CN116127361A - GIS equipment defect identification and early warning evaluation method based on eddy current sensing - Google Patents
GIS equipment defect identification and early warning evaluation method based on eddy current sensing Download PDFInfo
- Publication number
- CN116127361A CN116127361A CN202310138981.5A CN202310138981A CN116127361A CN 116127361 A CN116127361 A CN 116127361A CN 202310138981 A CN202310138981 A CN 202310138981A CN 116127361 A CN116127361 A CN 116127361A
- Authority
- CN
- China
- Prior art keywords
- defect
- early warning
- gis equipment
- corrosion
- crack
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Investigating Or Analyzing Materials By The Use Of Magnetic Means (AREA)
Abstract
本发明公开了一种基于涡流传感的GIS设备缺陷识别及预警评估方法，本方案通过建立仿真模型来设定GIS设备缺陷的静态阈值和动态阈值，使得GIS设备缺陷识别和预警具有较高的针对性，且识别结果的参考性更佳。本方案还通过对识别出的缺陷进行预警评估，引入静态阈值和动态阈值对识别结果进行预警等级划分，从而对GIS设备缺陷进行更为有效的质量安全评价，以令GIS设备存在故障时，能够被密切关注，提高了GIS设备检测的针对性，令本方案在具有实施可靠、评估信息丰富的优点。
The invention discloses a GIS equipment defect identification and early warning evaluation method based on eddy current sensing. This scheme sets the static threshold and dynamic threshold of GIS equipment defects by establishing a simulation model, so that the GIS equipment defect identification and early warning have higher Targeted, and the reference of the recognition results is better. This program also conducts early warning evaluation on the identified defects, and introduces static thresholds and dynamic thresholds to classify the early warning levels of the identification results, so as to conduct more effective quality and safety evaluations on GIS equipment defects, so that when GIS equipment has faults, it can It has been closely watched, which improves the pertinence of GIS equipment detection, and makes this scheme have the advantages of reliable implementation and rich evaluation information.
Description
Technical Field
The application relates to an electrical equipment defect detection technology, in particular to a GIS equipment defect identification and early warning assessment method based on eddy current sensing.
Background
The gas-insulated switchgear (Gas lnsulated Switchgear) is a GIS for short, and is characterized in that primary equipment except a transformer in a transformer substation comprises electric equipment such as a circuit breaker, a disconnecting switch, a grounding switch, a voltage transformer, a current transformer, a lightning arrester, a bus, a cable terminal, a wire inlet and outlet sleeve and the like, and is organically combined into a closed gas-insulated electric equipment whole through an optimal design. Because the GIS air chamber is a main part of pressure-bearing insulation, cracks and corrosion defects are inevitably generated on the surface in the production or use process, in order to ensure the normal operation of the GIS air chamber, the traditional method comprises manual visual inspection, infrared thermal imaging and ultrasonic detection, and along with the continuous updating of the detection technology, a plurality of online automatic detection technologies without stopping are present, and the method adopting the visual inspection and the infrared thermal imaging detection of workers is limited by the change of working environment and temperature, so that the problems of low defect detection efficiency, large error, incomplete detection and the like are easily caused; part of GIS air chambers are detected by using automatic detection equipment, but most equipment cannot realize identification and early warning evaluation of defects of GIS equipment, cannot properly give early warning information according to detection results, and even cannot realize classification of cracks or corrosion defects.
Because GIS equipment also needs to be subjected to health detection in the working process, the fault part of the GIS equipment has a certain precursor in a certain time period, the current online detection mode mostly carries out flaw detection on the GIS equipment regularly, and the GIS equipment can be interfered in an emergency stop or early warning mode when the GIS equipment has a fault or a certain precursor of the fault, so that equipment damage or other associated losses are avoided. Under the condition that some fault precursors tend to be smaller, the damage defect can be repaired in time by adopting a maintenance mode. Therefore, how to identify and early-warning evaluate the defects of the GIS equipment is a very practical topic.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention aims to provide a GIS equipment defect identification and early warning evaluation method based on eddy current sensing, and aims to provide a quality safety evaluation method for enabling GIS equipment defect detection to be more effective, so that GIS equipment can be closely concerned when precursor faults or faults exist, and the detection pertinence of the GIS equipment is improved.
Therefore, the invention aims to provide a GIS equipment defect detection and early warning evaluation method which is reliable to implement, early warning in time and good in result reference.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
a GIS equipment defect identification and early warning assessment method based on eddy current sensing comprises the following steps:
step 1: according to basic parameters of GIS equipment, constructing a finite element simulation model of the vortex sensing of the GIS equipment, and changing different crack depths D= [ D ] 1 ，D 2 ，…，D k ，…，D e ]Obtaining different moments T= [ T ] 1 ，t 2 ，t 3 ，…，t k ，…，t w ]Is a simulated crack defect signal P L ＝[P L (t 1 ，D 1 )，P L (t 2 ，D 1 )，P L (t 3 ，D 1 )，…，P L (t k ，D k )，…，P L (t w ，D 1 )，P L (t 1 ，D e )，P L (t 2 ，D e )，P L (t 3 ，D e )，…，P L (t k ，D e )，…，P L (t w ，D e )]，
At any time t k The lower crack sampling result comprises m multiplied by n detection data in a designated area; by varying the different corrosion areas s= [ S ] 1 ，S 2 ，…，S k ，…，S e ]Obtaining different moments T= [ T ] 1 ，t 2 ，t 3 ，…，t k ，…，t w ]Is a simulated corrosion defect signal P C ＝[P C (t 1 ，S 1 )，P C (t 2 ，S 1 )，P C (t 3 ，S 1 )，…，P C (t k ，S k )，…，P C (t w ，D 1 )，P C (t 1 ，D e )，P C (t 2 ，D e )，P C (t 3 ，D e )，…，P C (t k ，D e )，…，P C (t w ，D e )]，
At any timet k The downsampling result comprises m×n detection data in a designated area;
step 2: obtaining a crack defect differential simulation signal Q at adjacent time points L ＝[Q L 1 ，Q L 2 ，Q L 3 ，…，Q L k ，…，Q L n －1 ]，Q L k ＝[Q L1，1 k ，Q L1，2 k ，…，Q L1，n k ，…，Q Li，1 k ，Q Li，2 k ，…，Q Li，j k ，…，Q Li，n k ，…，Q Lm，1 k ，Q Lm，2 k ，…，Q Lm，n k ]And corrosion defect differential simulation signal
Wherein->
And->
The calculation method of (1) is as follows:
step 3: constructing a GIS equipment defect classification data set N= [ Q ] L ，Q C ]Training learning is performed in a convolutional neural network after homogenization and regularization, and network output settings are divided into two categories: after the preset network convergence accuracy condition is met, acquiring a GIS equipment defect classification model f1;
step 4: respectively at different moments t= [ T ] 1 ，t 2 ，t 3 ，…，t k ，…，t w ]Detection defect signal P' = [ P (t) 1 )’，P(t 2 )’，P(t 3 )’，…，P(t k )’，…，P(t w )’]，P(t k )’＝[P1，1(t k )’，P 1，2 (t k )’，…，P 1，n (t k )’，…，P i，1 (t k )’，P i，2 (t 1 )’，…，P i，j (t k )’，…，P i，n (t 1 )’，…，P m，1 (t 1 )’，P m，2 (t 1 )’，…，P m，n (t 1 )’]The sampling result at any time ti includes m×n pieces of detection data in the designated area.
Step 5: obtaining a crack defect differential detection signal Q at adjacent time points L ’＝[Q L 1 ’，Q L 2 ’，Q L 3 ’，…，Q L k ’，…，Q L n－1 ’]，Q L k ’＝[Q L1，1 k ’，Q L1，2 k ’，…，Q L1，n k ’，…，Q Li，1 k ’，Q Li，2 k ’，…，Q Li，j k ’，…，Q Li，n k ’，…，Q Lm，1 k ’，Q Lm，2 k ’，…，Q Lm，n k ’]And a corrosion defect differential detection signal
step 6: based on the differential signal Q, after homogenization and regularization, a data set N' = [ Q ] for convolutional neural network learning is constructed L ’，Q C ’]Input to a trained model f 1 Obtain the classification result O= [ O ] of the detection signal 1 ，O 2 ，O 3 ，…O g ，…，O 2n－2 ]；
Step 7: and according to the classification result of the detection region, carrying out early warning evaluation on the region with the classification result of the crack by adopting the following method: if the classification result O g Is a crack, and the corresponding defect detection signal is P L (t k ) ' the corresponding defect differential signal is
The following parameters were calculated: />
If it is
Greater than the static threshold of the set crack defect and V L (t k ) If the detection result is larger than the set dynamic threshold value of the crack defect, the early warning grade is first-grade;
if it is
Greater than the static threshold of the set crack defect and V L (t k ) If the pre-warning level is smaller than the set dynamic threshold value of the crack defect, the pre-warning level is two-level;
if it is
Less than the set crack defect static threshold and V L (t k ) If the pre-warning level is greater than the set dynamic threshold value of the crack defect, the pre-warning level is three-level;
if it is
Less than the set crack defect static threshold and V L (t k ) And if the dynamic threshold value is smaller than the set dynamic threshold value of the crack defect, the safety is considered.
For the region with the corrosion classification result, the following method is adopted for early warning evaluation
If the classification result O g Is a corrosion defect, and the corresponding defect detection signal is P C (t k ) ' the corresponding defect differential signal is
The following parameters were calculated:
if it is
Greater than the static threshold of the set corrosion defect and V C (t k ) If the early warning level is greater than the set dynamic threshold value of the corrosion defect, the early warning level is first-level;
if it is
Greater than the static threshold of the set corrosion defect and V C (t k ) If the early warning level is smaller than the set dynamic threshold value of the corrosion defect, the early warning level is two-level;
if it is
Less than the static threshold of the set corrosion defect andV C (t k ) If the early warning level is greater than the set dynamic threshold value of the corrosion defect, the early warning level is three-level;
if it is
Less than the static threshold of the set corrosion defect and V C (t k ) And if the corrosion defect dynamic threshold value is smaller than the set corrosion defect dynamic threshold value, the safety is considered.
The early warning levels are respectively sorted according to the dangerous level: the first early warning level is higher than the second early warning level and higher than the third early warning level.
The static threshold DeltaQ L /△Q C And a dynamic threshold DeltaV L /△V C It is required to obtain it through finite element simulation.
Based on the above, the invention provides application of the GIS equipment defect identification and early warning evaluation method in electrical equipment detection.
The beneficial effects are that:
according to the method, the detection signals are classified and identified, the detection results are subjected to preliminary evaluation, the crack defects or corrosion defects of the GIS equipment are determined, then the identified crack defects and corrosion defects are further evaluated, and early warning grades of damage of different degrees are given, so that monitoring staff can timely know the detection conditions of the GIS equipment.
Description of the drawings:
in order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for identifying and early warning and evaluating defects of GIS equipment according to the present invention;
fig. 2 is an evaluation and early warning grade division schematic diagram of the GIS equipment defect recognition and early warning evaluation method.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments.
The invention is described in further detail below with reference to the drawings and examples. It is specifically noted that the following examples are only for illustrating the present invention, but do not limit the scope of the present invention. Likewise, the following examples are only some, but not all, of the examples of the present invention, and all other examples, which a person of ordinary skill in the art would obtain without making any inventive effort, are within the scope of the present invention.
As shown in fig. 1, the present embodiment is a method for identifying and early warning and evaluating defects of a GIS device based on eddy current sensing, which includes:
step 1: according to basic parameters of GIS equipment, constructing a finite element simulation model of the vortex sensing of the GIS equipment, and changing different crack depths D= [ D ] 1 ，D 2 ，…，D k ，…，D e ]Obtaining different moments T= [ T ] 1 ，t 2 ，t 3 ，…，t k ，…，t w ]Is a simulated crack defect signal P L ＝[P L (t 1 ，D 1 )，P L (t 2 ，D 1 )，P L (t 3 ，D 1 )，…，P L (t k ，D k )，…，P L (t w ，D 1 )，P L (t 1 ，D e )，P L (t 2 ，D e )，P L (t 3 ，D e )，…，P L (t k ，D e )，…，P L (t w ，D e )]，
At any time t k The lower crack sampling result comprises m multiplied by n detection data in a designated area; by varying the different corrosion areas s= [ S ] 1 ，S 2 ，…，S k ，…，S e ]Obtaining different moments T= [ T ] 1 ，t 2 ，t 3 ，…，t k ，…，t w ]Is a simulated corrosion defect signal P C ＝[P C (t 1 ，S 1 )，P C (t 2 ，S 1 )，P C (t 3 ，S 1 )，…，P C (t k ，S k )，…，P C (t w ，D 1 )，P C (t 1 ，D e )，P C (t 2 ，D e )，P C (t 3 ，D e )，…，P C (t k ，D e )，…，P C (t w ，D e )]，
At any time t k The downsampling result comprises m×n detection data in a designated area;
step 2: obtaining a crack defect differential simulation signal Q at adjacent time points L ＝[Q L 1 ，Q L 2 ，Q L 3 ，…，Q L k ，…，Q L n －1 ]，Q L k ＝[Q L1，1 k ，Q L1，2 k ，…，Q L1，n k ，…，Q Li，1 k ，Q Li，2 k ，…，Q Li，j k ，…，Q Li，n k ，…，Q Lm，1 k ，Q Lm，2 k ，…，Q Lm，n k ]And corrosion defect differential simulation signal
Wherein->
And->
The calculation method of (1) is as follows:
step 3: constructing a GIS equipment defect classification data set N= [ Q ] L ，Q C ]Training learning is performed in a convolutional neural network after homogenization and regularization, and network output settings are divided into two categories: after the preset network convergence accuracy condition is met, acquiring a GIS equipment defect classification model f1;
step 4: respectively at different moments t= [ T ] 1 ，t 2 ，t 3 ，…，t k ，…，t w ]Detection defect signal P' = [ P (t) 1 )’，P(t 2 )’，P(t 3 )’，…，P(t k )’，…，P(t w )’]，P(t k )’＝[P1，1(t k )’，P 1，2 (t k )’，…，P 1，n (t k )’，…，P i，1 (t k )’，P i，2 (t 1 )’，…，P i，j (t k )’，…，P i，n (t 1 )’，…，P m，1 (t 1 )’，P m，2 (t 1 )’，…，P m，n (t 1 )’]The sampling result at any time ti includes m×n pieces of detection data in the designated area.
Step 5: obtaining a crack defect differential detection signal Q at adjacent time points L ’＝[Q L 1 ’，Q L 2 ’，Q L 3 ’，…，Q L k ’，…，Q L n－1 ’]，Q L k ’＝[Q L1，1 k ’，Q L1，2 k ’，…，Q L1，n k ’，…，Q Li，1 k ’，Q Li，2 k ’，…，Q Li，j k ’，…，Q Li，n k ’，…，Q Lm，1 k ’，Q Lm，2 k ’，…，Q Lm，n k ’]And a corrosion defect differential detection signal
step 6: based on the differential signal Q, after homogenization and regularization, a data set N' = [ Q ] for convolutional neural network learning is constructed L ’，Q C ’]Input to a trained model f 1 Obtain the classification result O= [ O ] of the detection signal 1 ，O 2 ，O 3 ，…O g ，…，O 2n－2 ]；
Step 7: and according to the classification result of the detection region, carrying out early warning evaluation on the region with the classification result of the crack by adopting the following method: if the classification result O g Is a crack, and the corresponding defect detection signal is P L (t k ) ' the corresponding defect differential signal is
The following parameters were calculated:
if it is
Greater than the static threshold of the set crack defect and V L (t k ) If the detection result is larger than the set dynamic threshold value of the crack defect, the early warning grade is first-grade;
if it is
Greater than the static threshold of the set crack defect and V L (t k ) If the pre-warning level is smaller than the set dynamic threshold value of the crack defect, the pre-warning level is two-level;
if it is
Less than the set crack defect static threshold and V L (t k ) If the pre-warning level is greater than the set dynamic threshold value of the crack defect, the pre-warning level is three-level;
if it is
Less than the set crack defect static threshold and V L (t k ) And if the dynamic threshold value is smaller than the set dynamic threshold value of the crack defect, the safety is considered.
For the region with the corrosion classification result, the following method is adopted for early warning evaluation
If the classification result O g Is a corrosion defect, and the corresponding defect detection signal is P C (t k ) ' the corresponding defect differential signal is
The following parameters were calculated:
if it is
Greater than the static threshold of the set corrosion defect and V C (t k ) If the early warning level is greater than the set dynamic threshold value of the corrosion defect, the early warning level is first-level; />
If it is
Greater than the static threshold of the set corrosion defect and V C (t k ) If the early warning level is smaller than the set dynamic threshold value of the corrosion defect, the early warning level is two-level;
if it is
Less than the static threshold of the set corrosion defect and V C (t k ) If the early warning level is greater than the set dynamic threshold value of the corrosion defect, the early warning level is three-level;
if it is
Less than the static threshold of the set corrosion defect and V C (t k ) Less than the set corrosionAnd the defect dynamic threshold value is determined to be safe.
Wherein, the early warning grades are respectively according to the order of the dangerous magnitudes: the first early warning level is higher than the second early warning level and higher than the third early warning level. The static threshold DeltaQ L /△Q C And a dynamic threshold DeltaV L /△V C It is required to obtain it through finite element simulation.
The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the same, but rather, various modifications and variations may be made by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims (4)
1. A GIS equipment defect identification and early warning assessment method based on eddy current sensing is characterized by comprising a GIS equipment defect identification and early warning assessment method based on eddy current sensing detection, wherein a GIS equipment detection signal is mainly a cylindrical shell defect detection signal of a GIS equipment gas container; the method is characterized in that the GIS equipment defect signals are acquired through an eddy current sensing system, and the GIS equipment defect signals comprise GIS equipment crack and corrosion defect signals acquired through simulation and GIS equipment crack and corrosion defect signals detected on site; the identification and early warning evaluation method is mainly used for identifying and early warning evaluation of cracks and corrosion defects of GIS equipment and is characterized in that the cracks and the corrosion defects are identified through an improved neural network algorithm, and early warning evaluation is carried out on identification results.
2. The method for identifying and early warning and evaluating the defects of the GIS equipment based on the eddy current sensing according to claim 1 is characterized by comprising the following steps:
step 1: according to basic parameters of GIS equipment, constructing a finite element simulation model of the vortex sensing of the GIS equipment, and changing different crack depths D= [ D ] 1 ，D 2 ，…，D k ，…，D e ]Obtaining different moments T= [ T ] 1 ，t 2 ，t 3 ，…，t k ，…，t w ]Is a simulated crack defect signal P L ＝[P L (t 1 ，D 1 )，P L (t 2 ，D 1 )，P L (t 3 ，D 1 )，…，P L (t k ，D k )，…，P L (t w ，D 1 )，P L (t 1 ，D e )，P L (t 2 ，D e )，P L (t 3 ，D e )，…，P L (t k ，D e )，…，P L (t w ，D e )]，P L (t k ，D k )＝[P 1，1 L (t k ，D k )，P 1，2 L (t k ，D k )，…，P 1，n L (t k ，D k )，…，P i，1 L (t k ，D k )，P i，2 L (t k ，D k )，…，P i，j L (t k ，D k )，…，P i，n L (t k ，D k )，…，P m，1 L (t k ，D k )，P m，2 L (t k ，D k )，…，P m，n L (t k ，D k )]At any time t k The lower crack sampling result comprises m multiplied by n detection data in a designated area; by varying the different corrosion areas s= [ S ] 1 ，S 2 ，…，S k ，…，S e ]Obtaining different moments T= [ T ] 1 ，t 2 ，t 3 ，…，t k ，…，t w ]Is a simulated corrosion defect signal P C ＝[P C (t 1 ，S 1 )，P C (t 2 ，S 1 )，P C (t 3 ，S 1 )，…，P C (t k ，S k )，…，P C (t w ，D 1 )，P C (t 1 ，D e )，P C (t 2 ，D e )，P C (t 3 ，D e )，…，P C (t k ，D e )，…，P C (t w ，D e )]，P C (tk，D k )＝[P 1，1 C (t k ，D k )，P 1，2 C (t k ，D k )，…，P 1，n C (t k ，D k )，…，P i，1 C (t k ，D k )，P i，2 C (t k ，D k )，…，P i，j C (t k ，D k )，…，P i，n C (t k ，D k )，…，P m，1 C (t k ，D k )，P m，2 C (t k ，D k )，…，P m，n C (t k ，D k )]At any time t k The downsampling result comprises m×n detection data in a designated area;
step 2: obtaining a crack defect differential simulation signal Q at adjacent time points L ＝[Q L 1 ，Q L 2 ，Q L 3 ，…，Q L k ，…，Q L n－1 ]，Q L k ＝[Q L1，1 k ，Q L1，2 k ，…，Q L1，n k ，…，Q Li，1 k ，Q Li，2 k ，…，Q Li，j k ，…，Q Li，n k ，…，Q Lm，1 k ，Q Lm，2 k ，…，Q Lm，n k ]And corrosion defect differential simulation signal
Wherein Q is Li，j k And Q Ci，j k The calculation method of (1) is as follows:
step 3: constructing a GIS equipment defect classification data set N= [ Q ] L ，Q C ]Training learning is performed in a convolutional neural network after homogenization and regularization, and network output settings are divided into two categories: after the preset network convergence accuracy condition is met, acquiring a GIS equipment defect classification model f1;
step 4: respectively at different moments t= [ T ] 1 ，t 2 ，t 3 ，…，t k ，…，t w ]Detection defect signal P' = [ P (t) 1 )’，P(t 2 )’，P(t 3 )’，…，P(t k )’，…，P(t w )’]，P(t k )’＝[P1，1(t k )’，P 1，2 (t k )’，…，P 1，n (t k )’，…，P i，1 (t k )’，P i，2 (t 1 )’，…，P i，j (t k )’，…，P i，n (t 1 )’，…，P m，1 (t 1 )’，P m，2 (t 1 )’，…，P m，n (t 1 )’]The sampling result at any time ti comprises m×n detection data in a designated area;
step 5: obtaining a crack defect differential detection signal Q at adjacent time points L ’＝[Q L 1 ’，Q L 2 ’，Q L 3 ’，…，Q L k ’，…，Q L n－1 ’]，Q L k ’＝[Q L1，1 k ’，Q L1，2 k ’，…，Q L1，n k ’，…，Q Li，1 k ’，Q Li，2 k ’，…，Q Li，j k ’，…，Q Li，n k ’，…，Q Lm，1 k ’，Q Lm，2 k ’，…，Q Lm，n k ’]And a corrosion defect differential detection signal
Wherein->
And->
The calculation method of (1) is as follows:
step 6: based on the differential signal Q, after homogenization and regularization, a data set N' = [ Q ] for convolutional neural network learning is constructed L ’，Q C ’]Input to a trained model f 1 Obtain the classification result O= [ O ] of the detection signal 1 ，O 2 ，O 3 ，…O g ，…，O 2n－2 ]；
Step 7: and according to the classification result of the detection region, carrying out early warning evaluation on the region with the classification result of the crack by adopting the following method: if the classification result O g Is a crack, and the corresponding defect detection signal is P L (t k ) ' the corresponding defect differential signal is Q Li，j k The following parameters were calculated:
if Q Li.j k Greater than the static threshold of the set crack defect and V L (t k ) If the detection result is larger than the set dynamic threshold value of the crack defect, the early warning grade is first-grade;
if Q Li.j k Greater than the static threshold of the set crack defect and V L (t k ) If the pre-warning level is smaller than the set dynamic threshold value of the crack defect, the pre-warning level is two-level;
if Q Li.j k Less than the set crack defect static threshold and V L (t k ) If the pre-warning level is greater than the set dynamic threshold value of the crack defect, the pre-warning level is three-level;
if Q Li.j k Less than the set crack defect static threshold and V L (t k ) If the dynamic threshold value of the crack defect is smaller than the set dynamic threshold value of the crack defect, the safety is determined;
for the region with the corrosion classification result, the following method is adopted for early warning evaluation
If the classification result O g For corrosion, the corresponding defect detection signal is P C (t k ) ' the corresponding defect differential signal is Q Ci，j k The following parameters were calculated:
if Q Ci，j k Greater than the static threshold of the set corrosion defect and V C (t k ) If the early warning level is greater than the set dynamic threshold value of the corrosion defect, the early warning level is first-level;
if Q Ci，j k Greater than the static threshold of the set corrosion defect and V C (t k ) If the early warning level is smaller than the set dynamic threshold value of the corrosion defect, the early warning level is two-level;
if Q Ci，j k Less than the static threshold of the set corrosion defect and V C (t k ) If the corrosion defect dynamic threshold value is larger than the set corrosion defect dynamic threshold value, early warning and the likeThe stage is three stages;
if Q Ci，j k Less than the static threshold of the set corrosion defect and V C (t k ) And if the corrosion defect dynamic threshold value is smaller than the set corrosion defect dynamic threshold value, the safety is considered.
3. The method for identifying and pre-warning and evaluating defects of GIS equipment based on eddy current sensing according to claim 2, wherein the pre-warning levels are respectively as follows according to the sequence of the dangerous magnitudes: the first early warning level is higher than the second early warning level and higher than the third early warning level.
4. The method for identifying and pre-warning and evaluating defects of GIS equipment based on eddy current sensing according to claim 3, wherein the static threshold and the dynamic threshold are required to be obtained through finite element simulation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310138981.5A CN116127361A (en) | 2023-02-10 | 2023-02-10 | GIS equipment defect identification and early warning evaluation method based on eddy current sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310138981.5A CN116127361A (en) | 2023-02-10 | 2023-02-10 | GIS equipment defect identification and early warning evaluation method based on eddy current sensing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116127361A true CN116127361A (en) | 2023-05-16 |
Family
ID=86311605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310138981.5A Pending CN116127361A (en) | 2023-02-10 | 2023-02-10 | GIS equipment defect identification and early warning evaluation method based on eddy current sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116127361A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118278653A (en) * | 2024-03-08 | 2024-07-02 | 易唯思智能自动化装备无锡有限公司 | A device defect detection system based on visual robot |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050182613A1 (en) * | 2003-11-13 | 2005-08-18 | Southwest Research Institute | Simulation of guided wave reflection signals representing defects in conduits |
| CN112200000A (en) * | 2020-09-11 | 2021-01-08 | 上海交通大学 | Welding stability recognition model training method and welding stability recognition method |
| CN112229904A (en) * | 2020-11-23 | 2021-01-15 | 南昌航空大学 | Pulse far-field eddy current detection probe and use method thereof |
| CN114359193A (en) * | 2021-12-23 | 2022-04-15 | 华中科技大学 | Defect classification method and system based on ultrasonic phased array imaging |
| CN114414658A (en) * | 2022-01-11 | 2022-04-29 | 南京大学 | Laser ultrasonic detection method for microcrack depth on metal surface |
-
2023
- 2023-02-10 CN CN202310138981.5A patent/CN116127361A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050182613A1 (en) * | 2003-11-13 | 2005-08-18 | Southwest Research Institute | Simulation of guided wave reflection signals representing defects in conduits |
| CN112200000A (en) * | 2020-09-11 | 2021-01-08 | 上海交通大学 | Welding stability recognition model training method and welding stability recognition method |
| CN112229904A (en) * | 2020-11-23 | 2021-01-15 | 南昌航空大学 | Pulse far-field eddy current detection probe and use method thereof |
| CN114359193A (en) * | 2021-12-23 | 2022-04-15 | 华中科技大学 | Defect classification method and system based on ultrasonic phased array imaging |
| CN114414658A (en) * | 2022-01-11 | 2022-04-29 | 南京大学 | Laser ultrasonic detection method for microcrack depth on metal surface |
Non-Patent Citations (1)
| Title |
|---|
| 胡浪涛;何辅云;查君君;: "小波变换和神经网络在漏磁缺陷信号识别中的应用", 无损检测, no. 04, 10 April 2007 (2007-04-10) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118278653A (en) * | 2024-03-08 | 2024-07-02 | 易唯思智能自动化装备无锡有限公司 | A device defect detection system based on visual robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105891629B (en) | A kind of discrimination method of transformer equipment failure | |
| CN111832914B (en) | Power transmission line structure health assessment method and system based on digital twinning | |
| CN104020754B (en) | Method for enabling state monitoring information of transformer station primary main equipment to access to regulation and control system | |
| CN117612345A (en) | A power equipment status monitoring and alarm system and method | |
| CN109324236A (en) | A Fault Evaluation Method Based on Typical Defects of Cable Joints | |
| CN104318347A (en) | Power transmission line icing state assessment method based on information fusion of multiple sensors | |
| CN104655948A (en) | Novel multistage fault diagnosis method for power transformer | |
| CN115796832B (en) | Comprehensive evaluation method of health status of substation equipment based on multi-dimensional parameters | |
| CN117977582B (en) | A real-time monitoring method for substation load based on digital twin technology | |
| CN111965214B (en) | Method and system for judging heating defects of composite insulators for overhead lines | |
| CN113780401A (en) | Composite insulator fault detection method and system based on principal component analysis | |
| CN106570651A (en) | Method for evaluating pollution flashover risk of insulator of power transmission line | |
| CN107271867A (en) | GIS partial discharge fault type recognition method based on D S evidence theories | |
| CN113376494B (en) | Method for detecting potential defects of fire hidden danger of cable | |
| CN118169507A (en) | Power distribution network fault diagnosis and early warning system based on big data | |
| CN105223293A (en) | Based on the transformer state method for early warning of oil chromatography on-line monitoring | |
| Yin et al. | A novel method for visualizing the pollution distribution of insulators | |
| CN116184265A (en) | A method and system for detecting leakage current of lightning arrester based on multi-classification SVM | |
| CN118914761B (en) | A method and system for detecting insulation of high voltage cables for mining | |
| CN116595459A (en) | A pollution flashover warning method and system based on electric field signal | |
| CN116626543A (en) | Heating cable fault detection method and system based on skin effect | |
| CN117783689A (en) | An intelligent assessment method for pot insulator defects in UHV GIS equipment | |
| Shahid et al. | Health diagnosis scheme for in-service low voltage Aerial Bundled Cables using super-heterodyned airborne Ultrasonic testing | |
| Mei et al. | Defect detection of electrical insulating materials using optically excited transient thermography and deep autoencoder | |
| CN116127361A (en) | GIS equipment defect identification and early warning evaluation method based on eddy current sensing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |