volume, the percentage of valid project operation data in the slow data distribution recorder relative to the valid project operation data in all project operation data in the slow data distribution recorder is obtained, and all project operation data in the slow data distribution recorder are arranged from smallest to largest to obtain sorted data. The current alarm threshold is determined from the sorted data based on the valid percentage. Whether a fault has occurred is determined based on the current alarm threshold.

8. A computer device, comprising a memory and a processor, wherein the memory stores computer-readable instructions, which, when executed by the processor, cause the processor to perform the fault detection method according to any one of claims 1 to 5.

9. A non-volatile computer-readable storage medium comprising computer-executable instructions, which, when executed by one or more processors, cause the processors to perform the fault detection method according to any one of claims 1 to 5.

Images