Bus duct abnormal temperature rise alarm method, device and equipment with dynamic threshold adjustment

Abstract

The present invention discloses a bus duct abnormal temperature rise alarm method, device and equipment with dynamic threshold adjustment, and relates to the field of temperature early warning technology. The method includes: collecting bus duct data of multiple projects, establishing a time series data set, performing data analysis on the time series data set, and performing joint identification based on expert models and data analysis results to establish an initial dynamic threshold table; establishing a real-time monitoring data set; taking the current time node as time zero, performing backtracking analysis, and establishing backtracking analysis results; configuring a backtracking window, performing dynamic threshold adjustment on the initial dynamic threshold table, and establishing a dynamic temperature threshold; using the dynamic temperature threshold to perform temperature comparison of the real-time monitoring data set at time zero, and establishing a temperature rise alarm. The technical problem of the fixed and inflexible bus duct temperature monitoring threshold in the prior art is solved, and the technical effect of improving the accuracy and timeliness of the bus duct abnormal temperature rise alarm is achieved by dynamically adjusting the threshold.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature early warning, and in particular to a method, device and equipment for abnormal temperature rise alarm of a bus duct with dynamic threshold adjustment. Background Art

[0002] As an important transmission equipment in the power system, bus duct is widely used in high and low voltage power transmission, distribution and power supply systems. With the advancement of industrialization, the load conditions and ambient temperature of bus duct often change, making its working state difficult to predict. As an important precursor to bus duct failure, abnormal temperature increase often means potential risks to equipment, such as insulation damage, overload or fire and other safety hazards. Therefore, real-time and accurate temperature monitoring is crucial to ensure the safe operation of bus duct. However, traditional bus duct temperature monitoring methods often use fixed temperature thresholds as alarm standards. This method ignores the complexity and variability of the bus duct operating environment, resulting in low alarm accuracy and easy false alarms or omissions. Summary of the invention

[0003] The present application provides a bus duct abnormal temperature rise alarm method, device and equipment with dynamic threshold adjustment, which solves the technical problem of fixed bus duct temperature monitoring threshold and lack of flexibility in the prior art.

[0004] In view of the above problems, the present application provides a bus duct abnormal temperature rise alarm method, device and equipment with dynamic threshold adjustment.

[0005] In a first aspect of the present application, a bus duct abnormal temperature rise alarm method with dynamic threshold adjustment is provided, the method comprising:

[0006] The bus duct data of multiple projects are collected to establish a time series data set, which includes temperature changes, ambient temperature, and load conditions. The time series data set is analyzed, and joint identification is performed based on the expert model and the data analysis results to establish an initial dynamic threshold table. After the system is running, real-time data monitoring of the target bus duct is performed to establish a real-time monitoring data set. The current time node is used as the time zero point, and a backtracking analysis based on the real-time monitoring data set at the time zero point is performed to establish a backtracking analysis result. A backtracking window is configured according to the backtracking analysis result, and the real-time monitoring data set in the backtracking window is used to adjust the dynamic threshold of the initial dynamic threshold table to establish a dynamic temperature threshold. The dynamic temperature threshold is used to compare the temperature of the real-time monitoring data set at the time zero point to establish a temperature rise alarm.

[0007] In a second aspect of the present application, a bus duct abnormal temperature rise alarm device with dynamic threshold adjustment is provided, the device comprising:

[0008] Data acquisition module: collects bus duct data from multiple projects and establishes a time series data set, which includes temperature changes, ambient temperature, and load conditions. The time series data set is analyzed, and joint identification is performed based on the expert model and data analysis results to establish an initial dynamic threshold table; real-time monitoring module: after the system is running, the target bus duct is monitored in real time to establish a real-time monitoring data set; retrospective analysis module: takes the current time node as the time zero point, performs retrospective analysis based on the real-time monitoring data set at the time zero point, and establishes the retrospective analysis result; threshold adjustment module: configures the retrospective window according to the retrospective analysis result, uses the real-time monitoring data set in the retrospective window to adjust the dynamic threshold of the initial dynamic threshold table, and establishes a dynamic temperature threshold; early warning module: uses the dynamic temperature threshold to compare the temperature of the real-time monitoring data set at the time zero point, and establishes a temperature rise alarm.

[0009] The third aspect of the present application provides an electronic device, comprising: a memory for storing executable instructions; a processor for executing the executable instructions stored in the memory to implement the bus duct abnormal temperature rise alarm method with dynamic threshold adjustment provided in the present application.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] First, the bus duct data of multiple projects are collected to establish a time series data set, which includes temperature changes, ambient temperature, and load conditions. The time series data set is analyzed, and joint identification is performed based on the expert model and data analysis results to establish an initial dynamic threshold table. After the system is running, the target bus duct is monitored in real time to establish a real-time monitoring data set. Then, the current time node is taken as the time zero point, and a backtracking analysis based on the real-time monitoring data set at time zero is performed to establish the backtracking analysis results. Further, a backtracking window is configured according to the backtracking analysis results, and the real-time monitoring data set in the backtracking window is used to adjust the dynamic threshold of the initial dynamic threshold table to establish a dynamic temperature threshold. Finally, the dynamic temperature threshold is used to compare the temperature of the real-time monitoring data set at time zero, and a temperature rise alarm is established. The technical problem of the fixed and inflexible bus duct temperature monitoring threshold in the prior art is solved, and the accuracy and timeliness of the abnormal temperature rise alarm of the bus duct are improved by dynamically adjusting the threshold. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A schematic flow chart of a bus duct abnormal temperature rise alarm method with dynamic threshold adjustment provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of the structure of a bus duct abnormal temperature rise alarm device with dynamic threshold adjustment provided in an embodiment of the present application;

[0015] Figure 3 This is a schematic diagram of the structure of an exemplary electronic device of the present application.

[0016] Explanation of the accompanying drawings: data acquisition module 11, real-time monitoring module 12, retrospective analysis module 13, threshold adjustment module 14, early warning module 15, processor 21, memory 22, input device 23, output device 24. DETAILED DESCRIPTION

[0017] The present application solves the technical problem of fixed bus duct temperature monitoring threshold and lack of flexibility in the prior art by providing a bus duct abnormal temperature rise alarm method, device and equipment with dynamic threshold adjustment.

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0019] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0020] Embodiment 1, as Figure 1 As shown, the present application provides a bus duct abnormal temperature rise alarm method with dynamic threshold adjustment, wherein the method includes:

[0021] The bus duct data of multiple projects are collected to establish a time series data set, which includes temperature changes, ambient temperature, and load conditions. The time series data set is analyzed, and joint identification is performed based on the expert model and the data analysis results to establish an initial dynamic threshold table.

[0022] Data collection is performed on multiple bus ducts, including the temperature changes, ambient temperature and load conditions of the bus ducts, and the collected data are organized into a time series data set in chronological order. Data analysis is performed on the time series data set, including trend analysis of temperature changes, load conditions and ambient temperature, to reveal the correlation between different parameters and the potential law of abnormal temperature rise. On the basis of data analysis, joint identification is performed in combination with expert models. The expert model is a rule system established based on the experience of domain experts or based on historical data, which can assist the system in obtaining the normal range of temperature changes and factors that may cause abnormal temperature rise. Through the joint identification of data analysis and expert models, initial dynamic thresholds are set for parameters such as temperature changes, ambient temperature and load conditions of the bus duct, and an initial dynamic threshold table is formed. The initial dynamic threshold table provides starting values ​​for subsequent real-time monitoring and threshold adjustment, and provides a reference for normal temperature fluctuations and potential risks during actual operation.

[0023] After the system is running, real-time data monitoring of the target bus duct is carried out to establish a real-time monitoring data set.

[0024] After the system starts running, the actual operation data of the target bus duct is monitored and collected in real time, including parameters such as temperature, ambient temperature, load conditions, etc., to form a real-time monitoring data set.

[0025] The current time node is taken as time zero, and a backtracking analysis based on the real-time monitoring data set at the time zero is performed to establish a backtracking analysis result.

[0026] During the real-time monitoring process of the system, the current time node is set as time zero, and a retrospective analysis is performed on the real-time monitoring data set, that is, the data within a certain time range is analyzed from the current time point forward to understand the law of temperature changes in different time periods, and then generate retrospective analysis results.

[0027] Furthermore, the performing of the backtracking analysis based on the real-time monitoring data set at the time zero to establish the backtracking analysis result includes:

[0028] The real-time monitoring data set corresponding to the time zero point is used as the standard comparison data, input into the backtracking analysis channel, and the channel initialization of the backtracking analysis channel is performed; after the backtracking direction of the real-time monitoring data set is created based on the time zero point, the backtracking analysis channel analysis of each time data under the backtracking direction in the real-time monitoring data set is performed to establish the channel analysis result; the fluctuation characteristics of the channel analysis result are accumulated, the fluctuation characteristic accumulation result is triggered and identified through the fluctuation accumulation threshold, the backtracking node is determined by using the trigger identification result, and the backtracking node is used as the backtracking analysis result.

[0029] Specifically, the real-time monitoring data set corresponding to the current time node (time zero) is used as the standard comparison data and input into the retrospective analysis channel. The retrospective analysis channel is the path or framework for performing retrospective analysis, which defines the data input, processing method and output format required for the analysis; based on time zero, the retrospective direction of the real-time monitoring data set is created, that is, starting from time zero, the analysis is performed retrospectively to the past time points; after the retrospective direction is determined, the data analysis is performed point by point in time according to the retrospective direction in the real-time monitoring data set, and the analysis results of each time point are integrated to form the channel analysis results; after the retrospective analysis is completed, the fluctuation characteristics of the channel analysis results at each moment are accumulated (by counting the data fluctuations, it is identified whether the data has abnormal fluctuations), and the fluctuation accumulation threshold is used to trigger the accumulated results. Trigger identification is to compare the fluctuation characteristics with the set threshold. If the fluctuation of the data exceeds the predetermined threshold, the identification of the retrospective node is triggered, and the key time nodes (retrospective nodes) are determined. These retrospective nodes can reflect the key moments of temperature changes or the occurrence of abnormal events.

[0030] Furthermore, the accumulating fluctuation characteristics of the channel analysis results and triggering identification of the fluctuation characteristic accumulation results by using a fluctuation accumulation threshold include:

[0031] Obtain the ambient temperature difference and load change difference in the channel analysis results; use the ambient temperature difference and the load change difference to perform temperature impact fitting, and establish an impact characteristic value according to the temperature impact fitting result; obtain the temperature change difference in the channel analysis results, perform consistency analysis according to the temperature change difference and the temperature impact fitting result, and establish characteristic compensation; after correcting the impact characteristic value according to the characteristic compensation, perform fluctuation characteristic accumulation calculation, and establish a fluctuation characteristic accumulation result.

[0032] The ambient temperature difference and the load change difference are extracted from the channel analysis results. The ambient temperature difference and the load change difference represent the magnitude of changes in the ambient temperature and load conditions during the retrospective analysis process, respectively.

[0033] Based on the obtained ambient temperature difference and load change difference, temperature impact fitting is performed, that is, a model is constructed using statistical methods (such as regression analysis) to analyze how the ambient temperature difference and load change difference affect the temperature change of the bus duct; based on the temperature impact fitting results, the impact characteristic value is established, and the impact characteristic value indicates the degree of influence of ambient temperature change and load change on the temperature change of the bus duct. For example, the fitting result may be a linear model, where the temperature change (ΔT) is related to the ambient temperature difference (ΔT e ) and the load change difference (ΔL) is: ΔT = aΔT e+bΔL, where a and b are coefficients obtained through regression analysis, indicating the degree of influence of ambient temperature and load change on temperature change; the actual ambient temperature difference and load change difference are substituted into the fitting formula to calculate the corresponding influence characteristic value (temperature change).

[0034] The temperature change difference, that is, the temperature change amplitude of the bus duct during the retrospective time period, is obtained from the channel analysis results; a consistency analysis is performed based on the obtained temperature change difference and the previous temperature impact fitting results, and the deviation between them is evaluated by comparing the actual temperature change difference with the impact fitting results; based on the results of the consistency analysis, a feature compensation is generated, which is used to correct the inconsistency between the temperature change and the fitting results and make up for the deviation in the model; based on the corrected impact characteristic value, a fluctuation feature accumulation calculation is performed, that is, compared with the preset fluctuation accumulation threshold to obtain the fluctuation feature accumulation result, which represents the overall intensity and trend of the temperature fluctuation and can be used to determine whether there is abnormal fluctuation in the equipment.

[0035] A backtracking window is configured according to the backtracking analysis result, and the initial dynamic threshold table is dynamically adjusted using the real-time monitoring data set in the backtracking window to establish a dynamic temperature threshold.

[0036] The lookback window refers to a fixed time range used to analyze historical data and evaluate temperature change trends; the size of the lookback window is usually determined based on the characteristics of the equipment operation and the amount of historical data required. For example, the lookback window can be data from the past 24 hours, 48 ​​hours, or longer.

[0037] Based on the backtracking analysis results, the size and starting point of the backtracking window are determined; the real-time monitoring data set within the backtracking window is used to dynamically adjust the initial dynamic threshold table, thereby establishing a dynamic temperature threshold, which can be adjusted as the system operating status changes.

[0038] Furthermore, the step of adjusting the dynamic threshold value of the initial dynamic threshold value table by using the real-time monitoring data set in the backtracking window to establish the dynamic temperature threshold value further includes:

[0039] The window length of the lookback window is obtained, and a window timing factor is established based on the window length; the monitoring data in the lookback window is mapped with the window timing factor, and then input into the dynamic threshold impact model to establish a dynamic threshold impact result; after matching the real-time monitoring data set at time zero with the initial dynamic threshold table as matching data, the matching result is adjusted based on the dynamic threshold impact result to establish the dynamic temperature threshold.

[0040] Specifically, the window length of the lookback window is determined according to the lookback analysis results, and a window timing factor is established based on the length of the lookback window. The window timing factor is used to describe the time characteristics of the lookback data set, that is, to describe the importance of data at different time points in the dynamic threshold adjustment process. For example, if the lookback window is 24 hours, the timing factor may be weighted according to the data changes in the past few hours, with more recent time points having larger weights and more distant time points having smaller weights.

[0041] The monitoring data (such as temperature changes, load data, etc.) within the lookback window are mapped to the established time series factors. Specifically, the weight of the data at each time point is calculated to determine its contribution to the dynamic threshold adjustment. The mapped data is input into the dynamic threshold impact model, which is established through data analysis, regression or machine learning methods to calculate how the monitoring data in different time periods affect the final dynamic temperature threshold; the real-time monitoring data set at time zero is used as matching data to match the initial dynamic threshold table to determine whether the current temperature is within the normal range; the matching result is adjusted based on the dynamic threshold impact result to obtain a new dynamic temperature threshold.

[0042] The dynamic temperature threshold is used to perform temperature comparison of the real-time monitoring data set at time zero, and a temperature rise alarm is established.

[0043] The real-time temperature is compared with the dynamic temperature threshold previously generated through retrospective analysis and real-time data adjustment. If the real-time temperature exceeds the upper limit of the dynamic temperature threshold, a temperature rise alarm is triggered, indicating that the device temperature is abnormal and there may be risks such as overload or failure.

[0044] Furthermore, the establishing of a temperature rise alarm includes:

[0045] An alarm event is triggered according to the comparison result, wherein the alarm event includes an alarm level created based on the comparison result, a temperature point exceeding a threshold, a current temperature value, and a dynamic temperature threshold; and the alarm event is sent as an alarm through a preset communication channel.

[0046] Optionally, an alarm event is triggered based on the comparison result between the real-time temperature and the dynamic temperature threshold. The alarm event contains multiple important information, such as the alarm level created based on the comparison result (based on the severity of the temperature exceeding the standard, such as warning or emergency level), the specific temperature point exceeding the threshold, the current temperature value, and the dynamic temperature threshold when the alarm is triggered; the alarm event is sent to relevant personnel or systems in a timely manner through a preset communication channel (such as SMS, email, App notification) to ensure that the operator can quickly understand the equipment status and take necessary countermeasures, such as adjusting the load or shutting down for inspection, thereby effectively preventing equipment damage or safety accidents.

[0047] Furthermore, the method further comprises:

[0048] The alarm event is synchronized to the abnormal feedback unit; based on the abnormal feedback unit, the alarm frequency trigger authentication of the measuring point is performed, and the alarm frequency trigger authentication result is established; the real feedback corresponding to the alarm event is obtained, and an adjustment database is generated based on the real feedback and the alarm frequency trigger authentication result, and feedback management is performed according to the adjustment database.

[0049] Optionally, the triggered alarm event is synchronized to the abnormal feedback unit, which is responsible for further processing and analysis of the alarm event; based on the abnormal feedback unit, the system will perform alarm frequency trigger authentication of the measuring point to evaluate whether the alarm frequency of a certain measuring point within a certain time range reaches the preset standard, so as to determine whether the alarm is normal or needs further confirmation. On this basis, the system will obtain the real feedback corresponding to the alarm event, that is, the actual feedback information obtained through manual or automatic detection after the alarm, to verify whether the alarm is accurate or whether there is a false alarm. Combining the real feedback and the alarm frequency trigger authentication results, the system will generate an adjustment database to record the accuracy and frequency of the alarm; based on the adjustment database, the system can perform feedback management, optimize and adjust the alarm mechanism to improve the sensitivity and accuracy of the system, avoid unnecessary false alarms or missed alarms, and ensure that the alarm system is more efficient and accurate in actual operation.

[0050] Furthermore, the generating of an adjustment database based on the real feedback and the alarm frequency triggering authentication result, and performing feedback management according to the adjustment database, includes:

[0051] Determine the proportion of real alarms in the alarm frequency trigger authentication result; if the proportion of real alarms is higher than a preset ratio threshold, generate a focus monitoring instruction; and perform focus monitoring management of the corresponding measuring point based on the focus monitoring instruction.

[0052] Specifically, by analyzing the proportion of real alarms in the alarm frequency trigger authentication results, the proportion of alarms that truly reflect equipment abnormalities among all alarms is determined; if the proportion of real alarms is higher than the preset proportion threshold, the system believes that the alarm frequency of the measuring point is high and accurate, and it will generate a focus monitoring instruction, requiring stricter monitoring of the measuring point; according to the generated focus monitoring instruction, the system will perform focus monitoring management on the corresponding measuring point, continuously track the temperature changes or other key parameters of the measuring point, to ensure that potential problems are discovered and handled in time.

[0053] Furthermore, the method further comprises:

[0054] If the real alarm ratio is lower than the preset ratio threshold, a dynamic threshold optimization instruction is generated; and the initial dynamic threshold table correction is performed according to the dynamic threshold optimization instruction.

[0055] If the proportion of real alarms is lower than the preset ratio threshold, the system will determine that there are more false alarms or missed alarms when the alarm frequency is high, and then generate dynamic threshold optimization instructions; according to the generated dynamic threshold optimization instructions, the initial dynamic threshold table is corrected, including appropriate adjustments to the upper and lower limits of the temperature threshold to improve the accuracy and responsiveness of the threshold.

[0056] In summary, the embodiments of the present application have at least the following technical effects:

[0057] First, the bus duct data of multiple projects are collected to establish a time series data set, which includes temperature changes, ambient temperature, and load conditions. The time series data set is analyzed, and joint identification is performed based on the expert model and data analysis results to establish an initial dynamic threshold table. After the system is running, the target bus duct is monitored in real time to establish a real-time monitoring data set. Then, the current time node is taken as the time zero point, and a backtracking analysis based on the real-time monitoring data set at time zero is performed to establish the backtracking analysis results. Further, a backtracking window is configured according to the backtracking analysis results, and the real-time monitoring data set in the backtracking window is used to adjust the dynamic threshold of the initial dynamic threshold table to establish a dynamic temperature threshold. Finally, the dynamic temperature threshold is used to compare the temperature of the real-time monitoring data set at time zero, and a temperature rise alarm is established. The technical problem of the fixed and inflexible bus duct temperature monitoring threshold in the prior art is solved, and the accuracy and timeliness of the abnormal temperature rise alarm of the bus duct are improved by dynamically adjusting the threshold.

[0058] Embodiment 2 is based on the same inventive concept as the abnormal bus duct temperature rise alarm method with dynamic threshold adjustment in the above embodiment. Figure 2 As shown, the present application provides a bus duct abnormal temperature rise alarm device with dynamic threshold adjustment, wherein the device includes:

[0059] Data acquisition module 11: collects bus duct data of multiple projects and establishes a time series data set, which includes temperature changes, ambient temperature, and load conditions. The time series data set is analyzed, and joint identification is performed based on the expert model and data analysis results to establish an initial dynamic threshold table; real-time monitoring module 12: after the system is running, the target bus duct is monitored in real time to establish a real-time monitoring data set; retrospective analysis module 13: takes the current time node as the time zero point, performs retrospective analysis based on the real-time monitoring data set at the time zero point, and establishes a retrospective analysis result; threshold adjustment module 14: configures a retrospective window according to the retrospective analysis result, and uses the real-time monitoring data set in the retrospective window to adjust the dynamic threshold of the initial dynamic threshold table to establish a dynamic temperature threshold; early warning module 15: uses the dynamic temperature threshold to compare the temperature of the real-time monitoring data set at the time zero point, and establishes a temperature rise alarm.

[0060] Furthermore, the backtracking analysis module 13 is used to perform the following method:

[0061] The real-time monitoring data set corresponding to the time zero point is used as the standard comparison data, input into the backtracking analysis channel, and the channel initialization of the backtracking analysis channel is performed; after the backtracking direction of the real-time monitoring data set is created based on the time zero point, the backtracking analysis channel analysis of each time data under the backtracking direction in the real-time monitoring data set is performed to establish the channel analysis result; the fluctuation characteristics of the channel analysis result are accumulated, the fluctuation characteristic accumulation result is triggered and identified through the fluctuation accumulation threshold, the backtracking node is determined by using the trigger identification result, and the backtracking node is used as the backtracking analysis result.

[0062] Furthermore, the backtracking analysis module 13 is used to perform the following method:

[0063] Obtain the ambient temperature difference and load change difference in the channel analysis results; use the ambient temperature difference and the load change difference to perform temperature impact fitting, and establish an impact characteristic value according to the temperature impact fitting result; obtain the temperature change difference in the channel analysis results, perform consistency analysis according to the temperature change difference and the temperature impact fitting result, and establish characteristic compensation; after correcting the impact characteristic value according to the characteristic compensation, perform fluctuation characteristic accumulation calculation, and establish a fluctuation characteristic accumulation result.

[0064] Furthermore, the threshold adjustment module 14 is used to perform the following method:

[0065] The window length of the lookback window is obtained, and a window timing factor is established based on the window length; the monitoring data in the lookback window is mapped with the window timing factor, and then input into the dynamic threshold impact model to establish a dynamic threshold impact result; after matching the real-time monitoring data set at time zero with the initial dynamic threshold table as matching data, the matching result is adjusted based on the dynamic threshold impact result to establish the dynamic temperature threshold.

[0066] Furthermore, the early warning module 15 is used to execute the following method:

[0067] An alarm event is triggered according to the comparison result, wherein the alarm event includes an alarm level created based on the comparison result, a temperature point exceeding a threshold, a current temperature value, and a dynamic temperature threshold; and the alarm event is sent as an alarm through a preset communication channel.

[0068] Furthermore, the early warning module 15 is used to execute the following method:

[0069] The alarm event is synchronized to the abnormal feedback unit; based on the abnormal feedback unit, the alarm frequency trigger authentication of the measuring point is performed, and the alarm frequency trigger authentication result is established; the real feedback corresponding to the alarm event is obtained, and an adjustment database is generated based on the real feedback and the alarm frequency trigger authentication result, and feedback management is performed according to the adjustment database.

[0070] Furthermore, the early warning module 15 is used to execute the following method:

[0071] Determine the proportion of real alarms in the alarm frequency trigger authentication result; if the proportion of real alarms is higher than a preset ratio threshold, generate a focus monitoring instruction; and perform focus monitoring management of the corresponding measuring point based on the focus monitoring instruction.

[0072] Furthermore, the early warning module 15 is used to execute the following method:

[0073] If the real alarm ratio is lower than the preset ratio threshold, a dynamic threshold optimization instruction is generated; and the initial dynamic threshold table correction is performed according to the dynamic threshold optimization instruction.

[0074] Embodiment 3, Figure 3 The schematic diagram of the structure of the electronic device provided in the third embodiment of the present invention shows a block diagram of an exemplary electronic device suitable for implementing the implementation mode of the present invention. Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. Figure 3 As shown, the electronic device includes a processor 21, a memory 22, an input device 23 and an output device 24; the number of processors 21 in the electronic device can be one or more. Figure 3Taking a processor 21 as an example, the processor 21, memory 22, input device 23 and output device 24 in the electronic device can be connected through a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0075] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying 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.

[0076] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0077] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A bus duct abnormal temperature rise alarm method with dynamic threshold adjustment, characterized in that: The method comprises: Collect bus duct data of multiple projects and establish a time series data set, which includes temperature changes, ambient temperature, and load conditions. Perform data analysis on the time series data set, and perform joint identification based on the expert model and data analysis results to establish an initial dynamic threshold table. After the system is running, real-time data monitoring of the target bus duct is carried out to establish a real-time monitoring data set; Taking the current time node as time zero, performing a backtracking analysis based on the real-time monitoring data set at the time zero, and establishing a backtracking analysis result; Configure a backtracking window according to the backtracking analysis result, use the real-time monitoring data set in the backtracking window to adjust the dynamic threshold of the initial dynamic threshold table, and establish a dynamic temperature threshold; Using the dynamic temperature threshold to compare the temperature of the real-time monitoring data set at time zero, and establish a temperature rise alarm; The performing of the backtracking analysis based on the real-time monitoring data set at the time zero to establish the backtracking analysis result includes: The real-time monitoring data set corresponding to the time zero is used as standard comparison data, inputted into the retrospective analysis channel, and the channel initialization of the retrospective analysis channel is performed; After creating the backtracking direction of the real-time monitoring data set based on the time zero point, performing a time data backtracking analysis channel analysis under the backtracking direction in the real-time monitoring data set, and establishing a channel analysis result; Accumulate fluctuation characteristics of the channel analysis results, trigger identification of the fluctuation characteristic accumulation results through fluctuation accumulation thresholds, determine a backtracking node using the trigger identification results, and use the backtracking node as a backtracking analysis result; The accumulating fluctuation characteristics of the channel analysis results and triggering identification of the fluctuation characteristic accumulation results by using a fluctuation accumulation threshold include: Obtaining the ambient temperature difference and the load change difference in the channel analysis results; Performing temperature impact fitting using the ambient temperature difference and the load change difference, and establishing an impact characteristic value according to the temperature impact fitting result; Acquire the temperature change difference in the channel analysis result, perform consistency analysis according to the temperature change difference and the temperature influence fitting result, and establish feature compensation; After the influencing characteristic value is corrected according to the characteristic compensation, a fluctuation characteristic accumulation calculation is performed to establish a fluctuation characteristic accumulation result.

2. The bus duct abnormal temperature rise alarm method with dynamic threshold adjustment according to claim 1 is characterized in that: The step of adjusting the dynamic threshold value of the initial dynamic threshold value table by using the real-time monitoring data set in the backtracking window to establish the dynamic temperature threshold value further includes: Acquire a window length of the traceback window, and establish a window timing factor based on the window length; After mapping the monitoring data in the backtracking window with the window timing factor, the data is input into a dynamic threshold impact model to establish a dynamic threshold impact result; After the real-time monitoring data set at time zero is used as matching data to match the initial dynamic threshold table, the matching result is adjusted based on the dynamic threshold impact result to establish the dynamic temperature threshold.

3. The bus duct abnormal temperature rise alarm method with dynamic threshold adjustment according to claim 1 is characterized in that: The step of establishing a temperature rise alarm comprises: triggering an alarm event according to the comparison result, wherein the alarm event includes an alarm level created based on the comparison result, a temperature point exceeding a threshold, a current temperature value, and a dynamic temperature threshold; The alarm event is sent as an alarm through a preset communication channel.

4. The bus duct abnormal temperature rise alarm method with dynamic threshold adjustment as claimed in claim 3 is characterized in that: The method further comprises: Synchronize the alarm event to an abnormality feedback unit; Performing alarm frequency trigger authentication of the measuring point based on the abnormal feedback unit, and establishing an alarm frequency trigger authentication result; Acquire real feedback corresponding to the alarm event, generate an adjustment database based on the real feedback and the alarm frequency trigger authentication result, and perform feedback management according to the adjustment database.

5. The bus duct abnormal temperature rise alarm method with dynamic threshold adjustment as claimed in claim 4 is characterized in that: The generating an adjustment database based on the real feedback and the alarm frequency triggering authentication result, and performing feedback management according to the adjustment database, includes: Determine the proportion of real alarms in the alarm frequency trigger authentication result; If the proportion of the real alarms is higher than the preset ratio threshold, a monitoring instruction is generated; Based on the attention monitoring instruction, attention monitoring management of the corresponding measuring point is performed.

6. The bus duct abnormal temperature rise alarm method with dynamic threshold adjustment as claimed in claim 5, characterized in that: The method further comprises: If the real alarm ratio is lower than the preset ratio threshold, a dynamic threshold optimization instruction is generated; An initial dynamic threshold table correction is performed according to the dynamic threshold optimization instruction.

7. The bus duct abnormal temperature rise alarm device with dynamic threshold adjustment is characterized by: The bus duct abnormal temperature rise alarm method for implementing the dynamic threshold adjustment according to any one of claims 1 to 6, the device comprising: Data acquisition module: collects bus duct data of multiple projects and establishes a time series data set, which includes temperature changes, ambient temperature, and load conditions. It performs data analysis on the time series data set, and performs joint identification based on the expert model and data analysis results to establish an initial dynamic threshold table. Real-time monitoring module: After the system is running, it monitors the target bus duct in real time and establishes a real-time monitoring data set; Retrospective analysis module: taking the current time node as time zero, performing retrospective analysis based on the real-time monitoring data set at the time zero, and establishing retrospective analysis results; Threshold adjustment module: configures a backtracking window according to the backtracking analysis result, uses the real-time monitoring data set in the backtracking window to perform dynamic threshold adjustment on the initial dynamic threshold table, and establishes a dynamic temperature threshold; Early warning module: using the dynamic temperature threshold to compare the temperature of the real-time monitoring data set at time zero, and establish a temperature rise alarm.

8. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; The processor is used to implement the bus duct abnormal temperature rise alarm method with dynamic threshold adjustment as described in any one of claims 1 to 6 when executing the executable instructions stored in the memory.

Images