Internet-of-things method for box-type substation and box-type substation

Abstract

The invention relates to the technical field of substations, in particular to an internet of things method for a box-type substation and the box-type substation. The method comprises the following steps: acquiring different sequences by using an Internet of Things technology; periodically detecting the signal sequence to obtain periodicity, and obtaining internal characteristics of the signal in combination with integral assignment and fluctuation conditions of the sequence; external environment features are obtained based on cabin indoor and outdoor temperature sequence differences, and time domain fault features are obtained through combination of the two features; converting the sound wave signal into a spectrogram, and obtaining frequency domain fault features based on sequence monotonicity, amplitude, data change rate and peak value number in the spectrogram; and constructing a fault code according to the time domain fault feature and the frequency domain fault feature, and judging a partial discharge fault. According to the method, the characteristics of the monitoring data are mined fully, so that more accurate fault monitoring of the box-type substation is realized, and the false alarm rate is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of substations, and in particular to an Internet of Things method for box-type substations and a box-type substation. Background Art

[0002] With the development of smart grid, the demand for grid transformation is gradually increasing. In this process, box-type substation, as a complete set of power distribution equipment, integrates transformers, high and low voltage switchgear, power compensation devices, etc., and has become the mainstream equipment for terminal power distribution. Its proportion in the power supply and distribution system is also increasing. Therefore, the safety of box-type substation has become the key to ensuring the power supply and stability of the power supply and distribution system. With the application of Internet of Things technology, box-type substations are also developing in the direction of intelligence, and the online monitoring of the status of box-type substations has become a research focus.

[0003] The prior art installs various sensors in the box-type substation to monitor the electrical variables and non-electrical variables during the operation of the box-type substation, and judges whether the box-type substation has a fault based on the abnormal changes of these data. However, the prior art makes too simple use of monitoring data, often by setting thresholds. When one or more data exceeds the threshold, an alarm is issued in time, and offline investigation is required. This method does not make full use of the monitoring data and does not deeply explore the changing characteristics of the data. At the same time, due to the complexity of the operation of the box-type substation, the setting of a single threshold increases the probability of false alarms during the monitoring of the box-type substation, which undoubtedly increases the difficulty of troubleshooting, and at the same time causes a large number of invalid investigations, increasing the difficulty of work. Therefore, there is an urgent need for a more accurate fault monitoring method to reduce the false alarm rate. Summary of the invention

[0004] In order to solve the technical problem that abnormal monitoring false alarms increase the difficulty of troubleshooting, this application provides an IoT method for a box-type substation and a box-type substation. The technical solutions adopted are as follows: In a first aspect, the present application proposes an Internet of Things method for a box-type substation, the method comprising the following steps: The Internet of Things technology is used to collect a local signal sequence, an external temperature sequence, and temperature sequences and sound wave signal sequences of different cabins each time; Process the local signal sequence based on a window of preset size to obtain a moving average sequence; determine the periodicity based on the distance between the peaks of the moving average sequence; mark the peak of the local signal sequence to obtain the abnormal peak and its neighborhood range; and obtain the data fluctuation based on the coefficient of variation of the data in the neighborhood range, and obtain the internal characteristics of the signal according to the fluctuation of the data in the local signal sequence, the overall amplitude and the periodicity; obtain the external environment characteristics according to the difference in the temperature fluctuation of the cabin and the correlation between the temperature series inside and outside the cabin; forwardly fuse the internal characteristics of the signal and the external environment characteristics to obtain the time domain fault characteristics; The acoustic wave signal sequence of the cabin is segmented, and the data change rate is obtained based on the slope of the extreme value connection line after curve fitting; the acoustic wave signal sequence is converted into a spectrum diagram, and curve fitting is performed according to the peak value and the corresponding frequency in the spectrum diagram, and the monotonicity of the acoustic wave signal sequence in the frequency domain is obtained based on the positive and negative differences of the preset number of derivatives; the frequency domain fault characteristics are calculated based on the monotonicity of the acoustic wave signal sequence in the frequency domain, the data change rate, the number of peaks, and the average amplitude of each cabin; The time domain fault features and frequency domain fault features are clustered into vectors, and the fault code is obtained according to the difference in the fluctuation of the time domain fault features and frequency domain fault features in the cluster cluster to determine the partial discharge fault.

[0005] In the above scheme, the present application calculates the time domain fault characteristics according to the change characteristics of the local discharge signal and temperature in the box-type substation. This index reflects the time series change characteristics of the local discharge signal and temperature, which helps to improve the accuracy of the subsequent local discharge fault diagnosis and reduce the probability of misjudgment; then, according to the time-frequency domain characteristics of the acoustic signal, the frequency domain fault characteristics are calculated, which helps to capture the specific characteristics of the local discharge fault, improve the accuracy of the local discharge fault identification, and reduce the possibility of missed judgment; finally, clustering is performed according to the two indicators, and the fluctuation of the data in different clustering clusters is used to identify the fault, so as to improve the accuracy of fault identification. In this way, combined with the change characteristics of the monitoring data of the box-type substation in the time and frequency domain for fault judgment, it is helpful to capture the local discharge characteristics more carefully and sensitively, thereby improving the accuracy of the identification of the local discharge fault, and at the same time, the fault judgment is performed according to the data change characteristics, avoiding the possibility of misjudgment caused by the size change of the operating data alone, and making full use of the characteristics of the mining monitoring data, thereby realizing more accurate fault monitoring for the box-type substation and reducing the false alarm rate.

[0006] In one embodiment, the method for determining periodicity based on the distance between the peaks of the moving average sequence is: The peak indexes of the moving average sequence are sorted according to their sizes to obtain a position sequence, a first-order difference sequence of the position sequence is calculated, and the periodicity is represented by the variance of the first-order difference sequence.

[0007] In one embodiment, the method for obtaining the abnormal peak value and its neighborhood range by marking the peak value of the local signal sequence is: All peaks in the local signal sequence and the upper quartile of the peaks are obtained, and peaks greater than the upper quartile are marked as abnormal peaks; a domain range of a preset size is obtained with each abnormal peak as the center.

[0008] In one embodiment, the method for obtaining the internal characteristics of the signal according to the fluctuation of the data in the local signal sequence, the overall amplitude and the periodicity is: The internal eigenvalue of the signal is positively correlated with the fluctuation of the data in the local signal sequence and the overall amplitude, and is negatively correlated with the periodicity in the local signal sequence.

[0009] In one embodiment, the method for obtaining the external environment characteristics according to the difference between the temperature fluctuation of the cabin and the correlation of the temperature series inside and outside the cabin is: Calculate the variance of the temperature series inside different cabins, and use the variance as the temperature fluctuation measure of the temperature series corresponding to each cabin; calculate the correlation measure between the temperature series of each cabin and the external temperature series; The external environmental characteristics are negatively correlated with the correlation metric of each cabin and positively correlated with the temperature fluctuation metric.

[0010] In one embodiment, the method for acquiring the data change rate is: Perform polynomial fitting on each segmented sound wave sequence to obtain the corresponding fitting curve equation; sort all the corresponding extreme values ​​in index order to form an extreme value sequence; The slopes of two adjacent extreme points in the extreme value sequence are calculated, the mean of all slopes corresponding to the extreme value sequence is taken as the average slope of this segmented sound wave sequence, and the mean of the average slopes of all segmented sound wave sequences is recorded as the data change rate.

[0011] In one embodiment, the method of performing curve fitting according to the peak value and the corresponding frequency in the spectrum diagram and obtaining the monotonicity of the sound wave signal sequence in the frequency domain based on the positive and negative differences of the preset number of derivatives is: Calculate the mean of all peaks in the spectrum graph, and mark the peaks with amplitudes greater than the mean as characteristic peaks; use the peak value of the characteristic peak as the ordinate and the frequency corresponding to the characteristic peak as the abscissa to perform least squares fitting and output a quadratic fitting curve; A number of derivative points are preset in the quadratic fitting curve, the reciprocal of each derivative point is calculated, the positive and negative derivatives are counted, and the ratio of the number of negative derivatives to the number of positive derivatives is taken as the monotonicity of the acoustic signal sequence in the frequency domain.

[0012] In one embodiment, the method for calculating the frequency domain fault characteristics based on the monotonicity, data change rate, number of peaks and average amplitude of the acoustic wave signal sequence of each compartment in the frequency domain is: The frequency domain fault characteristics are positively correlated with the data change rate, peak number and average amplitude of the acoustic signal sequence, and negatively correlated with the monotonicity of the acoustic signal sequence in the frequency domain.

[0013] In one embodiment, the method for obtaining the fault code according to the difference in fluctuation of the time domain fault characteristics and the frequency domain fault characteristics in the cluster is: Calculate the mean of the time domain fault features and frequency domain fault features in each cluster; mark the cluster with the largest sum of the two means as the suspected fault cluster, and mark the cluster with the smallest sum of the two means as the fault-free cluster; the expression of the fault code is: ; It is a fault code. is the sum of the coefficients of variation of the time domain fault features and frequency domain fault features in the fault-free cluster. It is the sum of the coefficients of variation of the time domain fault features and frequency domain fault features in the set of all elements in the fault-free clusters and suspected fault clusters. is the mutation threshold.

[0014] On the other hand, an embodiment of the present application also provides a box-type substation, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of the Internet of Things method for a box-type substation described in any one of the above items are implemented.

[0015] The beneficial effects of this application are: This application calculates the time domain fault characteristics according to the change characteristics of the local discharge signal and temperature in the box-type substation. This indicator reflects the time series change characteristics of the local discharge signal and temperature, which helps to improve the accuracy of the subsequent local discharge fault diagnosis and reduce the probability of misjudgment; then, according to the time-frequency domain characteristics of the acoustic signal, the frequency domain fault characteristics are calculated, which helps to capture the specific characteristics of the local discharge fault, improve the accuracy of the local discharge fault identification, and reduce the possibility of missed judgment; finally, clustering is performed according to the two indicators, and the fluctuation of the data in different clustering clusters is used to identify the fault, so as to improve the accuracy of fault identification. In this way, combined with the change characteristics of the monitoring data of the box-type substation in the time and frequency domain for fault judgment, it is helpful to capture the local discharge characteristics more carefully and sensitively, thereby improving the accuracy of the identification of the local discharge fault, and at the same time, the fault judgment is performed according to the data change characteristics, avoiding the possibility of misjudgment caused by the size change of the operating data alone, and making full use of the characteristics of the mining monitoring data, thereby realizing more accurate fault monitoring for the box-type substation and reducing the false alarm rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A flow chart of an Internet of Things method for a box-type substation provided in one embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by this application to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of the Internet of Things method for box-type substation and box-type substation proposed in this application 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.

[0019] 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 application belongs.

[0020] Internet of Things method for box-type substation and box-type substation implementation example: The specific scheme of the Internet of Things method for box-type substation provided by this application is described in detail below with reference to the accompanying drawings.

[0021] See also Figure 1 , which shows a flow chart of a method for interconnecting things for a box-type substation provided by an embodiment of the present application, the method comprising the following steps: Step S001, collecting different sequences using Internet of Things technology.

[0022] The box-type substation is monitored using the Internet of Things technology. The perception layer collects data from the box-type substation through various sensors and equipment installed in the box-type substation. Ultrasonic PD detectors are used to monitor partial discharge signals. Temperature sensors and sound sensors installed in the transformer room, high-voltage room, and low-voltage room of the box-type substation are used to collect operating environment data of the box-type substation. Temperature monitoring equipment outside the box-type substation is used to collect external environmental temperature. In this embodiment, the acquisition frequency of the partial discharge signal is 50 KHz, the acquisition frequency of the acoustic wave signal is 10 KHz, the temperature is acquired once per second, and the total acquisition time is 15 minutes.

[0023] The various types of data collected by the perception layer are input separately, and every 5 data in the same category are grouped together, and pre-processed using a filtering algorithm. The filtering algorithm used in this embodiment is a median average filtering algorithm, and the processed data are formed into corresponding data sequences according to the order of collection time, which are local signal sequence, temperature sequence, sound wave signal sequence, and external temperature sequence. The median average filtering algorithm is a well-known technology and will not be described in detail. Since a temperature sensor and a sound sensor are installed in each transformer room, high-voltage room, and low-voltage room, a temperature sequence and a sound wave signal sequence are obtained in each transformer room, high-voltage room, and low-voltage room. The collected data is uploaded to the Internet of Things platform.

[0024] So far, the local signal sequence, the external temperature sequence, and the temperature sequences and acoustic wave signal sequences of different cabins have been obtained.

[0025] Step S002, perform periodic detection on the signal sequence to obtain periodicity, and obtain the internal characteristics of the signal by combining the overall value assignment and fluctuation of the sequence; then obtain the external environment characteristics based on the difference in temperature sequences inside and outside the cabin, and combine the two to obtain the time domain fault characteristics.

[0026] As the mainstream equipment in the power supply and distribution system, the safety of the box-type substation has a decisive influence on the quality of power supply and distribution. Therefore, ensuring the safety of the box-type substation has become the key. With the development of Internet of Things technology, the operating status of the box-type substation is monitored by various sensors, and the empirical threshold is set. When the operating data exceeds the threshold, a timely reminder is given, which improves the efficiency of fault response processing. However, this method is too simple to use the monitoring data, and often only considers the size change of the monitoring data, which makes the anti-interference ability weak and the false alarm rate large. For example, the partial discharge fault in the box-type substation often leads to intermittent data anomalies. Due to the complexity of the operating environment of the box-type substation, it may also cause accidental anomalies in the data. Therefore, it is difficult to accurately and timely judge whether a partial discharge fault has occurred based only on the relationship between the size of the data and the threshold. Therefore, it is necessary to deeply explore the information hidden in the data, determine the change characteristics of the data, avoid judging only based on the size of the data, improve the anti-interference ability of the monitoring system, reduce the false alarm rate, thereby improving the accuracy of fault diagnosis for the box-type substation, and helping to ensure the safe operation of the box-type substation.

[0027] Partial discharge fault means that as the insulation layer in some areas is damaged or aged, the insulation performance is weakened, thereby reducing the breakdown field strength required to break down the insulation material, which in turn causes the insulation material to be broken down; or when the field strength is unevenly distributed in the system, the local field strength is too large, causing the insulation material to be broken down; this fault will gradually damage the insulation material in the corresponding area, ultimately leading to serious hazards such as insulation failure, equipment failure or fire.

[0028] When there is no partial discharge fault in the box-type substation, each insulation layer has a good insulation effect, so the partial discharge signal is weak, the fluctuation is small, and there is no obvious abnormal peak. Due to the good insulation effect, the partial discharge signal will not strictly reflect the periodic changes of electric energy in a timely manner, that is, the periodicity of the partial discharge signal is weak or there is almost no periodic change. When a partial discharge fault occurs in the box-type substation, the insulation effect of the insulation layer is weakened, so that the partial discharge signal is enhanced, an obvious abnormal peak appears, and the volatility of the data near the peak increases. With the periodic changes of electric energy, the partial discharge signal will also show obvious periodic changes.

[0029] Secondly, when there is no partial discharge fault in the box-type substation, the insulation layer is more effective, so the temperature fluctuation is smaller, and the temperature change is mainly affected by the change in the external temperature, that is, there is a high correlation with the external temperature; when a partial discharge fault occurs in the box-type substation, the insulation material is broken down, which will cause the temperature to increase, thereby increasing the temperature fluctuation, and because the partial discharge has a greater impact on the temperature, the correlation with the external ambient temperature is weakened.

[0030] A local signal sequence and a window of preset length are input, and a moving average method is used to output a moving average sequence. In this embodiment, the preset length is 50. The moving average method is a well-known technology and will not be described in detail. The indexes of the peaks in the moving average sequence are sorted according to the index size to form a position sequence. The position sequence indicates the position order of the peaks. The first-order difference sequence of the position sequence is calculated. The data value in the first-order difference sequence represents the distance between the two peaks.

[0031] When a local discharge fault exists, the amplitude of the local discharge signal at the moment when the insulating layer is broken down reaches the peak value in the local area, which is approximately equal to the position of the peak value after moving average. Due to the periodic change of electric energy, the time interval of the insulation layer breakdown is basically the same, so the index difference between adjacent peak values ​​after moving average is also basically the same or close. Based on this feature, the periodicity can be represented by the variance of the first-order difference sequence of the position sequence, where the periodicity can also be represented by the standard deviation of the first-order difference sequence. In this embodiment, the variance is taken as an example for calculation.

[0032] All peaks and the upper quartile of the peaks in the local signal sequence are obtained, and the peaks greater than the upper quartile are marked as abnormal peaks. At the same time, with each abnormal peak as the center, the number of signal values ​​within the preset neighborhood range of the abnormal peak is obtained in the local signal sequence. In this embodiment, the size of the preset neighborhood range is 200.

[0033] The mean of the coefficient of variation of all data in the neighborhood of the abnormal peak in the local signal sequence is used as the fluctuation of the data in the neighborhood of the abnormal peak in the local signal sequence. The coefficient of variation is used to measure the discreteness of the data. The more discrete the data is, the more obvious the fluctuation of the data curve will be.

[0034] When the amplitude of the partial discharge signal is small, the data fluctuation between abnormal peaks is small, and the periodicity is weak, no partial discharge fault occurs in the box-type substation; that is, the internal characteristics of the signal are obtained based on the fluctuation of the data in the local signal sequence, the overall amplitude and the periodicity; The internal eigenvalue of the signal is positively correlated with the fluctuation of the data in the local signal sequence and the overall amplitude, and is negatively correlated with the periodicity in the local signal sequence.

[0035] It should be noted that positive correlation means that when one variable increases, the other variable also increases, and the two variables change in the same direction. When one variable changes from large to small or from small to large, the other variable also changes from large to small or from small to large. The specific relationship is determined by actual application and this application does not impose any special restrictions.

[0036] It should be noted that negative correlation means that when one variable increases, the other variable decreases accordingly, and the two variables change in opposite directions. When one variable changes from large to small or from small to large, the other variable also changes from small to large or from large to small. The specific relationship is determined by actual application and this application does not impose any special restrictions.

[0037] Preferably, in this embodiment, the expression of the internal characteristic of the signal is: , is the average amplitude of the local signal sequence, is a measure of the fluctuation of the local signal sequence, is a measure of the periodicity of the partial discharge signal, is a parameter adjustment coefficient to avoid the denominator being 0. In this embodiment, the value is 1. Represents the internal characteristics of the signal.

[0038] Calculate the variance of the temperature series inside different cabins, use the variance as the temperature fluctuation measure of the temperature series corresponding to each cabin, and calculate the correlation measure between the temperature series of each cabin and the external temperature series; When there is no partial discharge fault in the box-type substation, the temperature fluctuation of each compartment is small, and the temperature fluctuation is mainly affected by the external ambient temperature, and the positive correlation between the temperature and the external ambient temperature is strong. At this time, the correlation measure is large and the temperature fluctuation measure is small. Therefore, the external environment characteristics are obtained based on the correlation measure and temperature fluctuation measure of each compartment; The external environmental characteristics are negatively correlated with the correlation metric of each cabin and positively correlated with the temperature fluctuation metric.

[0039] Preferably, the expression of the external environment characteristics is: , represents the temperature fluctuation measure of the i-th cabin, represents the correlation measure of the ith cabin, Indicates the characteristics of the external environment.

[0040] Whether based on temperature or electrical signals, the analysis is in the time domain, so the time domain fault characteristics are calculated based on the internal characteristics of the signal and the external environment characteristics; The time domain fault characteristics are positively correlated with the internal characteristics of the signal and the external environment characteristics.

[0041] Preferably, in this embodiment, the time domain fault feature is the product of the internal signal feature and the external environment feature.

[0042] So far, the time domain fault characteristics within the time domain variation range are obtained based on the analysis of the internal signal and the external environment.

[0043] Step S003: convert the acoustic wave signal into a frequency spectrum, and obtain frequency domain fault characteristics based on sequence monotonicity, amplitude, data change rate and peak number in the frequency spectrum.

[0044] The time domain fault characteristics measure the time series changes of partial discharge signals and temperature during the operation of the box-type substation. However, since the temperature is greatly affected by the external environment, and the partial discharge signal is also closely related to the quality of power supply, it is difficult to fully reflect the insulation quality of the internal components of the box-type substation based on the changes in these data alone, which increases the possibility of misjudgment or omission of partial discharge faults. There are changes in the acoustic signal during the operation of the box-type substation. The acoustic signal is closely related to the performance of the internal components of the box-type substation. At the same time, when partial discharge occurs, a specific characteristic acoustic signal will be generated. Therefore, the recognition of the characteristics of the acoustic signal helps to enhance the accuracy of partial discharge fault detection.

[0045] When there is no partial discharge fault in the box-type substation, the amplitude of the acoustic wave signal is small and shows periodic changes, and the monotonicity does not change frequently within a cycle, so that the number of peaks in a cycle is small and the data changes slowly within a monotonic interval; in the frequency domain, the acoustic wave signal is mainly concentrated in the low-frequency part, and the signal amplitude of the high-frequency part is very low, so the amplitude shows an overall decreasing trend from low frequency to high frequency.

[0046] When a partial discharge fault occurs in a box-type substation, the breakdown of the insulating material will cause the acoustic signal to fluctuate frequently, that is, the acoustic signal still has periodic changes, but the amplitude of the acoustic signal is large, and the monotonicity will change more frequently within a cycle, resulting in a large number of peaks in a cycle and a faster data change rate within a monotonic interval; in the frequency domain, the high-frequency components increase, the amplitude of the high-frequency signal is higher, and the normal low-frequency components still exist, so that the amplitude from low frequency to high frequency shows an overall trend of first decreasing and then increasing.

[0047] For the sound wave signal sequence of each cabin, the sound wave signal sequence is segmented according to time periods of preset length to obtain several segmented sound wave sequences, wherein the preset length needs to include at least one cycle. In this embodiment, the preset length of the time period is 50ms.

[0048] For each segmented sound wave sequence, a polynomial fitting is performed to obtain the corresponding fitting curve equation; for the corresponding fitting curve equation, a derivative is taken, and all data points with a derivative of 0 are formed into an extreme value sequence in the order of indexes, and the elements in the extreme value sequence are the amplitudes of the sound wave signals at each extreme value point. In the above manner, each sound wave signal sequence is segmented, and the extreme value sequence of each segmented sound wave sequence is obtained. Polynomial fitting is a well-known technology and will not be described in detail in this application.

[0049] When a partial discharge fault occurs in a box-type substation, the data changes rapidly in a monotonic interval. Therefore, the slope of the line connecting two adjacent extreme points is calculated based on the extreme value sequence. The greater the change in this slope, the more likely a partial discharge fault will occur. The slopes of two adjacent extreme points in the extreme value sequence are calculated, and the mean of all slopes corresponding to the extreme value sequence is taken as the average slope of this segmented acoustic wave sequence. The mean of the average slopes of all segmented acoustic wave sequences is recorded as the data change rate.

[0050] Take a sound wave signal sequence as input, use Fourier transform to obtain a spectrum, calculate the mean of all peaks, mark the peaks with amplitude greater than the mean as characteristic peaks; use the peak value of the characteristic peak as the ordinate and the frequency corresponding to the characteristic peak as the abscissa to perform least squares fitting and output a quadratic fitting curve; evenly take H points on the quadratic fitting curve and take derivatives at these H points respectively. Fourier transform and least squares fitting are well-known technologies and will not be described in detail. In this embodiment, H is 100.

[0051] The number of negative derivatives and the number of positive derivatives of the H points taken in the quadratic fitting curve are counted. If the quadratic fitting curve is monotonically decreasing, the derivatives are all negative. If the quadratic fitting curve is monotonically increasing, the derivatives are all positive. The ratio of the number of negative derivatives to the number of positive derivatives is taken as the monotonicity of the acoustic wave signal sequence in the frequency domain.

[0052] The frequency domain fault characteristics are obtained based on the monotonicity, data change rate, number of peaks and average amplitude of the acoustic wave signal sequence of each compartment in the frequency domain.

[0053] The frequency domain fault characteristics are positively correlated with the data change rate, peak number and average amplitude of the acoustic signal sequence, and negatively correlated with the monotonicity of the acoustic signal sequence in the frequency domain.

[0054] Preferably, in this embodiment, the expression of the frequency domain fault characteristic is: ; represents the peak number of the acoustic wave signal sequence in the ith cabin, represents the average amplitude of the acoustic wave signal sequence in the ith cabin, represents the rate of change of the acoustic wave signal sequence data of the ith cabin, represents the monotonicity of the acoustic wave signal sequence of the ith cabin in the frequency domain, Represents the fault characteristics in the frequency domain.

[0055] It can be understood that when there is no partial discharge fault in the box-type substation, the number of peaks of the acoustic wave signal is small, the peak value is small, and the change speed in the monotonic interval is slow, that is, , , are all small; secondly, the quadratic fitting curve of the characteristic peak in the frequency domain is a monotonically decreasing trend, so the derivatives are all negative, that is, Large; so when there is no partial discharge fault in the box-type substation, the time-frequency domain characteristic coefficient On the contrary, when a partial discharge fault occurs in a box-type substation, the quadratic fitting curve of the characteristic peak in the frequency domain shows a trend of decreasing first and then increasing. The number of positive derivatives increases, and the number of negative derivatives decreases, that is, is smaller, and the other features are opposite, making the frequency domain fault feature larger.

[0056] So far, the frequency domain fault characteristics are obtained based on the acoustic wave signal sequence of each compartment from the frequency domain perspective.

[0057] Step S004, constructing a fault code according to the time domain fault characteristics and the frequency domain fault characteristics to determine a partial discharge fault.

[0058] According to the data collection method in step 1, calculate the time domain fault characteristics and frequency domain fault characteristics of each box-type substation monitoring; the two form a vector as the feature vector of a monitoring. As input, the K-means clustering algorithm is used to output each cluster. In this embodiment, the number of clusters The value is 4. K-means clustering is a well-known technology and will not be described in detail.

[0059] Then, the mean of the time domain fault characteristics and frequency domain fault characteristics in each cluster is calculated respectively, and the cluster with the largest sum of the two means is marked as the suspected fault cluster, and the cluster with the smallest sum of the two means is marked as the fault-free cluster. The fault code is determined according to the fluctuation of the suspected fault cluster and the fault-free cluster, so as to judge whether there is a partial discharge fault in the box-type substation.

[0060] The specific expression is: ; Is the fault code ( 0 means there is no partial discharge fault. 1 means it exists), It is the sum of the coefficients of variation of the time domain fault features and frequency domain fault features in the fault-free cluster. All elements in the fault-free cluster and the suspected fault cluster constitute a set. is the sum of the coefficients of variation of the time domain fault features and frequency domain fault features in the set, is a variation threshold, which is used to measure the difference between the elements in the suspected fault cluster and the elements in the fault-free cluster. It can be selected as needed. In this embodiment, Take experience value 1, need to pay attention The larger the value is, the stricter the requirement for the difference between the elements in the two clusters is, which can improve the sensitivity of partial discharge fault diagnosis, but at the same time it will also increase the probability of misjudgment.

[0061] In this way, fault judgment is made according to the changing characteristics of each monitoring data in the time and frequency domain during the operation of the box-type substation, avoiding the situation in which the existing detection technology only judges based on the size of the numerical value, which may cause a large risk of misjudgment. It can relatively more accurately grasp whether there are local discharge characteristics, improve the accuracy of local discharge fault diagnosis, help ensure the safe operation of the box-type substation, and reduce the adverse effects of misjudgment and ineffective maintenance.

[0062] Based on the same inventive concept as the above method, an embodiment of the present invention also provides a box-type substation, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the methods described in the above-mentioned Internet of Things method for a box-type substation are implemented.

[0063] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

[0064] 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. A method for interconnecting things for a box-type substation, characterized in that: The method comprises the following steps: The Internet of Things technology is used to collect a local signal sequence, an external temperature sequence, and temperature sequences and acoustic wave signal sequences of different cabins at a time; Process the local signal sequence based on a window of preset size to obtain a moving average sequence; determine the periodicity based on the distance between the peaks of the moving average sequence; mark the peak of the local signal sequence to obtain the abnormal peak and its neighborhood range; and obtain the data fluctuation based on the coefficient of variation of the data in the neighborhood range, and obtain the internal characteristics of the signal according to the fluctuation of the data in the local signal sequence, the overall amplitude and the periodicity; obtain the external environment characteristics according to the difference in the temperature fluctuation of the cabin and the correlation between the temperature series inside and outside the cabin; forwardly fuse the internal characteristics of the signal and the external environment characteristics to obtain the time domain fault characteristics; The acoustic wave signal sequence of the cabin is segmented, and the data change rate is obtained based on the slope of the extreme value connection line after curve fitting; the acoustic wave signal sequence is converted into a spectrum diagram, and curve fitting is performed according to the peak value and the corresponding frequency in the spectrum diagram, and the monotonicity of the acoustic wave signal sequence in the frequency domain is obtained based on the positive and negative differences of the preset number of derivatives; the frequency domain fault characteristics are calculated based on the monotonicity of the acoustic wave signal sequence in the frequency domain, the data change rate, the number of peaks, and the average amplitude of each cabin; The time domain fault features and frequency domain fault features are clustered into vectors, and the fault code is obtained according to the difference in the fluctuation of the time domain fault features and frequency domain fault features in the cluster cluster to determine the partial discharge fault.

2. The method for connecting Internet of Things for a box-type substation according to claim 1, characterized in that: The method for determining periodicity based on the distance between the peaks of the moving average sequence is: The peak indexes of the moving average sequence are sorted according to their sizes to obtain a position sequence, a first-order difference sequence of the position sequence is calculated, and the periodicity is represented by the variance of the first-order difference sequence.

3. The method for connecting Internet of Things for a box-type substation according to claim 1, characterized in that: The method for obtaining the abnormal peak value and its neighborhood range by marking the peak value of the local signal sequence is: All peaks in the local signal sequence and the upper quartile of the peaks are obtained, and peaks greater than the upper quartile are marked as abnormal peaks; a domain range of a preset size is obtained with each abnormal peak as the center.

4. The method for connecting Internet of Things for a box-type substation according to claim 1, characterized in that: The method for obtaining the internal characteristics of the signal according to the fluctuation of the data in the local signal sequence, the overall amplitude and the periodicity is: The internal eigenvalue of the signal is positively correlated with the fluctuation of the data in the local signal sequence and the overall amplitude, and is negatively correlated with the periodicity in the local signal sequence.

5. The method for interconnecting things for a box-type substation according to claim 1, characterized in that: The method for obtaining the external environment characteristics according to the difference between the temperature fluctuation of the cabin and the correlation of the temperature series inside and outside the cabin is: Calculate the variance of the temperature series inside different cabins, and use the variance as the temperature fluctuation measure of the temperature series corresponding to each cabin; calculate the correlation measure between the temperature series of each cabin and the external temperature series; The external environmental characteristics are negatively correlated with the correlation metric of each cabin and positively correlated with the temperature fluctuation metric.

6. The method for connecting Internet of Things for a box-type substation according to claim 1, characterized in that: The method for obtaining the data change rate is: Perform polynomial fitting on each segmented sound wave sequence to obtain the corresponding fitting curve equation; sort all the corresponding extreme values ​​in index order to form an extreme value sequence; The slopes of two adjacent extreme points in the extreme value sequence are calculated, the mean of all slopes corresponding to the extreme value sequence is taken as the average slope of this segmented sound wave sequence, and the mean of the average slopes of all segmented sound wave sequences is recorded as the data change rate.

7. The method for interconnecting things for a box-type substation according to claim 1, characterized in that: The method of performing curve fitting according to the peak value and the corresponding frequency in the spectrum graph and obtaining the monotonicity of the sound wave signal sequence in the frequency domain based on the positive and negative differences of the preset number of derivatives is: Calculate the mean of all peaks in the spectrum graph, and mark the peaks with amplitudes greater than the mean as characteristic peaks; With the peak value of the characteristic peak as the ordinate and the frequency corresponding to the characteristic peak as the abscissa, perform least square fitting and output a quadratic fitting curve; A number of derivative points are preset in the quadratic fitting curve, the reciprocal of each derivative point is calculated, the positive and negative derivatives are counted, and the ratio of the number of negative derivatives to the number of positive derivatives is taken as the monotonicity of the acoustic signal sequence in the frequency domain.

8. The method for connecting Internet of Things for a box-type substation according to claim 1, characterized in that: The method for calculating the frequency domain fault characteristics based on the monotonicity, data change rate, number of peaks and average amplitude of the acoustic wave signal sequence of each compartment in the frequency domain is: The frequency domain fault characteristics are positively correlated with the data change rate, peak number and average amplitude of the acoustic signal sequence, and negatively correlated with the monotonicity of the acoustic signal sequence in the frequency domain.

9. The method for connecting Internet of Things for a box-type substation according to claim 1, characterized in that: The method for obtaining the fault code according to the difference in fluctuation of the time domain fault characteristics and the frequency domain fault characteristics in the cluster is: Calculate the mean of the time domain fault features and frequency domain fault features in each cluster; mark the cluster with the largest sum of the two means as the suspected fault cluster, and mark the cluster with the smallest sum of the two means as the fault-free cluster; the expression of the fault code is: ; It is a fault code. is the sum of the coefficients of variation of the time domain fault features and frequency domain fault features in the fault-free cluster. It is the sum of the coefficients of variation of the time domain fault features and frequency domain fault features in the set of all elements in the fault-free clusters and suspected fault clusters. is the preset mutation threshold.

10. A box-type substation, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the Internet of Things method for a box-type substation are implemented as described in any one of claims 1-9.

Images