Intelligent monitoring method, device and system for distribution box

Abstract

The present invention relates to the technical field of current fault monitoring, and specifically to an intelligent monitoring method, device and system for a distribution box, including: obtaining current monitoring data of a distribution box; performing periodic segmentation processing on the current monitoring data into periodic monitoring data; performing incremental fitting on the periodic monitoring data to obtain fitting results; obtaining the incremental fitting influence degree of each current cycle based on the parameter change analysis of the fitting function in the fitting results; performing fine-grained analysis on each current cycle according to the incremental fitting influence degree to obtain the division duration of each current cycle; and using the division duration of each current cycle to screen and obtain the current threshold. By analyzing the periodicity of the current, the historical current data is periodically segmented and incrementally fitted, and the optimal time interval is determined in combination with the fine-grained analysis. Then, the current threshold is determined using the fitting margin, the current is monitored in real time and an early warning is issued to reduce the monitoring error caused by interference to the current transformer.

Description

Technical Field

[0001] The present invention relates to the technical field of current fault monitoring, and in particular to an intelligent monitoring method, device and system for a distribution box. Background Art

[0002] In the intelligent monitoring system of the distribution box, the current transformer (CT) can monitor the current in real time, help evaluate the load condition, prevent overload, diagnose faults and trigger early warnings to ensure the safety and reliability of the distribution system. CT data can also be used to count and optimize energy consumption, support the formulation of scientific maintenance plans and equipment life cycle management, perform harmonic analysis and current imbalance monitoring, and improve power quality. By remotely transmitting and storing historical data, CT realizes intelligent operation and maintenance and intelligent decision support, significantly improving the operating efficiency and stability of the distribution system.

[0003] However, the monitoring accuracy of the current transformer is significantly affected by load and environmental factors. For example, factors such as secondary load impedance, load changes such as dynamic load and nonlinear load, environmental humidity, electromagnetic interference, vibration and mechanical stress may affect the stability of the current transformer. Therefore, how to comprehensively control the influence of these load and environmental factors to improve the measurement accuracy of the current transformer is a technical problem that needs to be solved urgently. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide an intelligent monitoring method, device and system for a distribution box. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0005] In a first aspect, the present invention provides an intelligent monitoring method for a distribution box, the method comprising: acquiring current monitoring data of the distribution box within a historical time period; performing period segmentation processing on the current monitoring data within the historical time period into period monitoring data, the period monitoring data being current monitoring data corresponding to several current periods of the distribution box within the historical time period; performing incremental fitting on the period monitoring data to obtain a fitting result, the fitting result comprising a fitting function corresponding to each current period; obtaining an incremental fitting influence degree of each current period based on parameter change analysis of the fitting function within the fitting result; performing a fine-grained analysis of time intervals of different lengths for each current cycle according to the incremental fitting influence degree to obtain a divided time length for each current cycle; and obtaining a current threshold by screening using the divided time length of each current cycle, the current threshold corresponding to each current cycle being used to monitor the real-time current detection data of the distribution box in each time period.

[0006] In combination with the first aspect, in a possible implementation method, the incremental fitting influence of each current cycle is obtained based on the parameter change analysis of the fitting function in the fitting result, including: extracting a fitting vector based on each of the fitting functions, each element of the fitting vector is a fitting parameter of the fitting function; using a preset first calculation formula to calculate the fitting vector corresponding to each of the current cycles to obtain the incremental fitting influence corresponding to each of the current cycles.

[0007] In combination with the first aspect, in a possible implementation method, a fine-grained analysis of time intervals of different lengths for each current cycle is performed according to the degree of influence of the incremental fitting to obtain the divided time length of each current cycle, including: dividing a current cycle into time intervals of different lengths to obtain a number of time intervals under each time length division; calculating the environmental sensitivity corresponding to each time interval of the same length based on the difference in current changes in the several time intervals divided by the same time length; calculating the environmental factor sensitivity corresponding to each time length based on the degree of influence of the incremental fitting and the environmental sensitivity corresponding to each time interval of the same time length; calculating the average peak duration corresponding to each time length based on the duration of current peak occurrence in the several time intervals divided by the same time length; calculating the reference weight corresponding to each time length based on the average peak duration corresponding to each time length and the environmental factor sensitivity; and performing weighted average calculation based on the reference weight of each time length to obtain the divided time length of a current cycle.

[0008] In combination with the first aspect, in a possible implementation method, the environmental sensitivity corresponding to each time interval of the same time length is calculated based on the current change difference in several time intervals divided by the same time length, including: calculating the fitting current data corresponding to the several time intervals of the same time length based on the fitting function; subtracting the fitting current data from the current monitoring data in sequence in chronological order and then summing them up to obtain the fitting margins in the several time intervals of the same time length; calculating the mean of the fitting margins based on the fitting margins in the several time intervals of the same time length; and calculating the environmental sensitivity corresponding to each time interval based on the fitting margin mean corresponding to each time length and the current difference in each time interval.

[0009] In combination with the first aspect, in a possible implementation method, the current threshold is obtained by screening using the divided time length of each current cycle, including: segmenting the current monitoring data corresponding to the current cycle based on the divided time length to obtain current monitoring data corresponding to several optimal time intervals; performing straight line fitting on the current monitoring data corresponding to each optimal time interval to obtain a fitted straight line corresponding to each optimal time interval; calculating the fitted current data corresponding to each optimal time interval based on the fitted straight line corresponding to each optimal time interval; subtracting the fitted current data and the current monitoring data corresponding to each optimal time interval and then summing them to obtain a fitting margin corresponding to each optimal time interval; screening the maximum fitting margin from the fitting margin corresponding to each optimal time interval; comparing the fitting margin corresponding to each optimal time interval with the maximum fitting margin to obtain the margin ratio; and judging the current threshold based on the margin ratio corresponding to each optimal time interval and a preset threshold.

[0010] In the second aspect, the present invention also provides an intelligent monitoring device for a distribution box, comprising: an acquisition module, used to acquire current monitoring data of the distribution box within a historical time period; a cycle segmentation module, used to perform cycle segmentation processing on the current monitoring data within the historical time period into cycle monitoring data, wherein the cycle monitoring data is the current monitoring data corresponding to several current cycles of the distribution box within the historical time period; an incremental fitting module, used to perform incremental fitting on the cycle monitoring data to obtain a fitting result, wherein the fitting result includes a fitting function corresponding to each current cycle; an incremental analysis module, used to obtain the incremental fitting influence degree of each current cycle based on the parameter change analysis of the fitting function in the fitting result; a fine-grained analysis module, used to perform fine-grained analysis of time intervals of different lengths for each current cycle according to the incremental fitting influence degree to obtain the divided time length of each current cycle; a screening module, used to obtain a current threshold by screening using the divided time length of each current cycle, and the current threshold corresponding to each current cycle is used to monitor the real-time current detection data of the distribution box in each time period.

[0011] In combination with the second aspect, in a possible implementation, the incremental analysis module includes: a vector extraction module, used to extract a fitting vector based on each of the fitting functions, each element of the fitting vector is a fitting parameter of the fitting function; a first calculation module, used to use a preset first calculation formula to calculate the fitting vector corresponding to each of the current cycles to obtain the incremental fitting influence degree corresponding to each of the current cycles.

[0012] In combination with the second aspect, in a possible implementation method, the fine-grained analysis module includes: an initial division module, which is used to divide a current cycle into time intervals of different lengths to obtain several time intervals under each time length division; a second calculation module, which is used to calculate the environmental sensitivity corresponding to each time interval of the same length based on the current change difference in several time intervals divided with the same time length; a third calculation module, which is used to calculate the environmental factor sensitivity based on the incremental fitting influence degree and the environmental sensitivity corresponding to each time interval of the same time length; a peak calculation module, which is used to calculate the average peak duration corresponding to each time length based on the current peak occurrence duration in several time intervals divided with the same time length; a weight calculation module, which is used to calculate the reference weight corresponding to each time length based on the peak duration average corresponding to each time length and the environmental factor sensitivity; a weighted calculation module, which is used to perform weighted average calculation based on the reference weight of each time length to obtain the divided time length of a current cycle.

[0013] In combination with the second aspect, in a possible implementation, the screening module includes: an interval division module, which is used to segment the current monitoring data corresponding to the current cycle based on the division time to obtain current monitoring data corresponding to several optimal time intervals; a straight line fitting module, which is used to perform straight line fitting on the current monitoring data corresponding to each optimal time interval to obtain a fitting straight line corresponding to each optimal time interval; a current calculation module, which is used to obtain the fitting current data corresponding to each optimal time interval based on the fitting straight line corresponding to each optimal time interval; a residual calculation module, which is used to subtract and sum the fitting current data and current monitoring data corresponding to each optimal time interval to obtain the fitting residual corresponding to each optimal time interval; a residual screening module, which is used to filter out the maximum fitting residual from the fitting residual corresponding to each optimal time interval; a residual proportion module, which is used to compare the fitting residual corresponding to each optimal time interval with the maximum fitting residual to obtain the residual proportion; a judgment module, which is used to judge based on the residual proportion corresponding to each optimal time interval and a preset threshold to obtain a current threshold.

[0014] In a third aspect, the present invention further provides an intelligent monitoring system for a distribution box, comprising: a memory for storing a computer program; and a processor for implementing the steps of any one of the intelligent monitoring methods for a distribution box as described above when executing the computer program.

[0015] The present invention has the following beneficial effects:

[0016] In the present invention, it is first considered that the electricity consumption at every moment is periodic when it is measured in days. Therefore, the current monitoring data in the historical time period is firstly subjected to periodic segmentation and then incremental fitting processing, and then the best time interval division interval is screened in combination with the fine-grained analysis method. In this way, the division result is then combined with the fitting margin calculation method proposed in the present invention to screen the acceptable current threshold, and the real-time current data is monitored, and according to the degree to which the current change exceeds the acceptable range, real-time warning and subsequent related processing such as related equipment shutdown and maintenance are performed, and the accurate detection of the current in the distribution box is completed, which reduces the probability of inaccurate current monitoring caused by external interference of the current transformer. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. 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 paying creative work.

[0018] Figure 1 A schematic flow chart of an intelligent monitoring method for a distribution box provided in Embodiment 1 of the present invention;

[0019] Figure 2 A schematic flow chart of step S4 provided in Example 1 of the present invention;

[0020] Figure 3 A schematic flow chart of step S5 provided in Example 1 of the present invention;

[0021] Figure 4 A schematic diagram of the flow of step S6 provided in Embodiment 1 of the present invention;

[0022] Figure 5 This is a schematic diagram of the structure of the intelligent monitoring device for the distribution box described in Example 2 of the present invention;

[0023] Figure 6 This is a structural schematic diagram of the intelligent monitoring system for the distribution box described in Example 3 of the present invention;

[0024] Markings in the figure: 800, intelligent monitoring system of distribution box; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0025] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the intelligent monitoring method, device and system of a distribution box proposed by the present invention, its specific implementation method, structure, characteristics and effects in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0026] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0027] Embodiment 1:

[0028] The specific scheme of the intelligent monitoring method for a distribution box provided by the present invention is described in detail below with reference to the accompanying drawings.

[0029] See also Figure 1 , which shows a flow chart of an intelligent monitoring method for a distribution box provided by an embodiment of the present invention, which includes steps S1 to S6 in this embodiment.

[0030] S1. Obtain the current monitoring data of the distribution box in the historical time period.

[0031] In this embodiment, the time span involved is preferably a seven-day period. During this period, the current monitoring data is collected once every ten seconds. The analog-to-digital conversion is performed through the secondary output signal of the current transformer, and the data is transmitted through wired or wireless communication. In addition, for those skilled in the art, the data can also be directly transmitted to a preset database for storage, so as to facilitate subsequent reading and analysis.

[0032] S2. The current monitoring data in the historical time period is processed into periodic monitoring data by periodic segmentation, wherein the periodic monitoring data is the current monitoring data corresponding to several current cycles of the distribution box in the historical time period.

[0033] Specifically, in this embodiment, the duration of the current cycle is 60 minutes, but the duration of the current cycle can be modified according to actual conditions, and no specific limitation is made in this embodiment.

[0034] The timing characteristics of the acquired current monitoring data set are taken into consideration in the embodiment. The current monitoring data set reflects the dynamic characteristics of the current changing over time, and its changes are affected by factors of multiple dimensions, including but not limited to load fluctuations, changes in the current itself, humidity changes, and possible environmental factors that cause fluctuations in the internal monitoring current of the current transformer. Therefore, in this embodiment, the processing of the current monitoring data focuses on analyzing the differences in the overall trend.

[0035] In view of this, this embodiment proposes to use an incremental fitting method to define the current refinement trend range to effectively eliminate the influence of environmental factors in the data set. Therefore, the analysis of the influence of environmental factors is crucial in this embodiment, and the purpose is to extract effective information from the fluctuations of current monitoring data under the influence of different environmental factors.

[0036] Based on this, the data in multiple current cycles were analyzed. In the current cycle, the change trend of the current monitoring data is mainly affected by the load change of the distribution box. However, the periodic regular change part in the current cycle is not only caused by the load change, but also includes environmental factors such as temperature, humidity, vibration and other factors that affect the current transformer. These factors cause fluctuations in the regular change part, thereby increasing the fluctuation of the overall trend change. This part of the fluctuation can be regarded as the disordered change part.

[0037] Therefore, the main task in this embodiment is to extract this disordered change part to eliminate the influence of environmental factors. For specific operations, please refer to steps S3 and S4 in the research case. Through these steps, the current monitoring data can be analyzed and processed more accurately, thereby improving the accuracy and reliability of data processing.

[0038] S3. Perform incremental fitting on the periodic monitoring data to obtain a fitting result, wherein the fitting result includes a fitting function corresponding to each current cycle.

[0039] Incremental fitting is a method of gradually updating a statistical model. In this embodiment, a two-dimensional rectangular coordinate system is first constructed, in which the horizontal axis represents time and the vertical axis represents current. In this two-dimensional rectangular coordinate system, the current monitoring data corresponding to a current cycle is marked. Then, these data points are connected by linear fitting to finally obtain a fitting function In this fitting equation, and represent the fitting parameters respectively.

[0040] By adopting the incremental fitting method, subtle changes in the data can be effectively captured. The advantage of this method is that as the amount of data gradually increases, the fitting process will be continuously updated, making the model more accurate. In this process, the more current cycles the current transformer of the distribution box monitors, the more accurate the main change trend of the distribution box load represented by the fitting function. In addition, as the amount of data increases, the influence of environmental factors on the fitting function will gradually decrease.

[0041] Therefore, in this embodiment, it is considered that the fitting parameter corresponding to the last current cycle in the historical time period is and is the best fitting parameter pair. This is because the data point of the last current cycle can reflect the latest load change, making the fitting result closer to the current actual situation. Through this method, the load change of the distribution box can be better understood and predicted, thus providing strong support for the optimization and management of the power system.

[0042] S4. Analyzing the parameter changes of the fitting function in the fitting result to obtain the incremental fitting influence degree of each current cycle.

[0043] Specifically, see Figure 2 , the figure shows that step S4 in this embodiment also includes step S41 and step S42.

[0044] S41. Extract a fitting vector based on each of the fitting functions, where each element of the fitting vector is a fitting parameter of the fitting function.

[0045] S42. Calculate the fitting vector corresponding to each current cycle using a preset first calculation formula to obtain the incremental fitting influence degree corresponding to each current cycle.

[0046] In this embodiment, the changes in the fitting parameter pairs during the incremental fitting process are taken into account. Specifically, when the changes in the fitting parameter pairs are large, this indicates that in the current current cycle, the influence of environmental factors has led to a significant trend change. The more obvious the effect of this trend change is, the more it can prove that the change in the current cycle data is due to the overall difference in the current cycle data caused by the change in environmental factors. Therefore, in this embodiment, a method based on the difference between a current cycle and its adjacent previous current cycle is adopted, and the difference between the current cycle and the best fitting parameters is combined as a weight. Such weights will serve as the basis for constructing the first calculation formula, thereby more accurately reflecting the impact of environmental factors on the change in current cycle data. In this way, the contribution of environmental factors to the change in current cycle data can be more effectively identified and quantified.

[0047] Specifically, in this embodiment, the first calculation formula is:

[0048] ;

[0049] in, Indicates The degree of influence of incremental fitting of current cycles; represents the maximum and minimum normalized function; Indicates The fitting vector corresponding to the fitting function of the current cycle; Indicates The fitting vector corresponding to the fitting function of the current cycle; The fitting vector corresponding to the fitting function of the last current cycle.

[0050] In the above calculation formula, Representation vector and vector The modulus of the difference can be called the difference between the fitting vectors of two adjacent current cycles of the current transformer of the distribution box, that is, it measures the incremental fitting influence of the adjacent current cycle data. +0.1 is to avoid the situation where the denominator of the fraction is zero when the modulus of the vector difference is equal to 0; The larger the value is, the more obvious the effect of the trend change caused by the environmental factors in the current cycle is, and the more it can prove that the change in the current cycle is an overall difference caused by the change in environmental factors.

[0051] In this embodiment, although the above steps have been taken, the influence of environmental factors on the performance of the current transformer has not been completely eliminated. Therefore, in order to further improve the accuracy and reliability of the present method, this embodiment adopts a fine-grained analysis method to identify and define the negative impact of environmental factors. Through this detailed analysis, the specific impact of environmental factors on the current transformer data can be more accurately identified, and on this basis, the system's ability to distinguish abnormal data can be further improved. Specifically, this fine-grained analysis method includes detailed classification and quantification of environmental factors in order to better understand their specific impact on current transformer data. Then, based on these negative impacts, these interference factors can be more effectively identified and eliminated, thereby improving the ability to distinguish abnormal data. For detailed steps, please refer to step S5 and step S6.

[0052] S5. Perform a fine-grained analysis of time intervals of different durations on each current cycle according to the incremental fitting influence degree to obtain a divided duration of each current cycle.

[0053] In this embodiment, a fine-grained analysis method is used to perform an in-depth and accurate analysis of the data so as to capture those tiny differences and details in the data. Specifically, in this embodiment, by adjusting the size of the time interval range, a detailed analysis is performed on the range of different current cycles during the incremental change process. The purpose of this method is to more accurately extract the impact of environmental factors on the current cycle, that is, to determine the sensitivity of the size of different time intervals in each current cycle to the extraction of environmental factors.

[0054] Based on this fine-grained analysis, we can effectively define the scope of the current refinement trend, thereby eliminating the impact of environmental factors in the data set. The advantage of this method is that it can help us more accurately identify and analyze the subtle differences in current changes, thereby improving the accuracy and reliability of data processing.

[0055] To better illustrate this process, see Figure 3 The figure shows steps S51 to S56 included in this embodiment.

[0056] S51. Divide a current cycle into time intervals of different lengths to obtain a plurality of time intervals under each time interval division.

[0057] In order to facilitate the understanding of those skilled in the art, For the 60-min current cycle For each current cycle, 1min, 2min, 3min...30min arithmetic progression groups are used as the time interval range, and the The current cycle is divided into , , … time intervals, where n represents the total number of time intervals contained in a time interval range. If the current cycle is 1, the remainder is also regarded as a time interval. Meanwhile, for those skilled in the art, the change of the time interval range can be selected according to the actual situation, and no specific limitation is made in this embodiment.

[0058] In order to enable those skilled in the art to more clearly understand the specific operation of this step, In this example, a current cycle lasting 60 minutes In order to divide this current cycle, an arithmetic progression from 1 minute to 30 minutes is used as the time interval range. Specifically, this 60-minute cycle is divided into 60 time intervals, each of which is 1 minute; 30 time intervals, each of which is 2 minutes; 20 time intervals, each of which is 3 minutes; and so on, until it is divided into 2 time intervals, each of which is 30 minutes.

[0059] In practice, if If a current cycle cannot be divided evenly, that is, there is a remainder, then this remainder part will also be divided into a time interval separately. This processing method ensures that the entire current cycle is completely covered without omission. For technicians in this field, they can flexibly choose the division method of the time interval range according to actual needs and specific circumstances. In this embodiment, no specific restrictions are made on the selection of the time interval range to adapt to different application scenarios and needs.

[0060] S52, calculating the environmental sensitivity corresponding to each time interval of the same duration based on the current change difference within a plurality of time intervals divided into the same duration.

[0061] In order to facilitate understanding by those skilled in the art, in this embodiment, one time interval is used as an example to illustrate how to calculate the environmental sensitivity, see steps S521 to S524 for details.

[0062] S521. Calculate fitting current data corresponding to a plurality of time intervals divided into the same time length based on the fitting function.

[0063] S522, sequentially fitting the current data and the current monitoring data in a time sequence, performing subtraction and summing calculations to obtain fitting margins within a plurality of time intervals divided into the same time length.

[0064] S523, calculating the mean of the fitting margins in a plurality of time intervals divided based on the same duration to obtain a fitting margin mean.

[0065] S524: Calculate the environmental sensitivity corresponding to each time interval based on the fitting margin mean corresponding to each time length and the current difference in each time interval.

[0066] Specifically, the calculation formula for environmental sensitivity is as follows:

[0067] ;

[0068] in, Indicates The current cycle is within the time range of Divide into The environmental sensitivity corresponding to the time interval, , n represents the time interval range When , the total number of time intervals it contains; represents the maximum and minimum normalized function; Indicates the time interval range is When The fitting margin between the current monitoring data and the fitting current data in a time interval may also be referred to as the difference cumulative sum in this embodiment; Indicates the time interval range is When , the mean of the fitting margins of all time intervals can also be called the mean of the difference cumulative sums in this embodiment; Indicates The incremental fitting of each current cycle affects the degree of influence.

[0069] In the above calculation formula, The larger the value is, the more sensitive the time interval range corresponding to the time interval is to the extraction of environmental factors. The fitting margin represents the difference between the current monitoring data and the fitting current data at each time point in a time interval, and then the difference corresponding to all time points in the time interval is summed up. The smaller it is, the The time interval range under the environmental impact degree of a current cycle is The better the sensitivity performance, the more obvious the effect of measuring the impact of environmental factors by the size of its interval range.

[0070] S53: Calculate the environmental factor sensitivity based on the incremental fitting influence degree and the environmental sensitivity corresponding to each time interval of the same duration.

[0071] Specifically, the calculation formula for environmental factor sensitivity is as follows:

[0072] ;

[0073] in, Indicates The current cycle is within the time range of The sensitivity of environmental factors corresponding to the time; represents the variance calculation function; Indicates The current cycle is within the time range of Divide the environmental sensitivity corresponding to all time intervals; Indicates The incremental fitting of each current cycle affects the degree of influence.

[0074] In the above calculation formula, The smaller it is, the The current cycle is within the time range of The better the sensitivity of the environmental impact within this range, the more 0.1 is added to the denominator of the fraction to avoid the special situation where the denominator is zero when the incremental fitting impact is zero.

[0075] In this embodiment, the fluctuation of current changes within the current cycle is fully considered, and these changes are affected by a variety of different types of environmental factors. The impact of these environmental factors on the current in the time dimension is continuous, rather than just transient. Therefore, it can be observed that the current distribution in the time dimension presents a multi-peak feature.

[0076] Based on the above analysis and description, a conclusion can be drawn: if the degree of change in the sensitivity of environmental factors is relatively low within each specific time interval, then this indicates that the time interval has a higher impact on the size of the optimal range. In other words, the higher the stability of the sensitivity of environmental factors, the more significant its impact on the current distribution. Therefore, combining the distribution of current in the time dimension and the change in the sensitivity of environmental factors, it is possible to more accurately evaluate and describe whether a time interval is reasonable. The specific evaluation method and steps will be described in detail in the subsequent steps S54 and S56.

[0077] S54, calculating the duration of current peaks in a plurality of time intervals divided into the same duration to obtain an average value of the peak duration corresponding to each duration.

[0078] S55. Calculate a reference weight corresponding to each duration based on the mean value of the peak duration corresponding to each duration and the sensitivity to the environmental factors.

[0079] Specifically, the calculation formula of the reference weight is as follows:

[0080] ;

[0081] in, Indicates the time interval range is The reference weight when represents the maximum and minimum normalized function; Indicates the time interval range is When the peak in the time interval is calculated based on the duration of the current peak in several time intervals divided by the same duration, the average peak duration corresponding to each duration is obtained; It represents the average peak duration of all time intervals on the interval range coordinate axis. Indicates The current cycle is within the time range of The corresponding sensitivity to environmental factors, Indicates the time interval range is The smaller the value is, the greater its influence on the optimal range is.

[0082] S56. Perform weighted average calculation based on the reference weight of each duration to obtain the divided duration of a current cycle.

[0083] Specifically, the calculation formula for the division duration is as follows:

[0084] ;

[0085] in, Indicates the duration of the division; Indicates the time interval range is Length of time; Indicates the time interval range is The reference weight when A number representing the size of the interval range.

[0086] In this step, the division time of each current cycle is obtained by using weighted average, so that the division time is more universal for extracting environmental factors.

[0087] S6. A current threshold is obtained by screening using the divided time length of each current cycle. The current threshold corresponding to each current cycle is used to monitor the real-time current detection data of the distribution box in each time period.

[0088] In this step, the division time is obtained by the above calculation and combined with the fitting margin screening to obtain the current threshold. Figure 4 , the figure shows that step S6 includes steps S61 to S67.

[0089] S61. Segment the current monitoring data corresponding to the current cycle based on the divided time length to obtain current monitoring data corresponding to a plurality of optimal time intervals.

[0090] S62, performing straight line fitting on the current monitoring data corresponding to each optimal time interval to obtain a fitting straight line corresponding to each optimal time interval.

[0091] S63, obtaining fitting current data corresponding to each optimal time interval based on the fitting straight line corresponding to each optimal time interval.

[0092] S64, subtracting and summing the fitting current data and the current monitoring data corresponding to each optimal time interval to obtain a fitting margin corresponding to each optimal time interval.

[0093] S65. Filter the fitting margins corresponding to each optimal time interval to obtain the maximum fitting margin.

[0094] S66, comparing the fitting margin corresponding to each optimal time interval with the maximum fitting margin to obtain a margin ratio.

[0095] S67, determining a current threshold based on the margin ratio corresponding to each optimal time interval and a preset threshold.

[0096] In this step, the best time intervals where the margin ratio exceeds the preset threshold are considered as abnormal time periods where abnormal data appears. The maximum current value and the minimum current value are extracted in the abnormal time period, and these current values ​​will be used as current thresholds. In addition, it is necessary to combine the specific time range of the abnormal time period to confirm the current threshold that should be used when monitoring the distribution box current within this time range.

[0097] For example, suppose an abnormal time period is identified as 5:10 a.m. to 5:30 a.m. During this time period, the minimum current value we extracted is 301 amperes (A), and the maximum current value is 352 amperes (A). Then, in the subsequent monitoring process, 301 amperes and 352 amperes will be used as the current data monitoring thresholds within the time range of 5:10 a.m. to 5:30 a.m.

[0098] At the same time, for the situation where the abnormal time periods obtained by screening overlap in the historical time period, the mean calculation method can be used to balance these conflicts. Specifically, the average value of the current value in the overlapping time period can be calculated and used as the comprehensive threshold to avoid misjudgment caused by a single abnormal value.

[0099] In this embodiment, by finely defining the trend range of the current monitoring data in the distribution box and eliminating the influence of environmental factors, the accuracy and reliability of the current monitoring data can be significantly improved. This refined analysis method helps to enhance the fault diagnosis capability and can detect potential problems with the current in the distribution box as early as possible. In addition, accurate current monitoring data can also support the optimization of the maintenance and management strategy of the distribution box, reduce misjudgment and unnecessary maintenance costs, and improve the energy efficiency management level of the distribution box to ensure efficient and stable operation of the distribution system.

[0100] Embodiment 2:

[0101] like Figure 5 As shown, this embodiment provides an intelligent monitoring device for a distribution box, the device comprising:

[0102] An acquisition module is used to obtain current monitoring data of the distribution box in a historical time period;

[0103] A cycle segmentation module, used for performing cycle segmentation processing on the current monitoring data in the historical time period into cycle monitoring data, wherein the cycle monitoring data is the current monitoring data corresponding to several current cycles of the distribution box in the historical time period;

[0104] An incremental fitting module, used for performing incremental fitting on the periodic monitoring data to obtain a fitting result, wherein the fitting result includes a fitting function corresponding to each current cycle;

[0105] An incremental analysis module, used for analyzing the parameter changes of the fitting function in the fitting result to obtain the incremental fitting influence degree of each current cycle;

[0106] A fine-grained analysis module, used to perform a fine-grained analysis of time intervals of different durations on each current cycle according to the degree of influence of the incremental fitting to obtain a divided duration of each current cycle;

[0107] The screening module is used to screen and obtain a current threshold using the divided time length of each current cycle. The current threshold corresponding to each current cycle is used to monitor the real-time current detection data of the distribution box in each time period.

[0108] In some specific embodiments, the incremental analysis module includes:

[0109] A vector extraction module, used for extracting a fitting vector based on each of the fitting functions, wherein each element of the fitting vector is a fitting parameter of the fitting function;

[0110] The first calculation module is used to calculate the fitting vector corresponding to each current cycle by using a preset first calculation formula to obtain the incremental fitting influence degree corresponding to each current cycle.

[0111] In some specific embodiments, the fine-grained analysis module includes:

[0112] An initial division module is used to divide a current cycle into time intervals of different lengths to obtain a number of time intervals under each time division;

[0113] The second calculation module is used to calculate the environmental sensitivity corresponding to each time interval of the same duration based on the current change difference in a plurality of time intervals divided by the same duration;

[0114] A third calculation module is used to calculate the environmental factor sensitivity based on the incremental fitting influence degree and the environmental sensitivity corresponding to each time interval of the same duration;

[0115] A peak calculation module, used to calculate the peak duration corresponding to each time interval based on the current peak duration in several time intervals divided by the same time interval;

[0116] A weight calculation module, used to calculate a reference weight corresponding to each duration based on the mean value of the peak duration corresponding to each duration and the sensitivity of the environmental factors;

[0117] The weighted calculation module is used to perform weighted average calculation based on the reference weight of each duration to obtain the divided duration of a current cycle.

[0118] In some specific embodiments, the screening module includes:

[0119] An interval division module, used for segmenting the current monitoring data corresponding to the current cycle based on the division time to obtain current monitoring data corresponding to several optimal time intervals;

[0120] A straight line fitting module is used to perform straight line fitting on the current monitoring data corresponding to each optimal time interval to obtain a fitting straight line corresponding to each optimal time interval;

[0121] A current calculation module, used to calculate the fitting current data corresponding to each optimal time interval based on the fitting straight line corresponding to each optimal time interval;

[0122] A margin calculation module, used for performing a difference calculation and then summing the fitting current data and the current monitoring data corresponding to each optimal time interval to obtain a fitting margin corresponding to each optimal time interval;

[0123] The margin screening module is used to screen the fitting margins corresponding to each optimal time interval to obtain the maximum fitting margin;

[0124] The margin ratio module is used to compare the fitting margin corresponding to each optimal time interval with the maximum fitting margin to obtain the margin ratio;

[0125] The judgment module is used to determine the current threshold based on the margin ratio corresponding to each optimal time interval and the preset threshold.

[0126] Embodiment 3:

[0127] Corresponding to the above method embodiment, this embodiment further provides an intelligent monitoring system 800 for a distribution box. The intelligent monitoring system 800 for a distribution box described below and the intelligent monitoring method for a distribution box described above can refer to each other.

[0128] Figure 6 FIG. 8 is a schematic diagram of a smart monitoring system 800 for a distribution box according to an exemplary embodiment. Figure 6 As shown, the intelligent monitoring system 800 for a distribution box may include: a processor 801 and a memory 802. The intelligent monitoring system 800 for a distribution box may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0129] The processor 801 is used to control the overall operation of the intelligent monitoring system 800 of the distribution box to complete all or part of the steps in the above-mentioned intelligent monitoring method of the distribution box. The memory 802 is used to store various types of data to support the operation of the intelligent monitoring system 800 of the distribution box, and these data may include, for example, instructions for any application or method operating on the intelligent monitoring system 800 of the distribution box, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage system or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the intelligent monitoring system 800 of the distribution box and other systems. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0130] In an exemplary embodiment, the intelligent monitoring system 800 of the distribution box can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing systems (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned intelligent monitoring method of the distribution box.

[0131] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned intelligent monitoring method for a distribution box are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the intelligent monitoring system 800 for a distribution box to complete the above-mentioned intelligent monitoring method for a distribution box.

[0132] It should be noted that, regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0133] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. 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.

[0134] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. An intelligent monitoring method for a distribution box, characterized in that: The method comprises: Obtain current monitoring data of the distribution box in the historical time period; The current monitoring data in the historical time period is processed into periodic monitoring data by periodic segmentation, wherein the periodic monitoring data is the current monitoring data corresponding to several current cycles of the distribution box in the historical time period; Performing incremental fitting on the periodic monitoring data to obtain a fitting result, wherein the fitting result includes a fitting function corresponding to each current cycle; Analyzing the parameter changes of the fitting function in the fitting result to obtain the incremental fitting influence degree of each current cycle; Performing a fine-grained analysis of time intervals of different durations on each current cycle according to the incremental fitting influence degree to obtain a divided duration of each current cycle; The current threshold is obtained by screening the divided time length of each current cycle, and the current threshold corresponding to each current cycle is used to monitor the real-time current detection data of the distribution box in each time period; The incremental fitting influence degree of each current cycle is obtained based on the parameter change analysis of the fitting function in the fitting result, including: Extracting a fitting vector based on each of the fitting functions, each element of the fitting vector is a fitting parameter of the fitting function; The fitting vector corresponding to each current cycle is calculated using a preset first calculation formula to obtain the incremental fitting influence degree corresponding to each current cycle.

2. The intelligent monitoring method for a distribution box according to claim 1, characterized in that: According to the incremental fitting influence degree, a fine-grained analysis of time intervals of different durations is performed on each current cycle to obtain the divided duration of each current cycle, including: Divide a current cycle into time intervals of different lengths to obtain a number of time intervals under each time interval; The environmental sensitivity corresponding to each time interval of the same length is calculated based on the difference in current changes in several time intervals divided by the same length; The environmental factor sensitivity corresponding to each time period is calculated based on the incremental fitting influence degree and the environmental sensitivity corresponding to each time interval under the same time period; The peak duration of the current in several time intervals divided by the same duration is calculated to obtain the average peak duration corresponding to each duration; The reference weight corresponding to each duration is calculated based on the mean value of the peak duration corresponding to each duration and the sensitivity of the environmental factors; The divided duration of a current cycle is obtained by performing a weighted average calculation based on the reference weight of each duration.

3. The intelligent monitoring method for a distribution box according to claim 2, characterized in that: Based on the current change difference in several time intervals divided by the same duration, the environmental sensitivity corresponding to each time interval of the same duration is calculated, including: Based on the fitting function, fitting current data corresponding to a plurality of time intervals divided into the same time length are calculated; Subtracting the fitted current data from the current monitoring data in a time sequence and then summing them up to obtain the fitting margins in several time intervals divided by the same time length; The mean value of the fitting residuals is calculated based on the fitting residuals in several time intervals divided by the same time length to obtain the mean value of the fitting residuals; The environmental sensitivity corresponding to each time interval is calculated based on the fitting margin mean corresponding to each time length and the current difference in each time interval.

4. The intelligent monitoring method for a distribution box according to claim 1, characterized in that: The current threshold is obtained by screening using the divided time length of each current cycle, including: Segmenting the current monitoring data corresponding to the current cycle based on the divided time length to obtain current monitoring data corresponding to a plurality of optimal time intervals; Perform straight line fitting on the current monitoring data corresponding to each optimal time interval to obtain a fitting straight line corresponding to each optimal time interval; Based on the fitting straight line corresponding to each optimal time interval, the fitting current data corresponding to each optimal time interval is calculated; The fitting current data and the current monitoring data corresponding to each optimal time interval are subtracted and then summed to obtain a fitting margin corresponding to each optimal time interval; The maximum value of the fitting margin is obtained by screening the fitting margins corresponding to each optimal time interval; The fitting margin corresponding to each optimal time interval is compared with the maximum fitting margin to obtain the margin ratio; The current threshold is obtained based on the margin ratio corresponding to each optimal time interval and the preset threshold.

5. An intelligent monitoring device for a distribution box, characterized in that: include: An acquisition module is used to obtain current monitoring data of the distribution box in a historical time period; A cycle segmentation module, used for performing cycle segmentation processing on the current monitoring data in the historical time period into cycle monitoring data, wherein the cycle monitoring data is the current monitoring data corresponding to several current cycles of the distribution box in the historical time period; An incremental fitting module, used for performing incremental fitting on the periodic monitoring data to obtain a fitting result, wherein the fitting result includes a fitting function corresponding to each current cycle; An incremental analysis module, used for analyzing the parameter changes of the fitting function in the fitting result to obtain the incremental fitting influence degree of each current cycle; A fine-grained analysis module, used to perform a fine-grained analysis of time intervals of different durations on each current cycle according to the degree of influence of the incremental fitting to obtain a divided duration of each current cycle; A screening module, used to screen and obtain a current threshold value by using the divided time length of each current cycle, and the current threshold value corresponding to each current cycle is used to monitor the real-time current detection data of the distribution box in each time period; The incremental analysis module includes: A vector extraction module, used for extracting a fitting vector based on each of the fitting functions, wherein each element of the fitting vector is a fitting parameter of the fitting function; The first calculation module is used to calculate the fitting vector corresponding to each current cycle by using a preset first calculation formula to obtain the incremental fitting influence degree corresponding to each current cycle.

6. The intelligent monitoring device for a distribution box according to claim 5, characterized in that: The fine-grained analysis module includes: An initial division module is used to divide a current cycle into time intervals of different lengths to obtain a number of time intervals under each time division; The second calculation module is used to calculate the environmental sensitivity corresponding to each time interval of the same duration based on the current change difference in a plurality of time intervals divided by the same duration; A third calculation module is used to calculate the environmental factor sensitivity based on the incremental fitting influence degree and the environmental sensitivity corresponding to each time interval of the same duration; A peak calculation module, used to calculate the peak duration corresponding to each time interval based on the current peak duration in several time intervals divided by the same time interval; A weight calculation module, used to calculate a reference weight corresponding to each duration based on the mean value of the peak duration corresponding to each duration and the sensitivity of the environmental factors; The weighted calculation module is used to perform weighted average calculation based on the reference weight of each duration to obtain the divided duration of a current cycle.

7. The intelligent monitoring device for a distribution box according to claim 5, characterized in that: The screening module comprises: An interval division module, used for segmenting the current monitoring data corresponding to the current cycle based on the division time to obtain current monitoring data corresponding to several optimal time intervals; A straight line fitting module is used to perform straight line fitting on the current monitoring data corresponding to each optimal time interval to obtain a fitting straight line corresponding to each optimal time interval; A current calculation module, used to calculate the fitting current data corresponding to each optimal time interval based on the fitting straight line corresponding to each optimal time interval; A margin calculation module, used for performing a difference calculation and then summing the fitting current data and the current monitoring data corresponding to each optimal time interval to obtain a fitting margin corresponding to each optimal time interval; The margin screening module is used to screen the fitting margins corresponding to each optimal time interval to obtain the maximum fitting margin; The margin ratio module is used to compare the fitting margin corresponding to each optimal time interval with the maximum fitting margin to obtain the margin ratio; The judgment module is used to determine the current threshold based on the margin ratio corresponding to each optimal time interval and the preset threshold.

8. An intelligent monitoring system for a distribution box, characterized in that: include: Memory for storing computer programs; A processor, used to implement the steps of the intelligent monitoring method for a distribution box as claimed in any one of claims 1 to 4 when executing the computer program.

Images