CN117014472B - Cloud side end cooperation-based intelligent power plant equipment inspection method and system - Google Patents
Cloud side end cooperation-based intelligent power plant equipment inspection method and system Download PDFInfo
- Publication number
- CN117014472B CN117014472B CN202311129655.4A CN202311129655A CN117014472B CN 117014472 B CN117014472 B CN 117014472B CN 202311129655 A CN202311129655 A CN 202311129655A CN 117014472 B CN117014472 B CN 117014472B
- Authority
- CN
- China
- Prior art keywords
- inspection
- equipment
- path
- historical
- edge nodes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 221
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000004458 analytical method Methods 0.000 claims abstract description 100
- 238000012423 maintenance Methods 0.000 claims abstract description 76
- 238000007726 management method Methods 0.000 claims abstract description 38
- 238000012544 monitoring process Methods 0.000 claims abstract description 13
- 238000011156 evaluation Methods 0.000 claims description 84
- 230000006870 function Effects 0.000 claims description 14
- 230000036541 health Effects 0.000 claims description 14
- 238000010276 construction Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 230000004888 barrier function Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000007423 decrease Effects 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 abstract description 5
- 230000003111 delayed effect Effects 0.000 abstract description 3
- 238000012549 training Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000005856 abnormality Effects 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
- 238000001816 cooling Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000011418 maintenance treatment Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Medical Informatics (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an intelligent power plant equipment inspection method and system based on cloud side end cooperation, which relate to the technical field of intelligent inspection and comprise the following steps: deploying monitoring equipment on Q edge nodes of a target power plant, acquiring Q equipment operation data, inputting Q local equipment state analysis models of the edge nodes, acquiring Q equipment state analysis results, acquiring P edge nodes corresponding to a fault mode, sending the P edge nodes to a cloud end, calling historical inspection information including a historical inspection time set, conducting inspection path planning, generating an inspection path, conducting inspection, acquiring inspection data, conducting fault analysis, and conducting maintenance management on equipment according to the fault analysis results. The invention solves the technical problems that the traditional equipment inspection method is generally based on a periodic plan, can not acquire the running state of equipment in real time and identify potential faults in advance, and can not cooperatively manage the equipment, so that the efficiency is low and the maintenance is delayed.
Description
Technical Field
The invention relates to the technical field of intelligent patrol, in particular to an intelligent patrol method and system for power plant equipment based on cloud edge end cooperation.
Background
With the increasing demand for electricity, the power plant equipment is also becoming larger and more complex, and regular inspection is required to prevent faults and accidents, and in addition, the improvement of environmental awareness requires effective monitoring and maintenance of the power plant equipment. Therefore, plant inspection is becoming an important part of plant management.
The conventional power plant equipment inspection method also has certain defects, and the conventional equipment inspection method is generally based on a periodic plan, cannot acquire the running state of equipment in real time and identify potential faults in advance, and cannot cooperatively manage the equipment, so that the efficiency is low and the maintenance is delayed. Therefore, a certain lifting space exists for the power plant equipment inspection.
Disclosure of Invention
The utility model provides a power plant equipment intelligent inspection method and system based on cloud side cooperation, which aims at solving the technical problems that the traditional equipment inspection method is generally based on a periodic plan, the running state of equipment cannot be acquired in real time, potential faults can not be identified in advance, and cooperative management can not be carried out between the equipment, so that inefficiency and maintenance delay exist.
In view of the above problems, the application provides an intelligent power plant equipment inspection method and system based on cloud edge end cooperation.
According to a first aspect of the disclosure, a cloud side end cooperation-based intelligent power plant equipment inspection method is provided, and the method comprises the following steps: deploying monitoring equipment at Q edge nodes of a target power plant, and acquiring equipment operation parameters in real time to acquire Q pieces of equipment operation data; inputting the Q pieces of equipment operation data into an equipment state analysis model of the local Q edge nodes to obtain Q pieces of equipment state analysis results, wherein the equipment state analysis results comprise a health mode and a fault mode; p edge nodes corresponding to the fault mode are obtained, and the position information of the P edge nodes is sent to a cloud; the historical inspection information of the P edge nodes is called, and the historical inspection information comprises a historical inspection time set; according to the historical inspection time set and the position information, performing inspection path planning to generate an inspection path; the P edge nodes are inspected according to the inspection path, and inspection data are obtained; and carrying out fault analysis on the equipment of the P edge nodes according to the inspection data, and carrying out maintenance management on the equipment according to a fault analysis result.
In another aspect of the disclosure, a cloud-edge-based intelligent power plant equipment inspection system is provided, where the system is used in the above method, and the system includes: the operation data acquisition module is used for deploying monitoring equipment at Q edge nodes of a target power plant, acquiring equipment operation parameters in real time and acquiring Q pieces of equipment operation data; the analysis result acquisition module is used for inputting the Q pieces of equipment operation data into the equipment state analysis models of the Q edge nodes to obtain Q pieces of equipment state analysis results, wherein the equipment state analysis results comprise a health mode and a fault mode; the edge node acquisition module is used for acquiring P edge nodes corresponding to the fault mode and sending the position information of the P edge nodes to a cloud; the routing inspection information acquisition module is used for calling historical routing inspection information of the P edge nodes, and the historical routing inspection information comprises a historical routing inspection time set; the routing inspection path planning module is used for conducting routing inspection path planning according to the historical routing inspection time set and the position information to generate a routing inspection path; the inspection data acquisition module is used for inspecting the P edge nodes according to the inspection path to acquire inspection data; and the maintenance management module is used for carrying out fault analysis on the equipment of the P edge nodes according to the inspection data and carrying out maintenance management on the equipment according to a fault analysis result.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
deploying monitoring equipment on Q edge nodes of a target power plant, acquiring Q equipment operation data, inputting Q local equipment state analysis models of the edge nodes, acquiring Q equipment state analysis results, acquiring P edge nodes corresponding to a fault mode, sending the P edge nodes to a cloud end, calling historical inspection information including a historical inspection time set, conducting inspection path planning, generating an inspection path, conducting inspection, acquiring inspection data, conducting fault analysis, and conducting maintenance management on equipment according to the fault analysis results. The technical problems that the traditional equipment inspection method is generally based on a periodic plan, the running state of equipment cannot be obtained in real time, potential faults can not be identified in advance, and collaborative management can not be carried out among the equipment, so that inefficiency and maintenance delay exist are solved.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
Fig. 1 is a schematic flow diagram of a power plant equipment intelligent inspection method based on cloud edge end collaboration according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a possible flow for obtaining Q device status analysis results in a cloud-edge-based intelligent power plant device inspection method according to an embodiment of the present application;
fig. 3 is a schematic flow chart of a possible route generation method in the intelligent power plant equipment routing inspection method based on cloud edge end coordination according to the embodiment of the present application;
fig. 4 is a schematic diagram of a possible structure of an intelligent inspection system for power plant equipment based on cloud end coordination according to an embodiment of the present application.
Reference numerals illustrate: the system comprises an operation data acquisition module 10, an analysis result acquisition module 20, an edge node acquisition module 30, a routing inspection information acquisition module 40, a routing inspection path planning module 50, a routing inspection data acquisition module 60 and a maintenance management module 70.
Detailed Description
According to the intelligent power plant equipment inspection method based on cloud side cooperation, the technical problems that equipment operation states cannot be obtained in real time and potential faults cannot be identified in advance and collaborative management cannot be conducted among equipment, so that low efficiency and delayed maintenance exist are solved, the local analysis of edge nodes and collaborative cloud processing are achieved, factors such as equipment distribution, inspection historical data and path constraint are integrated, optimal inspection path planning is achieved, and therefore inspection time and workload are reduced, and equipment inspection efficiency is improved.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present application provides an intelligent power plant equipment inspection method based on cloud edge end coordination, where the method includes:
step S100: deploying monitoring equipment at Q edge nodes of a target power plant, and acquiring equipment operation parameters in real time to acquire Q pieces of equipment operation data;
in a preferred embodiment, on each edge node of the target power plant, such as a generator, boiler, turbine, transformer, cooling system, etc., a respective monitoring device, such as a sensor, meter or other related device, is deployed for collecting operational parameters and status information of the device. The deployed monitoring device periodically or continuously collects the operating parameters of the device, such as key parameters of temperature, pressure, vibration, current, voltage, etc., and the collected frequency can be configured as required to obtain enough data for analysis, so as to obtain the operating data of Q devices, where the data includes information of time stamps, device parameter values, device states, etc.
Step S200: inputting the Q pieces of equipment operation data into an equipment state analysis model of the local Q edge nodes to obtain Q pieces of equipment state analysis results, wherein the equipment state analysis results comprise a health mode and a fault mode;
further, as shown in fig. 2, inputting the Q pieces of device operation data into a device state analysis model local to the Q pieces of edge nodes to obtain Q pieces of device state analysis results, including:
step S210: in a first edge node, collecting historical equipment operation data in a preset historical time;
step S220: acquiring a device state index set, evaluating the historical device operation data according to the device state index set, marking the evaluation result meeting the requirement as a health mode, marking the evaluation result not meeting the requirement as a fault mode, and acquiring a historical device analysis result;
step S230: performing supervision data annotation on the historical equipment operation data and the historical equipment analysis result to obtain a first construction data set;
step S240: constructing a first equipment state analysis model, and performing supervised learning on the first equipment state analysis model by adopting the first construction data set to obtain the first equipment state analysis model with accuracy meeting the requirement;
Step S250: and continuously constructing corresponding equipment state analysis models in other edge nodes respectively, and inputting the Q pieces of equipment operation data into the corresponding equipment state analysis models to obtain Q pieces of equipment state analysis results.
In a preferred embodiment, the historical time range of the required acquisition is determined according to specific requirements and inspection objectives, for example, the last week, month or longer period may be selected as the preset historical time. Firstly, available historical equipment operation data sources such as a historical data recorder, a database, a monitoring system and the like are required to be determined, and equipment operation data in preset historical time, including equipment parameter values, time stamps and other information related to equipment states, is obtained by accessing the corresponding data sources.
According to the requirements and specific equipment types, index sets for evaluating equipment states are determined, the indexes can be used for equipment operation parameters such as temperature, pressure, current and vibration, and equipment state prompts such as abnormal alarms and fault codes, the acquired historical equipment operation data are in one-to-one correspondence with the equipment state index sets, and each piece of historical data is ensured to contain relevant information of equipment states defined in the selected index sets. And evaluating the historical equipment operation data according to the equipment state index set, and judging whether each piece of historical data meets the health mode according to the required equipment state range, threshold or rule. According to the evaluation result, marking the historical equipment operation data meeting the requirements as a health mode, marking the historical equipment operation data not meeting the requirements as a fault mode, ensuring the accurate classification and marking of the equipment states, and sorting the classified and marked historical equipment operation data into a historical equipment analysis result.
Marking corresponding historical equipment operation data according to the health mode and fault mode marks in the historical equipment analysis result, for example, binary labels can be used, 0 represents health, 1 represents faults, the supervised marked historical equipment operation data and the corresponding labels are combined together to form a first construction data set, and each data is associated with the corresponding label for subsequent model training, verification and evaluation.
Based on the BP neural network, a network structure of a first equipment state analysis model is constructed, a first constructed data set is divided into a training set and a verification set, the training set is used for parameter training and optimization of the model, and the verification set is used for evaluating performance and adjustment of the model. Using the first constructed data set as input, performing supervised learning on the equipment state analysis model, matching historical equipment operation data with corresponding labels through a loss function and an optimization algorithm of the model, and performing model training related parameter updating, weight adjustment and the like. And evaluating the trained model by using the verification set, calculating indexes such as accuracy, precision, recall rate and the like of the model, and optimizing and adjusting the model according to the evaluation result so as to improve the performance and accuracy of the model. And repeating training and verification until the accuracy of the equipment state analysis model meets the predefined requirement or reaches a certain convergence, and outputting the first equipment state analysis model.
Repeating the steps for each edge node, constructing a corresponding equipment state analysis model, inputting the operation data of the Q pieces of equipment into the corresponding equipment state analysis model according to the corresponding edge nodes, and analyzing the operation data of the Q pieces of equipment to obtain a state analysis result of each piece of equipment.
Step S300: p edge nodes corresponding to the fault mode are obtained, and the position information of the P edge nodes is sent to a cloud;
in a preferred embodiment, a device having a failure mode is identified based on the device state analysis, the failure mode being a device state in which an abnormality or failure has occurred, and P edge nodes are selected from the identified failure modes, the edge nodes being associated with the failure mode. For the selected P edge nodes, location information for each node is obtained, including longitude, latitude, altitude, or other positioning information. The position information of the P selected edge nodes is sent to the cloud end for processing through a network transmission mechanism, and the cloud end can conduct further operations such as data processing, path planning and related decisions according to the position information.
Step S400: the historical inspection information of the P edge nodes is called, and the historical inspection information comprises a historical inspection time set;
In a preferred embodiment, for the selected P edge nodes, the inspection records or historical inspection data of the nodes are obtained, and the historical inspection information includes relevant information such as the time of each inspection, inspection personnel, inspection results and the like. And extracting the historical inspection time from the historical inspection information, sorting and summarizing all inspection time points, forming a set, and recording the historical inspection time of the edge nodes. The historical inspection time can be used for analyzing the inspection frequency, time period and other conditions of the equipment and carrying out path planning by combining other factors so as to realize more efficient and accurate inspection plan.
Step S500: according to the historical inspection time set and the position information, performing inspection path planning to generate an inspection path;
further, as shown in fig. 3, according to the historical inspection time set and the position information, an inspection path is planned to generate an inspection path, which includes:
step S510: obtaining barrier position information among the P edge nodes, and carrying out path constraint according to the barrier position information to obtain a path constraint result;
step S520: acquiring P edge node coordinates according to the position information of the P edge nodes;
In a preferred embodiment, the position information of obstacles, which may be objects such as buildings, equipment, pipes, etc., present between the P edge nodes is obtained by means of different sensors or measuring devices. Based on the obstacle location information, path constraint rules are defined, such as avoiding direct crossing the obstacle, maintaining a minimum safe distance, or bypassing the obstacle, etc. And adding a path constraint condition by using a special path planning algorithm, such as an A algorithm, realizing path constraint operation, and obtaining a path constraint result according to the input obstacle position information and the path constraint operation, wherein the result indicates a feasible path obtained after path planning according to the obstacle position.
For each edge node, coordinates are extracted from its location information, and the coordinates of each edge node are recorded, e.g. saved as a set of coordinates, which contains the coordinate information of all P edge nodes.
Step S530: carrying out path planning on the P edge node coordinates according to the path constraint result to generate a path planning result;
further, performing path planning on the P edge node coordinates according to the path constraint result, to generate a path planning result, including:
Step S531: according to the path constraint result and the P edge node coordinates, randomly generating an initial patrol path set, wherein each initial patrol represents a solution and consists of the P edge node coordinates;
step S532: obtaining distance information between nodes, and constructing a fitness function according to the distance information, wherein the fitness function comprises the following formula:
wherein Y represents fitness, d represents distance information between nodes, I represents the number of pairwise matching in P edge nodes, and I represents any pair of nodes;
in a preferred embodiment, for each initial patrol path, the coordinates of P edge nodes are randomly extracted from the coordinates of P edge nodes, and screened according to the path constraint result, and if the path constraint is satisfied, the coordinates of P edge nodes are sequentially added to the initial patrol paths in random order, and the generated initial patrol paths are added to the initial patrol path set, and the steps are repeated to generate a plurality of random initial patrol paths, wherein each initial patrol path represents a possible solution and includes the coordinates of all P edge nodes.
Distance information between nodes is obtained, the information is used for measuring the spatial distance between the nodes, the distance information between any pair of P edge nodes is calculated and added to the fitness function, the node pairs with shorter distance can obtain higher fitness, and the distance information of all the node pairs is accumulated to obtain a final fitness value Y. Through the fitness function, the adaptability of each routing inspection path can be evaluated by considering the distance information among the nodes, and the routing inspection path with a shorter distance has a higher fitness value.
Step S533: and evaluating the initial inspection path set according to the fitness function, and generating an optimal path planning result according to a path evaluation result.
Further, the method includes evaluating the initial inspection path set according to the fitness function, and generating an optimal path planning result according to a path evaluation result, including:
step S5331: randomly selecting a first path evaluation result from the path evaluation results as a current optimal evaluation result;
step S5332: continuing to randomly select a second path evaluation result from the path evaluation results;
step S5333: judging whether the second path evaluation result is larger than the first path evaluation result, if so, taking the second path evaluation result as an optimal evaluation result;
step S5334: if not, calculating probability, randomly generating numbers in [0,1], judging whether the probability is larger than the probability, and taking the second path evaluation result as an optimal evaluation result if not, wherein the probability is calculated by the following formula:
wherein Y is 2 For the second path evaluation result, Y 1 C is a constant which decreases with the increase of the optimizing iteration number for the first path evaluation result;
step S5335: and continuing to perform iterative optimization until the preset iterative times are reached, and outputting an initial inspection path corresponding to the final optimal evaluation result as an optimal path planning result.
In a preferred embodiment, a path evaluation result is randomly selected from the path evaluation results as a current optimal evaluation result, and further path optimization is continued with the result as a reference to improve the quality and efficiency of the patrol path.
The second path evaluation result is randomly selected again, so that another selection different from the first evaluation result can be obtained, randomness is introduced, the search space is enlarged, and the possibility of finding a better routing inspection path is improved.
Comparing the first path evaluation result with the second path evaluation result, if the second path evaluation result is larger than the first path evaluation result, setting the second path evaluation result as the current optimal evaluation result, and selecting the path evaluation result with higher fitness value as the optimal evaluation result through the judging process, so that the quality and efficiency of the inspection path can be improved.
If the second path evaluation result is not greater than the first path evaluation result, calculating the probability according to the formula, then randomly generating a numerical value in the range of [0,1], judging whether the generated random number is greater than the calculated probability, if so, taking the second path evaluation result as an optimal evaluation result, and if not, keeping the first path evaluation result as the optimal evaluation result. This method allows decisions to be made based on the probability that although the second path evaluation result may be poor, there is a probability that a certain probability is chosen as the optimal evaluation result, by introducing randomness, different solution spaces can be explored during the search and trapping in locally optimal solutions is avoided.
And determining the iteration times to be carried out, for example, 500 times, setting the iteration counter to 0, repeating the steps to obtain a new optimal evaluation result and a corresponding initial routing inspection path, judging whether the iteration counter reaches the preset iteration times, if not, continuing iteration, and if so, outputting the initial routing inspection path corresponding to the final optimal evaluation result as an optimal path planning result. Through iterative optimization, the inspection path is optimized in each iteration, the optimal evaluation result is updated, the quality and effect of the inspection path can be gradually improved, and finally, after the preset iteration times are reached, the initial inspection path with the optimal fitness value can be obtained and is output as the optimal path planning result.
Step S540: acquiring last inspection time and historical inspection frequency of the P edge nodes according to the historical inspection time set;
step S550: the P edge nodes are subjected to priority ranking according to the last inspection time and the historical inspection frequency, and node priorities are obtained;
step S560: and adjusting the path planning result according to the node priority to acquire a routing inspection path.
Extracting the last time of inspection of each edge node from the historical inspection time set, wherein the last time of inspection refers to the latest inspection time point, and sequencing the historical inspection time of each edge node according to the time sequence for subsequent calculation and analysis; according to the ordered inspection time, the historical inspection frequency is determined by counting the time interval between adjacent inspection time points, so that the historical inspection frequency is calculated on each edge node, and the frequency can be expressed as times/time units, such as once every week.
And calculating the priority of each edge node according to the last inspection time and the historical inspection frequency, for example, determining the priority according to the interval between the last inspection time and the current time, determining the priority according to the historical inspection frequency, and sorting the P edge nodes in descending order according to the calculated priority so as to obtain the priority order of the nodes.
According to the priority of the nodes, the path planning result is adjusted, and the nodes with higher priority are illustratively placed at the starting point or the end point of the path so as to carry out inspection on the equipment with higher priority as early as possible or as late as possible, the order of the nodes in the path is adjusted, and the nodes with higher priority are adjacent or close together so as to facilitate continuous inspection of the equipment with higher priority. And outputting the adjusted path as a final routing inspection path, wherein the routing inspection path comprises a starting point, an ending point and a node sequence of the path, so that subsequent routing inspection operation and navigation guidance are facilitated.
Further, the present application further includes:
step S561: acquiring a preset maintenance period;
step S562: comparing the historical inspection frequency according to the preset maintenance period to obtain a comparison result, wherein the comparison result is used as a first influence factor;
step S563: acquiring the historical overhaul degree of the P edge nodes, and taking the historical overhaul degree as a second influencing factor;
step S564: acquiring the historical overhaul times of the P edge nodes, and taking the historical overhaul times as a third influencing factor;
step S565: weight distribution is carried out on the first influence factor, the second influence factor and the third influence factor, equipment life attenuation degree analysis is carried out on the P edge nodes according to the distribution result, and equipment life attenuation degree is obtained;
step S566: and adjusting the path planning result according to the equipment life attenuation degree to obtain a patrol path.
In a preferred embodiment, the power plant or the equipment management side determines the advice and guidance of equipment maintenance according to the equipment characteristics, operation requirements, relevant standards and other factors, wherein the advice and guidance comprises a preset maintenance period, or summarizes and analyzes the maintenance requirements and period of the equipment according to the actual operation experience and history data of the equipment, for example, according to the past maintenance plan and implementation condition, evaluates the failure rate, service life characteristics and other factors of the equipment, thereby determining a reasonable maintenance period.
Taking a preset maintenance period as a reference value, which is a recommended maintenance interval of the equipment or the system under normal conditions, comparing the inspection frequency of each edge node with the preset maintenance period, and performing division operation on the inspection frequency and the preset maintenance period to obtain a ratio, wherein the ratio is smaller than 1, the inspection frequency of the equipment is lower than the preset period, and the ratio is larger than 1, and the inspection frequency is higher than the preset period. And obtaining the comparison result of each edge node according to the comparison result. The comparison result is used as a first influencing factor, and according to the specific situation of the comparison result, whether the inspection frequency needs to be adjusted, the maintenance plan is optimized or other measures are taken to enable the actual inspection to meet the requirement of the preset maintenance period.
The method comprises the steps of obtaining historical overhaul records of each edge node, wherein the records comprise operation conditions of equipment maintenance, repair, update and the like, evaluating the historical overhaul records of each edge node, and determining an index or index to represent the historical overhaul degree, such as overhaul times, maintenance activity frequency or a qualitative evaluation, such as patrol inspection and maintenance plan compliance of key equipment and the like, wherein the historical overhaul degree is used as a second influencing factor.
And acquiring overhaul frequency information in the historical overhaul record of each edge node, wherein the overhaul frequency information comprises operation conditions in the aspects of equipment maintenance, repair, update and the like. And counting the overhaul times in the historical overhaul records of each edge node, wherein the historical overhaul times reflect the maintenance frequency and possible fault conditions of the equipment, are beneficial to measuring the reliability and the maintenance importance of the equipment, and take the historical overhaul times as a third influencing factor.
The first influence factor, the second influence factor and the third influence factor are assigned weights, the weights represent the relative importance degree of each factor on the service life attenuation degree of the equipment, the first influence factor, the second influence factor and the third influence factor and the corresponding weights thereof are combined for each edge node, for example, weighted summation can be adopted for calculation, the service life attenuation degree of the equipment is obtained, and the relative health state of the equipment or the node which needs more frequent maintenance can be judged according to the relative size of the attenuation degree, so that the service life state of the equipment of the edge node can be quantitatively evaluated and compared.
According to the equipment life attenuation degree, the path planning result is adjusted, and the node with higher equipment life attenuation degree is placed at the starting point or the end point of the path in an exemplary manner so as to preferentially inspect the equipment with poorer state; the order of the devices in the path is adjusted, and the devices with higher attenuation degree are adjacent or close together so as to intensively inspect the nodes which need more frequent maintenance. And outputting the adjusted path as a final inspection path.
Step S600: the P edge nodes are inspected according to the inspection path, and inspection data are obtained;
in a preferred embodiment, P edge nodes are sequentially inspected according to the sequence specified by the inspection path, that is, the P edge nodes go to the position of each node, and the corresponding inspection operation is performed. As each edge node is inspected, relevant data is collected, including equipment operating parameters, status information, sensor readings, or other information regarding equipment performance. The inspection data collected from each edge node is recorded and stored, including time stamps, node identifiers, parameter values, etc., ensuring accuracy, integrity and traceability of the data. By inspecting the P edge nodes according to the inspection path and acquiring inspection data, real-time information about the state and operation condition of the device can be obtained, and the data can be used for subsequent fault analysis, maintenance management, predictive maintenance and other works.
Step S700: and carrying out fault analysis on the equipment of the P edge nodes according to the inspection data, and carrying out maintenance management on the equipment according to a fault analysis result.
In a preferred embodiment, the inspection data is processed and analyzed using fault analysis algorithms, which may be rule-based, machine learning, statistical analysis, etc., to identify any potential faults or anomalies. According to the result of the fault analysis algorithm, the state of the equipment is judged by comparing the operation parameters of the equipment with a predefined fault mode, so that the abnormal type and the abnormal grade of the equipment of each edge node are determined, corresponding maintenance management strategies including maintenance priority, urgency, required resources, maintenance schemes and the like are determined according to the fault analysis result of the equipment, and corresponding measures are taken to carry out maintenance treatment on the equipment according to the maintenance management decisions. Thus, the possible problems of the equipment can be found and solved in time, and the reliability and the operation efficiency of the equipment are improved.
Further, the present application further includes:
step S810: acquiring a maintenance management record, wherein the maintenance management record comprises problem information in a maintenance process;
step S820: uploading the problem information to a cloud end to generate an adjustment suggestion;
step S830: and generating a secondary inspection path according to the adjustment suggestion, and carrying out maintenance management on the equipment.
In a preferred embodiment, after performing maintenance management of the equipment according to the failure analysis result, accessing the maintenance management system, acquiring maintenance management records by using the query function of the maintenance management system, and acquiring information related to the problem description and maintenance process corresponding to each maintenance in the retrieved maintenance records, wherein the information comprises equipment failure description, error codes or alarms occurring, solutions, used tools and materials, completed maintenance work and the like.
Uploading the problem information to a cloud, performing data processing and analysis on a cloud platform, performing fault diagnosis according to the uploaded problem information, and generating relevant adjustment suggestions based on the processed and analyzed data, wherein the suggestions comprise suggestions in aspects of common fault modes, maintenance requirements, optimized path planning and the like identified according to the problem information.
Analyzing the generated adjustment advice, knowing the content, purpose and implementation of the advice, properly explaining and evaluating according to the requirement, re-planning the inspection path according to the adjustment advice, taking factors such as maintenance tasks, equipment positions and time constraints in the advice into consideration, generating a secondary inspection path, and organizing and arranging corresponding maintenance management work according to the generated secondary inspection path. By generating a secondary inspection path according to the adjustment advice and implementing equipment maintenance management, the identified problems can be timely inspected and handled, and the reliability and performance of the equipment are improved.
In summary, the intelligent power plant equipment inspection method and system based on cloud edge end cooperation provided by the embodiment of the application have the following technical effects:
deploying monitoring equipment on Q edge nodes of a target power plant, acquiring Q equipment operation data, inputting Q local equipment state analysis models of the edge nodes, acquiring Q equipment state analysis results, acquiring P edge nodes corresponding to a fault mode, sending the P edge nodes to a cloud end, calling historical inspection information including a historical inspection time set, conducting inspection path planning, generating an inspection path, conducting inspection, acquiring inspection data, conducting fault analysis, and conducting maintenance management on equipment according to the fault analysis results.
The technical problems that the traditional equipment inspection method is generally based on a periodic plan, the running state of equipment cannot be obtained in real time, potential faults can not be identified in advance, and collaborative management can not be carried out among the equipment, so that inefficiency and maintenance delay exist are solved.
Example two
Based on the same inventive concept as the intelligent inspection method of the power plant equipment based on cloud side cooperation in the foregoing embodiment, as shown in fig. 4, the present application provides an intelligent inspection system of the power plant equipment based on cloud side cooperation, where the system includes:
the operation data acquisition module 10 is used for deploying monitoring equipment at Q edge nodes of a target power plant, acquiring equipment operation parameters in real time and acquiring Q pieces of equipment operation data;
the analysis result acquisition module 20 is configured to input the Q pieces of equipment operation data into an equipment state analysis model local to the Q pieces of edge nodes, to obtain Q pieces of equipment state analysis results, where the equipment state analysis results include a health mode and a fault mode;
The edge node obtaining module 30 is configured to obtain P edge nodes corresponding to the failure mode, and send position information of the P edge nodes to a cloud;
the inspection information acquisition module 40 is configured to retrieve historical inspection information of the P edge nodes, where the historical inspection information includes a historical inspection time set;
the inspection path planning module 50 is configured to perform inspection path planning according to the historical inspection time set and the position information, and generate an inspection path;
the inspection data acquisition module 60, where the inspection data acquisition module 60 is configured to perform inspection on the P edge nodes according to the inspection path to acquire inspection data;
and the maintenance management module 70 is used for carrying out fault analysis on the equipment of the P edge nodes according to the inspection data, and carrying out maintenance management on the equipment according to a fault analysis result.
Further, the system further comprises:
the historical data acquisition module is used for acquiring historical equipment operation data in a preset historical time in the first edge node;
The historical analysis result acquisition module is used for acquiring a device state index set, evaluating the historical device operation data according to the device state index set, marking the evaluation result meeting the requirement as a health mode, marking the evaluation result not meeting the requirement as a fault mode, and acquiring a historical device analysis result;
the monitoring data labeling module is used for labeling the monitoring data of the historical equipment operation data and the analysis result of the historical equipment to obtain a first construction data set;
the model construction module is used for constructing a first equipment state analysis model, and performing supervised learning on the first equipment state analysis model by adopting the first construction data set to obtain the first equipment state analysis model with accuracy meeting the requirement;
and the state analysis result acquisition module is used for continuously constructing corresponding equipment state analysis models in other edge nodes respectively, inputting the Q pieces of equipment operation data into the corresponding equipment state analysis models and obtaining Q pieces of equipment state analysis results.
Further, the system further comprises:
the path constraint module is used for acquiring the barrier position information among the P edge nodes, and performing path constraint according to the barrier position information to acquire a path constraint result;
The node coordinate acquisition module is used for acquiring P edge node coordinates according to the position information of the P edge nodes;
the path planning module is used for carrying out path planning on the P edge node coordinates according to the path constraint result to generate a path planning result;
the historical information acquisition module is used for acquiring the last inspection time and the historical inspection frequency of the P edge nodes according to the historical inspection time set;
the priority ordering module is used for ordering the priorities of the P edge nodes according to the last inspection time and the historical inspection frequency to obtain node priorities;
and the adjusting module is used for adjusting the path planning result according to the node priority and acquiring a routing inspection path.
Further, the system further comprises:
the initial patrol path generation module is used for randomly generating an initial patrol path set according to the path constraint result and the P edge node coordinates, wherein each initial patrol represents a solution and consists of the P edge node coordinates;
the distance information acquisition module is used for acquiring the distance information between the nodes and constructing a fitness function according to the distance information, wherein the fitness function is represented by the following formula:
Wherein Y represents fitness, d represents distance information between nodes, I represents the number of pairwise matching in P edge nodes, and I represents any pair of nodes;
and the evaluation module is used for evaluating the initial inspection path set according to the fitness function and generating an optimal path planning result according to the path evaluation result.
Further, the system further comprises:
the first evaluation result acquisition module is used for randomly selecting a first path evaluation result from the path evaluation results as a current optimal evaluation result;
the second evaluation result acquisition module is used for continuing to randomly select a second path evaluation result from the path evaluation results;
the judging module is used for judging whether the second path evaluation result is larger than the first path evaluation result or not, and if so, taking the second path evaluation result as an optimal evaluation result;
the judging module is used for calculating the probability and randomly generating numbers in [0,1] to judge whether the probability is larger than the probability, and taking the second path evaluation result as the optimal evaluation result under the condition of no, wherein the probability is calculated as follows:
wherein Y is 2 For the second path evaluation result, Y 1 C is a constant which decreases with the increase of the optimizing iteration number for the first path evaluation result;
and the iterative optimization module is used for continuing iterative optimization until the preset iterative times are reached, and outputting an initial inspection path corresponding to the final optimal evaluation result as an optimal path planning result.
Further, the system further comprises:
the maintenance period acquisition module is used for acquiring a preset maintenance period;
the first influence factor acquisition module is used for comparing the historical inspection frequency according to the preset maintenance period to acquire a comparison result, and the comparison result is used as a first influence factor;
the second influence factor obtaining module is used for obtaining the historical overhaul degrees of the P edge nodes and taking the historical overhaul degrees as a second influence factor;
the third influence factor obtaining module is used for obtaining the historical overhaul times of the P edge nodes and taking the historical overhaul times as a third influence factor;
the attenuation degree analysis module is used for carrying out weight distribution on the first influence factor, the second influence factor and the third influence factor, carrying out equipment life attenuation degree analysis on the P edge nodes according to the distribution result and obtaining equipment life attenuation degree;
And the adjustment module is used for adjusting the path planning result according to the equipment life attenuation degree to obtain a patrol path.
Further, the system further comprises:
the management record acquisition module is used for acquiring maintenance management records, wherein the maintenance management records comprise problem information in the maintenance process;
the adjustment suggestion generation module is used for uploading the problem information to the cloud end to generate adjustment suggestions;
and the secondary inspection module is used for generating a secondary inspection path according to the adjustment suggestion and carrying out maintenance management on the equipment.
Through the foregoing detailed description of the intelligent inspection method for the power plant equipment based on the cloud side coordination, those skilled in the art can clearly know the intelligent inspection method and the intelligent inspection system for the power plant equipment based on the cloud side coordination in the embodiment, and for the device disclosed in the embodiment, the description is simpler because the device corresponds to the method disclosed in the embodiment, and relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (5)
1. The intelligent power plant equipment inspection method based on cloud side end cooperation is characterized by comprising the following steps of:
deploying monitoring equipment at Q edge nodes of a target power plant, and acquiring equipment operation parameters in real time to acquire Q pieces of equipment operation data;
inputting the Q pieces of equipment operation data into an equipment state analysis model of the local Q edge nodes to obtain Q pieces of equipment state analysis results, wherein the equipment state analysis results comprise a health mode and a fault mode;
p edge nodes corresponding to the fault mode are obtained, and the position information of the P edge nodes is sent to a cloud;
the historical inspection information of the P edge nodes is called, and the historical inspection information comprises a historical inspection time set;
according to the historical inspection time set and the position information, performing inspection path planning to generate an inspection path;
the P edge nodes are inspected according to the inspection path, and inspection data are obtained;
performing fault analysis on the equipment of the P edge nodes according to the inspection data, and performing maintenance management on the equipment according to a fault analysis result;
and performing routing inspection path planning according to the historical routing inspection time set and the position information to generate a routing inspection path, wherein the routing inspection path comprises the following steps:
Obtaining barrier position information among the P edge nodes, and carrying out path constraint according to the barrier position information to obtain a path constraint result;
acquiring P edge node coordinates according to the position information of the P edge nodes;
carrying out path planning on the P edge node coordinates according to the path constraint result to generate a path planning result;
acquiring last inspection time and historical inspection frequency of the P edge nodes according to the historical inspection time set;
the P edge nodes are subjected to priority ranking according to the last inspection time and the historical inspection frequency, and node priorities are obtained;
adjusting the path planning result according to the node priority to obtain a routing inspection path;
and carrying out path planning on the P edge node coordinates according to the path constraint result to generate a path planning result, wherein the path planning result comprises the following steps:
according to the path constraint result and the P edge node coordinates, randomly generating an initial patrol path set, wherein each initial patrol represents a solution and consists of the P edge node coordinates;
acquiring distance information between nodes, and constructing an adaptability function according to the distance information;
Evaluating the initial inspection path set according to the fitness function, and generating an optimal path planning result according to a path evaluation result;
evaluating the initial inspection path set according to the fitness function, and generating an optimal path planning result according to a path evaluation result, wherein the method comprises the following steps:
randomly selecting a first path evaluation result from the path evaluation results as a current optimal evaluation result;
continuing to randomly select a second path evaluation result from the path evaluation results;
judging whether the second path evaluation result is larger than the first path evaluation result, if so, taking the second path evaluation result as an optimal evaluation result;
if not, calculating probability, randomly generating numbers in [0,1], judging whether the probability is larger than the probability, and taking the second path evaluation result as an optimal evaluation result if not, wherein the probability is calculated by the following formula:
wherein Y is 2 For the second path evaluation result, Y 1 C is a constant which decreases with the increase of the optimizing iteration number for the first path evaluation result;
and continuing to perform iterative optimization until the preset iterative times are reached, and outputting an initial inspection path corresponding to the final optimal evaluation result as an optimal path planning result.
2. The method of claim 1, wherein inputting the Q device operational data into a device state analysis model local to the Q edge nodes to obtain Q device state analysis results comprises:
in a first edge node, collecting historical equipment operation data in a preset historical time;
acquiring a device state index set, evaluating the historical device operation data according to the device state index set, marking the evaluation result meeting the requirement as a health mode, marking the evaluation result not meeting the requirement as a fault mode, and acquiring a historical device analysis result;
performing supervision data annotation on the historical equipment operation data and the historical equipment analysis result to obtain a first construction data set;
constructing a first equipment state analysis model, and performing supervised learning on the first equipment state analysis model by adopting the first construction data set to obtain the first equipment state analysis model with accuracy meeting the requirement;
and continuously constructing corresponding equipment state analysis models in other edge nodes respectively, and inputting the Q pieces of equipment operation data into the corresponding equipment state analysis models to obtain Q pieces of equipment state analysis results.
3. The method as recited in claim 1, further comprising:
acquiring a preset maintenance period;
comparing the historical inspection frequency according to the preset maintenance period to obtain a comparison result, wherein the comparison result is used as a first influence factor;
acquiring the historical overhaul degree of the P edge nodes, and taking the historical overhaul degree as a second influencing factor;
acquiring the historical overhaul times of the P edge nodes, and taking the historical overhaul times as a third influencing factor;
weight distribution is carried out on the first influence factor, the second influence factor and the third influence factor, equipment life attenuation degree analysis is carried out on the P edge nodes according to the distribution result, and equipment life attenuation degree is obtained;
and adjusting the path planning result according to the equipment life attenuation degree to obtain a patrol path.
4. The method as recited in claim 1, further comprising:
acquiring a maintenance management record, wherein the maintenance management record comprises problem information in a maintenance process;
uploading the problem information to a cloud end to generate an adjustment suggestion;
and generating a secondary inspection path according to the adjustment suggestion, and carrying out maintenance management on the equipment.
5. The intelligent power plant equipment inspection system based on cloud side cooperation is characterized by being used for implementing the intelligent power plant equipment inspection method based on cloud side cooperation as claimed in any one of claims 1-4, and comprises the following steps:
the operation data acquisition module is used for deploying monitoring equipment at Q edge nodes of a target power plant, acquiring equipment operation parameters in real time and acquiring Q pieces of equipment operation data;
the analysis result acquisition module is used for inputting the Q pieces of equipment operation data into the equipment state analysis models of the Q edge nodes to obtain Q pieces of equipment state analysis results, wherein the equipment state analysis results comprise a health mode and a fault mode;
the edge node acquisition module is used for acquiring P edge nodes corresponding to the fault mode and sending the position information of the P edge nodes to a cloud;
the routing inspection information acquisition module is used for calling historical routing inspection information of the P edge nodes, and the historical routing inspection information comprises a historical routing inspection time set;
the routing inspection path planning module is used for conducting routing inspection path planning according to the historical routing inspection time set and the position information to generate a routing inspection path;
The inspection data acquisition module is used for inspecting the P edge nodes according to the inspection path to acquire inspection data;
and the maintenance management module is used for carrying out fault analysis on the equipment of the P edge nodes according to the inspection data and carrying out maintenance management on the equipment according to a fault analysis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311129655.4A CN117014472B (en) | 2023-09-04 | 2023-09-04 | Cloud side end cooperation-based intelligent power plant equipment inspection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311129655.4A CN117014472B (en) | 2023-09-04 | 2023-09-04 | Cloud side end cooperation-based intelligent power plant equipment inspection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117014472A CN117014472A (en) | 2023-11-07 |
| CN117014472B true CN117014472B (en) | 2024-03-22 |
Family
ID=88569163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311129655.4A Active CN117014472B (en) | 2023-09-04 | 2023-09-04 | Cloud side end cooperation-based intelligent power plant equipment inspection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117014472B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236916B (en) * | 2023-11-13 | 2024-02-06 | 湖南承希科技有限公司 | Comprehensive safety inspection method for intelligent power plant |
| CN117499439A (en) * | 2023-11-14 | 2024-02-02 | 北京理工大学前沿技术研究院 | Inspection data processing system and method based on industrial Internet of things |
| CN117391454A (en) * | 2023-11-16 | 2024-01-12 | 龙滩水电开发有限公司龙滩水力发电厂 | Industrial management system and method based on cloud edge cooperation |
| CN117764303B (en) * | 2023-11-17 | 2024-06-21 | 南京公路发展(集团)有限公司 | Road inspection data analysis system and method based on artificial intelligence |
| CN117560470B (en) * | 2023-11-17 | 2024-06-11 | 龙滩水电开发有限公司龙滩水力发电厂 | Cloud edge end cooperative distributed industrial television monitoring and identifying system and method |
| CN117390403B (en) * | 2023-12-11 | 2024-04-12 | 交通运输部东海航海保障中心上海航标处 | Power grid fault detection method and system for new energy lighthouse power station |
| CN117554885B (en) * | 2023-12-13 | 2024-05-07 | 浙江万昌电力设备有限公司 | Intelligent metering box operation abnormality detection method and system |
| CN117554751A (en) * | 2023-12-14 | 2024-02-13 | 胡波 | Power system fault diagnosis system based on artificial intelligence |
| CN117782097B (en) * | 2023-12-26 | 2024-06-11 | 湖南比邻星科技有限公司 | Cloud platform-based robot inspection path planning method and system |
| CN117670313B (en) * | 2024-02-01 | 2024-04-30 | 西安咸林能源科技有限公司 | Power plant inspection method, power plant inspection system and storable medium |
| CN117741372B (en) * | 2024-02-20 | 2024-05-10 | 深圳市华科科技有限公司 | On-line monitoring method and system for electrical equipment aiming at insulativity |
| CN118096131A (en) * | 2024-04-23 | 2024-05-28 | 青岛华林电力有限公司 | Operation and maintenance inspection method based on electric power scene model |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112527613A (en) * | 2020-11-30 | 2021-03-19 | 北京航天智造科技发展有限公司 | Equipment fault maintenance method and device based on cloud edge cooperation |
| CN114093052A (en) * | 2021-11-17 | 2022-02-25 | 中国工商银行股份有限公司 | Intelligent inspection method and system suitable for machine room management |
| CN114826147A (en) * | 2022-04-29 | 2022-07-29 | 华电电力科学研究院有限公司 | Fault inspection method, device and medium for photovoltaic power station |
| CN115857535A (en) * | 2022-10-12 | 2023-03-28 | 深圳市中燃科技有限公司 | Method and system for inspecting gas pipeline by using unmanned aerial vehicle |
| CN115994046A (en) * | 2023-03-22 | 2023-04-21 | 远洋亿家物业服务股份有限公司 | High-precision identification method and system for equipment inspection |
| CN116506470A (en) * | 2023-06-26 | 2023-07-28 | 成都秦川物联网科技股份有限公司 | Intelligent gas GIS-based safety inspection method and Internet of things system |
-
2023
- 2023-09-04 CN CN202311129655.4A patent/CN117014472B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112527613A (en) * | 2020-11-30 | 2021-03-19 | 北京航天智造科技发展有限公司 | Equipment fault maintenance method and device based on cloud edge cooperation |
| CN114093052A (en) * | 2021-11-17 | 2022-02-25 | 中国工商银行股份有限公司 | Intelligent inspection method and system suitable for machine room management |
| CN114826147A (en) * | 2022-04-29 | 2022-07-29 | 华电电力科学研究院有限公司 | Fault inspection method, device and medium for photovoltaic power station |
| CN115857535A (en) * | 2022-10-12 | 2023-03-28 | 深圳市中燃科技有限公司 | Method and system for inspecting gas pipeline by using unmanned aerial vehicle |
| CN115994046A (en) * | 2023-03-22 | 2023-04-21 | 远洋亿家物业服务股份有限公司 | High-precision identification method and system for equipment inspection |
| CN116506470A (en) * | 2023-06-26 | 2023-07-28 | 成都秦川物联网科技股份有限公司 | Intelligent gas GIS-based safety inspection method and Internet of things system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117014472A (en) | 2023-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117014472B (en) | Cloud side end cooperation-based intelligent power plant equipment inspection method and system | |
| CN109146093B (en) | Power equipment field investigation method based on learning | |
| CN110555551B (en) | Air quality big data management method and system for smart city | |
| CN112817280A (en) | Implementation method for intelligent monitoring alarm system of thermal power plant | |
| CN107430715A (en) | Cascade identification in building automation | |
| US11959777B2 (en) | Methods and Internet of Things (IoT) systems for safety management of smart gas underground gas pipeline networks | |
| CN109523077B (en) | Wind power prediction method | |
| CN115994046B (en) | High-precision identification method and system for equipment inspection | |
| US20240060605A1 (en) | Method, internet of things (iot) system, and storage medium for smart gas abnormal data analysis | |
| CN114611372A (en) | Industrial equipment health prediction method based on Internet of things edge calculation | |
| CN117630758B (en) | Method and system for monitoring health state of power station transformer | |
| CN117436846B (en) | Equipment predictive maintenance method and system based on neural network | |
| CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
| CN117930815A (en) | Wind turbine generator remote fault diagnosis method and system based on cloud platform | |
| CN117705121A (en) | Multi-dimensional inspection system for power plant | |
| CN110766248B (en) | Workshop artificial factor reliability assessment method based on SHEL and interval intuitionistic fuzzy assessment | |
| CN114897262A (en) | Rail transit equipment fault prediction method based on deep learning | |
| CN115330237A (en) | Power distribution Internet of things maturity evaluation method | |
| CN114266370A (en) | Method and system for generating fault handling plan of power grid equipment in typhoon meteorological environment on line and storage medium | |
| Moehrle | Generic self-learning decision support system for large-scale disasters. | |
| CN117390590B (en) | CIM model-based data management method and system | |
| CN114492877B (en) | Operation and maintenance analysis method and device of business system | |
| CN112699927B (en) | Pipeline fault diagnosis method and system | |
| CN118278914A (en) | Method for realizing equipment fault rush repair based on GIS (geographic information System) | |
| CN117853078B (en) | Unmanned aerial vehicle-based dynamic safety alarm system and method for construction site of building engineering |
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 |