Intelligent diagnosis method for high-voltage cable

Abstract

The invention discloses an intelligent diagnosis method for a high-voltage cable, and belongs to the technical field of cable diagnosis, and the method specifically comprises the steps: dividing a high-voltage cable line into a plurality of monitoring sections with different lengths, installing various types of collection sensors in the monitoring sections to collect cable data, and setting an Internet of Things gateway for each monitoring section, the Internet of Things gateway adjusts the sampling frequency of the acquisition sensor, preprocesses the data transmitted by the acquisition sensor to obtain integrated data, and compresses and sends the integrated data to the cloud monitoring platform, and the cloud monitoring platform judges whether the integrated data is abnormal or not according to an abnormal threshold value; after the abnormity is found, a monitoring section where the abnormity occurs is determined, the sensor sampling frequency of the monitoring section is improved, whether the abnormity is true or not is determined, the abnormity type is judged by integrating various kinds of abnormal data, the alarm level is determined according to the abnormity type, and a diagnosis result is visually output at a monitoring terminal. According to the invention, the long-distance real-time monitoring of the state of the high-voltage cable is realized, and the abnormal condition judgment accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cable diagnosis, and particularly to an intelligent diagnosis method for high-voltage cables. Background Art

[0002] A high-voltage cable is a type of power cable, which refers to a power cable used for transmitting electricity between 1 kV and 1000 kV. High-voltage cables are an important part of the power transmission and distribution system, capable of achieving long-distance and large-capacity power transmission, and playing an important role in today's life and production. During the operation of high-voltage cables, partial discharge phenomena are an important cause of insulation breakdown of cable equipment and an important indication of insulation deterioration of high-voltage cables. Therefore, it is necessary to detect the partial discharge phenomena of high-voltage cables in a timely manner.

[0003] Currently, most of the partial discharge detection methods for high-voltage cables are still planned maintenance. Various specialized portable partial discharge detection devices are used to collect and process high-frequency signals such as pulse current or electromagnetic waves to judge the occurrence of partial discharge.

[0004] However, this method of planned maintenance has low detection efficiency and is difficult to detect potential faults of high-voltage cables in a timely manner. At the same time, it is difficult to ensure the accuracy of the detection results relying only on one type of detection data. Therefore, the present invention proposes an intelligent diagnosis method for high-voltage cables, which realizes long-distance real-time monitoring of high-voltage cables through sensors and the Internet of Things, can comprehensively judge the types of cable abnormalities based on various detection data, and visually output the diagnosis results. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent diagnosis method for high-voltage cables to solve the following technical problems:

[0006] The traditional method for detecting the operating state of high-voltage cables is still planned maintenance. This method has low detection efficiency and cannot detect potential faults of high-voltage cables in a timely manner. At the same time, a single detection device is often used to detect the partial discharge phenomena of high-voltage cables during planned maintenance, and the types of collected detection data are single, making it difficult to ensure the accuracy of the detection results.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An intelligent diagnosis method for high-voltage cables includes the following steps:

[0009] The entire high-voltage cable transmission line is initially divided into M equal-length initial sections. The length of the initial section is marked as L, where L is a positive number. Measure the environmental temperature value and environmental noise value of the initial section, calculate the environmental factor u of the initial section, and the value range of u is (0, 1). Then, perform a secondary division of a single initial section according to the environmental factor to obtain a monitoring section. After the secondary division of all the initial sections is completed, all the obtained monitoring sections are respectively marked as N1, N2,..., N i , where M and i are positive integers;

[0010] Install acquisition sensors for the cable joint part of the high-voltage cable in each monitoring section. The acquisition sensors include a high-frequency pulse current sensor, an ultra-high-frequency electromagnetic wave sensor, a cable temperature sensor, a load current sensor, and a vibration sensor;

[0011] Set an Internet of Things gateway for each monitoring section. All the acquisition sensors within the monitoring section can transmit data to the Internet of Things gateway corresponding to the monitoring section, and adjust the sampling frequency of the acquisition sensors through the Internet of Things gateway;

[0012] The acquisition sensors send the acquired data to the Internet of Things gateway. After receiving the data, the Internet of Things gateway preprocesses the data through edge computing to obtain integrated data. The integrated data includes: pulse current data, electromagnetic wave data, cable temperature data, load current data, and vibration data, and compresses the integrated data;

[0013] Connect all the Internet of Things gateways to the same cloud monitoring platform. The Internet of Things gateway sends the compressed integrated data to the cloud monitoring platform. The cloud monitoring platform performs decompression operations on the integrated data, sets abnormal thresholds for various types of integrated data, and determines whether the integrated data is abnormal. When any type of integrated data exceeds the abnormal threshold, mark the integrated data as abnormal data. After the cloud monitoring platform discovers abnormal data, locate the monitoring section N i where the abnormal data comes from, and increase the sampling frequency of the acquisition sensors in N i . Continuously detect whether abnormal data appears again in various types of integrated data in N i . Determine the operating state of the high-voltage cable within N i based on the analysis results of various types of integrated data, and display the diagnosis result on the terminal device.

[0014] As a further solution of the present invention: The specific steps for the secondary division of the initial section are as follows:

[0015] The lengths of the initial section and the monitoring section refer to the length of the high-voltage cable body within the corresponding section. Measure the environmental temperature value P and environmental noise value H of each initial section. When the high-voltage cable and the acquisition sensors are operating, set the ranges of the environmental temperature value and environmental noise value within which they can operate normally as (Pmin , P max ), and (H min , H max ), and normalize P and H. The calculation formula is:

[0016] P j = (P - P min + 1) / (P max - P min + 1)

[0017] H j = (H - H min + 1) / (H max - H min + 1)

[0018] Where P j and H j represent the normalized values of the environmental temperature value P and the environmental noise value H corresponding to the initial section, j = 1, 2,..., M;

[0019] Use P j and H j and the sigmoid function to calculate the environmental factor u, and constrain the value of u to the range of (0, 1). The calculation formula is:

[0020] u = sigmoid(a·P j + b·H j + ε)

[0021] sigmoid(x) = 1 / (1 + e(-x))

[0022] Where a and b are the weight coefficients of the environmental temperature value and the environmental noise value respectively, a + b < 1, ε is the error term, and its value range is [-0.1, 0.1]. sigmoid(x) represents the sigmoid function, and e is the base of the natural logarithm;

[0023] When 0 < u ≤ 0.5, divide the corresponding initial section into m monitoring sections of the same length for the second time. The calculation formula of m is:

[0024] m = [1 / u]

[0025] Where [1 / u] represents rounding down the value of 1 / u;

[0026] When 0.5 < u ≤ 0.8, divide the corresponding initial section into two monitoring sections, and the lengths are marked as L u1 and L u2 , and the calculation formula is:

[0027] L u1 = L·u

[0028] L u2 = L·(1 - u)

[0029] When 0.8 < u < 1, the value of u is uniformly taken as 1, and the corresponding initial section is directly set as the monitoring section. If the u values of two adjacent initial sections are both 1, they are merged into one monitoring section.

[0030] As a further solution of the present invention: The IoT gateway adjusts the sampling frequency of the acquisition sensors in the corresponding section according to the environmental factor u. Mark the sampling frequency of the acquisition sensors as f, and the calculation formula is:

[0031] f1 = f0·(1 + K / u)

[0032] f = min(f1, f max )

[0033] where f0 is the default initial sampling frequency of the acquisition sensor, K is a positive constant, f1 is the reference sampling frequency obtained by adjusting f0 according to the environmental factor u, and f max is the maximum sampling frequency that the sampling sensor can support. min means taking the minimum value between f1 and f max ;

[0034] The IoT gateway detects the operating status of the acquisition sensors. When it detects that an acquisition sensor fails in the corresponding monitoring section, the IoT gateway reports the fault information to the cloud monitoring platform and increases the sampling frequency of the remaining normally operating acquisition sensors in the monitoring section.

[0035] As a further solution of the present invention: The specific process of installing the acquisition sensors is as follows:

[0036] The cable joints of the high-voltage cable include terminal joints and intermediate joints. When installing the high-frequency pulse current sensor, connect the sensor to the grounding wire of the high-voltage cable;

[0037] The ultra-high frequency electromagnetic wave sensor adopts a non-contact working method and does not directly contact or access the cable. The ultra-high frequency electromagnetic wave sensor is installed at the terminal joints and intermediate joints of the high-voltage cable;

[0038] The vibration sensor selects a piezoelectric acceleration sensor. When installing, the sensing surface of the sensor is in full contact with the surface of the high-voltage cable.

[0039] As a further solution of the present invention: The installed acquisition sensor has a built-in DSP data acquisition function, supports the IuC60870-5-104 or IuC61850 Internet of Things communication protocol. The communication methods between the Internet of Things gateway and the acquisition sensor include wired communication and wireless communication. At the same time, an automatic gain controller is built into the high-frequency pulse current sensor and the ultra-high frequency electromagnetic wave sensor, and the acquired data is subjected to gain processing before being sent to the Internet of Things gateway.

[0040] As a further solution of the present invention: The preprocessing includes data standardization, data alignment, and data denoising;

[0041] The method of data standardization is: converting the storage formats of the data acquired by various acquisition sensors into a unified XML or JSON format;

[0042] The method of data alignment is: within any monitoring section, aligning the data acquired by all acquisition sensors according to a common time point;

[0043] The method of data denoising is: The Internet of Things gateway uses the Kalman filtering method to denoise the received data.

[0044] As a further solution of the present invention: The specific process of compressing and decompressing the integrated data utilizes the compressed sensing theory. The steps of compression and decompression are as follows:

[0045] S1: In the Internet of Things gateway, using the Fourier transform or wavelet transform as a sparse basis, obtaining a sparse signal by solving the L1 norm minimization problem for the signals in the acquired data;

[0046] S2: In the Internet of Things gateway, using the Hadamard matrix or Gaussian matrix as a random matrix to measure the sparse signal, obtaining a measurement value, and completing the compression process;

[0047] S3: In the cloud monitoring platform, according to the measurement value, using the orthogonal matching pursuit algorithm for signal reconstruction to complete the decompression process.

[0048] As a further solution of the present invention: The diagnosis results include: abnormal types and alarm levels. The abnormal types include cable temperature abnormality, load current abnormality, cable vibration abnormality, pulse current abnormality, and partial discharge abnormality. The alarm levels are divided into first-level alarm, second-level alarm, and third-level alarm;

[0049] Among the abnormal types, the cable temperature abnormality, load abnormality, and cable vibration abnormality are judged separately according to the corresponding integrated data, and the pulse current abnormality and partial discharge abnormality are judged comprehensively according to the integrated data of all types;

[0050] The basis for judging the alarm level is as follows: when only one of the abnormal types of cable temperature abnormality, load current abnormality, and cable vibration abnormality occurs, it is judged as a first-level alarm; when two or more of the abnormal types occur simultaneously, it is judged as a second-level alarm; and when only pulse current abnormality or partial discharge abnormality occurs, it is also judged as a second-level alarm. When partial discharge abnormality and other abnormal types occur, it is judged as a third-level alarm;

[0051] The diagnostic results output by the cloud monitoring platform to the monitoring terminal display all detected abnormal types, give the judged alarm level, and at the same time mark the monitoring section where the abnormality is found.

[0052] As a further solution of the present invention: the specific process of judging the abnormal type of high-voltage cable is as follows:

[0053] When the cloud monitoring platform discovers abnormal data, locate the monitoring section N where the abnormal data source is located i , set the continuous monitoring time period T, and the Internet of Things gateway will increase the sampling frequency of the sensors in N i by G times during the detection time period T, G>1, and continuously detect various integrated data in N i . If the abnormal data appears continuously or periodically within T, it is determined that the abnormal data is true;

[0054] When the cloud monitoring platform determines that the abnormal data in any of the cable temperature data, load current data, or vibration data is true, it is judged that the high-voltage cable has the corresponding abnormal type;

[0055] When the cloud monitoring platform determines that the abnormal data of the pulse current data is true and the electromagnetic wave data is normal, only when it is determined that other abnormal types have occurred at the same time, it is judged that the high-voltage cable has a partial discharge abnormality, otherwise it is judged as a pulse current abnormality;

[0056] When the cloud monitoring platform determines that the abnormal data of the pulse current data and the electromagnetic wave data are both true, or only the abnormal data of the electromagnetic wave data is true, it is directly judged that the high-voltage cable has a partial discharge abnormality;

[0057] The cloud monitoring platform records the historical diagnostic results, counts the frequency of abnormal types in each monitoring section, and displays the statistical results on the monitoring terminal.

[0058] The beneficial effects of the present invention:

[0059] The present invention provides an intelligent diagnosis method for high-voltage cables, which realizes long-distance real-time monitoring of high-voltage cables through the joint operation of acquisition sensors, Internet of Things gateways, and cloud monitoring platforms, and solves the deficiency that traditional planned maintenance cannot detect cable fault hidden dangers in a timely manner. The present invention divides a high-voltage cable transmission line into different monitoring sections according to environmental factors, and sets different sensor sampling frequencies for each monitoring section, maximizing the reliability of the monitored data. In the present invention, the cloud monitoring platform comprehensively judges the partial discharge phenomenon of the high-voltage cable based on various data, and can also diagnose other types of abnormal conditions of the high-voltage cable, and intelligently diagnose the alarm level of the abnormal conditions of the high-voltage cable, improving the accuracy of judging the partial discharge phenomenon and providing a visual diagnosis result for relevant personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The present invention will be further described below with reference to the accompanying drawings.

[0061] Figure 1 is a schematic flow chart of the present invention;

[0062] Figure 2 is a schematic flow chart of dividing the monitoring section of the present invention;

[0063] Figure 3 is a schematic flow chart of the cloud monitoring platform of the present invention outputting the diagnosis result of the high-voltage cable. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0065] Please refer to Figures 1-3 As shown, the present invention is an intelligent diagnosis method for high-voltage cables, including the following steps:

[0066] Step 1: Initially divide the entire high-voltage cable transmission line into M initial sections of equal length, mark the length of the initial section as L, where L is a positive number, measure the environmental temperature value and environmental noise value of the initial section, and calculate the environmental factor u of the initial section. The value range of u is (0, 1), and the specific calculation method is:

[0067] Measure the environmental temperature value P and environmental noise value H of each initial section. When the high-voltage cable and the acquisition sensor are operating, the normal working environmental temperature value and environmental noise value ranges are respectively set as (P min , P max ) and (H min,H max ), and normalize P and H, and the calculation formula is:

[0068] P j =(P - P min + 1) / (P max - P min + 1)

[0069] H j =(H - H min + 1) / (H max - H min + 1)

[0070] Where P j and H j represent the normalized values of the environmental temperature value P and the environmental noise value H corresponding to the initial section. j = 1, 2,..., M. The purpose of normalization is to convert data with different dimensions and dimension units to the same range, thereby eliminating the dimension influence between different features.

[0071] Use P j and H j and the sigmoid function to calculate the environmental factor u, and constrain the value of u to the range of (0, 1). The calculation formula is:

[0072] u = sigmoid(a·P j + b·H j + ε)

[0073] sigmoid(x) = 1 / (1 + e(-x))

[0074] Where a and b are the weight coefficients of the environmental temperature value and the environmental noise value respectively, a + b < 1, ε is the error term, and its value range is [-0.1, 0.1]. sigmoid(x) represents the sigmoid function, and e is the base of the natural logarithm.

[0075] Step 2: After obtaining the environmental factors e corresponding to each initial section, perform a secondary division on a single initial section according to the range of e. The specific division steps are as follows:

[0076] When 0 < u ≤ 0.5, divide the corresponding initial section into m monitoring sections with the same length. The calculation formula for m is:

[0077] m = [1 / u]

[0078] Where [1 / u] represents rounding down the value of 1 / u;

[0079] When 0.5 < u ≤ 0.8, divide the corresponding initial section into two monitoring sections, and the lengths are marked as L u1 and Lu2 , the calculation formula is:

[0080] L u1 = L·u

[0081] L u2 = L·(1 - u)

[0082] When 0.8 < u < 1, it indicates that the ambient temperature and ambient noise of the high - voltage cable environment are within the normal range. Therefore, the value of u is uniformly taken as 1, and the corresponding initial section is directly set as the monitoring section. If the u values of two adjacent initial sections are both 1, it means that the environments of these two sections are relatively stable, so they can be merged as one monitoring section.

[0083] After all the initial sections are completed with the secondary division, all the obtained monitoring sections are respectively marked as N1, N2,..., N i , where M and i are positive integers. The lengths of the initial section and the monitoring section refer to the length of the high - voltage cable body within the corresponding section, rather than the straight - line distance between the section starting points.

[0084] Step 3: Install acquisition sensors for the cable joint parts of the high - voltage cable in each monitoring section. The acquisition sensors include high - frequency pulse current sensors, ultra - high - frequency electromagnetic wave sensors, cable temperature sensors, load current sensors, and vibration sensors.

[0085] When installing the sensors, connect the high - frequency pulse current sensor to the ground wire of the high - voltage cable. The ultra - high - frequency electromagnetic wave sensor adopts a non - contact working method and does not directly contact or connect to the cable. The vibration sensor selects a piezoelectric acceleration sensor, and ensure that the sensing surface of the sensor is in full contact with the surface of the high - voltage cable during installation. When installing the cable temperature sensor, use a heat - conducting pad or heat - conducting paste to completely fill the gap between the sensor and the cable outer sheath.

[0086] Step 4: Set an Internet of Things gateway for each monitoring section. All the acquisition sensors within the monitoring section have built - in DSP data acquisition functions and support IuC60870 - 5 - 104 or IuC61850 Internet of Things communication protocols. The communication methods between the Internet of Things gateway and the acquisition sensors include wired communication and wireless communication. At the same time, an automatic gain controller is built into the high - frequency pulse current sensor and the ultra - high - frequency electromagnetic wave sensor. The acquired data is subjected to gain processing and then sent to the Internet of Things gateway. Through the Internet of Things gateway, the sampling frequency of the acquisition sensors can be adjusted. The specific adjustment process is as follows:

[0087] The Internet of Things gateway will adjust the sampling frequency of the acquisition sensors within the corresponding section according to the environmental factor u. Mark the sampling frequency of the acquisition sensors as f, and the calculation formula is:

[0088] f1 = f0·(1 + K / u)

[0089] f = min(f1, f max )

[0090] where f0 is the default initial sampling frequency of the acquisition sensor, K is a positive constant, f1 is the reference sampling frequency obtained by adjusting f0 according to the environmental factor u, and f max is the maximum sampling frequency that the sampling sensor can support. min represents taking the minimum value between f1 and f max .

[0091] Meanwhile, the IoT gateway will detect the operating status of the acquisition sensor. When it detects that an acquisition sensor fails in the corresponding monitoring section, the IoT gateway will report the fault information to the cloud monitoring platform and increase the sampling frequency of the remaining normally operating acquisition sensors in the monitoring section. This can temporarily compensate for the amount of monitoring data in this monitoring section and ensure the richness of the data.

[0092] Step Five: The acquisition sensor sends the collected data to the IoT gateway. After receiving the data, the IoT gateway preprocesses the data through edge computing. The preprocessing operations include data standardization, data alignment, and data denoising. The specific preprocessing process is as follows: Data standardization converts the storage formats of the data collected by various acquisition sensors into a unified XML or JSON format. Data alignment aligns the data collected by all acquisition sensors in any monitoring section according to a common time point. Data denoising uses the Kalman filtering method to denoise the received data.

[0093] Step Six: After preprocessing, integrated data is obtained. The integrated data includes: pulsed current data, electromagnetic wave data, cable temperature data, load current data, and vibration data. And the integrated data is compressed, and the compressive sensing theory is utilized for the compression. The specific compression process is as follows: First, the Fourier transform or wavelet transform is used as the sparse basis, and the signal in the collected data is obtained as a sparse signal by solving the L1 norm minimization problem. Then, the Hadamard matrix or Gaussian matrix is used as the random matrix to measure the sparse signal to obtain the measurement value, completing the compression process.

[0094] Step Seven: All IoT gateways are connected to the same cloud monitoring platform. The IoT gateway sends the compressed integrated data to the cloud monitoring platform, and the cloud monitoring platform uses the orthogonal matching pursuit algorithm for signal reconstruction to complete the decompression process of the integrated data.

[0095] Set an anomaly threshold for various types of integrated data to determine whether the integrated data is abnormal. When any type of integrated data exceeds the anomaly threshold, mark this integrated data as abnormal data. When the cloud monitoring platform discovers abnormal data, locate the monitoring section N where the abnormal data source is locatedi Set a continuous monitoring time period T. During the detection time period T, the IoT gateway increases the sampling frequency of the sensors collected within N by G times simultaneously, where G > 1, and continuously detects various integrated data in N. i If abnormal data appears continuously or periodically within T, then determine that the abnormal data is true. The purpose of increasing the sampling frequency is to prevent abnormal data from being staggered from the existing sampling frequency and resulting in sampling failure if it appears periodically. i Step Eight: When the cloud monitoring platform determines that the abnormal data in any of the cable temperature data, load current data, or vibration data is true, determine the corresponding abnormal type that has occurred in the high-voltage cable.

[0096] When the cloud monitoring platform determines that the abnormal data of the pulse current data is true and the electromagnetic wave data is normal, only when it is simultaneously determined that other abnormal types have occurred, it is judged that the high-voltage cable has a partial discharge abnormality. Otherwise, it is judged as a pulse current abnormality because the reason for the abnormal pulse current data may not necessarily be partial discharge, and abnormal current inside the cable may also cause data abnormalities.

[0097] When the cloud monitoring platform determines that the abnormal data of the pulse current data and the electromagnetic wave data are both true, or only the abnormal data of the electromagnetic wave data is true, directly judge that the high-voltage cable has a partial discharge abnormality because the pulse current data and the electromagnetic wave data have a high weight in judging the partial discharge phenomenon, and the detection accuracy of the ultra-high frequency electromagnetic wave sensor is higher than that of the high-frequency pulse current sensor. When its data is determined to be abnormal, it can directly judge that a partial discharge phenomenon has occurred.

[0098] Step Nine: The cloud monitoring platform displays the diagnostic results on the terminal device. The diagnostic results include: abnormal type and alarm level. The abnormal types include cable temperature abnormality, load current abnormality, cable vibration abnormality, pulse current abnormality, and partial discharge abnormality. The alarm level is divided into first-level alarm, second-level alarm, and third-level alarm.

[0099] Among the abnormal types, the cable temperature abnormality, load abnormality, and cable vibration abnormality are judged separately according to the corresponding integrated data, while the pulse current abnormality and partial discharge abnormality are judged comprehensively according to the integrated data of all types.

[0100] The basis for judging the alarm level is that when only one of the abnormal types of cable temperature abnormality, load current abnormality, and cable vibration abnormality appears, it is judged as a first-level alarm. When two or more of them appear simultaneously, it is judged as a second-level alarm. And when only the pulse current abnormality or partial discharge abnormality appears, it is also judged as a second-level alarm. When the partial discharge abnormality and other abnormal types appear, it is judged as a third-level alarm.

[0101]

[0102] ​Step Ten: In the diagnostic results output by the cloud monitoring platform to the monitoring terminal, all detected abnormal types are displayed, and the judged alarm level is given. At the same time, the monitoring section where the abnormality is found will be marked. The cloud monitoring platform will also record the historical diagnostic results, count the frequency of abnormal types in each monitoring section, and display the statistical results on the monitoring terminal. Relevant personnel can strengthen the maintenance of the cables in the monitoring sections prone to abnormal conditions according to the statistical results.

[0103] The above formulas are all calculated by taking the numerical values after dimensionless. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters and threshold selection in the formula are set by those skilled in the art according to the actual situation.

[0104] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claimed rights.

[0105] The above has described a specific embodiment of the present invention in detail, but the content described is only the preferred embodiment of the present invention and cannot be considered as limiting the implementation scope of the present invention. All equivalent changes and improvements made within the scope of the application of the present invention shall still fall within the scope covered by the patent of the present invention.

Claims

1. An intelligent diagnosis method for high voltage cables, characterized in that: It includes the following steps: The entire high-voltage cable transmission line is initially divided into M initial sections of equal length. The length of the initial section is marked as L, where L is a positive number. The ambient temperature and ambient noise values ​​of the initial section are measured, and the environmental factor u of the initial section is calculated. The value range of u is (0,1). The single initial section is divided twice according to the environmental factor to obtain the monitoring section. After all the initial sections have completed the secondary division, all the monitoring sections are marked as N1, N2, ..., N i , where M,i is a positive integer; Install acquisition sensors for the cable joint parts of high-voltage cables in each monitoring section. The acquisition sensors include high-frequency pulse current sensors, ultra-high-frequency electromagnetic wave sensors, cable temperature sensors, load current sensors, and vibration sensors; Set up an Internet of Things gateway for each monitoring section. All acquisition sensors within the monitoring section can transmit data to the Internet of Things gateway corresponding to the monitoring section, and the sampling frequency of the acquisition sensors is adjusted through the Internet of Things gateway; The acquisition sensors send the acquired data to the Internet of Things gateway. After receiving the data, the Internet of Things gateway preprocesses the data through edge computing to obtain integrated data. The integrated data includes: pulse current data, electromagnetic wave data, cable temperature data, load current data, and vibration data, and compresses the integrated data; All IoT gateways are connected to the same cloud monitoring platform. The IoT gateway sends the compressed integrated data to the cloud monitoring platform. The cloud monitoring platform decompresses the integrated data, sets abnormal thresholds for each type of integrated data, and determines whether the integrated data is abnormal. When any type of integrated data exceeds the abnormal threshold, the integrated data is marked as abnormal data. After the cloud monitoring platform finds the abnormal data, it locates the monitoring segment N where the abnormal data comes from. i , and increase N i The sampling frequency of the acquisition sensor in the continuous detection of N i Whether there are abnormal data again in various types of integrated data, and determine N based on the analysis results of various types of integrated data i The operating status of the internal high-voltage cable can be monitored and the diagnostic results can be displayed on the terminal device.

2. The intelligent diagnosis method for high voltage cables according to claim 1, characterized in that: The specific steps for secondary partitioning of the initial section are: The length of the initial section and the monitoring section refers to the length of the high-voltage cable body in the corresponding section. The ambient temperature value P and the ambient noise value H of each initial section are measured. The ambient temperature value and the ambient noise value range that can work normally when the high-voltage cable and the acquisition sensor are running are set to (P min ,P max ) and (H min ,H max ), and normalize P and H, the calculation formula is: P j =(P-P min +1) / (P max -P min +1) H j =(H-H min +1) / (H max -H min +1) Where P j and H j represents the normalized value of the ambient temperature value P and the ambient noise value H of the corresponding initial section, j=1, 2, ..., M; Using P j and H j And the sigmoid function calculates the environmental factor u, constraining the value of u to the range of (0,1). The calculation formula is: u=sigmoid(a·P j +b·H j +ε) sigmoid(x) = 1 / (1 + e(-x)) where a and b are the weight coefficients of the environmental temperature value and the environmental noise value respectively, a + b < 1, ε is the error term, and its value range is [-0.1, 0.1]. sigmoid(x) represents the sigmoid function, and e is the base of the natural logarithm; When 0 < u ≤ 0.5, the corresponding initial section is secondarily partitioned into m monitoring sections with the same length. The calculation formula for m is: m = [1 / u] where [1 / u] represents rounding down the value of 1 / u; When 0.5 < u ≤ 0.8, the corresponding initial section is further divided into two monitoring sections, with lengths marked as L u1 and L u2 , and the calculation formula is: L u1 =L·u L u2 =L·(1-u) When 0.8 < u < 1, the value of u is uniformly taken as 1, and the corresponding initial section is directly set as the monitoring section. If the u values of two adjacent initial sections are both 1, they are merged into one monitoring section.

3. The intelligent diagnosis method for high voltage cables according to claim 2 is characterized in that: The Internet of Things gateway will adjust the sampling frequency of the acquisition sensors within the corresponding section according to the environmental factor u. Mark the sampling frequency of the acquisition sensors as f, and the calculation formula is: f1 = f0·(1 + K / u) f=min(f1,f max ) Where f0 is the default initial sampling frequency of the acquisition sensor, K is a positive constant, f1 is the reference sampling frequency obtained by adjusting f0 according to the environmental factor u, and f max is the maximum sampling frequency that the sampling sensor can support, and min means the frequency between f1 and f max Take the minimum value; The Internet of Things gateway will detect the operating status of the acquisition sensors. When it detects that an acquisition sensor fails within the corresponding monitoring section, the Internet of Things gateway will report the fault information to the cloud monitoring platform and increase the sampling frequency of the remaining normally operating acquisition sensors within the monitoring section.

4. The intelligent diagnosis method for high voltage cables according to claim 1, characterized in that: The specific process of installing the acquisition sensors is: The cable joints of the high-voltage cable include terminal joints and intermediate joints. When installing the high-frequency pulse current sensor, connect the sensor to the grounding wire of the high-voltage cable; The ultra-high-frequency electromagnetic wave sensor adopts a non-contact working method and does not directly contact or connect to the cable. The ultra-high-frequency electromagnetic wave sensor is installed at the terminal joints and intermediate joints of the high-voltage cable; Select a piezoelectric acceleration sensor for the vibration sensor. When installing, the sensing surface of the sensor is in full contact with the surface of the high-voltage cable.

5. The intelligent diagnosis method for high voltage cables according to claim 3 is characterized in that: The installed acquisition sensors have built-in DSP data acquisition functions and support IuC60870-5-104 or IuC61850 Internet of Things communication protocols. The communication methods between the Internet of Things gateway and the acquisition sensors include wired communication and wireless communication. At the same time, the high-frequency pulse current sensor and the ultra-high-frequency electromagnetic wave sensor are built-in with automatic gain controllers, and the acquired data is subjected to gain processing before being sent to the Internet of Things gateway.

6. The intelligent diagnosis method for high voltage cables according to claim 1, characterized in that: The preprocessing includes data standardization, data alignment, and data denoising; The method of data standardization is: converting the storage format of data collected by various types of collection sensors into a unified XML or JSON format; The method of data alignment is: in any monitoring section, all data collected by the collection sensors are aligned according to a common time point; The method for data denoising is as follows: the Internet of Things gateway uses the Kalman filtering method to denoise the received data.

7. The intelligent diagnosis method for a high voltage cable according to claim 1, characterized in that: The specific process of compressing and decompressing the integrated data uses the compressed sensing theory. The steps of compression and decompression are: S1: In the IoT gateway, Fourier transform or wavelet transform is used as a sparse basis to obtain a sparse signal by solving the L1 norm minimization problem for the signal in the collected data; S2: In the IoT gateway, the sparse signal is measured using the Hadamard matrix or the Gaussian matrix as a random matrix to obtain the measured value and complete the compression process; S3: In the cloud monitoring platform, the orthogonal matching pursuit algorithm is used to reconstruct the signal based on the measured value to complete the decompression process.

8. The intelligent diagnosis method for high voltage cables according to claim 1, characterized in that: The diagnosis result includes: abnormality type and alarm level, the abnormality type includes abnormal cable temperature, abnormal load current, abnormal cable vibration, abnormal pulse current and abnormal partial discharge, and the alarm level is divided into level 1 alarm, level 2 alarm and level 3 alarm; Among the abnormal types, cable temperature abnormality, load abnormality and cable vibration abnormality are judged separately according to the corresponding integrated data, and pulse current abnormality and partial discharge abnormality are judged comprehensively according to the integrated data of all types; The basis for judging the alarm level is that when only one of the abnormal types of cable temperature abnormality, load current abnormality, and cable vibration abnormality occurs, it is judged as a first-level alarm; when two or more of the abnormal types occur at the same time, it is judged as a second-level alarm; and when only pulse current abnormality or partial discharge abnormality occurs, it is also judged as a second-level alarm; when partial discharge abnormality and other abnormal types occur, it is judged as a third-level alarm; The cloud monitoring platform displays all detected anomalies in the diagnostic results output to the monitoring terminal, gives the judged alarm level, and identifies the monitoring section where the anomaly is found.

9. The intelligent diagnosis method for high voltage cables according to claim 8, characterized in that: The specific process of judging the abnormal type of high-voltage cable is as follows: When the cloud monitoring platform finds abnormal data, it locates the monitoring segment N where the abnormal data comes from. i , set a continuous monitoring time period T, and the IoT gateway will detect N i The sampling frequency of the internal acquisition sensor is increased by G times, G>1, and N is continuously detected. i For all kinds of integrated data in , if the abnormal data appears continuously or periodically within T, the abnormal data is determined to be true; When the cloud monitoring platform determines that the abnormal data in any of the cable temperature data, load current data or vibration data is true, it is determined that the high-voltage cable has a corresponding abnormal type; When the cloud monitoring platform determines that the abnormal data of the pulse current data is true and the electromagnetic wave data is normal, it is judged that the high-voltage cable has a partial discharge abnormality only when it is determined that other abnormal types have occurred at the same time. Otherwise, it is judged as a pulse current abnormality; When the cloud monitoring platform determines that the abnormal data of the pulse current data and the electromagnetic wave data are both true, or only the abnormal data of the electromagnetic wave data is true, it is directly judged that the high-voltage cable has a partial discharge abnormality; The cloud monitoring platform records historical diagnostic results, counts the frequency of abnormal types in each monitoring section, and displays the statistical results on the monitoring terminal.

Images