CN117373144A - Intelligent equipment inspection method and system based on fault prediction and image recognition - Google Patents
Intelligent equipment inspection method and system based on fault prediction and image recognition Download PDFInfo
- Publication number
- CN117373144A CN117373144A CN202311196364.7A CN202311196364A CN117373144A CN 117373144 A CN117373144 A CN 117373144A CN 202311196364 A CN202311196364 A CN 202311196364A CN 117373144 A CN117373144 A CN 117373144A
- Authority
- CN
- China
- Prior art keywords
- inspection
- equipment
- fault
- area
- screen cabinet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 310
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012423 maintenance Methods 0.000 claims abstract description 37
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 238000012790 confirmation Methods 0.000 claims abstract description 17
- 230000000737 periodic effect Effects 0.000 claims abstract description 15
- 238000004519 manufacturing process Methods 0.000 claims abstract description 4
- 239000003016 pheromone Substances 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 20
- 238000012360 testing method Methods 0.000 claims description 17
- 238000009826 distribution Methods 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 11
- 230000001681 protective effect Effects 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 241000257303 Hymenoptera Species 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 239000000306 component Substances 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 5
- 238000007726 management method Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 239000008358 core component Substances 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000008439 repair process Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 239000004065 semiconductor Substances 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/185—Electrical failure alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an intelligent equipment inspection method based on fault prediction and image recognition, which relates to the technical field of computers and comprises the steps of acquiring data information of equipment from a database; if the inspection reason is periodic inspection, determining an inspection area according to an inspection schedule, and entering a corresponding area to execute inspection operation of the protection screen cabinet by the protection screen cabinet; if the inspection cause is fault alarm, determining the actual position of the fault equipment according to the number of the fault equipment, performing equipment inspection to judge the fault cause and the fault grade, comparing the terminal strip lines one by using an image recognition algorithm based on Jetson Nano, and executing corresponding operation on the positioned fault protection screen cabinet; after the inspection and maintenance are completed, secondary confirmation is carried out on the equipment with problems so as to ensure that the equipment operates normally. According to the invention, the regular inspection and fault alarm are combined in the inspection schedule, so that more comprehensive, timely and efficient equipment inspection and maintenance are realized, and the stability and efficiency of the production process are improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an intelligent equipment inspection method and system based on fault prediction and image recognition.
Background
The traditional equipment inspection mainly relies on manual periodic inspection, and the method has the defects of low inspection frequency and small coverage. The manual inspection cannot intelligently judge the real-time state of the equipment, key monitoring of key equipment or parts cannot be realized, and the effect of comprehensive protection is difficult to achieve. Meanwhile, the manual inspection efficiency is low, the manual inspection efficiency is in direct proportion to the number and the distribution range of the equipment, and the manual inspection cost of a large number of equipment is high.
The fault early warning mode of the existing equipment is simpler, the alarm is mainly carried out by setting a threshold value, the early warning mechanism cannot accurately predict the state of the equipment, the alarm can be given only after serious faults occur, and the early warning of the faults cannot be realized. For equipment with similar appearance, such as hundreds of protection screen cabinets in a transformer substation, once faults occur, maintenance personnel can hardly quickly locate problem equipment, so that maintenance can not respond timely. Meanwhile, the existing fault detection and positioning mainly depends on manual comparison drawing and other low-efficiency modes, and quick and accurate positioning cannot be achieved.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description summary and in the title of the application, to avoid obscuring the purpose of this section, the description summary and the title of the invention, which should not be used to limit the scope of the invention.
The invention is provided in view of the problems of low manual inspection efficiency, inaccurate fault early warning, difficult maintenance and positioning and the like in the prior art.
Therefore, the invention aims to solve the problems of low efficiency and delayed fault response existing in the conventional equipment inspection and maintenance process by intelligent equipment state monitoring and prediction, image identification and quick positioning and maintenance flow optimization of closed loop feedback so as to realize intelligent maintenance and management of equipment.
In order to solve the technical problems, the invention provides the following technical scheme:
in a first aspect, an embodiment of the present invention provides an intelligent equipment inspection method based on fault prediction and image recognition, which includes acquiring an inspection record, fault alarm information and parameter information of equipment from a database; determining inspection reasons including periodic inspection and fault alarm; if the inspection reason is periodic inspection, determining an inspection area according to an inspection schedule, and entering a corresponding area to execute inspection operation of the protection screen cabinet by the protection screen cabinet; if the inspection cause is fault alarm, determining the actual position of the fault equipment according to the number of the fault equipment, performing equipment inspection to judge the fault cause and the fault grade, comparing the terminal strip lines one by using an image recognition algorithm based on Jetson Nano, and executing corresponding operation on the positioned fault protection screen cabinet; after the inspection and maintenance are completed, secondary confirmation is carried out on the equipment with problems so as to ensure that the equipment operates normally.
As a preferable scheme of the intelligent equipment inspection method based on fault prediction and image recognition, the invention comprises the following steps: the construction of the inspection schedule comprises the following steps: dividing all the protection screen cabinets into a transformer area, a power distribution area, a control room area and 4 areas for transmitting equipment areas according to equipment types; determining the number n of inspection areas in an optimal inspection schedule; if the number of the inspection areas is n=1, the inspection operation of the protection screen cabinets of the corresponding areas is executed; if the number of the inspection areas is more than or equal to 2 and less than or equal to 4, determining an optimal initial area, making an optimal inspection route according to equipment of an optimal inspection schedule, and sequentially executing inspection operation of the protective screen cabinet by the optimal inspection route.
As the base of the inventionAn optimal scheme of the intelligent equipment inspection method for fault prediction and image recognition is as follows: the determining of the number n of inspection areas in the optimal inspection schedule comprises the following steps: acquiring basic information of all equipment, the last inspection time of the equipment, equipment inspection period configuration and equipment fault record data; determining scoring indexes as a patrol time interval, fault records, key equipment and key areas; calculating equipment inspection priority, if an optimal inspection schedule is manufactured through regular inspection, giving an alarm on real-time faults of the equipment, marking the equipment as 10 points, otherwise marking the equipment as 0 points; if the time interval of the last inspection of the equipment s is 5/4T s Wherein T is s The score is recorded as 2 points for the inspection period of the equipment s, and is recorded as 0 points otherwise; checking the latest 3 times of inspection records, if fault records exist, marking the latest 3 times of inspection records as 3 points, 2 points and 1 point respectively according to the near-far scores of time, otherwise marking the latest 3 times of inspection records as 0 point; if the equipment belongs to key equipment, marking the score as 3 points, otherwise marking the score as 0 points; if the equipment is positioned in the key area, marking the score as 3 points, otherwise marking the score as 0 points; weighting and summing the four scoring indexes according to preset weights to obtain the inspection priority scores of the equipment; calculating the sum of accumulated patrol priority scores of all devices in all areas, and marking the sum as P all The method comprises the steps of carrying out a first treatment on the surface of the The time limit T of the inspection is predetermined, the average time T of the inspection in a single area is obtained through experiments, and the number n= [ T/T ] of the area with the most inspection is calculated at the same time]The method comprises the steps of carrying out a first treatment on the surface of the Grouping devices by region, and calculating the accumulated priority score P of devices in each region 1 、P 2 、P 3 、P 4 The method comprises the steps of carrying out a first treatment on the surface of the Selecting n areas with the largest accumulated priority scores as the current inspection area; if the accumulated priority values are close, selecting an area with more key equipment in the area; if P all If the number of the inspection areas is larger, the time limit is properly relaxed, and the number of the inspection areas is increased; and outputting the determined n inspection areas to generate the optimal inspection schedule.
As a preferable scheme of the intelligent equipment inspection method based on fault prediction and image recognition, the invention comprises the following steps: if the number of inspection areas n=1, performing the inspection operation of the protection screen cabinet by protection screen cabinet of the corresponding area includes the following steps: inquiring all the equipment numbers of the protection screen cabinet in the inspection area, and scanning the bar codes of the protection screen cabinet to read the equipment information; if the inspection area is a transformer area, checking whether the appearance, the label and the interface are abnormal or not, and opening a door to check the connection condition of an internal circuit; finally, testing operation and checking working parameters; if the inspection area is a power distribution area, checking whether the shell, the door lock and the mark are damaged or not, and detecting temperature, humidity and noise parameters; finally, simulating an input signal, and testing the control and protection functions of the protection screen cabinet; if the inspection area is a control room area, checking whether the connecting cable is worn or not, and accessing a test signal to the communication port to check the communication function; finally, simulating fault signals and testing alarm response of the protection screen cabinet; if the inspection area is a transmission equipment area, detecting port transmission quality and bandwidth utilization rate, sending a test data packet, and checking forwarding and communication functions; finally, whether the environmental parameters are in the working range is checked.
As a preferable scheme of the intelligent equipment inspection method based on fault prediction and image recognition, the invention comprises the following steps: the method for making the optimal routing inspection route comprises the following steps: dividing the equipment in the optimal inspection schedule into nodes, and taking the distance between the nodes as edge weight; initializing a pheromone value for each edge to represent the attractive force of the path; ants select the next node to be accessed according to the pheromone of the current node and the edge and the node distance; after the ants complete the path once, updating the pheromone value of the passed side according to the path distance; introducing a global pheromone updating strategy to update the pheromone of the global optimal path; when a certain iteration number is reached or after a plurality of iterations, an optimal path is found; and taking the found optimal path as an optimal inspection route, and sequentially executing the inspection operation of the protection screen cabinet by the optimal inspection route.
As a preferable scheme of the intelligent equipment inspection method based on fault prediction and image recognition, the invention comprises the following steps: if the appearance is not obviously damaged and the operation parameters are normal, but the small problem easy to repair exists, judging the failure grade to be a mild failure, and rapidly processing the small problem on site by a patrol personnel; if the appearance is not damaged but the operation parameters are abnormal, or if some components are damaged but the operation is not seriously affected, judging that the fault grade is a moderate grade, and the fault grade cannot be repaired on site, generating an equipment maintenance list in the system, filling fault description information and the fault grade to submit a maintenance department, and marking the operation state of the fault equipment in the system as a fault; if the appearance is seriously damaged, the core component is faulty, the operation is completely abnormal or the equipment cannot be started, judging that the fault level is severe fault, the equipment cannot be repaired, stopping operation and waiting for maintenance, adding a warning mark by a patrol personnel, reporting a management layer, and simultaneously notifying project technicians to process.
As a preferable scheme of the intelligent equipment inspection method based on fault prediction and image recognition, the invention comprises the following steps: the image recognition algorithm based on Jetson Nano compares the terminal strip lines one by one, and the method comprises the following steps: photographing to obtain an actual wiring diagram of the terminal strip of the protection screen cabinet, detecting and positioning a terminal strip region on an image by using OpenCV, and dividing and preprocessing the terminal strip region to obtain a color image; constructing a convolutional neural network model, and training a reference terminal row drawing data set; using a Jetson Nano loading model to predict, and outputting a terminal strip wiring identification result; judging whether the wiring of each terminal is correct or not according to the terminal strip drawing; comparing the identification result with a standard drawing, and judging whether the wiring is consistent; if not, judging the next protective screen cabinet until the wiring of the terminal strip is consistent with the terminal strip drawing of the protective screen cabinet; and outputting the final output consistent protection screen cabinet.
In a second aspect, an embodiment of the present invention provides an intelligent equipment inspection system based on fault prediction and image recognition, which includes a data acquisition module, configured to acquire an inspection record, fault alarm information and parameter information of equipment from a database; the inspection plan making module is used for determining an inspection reason and an inspection plan, determining an inspection area according to the inspection plan, and determining the actual position of the fault equipment according to the number of the fault equipment; the routing inspection route planning module is used for determining an optimal routing inspection route according to the routing inspection schedule and the ant colony algorithm; the fault processing module is used for carrying out equipment inspection according to the inspection reasons, judging the fault reasons and the fault grades, comparing the terminal strip lines by using an image recognition algorithm, executing corresponding operation on the positioned fault protection screen cabinet, and following the processing progress of the maintenance list; and the secondary confirmation module is used for carrying out secondary confirmation on the equipment with the problem so as to ensure that the equipment operates normally.
In a third aspect, embodiments of the present invention provide a computer apparatus comprising a memory and a processor, the memory storing a computer program, wherein: the computer program instructions, when executed by a processor, implement the steps of the intelligent device inspection method based on fault prediction and image recognition according to the first aspect of the present invention.
In a fourth aspect, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: the computer program instructions, when executed by a processor, implement the steps of the intelligent device inspection method based on fault prediction and image recognition according to the first aspect of the present invention.
The invention has the beneficial effects that: according to the invention, the inspection is divided into periodic inspection and fault alarm by judging the inspection reason, and different processing modes are adopted, so that the inspection efficiency and accuracy are improved; the optimal routing inspection route is determined through the optimized ant colony algorithm and the routing inspection schedule, so that repeated walking of the routing inspection route is reduced to the maximum extent, and the routing inspection efficiency is improved; aiming at fault processing, corresponding processing measures are judged according to the fault level, so that the accuracy and the efficiency of fault processing are improved; the image recognition algorithm is utilized to compare the terminal strip lines, so that the protection screen cabinet corresponding to the fault equipment is rapidly positioned, and the error and omission rate of manual judgment are reduced; the regular inspection and fault alarm are combined in the inspection schedule, so that more comprehensive, timely and efficient equipment inspection and maintenance are realized, and the stability and efficiency of the production process are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
fig. 1 is a method flow diagram of an intelligent inspection method for a device based on fault prediction and image recognition.
Fig. 2 is a computer device diagram of a device intelligent patrol method based on fault prediction and image recognition.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
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 other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be 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.
Example 1
Referring to fig. 1-2, a first embodiment of the present invention provides an intelligent inspection method for a device based on fault prediction and image recognition, including,
s1: and acquiring the inspection record, fault alarm information and parameter information of the equipment from the database.
Specifically, the inspection record comprises inspection time, inspection personnel and inspection results; the fault alarm information comprises fault equipment codes, alarm time, alarm types and alarm descriptions; the device parameter information includes a device code, a device name, a device model number, and an operation state.
S2: determining the inspection cause comprises periodic inspection and fault alarm.
Specifically, if the inspection is performed according to a set inspection plan or period, the inspection is judged to be periodic inspection, and the purpose of periodic inspection is to prevent potential faults and ensure the normal running state of equipment, wherein the inspection period is daily, weekly and monthly; if the inspection is performed due to an alarm signal sent by the equipment, the type of alarm, the alarm information and the state of the equipment are checked, and the inspection is judged to be fault alarm.
S3: if the inspection reason is periodic inspection, determining an inspection area according to an inspection schedule, and entering the corresponding area to execute the inspection operation of the protection screen cabinet by cabinet.
Specifically, the method comprises the following steps:
s3.1: and dividing all the protection screen cabinets into a transformer area, a power distribution area, a control room area and 4 areas for transmitting equipment areas according to the equipment types.
Specifically, the transformer area comprises a protection screen cabinet related to the power supply transformer and is used for protecting, controlling and monitoring the transformer; the power distribution area comprises a protection screen cabinet related to a power distribution system and is used for protecting, controlling and monitoring power distribution equipment of various levels such as low-voltage power distribution, medium-voltage power distribution and the like; the control room area relates to a protection screen cabinet related to a control and monitoring system and is used for protecting and controlling equipment and systems in the control room; the transmission device area includes a protective screen cabinet associated with the communication and transmission devices for protection and control of the transmission devices.
S3.2: and determining the number n of the inspection areas in the optimal inspection schedule.
Specifically, constructing the inspection schedule includes the following steps: acquiring basic information of all equipment, the last inspection time of the equipment, equipment inspection period configuration and equipment fault record data; determining scoring indexes as real-time fault alarm, routing inspection time intervals, fault records, key equipment and key areas; calculating equipment inspection priority, if an optimal inspection schedule is manufactured through regular inspection, giving an alarm on real-time faults of the equipment, marking the equipment as 10 points, otherwise marking the equipment as 0 points; if the time interval of the last inspection of the equipment s is 5/4T s Wherein T is s The score is 2 points for the inspection period of the equipment s, and the score is 0 points otherwise; view the most3 times of inspection records, if fault records exist, scoring 3 points, 2 points and 1 point respectively according to the time from near to far, otherwise, scoring 0 point; if the equipment belongs to key equipment, scoring 3 points, otherwise, 0 points; if the equipment is positioned in the key area, scoring for 2 points, otherwise, scoring for 0 points; and carrying out weighted summation on the four scoring indexes according to preset weights to obtain the inspection priority scores of the equipment.
Further, the sum of the accumulated patrol priority scores of all the devices in all the areas is calculated and is recorded as P all The method comprises the steps of carrying out a first treatment on the surface of the The time limit T of the inspection is predetermined, and the average time T for executing the inspection in a single area is obtained through experiments; calculating the number of areas which can be inspected at most this time: n= [ T/T ]]The method comprises the steps of carrying out a first treatment on the surface of the Grouping devices by region, and calculating the accumulated priority score P of devices in each region 1 、P 2 、P 3 、P 4 The method comprises the steps of carrying out a first treatment on the surface of the Selecting n areas with the largest accumulated priority scores as the current inspection area; if the accumulated priority values are similar, selecting an area with more key equipment in the area; if P all If the number of the inspection areas is larger, the time limit is properly relaxed, and the number of the inspection areas is increased; and outputting the determined n inspection areas to generate the optimal inspection schedule.
It should be noted that, the weights corresponding to the scoring index real-time fault alarm, the inspection time interval, the fault record, the key equipment and the key area are respectively 0.3, 0.1, 0.2 and 0.2, because if the optimal inspection schedule is made by regular inspection, the equipment real-time fault alarm needs to be adjusted to the highest priority; the inspection time interval is less important than other indexes, so 0.1 is taken, and the other indexes are taken as 0.2;
s3.3: and if the number n=1 of the inspection areas, executing the inspection operation of the protection screen cabinets of the corresponding areas.
Specifically, all the equipment numbers of the protection screen cabinet in the inspection area are inquired, and the bar codes of the protection screen cabinet are scanned to read the equipment information; if the inspection area is a transformer area, checking whether the appearance, the label and the interface are abnormal or not, and opening a door to check the connection condition of an internal circuit; finally, testing operation and checking working parameters; if the inspection area is a power distribution area, checking whether the shell, the door lock and the mark are damaged or not, and detecting parameters such as temperature, humidity, noise and the like; finally, simulating an input signal, and testing the control and protection functions of the protection screen cabinet; if the inspection area is a control room area, checking whether the connecting cable is worn or not, and accessing a test signal to the communication port to check the communication function; finally, simulating fault signals and testing alarm response of the protection screen cabinet; if the inspection area is a transmission equipment area, detecting port transmission quality and bandwidth utilization rate, sending a test data packet, and checking forwarding and communication functions; finally, whether the environmental parameters are in the working range is checked.
S3.4: if the number of the inspection areas is more than or equal to 2 and less than or equal to 4, determining an optimal initial area, making an optimal inspection route according to equipment of an optimal inspection schedule, and sequentially executing inspection operation of the protective screen cabinet by the optimal inspection route.
Specifically, the method for making the optimal routing inspection route comprises the following steps: dividing the equipment in the optimal inspection schedule into nodes, and taking the distance between the nodes as edge weight; initializing a pheromone value for each edge to represent the attractive force of the path; ants select the next node to be accessed according to the pheromone of the current node and the edge and the node distance; after the ants complete the path once, updating the pheromone value of the passed side according to the path distance; introducing a global pheromone updating strategy to update the pheromone of the global optimal path; when a certain iteration number is reached or after a plurality of iterations, an optimal path is found; and taking the found optimal path as an optimal inspection route, and sequentially executing the inspection operation of the protection screen cabinet by the optimal inspection route.
Further, the inspection operation of each area-by-area protection screen cabinet is consistent with S3.3.
S4: if the inspection reason is fault alarm, determining the actual position of the fault equipment according to the number of the fault equipment, performing equipment inspection to judge the fault reason and the fault grade, comparing the terminal strip lines one by using an image recognition algorithm based on Jetson Nano, and executing corresponding operation on the positioned fault protection screen cabinet.
Specifically, the method comprises the following steps:
s4.1: inquiring the number of the fault equipment in the database according to the fault alarm information, and determining the actual position of the fault equipment according to the number of the fault equipment.
S4.2: and going to the actual position of the fault equipment, performing equipment inspection to judge the fault reason and the fault grade.
If the appearance is not obviously damaged and the operation parameters are normal, but the small problem easy to repair exists, the fault grade is judged to be a mild fault, the small problem can be repaired on site, and the patrol personnel can rapidly process the small problem on site.
If the appearance is not damaged but the operation parameters are abnormal, or if some components are damaged but the operation is not seriously affected, judging that the fault grade is a moderate grade, and the fault grade cannot be repaired on site, generating an equipment maintenance list in the system, filling fault description information and the fault grade to submit a maintenance department, and marking the operation state of the fault equipment in the system as a fault;
if the appearance is seriously damaged, the core component is faulty, the operation is completely abnormal or the equipment cannot be started, judging that the fault level is severe fault, the equipment cannot be repaired, stopping operation and waiting for maintenance, adding a warning mark by a patrol personnel, reporting a management layer, and simultaneously notifying project technicians to process.
S4.3: if the fault is a moderate fault and a severe fault, determining the area of the protection screen cabinet corresponding to the fault equipment according to the equipment maintenance list information, comparing the terminal strip lines one by using an image recognition algorithm based on Jetson Nano so as to position the protection screen cabinet corresponding to the fault equipment, and executing corresponding operation on the positioned protection screen cabinet.
Specifically, taking a photo to obtain an actual wiring diagram of the terminal strip of the protection screen cabinet, detecting and positioning a terminal strip region on an image by using OpenCV, and dividing and preprocessing the terminal strip region to obtain a color image; constructing a convolutional neural network model, and training a reference terminal row drawing data set; using a Jetson Nano loading model to predict, and outputting a terminal strip wiring identification result; judging whether the wiring of each terminal is correct or not according to the terminal strip drawing; comparing the identification result with a standard drawing, and judging whether the wiring is consistent; if not, judging the next protective screen cabinet until the wiring of the terminal strip is consistent with the terminal strip drawing of the protective screen cabinet; and finally outputting the consistent protection screen cabinet.
Further, after the fault protection screen cabinet is positioned, inquiring maintenance list information of the equipment; extracting fault description and fault grade content from the maintenance list; and performing power failure, and matching the failure level with the corresponding processing measure; after the corresponding steps are executed, starting the testing equipment again, and checking whether the faults are correctly removed; if the fault is removed, updating the maintenance state of the fault equipment in the system to be processed.
S4.4: the processing progress of the maintenance list is regularly followed to ensure that faults can be removed in time.
S5: after the inspection and maintenance are completed, the equipment with problems is secondarily confirmed to ensure that the equipment operates normally.
Specifically, the second confirmation of the regular inspection is performed after all equipment inspection is completed, the standard is that the recorded data is complete and is completely omitted, and the confirmation mode is that the recorded table data is checked and spot inspection equipment is performed; the second confirmation of the fault alarm is carried out after the maintenance of the corresponding equipment is completed, the standard is that the fault is cleared and the running index of the equipment is normal, and the confirmation mode is that the checking alarm record is cleared and the test equipment is operated; if the secondary confirmation is not passed, the inspection or maintenance is required again until the confirmation is correct.
Further, the embodiment also provides an intelligent equipment inspection system based on fault prediction and image recognition, which comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring inspection records, fault alarm information and parameter information of equipment from a database; the inspection plan making module is used for determining an inspection reason and an inspection plan, determining an inspection area according to the inspection plan, and determining the actual position of the fault equipment according to the number of the fault equipment; the routing inspection route planning module is used for determining an optimal routing inspection route according to the routing inspection schedule and the ant colony algorithm; the fault processing module is used for carrying out equipment inspection according to the inspection reasons, judging the fault reasons and the fault grades, comparing the terminal strip lines by using an image recognition algorithm, executing corresponding operation on the positioned fault protection screen cabinet, and following the processing progress of the maintenance list; and the secondary confirmation module is used for carrying out secondary confirmation on the equipment with the problem so as to ensure that the equipment operates normally.
The embodiment also provides computer equipment which is suitable for the conditions of the nuclear power equipment fault prediction and intelligent calibration method, and comprises a memory and a processor; the memory is used for storing computer executable instructions, and the processor is used for executing the computer executable instructions to realize the nuclear power equipment fault prediction and intelligent calibration method according to the embodiment.
The computer device may be a terminal comprising a processor, a memory, a communication interface, a display screen and input means connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
The present embodiment also provides a storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of: acquiring inspection records, fault alarm information and parameter information of equipment from a database; determining inspection reasons including periodic inspection and fault alarm; if the inspection reason is periodic inspection, determining an inspection area according to an inspection schedule, and entering a corresponding area to execute inspection operation of the protection screen cabinet by the protection screen cabinet; if the inspection cause is fault alarm, determining the actual position of the fault equipment according to the number of the fault equipment, performing equipment inspection to judge the fault cause and the fault grade, comparing the terminal strip lines one by using an image recognition algorithm based on Jetson Nano, and executing corresponding operation on the positioned fault protection screen cabinet; after the inspection and maintenance are completed, secondary confirmation is carried out on the equipment with problems so as to ensure that the equipment operates normally.
In summary, the invention divides the inspection into periodic inspection and fault alarm by judging the inspection reason, adopts different processing modes, and improves the inspection efficiency and accuracy; the optimal routing inspection route is determined through the optimized ant colony algorithm and the routing inspection schedule, so that repeated walking of the routing inspection route is reduced to the maximum extent, and the routing inspection efficiency is improved; aiming at fault processing, corresponding processing measures are judged according to the fault level, so that the accuracy and the efficiency of fault processing are improved; the image recognition algorithm is utilized to compare the terminal strip lines, so that the protection screen cabinet corresponding to the fault equipment is rapidly positioned, and the error and omission rate of manual judgment are reduced; the regular inspection and fault alarm are combined in the inspection schedule, so that more comprehensive, timely and efficient equipment inspection and maintenance are realized, and the stability and efficiency of the production process are improved.
Example 2
Referring to fig. 1 to 2, in order to verify the beneficial effects of the present invention, a second embodiment of the present invention provides an intelligent inspection method for equipment based on fault prediction and image recognition, and scientific demonstration is performed through economic benefit calculation and simulation experiments.
Specifically, taking a certain power plant as an example, the last patrol record is obtained from a database, wherein the last patrol record comprises 167 patrol record codes, equipment codes, patrol time and patrol results, and part of equipment patrol record tables are shown in table 1.
Table 1 part equipment inspection record table
| Patrol record code | Device encoding | Patrol personnel | Inspection time | Inspection result |
| X001 | JD007 | To stretch to | 2022-11-04 13：30 | Normal state |
| X002 | JD009 | Gu Qi | 2022-11-04 13：30 | Interface looseness |
| X003 | JD015 | Gu Qi | 2022-11-04 13：50 | Normal state |
| X004 | JD017 | Yan Luo | 2022-11-04 13：30 | Normal state |
| X005 | JD027 | Yan Luo | 2022-11-04 12：15 | Normal state |
| ... | ... | ... | ... | ... |
| X167 | JD0156 | Li San | 2022-11-04 17：30 | Interface looseness |
Further, a fault alarm information table and a device parameter information table are obtained, and partial data are shown in tables 2 and 3.
Table 2 fault alarm information table
| Alarm record code | Fault device coding | Alarm time | Alarm type | Alarm description |
| B001 | JD002 | 2022-11-04 8：30 | Overload alarm | ... |
| B002 | JD017 | 2022-11-04 9：10 | Component damage | ... |
| B003 | JD023 | 2022-11-04 12：50 | Abnormal temperature | ... |
| B004 | JD034 | 2022-11-04 13：20 | Ground fault | ... |
| ... | ... | ... | ... | ... |
| B176 | JD017 | 2022-11-04 14：50 | Ground fault | ... |
TABLE 3 Equipment parameter information
| Fault device coding | Device name | Device model | Operating state |
| JD001 | 1000kVA oil immersed transformer | TXS-1000 type | Normal operation |
| JD002 | 600kVA dry-type transformer | KTS-600 type | Fault alarm |
| JD003 | 2500kW intelligent power distribution cabinet | PDC-2500 type | Normal operation |
| JD004 | 5kV intelligent switch cabinet | SC-5 type | Normal operation |
| ... | ... | ... | ... |
| JD378 | 6 core optical fiber transmission equipment | FOS-6 type | Normal operation |
Further, 2022-11-10 is a periodic inspection date; determining scoring indexes as a patrol time interval, fault records, key equipment and key areas; and calculating equipment inspection priority, determining an inspection area as a power distribution area and a control area according to the equipment inspection priority, and generating the optimal inspection schedule (comprising specific equipment).
Further, dividing the equipment in the optimal inspection schedule into nodes, and taking the distance between the nodes as edge weight; initializing a pheromone value for each edge to represent the attractive force of the path; ants select the next node to be accessed according to the pheromone of the current node and the edge and the node distance; after the ants complete the path once, updating the pheromone value of the passed side according to the path distance; introducing a global pheromone updating strategy to update the pheromone of the global optimal path; when a certain iteration number is reached or after a plurality of iterations, an optimal path is found; taking the found optimal path as an optimal inspection route, and sequentially executing the inspection operation of the protection screen cabinet by the optimal inspection route; in the process of inspection, the JD008 interface of the distribution transformer is found to be loose, and maintenance is marked.
Preferably, JD017 gives a fault alarm, go to the actual position of the fault device to check the device to determine the cause and grade of the fault, find that some components are damaged but do not seriously affect operation, determine the grade of severity, generate a device maintenance list in the system, fill in fault description information and grade of the fault to submit the maintenance department, and mark the operation state of the fault device in the system as a fault; the protection screen cabinet corresponding to the JD017 is positioned in the transformer area, the terminal strip lines are compared one by using an image recognition algorithm based on the Jetson Nano to position the JD017 corresponding to the protection screen cabinet, power-off is carried out, and secondary confirmation is carried out on equipment with problems after inspection and maintenance are completed so as to ensure that the equipment operates normally.
Further, the comparison of my invention with the conventional method is shown in table 4.
TABLE 4 comparison of My invention with traditional methods
| Contrast index | My invention | Conventional invention |
| Fault identification accuracy | 90％ | 82％ |
| Positioning accuracy | 93％ | 72％ |
| Inspection plan optimization | Dynamic optimization of application algorithms | Manual checking calculation |
| Secondary validation | Canonical validation mechanism | Without any means for |
| Response time | Real time | For 1 day |
| Leak rate | 3％ | 15％ |
Preferably, the fault recognition accuracy of my invention is 90%, which is higher than 82% of the traditional method. This means that my invention has better ability to accurately identify faults in the device; the positioning accuracy of my invention is 93%, whereas the traditional method is only 72%. This indicates that my invention can more precisely locate the corresponding protective screen cabinet position of the device; compared with the traditional manual checking method, the method can more efficiently optimize the inspection plan; the invention adopts a standard confirmation mechanism to ensure the accuracy of the inspection result. However, the conventional method lacks this link, and there may be a risk of missed detection or missing report.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, 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 the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (10)
1. An intelligent equipment inspection method based on fault prediction and image recognition is characterized in that: comprising the steps of (a) a step of,
acquiring inspection records, fault alarm information and parameter information of equipment from a database;
determining inspection reasons including periodic inspection and fault alarm;
if the inspection reason is periodic inspection, determining an inspection area according to an inspection schedule, and entering a corresponding area to execute inspection operation of the protection screen cabinet by the protection screen cabinet;
if the inspection cause is fault alarm, determining the actual position of the fault equipment according to the number of the fault equipment, performing equipment inspection to judge the fault cause and the fault grade, comparing the terminal strip lines one by using an image recognition algorithm based on Jetson Nano, and executing corresponding operation on the positioned fault protection screen cabinet;
after the inspection and maintenance are completed, the equipment with problems is secondarily confirmed to ensure that the equipment operates normally.
2. The intelligent equipment inspection method based on fault prediction and image recognition as claimed in claim 1, wherein: the construction of the inspection schedule comprises the following steps:
dividing all the protection screen cabinets into a transformer area, a power distribution area, a control room area and 4 areas for transmitting equipment areas according to equipment types;
determining the number n of inspection areas in an optimal inspection schedule;
if the number of the inspection areas is n=1, the inspection operation of the protection screen cabinets of the corresponding areas is executed;
if the number of the inspection areas is more than or equal to 2 and less than or equal to 4, determining an optimal initial area, making an optimal inspection route according to equipment of an optimal inspection schedule, and sequentially executing inspection operation of the protective screen cabinet by the optimal inspection route.
3. The intelligent equipment inspection method based on fault prediction and image recognition as claimed in claim 2, wherein: the determining of the number n of inspection areas in the optimal inspection schedule includes the following steps:
acquiring basic information of all equipment, the last inspection time of the equipment, equipment inspection period configuration and equipment fault record data;
determining scoring indexes as a patrol time interval, fault records, key equipment and key areas;
calculating equipment inspection priority, if an optimal inspection schedule is manufactured through regular inspection, giving an alarm on real-time faults of the equipment, marking the equipment as 10 points, otherwise marking the equipment as 0 points;
if the time interval of the last inspection of the equipment s is 5/4T s Wherein T is s The score is recorded as 2 points for the inspection period of the equipment s, and is recorded as 0 points otherwise;
checking the latest 3 times of inspection records, if fault records exist, marking the latest 3 times of inspection records as 3 points, 2 points and 1 point respectively according to the near-far scores of time, otherwise marking the latest 3 times of inspection records as 0 point;
if the equipment belongs to key equipment, marking the score as 3 points, otherwise marking the score as 0 points;
if the equipment is positioned in the key area, marking the score as 3 points, otherwise marking the score as 0 points;
weighting and summing the four scoring indexes according to preset weights to obtain the inspection priority scores of the equipment;
calculating the sum of accumulated patrol priority scores of all devices in all areas, and marking the sum as P all ；
The time limit T of the inspection is predetermined, the average time T of the inspection in a single area is obtained through experiments, and the number n= [ T/T ] of the area with the most inspection is calculated;
grouping devices by region, and calculating the accumulated priority score P of devices in each region 1 、P 2 、P 3 、P 4 ；
Selecting n areas with the largest accumulated priority scores as the current inspection area;
if the accumulated priority values are close, selecting an area with more key equipment in the area;
if P all If the number of the inspection areas is larger, the time limit is properly relaxed, and the number of the inspection areas is increased;
and outputting the determined n inspection areas to generate the optimal inspection schedule.
4. The intelligent equipment inspection method based on fault prediction and image recognition as claimed in claim 2, wherein: if the number n=1 of the inspection areas, performing the inspection operation of the protection screen cabinet by protection screen cabinet of the corresponding area includes the following steps:
inquiring all the equipment numbers of the protection screen cabinet in the inspection area, and scanning the bar codes of the protection screen cabinet to read the equipment information;
if the inspection area is a transformer area, checking whether the appearance, the label and the interface are abnormal or not, and opening a door to check the connection condition of an internal circuit; finally, testing operation and checking working parameters;
if the inspection area is a power distribution area, checking whether the shell, the door lock and the mark are damaged or not, and detecting temperature, humidity and noise parameters; finally, simulating an input signal, and testing the control and protection functions of the protection screen cabinet;
if the inspection area is a control room area, checking whether the connecting cable is worn or not, and accessing a test signal to the communication port to check the communication function; finally, simulating fault signals and testing alarm response of the protection screen cabinet;
if the inspection area is a transmission equipment area, detecting port transmission quality and bandwidth utilization rate, sending a test data packet, and checking forwarding and communication functions; finally, whether the environmental parameters are in the working range is checked.
5. The intelligent equipment inspection method based on fault prediction and image recognition as claimed in claim 2, wherein: the making of the optimal routing inspection route comprises the following steps:
dividing the equipment in the optimal inspection schedule into nodes, and taking the distance between the nodes as edge weight; initializing a pheromone value for each edge to represent the attractive force of the path;
ants select the next node to be accessed according to the pheromone of the current node and the edge and the node distance; after the ant completes a path, updating the pheromone value of the passed side according to the path distance;
introducing a global pheromone updating strategy to update the pheromone of the global optimal path;
when a certain iteration number is reached or after a plurality of iterations, an optimal path is found;
and taking the found optimal path as an optimal inspection route, and sequentially executing the inspection operation of the protection screen cabinet by the optimal inspection route.
6. The intelligent equipment inspection method based on fault prediction and image recognition as claimed in claim 1, wherein: the judging of the fault level comprises the following steps:
if the appearance is not obviously damaged and the operation parameters are normal, but the small problem easy to repair exists, judging the failure grade to be a mild failure, and rapidly processing the small problem on site by a patrol personnel;
if the appearance is not damaged but the operation parameters are abnormal, or if some components are damaged but the operation is not seriously affected, judging that the fault grade is a moderate grade, and the fault grade cannot be repaired on site, generating an equipment maintenance list in the system, filling fault description information and the fault grade to submit a maintenance department, and marking the operation state of the fault equipment in the system as a fault;
if the appearance is seriously damaged, the core component is faulty, the operation is completely abnormal or the equipment cannot be started, judging that the fault level is severe fault, the equipment cannot be repaired, stopping operation and waiting for maintenance, adding a warning mark by a patrol personnel, reporting a management layer, and simultaneously notifying project technicians to process.
7. The intelligent equipment inspection method based on fault prediction and image recognition as claimed in claim 1, wherein: the Jetson Nano-based image recognition algorithm compares the terminal strip lines one by one, and comprises the following steps:
photographing to obtain an actual wiring diagram of the terminal strip of the protection screen cabinet, detecting and positioning a terminal strip region on an image by using OpenCV, and dividing and preprocessing the terminal strip region to obtain a color image;
constructing a convolutional neural network model, and training a reference terminal row drawing data set;
using a Jetson Nano loading model to predict, and outputting a terminal strip wiring identification result;
judging whether the wiring of each terminal is correct or not according to the terminal strip drawing;
comparing the identification result with a standard drawing, and judging whether the wiring is consistent;
if not, judging the next protective screen cabinet until the wiring of the terminal strip is consistent with the terminal strip drawing of the protective screen cabinet;
and outputting the final output consistent protection screen cabinet.
8. An intelligent equipment inspection system based on fault prediction and image recognition, based on the intelligent equipment inspection method based on fault prediction and image recognition as set forth in any one of claims 1 to 7, characterized in that: also included is a method of manufacturing a semiconductor device,
the data acquisition module is used for acquiring the inspection record, the fault alarm information and the parameter information of the equipment from the database;
the inspection plan making module is used for determining an inspection reason and an inspection plan, determining an inspection area according to the inspection plan, and determining the actual position of the fault equipment according to the number of the fault equipment;
the routing inspection route planning module is used for determining an optimal routing inspection route according to the routing inspection schedule and the ant colony algorithm;
the fault processing module is used for carrying out equipment inspection according to the inspection reasons, judging the fault reasons and the fault grades, comparing the terminal strip lines by using an image recognition algorithm, executing corresponding operation on the positioned fault protection screen cabinet, and following the processing progress of the maintenance list;
and the secondary confirmation module is used for carrying out secondary confirmation on the equipment with the problem so as to ensure that the equipment operates normally.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that: the steps of the intelligent equipment inspection method based on fault prediction and image recognition according to any one of claims 1 to 7 are realized when the processor executes the computer program.
10. A computer-readable storage medium having stored thereon a computer program, characterized by: the steps of the intelligent equipment inspection method based on fault prediction and image recognition according to any one of claims 1 to 7 are realized when the computer program is executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311196364.7A CN117373144A (en) | 2023-09-15 | 2023-09-15 | Intelligent equipment inspection method and system based on fault prediction and image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311196364.7A CN117373144A (en) | 2023-09-15 | 2023-09-15 | Intelligent equipment inspection method and system based on fault prediction and image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117373144A true CN117373144A (en) | 2024-01-09 |
Family
ID=89403126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311196364.7A Pending CN117373144A (en) | 2023-09-15 | 2023-09-15 | Intelligent equipment inspection method and system based on fault prediction and image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117373144A (en) |
-
2023
- 2023-09-15 CN CN202311196364.7A patent/CN117373144A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11474163B2 (en) | Power transformer winding fault positioning method based on deep convolutional neural network integrated with visual identification | |
| CN101710400B (en) | Method and device for evaluating risk of nuclear power station | |
| CN115329812B (en) | Bridge infrastructure anomaly monitoring method based on artificial intelligence | |
| CN114862275B (en) | Storage logistics system reliability assessment method and system based on digital twin model | |
| CN116388402B (en) | Abnormality alarm analysis method applied to power transformation equipment | |
| CN117406026A (en) | Power distribution network fault detection method suitable for distributed power supply | |
| CN113326612A (en) | Power distribution network reliability assessment method and device | |
| CN116823226A (en) | Electric power district fault monitoring system based on big data | |
| CN108093210A (en) | A kind of transformer oil level warning system and its alarm method | |
| CN117390403B (en) | Power grid fault detection method and system for new energy lighthouse power station | |
| CN117347796B (en) | Intelligent gateway-based switching equipment partial discharge diagnosis system and method | |
| CN117674407A (en) | Power grid equipment fault early warning method, device, equipment and storage medium | |
| CN114400776B (en) | Digital mirror image-based substation automation equipment state diagnosis method and system | |
| CN117373144A (en) | Intelligent equipment inspection method and system based on fault prediction and image recognition | |
| Chen et al. | Condition assessment of distribution automation remote terminal units based on double-layer improved cloud model | |
| CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence | |
| CN113159411B (en) | Method and system for testing power grid meteorological risk early warning model | |
| LU500843B1 (en) | A monitoring system and prediction method of temperature for generator carbon brush based on an infrared image | |
| CN117318024B (en) | CNN neural network-based photovoltaic power generation power prediction management method and system | |
| CN116454839A (en) | Insulation detection grounding control method | |
| CN117611135A (en) | Operation and maintenance control method and system for visual equipment | |
| CN118095845A (en) | Potential safety hazard management method and system, electronic equipment and storage medium | |
| CN117825866A (en) | Power grid short-circuit capacity on-site detection method and system based on power grid model | |
| CN117808456A (en) | Equipment fault early warning method and device based on intelligent operation management | |
| CN117269340A (en) | GIS equipment intelligent fault diagnosis method and system based on gas components |
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 |