CN112332541A - Monitoring system and method for transformer substation - Google Patents
Monitoring system and method for transformer substation Download PDFInfo
- Publication number
- CN112332541A CN112332541A CN202011180479.3A CN202011180479A CN112332541A CN 112332541 A CN112332541 A CN 112332541A CN 202011180479 A CN202011180479 A CN 202011180479A CN 112332541 A CN112332541 A CN 112332541A
- Authority
- CN
- China
- Prior art keywords
- module
- substation
- learning
- data
- monitoring
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000007689 inspection Methods 0.000 claims abstract description 73
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 238000013507 mapping Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 7
- 230000005236 sound signal Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 4
- 238000001931 thermography Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 abstract description 12
- 230000007547 defect Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 230000009466 transformation Effects 0.000 description 6
- 230000004927 fusion Effects 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 239000013589 supplement Substances 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 230000000875 corresponding effect Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000001351 cycling effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 231100000817 safety factor Toxicity 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
- H02J13/00022—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using wireless data transmission
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
- H02J13/00034—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving an electric power substation
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
-
- 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
- Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
- Y04S40/12—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment
- Y04S40/126—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment using wireless data transmission
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a monitoring system and a monitoring method for a transformer substation, which comprise a plurality of inspection robots, a supply station, a central control station and a supervision platform, wherein an acquisition module is wirelessly connected with the central control station and the supply station and is used for acquiring data near a monitoring point of the transformer substation for the inspection robots; the supply station and the central control station are arranged near the monitoring point of the transformer substation; the processing module is used for preprocessing, matching and identifying the data acquired by the acquisition module; sample data is preset in the storage module; the analysis module is connected with the alarm module and is used for comparing the data processed by the processing module with the sample data; the alarm module is wirelessly connected with the supervision platform; the learning module is used for updating and perfecting the sample. The method has the advantages of autonomously updating learning capacity, expanding monitoring protection, reasonably predicting and predicting outside the range of sample data, and timely finding abnormal or suspected abnormal substation equipment data or images, thereby providing more effective guarantee for the substation.
Description
Technical Field
The invention relates to the technical field of transformer substation monitoring, in particular to a monitoring system and a monitoring method for a transformer substation.
Background
The inspection cost of substation personnel is high, the unattended operation is gradually realized at present, and the CN108890652A discloses a substation inspection robot and a substation equipment inspection method, wherein the moving path adjustment is carried out by combining an image acquired by the inspection robot, so that the accuracy of acquiring an equipment inspection target image can be improved, and the accuracy of an inspection identification result is ensured; although high-quality image information can be obtained, automatic identification of partial faults is difficult, and manual identification is also needed. CN10683301A discloses an effective transformer substation intelligence inspection robot, through the construction connection of each module, realizes the intellectuality and unmanned monitoring of transformer substation. However, moving objects, environmental conditions or other uncertain factors near the monitoring point of the transformer substation cannot be effectively mastered and identified, and equipment or environmental hidden dangers are difficult to find in time.
Disclosure of Invention
In order to overcome the defects, the invention aims to provide a monitoring system and a monitoring method for a transformer substation, which monitor transformer substation monitoring points in an all-dimensional and multi-view manner by presetting sample data and a learning module in a patrol robot, find abnormal or suspected abnormal transformer substation equipment in time and perform early warning.
In order to achieve the purpose, the invention adopts the following technical scheme:
a monitoring system for a transformer substation comprises a plurality of inspection robots, a supply station, a central control station and a supervision platform, wherein each inspection robot comprises an acquisition module, a processing module, a learning module, an analysis module, a storage module and an alarm module which are connected with one another; the acquisition module is wirelessly connected with the central control station and the supply station and is used for acquiring data near a monitoring point of the transformer substation for the inspection robot; the supply station and the central control station are arranged near the monitoring point of the transformer substation; the processing module is used for preprocessing, matching and identifying the data acquired by the acquisition module; sample data is preset in the storage module; the analysis module is connected with the alarm module and is used for comparing the data processed by the processing module with the sample data; the alarm module is wirelessly connected with the supervision platform; the learning module is used for updating and perfecting the sample.
Optionally, the acquisition module includes a video camera, a thermal imaging camera, an ultraviolet camera, an audio signal acquisition device, and a signal receiver and transmitter.
Optionally, still be provided with laser radar and a plurality of distance sensor on patrolling and examining the robot, distance sensor distributes patrolling and examining the different positions of robot.
Optionally, the supervision platform is provided with a database, a display terminal and a second alarm module; the database is wirelessly connected with the storage module, and the second alarm module is wirelessly connected with the alarm module; and the display terminal is connected with the database and the second alarm module.
The invention also discloses a method for the monitoring system of the transformer substation, which comprises the following steps:
surveying and mapping monitoring points of the transformer substation and the surrounding environment, and constructing a map;
presetting sample data and a learning module for the inspection robot;
setting a supply station and a patrol stop point in a map;
arranging a central control station and a supervision platform outside a map;
and presetting detection time and intervals, and acquiring data.
Optionally, the mapping the substation monitoring points and the surrounding environment, and the map building includes the steps of:
manually controlling the inspection robot to walk for a circle along the edge of the map to be constructed;
scanning the edge area by a laser radar;
recording edge scenes through a video camera;
a closed map is constructed.
Optionally, the module for presetting sample data and learning for the inspection robot comprises the following steps:
storing sample data of the substation equipment in normal work and fault in a storage module;
extracting sample data as a training sample, preprocessing the training sample and extracting characteristics to obtain an observation sequence;
establishing learning module parameters and storing initial values of the parameters;
reestimating the initial values of the learning module parameters according to the observation sequence to complete training;
storing the reestimated learning model parameters;
extracting the characteristics of the test sample, and calculating the output probability of the observation sequence under each learning model parameter according to the learning model parameters;
and saving the learning model with the maximum output probability.
The most main mode of transformer substation inspection is manual inspection, but inspection cost is high based on personnel, inspection state is unstable, so that some transformer substations gradually realize unattended operation, but moving objects, environment states or other safety factors near monitoring points of the transformer substations cannot be effectively mastered and identified, and thus some external factors may influence normal operation and safety of the transformer substations. Due to the fact that the inspection robot is single in function and insufficient in intellectualization, equipment or environment hidden dangers are difficult to find in time, operation and maintenance personnel are generally required to conduct remote abnormity inspection and defect finding on images acquired by the inspection robot, the inspection robot does not have the automatic detection capability on defects such as equipment appearance, a large number of inspection images need to be manually distinguished, and inspection efficiency is reduced; on the other hand, the video image data of the transformer substation is huge, the background processing speed is low, the remote transmission speed is limited, the requirements of timely response and real-time analysis and processing cannot be met, and the effect is limited. Even if some sample data of normal and abnormal equipment is preset, some other uncertain factors exist, and the machine may ignore such hidden troubles, thereby causing loss.
The invention has the following positive beneficial effects:
the invention is provided with a plurality of inspection robots to monitor the transformer substation monitoring points in all directions and in multiple visual angles, monitoring and shift changing are carried out for 24 hours in turn to supplement electric energy, the supply stations are arranged in the transformer substation monitoring points, and the inspection robots can enter the supply stations in turn or simultaneously to charge and supplement energy or carry out other supplies; the central control station is arranged near the monitoring point of the transformer substation, so that the inspection robot can be conveniently and artificially controlled to move, and work such as debugging, surveying and mapping can be carried out. The inspection robot comprises an acquisition module, a processing module, a learning module, an alarm module and a monitoring platform, wherein the acquisition module of the inspection robot is used for acquiring data or image information of a monitoring point of a transformer substation and nearby, the processing module is used for preprocessing, matching and identifying the data acquired by the acquisition module and improving monitoring precision, the processing module is used for carrying out comparison analysis according to sample data preset in a storage module and determining whether to trigger the alarm module, the learning module is used for updating and perfecting the sample data based on theories such as edge calculation, depth increment learning and the like, the sample data has the self-updating learning capability, monitoring protection is enlarged, processing efficiency is improved, reasonable prejudgment conjecture can be carried out outside the range of the sample data, and abnormal or suspected abnormal transformer substation equipment data or images are found in time, so that the; and more effective guarantee is provided for the transformer substation.
Drawings
Fig. 1 is a schematic structural framework diagram of a monitoring system for a substation provided in embodiment 1 of the present invention;
FIG. 2 is a schematic diagram of a deep incremental learning framework provided in embodiment 1 of the present invention;
FIG. 3 is a schematic structural diagram of image fusion provided in embodiment 1 of the present invention;
fig. 4 is a schematic structural diagram of a ResNet series algorithm provided in embodiment 1 of the present invention;
fig. 5 is a schematic diagram of a method for a monitoring system of a substation according to embodiment 2 of the present invention;
fig. 6 is a schematic diagram of a method for mapping a monitoring point of a substation and a surrounding environment and constructing a map according to embodiment 2 of the present invention;
fig. 7 is a schematic diagram of a method for presetting sample data and a learning module for an inspection robot according to embodiment 2 of the present invention.
Detailed Description
The invention will be further illustrated with reference to some specific embodiments.
Example 1
As shown in fig. 1, a monitoring system for a transformer substation comprises a plurality of inspection robots, a supply station, a central control station and a supervision platform, wherein each inspection robot comprises an acquisition module, a processing module, a learning module, an analysis module, a storage module and an alarm module which are connected with one another; the acquisition module is wirelessly connected with the central control station and the supply station and is used for acquiring data near a monitoring point of the transformer substation for the inspection robot; the supply station and the central control station are arranged near the monitoring point of the transformer substation; the processing module is used for preprocessing, matching and identifying the data acquired by the acquisition module; sample data is preset in the storage module; the analysis module is connected with the alarm module and is used for comparing the data processed by the processing module with the sample data; the alarm module is wirelessly connected with the supervision platform; the learning module is used for updating and perfecting the sample.
The general inspection and inspection screen monitoring needs operation and maintenance personnel to perform abnormal inspection and defect searching, does not have the detection capability on the defects such as equipment appearance and the like, a large number of inspection images need manual screening, and due to the problems of insufficient image quality and image analysis level, the equipment hidden danger is difficult to effectively find, and the monitoring efficiency is low; in the embodiment, a plurality of inspection robots are arranged so as to monitor the transformer substation monitoring points in an omnibearing and multi-view manner, shift change is monitored in turn for 24 hours to supplement electric energy, a replenishment station is arranged in the transformer substation monitoring points, and the inspection robots can enter the replenishment station in turn or simultaneously to charge and supplement energy or perform other replenishment; the central control station is arranged near the monitoring point of the transformer substation, so that the inspection robot can be conveniently and artificially controlled to move, and work such as debugging, surveying and mapping can be carried out. The inspection robot comprises an acquisition module, a processing module, a learning module, a monitoring module and a monitoring platform, wherein the acquisition module of the inspection robot is used for acquiring data or image information of a monitoring point of a transformer substation and nearby, the processing module is used for preprocessing, matching and identifying the data acquired by the acquisition module and improving monitoring precision, the processing module is used for carrying out comparison analysis according to sample data preset in a storage module and determining whether to trigger an alarm module, the learning module is used for updating and perfecting the sample data based on theories such as edge calculation, depth increment learning and the like, monitoring protection is enlarged, processing efficiency is improved, reasonable prejudgment and speculation can be carried out outside the range of the sample data, abnormal or suspected abnormal transformer substation equipment data or images are found in time, and the analysis module triggers; and more effective guarantee is provided for the transformer substation.
Deep incremental learning is an automatic supervision learning method, which not only has strong perception capability of deep learning, but also has decision-making capability of incremental learning. As shown in fig. 2, the specific process is (1) at each moment, the learning module interacts with the environment to obtain a high-dimensional observation, and the observation is sensed by using a deep learning method to obtain a specific state feature representation; (2) evaluating a value function of each action based on expected returns, and mapping the current state into a corresponding action through a certain strategy; (3) the environment reacts to this action and gets the next observation. By continuously cycling the above processes, the optimal strategy for achieving the target can be finally obtained.
The acquisition module comprises a video camera, a thermal imaging camera, an ultraviolet camera, audio signal acquisition equipment, a signal receiver and a transmitter. And a multi-vision image fusion technology is adopted, and a visible light image shot by a video camera and a non-visible light image shot by a thermal imaging camera are automatically synthesized through an artificial intelligence technology. Because many devices in the substation are difficult to realize high-precision target defect detection by only using a visible light camera. Under severe or extreme conditions, the non-visible light camera is adopted to greatly improve the visual identification degree of the image, and further improve the accuracy of automatic tracking and positioning of the defect target of the power transformation equipment. The ultraviolet camera can identify short-wavelength light emitted by the power transformation equipment and generate a corresponding image for the analysis module and the processing module to identify and judge whether the short-wavelength light is abnormal or not; a multi-resolution tower type image fusion algorithm is adopted. In this type of algorithm, the original image is continuously filtered, forming a tower-like structure, as shown in fig. 3. The data of each layer of the tower is fused by a fusion algorithm, so that a composite tower structure is obtained. And then reconstructing the synthesized tower structure to obtain a synthesized image. The purpose of the LaPlacian tower decomposition is to decompose an original image into different spatial frequency bands respectively, and different fusion operators are respectively adopted to perform fusion processing on different decomposition layers with different spatial resolutions by utilizing the decomposed tower structure, so that features and details from different images can be effectively fused together.
Meanwhile, the audio signal acquisition equipment can identify whether the transformer substation equipment with the audio signals is abnormal or not, such as audio information of equipment such as a protection screen, a communication screen, a battery cabinet and a background machine, and signals sent by the equipment are mainly discharge sound signals.
In order to adapt to complex scenes, a representative algorithm-RseNet in a convolutional neural network is adopted to extract the characteristics of the defect image of the power transformation equipment under the complex background. As shown in fig. 4, by adding identity mapping layer and identity mapping layer in the conventional neural network
To replace the function to be learned
The two methods have the same goal, except for the difficulty in optimizing the two methods,
is optimized and
the optimization is less difficult. When residual vector coding is used in image processing, a problem is divided into a plurality of mutually related residual problems by information reorganizationThe aim of optimizing training can be achieved. The process of extracting the defect image features of the power transformation equipment under the complex background by applying ResNet is as follows: (1) firstly, inputting a large number of power transformation equipment defect images into an input layer of ResNet one by one for preprocessing, wherein the input images are used as the input of a whole neural network model, and the size of the input images is fixed; (2) performing convolution calculation on an input image and a corresponding convolution kernel layer by layer according to a network architecture of ResNet to obtain a multi-dimensional feature map; (3) and connecting the multi-dimensional characteristic graph with the fully-connected network, and calculating the difference between the forward calculation result and the expected result through a loss function. (4) Parameters within the convolution kernel are updated back by a back propagation algorithm depending on the difference between the forward computed result and the expected result. (5) And (4) repeating the steps (2) to (4) until the forward calculation obtains an ideal result, and stopping the iteration process. After the trained ResNet model is obtained, inputting the to-be-detected transformer equipment defect image into the ResNet model, and obtaining the defect characteristics in the image through a series of convolution calculations.
Still be provided with laser radar and a plurality of distance sensor on patrolling and examining the robot, distance sensor distributes patrolling and examining the different positions of robot. Because the routing inspection route or the track is not arranged in the map, the routing inspection robot is in a free routing inspection state in a time period after fixed-point detection is finished, and because factors such as a visual field blind area, movement of some uncertain moving objects and the like exist, distance sensors are respectively arranged in different directions, and collision and damage are prevented.
The monitoring platform is provided with a database, a display terminal and a second alarm module; the database is wirelessly connected with the storage module; the second alarm module is in wireless connection with the alarm module; and the display terminal is connected with the database and the second alarm module. The supervision platform supervises all substations, the database is arranged, data information such as all substations, the inspection robots and historical samples is stored, operation and maintenance personnel can call information in the database to check, analyze and position the information through the display terminal, new appearing data or historical data in the database are analyzed, sample data can be updated through the data, the alarm module can trigger the second alarm module of the supervision platform, and therefore the operation and maintenance personnel can be quickly reminded to check, analyze, position and timely process the information, and potential safety hazards are solved.
Example 2
As shown in fig. 5, a method for a monitoring system of the substation is disclosed, comprising the steps of:
s1, surveying and mapping the transformer substation monitoring points and the surrounding environment, and constructing a map;
s2, presetting sample data and a learning module for the inspection robot;
s3, setting a supply station and a patrol inspection stop point in the map;
s4, arranging a central control station and a supervision platform outside the map;
and S5, presetting detection time and intervals, and acquiring data.
The first task of the inspection robot in an unfamiliar environment is to construct a map, and the robot knows the environment where the robot faces and the safe area where the robot can reach. The sample data stores some existing data information of the substation equipment, an operation frame and a learning frame, and the learning module is used for updating and perfecting the sample so as to improve the speed of next operation and judgment. The inspection robot goes to an inspection stop point at preset intervals to analyze and judge data information of the collected power transformation equipment, and the inspection robot can perform free inspection in other time, namely the inspection robot possibly encounters equipment faults or potential safety hazards except samples in the time, intelligent learning is required to be performed, the samples need to be perfected, and in the period, the samples can be manually and remotely judged, analyzed and processed by a worker of a central control station or a supervision platform and updated; the inspection robots are on duty in turn, the inspection robots after shift are driven to the supply station for charging or other supply, for example, tire damage, camera head shielding by foreign matters and other external damage can be automatically processed or replaced by automatic equipment in the supply station, and the inspection robots are driven to the supply station if the acquisition system or other systems are out of order or damaged, and wait for maintenance personnel to maintain.
As shown in fig. 6, the mapping the substation monitoring points and the surrounding environment, and the map building includes the steps of:
s11, manually controlling the inspection robot to walk for a circle along the edge of the map to be constructed;
s12, scanning the edge area through a laser radar;
s13, recording edge scenes through a video camera;
and S14, constructing a closed map.
Even if the inspection robot does not have a fixed cruising route, the inspection robot can freely inspect, but the area for constructing the map must be a closed area, otherwise, problems can occur probably. The inspection robot can be manually controlled at a nearby central control station to walk for a circle along the edge of the map to be constructed, the edge scene is recorded and determined by scanning the edge area through the laser radar, and the condition that the robot judges that the map construction is finished is to obtain a closed map.
As shown in fig. 7, the module for presetting sample data and learning for the inspection robot includes the steps of:
s21, storing sample data of the substation equipment in normal work and fault in a storage module;
s22, extracting sample data to serve as a training sample, preprocessing the training sample and extracting characteristics to obtain an observation sequence;
s23, establishing learning module parameters and storing initial values of the parameters;
s24, reestimating the initial values of the learning module parameters according to the observation sequence to complete training;
s25, storing the reestimated learning model parameters;
s26, extracting the characteristics of the test sample, and calculating the output probability of the observation sequence under each learning model parameter according to the learning model parameters;
and S27, storing the learning model with the maximum output probability.
The sample data is internally provided with some existing data information of the substation equipment, an operation frame and a learning model parameter, so that the inspection robot can conveniently refer, analyze and judge, and the learning module is used for updating and perfecting the sample so as to improve the speed of next operation and judgment and improve the inspection efficiency; and performing multiple tests for perfection required by the construction of the learning model, selecting and storing optimal parameters and models, performing multiple iterations for each updating, calculating the output probability of the observation sequence under each learning model parameter according to the learning model parameters, wherein the model with the maximum probability is the recognition result, and storing the learning model with the maximum output probability.
Finally, the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting, and other modifications or equivalent substitutions made by the technical solutions of the present invention by those of ordinary skill in the art should be covered within the scope of the claims of the present invention as long as they do not depart from the spirit and scope of the technical solutions of the present invention.
Claims (7)
1. A monitoring system for a transformer substation is characterized by comprising a plurality of inspection robots, a supply station, a central control station and a supervision platform, wherein each inspection robot comprises an acquisition module, a processing module, a learning module, an analysis module, a storage module and an alarm module which are connected with one another; the acquisition module is wirelessly connected with the central control station and the supply station and is used for acquiring data near a monitoring point of the transformer substation for the inspection robot; the supply station and the central control station are arranged near the monitoring point of the transformer substation; the processing module is used for preprocessing, matching and identifying the data acquired by the acquisition module; sample data is preset in the storage module; the analysis module is connected with the alarm module and is used for comparing the data processed by the processing module with the sample data; the alarm module is wirelessly connected with the supervision platform; the learning module is used for updating and perfecting the sample.
2. The monitoring system for a substation of claim 1, wherein the acquisition module comprises a video camera, a thermal imaging camera, an ultraviolet camera, an audio signal acquisition device, and a signal receiver and transmitter.
3. The monitoring system for the substation according to claim 1, wherein the inspection robot is further provided with a laser radar and a plurality of distance sensors, and the distance sensors are distributed at different positions of the inspection robot.
4. A monitoring system for a substation according to claim 1, wherein the supervision platform is provided with a database, a display terminal and a second alarm module; the database is wirelessly connected with the storage module; the second alarm module is in wireless connection with the alarm module; and the display terminal is connected with the database and the second alarm module.
5. A method for a monitoring system of a substation according to any of claims 1-4, characterized in that it comprises the steps of:
surveying and mapping monitoring points of the transformer substation and the surrounding environment, and constructing a map;
presetting sample data and a learning module for the inspection robot;
setting a supply station and a patrol stop point in a map;
arranging a central control station and a supervision platform outside a map;
and presetting detection time and intervals, and acquiring data.
6. The method of claim 5, wherein the mapping of the substation monitoring points and the surrounding environment comprises the steps of:
manually controlling the inspection robot to walk for a circle along the edge of the map to be constructed;
scanning the edge area by a laser radar;
recording edge scenes through a video camera;
a closed map is constructed.
7. The method for the monitoring system of the substation according to claim 5, wherein the presetting of sample data and the learning module for the inspection robot comprises the steps of:
storing sample data of the substation equipment in normal work and fault in a storage module;
extracting sample data as a training sample, preprocessing the training sample and extracting characteristics to obtain an observation sequence;
establishing learning module parameters and storing initial values of the parameters;
reestimating the initial values of the learning module parameters according to the observation sequence to complete training;
storing the reestimated learning model parameters;
extracting the characteristics of the test sample, and calculating the output probability of the observation sequence under each learning model parameter according to the learning model parameters;
and saving the learning model with the maximum output probability.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011180479.3A CN112332541B (en) | 2020-10-29 | 2020-10-29 | Monitoring system and method for transformer substation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011180479.3A CN112332541B (en) | 2020-10-29 | 2020-10-29 | Monitoring system and method for transformer substation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112332541A true CN112332541A (en) | 2021-02-05 |
| CN112332541B CN112332541B (en) | 2024-07-12 |
Family
ID=74297710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011180479.3A Active CN112332541B (en) | 2020-10-29 | 2020-10-29 | Monitoring system and method for transformer substation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112332541B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113551765A (en) * | 2021-08-17 | 2021-10-26 | 中冶北方（大连）工程技术有限公司 | Sound spectrum analysis and diagnosis method for equipment fault |
| CN114025138A (en) * | 2021-11-09 | 2022-02-08 | 国网河南省电力公司新野县供电公司 | Substation inspection cooperative system and method |
| CN116054417A (en) * | 2023-03-16 | 2023-05-02 | 山东联行智能科技有限公司 | Monitoring system and method for transformer substation |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130231779A1 (en) * | 2012-03-01 | 2013-09-05 | Irobot Corporation | Mobile Inspection Robot |
| CN106451201A (en) * | 2016-08-31 | 2017-02-22 | 杭州申昊科技股份有限公司 | Inspection system for transformer substation |
| WO2018107916A1 (en) * | 2016-12-14 | 2018-06-21 | 南京阿凡达机器人科技有限公司 | Robot and ambient map-based security patrolling method employing same |
| CN108189043A (en) * | 2018-01-10 | 2018-06-22 | 北京飞鸿云际科技有限公司 | A kind of method for inspecting and crusing robot system applied to high ferro computer room |
| CN109752300A (en) * | 2019-01-02 | 2019-05-14 | 五邑大学 | A kind of coating material production safe and intelligent crusing robot, system and method |
| CN111239768A (en) * | 2020-01-13 | 2020-06-05 | 南京七宝机器人技术有限公司 | Method for automatically constructing map and searching inspection target by electric power inspection robot |
-
2020
- 2020-10-29 CN CN202011180479.3A patent/CN112332541B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130231779A1 (en) * | 2012-03-01 | 2013-09-05 | Irobot Corporation | Mobile Inspection Robot |
| CN106451201A (en) * | 2016-08-31 | 2017-02-22 | 杭州申昊科技股份有限公司 | Inspection system for transformer substation |
| WO2018107916A1 (en) * | 2016-12-14 | 2018-06-21 | 南京阿凡达机器人科技有限公司 | Robot and ambient map-based security patrolling method employing same |
| CN108189043A (en) * | 2018-01-10 | 2018-06-22 | 北京飞鸿云际科技有限公司 | A kind of method for inspecting and crusing robot system applied to high ferro computer room |
| CN109752300A (en) * | 2019-01-02 | 2019-05-14 | 五邑大学 | A kind of coating material production safe and intelligent crusing robot, system and method |
| CN111239768A (en) * | 2020-01-13 | 2020-06-05 | 南京七宝机器人技术有限公司 | Method for automatically constructing map and searching inspection target by electric power inspection robot |
Non-Patent Citations (2)
| Title |
|---|
| 董育宁等: "《医学图像处理理论与应用》", 31 August 2020, 东南大学出版社, pages: 204 - 206 * |
| 那彦等: "《基于多分辨分析理论的图像融合方法》", 31 May 2007, 西安电子科技大学出版社, pages: 244 - 246 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113551765A (en) * | 2021-08-17 | 2021-10-26 | 中冶北方（大连）工程技术有限公司 | Sound spectrum analysis and diagnosis method for equipment fault |
| CN114025138A (en) * | 2021-11-09 | 2022-02-08 | 国网河南省电力公司新野县供电公司 | Substation inspection cooperative system and method |
| CN116054417A (en) * | 2023-03-16 | 2023-05-02 | 山东联行智能科技有限公司 | Monitoring system and method for transformer substation |
| CN116054417B (en) * | 2023-03-16 | 2023-09-19 | 山东联行智能科技有限公司 | Monitoring system and method for transformer substation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112332541B (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112332541B (en) | Monitoring system and method for transformer substation | |
| CN108189043B (en) | Inspection method and inspection robot system applied to high-speed rail machine room | |
| CN109334543B (en) | Power line inspection system and method with cooperation of power inspection vehicle and unmanned aerial vehicle | |
| CN109284739B (en) | Power transmission line external damage prevention early warning method and system based on deep learning | |
| CN111353413A (en) | Low-missing-report-rate defect identification method for power transmission equipment | |
| CN110908370A (en) | Unmanned inspection task planning method and system for thermal power plant | |
| CN113052876B (en) | Video relay tracking method and system based on deep learning | |
| CN114240868A (en) | Unmanned aerial vehicle-based inspection analysis system and method | |
| CN109711348A (en) | Intelligent monitoring method and system based on the long-term real-time architecture against regulations in hollow panel | |
| CN112557512A (en) | Acoustic imaging method, device and equipment and inspection robot based on acoustic imaging equipment | |
| CN117111660A (en) | Unattended intelligent granary system and method | |
| CN114905512A (en) | Panoramic tracking and obstacle avoidance method and system for intelligent inspection robot | |
| CN117806355A (en) | Control method and system for electric power line inspection unmanned aerial vehicle | |
| CN116310891A (en) | Cloud-edge cooperative transmission line defect intelligent detection system and method | |
| CN116301046A (en) | Unmanned aerial vehicle aerial photographing safety distance automatic positioning method based on electric power pole tower identification | |
| CN115272888A (en) | Digital twin-based 5G + unmanned aerial vehicle power transmission line inspection method and system | |
| CN114721432A (en) | Unmanned aerial vehicle intelligent inspection equipment based on big data and inspection image defect analysis method | |
| CN113095160B (en) | Power system personnel safety behavior identification method and system based on artificial intelligence and 5G | |
| CN115880595A (en) | Multi-source camera-based intelligent inspection method for unmanned aerial vehicle transformer substation | |
| CN115355952A (en) | Intelligent inspection system for crude oil storage tank | |
| CN109902647A (en) | The portable online Bird's Nest intelligent identification Method of one kind and system | |
| Panahi et al. | Cooperative Unmanned Aerial Vehicles for Monitoring and Maintenance of Heat and Electricity Incorporated Networks: A Learning‐based Approach | |
| CN112417661B (en) | Data acquisition and analysis system for unmanned equipment packaging test | |
| Hwang et al. | Soiling detection for photovoltaic modules based on an intelligent method with image processing | |
| Wu et al. | Design and Application of Image Recognition Framework Based on Cloud Edge Collaboration in Distribution Stations |
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 |