CN113252218B - Insulator surface stress prediction method and prediction device - Google Patents
Insulator surface stress prediction method and prediction device Download PDFInfo
- Publication number
- CN113252218B CN113252218B CN202110518748.0A CN202110518748A CN113252218B CN 113252218 B CN113252218 B CN 113252218B CN 202110518748 A CN202110518748 A CN 202110518748A CN 113252218 B CN113252218 B CN 113252218B
- Authority
- CN
- China
- Prior art keywords
- neural network
- stress
- insulator
- value
- working conditions
- 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.)
- Active
Links
- 239000012212 insulator Substances 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000013528 artificial neural network Methods 0.000 claims abstract description 64
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000001514 detection method Methods 0.000 claims description 21
- 230000005540 biological transmission Effects 0.000 claims description 19
- 238000010276 construction Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 239000004020 conductor Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000004026 adhesive bonding Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003822 epoxy resin Substances 0.000 description 1
- 238000009422 external insulation Methods 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 229920000647 polyepoxide Polymers 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L1/00—Measuring force or stress, in general
- G01L1/25—Measuring force or stress, in general using wave or particle radiation, e.g. X-rays, microwaves, neutrons
- G01L1/255—Measuring force or stress, in general using wave or particle radiation, e.g. X-rays, microwaves, neutrons using acoustic waves, or acoustic emission
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Toxicology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Acoustics & Sound (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention discloses an insulator surface stress prediction method and a prediction device, wherein the method comprises the following steps: determining working conditions of the insulator, and dividing the working conditions into normal working conditions and working conditions when bolts are loosened; collecting ultrasonic signal values of the insulator under normal working conditions, and ultrasonic signal values and stress values of the insulator under different loosening working conditions of bolts; taking the energy difference value and the stress value of the ultrasonic signals under the normal working condition and the bolt loosening working condition as the input value and the output value of the BP neural network, and training the BP neural network to obtain a trained BP neural network; verifying the accuracy of the BP neural network; the invention realizes the surface stress prediction of the online basin-type insulator.
Description
Technical Field
The invention relates to the technical field of stress prediction, in particular to an insulator surface stress prediction method and a prediction device.
Background
Currently, basin-type insulators are generally formed by gluing or mechanically clamping insulating pieces and metal accessories (such as steel feet, bolts and the like) with glue. Insulators are widely used in power systems, generally belong to external insulation, and operate under atmospheric conditions. The external live conductors of overhead transmission lines, power plants and substations, and of various electrical equipment, are all supported by insulators and insulated from the earth or other conductors with potential differences.
However, when the basin-type insulator runs in a high-voltage environment, the basin-type insulator loosens due to vibration during switching-on and switching-off of a breaker in a GIS (gas insulated switchgear) and the fact that bolts are not sealed uniformly in the assembling and disassembling process, when the bolts of the basin-type insulator loosen, the flanges are stressed unevenly, the stress on the inner surface of the basin-type insulator is distorted, and then the basin-type insulator is broken, so that an air leakage accident occurs; in the prior art, the ultrasonic injection method can theoretically realize the detection of the stress of the basin-type insulator, but the technology has the problems that the ultrasonic wave is difficult to go deep and the internal on-line detection cannot be realized. The Chinese patent with publication number of CN110531233 uses ultrasonic injection method to measure the surface condition of the basin-type insulator so as to achieve the purpose of measuring the surface pollution state of the basin-type insulator, but the method can not test the surface stress of the basin-type insulator due to the gap between the flange and the epoxy resin.
Therefore, how to provide an insulator surface stress prediction method capable of solving the above-mentioned problems is a problem that needs to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, the invention provides a method and a device for predicting the surface stress of an insulator, which can be used for predicting the surface stress of an online basin-type insulator and early warning of the breakage accident of the basin-type insulator.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
an insulator surface stress prediction method, comprising:
determining working conditions of the insulator, and dividing the working conditions into normal working conditions and working conditions when bolts are loosened;
collecting ultrasonic signal values of the insulator under normal working conditions, and ultrasonic signal values and stress values of the insulator under different loosening working conditions of bolts;
taking the energy difference value and the stress value of the ultrasonic signals under the normal working condition and the bolt loosening working condition as the input value and the output value of the BP neural network, and training the BP neural network to obtain a trained BP neural network;
verifying the accuracy of the BP neural network
Preferably, the method further comprises: the specific process for verifying the accuracy of the BP neural network is as follows:
comparing absolute errors of the stress measured value and the stress predicted value of the insulator under different loosening working conditions;
and training and correcting the BP neural network, and obtaining the predicted BP neural network when the counter transmission error of the stress measured value and the stress predicted value meets the requirement.
Preferably, the BP neural network correction process includes: and adjusting the weight and the threshold of the BP neural network by using the back propagation error function to correct, and completing adjustment when the back propagation error function value reaches the minimum.
Preferably, the BP neural network includes: the ultrasonic transmission signal energy difference value of the insulator loosening bolt is adopted as the input layer, and the stress value of a typical stress distortion point of the basin-type insulator is adopted as the output layer.
Preferably, the number of the input layers is 1-3, and the number of the output layers is 3-9.
Further, the invention also provides a device for predicting the surface stress of the insulator, which comprises the following steps:
the stress detection unit is used for collecting the surface stress of the insulator to be tested;
the ultrasonic detection unit is used for collecting ultrasonic signal values of the surface of the insulator to be detected;
the upper computer is connected with the stress detection unit and the ultrasonic detection unit, and is used for processing data acquired by the stress detection unit and the ultrasonic detection unit.
Preferably, the upper computer includes:
the BP neural network construction unit is used for establishing a BP neural network and training the BP neural network by utilizing surface stress and ultrasonic signal values under normal working conditions and bolt loosening working conditions;
and the BP neural network evaluation unit is used for verifying the accuracy of the BP neural network.
Compared with the prior art, the invention discloses a method and a device for predicting the surface stress of the insulator, which are based on the combination of ultrasonic transmission signal energy comparison and BP neural network, overcome the defect that ultrasonic waves are difficult to inject into the basin-type insulator, improve the feasibility of online prediction of the surface stress of the basin-type insulator, and improve the early warning efficiency of the cracking accident of the basin-type insulator.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an insulator surface stress prediction method provided by the invention;
FIG. 2 is a schematic block diagram of a device for predicting surface stress of an insulator according to the present invention;
fig. 3 is a schematic structural diagram of a BP neural network according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
When the flange fixing bolt of the basin-type insulator is loosened, and the flange is stressed unevenly, malignant accidents such as GIS air leakage and the like can be possibly caused, when the basin-type insulator bolt is loosened, the stress distortion of the position, which is close to the flange and has smaller curvature radius, of the opposite side of the loosening bolt is most obvious,
the embodiment of the invention provides a surface stress prediction method applicable to a basin-type insulator, wherein an ultrasonic transmission signal measured when a basin-type insulator bolt is loosened and a stress value of a typical stress distortion point are used as training and testing samples of a BP neural network, a BP neural network model for stress prediction is obtained through training, and the BP neural network obtained through training can realize the surface stress prediction of the basin-type insulator. The method is beneficial to improving the stress monitoring efficiency of the basin-type insulator, realizing online stress prediction, and achieving the purposes of eliminating hidden danger and realizing safe production.
Example 1
Referring to fig. 1, embodiment 1 of the present invention discloses a method for predicting surface stress of an insulator, which includes:
determining working conditions of the insulator, and dividing the working conditions into normal working conditions and working conditions when bolts are loosened;
the bolt loosening working conditions of the basin-type insulator are determined, and the bolt loosening working conditions mainly comprise three working conditions, namely one bolt loosening, two bolt loosening and three bolt loosening.
When two bolts are loosened, the two bolts are classified according to the angle between the two bolts, and according to the classification mode, six modes of 30 degrees, 60 degrees, 90 degrees, 120 degrees, 150 degrees and 180 degrees are shared.
The pattern classification when the three bolts are loosened can be classified according to angles among the three bolts, the arrows are loosening bolts as shown in fig. 1, 3 and 5 are sequentially arranged in sequence, and the pattern numbers are determined to be 60-60 and 135.
Collecting ultrasonic signal values of the insulator under normal working conditions, and ultrasonic signal values and stress values of the insulator under different loosening working conditions of bolts;
specifically, under different working conditions, gradient setting is carried out on bolt torque, the bolt torque is combined according to the number of bolts, ultrasonic transmission signal energy and stress values under various bolt torque combinations are measured, partial group data are used as training samples of the BP neural network under the working conditions, and the data of the rest groups are used as test samples;
the stress value acquisition points are located at radial positions along the loose bolts, and each bolt acquires stress values of three points at corresponding positions.
Taking the energy difference value and the stress value of the ultrasonic signals under the normal working condition and the bolt loosening working condition as the input value and the output value of the BP neural network, and training the BP neural network to obtain a trained BP neural network;
and verifying the accuracy of the BP neural network.
In a specific embodiment, the method further comprises: the specific process for verifying the accuracy of the BP neural network is as follows:
comparing absolute errors of the stress measured value and the stress predicted value of the insulator under different loosening working conditions;
and training and correcting the BP neural network, and obtaining the predicted BP neural network when the counter transmission error of the stress measured value and the stress predicted value meets the requirement.
Specifically, the BP neural network correction process includes: and adjusting the weight and the threshold value of the BP neural network by using a back transmission error function to correct, and completing adjustment when the back transmission error function value E reaches the minimum, wherein the specific expression is as follows:
wherein t is i And O i The expected output of the surface stress of the basin-type insulator and the calculation output of the BP neural network are respectively.
Referring to fig. 3, in a specific embodiment, the BP neural network includes: the ultrasonic transmission signal energy difference value of the insulator loosening bolt is adopted as the input layer, and the stress value of a typical stress distortion point of the basin-type insulator is adopted as the output layer.
In a specific embodiment, the number of the input layers is 1-3, the number of the output layers is 3-9, the number of hidden layer nodes is determined according to the number of the input nodes and the number of the output nodes, and the value of the hidden layer nodes is usually between the number of the input layer nodes and the number of the output layer nodes and can be adjusted in the interval according to the requirement.
Specifically, the number of input layers and the number of output layers of the BP neural network are determined according to the number of loose bolts and the number of typical stress distortion points, the number of hidden layers can be set to be 1, the number of output layers can be selected to be 3, 6 and 9 according to the number of typical stress distortion points, namely when the number of loose bolts is 1, the number of input layers is 1, and the number of output layers is 3; when the number of loose bolts is 2, the number of input layers is 2, and the number of output layers is 6; when the number of loose bolts is 3, the number of input layers is 3, and the number of output layers is 9
When one bolt and two bolts of the insulator are loosened, namely, the number of input layers is 1 and 2 respectively, the stress value distortion of the corresponding typical stress distortion point is obvious, so that the prediction effect is more obvious.
Specifically, the number of hidden layer nodes is determined according to the number of input and output nodes, the value is determined by the following formula, n is the number of neurons of the input layer, m is the number of neurons of the output layer, and a is [1,10 ]]The constant of the hidden layer node number, the expression of which is:
specifically, determining parameters such as error index, learning rate, relative error and the like of the BP neural network according to requirements;
the learning rate is determined according to the training speed and the loss, and is usually between 0.001 and 0.1, too much learning is difficult to converge, too little training process is greatly increased, and 0.1 is preferably selected; the error index selection range is 10 -5 To 10 -1 The training result is relatively error-large, the training time is long, the BP neural network cannot reach and takes precedenceSelection 10 -5 。
Referring to fig. 2, embodiment 1 of the present invention further provides an insulator surface stress prediction apparatus, including:
the stress detection unit 1 is used for collecting the surface stress of the insulator to be detected;
the ultrasonic detection unit 2 is used for collecting ultrasonic signal values of the surface of the insulator to be detected;
the upper computer 3, stress detection unit 1 with ultrasonic detection unit 2 all with upper computer 3 is connected, upper computer 3 is used for handling stress detection unit 1 with the data that ultrasonic detection unit 2 gathered.
In a specific embodiment, the upper computer 3 includes:
the BP neural network construction unit 31, the BP neural network construction unit 31 is used for establishing the BP neural network, and training the BP neural network by utilizing the surface stress and the ultrasonic signal value under the normal working condition and the bolt loosening working condition;
the BP neural network evaluation unit 32, the BP neural network evaluation unit 32 is for verifying the accuracy of the BP neural network.
Example 2
The method provided by the embodiment 1 of the invention comprises the following specific processes:
the model is selected as 252kV single-phase basin-type insulator, the screw thread specification of a fastening bolt is M16, the standard moment of the bolt is 110 N.M, and the specific steps of simulating actual working conditions are as follows:
(1) In order to simulate the actual working condition of the basin-type insulator, flanges and sealing sleeves are arranged on two sides of the insulator, and strain gauges are reasonably arranged;
(2) Setting the pretightening force of all bolts to be 110 N.M standard pretightening force by using a torque wrench;
(3) Air with the pressure of 0.45MPa is respectively injected into the sealing sleeves at the two sides of the basin-type insulator by using an air compressor;
(4) The ultrasonic transmitting and receiving probes are respectively arranged on two sides of the bolt and used for transmitting and receiving ultrasonic transmission signals, and the energy difference value of the ultrasonic transmission signals is calculated as follows:
ΔE＝E 0 -E 0
wherein E is 0 Transmitting energy for ultrasonic signals of bolts under standard pretightening force, E 1 For transmitting energy of ultrasonic signal when bolt is loosened, f s For the sampling frequency, V is the voltage amplitude.
(5) Respectively collecting ultrasonic transmission signals of the bolts under the conditions of standard pre-tightening force and loosening, collecting stress values of typical stress distortion points of the basin-type insulator, which are in one-to-one correspondence with the loosening conditions of the bolts, and calculating the difference value of the ultrasonic transmission signal energy values under the conditions of loosening of the bolts and the standard pre-tightening force;
(6) After the ultrasonic transmission signal energy difference value when the basin-type insulator bolt is loosened is obtained, further, the ultrasonic transmission signal energy difference value when the basin-type insulator bolt is loosened and the stress value of a typical stress distortion point corresponding to the ultrasonic transmission signal energy difference value one by one are used as training and testing samples of the BP neural network to train the BP neural network.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. The method for predicting the surface stress of the insulator is characterized by comprising the following steps of:
determining working conditions of the insulator, and dividing the working conditions into normal working conditions and working conditions when bolts are loosened;
collecting ultrasonic signal values of the insulator under normal working conditions, and ultrasonic signal values and stress values of the insulator under different loosening working conditions of bolts;
taking the energy difference value and the stress value of the ultrasonic signals under the normal working condition and the bolt loosening working condition as the input value and the output value of the BP neural network, and training the BP neural network to obtain a trained BP neural network;
and verifying the accuracy of the BP neural network.
2. The method for predicting surface stress of an insulator as set forth in claim 1, further comprising: the specific process for verifying the accuracy of the BP neural network is as follows:
comparing absolute errors of the stress measured value and the stress predicted value of the insulator under different loosening working conditions;
and training and correcting the BP neural network, and obtaining the predicted BP neural network when the counter transmission error of the stress measured value and the stress predicted value meets the requirement.
3. The method for predicting surface stress of insulator according to claim 2, wherein the BP neural network correction process comprises: and adjusting the weight and the threshold of the BP neural network by using the back propagation error function to correct, and completing adjustment when the back propagation error function value reaches the minimum.
4. The method for predicting surface stress of insulator according to claim 2, wherein the BP neural network comprises: the ultrasonic transmission signal energy difference value of the insulator loosening bolt is adopted as the input layer, and the stress value of a typical stress distortion point of the basin-type insulator is adopted as the output layer.
5. The method of claim 4, wherein the number of input layers is 1-3 and the number of output layers is 3-9.
6. An insulator surface stress prediction device, comprising:
the device comprises a stress detection unit (1), wherein the stress detection unit (1) is used for collecting the surface stress of an insulator to be tested under a normal working condition and a bolt loosening working condition;
the ultrasonic detection unit (2) is used for collecting surface ultrasonic signal values of the insulator to be detected under a normal working condition and a bolt loosening working condition;
the upper computer (3), the stress detection unit (1) and the ultrasonic detection unit (2) are connected with the upper computer (3), and the upper computer (3) is used for processing data acquired by the stress detection unit (1) and the ultrasonic detection unit (2);
the upper computer (3) comprises:
the BP neural network construction unit (31), the said BP neural network construction unit (31) is used for setting up BP neural network, and utilize surface stress and supersonic signal value in normal working condition and bolt looseness working condition to train the said BP neural network;
-a BP neural network assessment unit (32), the BP neural network assessment unit (32) being adapted to verify the accuracy of the BP neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110518748.0A CN113252218B (en) | 2021-05-12 | 2021-05-12 | Insulator surface stress prediction method and prediction device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110518748.0A CN113252218B (en) | 2021-05-12 | 2021-05-12 | Insulator surface stress prediction method and prediction device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113252218A CN113252218A (en) | 2021-08-13 |
| CN113252218B true CN113252218B (en) | 2023-11-17 |
Family
ID=77223204
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110518748.0A Active CN113252218B (en) | 2021-05-12 | 2021-05-12 | Insulator surface stress prediction method and prediction device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113252218B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005119233A1 (en) * | 2004-06-01 | 2005-12-15 | Cantion A/S | Stress sensor with capture coating for detecting a target substance |
| CN105005822A (en) * | 2015-06-26 | 2015-10-28 | 华能澜沧江水电股份有限公司 | Optimal step length and dynamic model selection based ultrahigh arch dam response prediction method |
| CN105913122A (en) * | 2015-09-09 | 2016-08-31 | 广东技术师范学院 | Finishing axle sleeve surface residual stress prediction method based on hybrid Taguchi genetic algorithm |
| CN106405352A (en) * | 2016-11-16 | 2017-02-15 | 国网河南省电力公司电力科学研究院 | Equivalent salt deposit density (ESDD) prediction and early warning system for power insulator surface contaminant |
| CN108181562A (en) * | 2018-01-18 | 2018-06-19 | 福州大学 | Insulator breakdown diagnostic device and method based on Study On Reliability Estimation Method For Cold Standby Systems |
| CN110207871A (en) * | 2018-02-28 | 2019-09-06 | 新疆金风科技股份有限公司 | Method, apparatus, storage medium and the system of the stress prediction of Wind turbines |
| CN110672312A (en) * | 2019-10-12 | 2020-01-10 | 北京工业大学 | Method for predicting bolt residual clamping force based on BP neural network |
| CN111948286A (en) * | 2020-08-10 | 2020-11-17 | 湖南大学 | Stress detection method, device and equipment based on ultrasonic waves and deep learning |
| WO2021076575A1 (en) * | 2019-10-15 | 2021-04-22 | University Of Pittsburgh - Of The Commonwealth System Of Higher Education | Stress prediction based on neural network |
-
2021
- 2021-05-12 CN CN202110518748.0A patent/CN113252218B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005119233A1 (en) * | 2004-06-01 | 2005-12-15 | Cantion A/S | Stress sensor with capture coating for detecting a target substance |
| CN105005822A (en) * | 2015-06-26 | 2015-10-28 | 华能澜沧江水电股份有限公司 | Optimal step length and dynamic model selection based ultrahigh arch dam response prediction method |
| CN105913122A (en) * | 2015-09-09 | 2016-08-31 | 广东技术师范学院 | Finishing axle sleeve surface residual stress prediction method based on hybrid Taguchi genetic algorithm |
| CN106405352A (en) * | 2016-11-16 | 2017-02-15 | 国网河南省电力公司电力科学研究院 | Equivalent salt deposit density (ESDD) prediction and early warning system for power insulator surface contaminant |
| CN108181562A (en) * | 2018-01-18 | 2018-06-19 | 福州大学 | Insulator breakdown diagnostic device and method based on Study On Reliability Estimation Method For Cold Standby Systems |
| CN110207871A (en) * | 2018-02-28 | 2019-09-06 | 新疆金风科技股份有限公司 | Method, apparatus, storage medium and the system of the stress prediction of Wind turbines |
| CN110672312A (en) * | 2019-10-12 | 2020-01-10 | 北京工业大学 | Method for predicting bolt residual clamping force based on BP neural network |
| WO2021076575A1 (en) * | 2019-10-15 | 2021-04-22 | University Of Pittsburgh - Of The Commonwealth System Of Higher Education | Stress prediction based on neural network |
| CN111948286A (en) * | 2020-08-10 | 2020-11-17 | 湖南大学 | Stress detection method, device and equipment based on ultrasonic waves and deep learning |
Non-Patent Citations (2)
| Title |
|---|
| 基于LSTM循环神经网络的汽轮机转子表面应力预测模型;唐成顺等;《中国电机工程学报》;20200828;第41卷(第2期);全文 * |
| 基于SCADA数据和改进BP神经网络的塔筒应力预测;薛磊等;《噪声与振动控制》;20210218;第41卷(第1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113252218A (en) | 2021-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021098611A1 (en) | Platform for testing leakage current difference factor of aged xlpe cable, and method | |
| CN108413921A (en) | A kind of iron tower in power transmission line material deformation on-line monitoring system and monitoring method | |
| CN104198929A (en) | Detection device and detection method for outdoor high voltage isolator | |
| CN114323375B (en) | GIS basin-type insulator flange stress detection method and system | |
| CN103336259A (en) | Detecting system and method for partial discharge detecting sensor of GIS (gas insulated switchgear) | |
| CN102944745B (en) | 750kV line live-line work insulator tester | |
| CN103576061A (en) | Method for discharge fault diagnosis of transformer | |
| CN107064648A (en) | The detection device and method of the lightning-arrest lead resistance of blower fan pylon based on leakage cable | |
| CN107621591A (en) | A kind of transmission line of electricity iteration distance-finding method based on zero mould traveling wave speed variation characteristic | |
| CN106645404A (en) | Nondestructive testing method and device for basin type insulator curing degree of high-voltage switch equipment | |
| CN113702778B (en) | GIL arc discharge fault positioning method and system | |
| CN104501863A (en) | Composite cross arm stress strain online monitoring system and monitoring method thereof | |
| CN115629130A (en) | Imaging method and system for residual stress of basin-type insulator and test block preparation method | |
| CN113252218B (en) | Insulator surface stress prediction method and prediction device | |
| CN112444705B (en) | Regression correction method for wavelet transformation fault location | |
| CN113156278A (en) | CNN network-based GIS partial discharge positioning method | |
| CN205175640U (en) | Analogue test device of GIS vibration signal characteristic | |
| CN109239525B (en) | Cable radial damage fault simulation evaluation method under split-phase overvoltage | |
| CN108896947B (en) | On-site calibration method and transient voltage measurement method of converter station direct current field transient voltage non-contact measurement device | |
| CN111289837A (en) | Method and system for evaluating latent fault of power distribution network equipment | |
| CN116699304A (en) | GIS partial discharge positioning algorithm based on multi-parameter joint detection | |
| CN105486588A (en) | Nondestructive testing method and apparatus for pressure endurance capability of basin-type insulator | |
| Hou et al. | Discriminant approach to the GIS mechanical fault diagnosis based on the KL divergence of vibration signals | |
| CN106405323A (en) | Single port measurement calibration model based cable sweep frequency positioning analyzing system and method | |
| CN108170964B (en) | Method for calculating potential of grounding body of lightning pole tower |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230902 Address after: No.6 Qingnian Road, Yingze Street, Yingze District, Taiyuan City, Shanxi Province, 030000 Applicant after: STATE GRID ELECTRIC POWER Research Institute OF SEPC Applicant after: Taiyuan University of Technology Address before: 030024 No. 79 West Main Street, Taiyuan, Shanxi, Yingze Applicant before: Taiyuan University of Technology |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information |
Inventor after: Song Jiancheng Inventor after: Jiao Guoxun Inventor after: Wang Wei Inventor after: Xu Yudong Inventor after: Zhang Jie Inventor after: Liu Hong Inventor after: Ge Jian Inventor after: Li Pengjiang Inventor after: Gao Jinwu Inventor before: Song Jiancheng Inventor before: Jiao Guoxun Inventor before: Ge Jian Inventor before: Li Pengjiang Inventor before: Gao Jinwu Inventor before: Zhang Jie |
|
| CB03 | Change of inventor or designer information |