A distribution network cable early fault identification and warning system and method based on transient disturbance

Abstract

The present invention discloses a distribution network cable early fault identification and early warning system and method based on transient disturbance, the system includes an information transmission module, a transient disturbance early signal detection module, a transient disturbance early signal identification module, a fault early warning module, a fault data preprocessing module, a fault data analysis module and a fault classification alarm module; the system can perform early fault identification and early warning for unknown measurement points, and can also perform fault type identification and alarm for known fault points. The present invention can timely discover early faults of cables and avoid power outage losses caused by cable faults.

Description

Technical Field

[0001] The invention belongs to the technical field of electric power, and relates to a distribution network cable early fault identification and early warning system and method based on transient disturbance. Background Art

[0002] The distribution network is located at the end of the power system and is directly connected to the users. The power supply capacity and quality of the entire power system to users are realized and guaranteed by it. Therefore, the distribution network is not only the development foundation of the entire power system, but also its final destination, and is an important link in realizing the smart grid. At the same time, with the gradual expansion of urban scale, the load density of the distribution network continues to increase, and the requirements for its power supply reliability and power supply quality are getting higher and higher. However, at present, the mutual supply capacity of the power grid during high load periods is insufficient, and large-scale power outages are very likely to occur. Its power supply reliability and ability to resist natural disasters need to be improved urgently.

[0003] With the acceleration of urbanization, the proportion of cables in urban power supply has become increasingly important. They have gradually replaced overhead power supply lines and are widely used in distribution networks. Underground cables are safer than overhead lines in bad weather, more economical for short-distance transmission, and are not easily affected by the environment and easy to maintain, so they have been widely used. Power cables are mainly used for power lead-in lines of substations, power plants and industrial and mining enterprises. Their scope of use has gradually become wider and they have received attention. With the development of urban construction, overhead transmission lines have been gradually replaced by power cables, and their proportion in urban power supply has become larger and larger. With the widespread use of power cables, there will inevitably be an increase in cable faults. Underground cables are more likely to cause permanent faults due to partial discharge, flashover, etc., and fault finding is more difficult. They are the equipment with the highest failure rate in distribution network equipment. In order to ensure the safe and stable operation of power cables, early cable faults should be discovered and dealt with in a timely manner. Summary of the invention

[0004] To solve the above problems, the present invention provides a distribution network cable early fault identification and early warning system and method based on transient disturbance, which can timely detect early cable faults and avoid power outage losses caused by cable faults.

[0005] The present invention is specifically a distribution network cable early fault identification and warning system based on transient disturbance, and the distribution network cable early fault identification and warning system based on transient disturbance includes an information transmission module, a transient disturbance early signal detection module, a transient disturbance early signal identification module, a fault warning module, a fault data preprocessing module, a fault data analysis module and a fault classification alarm module; the information transmission module transmits the information of the measurement point to the transient disturbance early signal detection module and the fault data preprocessing module, and the transient disturbance early signal detection module detects the transient disturbance signal of the cable; the transient disturbance early signal detection module is connected to the transient disturbance early signal identification module, and the transient disturbance early signal identification module identifies the detected transient disturbance signal and preliminarily determines whether a fault has occurred. the possibility of a fault; the transient disturbance early signal recognition module is connected to the fault warning module, and the fault warning module sends a warning signal when the transient disturbance early signal recognition module recognizes that the possibility of a fault is too high; the transient disturbance early signal recognition module is also connected to the fault data preprocessing module, and the fault data preprocessing module further judges and processes the identified suspected fault information; the fault data preprocessing module is connected to the fault data analysis module, and the fault data analysis module analyzes the fault information processed by the fault data preprocessing module and determines the fault type and level; the fault data analysis module is connected to the fault classification alarm module, and the fault classification alarm module alarms the fault type and level determined by the fault data analysis module.

[0006] Furthermore, the system can not only perform early fault identification and early warning for unknown measurement points, but also perform fault type identification and alarm for known fault points.

[0007] Furthermore, when the system identifies the fault type and alarms for a known fault point, the fault data preprocessing module receives and processes the known fault point information transmitted by the information transmission module, the fault data analysis module analyzes the fault information processed by the fault data preprocessing module and determines the fault type and level, and the fault classification alarm module alarms the fault type and level determined by the fault data analysis module.

[0008] Furthermore, the information transmission module can perform signal conversion and data transmission on the fault signal collected by the measuring point between the modules.

[0009] Furthermore, the transient disturbance early signal detection module can detect electrical characteristic quantities such as the grounding line current, zero-sequence voltage, and zero-sequence current of the cable that reflect the electrical characteristics of the cable.

[0010] The present invention also includes a distribution network cable early fault identification and early warning method based on transient disturbance, and the method specifically includes the following steps:

[0011] Step 1, detecting and transmitting the information of the cable measurement point;

[0012] Step 2: Detect the transient disturbance signals of the grounding wire current, zero-sequence voltage, and zero-sequence current according to the information of the cable measurement point;

[0013] Step 3: Identify the detected transient disturbance signal and preliminarily determine the possibility of a fault. If the possibility of a fault is higher than a set value, proceed to step 4.

[0014] Step 4: Send out an early warning signal of cable failure;

[0015] Step 5: further judge and process the identified suspected fault information;

[0016] Step 6: Analyze the preprocessed fault information and determine the fault type and level;

[0017] Step 7: Send out a corresponding alarm signal according to the determined fault type and level.

[0018] The detection of the transient disturbance signal in step 2 is realized based on complex wavelet transform: using complex wavelet function The signal is decomposed at scales of 1-32 to obtain the real part, imaginary part, amplitude and phase value of the wavelet transform coefficient at each scale; the amplitude and phase information of the wavelet coefficient at each scale are extracted; the modulus maximum of the wavelet coefficient amplitude at each scale is tracked, and the points where the modulus maximum appears at each scale are located to obtain the start and end time and duration of the transient disturbance signal.

[0019] The recognition of the detected transient disturbance signal in step 3 is implemented based on a support vector machine: the kernel function of the support vector machine is a Gaussian radial basis function, that is, Where σ is the kernel parameter of the Gaussian radial basis function, and the learning process of SVM is changed by changing the σ parameter; the value range of the kernel parameter σ is selected by the cross-validation method; the selected data is used as the training sample to form a working set, and the remaining samples are used as a set N composed of test samples, and the Lagrange multipliers of all samples in N are set to 0; the quadratic programming method is used to solve the optimization problem of the working set, and the support vector, that is, the vector whose Lagrange multiplier is not 0, is obtained, and a classifier is constructed; the samples in the set N are tested with the constructed classifier, and if all samples in N meet the optimization conditions or are an empty set, the test ends, otherwise it continues; the samples in the set N that do not meet the optimization conditions are put into the working set, and at the same time, the same number of samples are extracted from the working set and put into N, and the classifier is continued to be constructed and tested; the classification recognition result is output. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 The invention provides a structural schematic diagram of a distribution network cable early fault location system based on transient disturbance. DETAILED DESCRIPTION

[0021] The following is a detailed description of a specific example of a distribution network cable early fault identification and early warning system and method based on transient disturbances with reference to the accompanying drawings.

[0022] like Figure 1As shown, the distribution network cable early fault identification and warning system based on transient disturbance of the present invention includes an information transmission module, a transient disturbance early signal detection module, a transient disturbance early signal identification module, a fault warning module, a fault data preprocessing module, a fault data analysis module and a fault classification alarm module; the information transmission module transmits the information of the measurement point to the transient disturbance early signal detection module and the fault data preprocessing module, and the transient disturbance early signal detection module detects the transient disturbance signal of the cable; the transient disturbance early signal detection module is connected to the transient disturbance early signal identification module, and the transient disturbance early signal identification module identifies the detected transient disturbance signal and preliminarily determines the possibility of a fault; the transient disturbance early signal The signal recognition module is connected to the fault warning module, and the fault warning module sends a warning signal when the transient disturbance early signal recognition module recognizes that the possibility of a fault is too high; the transient disturbance early signal recognition module is also connected to the fault data preprocessing module, and the fault data preprocessing module further judges and processes the identified suspected fault information; the fault data preprocessing module is connected to the fault data analysis module, and the fault data analysis module analyzes the fault information processed by the fault data preprocessing module and determines the fault type and level; the fault data analysis module is connected to the fault classification alarm module, and the fault classification alarm module alarms the fault type and level determined by the fault data analysis module.

[0023] The system can not only perform early fault identification and early warning for unknown measurement points, but also perform fault type identification and alarm for known fault points.

[0024] When the system identifies the fault type and alarms for a known fault point, the fault data preprocessing module receives the known fault point information transmitted by the information transmission module and processes it, the fault data analysis module analyzes the fault information processed by the fault data preprocessing module and determines the fault type and level, and the fault classification alarm module alarms the fault type and level determined by the fault data analysis module.

[0025] The information transmission module can perform signal conversion and data transmission on the fault signals collected by the measuring points between the modules.

[0026] The transient disturbance early signal detection module can detect electrical characteristic quantities such as the grounding line current, zero-sequence voltage, and zero-sequence current of the cable that reflect the electrical characteristics of the cable.

[0027] The present invention provides a method for early fault identification and early warning of distribution network cables based on transient disturbances, comprising the following steps:

[0028] Step 1, detecting and transmitting the information of the cable measurement point;

[0029] Step 2: Detect the transient disturbance signals of the grounding wire current, zero-sequence voltage, and zero-sequence current according to the information of the cable measurement point;

[0030] Step 3: Identify the detected transient disturbance signal and preliminarily determine the possibility of a fault. If the possibility of a fault is higher than a set value, proceed to step 4.

[0031] Step 4: Send out an early warning signal of cable failure;

[0032] Step 5: further judge and process the identified suspected fault information;

[0033] Step 6: Analyze the preprocessed fault information and determine the fault type and level;

[0034] Step 7: Send out a corresponding alarm signal according to the determined fault type and level.

[0035] The detection of the transient disturbance signal in step 2 is realized based on complex wavelet transform: using complex wavelet function The signal is decomposed at scales of 1-32 to obtain the real part, imaginary part, amplitude and phase value of the wavelet transform coefficient at each scale; the amplitude and phase information of the wavelet coefficient at each scale are extracted; the modulus maximum of the wavelet coefficient amplitude at each scale is tracked, and the points where the modulus maximum appears at each scale are located to obtain the start and end time and duration of the transient disturbance signal.

[0036] The recognition of the detected transient disturbance signal in step 3 is implemented based on a support vector machine: the kernel function of the support vector machine is a Gaussian radial basis function, that is, Where σ is the kernel parameter of the Gaussian radial basis function, and the learning process of SVM is changed by changing the σ parameter; the value range of the kernel parameter σ is selected by the cross-validation method; the selected data is used as the training sample to form a working set, and the remaining samples are used as a set N composed of test samples, and the Lagrange multipliers of all samples in N are set to 0; the quadratic programming method is used to solve the optimization problem of the working set, and the support vector, that is, the vector whose Lagrange multiplier is not 0, is obtained, and a classifier is constructed; the samples in the set N are tested with the constructed classifier, and if all samples in N meet the optimization conditions or are an empty set, the test ends, otherwise it continues; the samples in the set N that do not meet the optimization conditions are put into the working set, and at the same time, the same number of samples are extracted from the working set and put into N, and the classifier is continued to be constructed and tested; the classification recognition result is output.

[0037] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not intended to limit the present invention. A person skilled in the art should understand that the specific implementation of the present invention can be modified or replaced by equivalents, but these modifications or changes are within the scope of protection of the pending claims.

Claims

1. A distribution network cable early fault identification and early warning method based on transient disturbance, characterized in that: The method specifically comprises the following steps: Step 1, detecting and transmitting the information of the cable measurement point; Step 2: Detect the transient disturbance signals of the grounding wire current, zero-sequence voltage, and zero-sequence current according to the information of the cable measurement point; Detection of transient disturbance signals based on complex wavelet transform: using complex wavelet function Decompose the signal at scales of 1-32 to obtain the real part, imaginary part, amplitude and phase value of the wavelet transform coefficient at each scale; Extract the amplitude and phase information of wavelet coefficients at each scale; track the modulus maximum of the wavelet coefficient amplitude at each scale, locate the points where the modulus maximum appears at each scale, and obtain the start and end time and duration of the transient disturbance signal; Step 3: Identify the detected transient disturbance signal and preliminarily determine the possibility of a fault. If the possibility of a fault is higher than a set value, proceed to step 4. The recognition of the detected transient disturbance signal is realized based on the support vector machine: the kernel function of the support vector machine is the Gaussian radial basis function, that is, Where σ is the kernel parameter of the Gaussian radial basis function, and the learning process of SVM is changed by changing the σ parameter; the value range of the kernel parameter σ is selected by the cross-validation method; the selected data is used as the training sample to form a working set, and the remaining samples are used as a set N composed of test samples, and the Lagrange multipliers of all samples in N are set to 0; the quadratic programming method is used to solve the optimization problem of the working set, and the support vector, that is, the vector whose Lagrange multiplier is not 0, is obtained, and a classifier is constructed; the samples in the set N are tested with the constructed classifier, and if all samples in N meet the optimization conditions or are an empty set, the test ends, otherwise it continues; the samples in the set N that do not meet the optimization conditions are put into the working set, and at the same time, the same number of samples are extracted from the working set and put into N, and the classifier is continued to be constructed and tested; the classification recognition result is output; Step 4: Send out an early warning signal of cable failure; Step 5: further judge and process the identified suspected fault information; Step 6: Analyze the preprocessed fault information and determine the fault type and level; Step 7: Send out a corresponding alarm signal according to the determined fault type and level.

2. A distribution network cable early fault identification and early warning system based on transient disturbance, which performs distribution network cable early fault identification and early warning based on the distribution network cable early fault identification and early warning method based on transient disturbance according to claim 1, characterized in that: The distribution network cable early fault identification and warning system based on transient disturbance includes an information transmission module, a transient disturbance early signal detection module, a transient disturbance early signal identification module, a fault warning module, a fault data preprocessing module, a fault data analysis module and a fault classification alarm module; the information transmission module transmits the information of the measurement point to the transient disturbance early signal detection module and the fault data preprocessing module, and the transient disturbance early signal detection module detects the transient disturbance signal of the cable; the transient disturbance early signal detection module is connected to the transient disturbance early signal identification module, and the transient disturbance early signal identification module identifies the detected transient disturbance signal and preliminarily determines the possibility of a fault; the transient disturbance early signal identification module is connected to the fault warning module, and the fault warning module sends a warning signal when the transient disturbance early signal identification module identifies that the possibility of a fault is too high; the transient disturbance early signal identification module is also connected to the fault data preprocessing module, and the fault data preprocessing module further determines and processes the identified suspected fault information; The fault data preprocessing module is connected to the fault data analysis module, and the fault data analysis module analyzes the fault information processed by the fault data preprocessing module and determines the fault type and level; the fault data analysis module is connected to the fault grading alarm module, and the fault grading alarm module alarms the fault type and level determined by the fault data analysis module.

3. The distribution network cable early fault identification and early warning system based on transient disturbance according to claim 2 is characterized in that: The system can not only perform early fault identification and early warning for unknown measurement points, but also perform fault type identification and alarm for known fault points.

4. The distribution network cable early fault identification and early warning system based on transient disturbance according to claim 3 is characterized in that: When the system identifies the fault type and alarms for a known fault point, the fault data preprocessing module receives the known fault point information transmitted by the information transmission module and processes it, the fault data analysis module analyzes the fault information processed by the fault data preprocessing module and determines the fault type and level, and the fault classification alarm module alarms the fault type and level determined by the fault data analysis module.

5. The distribution network cable early fault identification and early warning system based on transient disturbance according to claim 2 is characterized in that: The information transmission module can perform signal conversion and data transmission on the fault signals collected by the measuring points between the modules.

6. The distribution network cable early fault identification and early warning system based on transient disturbance according to claim 2 is characterized in that: The transient disturbance early signal detection module can detect the electrical characteristic quantity of the cable that reflects the electrical characteristics of the cable.

Images