A DC power system insulation detection method based on 5G technology

Abstract

The present invention relates to the technical field of measuring electrical variables, and specifically to a method for insulation detection of a DC power supply system based on 5G technology, including: obtaining a leakage current signal data sequence and a leakage voltage signal data sequence, a current data sequence and a voltage data sequence; obtaining an initial abnormal factor of a target time period through the difference in current data at corresponding moments in the leakage current signal data sequence of a target time period and each reference time period, the difference between data in the current data sequence, and the difference between data at the same position in the current data sequence and the voltage data sequence of the target time period; obtaining an insulation evaluation factor of the target time period through the trend change between the initial abnormal factor and all adjacent abnormal sequences; and performing insulation detection of a DC power supply system using 5G technology. The present invention reduces the impact of electromagnetics on leakage current data and improves the accuracy of insulation detection of a DC power supply system using 5G technology.

Description

Technical Field

[0001] The present invention relates to the technical field of measuring electrical variables, and in particular to a method for detecting insulation of a DC power supply system based on 5G technology. Background Art

[0002] The DC power supply system of 5G technology provides stable power support for the 5G network, ensuring the normal operation of base stations and network equipment. The DC power supply system of 5G technology needs to pay special attention to insulation in the design to ensure the safety, reliability and performance of the system. Good insulation can effectively isolate the current and prevent the current from leaking to the equipment casing or other contact surfaces, thereby protecting operators and maintenance personnel from the risk of electric shock, and also improving the stability of the system. Therefore, the insulation of the DC power supply system is of great significance.

[0003] During the insulation detection of the DC power supply system of 5G technology, the insulation problem of the DC power supply system is analyzed by analyzing the changes in the current data in the DC power supply system. However, due to the existence of electromagnetic interference, the accuracy of the current data collected in the DC power supply system is not high, resulting in a reduction in the accuracy of the insulation detection of the DC power supply system of 5G technology. Summary of the invention

[0004] The present invention provides a DC power supply system insulation detection method based on 5G technology to solve the existing problems.

[0005] A DC power supply system insulation detection method based on 5G technology of the present invention adopts the following technical solution:

[0006] An embodiment of the present invention provides a method for insulation detection of a DC power supply system based on 5G technology, the method comprising the following steps:

[0007] Obtain leakage current signal data sequence and leakage voltage signal data sequence for several consecutive days in the DC power supply system of 5G technology;

[0008] By the difference between the adjacent data in the leakage current signal data sequence and the leakage voltage signal data sequence of each day, the current data sequence and the voltage data sequence of each day are obtained respectively; the time length corresponding to each day is recorded as the time period, the time length corresponding to any day is recorded as the target time period, and all time periods before the target time period are recorded as the reference time period of the target time period; by the difference between the current data at the corresponding moment in the leakage current signal data sequence of the target time period and each reference time period, and the difference between the data in the current data sequence, the similarity parameters between the target time period and each corresponding reference time period are obtained; by the difference between the similarity parameters and the data at the same position in the current data sequence and the voltage data sequence of the target time period, the initial abnormality factor of the target time period is obtained;

[0009] Acquire all abnormal sequences in the current data sequence of the target time period; obtain the insulation evaluation factor of the target time period through the trend change between the initial abnormal factor and all adjacent abnormal sequences;

[0010] The insulation evaluation factor of the target time period is used to conduct insulation testing on the DC power supply system of 5G technology.

[0011] Furthermore, the method of obtaining the current data sequence and the voltage data sequence of each day by the difference between adjacent data in the leakage current signal data sequence and the leakage voltage signal data sequence of each day comprises the following specific steps:

[0012] The differences between all the current data at adjacent moments in the daily leakage current signal data sequence are grouped into a sequence in chronological order, which is recorded as the daily current data sequence; the differences between all the voltage data at adjacent moments in the daily leakage voltage signal data sequence are grouped into a sequence in chronological order, which is recorded as the daily voltage data sequence.

[0013] Furthermore, the method of obtaining similar parameters between the target time period and each corresponding reference time period by comparing the current data at corresponding moments in the leakage current signal data sequence of the target time period with each reference time period and the data in the current data sequence includes the following specific steps:

[0014] Obtaining a first difference degree between the target time period and each corresponding reference time period according to a difference between current data at corresponding moments in the leakage current signal data sequence of the target time period and each reference time period;

[0015] According to the difference between all data in the current data sequence of the target time period and each reference time period, a second difference degree between the target time period and each corresponding reference time period is obtained;

[0016] The similarity parameter between the target time period and each corresponding reference time period is obtained through the first difference degree and the second difference degree.

[0017] Further, the step of obtaining a first difference degree between the target time period and each corresponding reference time period according to the difference between the current data at the corresponding moment in the leakage current signal data sequence of the target time period and each reference time period includes the following specific steps:

[0018] The average value of the difference between the current data at all corresponding moments in the leakage current signal data sequence of the target time period and each reference time period is recorded as the first difference degree between the target time period and each corresponding reference time period.

[0019] Furthermore, the step of obtaining the second difference degree between the target time period and each corresponding reference time period according to the difference between all data in the current data sequence of the target time period and each reference time period includes the following specific steps:

[0020] The difference between the cumulative sum of all data in the current data sequence of the target time period and each reference time period is recorded as the second difference degree between the target time period and each corresponding reference time period.

[0021] Furthermore, the initial abnormal factor of the target time period is obtained by the difference change between the data at the same position in the current data sequence and the voltage data sequence of the target time period through the similar parameters, and the specific steps include the following:

[0022] According to the difference between the data at the same position in the current data sequence and the voltage data sequence in the target time period, the current and voltage trend difference in the target time period is obtained;

[0023] According to the mean values ​​of similar parameters between the target time period and all corresponding reference time periods and the current and voltage trend differences of the target time period, the initial abnormal factor of the target time period is obtained;

[0024] Among them, the mean value of the similar parameters is negatively correlated with the initial abnormal factor of the target time period, and the current and voltage trend difference of the target time period is positively correlated with the initial abnormal factor of the target time period.

[0025] Furthermore, the current and voltage trend differences of the target time period are obtained according to the difference changes between the data at the same position in the current data sequence and the voltage data sequence of the target time period, and the specific steps include the following:

[0026] The average of the differences between all data at the same position in the current data sequence and the voltage data sequence in the target time period is recorded as the current and voltage trend difference in the target time period.

[0027] Furthermore, the step of acquiring all abnormal sequences in the current data sequence in the target time period includes the following specific steps:

[0028] The data in the current data sequence of the target time period that is greater than or equal to the preset parameter is recorded as abnormal data, and the sequence of continuous abnormal data in chronological order is recorded as an abnormal sequence.

[0029] Furthermore, the insulation evaluation factor of the target time period is obtained by the trend change between the initial abnormal factor and all adjacent abnormal sequences, and the specific steps include the following:

[0030] The slope between the mean values ​​of all data in two adjacent abnormal sequences in the target time period is taken as the slope between the two abnormal sequences;

[0031] The cumulative sum of the slopes between all adjacent abnormal sequences in the target time period is recorded as the trend feature of the target time period;

[0032] The result of normalizing the product of the initial abnormal factor and the trend characteristic of the target time period is recorded as the insulation evaluation factor of the target time period.

[0033] Furthermore, the insulation test of the DC power supply system of the 5G technology is performed by the insulation evaluation factor of the target time period, and the specific steps include the following:

[0034] Get the insulation evaluation factor of the current time period. If the insulation evaluation factor of the current time period is greater than or equal to the preset threshold, an early warning is issued; if the insulation evaluation factor of the current time period is less than the preset threshold No warning will be given.

[0035] The beneficial effects of the technical solution of the present invention are as follows: the present invention obtains similarity parameters between the target time period and each corresponding reference time period through the difference between the current data at corresponding moments in the leakage current signal data sequence of the target time period and each reference time period, and the difference between the data in the current data sequence, and improves the accuracy of similarity distribution analysis of current data in the target time period and all previous reference time periods through the similarity parameters; obtains the initial abnormal factor of the target time period through the difference changes between the similarity parameters, the current data sequence of the target time period and the data at the same position in the voltage data sequence, and reduces the influence of electromagnetic on the analysis process through the initial abnormal factor; obtains the insulation evaluation factor of the target time period through the trend change between the initial abnormal factor and all adjacent abnormal sequences, and improves the accuracy of trend feature analysis in the attenuation process of insulating materials; performs insulation detection of the DC power supply system of 5G technology through the insulation evaluation factor of the target time period, and improves the accuracy of insulation detection of the DC power supply system of 5G technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be 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.

[0037] Figure 1 This is a flowchart of the steps of a DC power system insulation detection method based on 5G technology of the present invention;

[0038] Figure 2 Insulation detection flow chart of DC power system for 5G technology. DETAILED DESCRIPTION

[0039] 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 insulation detection method of a DC power system based on 5G technology 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.

[0040] 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.

[0041] The following is a detailed description of a specific scheme of a DC power supply system insulation detection method based on 5G technology provided by the present invention in conjunction with the accompanying drawings.

[0042] See also Figure 1 , which shows a flowchart of a method for insulation detection of a DC power supply system based on 5G technology provided by an embodiment of the present invention, the method comprising the following steps:

[0043] Step S001: Collecting time series data of leakage current and leakage voltage in the DC power supply system of 5G technology.

[0044] It should be noted that due to long-term electrical stress, thermal stress or chemical reaction, the insulation materials in the DC power supply system may age over time, which may lead to a decrease in insulation performance. In order to ensure the safety of workers and the stability of the operation of the DC power supply system, it is necessary to detect the insulation conditions in the DC power supply system of 5G technology. Due to the damage of the insulation materials in the DC power supply system, the current data in the DC power supply system will change. Therefore, the insulation performance of the DC power supply system can be analyzed by the change of the current data, so it is necessary to collect the current data in time series for analysis.

[0045] It should be further explained that in the DC power supply system of 5G technology, the periodic change of current may be related to the peak and off-peak periods of network traffic. During peak periods, such as daytime on weekdays, the current may be higher, while during off-peak periods, such as nighttime, the current is lower, so the data is collected on a day-long basis.

[0046] Specifically, a DC leakage current sensor is installed on the cable in the DC power supply system, and the current data of all moments in the DC power supply system are collected at a sampling time interval of 0.5 seconds every day, and the current signal data of all moments are grouped into a sequence in chronological order, which is recorded as the leakage current signal data sequence of each day; and the leakage current signal data sequence of all days in a month is continuously collected. Among them, the sampling time interval and sampling duration are not specifically limited, and the implementer can determine according to the specific situation.

[0047] By using the fluxgate principle, the current collected in the DC power supply system is converted into voltage signal data proportional to the current, and the voltage signal data at all times of the day are formed into a set of sequences according to the order of the leakage current signal data sequence, which is recorded as the leakage voltage signal data sequence of each day. Among them, the fluxgate principle is a well-known technology and will not be described in detail here.

[0048] At this point, the leakage current signal data sequence and the leakage voltage signal data sequence for each day are obtained.

[0049] Step S002: Obtain the current data sequence and voltage data sequence of each day respectively by the difference between adjacent data in the leakage current signal data sequence and the leakage voltage signal data sequence of each day; record the time length corresponding to each day as the time period, record the time length corresponding to any day as the target time period, and record all time periods before the target time period as the reference time period of the target time period; obtain similar parameters between the target time period and each reference time period by the difference between the current data at the corresponding moment in the leakage current signal data sequence of the target time period and each reference time period, and the difference between the data in the current data sequence; obtain the initial abnormal factor of the target time period by the similar parameters and the difference between the data at the same position in the current data sequence and the voltage data sequence of the target time period.

[0050] It should be noted that in the DC power supply system of 5G technology, when the insulating material of the DC power supply system is intact, the current data at each moment in the DC power supply system collected by the DC leakage sensor should be 0, and the difference between the current data at adjacent moments should be 0, that is, the difference between the voltage data at adjacent moments after conversion should also be 0; when the insulating material of the DC power supply system is damaged, causing leakage in the DC power supply system, that is, the current data at each moment in the DC power supply system is not 0, and there is a certain degree of fluctuation.

[0051] Preferably, the differences between the current data at all adjacent moments in the daily leakage current signal data sequence are grouped into a group of sequences in chronological order, recorded as the daily current data sequence; the differences between the voltage data at all adjacent moments in the daily leakage voltage signal data sequence are grouped into a group of sequences in chronological order, recorded as the daily voltage data sequence.

[0052] It should be noted that since the electromagnetic interference to the DC power supply system mainly comes from electronic equipment and electromagnetic radiation sources, and the radiation of the electromagnetic radiation source shows a certain periodic change, the electromagnetic interference corresponding to the same leakage current data in different periodic time periods is the same, that is, the data fluctuation distribution in different periodic time periods is the same; and the damage to the insulation measurement in the DC power supply system causes the fluctuation distribution in different periodic time periods to be different. Therefore, the difference in current data at corresponding moments in the leakage current signal data sequence of the target time period and each reference time period, and the difference between the data in the current data sequence, obtain the similarity parameters between the target time period and each corresponding reference time period.

[0053] Preferably, the time length corresponding to each day is recorded as a time period, the time length corresponding to any day is recorded as a target time period, and all time periods before the target time period are recorded as reference time periods of the target time period.

[0054] Further, as an embodiment, the specific calculation method of the similarity parameter between the target time period and each corresponding reference time period is:

[0055] The average value of the difference between the current data at all corresponding moments in the leakage current signal data sequence of the target time period and each reference time period is recorded as the first difference degree between the target time period and each corresponding reference time period;

[0056] The difference between the cumulative sum of all data in the current data sequence of the target time period and each reference time period is recorded as the second difference degree between the target time period and each corresponding reference time period;

[0057] The similarity parameter between the target time period and each corresponding reference time period is obtained through the first difference degree and the second difference degree.

[0058] In one embodiment of the present invention, it is specifically expressed by the formula:

[0059]

[0060] In the formula, Represents the cumulative sum of all data in the current data sequence of the target time period, Indicates the first The cumulative sum of all data in the current data sequence of the reference time period, The first Data at a moment, Indicates the first The first of the leakage current signal data sequences of the reference time period Data at a moment, Indicates the number of data at all times in each leakage current signal data sequence, is the absolute value symbol, represents an exponential function with a natural constant as base, Indicates the target time period and the corresponding The purpose of adding 0.01 to the formula is to prevent the denominator from being zero.

[0061] in, It represents the difference between the leakage current data collected in the target time period and the corresponding reference time period at the same time. The larger the difference is, the lower the similarity between the current data in the two time periods is. On the contrary, the smaller the difference is, the more it indicates that there is no leakage in the DC power supply system, that is, the current distribution is the same in the corresponding time period, and the higher the similarity between the current data in the two time periods is. It represents the ratio of the difference between the current data at adjacent moments in the target time period and each corresponding reference time period. When the ratio is closer to 1, it means that there is no leakage in the DC power supply system, that is, the similarity between the current data differences at adjacent moments in the two time periods is higher. Conversely, it means that there is leakage in the DC power supply system, that is, the similarity between the current data differences at adjacent moments in the two time periods is lower.

[0062] At this point, the similarity parameters between the target time period and each corresponding reference time period are obtained.

[0063] It should be noted that, due to the fluxgate principle that converts current data into proportional voltage data, when there is no electromagnetic interference in the external environment, the current data and voltage data change linearly with time, and when subject to electromagnetic interference, there is a deviation in the linear relationship between the current data and the voltage data, that is, it may become a nonlinear relationship. Therefore, the initial abnormal factor of the target time period is obtained by the difference between the similar parameters, the current data sequence of the target time period, and the data at the same position in the voltage data sequence.

[0064] Preferably, as an embodiment, the specific calculation method of the initial abnormal factor of the target time period is:

[0065] The average of the differences between all data at the same position in the current data sequence and the voltage data sequence in the target time period is recorded as the current and voltage trend difference in the target time period;

[0066] According to the mean values ​​of similar parameters between the target time period and all corresponding reference time periods and the current and voltage trend differences of the target time period, the initial abnormal factor of the target time period is obtained;

[0067] Among them, the mean value of the similar parameters is negatively correlated with the initial abnormal factor of the target time period, and the current and voltage trend difference of the target time period is positively correlated with the initial abnormal factor of the target time period.

[0068] In one embodiment of the present invention, it is specifically expressed by the formula:

[0069]

[0070] In the formula, The first data, The first data, Indicates the number of all data in the voltage data sequence of the target time period, represents the mean value of similarity parameters between the target time period and all corresponding reference time periods, represents the initial anomaly factor of the target time period, The absolute value symbol is added in the formula to prevent the denominator from being zero.

[0071] in, Indicates the changing relationship between the voltage data and current data at adjacent moments in the target time period. When it presents a linear change, it means that the closer the ratio of the two is to 1, the smaller the possibility of electromagnetic interference, and the smaller the initial abnormal factor of the target time period at this time; when it presents a nonlinear change, it means that the closer the ratio of the two is to 1, the greater the possibility of electromagnetic interference, and the larger the initial abnormal factor of the target time period at this time. When the mean value of the similar parameters between the target time period and all corresponding reference time periods is larger, it means that the current distribution between the target time period and the previous reference is more similar, that is, the possibility of abnormal current in the target time period is smaller; when the mean value of the similar parameters between the target time period and all corresponding reference time periods is smaller, it means that the current distribution between the target time period and the previous reference is more different, that is, the possibility of abnormal current in the target time period is greater.

[0072] At this point, the initial abnormal factor of the target time period is obtained.

[0073] Step S003: Acquire all abnormal sequences in the current data sequence of the target time period; obtain the insulation evaluation factor of the target time period through the trend change between the initial abnormal factor and all adjacent abnormal sequences.

[0074] It should be noted that the working and non-working phases of the day have a certain impact on the current in the DC power supply system of 5G technology. That is, during the high-load working time of the equipment, the load current is large, which may cause the insulation material of the power supply system to expand due to heat, thereby increasing the leakage current; in the non-working phase, the leakage current may be small due to the small current itself, so the leakage current in the non-working phase will affect the abnormal analysis results, so further analysis is performed through the leakage current in the working phase.

[0075] Preferably, a parameter is preset , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. It can be determined according to the specific implementation situation. The current data sequence in the target time period is greater than or equal to the preset parameter The data is recorded as abnormal data, and the sequence of continuous abnormal data in chronological order is recorded as abnormal sequence.

[0076] At this point, all abnormal sequences in the current data sequence of the target time period are obtained.

[0077] It should be further explained that as the insulation material in the DC power supply system is used for a longer time, the degree of wear of the insulation material will increase, that is, the current data collected by the DC leakage current sensor will gradually increase, that is, it will show a trend over time. Therefore, the insulation evaluation factor of the target time period is obtained through the trend change between the initial abnormal factor and all adjacent abnormal sequences.

[0078] Further, as an embodiment, the specific calculation method of the insulation evaluation factor in the target time period is:

[0079] The slope between the mean values ​​of all data in two adjacent abnormal sequences in the target time period is taken as the slope between the two abnormal sequences;

[0080] The cumulative sum of the slopes between all adjacent abnormal sequences in the target time period is recorded as the trend feature of the target time period;

[0081] The result of normalizing the product of the initial abnormal factor and the trend characteristic of the target time period is recorded as the insulation evaluation factor of the target time period.

[0082] In one embodiment of the present invention, it is specifically expressed by the formula:

[0083]

[0084] In the formula, represents the initial anomaly factor of the target time period, Indicates the target time period The abnormal sequence and The slope between the abnormal sequences, Indicates the number of all abnormal sequences in the target time period, Indicates the insulation evaluation factor for the target time period, Represents a linear normalization function. The slope between the mean data of all data in the two abnormal sequences is taken as the slope between the two abnormal sequences. When the slope between the mean data is calculated, the horizontal axis is time and the vertical axis is the corresponding data.

[0085] Among them, when the cumulative sum of the slopes between two adjacent abnormal sequences is larger, the leakage current shows a stronger trend of increasing, indicating that the insulation performance in the DC power supply system is worse, that is, the insulation evaluation factor is larger; when the cumulative sum of the slopes between two adjacent abnormal sequences is smaller, it means that the insulation performance in the DC power supply system is stronger, that is, the insulation evaluation factor is larger. When the initial abnormal factor of the target time period is larger, it means that the possibility of insulation abnormality in the DC power supply system is greater, that is, the worse the insulation performance in the DC power supply system, the greater the insulation evaluation factor; when the initial abnormal factor of the target time period is smaller, it means that the possibility of insulation abnormality in the DC power supply system is smaller, that is, the stronger the insulation performance in the DC power supply system, the smaller the insulation evaluation factor.

[0086] At this point, the insulation evaluation factor for the target time period is obtained.

[0087] Step S004: Perform insulation detection on the DC power supply system of 5G technology through the insulation evaluation factor of the target time period.

[0088] It should be noted that the worse the insulation performance in the DC power supply system is, the greater the possibility of insulation abnormalities in the DC power supply system is, and the larger the insulation evaluation factor is, which means that the insulation material in the DC power supply system is not compliant, and an early warning should be issued and the insulation material of the DC power supply system should be replaced.

[0089] Preset a threshold , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. It may depend on the specific implementation situation.

[0090] Get the insulation evaluation factor of the current time period. If the insulation evaluation factor of the current time period is greater than or equal to the preset threshold If the insulation evaluation factor of the current time period is less than the preset threshold, an early warning is issued. When the insulation is detected, no warning is given. The insulation detection flow chart of the DC power supply system of 5G technology is as follows: Figure 2 shown.

[0091] It should be noted that the The model is only used to represent negative correlation and constrain the output of the model to be in In the specific implementation, it can be replaced by other models with the same purpose. This embodiment is only based on The model is described as an example without any specific limitation. is the input to the model.

[0092] At this point, this embodiment is completed.

[0093] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A DC power supply system insulation detection method based on 5G technology, characterized in that: The method comprises the following steps: Obtain leakage current signal data sequence and leakage voltage signal data sequence for several consecutive days in the DC power supply system of 5G technology; By the difference between the adjacent data in the leakage current signal data sequence and the leakage voltage signal data sequence of each day, the current data sequence and the voltage data sequence of each day are obtained respectively; the time length corresponding to each day is recorded as the time period, the time length corresponding to any day is recorded as the target time period, and all time periods before the target time period are recorded as the reference time period of the target time period; by the difference between the current data at the corresponding moment in the leakage current signal data sequence of the target time period and each reference time period, and the difference between the data in the current data sequence, the similarity parameters between the target time period and each corresponding reference time period are obtained; by the difference between the similarity parameters and the data at the same position in the current data sequence and the voltage data sequence of the target time period, the initial abnormality factor of the target time period is obtained; Acquire all abnormal sequences in the current data sequence of the target time period; obtain the insulation evaluation factor of the target time period through the trend change between the initial abnormal factor and all adjacent abnormal sequences; Conduct insulation testing of the DC power supply system of 5G technology through insulation evaluation factors in the target time period; The initial abnormal factor of the target time period is obtained by using the similar parameters, the difference between the data at the same position in the current data sequence and the voltage data sequence of the target time period, and the specific steps include the following: According to the difference between the data at the same position in the current data sequence and the voltage data sequence in the target time period, the current and voltage trend difference in the target time period is obtained; According to the mean values ​​of similar parameters between the target time period and all corresponding reference time periods and the current and voltage trend differences of the target time period, the initial abnormal factor of the target time period is obtained; The mean of the similar parameters is negatively correlated with the initial abnormal factor of the target time period, and the current and voltage trend difference of the target time period is positively correlated with the initial abnormal factor of the target time period; The step of obtaining the insulation evaluation factor of the target time period through the trend change between the initial abnormal factor and all adjacent abnormal sequences includes the following specific steps: The slope between the mean values ​​of all data in two adjacent abnormal sequences in the target time period is taken as the slope between the two abnormal sequences; The cumulative sum of the slopes between all adjacent abnormal sequences in the target time period is recorded as the trend feature of the target time period; The result of normalizing the product of the initial abnormal factor and the trend characteristic of the target time period is recorded as the insulation evaluation factor of the target time period; The insulation test of the DC power supply system of the 5G technology is performed by using the insulation evaluation factor of the target time period, and the specific steps include the following: Get the insulation evaluation factor of the current time period. If the insulation evaluation factor of the current time period is greater than or equal to the preset threshold, an early warning is issued; if the insulation evaluation factor of the current time period is less than the preset threshold No warning will be given.

2. According to a 5G technology-based DC power supply system insulation detection method according to claim 1, it is characterized in that: The method of obtaining the current data sequence and the voltage data sequence of each day respectively by the difference between adjacent data in the leakage current signal data sequence and the leakage voltage signal data sequence of each day includes the following specific steps: The differences between all the current data at adjacent moments in the daily leakage current signal data sequence are grouped into a sequence in chronological order, which is recorded as the daily current data sequence; the differences between all the voltage data at adjacent moments in the daily leakage voltage signal data sequence are grouped into a sequence in chronological order, which is recorded as the daily voltage data sequence.

3. According to a 5G technology-based DC power supply system insulation detection method according to claim 1, it is characterized in that: The specific steps of obtaining similar parameters between the target time period and each corresponding reference time period by the difference between the current data at the corresponding moment in the leakage current signal data sequence of the target time period and each reference time period and the difference between the data in the current data sequence are as follows: Obtaining a first difference degree between the target time period and each corresponding reference time period according to a difference between current data at corresponding moments in the leakage current signal data sequence of the target time period and each reference time period; According to the difference between all data in the current data sequence of the target time period and each reference time period, a second difference degree between the target time period and each corresponding reference time period is obtained; The similarity parameter between the target time period and each corresponding reference time period is obtained through the first difference degree and the second difference degree.

4. According to the 5G technology-based DC power supply system insulation detection method of claim 3, it is characterized in that: The step of obtaining a first difference degree between the target time period and each corresponding reference time period according to the difference between the current data at the corresponding moment in the leakage current signal data sequence of the target time period and each reference time period comprises the following specific steps: The average value of the difference between the current data at all corresponding moments in the leakage current signal data sequence of the target time period and each reference time period is recorded as the first difference degree between the target time period and each corresponding reference time period.

5. According to the 5G technology-based DC power supply system insulation detection method of claim 3, it is characterized in that: The step of obtaining the second difference degree between the target time period and each corresponding reference time period according to the difference between all data in the current data sequence of the target time period and each reference time period includes the following specific steps: The difference between the cumulative sum of all data in the current data sequence of the target time period and each reference time period is recorded as the second difference degree between the target time period and each corresponding reference time period.

6. According to a 5G technology-based DC power supply system insulation detection method according to claim 1, it is characterized in that: The method of obtaining the current and voltage trend difference of the target time period according to the difference change between the data at the same position in the current data sequence and the voltage data sequence of the target time period includes the following specific steps: The average of the differences between all data at the same position in the current data sequence and the voltage data sequence in the target time period is recorded as the current and voltage trend difference in the target time period.

7. According to a 5G technology-based DC power supply system insulation detection method according to claim 1, it is characterized in that: The specific steps of obtaining all abnormal sequences in the current data sequence in the target time period include: The data in the current data sequence of the target time period that is greater than or equal to the preset parameter is recorded as abnormal data, and the sequence of continuous abnormal data in chronological order is recorded as an abnormal sequence.

Images