CN113705763A - Real-time detection method and system for distribution network transformer based on neural computing rod - Google Patents
Real-time detection method and system for distribution network transformer based on neural computing rod Download PDFInfo
- Publication number
- CN113705763A CN113705763A CN202010429817.6A CN202010429817A CN113705763A CN 113705763 A CN113705763 A CN 113705763A CN 202010429817 A CN202010429817 A CN 202010429817A CN 113705763 A CN113705763 A CN 113705763A
- Authority
- CN
- China
- Prior art keywords
- transformer
- distribution network
- detection
- real
- positioning
- 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.)
- Granted
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000011897 real-time detection Methods 0.000 title claims abstract description 36
- 230000001537 neural effect Effects 0.000 title claims abstract description 33
- 238000001514 detection method Methods 0.000 claims abstract description 85
- 238000012795 verification Methods 0.000 claims abstract description 16
- 230000008569 process Effects 0.000 claims abstract description 14
- 240000007651 Rubus glaucus Species 0.000 claims abstract description 13
- 235000011034 Rubus glaucus Nutrition 0.000 claims abstract description 13
- 235000009122 Rubus idaeus Nutrition 0.000 claims abstract description 13
- 230000009466 transformation Effects 0.000 claims abstract description 10
- 238000010207 Bayesian analysis Methods 0.000 claims abstract description 8
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims abstract description 7
- 238000004587 chromatography analysis Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 59
- 238000012549 training Methods 0.000 claims description 24
- 238000004458 analytical method Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 12
- 238000005265 energy consumption Methods 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 7
- 238000009792 diffusion process Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 7
- 230000007613 environmental effect Effects 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 6
- 230000002195 synergetic effect Effects 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 230000002238 attenuated effect Effects 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 230000004807 localization Effects 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims 4
- 239000002994 raw material Substances 0.000 claims 4
- 239000007789 gas Substances 0.000 description 56
- 238000012360 testing method Methods 0.000 description 7
- 238000004088 simulation Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 4
- 238000001237 Raman spectrum Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- 230000007423 decrease Effects 0.000 description 3
- 239000001257 hydrogen Substances 0.000 description 3
- 229910052739 hydrogen Inorganic materials 0.000 description 3
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 2
- 238000004057 DFT-B3LYP calculation Methods 0.000 description 2
- OTMSDBZUPAUEDD-UHFFFAOYSA-N Ethane Chemical compound CC OTMSDBZUPAUEDD-UHFFFAOYSA-N 0.000 description 2
- VGGSQFUCUMXWEO-UHFFFAOYSA-N Ethene Chemical compound C=C VGGSQFUCUMXWEO-UHFFFAOYSA-N 0.000 description 2
- 239000005977 Ethylene Substances 0.000 description 2
- 238000001069 Raman spectroscopy Methods 0.000 description 2
- HSFWRNGVRCDJHI-UHFFFAOYSA-N alpha-acetylene Natural products C#C HSFWRNGVRCDJHI-UHFFFAOYSA-N 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 229910002092 carbon dioxide Inorganic materials 0.000 description 2
- 239000001569 carbon dioxide Substances 0.000 description 2
- 229910002091 carbon monoxide Inorganic materials 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 125000002534 ethynyl group Chemical group [H]C#C* 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 150000002431 hydrogen Chemical class 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 150000001335 aliphatic alkanes Chemical class 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000004868 gas analysis Methods 0.000 description 1
- 238000009396 hybridization Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/28—Measuring arrangements characterised by the use of optical techniques for measuring areas
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention discloses a real-time detection method and a real-time detection system for a distribution network transformer based on a neural computing rod, which comprises the steps of collecting a picture of the distribution network transformer to be detected by using a yolo3 target detection strategy, converting the picture into image data, transmitting the image data into an image sensor, carrying out affine transformation and outputting a corresponding actual position; collecting transformer oil characteristic gas in a transformer by using a gas chromatographic analysis method, and fusing a WSMOTE strategy for pretreatment; constructing a positioning model based on a distributed sequential estimation gas leakage source position strategy to detect the actual position of the distribution network transformer and the preprocessed characteristic gas, accelerating the positioning judgment process of the positioning model in real time by combining an AI accelerator, and outputting a positioning result; and importing the positioning result into a Bayesian analysis model for secondary verification and judgment to obtain the position information of the distribution network transformer and displaying the result in real time by using a mobile terminal or a raspberry display. The invention achieves the high-speed AI reasoning arithmetic capability and the low power consumption capability by adopting the neural computing rod of the AI accelerator.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a real-time detection method and a real-time detection system for a distribution network transformer based on a neural computing rod.
Background
In order to realize intelligent management of main power equipment of a transformer substation and guarantee safe and reliable operation of a power system, a power company strengthens a method and means for monitoring operation of the power equipment. At present, massive visible light and infrared images are generated based on vigorous popularization and use of infrared thermal imager live detection, unmanned aerial vehicle routing inspection, video online monitoring and the like, but all problems of main equipment are mainly processed in a manual analysis mode. This approach results in a waste of significant human resources and also results in errors due to lack of objectivity. Therefore, the intelligent identification of the target of the power equipment by using the image identification technology is very necessary for the subsequent fault detection and diagnosis of the power equipment, the mode not only can reduce the manual workload, but also can avoid the misjudgment caused by the artificial detection of a real object, and the aim of improving the detection accuracy is fulfilled.
At present, artificial intelligence is gradually applied in the power industry, for the process of identifying a transformer of a distribution network, the traditional solution is to perform offline identification in an image processing mode but has the problem of poor identification effect, and a deep learning mode is also adopted but a model is deployed on a GPU server, so that the cost is high, the provided online service AI interface can be used under the condition of good network, but the online service AI interface cannot be used under the conditions of no network or high network delay and the like in a specific use scene, so that an embedded device with high portability, low power consumption and small size is urgently needed to be provided to complete the task of identifying the transformer of the distribution network offline in real time.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the invention provides a real-time detection method and a real-time detection system for a distribution network transformer based on a neural computing rod, which can solve the problem that the real-time detection task of the distribution network transformer cannot be completed in an off-line state.
In order to solve the technical problems, the invention provides the following technical scheme: acquiring a distribution network transformer picture to be detected by using a yolo3 target detection strategy, converting the distribution network transformer picture into image data, transmitting the image data into an image sensor, performing affine transformation and outputting a corresponding actual position; collecting transformer oil characteristic gas in a transformer by using a gas chromatographic analysis method, and fusing a WSMOTE strategy for pretreatment; constructing a positioning model based on a distributed sequential estimation gas leakage source position strategy to detect the actual position of the distribution network transformer and the preprocessed characteristic gas, accelerating the positioning judgment process of the positioning model in real time by combining an AI accelerator, and outputting a positioning result; and importing the positioning result into a Bayesian analysis model to perform secondary verification and judgment to obtain the position information of the distribution network transformer, and displaying the result in real time by using a mobile terminal or a raspberry display.
As an optimal scheme of the real-time detection method of the distribution network transformer based on the neural computation rod, the method comprises the following steps: acquiring the distribution network transformer picture and carrying out affine transformation to output the actual position, wherein the step of continuously detecting the sectional area characteristic of the pile head of the transformer by using a camera and carrying out real-time detection by combining the yolo3 target detection strategy; when the sectional area characteristic of the transformer pile head is detected, if the detection result is negative, the characteristic detection is continued, and the detection of the nameplate of the transformer is carried out until the sectional area characteristic of the transformer pile head is detected; when the transformer nameplate is detected, if the detection result is negative, the detection is continued until the transformer nameplate is detected, and then the detection of the environment of the distribution network equipment is carried out; when the distribution network transformer exists or not in the distribution network equipment environment is detected, if the detection result is negative, the action of detecting the cross section area characteristic of the transformer pile head is directly returned and the detection is carried out again, and if the detection result is positive, the action of returning to the coordinate of the transformer pile head is returned; calculating the coordinate of the center point of the transformer pile head bbox, and storing the coordinate values in a point2f format according to the sequence of the collected pictures; and performing radiation transformation on the coordinate values to convert the coordinate values into actual coordinates relative to the distribution network equipment, and calculating a track by using the transformed actual coordinates to obtain the position of the transformer in the distribution network equipment.
As an optimal scheme of the real-time detection method of the distribution network transformer based on the neural computation rod, the method comprises the following steps: calculating the track to train a neural network model in advance, wherein the calculation comprises the steps of collecting the environmental video data of the distribution network equipment by using the camera, converting the environmental video data into picture data of one frame and storing the picture data; generating png pictures with the same size for each frame of picture data, and marking the position of the pile head section of the transformer, the position of a nameplate and the position of the transformer in each electrical device; respectively obtaining 1000 pictures with 1920-1080 resolution and labeled data with the same number, and inputting the pictures into the constructed neural network model; and setting training parameters, and training the neural network model until the trajectory data is accurately output.
As an optimal scheme of the real-time detection method of the distribution network transformer based on the neural computation rod, the method comprises the following steps: preprocessing the characteristic gas comprises marking and dividing the collected transformer oil characteristic gas and constructing a sample data set; generating a classifier by using a weight-based oversampling strategy, and performing N-round iterative training on the classifier; respectively using the sample data sets with different weight distributions in each iteration training, and updating, learning and modifying the sample data sets until a new classifier and a new sample are generated, wherein the new sample is added into the original data set; and when the N rounds of iterative training are finished, all the generated classifiers are integrated together and a processing result is output.
As an optimal scheme of the real-time detection method of the distribution network transformer based on the neural computation rod, the method comprises the following steps: constructing the positioning model comprises constructing a time-averaged gas diffusion model by using a turbulent flow diffusion theory, and simultaneously establishing an observation model of the sensor node at the time t by combining the characteristic that the gas concentration is attenuated along with the increase of the propagation distance; constructing an information fusion objective function by using information gain parameters between sensor nodes and energy consumption parameters of a network communication link, and calculating a distributed minimum mean square error pre-measurement to determine a position parameter of a gas leakage source; and constructing the positioning model based on the information fusion objective function and the yolo3 multi-target detection strategy, and adjusting the size of the adjacent node set in real time according to the mean square error of the pre-measurement.
As an optimal scheme of the real-time detection method of the distribution network transformer based on the neural computation rod, the method comprises the following steps: the positioning model solves the extreme value of an objective function between a current node and an adjacent node thereof to select a routing node; outputting and positioning the position coordinates of the gas leakage source in real time according to the position parameters of the gas leakage source and the trajectory data output by the neural network model; and the AI accelerator accelerates the positioning judgment process of the positioning model in real time and outputs the positioning result.
As an optimal scheme of the real-time detection method of the distribution network transformer based on the neural computation rod, the method comprises the following steps: the secondary verification analysis comprises inputting the positioning result into the Bayesian analysis model; the frequency quantity, the pulse quantity and the gas volatilization quantity of the transformer are subjected to fusion processing and error probability calculation, as follows,
P(Bi|Ai)＝Bi|Aii＝1,2,……n
wherein, Bi: the number of correctly identified characteristic parameters in the ith synergistic analysis factor, Ai: the number of the characteristic parameters identified in the ith synergistic analysis factor; if the probability of the verification result is greater than or equal to 0.5, the positioning result is correct; and if the verification result probability is less than 0.5, the positioning result is wrong.
As an optimal scheme of the real-time detection system of the distribution network transformer based on the neural computation rod, the system comprises the following steps: the device comprises a detection module, a detection module and a control module, wherein the detection module is used for acquiring the distribution network transformer picture and the characteristic gas and comprises a camera and a sensor, the camera is used for detecting and shooting the transformer picture in real time, and the sensor is used for capturing the transformer oil characteristic gas in real time; the image sensing module is connected with the camera and used for acquiring the shot transformer picture, performing characteristic processing on the transformer picture, identifying and converting the transformer picture into image data and transmitting the image data into the core processing module; the core processing module is used for uniformly calculating and processing the image data and the characteristic gas acquired by the detection module, and comprises a data operation unit, a database and an input/output management unit, wherein the data operation unit is used for calculating acquired data information and giving an operation result, the database is used for providing a sample data set for the data operation unit and storing the operation result, and the input/output management unit is used for connecting each unit for information transmission interaction; the AI accelerator is connected with the core processing module and is used for accelerating the operation processing speed of the core processing module and controlling and reducing the energy consumption of the core processing module.
As an optimal scheme of the real-time detection system of the distribution network transformer based on the neural computation rod, the system comprises the following steps: the network module is connected with the core processing module and is used for distributing a network for the core processing module; the power supply module is connected with the core processing module and the network module and is used for supplying power and charging the core processing module and the network module by 5 v; the expansion interface module is connected with the core processing module and is used for expanding an interface for the core processing module.
As an optimal scheme of the real-time detection system of the distribution network transformer based on the neural computation rod, the system comprises the following steps: the AI accelerator is a second-generation nerve computing rod of intel and comprises an openvino platform for optimizing and compressing the positioning model; the network module is a wireless router, is connected with the core processing unit through a network cable to distribute a network and provides WiFi, so that equipment connected with the WiFi accesses the picture real-time detection service provided by the core processing unit.
The invention has the beneficial effects that: the invention achieves the high-speed AI reasoning and operation capability and the low power consumption capability by adopting the neural calculation rod of the AI accelerator, simultaneously carries out coordinate judgment on the acquisition and detection of the transformer image and the gas respectively, then carries out unified integrated positioning on two coordinate judgment results by utilizing a positioning model, finally ensures the accuracy of the positioning result through secondary verification and analysis, and realizes the network-free accurate real-time identification and detection of the transformer under the basic condition of long endurance time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a schematic flow chart of a distribution network transformer real-time detection method based on a neural computation rod according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of a simulation test result of a traditional transformer fault infrared image recognition detection method of a distribution network transformer real-time detection method based on a neural computation rod according to a first embodiment of the present invention;
fig. 3 is a schematic diagram of a simulation test result of a traditional transformer characteristic gas raman spectrum detection method of a distribution network transformer real-time detection method based on a neural computation rod according to a first embodiment of the present invention;
FIG. 4 is a schematic diagram showing a simulation test result of the method for detecting the distribution network transformer in real time based on the neural computation rod according to the first embodiment of the present invention;
fig. 5 is a schematic structural distribution diagram of modules of a distribution network transformer real-time detection system based on a neural computation rod according to a second embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1, a first embodiment of the present invention provides a method for detecting a distribution network transformer in real time based on a neural computing rod, including:
s1: and acquiring a distribution network transformer picture to be detected by using a yolo3 target detection strategy, converting the distribution network transformer picture into image data, transmitting the image data into an image sensor, performing affine transformation, and outputting a corresponding actual position. It should be noted that acquiring a distribution network transformer picture and performing affine transformation to output an actual position includes:
continuously detecting the sectional area characteristics of the pile head of the transformer by using a camera, and carrying out real-time detection by combining a yolo3 target detection strategy;
when the sectional area characteristic of the pile head of the transformer is detected, if the detection result is negative, the characteristic detection is continued, and the detection on the nameplate of the transformer is carried out until the sectional area characteristic of the pile head of the transformer is detected;
when the transformer nameplate is detected, if the detection result is negative, the detection is continued until the transformer nameplate is detected, and then the detection of the environment of the distribution network equipment is carried out;
when the distribution network transformer is detected in the distribution network equipment environment, if the detection result is negative, the action of detecting the sectional area characteristic of the pile head of the transformer is directly returned, the detection is carried out again, and if the detection result is positive, the pile head coordinate of the transformer is returned;
calculating the coordinates of the center point of the transformer pile head bbox, and storing the coordinates in a point2f format according to the sequence of the collected pictures;
and performing radiation transformation on the coordinate values to convert the coordinate values into actual coordinates relative to the distribution network equipment, and calculating a track by using the transformed actual coordinates to obtain the position of the transformer in the distribution network equipment.
Further, the calculation of the trajectory requires training the neural network model in advance, including:
acquiring environmental video data of the distribution network equipment by using a camera, and converting the environmental video data into picture data of one frame for storage;
generating png pictures with the same size for each frame of picture data, and marking the position of the pile head section of the transformer, the position of a nameplate and the position of the transformer in each electrical device;
respectively obtaining 1000 pictures with 1920-1080 resolution and labeled data with the same number, and inputting the pictures into the constructed neural network model;
and setting training parameters, and training the neural network model until the trajectory data is accurately output.
Still further, feature extraction needs to be performed on the image, including:
the input picture is an original picture collected by a camera, the resolution is 1920 x 1080, the number of channels is 3 (r, g and b), and the input picture is input into a neural network preprocessing unit;
carrying out resize processing on the input picture, wherein the resolution of the adjusted image is 512 x 512, and the number of channels is unchanged;
performing convolution operation on the picture, wherein the size of a convolution kernel is 3 x 3, the number of the convolution kernels is 64, the convolution mode is 'same', the size of the original image is unchanged after convolution, and the number of channels is 64;
relu activation operation is carried out on the characteristic image of 512 by 64, then maxporoling with the step size of 2 is carried out, the size of the characteristic image obtained after the pooling is halved, and the number of channels is unchanged.
Further, performing a convolution operation on the extracted feature image, including:
performing convolution operation on the feature map, wherein the size of a convolution kernel is 3 × 3, the number of the convolution kernels is 512, so that a feature map 64 × 512 is obtained, and the convolution operation is repeated for 3 times;
upsampling 64 × 512 feature maps by a scaling factor of 2 in a bilinear manner to obtain 128 × 512 feature maps;
and (4) superposing the feature maps together, wherein the former two dimensions are unchanged during superposition, and the number of the last channels is added to obtain the feature map of 128 × 768.
S2: and (3) collecting transformer oil characteristic gas in the transformer by using a gas chromatographic analysis method, and fusing a WSMOTE strategy for pretreatment. It should be noted that, in this step, the pre-treating the characteristic gas includes:
marking and dividing collected transformer oil characteristic gases (hydrogen, oxygen, methane, ethylene, ethane, acetylene, carbon monoxide and carbon dioxide content full analysis) to construct a sample data set;
generating a classifier by using an oversampling strategy based on the weight, and performing N-round iterative training on the classifier;
respectively using sample data sets with different weight distributions in each iteration training, and updating, learning and modifying the sample data sets until a new classifier and a new sample are generated, wherein the new sample is added into the original data set;
and when the N rounds of iterative training are finished, integrating all the generated classifiers together and outputting a processing result.
Specifically, the iterative training is performed by using a WSMOTE strategy, which comprises the following steps:
(1) initializing parameters, and t is 0;
(2) synthesizing a new sample by utilizing the similarity measurement and the oversampling rate R, constructing a new training set,
Xd＝Xi+δ*(Xa-Xi)
where X ═ X1, X2, …, xm and Y ═ Y1, Y2, …, ym denote two samples, m: number of sample features, Xi: minority samples, Wi: weight of ith feature, Xd: new synthetic sample, Xa: one neighbor of a few samples, δ: random parameters between values (0, 1);
(3) learning the new training set to obtain a base classifier and calculating the weight of the base classifier by using the following formula,
wherein f ist: base classifier at: weight value, et: the feature weight value;
(4) calculating the feature weight according to the classification error rate, updating the existing feature weight, and modifying the sample weight as follows
(5) If T is larger than or equal to T, exiting the iterative training, and calculating by utilizing the weighted combination to obtain a final classifier and outputting a result;
(6) and if T is less than T, re-synthesizing a new sample, constructing a new training set, and continuing the iterative training until the requirements are met, and finishing the iterative training.
S3: and constructing a positioning model based on a distributed sequential estimation gas leakage source position strategy to detect the actual position of the distribution network transformer and the preprocessed characteristic gas, accelerating the positioning judgment process of the positioning model in real time by combining an AI accelerator, and outputting a positioning result. It is further noted that constructing the localization model includes,
a time-averaged gas diffusion model is constructed by using a turbulent diffusion theory, an observation model of the sensor node at the time t is established by combining the characteristic that the gas concentration is attenuated along with the increase of the propagation distance,
Zk(t)＝θk(Xs)+Vk(t)，k＝1,2，……n
wherein, Ck(Xs) Coordinate XkSensor node SkConcentration value of (b), n: total number of sensor nodes in the network, q: gas release rate, k: turbulent diffusion coefficient, U: value of wind speed, θk(Xs): random quantity, V, containing information of the position of the gas leakage sourcek(t): the sensor measures noise;
an information fusion objective function is constructed by using information gain parameters (measured values of a current node and adjacent nodes and position information of a gas leakage source) between sensor nodes and energy consumption parameters (bandwidth, delay, node information acquisition and processing energy consumption and information transmission between nodes) of a network communication link, and a distributed minimum mean square error pre-measurement is calculated to determine a position parameter of the gas leakage source, wherein the method comprises the following steps:
R(Sj,Sk)＝βRi(θk,ZK,Yk)+(1-β)Rc(Sj,Sk)
wherein R isi(θk,ZK,Yk): operating node SjSelecting the next router node SkGain of information, R, generated by timec(Sj,Sk): node SjAnd SkEnergy consumption of communication link between beta is equal to 0,1]The method is a coefficient for balancing the influence of two parameters on an objective function, when beta is 1, the selection of the next routing node is mainly based on information gain and neglects the influence of energy consumption of a communication link, when beta is 0, the selection is mainly based on reducing the energy consumption of the communication link and neglects the influence of the information gain, and Y isk: the current node transmits the noise-containing prediction information to the next routing node;
constructing a positioning model based on an information fusion objective function and a yolo3 multi-target detection strategy, and solving an extreme value of the objective function between a current node and an adjacent node thereof to select a routing node, wherein the positioning model comprises the following steps:
when k is 1, θ is defined1(Xs) And observation noise V1Independent of each other, based on the observed value Z1Node s1The obtained prediction is
Mean square error of
When k > 1, node skIs predicted bykAnd corresponding mean square error MkAre respectively as
Adjusting the size of the adjacent node set in real time by using the predicted mean square error, and eliminating error precision;
outputting and positioning the position coordinates of the gas leakage source in real time according to the position parameters of the gas leakage source and the trajectory data output by the neural network model;
further, the AI accelerator accelerates the positioning judgment process of the positioning model in real time and outputs a positioning result.
Specifically, routing node selection based on a distributed sequential evaluation gas leakage source location strategy includes,
starting initial evaluation prediction operation, activating nodes and receiving prediction information of previous nodes;
updating the prediction quantity and the minimum mean square error of the prediction quantity, inputting a node observation value of the observation model, and judging whether the node observation value reaches a performance index threshold value;
if so, outputting final operation selection result data;
if not, selecting the next routing node from the adjacent node set according to the operation result to transmit the prediction information to the next routing node, adjusting the selection radius of the adjacent node set according to the prediction variance value of the previous node and updating the candidate node set, switching the current node into a sleep mode, and reactivating the node to receive the prediction information of the previous node until the operation result meets the threshold requirement of the performance index.
S4: and importing the positioning result into a Bayesian analysis model for secondary verification and judgment to obtain the position information of the distribution network transformer and displaying the result in real time by using a mobile terminal or a raspberry display. It should be further noted that the secondary verification analysis includes:
inputting the positioning result into a Bayesian analysis model;
the frequency quantity, the pulse quantity and the gas volatilization quantity of the transformer are subjected to fusion processing and error probability calculation, as follows,
P(Bi|Ai)＝Bi|Aii＝1,2,……n
wherein, Bi: the number of correctly identified characteristic parameters in the ith synergistic analysis factor, Ai: the number of the characteristic parameters identified in the ith synergistic analysis factor;
if the probability of the verification result is greater than or equal to 0.5, the positioning result is correct;
and if the probability of the verification result is less than 0.5, the positioning result is wrong.
Preferably, the embodiment also needs to be described in the following description, a detection method for a distribution network transformer generally adopts image recognition or utilizes a characteristic gas to perform equipment fault detection alone, for example, a traditional transformer characteristic gas raman spectrum detection method mainly utilizes a raman scattering effect to directly measure alkane gases and hydrogen in transformer insulating oil and infer the properties and content of substances, and the problem solved by the method is mainly directed to trace detection of complex fault characteristic gas and gas cross interference, but in real life application, the phenomena that a sensor is easy to age, minimum detection concentration analysis is limited, and the accuracy and operability of gas detection are affected; the traditional transformer fault infrared image identification method mainly utilizes a thermal infrared imaging technology to scan images through windows with different sizes, and trains a classification model according to manual shallow image characteristics to finish target classification identification detection, and solves the problems that the adaptability of the characteristic is poor and the running state of equipment is subjectively judged aiming at artificial extraction and description, but in real life application, the shallow image characteristics do not have the property on a semantic level, and the scanning of a whole image consumes a large amount of computing time, and meanwhile, a large amount of repeated phenomena occur in the processing mode, namely, a plurality of overlapped positioning windows exist in the same target part, so that the situations of mistaken image deletion, low detection precision and low efficiency are easily caused; the method combines image recognition detection and characteristic gas detection, and utilizes a positioning model and a Bayesian analysis model to respectively perform primary positioning and secondary verification positioning, so that the accuracy of a recognition result is greatly improved, an AI accelerator is utilized to promote the operation efficiency and balance power consumption in real time, the working efficiency is improved and real-time detection is performed under the conditions of realizing low energy consumption operation and random network switching, and the defects of the two methods when being applied independently are avoided.
In order to better verify and explain the technical effects adopted in the method, the method of the present invention selects the traditional transformer fault infrared image identification and detection method and the traditional transformer characteristic gas raman spectrum detection method to respectively perform the comparison test with the method of the present invention, and compares the test results by means of scientific demonstration to verify the real effects of the method.
In order to verify that the method has higher detection precision, lower power consumption performance, faster operation speed and better real-time performance compared with the two traditional methods, the two traditional methods and the method of the invention are adopted to respectively carry out real-time measurement comparison on the transformer of a certain transformer substation.
And (3) testing conditions are as follows: (1) the traditional transformer fault infrared image identification and detection method needs to perform weighted gray processing and then perform edge detection by using a Canny operator to obtain filtering so as to achieve the purpose of detection by performing subsequent identification and analysis, and adopts infrared thermal images of VS2008, OpenCV and 650 x 590 respectively and uses an MATLB platform for simulation;
(2) a traditional transformer characteristic gas Raman spectrum detection method optimizes a characteristic gas molecular model (hydrogen, carbon monoxide, carbon dioxide, methane, ethane, ethylene and acetylene) based on a density functional B3LYP strategy, utilizes Gaussian software to select a B3LYP hybridization function approximately consisting of three parameters of Becke exchange potential and LYP related potential, analyzes the motion state and the energy level of gas molecules in transformer oil, respectively combines a 270mm 195mm 190mm stainless steel oil gas permeation device, a tubular hollow permeable membrane temperature regulator, a motor and a plunger pump, and utilizes a MATLB platform to simulate;
(3) the method starts automatic test equipment (a camera, a sensor, a raspberry and an AI accelerator), utilizes an MATLB platform to simulate, and obtains simulation data according to an experimental result.
The simulation output results refer to fig. 2, fig. 3 and fig. 4 respectively, fig. 2 is the detection accuracy obtained by the traditional transformer fault infrared image identification detection method under different iteration optimization times, as shown in fig. 2, along with the increase of the detection iteration times, the accuracy fluctuates to some extent and is in an unstable trend, and the accuracy is high and low, so that the detection accuracy does not have good practicability; fig. 3 shows the detection accuracy obtained by the conventional transformer characteristic gas raman spectroscopy detection method under different detection distances and gas concentrations, as shown in fig. 3, the detection accuracy decreases with the decrease of the gas concentration with the increase of the detection distance, and thus it is known that the method does not have a substantial detection research; fig. 4 is a detection method for performing integrated positioning and secondary verification determination according to image recognition at different distance angles and gas analysis at different distance concentrations, and as shown in fig. 4, the detection accuracy does not fluctuate with the change (i.e., increase or decrease) of the gas concentration, and the detection time is not increased with the increase of the detection workload.
Example 2
Referring to fig. 5, a second embodiment of the present invention, which is different from the first embodiment, provides a system for detecting a distribution network transformer in real time based on a neural computation rod, including:
the detection module 100 is used for acquiring distribution network transformer pictures and characteristic gas and comprises a camera 101 and a sensor 102, wherein the camera 101 is used for detecting and shooting transformer pictures in real time, and the sensor 102 is used for capturing the transformer oil characteristic gas in real time;
the image sensing module 200 is connected with the camera 101, and is configured to acquire a photographed transformer picture, perform feature processing on the transformer picture, recognize and convert the transformer picture into image data, and transmit the image data to the core processing module 300;
the core processing module 300 is used for uniformly calculating and processing the image data and the characteristic gas acquired by the detection module 100, and includes a data operation unit 301, a database 302 and an input/output management unit 303, wherein the data operation unit 301 is used for calculating the acquired data information and giving an operation result, the database 302 is used for providing a sample data set and storing the operation result for the data operation unit 301, and the input/output management unit 303 is used for connecting each unit for information transmission interaction;
the AI accelerator 400 is connected to the core processing module 300, and is configured to accelerate the operation processing speed of the core processing module 300 and control and reduce the energy consumption of the core processing module 300;
the network module 500 is connected to the core processing module 300, and is configured to allocate a network to the core processing module 300;
the power supply module 600 is connected to the core processing module 300 and the network module 500, and is configured to supply and charge 5v power to and from the core processing module 300 and the network module 500;
the expansion interface module 700 is connected to the core processing module 300, and is used for expanding an interface for the core processing module 300.
Preferably, a tiny-yolo3 model trained for labeling data pictures through a distribution network transformer is arranged in the detection module 100, the calculated amount is small, and the detection module can run at a mobile end or an equipment end and is deployed on a raspberry group 3B + to provide picture real-time detection service; the core processing module 300 adopts an ARM processing chip, namely raspberry pi 3B +, the raspberry pi 3B + supplies power for 5v voltage, and linux is carried to operate a tensoflow frame; the AI accelerator 400 is a second-generation neural computing rod of intel, and comprises an openvino platform for optimizing and compressing a positioning model; the network module 500 is a wireless router, which is connected to the core processing unit 300 through a network cable to distribute a network and provide WiFi, so that a device connected to WiFi accesses the picture real-time detection service provided by the core processing unit 300; the power supply module 600 adopts a power bank with a large capacity and provides two 5V charging interfaces, so that the raspberry pie can continuously supply power for a long time in a low-power-consumption state.
Preferably, this embodiment also shows that the process of detecting the distribution network transformer in real time by the system of the present invention is as follows:
the method comprises the steps that a camera 101 is used for collecting photos in real time, and each frame of image is sent to a raspberry group through an image sensor for preprocessing;
the sensor 102 collects characteristic gas of the transformer oil in real time and transmits the characteristic gas to a raspberry group for pretreatment;
the data operation unit 301 reads the preprocessed characteristic gas data and image data and performs analysis operation on the characteristic gas data and the image data, and meanwhile, the AI accelerator 400 is connected with the raspberry pi through the USB port of the image sensing module 200 and supports the data operation unit 301 to accelerate operation processing;
the input/output management unit 303 outputs the position information of the distribution network transformer and returns the position information to the terminal or the raspberry display connected to the network module 500 to display the result.
It should be recognized that embodiments of the present invention can be realized and implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein. A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.
As used in this application, the terms "component," "module," "system," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution. For example, a component may be, but is not limited to being: a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of example, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and/or thread of execution and a component can be localized on one computer and/or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures thereon. The components may communicate by way of local and/or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and/or across a network such as the internet with other systems by way of the signal).
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (10)
1. A real-time detection method for a distribution network transformer based on a neural computing rod is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
acquiring a distribution network transformer picture to be detected by using a yolo3 target detection strategy, converting the distribution network transformer picture into image data, transmitting the image data into an image sensor, performing affine transformation, and outputting a corresponding actual position;
collecting transformer oil characteristic gas in a transformer by using a gas chromatographic analysis method, and fusing a WSMOTE strategy for pretreatment;
constructing a positioning model based on a distributed sequential estimation gas leakage source position strategy to detect the actual position of the distribution network transformer and the preprocessed characteristic gas, accelerating the positioning judgment process of the positioning model in real time by combining an AI accelerator, and outputting a positioning result;
and importing the positioning result into a Bayesian analysis model to perform secondary verification and judgment to obtain the position information of the distribution network transformer, and displaying the result in real time by using a mobile terminal or a raspberry display.
2. The method for detecting the distribution network transformer in real time based on the neural computation rod as claimed in claim 1, wherein the method comprises the following steps: acquiring the distribution network transformer picture, carrying out affine transformation and outputting the actual position,
continuously detecting the sectional area characteristics of the pile head of the transformer by using a camera, and carrying out real-time detection by combining the yolo3 target detection strategy;
when the sectional area characteristic of the transformer pile head is detected, if the detection result is negative, the characteristic detection is continued, and the detection of the nameplate of the transformer is carried out until the sectional area characteristic of the transformer pile head is detected;
when the transformer nameplate is detected, if the detection result is negative, the detection is continued until the transformer nameplate is detected, and then the detection of the environment of the distribution network equipment is carried out;
when the distribution network transformer exists or not in the distribution network equipment environment is detected, if the detection result is negative, the action of detecting the cross section area characteristic of the transformer pile head is directly returned and the detection is carried out again, and if the detection result is positive, the action of returning to the coordinate of the transformer pile head is returned;
calculating the coordinate of the center point of the transformer pile head bbox, and storing the coordinate values in a point2f format according to the sequence of the collected pictures;
and performing radiation transformation on the coordinate values to convert the coordinate values into actual coordinates relative to the distribution network equipment, and calculating a track by using the transformed actual coordinates to obtain the position of the transformer in the distribution network equipment.
3. The method for detecting the distribution network transformer in real time based on the neural computation rod as claimed in claim 1 or 2, wherein: the calculation of the trajectory requires training a neural network model in advance, including,
acquiring the environmental video data of the distribution network equipment by using the camera, and converting the environmental video data into picture data of one frame for storage;
generating png pictures with the same size for each frame of picture data, and marking the position of the pile head section of the transformer, the position of a nameplate and the position of the transformer in each electrical device;
respectively obtaining 1000 pictures with 1920-1080 resolution and labeled data with the same number, and inputting the pictures into the constructed neural network model;
and setting training parameters, and training the neural network model until the trajectory data is accurately output.
4. The real-time detection method for the distribution network transformer based on the neural computation rod as claimed in claim 3, wherein: pre-processing the characteristic gas includes pre-processing the characteristic gas,
marking and dividing the collected transformer oil characteristic gas to construct a sample data set;
generating a classifier by using a weight-based oversampling strategy, and performing N-round iterative training on the classifier;
respectively using the sample data sets with different weight distributions in each iteration training, and updating, learning and modifying the sample data sets until a new classifier and a new sample are generated, wherein the new sample is added into the original data set;
and when the N rounds of iterative training are finished, all the generated classifiers are integrated together and a processing result is output.
5. The real-time detection method for the distribution network transformer based on the neural computation rod as claimed in claim 4, wherein: constructing the localization model includes constructing the localization model by,
a time-averaged gas diffusion model is constructed by using a turbulent diffusion theory, and an observation model of the sensor node at the time t is established by combining the characteristic that the gas concentration is attenuated along with the increase of the propagation distance;
constructing an information fusion objective function by using information gain parameters between sensor nodes and energy consumption parameters of a network communication link, and calculating a distributed minimum mean square error pre-measurement to determine a position parameter of a gas leakage source;
and constructing the positioning model based on the information fusion objective function and the yolo3 multi-target detection strategy, and adjusting the size of the adjacent node set in real time according to the mean square error of the pre-measurement.
6. The real-time detection method for the distribution network transformer based on the neural computation rod as claimed in claim 5, wherein: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
the positioning model solves the extreme value of an objective function between the current node and the adjacent node to select a routing node;
outputting and positioning the position coordinates of the gas leakage source in real time according to the position parameters of the gas leakage source and the trajectory data output by the neural network model;
and the AI accelerator accelerates the positioning judgment process of the positioning model in real time and outputs the positioning result.
7. The method for detecting the distribution network transformer in real time based on the neural computation rod as claimed in claim 6, wherein: the secondary verification analysis includes the steps of,
inputting the positioning result into the Bayesian analysis model;
the frequency quantity, the pulse quantity and the gas volatilization quantity of the transformer are subjected to fusion processing and error probability calculation, as follows,
P(Bi|Ai)＝Bi|Aii＝1,2,……n
wherein, Bi: the number of correctly identified characteristic parameters in the ith synergistic analysis factor, Ai: the number of the characteristic parameters identified in the ith synergistic analysis factor;
if the probability of the verification result is greater than or equal to 0.5, the positioning result is correct;
and if the verification result probability is less than 0.5, the positioning result is wrong.
8. The utility model provides a join in marriage net transformer real-time detection system based on neural stick that calculates which characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
the detection module (100) is used for acquiring the distribution network transformer picture and the characteristic gas and comprises a camera (101) and a sensor (102), the camera (101) is used for detecting and shooting the transformer picture in real time, and the sensor (102) is used for capturing the transformer oil characteristic gas in real time;
the image sensing module (200) is connected with the camera (101) and is used for acquiring the shot transformer picture, performing characteristic processing on the transformer picture, identifying and converting the transformer picture into image data and transmitting the image data to the core processing module (300);
the core processing module (300) is used for uniformly calculating and processing the image data and the characteristic gas acquired by the detection module (100), and comprises a data operation unit (301), a database (302) and an input/output management unit (303), wherein the data operation unit (301) is used for calculating acquired data information and giving an operation result, the database (302) is used for providing a sample data set for the data operation unit (301) and storing the operation result, and the input/output management unit (303) is used for connecting each unit for information transmission interaction;
the AI accelerator (400) is connected to the core processing module (300) and is used for accelerating the operation processing speed of the core processing module (300) and controlling and reducing the energy consumption of the core processing module (300).
9. The system of claim 8, wherein the system comprises: also comprises the following steps of (1) preparing,
the network module (500) is connected with the core processing module (300) and is used for distributing a network for the core processing module (300);
a power supply module (600) connected to the core processing module (300) and the network module (500) for 5v powering and charging the core processing module (300) and the network module (500);
the expansion interface module (700) is connected with the core processing module (300) and is used for expanding an interface for the core processing module (300).
10. The system of claim 9, wherein the real-time detection system comprises: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
the AI accelerator (400) is a second-generation neural computing rod of intel and comprises an openvino platform for optimizing and compressing the positioning model;
the network module (500) is a wireless router, and is connected with the core processing unit (300) through a network cable to distribute a network and provide WiFi, so that the equipment connected with WiFi accesses the picture real-time detection service provided by the core processing unit (300).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010429817.6A CN113705763B (en) | 2020-05-20 | 2020-05-20 | Real-time detection method and system for distribution network transformer based on nerve computation stick |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010429817.6A CN113705763B (en) | 2020-05-20 | 2020-05-20 | Real-time detection method and system for distribution network transformer based on nerve computation stick |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113705763A true CN113705763A (en) | 2021-11-26 |
| CN113705763B CN113705763B (en) | 2024-02-20 |
Family
ID=78645500
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010429817.6A Active CN113705763B (en) | 2020-05-20 | 2020-05-20 | Real-time detection method and system for distribution network transformer based on nerve computation stick |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113705763B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11631238B1 (en) * | 2022-04-13 | 2023-04-18 | Iangxi Electric Power Research Institute Of State Grid | Method for recognizing distribution network equipment based on raspberry pi multi-scale feature fusion |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201402257Y (en) * | 2009-02-20 | 2010-02-10 | 国网电力科学研究院 | Gas content on-line monitoring system in transformer oil |
| CN101701940A (en) * | 2009-10-26 | 2010-05-05 | 南京航空航天大学 | On-line transformer fault diagnosis method based on SVM and DGA |
| CN106052962A (en) * | 2016-05-13 | 2016-10-26 | 重庆大学 | Gas source positioning technology in wireless sensor network without wind speed and wind direction measuring |
| US20170016796A1 (en) * | 2015-07-15 | 2017-01-19 | Hitachi, Ltd. | Leakage Oil Detection System |
| CN107063349A (en) * | 2017-04-17 | 2017-08-18 | 云南电网有限责任公司电力科学研究院 | A kind of method and device of Fault Diagnosis Method of Power Transformer |
| CN107332898A (en) * | 2017-06-27 | 2017-11-07 | 中国矿业大学(北京) | A kind of mine gas source of release localization method of Multiple Source Sensor fusion |
| CN109101906A (en) * | 2018-07-27 | 2018-12-28 | 中国南方电网有限责任公司超高压输电公司贵阳局 | A kind of converting station electric power equipment infrared image exception real-time detection method and device |
| CN109711437A (en) * | 2018-12-06 | 2019-05-03 | 武汉三江中电科技有限责任公司 | A kind of transformer part recognition methods based on YOLO network model |
| CN109856299A (en) * | 2018-11-26 | 2019-06-07 | 国家电网有限公司 | A kind of transformer online monitoring differentiation threshold value dynamic setting method, system |
| US20190302169A1 (en) * | 2018-03-30 | 2019-10-03 | Wuhan University | Nonlinear model transformation solving and optimization method for partial discharge positioning based on multi-ultrasonic sensor |
| CN110705395A (en) * | 2019-09-18 | 2020-01-17 | 北京邮电大学 | Detection system based on raspberry group |
-
2020
- 2020-05-20 CN CN202010429817.6A patent/CN113705763B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201402257Y (en) * | 2009-02-20 | 2010-02-10 | 国网电力科学研究院 | Gas content on-line monitoring system in transformer oil |
| CN101701940A (en) * | 2009-10-26 | 2010-05-05 | 南京航空航天大学 | On-line transformer fault diagnosis method based on SVM and DGA |
| US20170016796A1 (en) * | 2015-07-15 | 2017-01-19 | Hitachi, Ltd. | Leakage Oil Detection System |
| CN106052962A (en) * | 2016-05-13 | 2016-10-26 | 重庆大学 | Gas source positioning technology in wireless sensor network without wind speed and wind direction measuring |
| CN107063349A (en) * | 2017-04-17 | 2017-08-18 | 云南电网有限责任公司电力科学研究院 | A kind of method and device of Fault Diagnosis Method of Power Transformer |
| CN107332898A (en) * | 2017-06-27 | 2017-11-07 | 中国矿业大学(北京) | A kind of mine gas source of release localization method of Multiple Source Sensor fusion |
| US20190302169A1 (en) * | 2018-03-30 | 2019-10-03 | Wuhan University | Nonlinear model transformation solving and optimization method for partial discharge positioning based on multi-ultrasonic sensor |
| CN109101906A (en) * | 2018-07-27 | 2018-12-28 | 中国南方电网有限责任公司超高压输电公司贵阳局 | A kind of converting station electric power equipment infrared image exception real-time detection method and device |
| CN109856299A (en) * | 2018-11-26 | 2019-06-07 | 国家电网有限公司 | A kind of transformer online monitoring differentiation threshold value dynamic setting method, system |
| CN109711437A (en) * | 2018-12-06 | 2019-05-03 | 武汉三江中电科技有限责任公司 | A kind of transformer part recognition methods based on YOLO network model |
| CN110705395A (en) * | 2019-09-18 | 2020-01-17 | 北京邮电大学 | Detection system based on raspberry group |
Non-Patent Citations (4)
| Title |
|---|
| MANAS RANJAN PRUSTY等: "Weighted-SMOTE: A modification to SMOTE for event classification in sodium cooled fast reactors", 《PROGRESS IN NUCLEAR ENERGY》, pages 355 - 364 * |
| 洪浪: "基于油气量和超高频局放信号的变压器故障诊断研究", 《中国优秀硕士学位论文全文数据库（电子期刊）》, pages 042 - 271 * |
| 王伦宾: "基于分布传感技术的变压器油色谱在线监测技术应用研究", 《中国优秀硕士学位论文全文数据库（电子期刊）》, pages 042 - 47 * |
| 郭玉萱: "基于不平衡数据分类的中药肝毒性检测", 《计算应用与软件》, vol. 35, no. 8, pages 226 - 230 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11631238B1 (en) * | 2022-04-13 | 2023-04-18 | Iangxi Electric Power Research Institute Of State Grid | Method for recognizing distribution network equipment based on raspberry pi multi-scale feature fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113705763B (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109117731B (en) | Classroom teaching cognitive load measurement system | |
| CN103324937B (en) | The method and apparatus of label target | |
| CN104573706A (en) | Object identification method and system thereof | |
| CN113252701B (en) | Cloud edge cooperation-based power transmission line insulator self-explosion defect detection system and method | |
| CN110738132B (en) | Target detection quality blind evaluation method with discriminant perception capability | |
| CN114332578A (en) | Image anomaly detection model training method, image anomaly detection method and device | |
| CN111598942A (en) | Method and system for automatically positioning electric power facility instrument | |
| Wang | An improved machine learning and artificial intelligence algorithm for classroom management of English distance education | |
| CN115311618A (en) | Assembly quality inspection method based on deep learning and object matching | |
| CN114092697A (en) | Building facade semantic segmentation method with attention fused with global and local depth features | |
| CN114049515A (en) | Image classification method, system, electronic device and storage medium | |
| CN113705763B (en) | Real-time detection method and system for distribution network transformer based on nerve computation stick | |
| CN110909889A (en) | Training set generation and model training method and device based on feature distribution | |
| Kalash et al. | Relative saliency and ranking: Models, metrics, data and benchmarks | |
| CN112861809B (en) | Classroom head-up detection system based on multi-target video analysis and working method thereof | |
| KR20210142864A (en) | Apparatus and method for recognizing number of measuring intrument | |
| CN111161238A (en) | Image quality evaluation method and device, electronic device, and storage medium | |
| CN114387524B (en) | Image identification method and system for small sample learning based on multilevel second-order representation | |
| CN114821322A (en) | Small sample remote sensing image classification method and system based on attention mechanism | |
| CN109583513B (en) | Method, system and device for detecting similar frame and readable storage medium | |
| CN113627271A (en) | Mobile rock mineral rapid intelligent identification method | |
| Pu et al. | AutoRepo: A general framework for multi-modal LLM-based automated construction reporting | |
| CN113723536A (en) | Power inspection target identification method and system | |
| Dierenbach et al. | Next-Best-View method based on consecutive evaluation of topological relations | |
| Brander et al. | Improving Data-Scarce Image Classification Through Multimodal Synthetic Data Pretraining |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |