Unmanned intelligent inspection method and system for intelligent power plant

Abstract

The invention discloses an unmanned intelligent inspection method and system for an intelligent power plant, and relates to the technical field of power plant inspection, and the method comprises the steps: carrying out the inspection partitioning according to the function partitioning and environment attribute information of a target power plant, and arranging an inspection equipment group and an edge processing node; receiving real-time environment monitoring data through each edge node, adaptively optimizing a conventional routing inspection scheme, and executing intelligent routing inspection to obtain a routing inspection data set; and obtaining a local inspection result through independent anomaly analysis, uploading the local inspection result to a master control center for correlation influence analysis, and correcting the local inspection result. The technical problem that in the prior art, along with the complexity trend of an intelligent power plant, a traditional inspection method cannot adapt to complex and changeable inspection requirements, so that the inspection efficiency and accuracy are low is solved, and real-time monitoring and quick response of the operation state of the power plant are achieved through unmanned intelligent inspection. And the inspection efficiency and the data accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the field of power plant inspection technology, and in particular to an unmanned intelligent inspection method and system for a smart power plant. Background Art

[0002] With the rapid development and intelligent transformation of the power industry, the construction of smart power plants has become an important trend in the power industry. In modern smart power plants, with the expansion of equipment scale and the increase of system complexity, traditional manual inspection methods are difficult to meet the needs of efficient and accurate operation and maintenance. Especially in scenarios with complex environments and dense equipment, traditional inspection methods lack the ability to dynamically adjust inspection strategies based on real-time environment and equipment conditions, and cannot adapt to inspection needs under different conditions, resulting in low inspection efficiency and accuracy, affecting the safe operation of power plants and the long-term stability of equipment. Summary of the invention

[0003] The present application provides an unmanned intelligent inspection method and system for smart power plants, which is used to solve the technical problem in the prior art that as smart power plants become more complex, traditional inspection methods cannot adapt to complex and changeable inspection needs, resulting in low inspection efficiency and accuracy.

[0004] The first aspect of the present application provides an unmanned intelligent inspection method for a smart power plant, the method comprising: dividing the inspection zones according to the functional zoning information and environmental attribute information of the target power plant to obtain multiple inspection zones; deploying multiple inspection equipment groups and multiple edge processing nodes based on the multiple inspection zones, the multiple inspection equipment groups are configured with multiple conventional inspection schemes; the multiple edge processing nodes receive real-time environmental monitoring data of the corresponding inspection zones, adaptively optimize the multiple conventional inspection schemes, obtain multiple dynamic optimization schemes to perform partition intelligent inspections, and obtain multiple inspection data sets; through the multiple edge processing nodes, perform independent inspection anomaly analysis in combination with the inspection data sets to obtain multiple local inspection results; upload the multiple local inspection results to the main control center, the main control center performs partition correlation impact analysis in combination with the real-time environmental monitoring data of each inspection zone, and corrects the local inspection results according to the analysis results.

[0005] In a second aspect of the present application, an unmanned intelligent inspection system for a smart power plant is provided, the system comprising: an inspection partition division module, the inspection partition division module is used to perform inspection partition division according to functional partition information and environmental attribute information of the target power plant to obtain multiple inspection partitions; an inspection equipment group layout module, the inspection equipment group layout module is used to layout multiple inspection equipment groups and multiple edge processing nodes based on the multiple inspection partitions, the multiple inspection equipment groups are configured with multiple conventional inspection schemes; an inspection scheme optimization module, the inspection scheme optimization module is used to receive real-time environment information of corresponding inspection partitions by the multiple edge processing nodes The invention relates to a method for realizing intelligent inspection of partitions based on the real-time environmental monitoring data, adaptively optimizing the multiple conventional inspection schemes, obtaining multiple dynamic optimization schemes to perform intelligent inspection of partitions, and obtaining multiple inspection data sets; an independent inspection anomaly analysis module, which is used to perform independent inspection anomaly analysis through the multiple edge processing nodes in combination with the inspection data sets to obtain multiple local inspection results; a local inspection result correction module, which is used to upload the multiple local inspection results to the main control center, which performs partition correlation impact analysis based on the real-time environmental monitoring data of each inspection partition, and corrects the local inspection results according to the analysis results.

[0006] In a third aspect, the present application provides an electronic device, comprising: a processor, the processor is coupled to a memory, the memory is used to store a program, when the program is executed by the processor, the system executes the method of the first aspect.

[0007] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the method of the first aspect when executed by a processor.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The unmanned intelligent inspection method and system for smart power plants provided in this application relate to the field of power plant inspection technology. By dividing the power plant inspection zones, deploying inspection equipment groups and edge processing nodes, receiving real-time environmental monitoring data, optimizing conventional inspection plans and performing intelligent inspections, abnormal analysis is performed based on the data collected during the inspections, local inspection results are generated and uploaded to the master control center, which combines real-time data to perform correlation impact analysis and correct the inspection results. This solves the technical problem in the prior art that with the increasing complexity of smart power plants, traditional inspection methods cannot adapt to complex and changeable inspection needs, resulting in low inspection efficiency and accuracy. This achieves the technical effect of real-time monitoring and rapid response to the operating status of power plants through unmanned intelligent inspections, and improving inspection efficiency and data accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A flow chart of an unmanned intelligent inspection method for a smart power plant provided in an embodiment of the present application;

[0012] Figure 2 A schematic diagram of the structure of an unmanned intelligent inspection system for a smart power plant provided in an embodiment of the present application;

[0013] Figure 3 A structural schematic diagram of an electronic device is provided for the present application.

[0014] Explanation of the reference numerals: inspection zone division module 11, inspection equipment group layout module 12, inspection plan optimization module 13, independent inspection anomaly analysis module 14, local inspection result correction module 15, electronic device 300, memory 301, processor 302, communication interface 303, bus architecture 304. DETAILED DESCRIPTION

[0015] The present application provides an unmanned intelligent inspection method and system for smart power plants, which is used to solve the technical problem in the prior art that as smart power plants become more complex, traditional inspection methods cannot adapt to complex and changeable inspection needs, resulting in low inspection efficiency and accuracy.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides an unmanned intelligent inspection method for a smart power plant, the method comprising:

[0019] P10: According to the functional zoning information and environmental attribute information of the target power plant, inspection zones are divided to obtain multiple inspection zones.

[0020] Furthermore, step P10 of the embodiment of the present application further includes:

[0021] P11: Acquire the functional zoning information of the target power plant and the environmental attribute information of each functional zone; P12: Perform correlation impact analysis based on the functional zoning information and environmental attribute information, and extract key environmental indicators of each functional zone, wherein the key environmental indicators include zone function impact indicators and inspection equipment impact indicators; P13: Perform inspection demand analysis and clustering based on the key environmental indicators to obtain multiple inspection demand categories; P14: Divide the multiple inspection demand categories into multiple inspection zones in combination with the location distribution of each functional zone.

[0022] It should be understood that inspection zones are divided according to the functional zoning information and environmental attribute information of the target power plant to obtain multiple inspection zones. Specifically, the functional zoning information of the target power plant is first obtained through technical means (such as consulting the power plant design drawings, field visits, and using IoT sensors to collect data, etc.), including the main functions of different areas in the power plant, such as the power generation area, transmission area, control room, cooling tower area, etc. At the same time, the environmental attribute information of each functional zone is collected, including but not limited to factors such as temperature, humidity, dust concentration, and electromagnetic radiation intensity that may affect the operation of the power plant and inspection equipment.

[0023] Next, based on the obtained functional zoning information and environmental attribute information, correlation impact analysis is performed, that is, by analyzing the impact of different environmental factors on zoning functions and inspection equipment, critical environmental indicators in each zoning are identified. These key environmental indicators are mainly divided into two categories: one is the zoning function impact indicator, which refers to the environmental factors that affect the normal function of the zoning, such as high temperature and high humidity in the power generation area may affect the stable operation of the generator set. The other is the inspection equipment impact indicator, which refers to the environmental factors that affect the normal operation of the inspection equipment, such as excessive dust concentration may cause the clarity of the inspection camera to decrease.

[0024] After that, based on the extracted key environmental indicators, an inspection demand analysis is conducted for each zone to evaluate the inspection demand of each zone under specific environmental conditions. This step includes analyzing the impact of different environmental factors on inspection frequency, equipment selection, and inspection strategy. By clustering similar inspection demands, areas with similar inspection demands are grouped into the same category, forming multiple inspection demand categories.

[0025] Finally, inspection zones are divided based on the location distribution and inspection demand categories of each functional zone. According to the actual layout of the power plant, functional zones with similar inspection needs and close geographical locations are divided into the same inspection zone to ensure that each inspection zone can receive comprehensive and effective inspection coverage, laying a solid foundation for subsequent intelligent inspection work.

[0026] P20: Based on the multiple inspection zones, multiple inspection equipment groups and multiple edge processing nodes are deployed, and the multiple inspection equipment groups are configured with multiple conventional inspection schemes.

[0027] Optionally, according to the characteristics of multiple inspection zones, inspection equipment groups and edge processing nodes are reasonably deployed to ensure that inspection tasks can be performed efficiently.

[0028] First, configure appropriate inspection equipment groups based on the working environment characteristics, key environmental indicators, and inspection frequency requirements of multiple inspection zones. The working environment characteristics of each inspection zone refer to the physical conditions of the area (such as temperature, humidity, dust concentration, equipment type, etc.), which directly determine the selection of inspection equipment and the inspection method. For example, in high temperature or high dust environments, inspection equipment with high temperature resistance and dustproof capabilities is required. Key environmental indicators, such as high temperature and low humidity, are the factors that have the greatest impact on the operation of equipment and systems, so inspection equipment must effectively detect these indicators. The inspection frequency requirement determines the frequency of execution of inspection tasks, that is, in some areas where the environment changes drastically, more frequent inspections may be required, while in stable areas, the inspection frequency can be lower.

[0029] Next, according to these requirements, configure the inspection equipment group. Each inspection equipment group consists of multiple devices, which may include sensors, cameras, drones, mobile inspection robots, etc. The selection of specific equipment depends on the environmental characteristics and inspection requirements within the partition. For example, in a confined space, fixed sensors may be the most suitable choice, while in a wide outdoor area, drones or mobile robots can cover a larger inspection range. The configuration of the equipment group ensures the comprehensiveness and pertinence of the inspection work.

[0030] The edge processing nodes are set up for decentralized data processing. The edge processing nodes are located at the local end of each inspection zone. They can quickly make preliminary analysis and feedback by processing the data collected by the inspection equipment group in real time, reducing the delay in data transmission to the central system. This distributed processing architecture effectively improves the response speed of the system, which is especially important in environments that require instant response.

[0031] In addition, the multiple inspection equipment groups are configured with multiple conventional inspection schemes, which are pre-set based on different inspection requirements and environmental conditions, such as periodic inspections, abnormal event inspections, etc. The diversity of conventional inspection schemes ensures that the equipment group can adapt to changing environmental conditions and flexibly respond to different inspection tasks based on the established schemes. In this way, it is ensured that each inspection zone can be equipped with a suitable inspection equipment group, and efficient data processing is performed through edge processing nodes, making the inspection process more intelligent and automated.

[0032] P30: The multiple edge processing nodes receive real-time environmental monitoring data of the corresponding inspection partitions, adaptively optimize the multiple conventional inspection schemes, obtain multiple dynamic optimization schemes to perform intelligent inspection of the partitions, and obtain multiple inspection data sets.

[0033] Furthermore, step P30 of the embodiment of the present application further includes:

[0034] P31: The multiple routine inspection plans include routine inspection equipment, routine inspection paths and routine inspection frequencies of each inspection equipment group; P32: Based on the multiple edge processing nodes, real-time environmental monitoring data of the corresponding inspection partitions are received, and the real-time environmental monitoring data include multiple key environmental indicator sequences of each inspection partition; P33: Based on the multiple key environmental indicator sequences, environmental trend predictions are performed for each inspection partition respectively, and the multiple routine inspection plans are adaptively optimized according to the environmental trend prediction results to obtain multiple dynamic optimization plans.

[0035] Specifically, the data processing capabilities of edge processing nodes are utilized to optimize the intelligent inspection schemes for each inspection zone of the smart power plant. First, the specific content of the routine inspection scheme is clarified, which includes the routine inspection equipment, routine inspection paths, and routine inspection frequencies of each inspection equipment group. Among them, the routine inspection equipment refers to pre-configured hardware equipment for performing inspection tasks, such as fixed sensors, mobile inspection robots, drones, etc. These devices are deployed according to the working environment requirements of the inspection zones; the routine inspection paths refer to the established inspection paths of the equipment, which are usually designed with consideration of factors such as the functional distribution of the zones, the coverage of the equipment, and traffic obstacles; the routine inspection frequency refers to the time interval or frequency of the inspection, which is usually set based on the operating conditions of the equipment in the zone, the rate of environmental change, and other conditions. For example, in areas where the temperature changes dramatically, the inspection frequency is higher, while in stable areas it is lower.

[0036] Next, the edge processing nodes receive real-time environmental monitoring data from each inspection zone. These data include multiple key environmental indicator sequences for each inspection zone, i.e., continuous monitoring data that reflects environmental changes. For example, indicators such as temperature, humidity, air pressure, and wind speed can reflect the environmental status of the zone and its changing trend. Through the edge processing nodes, the system can grasp the environmental status of each zone in real time and provide data support for subsequent adaptive optimization.

[0037] Then, data analysis techniques, such as time series analysis and machine learning, are used to predict environmental trends for the key environmental indicator sequences of each inspection zone. By mining and analyzing historical data, environmental change trends in each region over a period of time in the future are predicted, thereby identifying potential risks and problems in advance. Based on these prediction results, conventional inspection plans are adaptively optimized to generate multiple dynamic optimization plans. These plans can flexibly adjust inspection equipment, inspection paths, and inspection frequencies according to changes in the current environmental conditions to ensure the pertinence and effectiveness of inspection work.

[0038] Furthermore, step P33 of the embodiment of the present application also includes:

[0039] P33-1: Based on the environmental trend prediction results, multiple environmental indicator change curves are generated, and multiple environmental critical nodes are extracted based on the multiple environmental indicator change curves; P33-2: Based on the multiple environmental critical nodes, after aligning the time nodes with the multiple conventional inspection plans, the inspection equipment, inspection path and inspection frequency are optimized respectively to obtain multiple dynamic optimization plans.

[0040] In a possible embodiment of the present application, the application of environmental trend prediction results is further refined, and accurate optimization of conventional inspection plans is achieved by generating environmental indicator change curves and extracting environmental critical nodes.

[0041] First, based on the environmental trend prediction results, data visualization technology is used to generate change curves of multiple key environmental indicators. These curves intuitively show the changing trends of environmental indicators such as temperature, humidity, and dust concentration over time in each inspection zone. By analyzing these curves, the changing patterns of environmental indicators and potential risk points can be clearly identified. On this basis, statistical methods and machine learning algorithms are used to extract multiple environmental critical nodes. These nodes represent the moments when environmental indicators reach or exceed the preset thresholds, and are the focus of inspection work that needs special attention. For example, when the temperature reaches a certain threshold, it may affect the normal operation of the equipment, or when the humidity drops to a certain level, it may trigger the frequency adjustment of the inspection equipment.

[0042] Next, align the extracted environmental critical nodes with the time nodes in the regular inspection plan. The key to this step is to ensure that the inspection work can match the critical moments of changes in environmental indicators, so as to achieve timely response and effective handling of potential risks. Based on the aligned time nodes, the inspection equipment, inspection paths and inspection frequencies are optimized respectively. Exemplarily, the configuration of the inspection equipment is adjusted according to the environmental changes at the critical nodes. For example, in extreme weather, it may be necessary to enable backup equipment or higher-precision sensors to ensure that the inspection task is not affected by the environment. If the environmental critical node involves special changes in a certain area (such as local temperature increase or increased thermal stress of equipment), the inspection path is adjusted so that the inspection equipment can preferentially cover the affected area. When the environmental critical node shows that the environmental indicators will fluctuate frequently in a certain period of time in the future, the system will increase the inspection frequency to ensure that the inspection tasks are more intensive to capture more environmental change information. Through these optimization measures,

[0043] Finally, through comprehensive optimization of inspection equipment, inspection paths and inspection frequencies, multiple dynamic optimization schemes are generated to ensure the flexibility and response speed of inspection tasks. These dynamic optimization schemes not only take into account the current environmental conditions, but also combine future environmental change trends to ensure that the inspection system can respond in time when environmental indicators change and make optimal adjustments when abnormal situations occur.

[0044] Furthermore, step P33-2 of the embodiment of the present application also includes:

[0045] P33-21: Based on the multiple environmental critical nodes, critical indicators are extracted to obtain node critical indicators, which can be independent indicators or mixed indicators; P33-22: According to the node critical indicators, the inspection equipment, inspection path and inspection frequency of the corresponding conventional inspection plan are adjusted respectively to generate multiple adjustment optimization plans; P33-23: For the multiple adjustment optimization plans, global optimization is performed with the inspection balance of critical indicators and the total inspection cost as the optimization goals to obtain the corresponding dynamic optimization plan.

[0046] Optionally, a dynamic optimization scheme is generated through in-depth analysis and optimization of environmental critical nodes. First, based on the extracted multiple environmental critical nodes, critical indicators are extracted. These critical indicators can be a single environmental parameter (such as temperature, humidity, etc.) or a combination of multiple parameters (such as a combined indicator of temperature and humidity). By deeply analyzing the data characteristics of critical nodes, it is determined which indicators play a key role at the critical moment, so that these indicators can be used as the focus of subsequent optimization work.

[0047] Next, according to the extracted node critical indicators, the conventional inspection plan is adjusted in a targeted manner, including adjusting the inspection equipment, inspection path and inspection frequency in the corresponding conventional inspection plan. Specifically, inspection equipment adjustment refers to evaluating the working environment of the inspection equipment according to the node critical indicators, which may require replacing more suitable equipment or adding spare equipment. For example, if a node predicts that the humidity in the area where the equipment is located drops sharply, the inspection frequency of humidity sensitive sensors may be increased, or equipment that is more tolerant to dry environments may be enabled. Inspection path adjustment refers to adjusting the inspection path of the inspection equipment for specific node critical indicators to ensure that the inspection equipment can preferentially cover the affected area when key environmental changes occur. This can prevent equipment failure or data distortion due to sudden environmental changes. Inspection frequency adjustment refers to increasing the inspection frequency for areas where rapid environmental changes are expected, so as to collect data multiple times in a short period of time to ensure that changes in each critical node are captured, thereby providing more reliable data support for subsequent decision-making. Through these adjustments, multiple adjustment optimization schemes are generated. These schemes are optimization adjustment strategies for different node critical indicators. Each scheme takes into account specific environmental changes and their impact on inspection work.

[0048] Then, for the generated multiple adjustment optimization schemes, global optimization is performed with the inspection balance of critical indicators and the total inspection cost as the optimization objectives. Inspection balance refers to ensuring the balanced distribution of inspection tasks in the entire power plant partition to avoid resource waste due to frequent inspections in a certain area and problems in other areas due to insufficient inspections. The total inspection cost covers comprehensive considerations such as manpower, equipment consumption and time cost to ensure the efficient completion of inspection tasks. By constructing a multi-objective optimization model and using intelligent optimization algorithms such as genetic algorithms and particle swarm algorithms, a global search can be performed on the adjustment optimization scheme to find a dynamic optimization scheme that can best meet the critical indicator monitoring needs under the constraints of inspection balance and total inspection cost. These schemes can flexibly adjust inspection equipment, paths and frequencies under complex environmental conditions with the lowest inspection cost and the best inspection effect to ensure the continuous and efficient inspection work.

[0049] P40: Perform independent inspection anomaly analysis in combination with the inspection data set through the multiple edge processing nodes to obtain multiple local inspection results.

[0050] Specifically, the computing power and data processing advantages of edge processing nodes are used to conduct independent inspection anomaly analysis on the inspection data sets collected from each inspection zone. This process aims to quickly identify possible abnormal conditions in various areas of the power plant through real-time and efficient data processing, providing strong support for subsequent fault warning and emergency response.

[0051] Specifically, the multiple edge processing nodes are local computing nodes distributed in each inspection zone, responsible for real-time processing of the inspection data collected by the inspection equipment group. These inspection data sets include multiple data types obtained from the inspection equipment, such as temperature, humidity, air pressure, current and other sensor data, as well as images and video data captured by cameras, drones and other equipment, which fully reflect the equipment operating status and environmental conditions of each zone of the power plant.

[0052] In order to achieve independent inspection anomaly analysis, a variety of data analysis technologies are used, such as machine learning algorithms and statistical models. These technologies can automatically learn the characteristics of normal inspection data and build corresponding anomaly detection models. When new inspection data is input, the model can analyze it in real time and compare it with the normal data characteristics to determine whether the data is abnormal. In addition, when performing anomaly analysis, the edge processing node can also use historical data for comparison. By comparing the data changes in the inspection partition over a period of time, it can determine whether the current environment or equipment is in an abnormal state. For example, the operating temperature of a device has been within a stable range. If the current temperature suddenly exceeds the historical peak, the system may identify this as a potential sign of failure.

[0053] The independent inspection and anomaly analysis of the edge processing node is highly autonomous and can complete data processing and anomaly judgment locally, reducing dependence on the central control system. This distributed processing architecture improves the response speed of the system, especially in scenarios that require rapid processing, such as when a high-risk fault or security threat is detected, the edge processing node can immediately generate a local alarm signal.

[0054] Finally, the edge processing node generates multiple local inspection results through independent analysis. These local inspection results include abnormal conditions, potential problems, and specific inspection data analysis reports within each inspection zone. The local inspection results not only provide the current operating status of the device, but also point out the environmental factors that may cause abnormalities, thereby providing support for subsequent inspection strategy adjustments.

[0055] P50: The multiple local inspection results are uploaded to the main control center, which performs a partition correlation impact analysis based on the real-time environmental monitoring data of each inspection partition, and corrects the local inspection results based on the analysis results.

[0056] Furthermore, step P50 of the embodiment of the present application also includes:

[0057] P51: The main control center receives the multiple local inspection results and real-time environmental monitoring data of each inspection zone, normalizes them, and then constructs a zone impact matrix; P52: Based on the zone impact matrix, a zone correlation impact analysis is performed to identify and obtain multiple abnormal propagation paths and multiple equipment interference factors; P53: Based on the multiple abnormal propagation paths and multiple equipment interference factors, the local inspection results are corrected.

[0058] It should be understood that the local inspection results generated by multiple edge processing nodes are uploaded to the main control center, and combined with the real-time environmental monitoring data of each inspection zone to conduct in-depth zone correlation impact analysis, and on this basis, the local inspection results are corrected to improve the accuracy and comprehensiveness of the inspection results.

[0059] First, as the core data processing and analysis platform of the system, the master control center receives two types of key information from each inspection zone: one is the local inspection results generated by each edge processing node, and the other is the real-time environmental monitoring data of each zone. These data represent the current status, abnormal conditions and environmental conditions of the equipment in each area of ​​the power plant, and can provide a sufficient data basis for the analysis of the master control center.

[0060] Secondly, in order to ensure that the data from different inspection zones can be analyzed uniformly, the master control center will normalize the inspection results and environmental monitoring data received. The purpose of normalization is to eliminate the dimension differences between different data sources so that different physical quantities such as temperature, humidity, and current can be compared and analyzed on the same dimension. For example, the measurement results of different sensors are converted into dimensionless relative values ​​for unified processing.

[0061] Next, the main control center will build a partition impact matrix based on the normalized data. For example, real-time data can be collected from the environmental sensors and equipment status monitoring devices of each inspection partition, and the correlation strength between each partition can be calculated by calculating the Pearson correlation coefficient, thereby building a multi-dimensional partition impact matrix. The matrix is ​​a multi-dimensional data structure that records the degree of correlation and influence between each inspection partition. Each element of the matrix reflects the possible impact of environmental changes in a certain partition on other partitions. For example, the temperature rise in the power generation area may have a chain reaction on the adjacent cooling system, or the electromagnetic interference of a certain device may affect the normal operation of adjacent equipment.

[0062] Furthermore, partition correlation impact analysis is performed based on the partition impact matrix to identify potential abnormal propagation paths and equipment interference factors within the power plant. The abnormal propagation path refers to the abnormality of a partition that may affect other partitions through the environment or the association between equipment. For example, overheating of a certain device may affect other equipment in the adjacent area through heat conduction, thereby causing group failures of equipment. By analyzing the partition impact matrix, the main control center can identify these potential abnormal propagation paths. At the same time, multiple equipment interference factors are identified through partition correlation impact analysis. Equipment interference factors refer to factors that may cause abnormal operation of equipment identified during the inspection process, such as electromagnetic interference, drastic changes in environmental conditions, etc. These interference factors are often the root cause of unstable or abnormal equipment operation. By identifying these factors, the main control center can more effectively predict and prevent faults.

[0063] Finally, the local inspection results are corrected based on the identified abnormal propagation paths and equipment interference factors. The correction process includes inferring the more likely source of the fault based on the abnormal propagation path, and re-evaluating the accuracy of the inspection data in combination with the impact of the equipment interference factor. For example, if the abnormality of a partition is caused by interference from other partitions, the system will readjust the inspection results to avoid misjudging it as a fault of the partition equipment itself. By correcting the local inspection results, the master control center can more accurately reflect the actual conditions of each area of ​​the power plant, ensure the accuracy of the abnormal analysis results, and provide a reliable basis for subsequent inspection strategy adjustments.

[0064] Furthermore, step P53 of the embodiment of the present application also includes:

[0065] P53-1: The multiple abnormal propagation paths include electrical abnormal propagation paths, thermal conduction abnormal propagation paths and environmental abnormal propagation paths, and the multiple equipment interference factors include electrical interference factors, thermal interference factors and environmental interference factors; P53-2: According to the multiple abnormal propagation paths and multiple equipment interference factors, the local inspection results are matched and screened to obtain multiple associated inspection areas and associated inspection equipment, and the local inspection results are corrected.

[0066] Specifically, the specific process of correcting the local inspection results can be, first, clarifying the classification of abnormal propagation paths and equipment interference factors. According to the actual operation of the power plant and the characteristics of the inspection data, the abnormal propagation paths are divided into electrical abnormal propagation paths, thermal conduction abnormal propagation paths and environmental abnormal propagation paths. Among them, the electrical abnormal propagation path refers to the propagation path caused by faults or abnormalities in the electrical system. For example, a short circuit or electromagnetic interference may occur in an electrical device due to unstable voltage. This abnormality may affect other adjacent devices through cables or electrical lines, thereby causing a chain reaction. The thermal conduction abnormal propagation path refers to abnormal propagation caused by temperature changes. For example, a device overheats, and the heat may be conducted to other devices through metal structures or device casings, thereby causing overheating of the local device group and affecting the normal operation of the device. The environmental abnormal propagation path refers to abnormal propagation caused by changes in the external environment (such as humidity, wind speed, air quality, etc.). For example, excessive humidity may cause the circuit inside the device to be wet, or strong winds may cause unstable operation of certain sensors. Such environmental changes may affect multiple devices at the same time.

[0067] At the same time, the equipment interference factors are also divided into electrical interference factors, thermal interference factors and environmental interference factors. These factors represent different types of factors that affect the normal operation of the equipment. Electrical interference factors refer to factors caused by electrical noise or electromagnetic interference, which may affect the data collection accuracy of the inspection equipment or the normal operation of the equipment. Thermal interference factors refer to interference caused by temperature changes in the equipment or environment. For example, excessive temperature may cause sensor failure or equipment performance degradation. Environmental interference factors refer to interference factors related to changes in the external environment, such as humidity, dust, air pressure, etc. These factors may interfere with the normal operation of the equipment or affect the accuracy of the inspection results.

[0068] Next, the local inspection results are matched and screened according to the determined abnormal propagation paths and equipment interference factors. The inspection areas and equipment associated with the abnormal propagation paths and equipment interference factors are found to make more accurate corrections to the inspection results. For example, if an area has an electrical abnormal propagation path and an obvious electrical interference factor, the master control center will focus on all equipment in the area that may be affected by the electrical abnormality.

[0069] Through matching and screening, multiple associated inspection areas and associated inspection devices are obtained. These areas and devices are closely related to abnormal propagation paths and device interference factors, and are the focus of inspection result correction. On this basis, the local inspection results are corrected. The correction process mainly includes the elimination of abnormal data, the confirmation of normal data, and the re-evaluation of inspection results. Exemplarily, based on the analysis of the propagation path, it is determined whether the abnormality of a certain device is caused by adjacent devices or environmental changes, rather than the failure of the device itself. For example, if the overheating of a certain device is caused by heat conduction from an adjacent device, then the abnormality is attributed to thermal interference rather than a problem with the device itself. And according to the matching results of the abnormal propagation path and the interference factor, the local inspection data is adjusted. For example, some noise data caused by electrical interference may be filtered or marked as inaccurate to avoid misjudgment.

[0070] Through corrections, we ensure that the inspection results can more accurately reflect the actual operating status of the power plant, providing strong data support for subsequent operation and maintenance management.

[0071] In summary, the embodiments of the present application have at least the following technical effects:

[0072] This application divides the power plant into inspection zones according to the functional zoning and environmental attribute information of the target power plant, and deploys inspection equipment groups and edge processing nodes, receives real-time environmental monitoring data, optimizes conventional inspection plans and performs intelligent inspections, conducts anomaly analysis based on the data collected during the inspection, generates local inspection results and uploads them to the main control center. The main control center combines real-time data for correlation impact analysis and corrects the inspection results.

[0073] The technical effect of real-time monitoring and rapid response to the operating status of the power plant through unmanned intelligent inspections has been achieved, thereby improving inspection efficiency and data accuracy.

[0074] Embodiment 2, based on the same inventive concept as the unmanned intelligent inspection method for smart power plants in the aforementioned embodiment, Figure 2 As shown, the present application provides an unmanned intelligent inspection system for a smart power plant, and the system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0075] The inspection zone division module 11 is used to divide the inspection zones according to the functional zone information and environmental attribute information of the target power plant to obtain a plurality of inspection zones.

[0076] The inspection equipment group deployment module 12 is used to deploy multiple inspection equipment groups and multiple edge processing nodes based on the multiple inspection partitions, and the multiple inspection equipment groups are configured with multiple conventional inspection schemes.

[0077] The inspection scheme optimization module 13 is used for receiving the real-time environmental monitoring data of the corresponding inspection partitions by the multiple edge processing nodes, adaptively optimizing the multiple conventional inspection schemes, obtaining multiple dynamic optimization schemes to perform intelligent inspection of the partitions, and obtaining multiple inspection data sets.

[0078] The independent inspection anomaly analysis module 14 is used to perform independent inspection anomaly analysis through the multiple edge processing nodes in combination with the inspection data set to obtain multiple local inspection results.

[0079] The local inspection result correction module 15 is used to upload the multiple local inspection results to the main control center, which performs partition correlation impact analysis based on the real-time environmental monitoring data of each inspection partition and corrects the local inspection results based on the analysis results.

[0080] Furthermore, the inspection zone division module 11 is also used to perform the following steps:

[0081] Acquire the functional zoning information of the target power plant and the environmental attribute information of each functional zone; perform correlation impact analysis based on the functional zoning information and environmental attribute information, and extract key environmental indicators of each functional zone, wherein the key environmental indicators include zone function impact indicators and inspection equipment impact indicators; perform inspection demand analysis and clustering based on the key environmental indicators to obtain multiple inspection demand categories; divide the multiple inspection demand categories into multiple inspection zones in combination with the location distribution of each functional zone.

[0082] Furthermore, the inspection scheme optimization module 13 is also used to perform the following steps:

[0083] The multiple routine inspection plans include routine inspection equipment, routine inspection paths and routine inspection frequencies of each inspection equipment group; based on the multiple edge processing nodes, real-time environmental monitoring data of the corresponding inspection partitions are received, and the real-time environmental monitoring data include multiple key environmental indicator sequences of each inspection partition; according to the multiple key environmental indicator sequences, environmental trend predictions are performed for each inspection partition respectively, and the multiple routine inspection plans are adaptively optimized according to the environmental trend prediction results to obtain multiple dynamic optimization plans.

[0084] Furthermore, the inspection scheme optimization module 13 is also used to perform the following steps:

[0085] According to the environmental trend prediction results, multiple environmental indicator change curves are generated, and based on the multiple environmental indicator change curves, multiple environmental critical nodes are extracted; based on the multiple environmental critical nodes, after aligning the time nodes with the multiple conventional inspection schemes, the inspection equipment, inspection path and inspection frequency are optimized respectively to obtain multiple dynamic optimization schemes.

[0086] Furthermore, the inspection scheme optimization module 13 is also used to perform the following steps:

[0087] Based on the multiple environmental critical nodes, critical indicators are extracted to obtain node critical indicators, which can be independent indicators or mixed indicators; according to the node critical indicators, the inspection equipment, inspection path and inspection frequency of the corresponding conventional inspection plan are adjusted respectively to generate multiple adjustment optimization plans; for the multiple adjustment optimization plans, global optimization is performed with the inspection balance of critical indicators and the total inspection cost as the optimization objectives to obtain the corresponding dynamic optimization plan.

[0088] Furthermore, the local inspection result correction module 15 is also used to perform the following steps:

[0089] The central control center receives the multiple local inspection results and real-time environmental monitoring data of each inspection zone, normalizes them, and then constructs a zone impact matrix; based on the zone impact matrix, a zone correlation impact analysis is performed to identify and obtain multiple abnormal propagation paths and multiple equipment interference factors; based on the multiple abnormal propagation paths and multiple equipment interference factors, the local inspection results are corrected.

[0090] Furthermore, the local inspection result correction module 15 is also used to perform the following steps:

[0091] The multiple abnormal propagation paths include electrical abnormal propagation paths, thermal conduction abnormal propagation paths and environmental abnormal propagation paths, and the multiple equipment interference factors include electrical interference factors, thermal interference factors and environmental interference factors; based on the multiple abnormal propagation paths and multiple equipment interference factors, the local inspection results are matched and screened to obtain multiple associated inspection areas and associated inspection equipment, and the local inspection results are corrected.

[0092] Embodiment 3

[0093] Based on the same inventive concept as the unmanned intelligent inspection method for smart power plants in the aforementioned embodiment, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method in embodiment one is implemented.

[0094] Through the above detailed description of the unmanned intelligent inspection method for smart power plants, those skilled in the art can clearly understand the unmanned intelligent inspection method and system for smart power plants in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0095] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0096] Exemplary Electronic Devices

[0097] Reference below Figure 3 To describe the electronic device of the embodiment of the present application.

[0098] Based on the same inventive concept as the unmanned intelligent inspection method for smart power plants in the aforementioned embodiment, the present application also provides an unmanned intelligent inspection system for smart power plants, including: a processor, the processor is coupled to a memory, the memory is used to store a program, when the program is executed by the processor, the system executes the steps of the method described in Example 1.

[0099] The electronic device 300 includes: a processor 302, a communication interface 303, and a memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. The communication interface 303, the processor 302, and the memory 301 may be interconnected via the bus architecture 304; the bus architecture 304 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus architecture 304 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0100] The processor 302 may be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0101] The communication interface 303 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), wired access networks, etc.

[0102] The memory 301 may be a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processor via the bus architecture 304. The memory may also be integrated with the processor.

[0103] The memory 301 is used to store computer-executable instructions for executing the solution of the present application, and the execution is controlled by the processor 302. The processor 302 is used to execute the computer-executable instructions stored in the memory 301, thereby realizing the unmanned intelligent inspection method for a smart power plant provided in the above embodiment of the present application.

[0104] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0105] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0106] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An unmanned intelligent inspection method for a smart power plant, characterized in that: The method comprises: According to the functional zoning information and environmental attribute information of the target power plant, the inspection zoning is divided to obtain multiple inspection zonings; Based on the multiple inspection zones, multiple inspection equipment groups and multiple edge processing nodes are deployed, and the multiple inspection equipment groups are configured with multiple conventional inspection schemes; The multiple edge processing nodes receive real-time environmental monitoring data of the corresponding inspection partitions, adaptively optimize the multiple conventional inspection schemes, obtain multiple dynamic optimization schemes to perform intelligent inspection of the partitions, and obtain multiple inspection data sets; By using the plurality of edge processing nodes, performing independent inspection anomaly analysis in combination with the inspection data set, a plurality of local inspection results are obtained; The multiple local inspection results are uploaded to the main control center, which performs partition correlation impact analysis based on the real-time environmental monitoring data of each inspection partition, and corrects the local inspection results based on the analysis results.

2. The unmanned intelligent inspection method for a smart power plant according to claim 1, characterized in that: According to the functional zoning information and environmental attribute information of the target power plant, the inspection zoning is divided, including: Obtain the functional zoning information of the target power plant and the environmental attribute information of each functional zoning; Based on the functional zoning information and environmental attribute information, correlation impact analysis is performed, and key environmental indicators of each functional zoning are extracted, wherein the key environmental indicators include zoning function impact indicators and inspection equipment impact indicators; According to the key environmental indicators, perform inspection demand analysis and clustering to obtain multiple inspection demand categories; According to the multiple inspection demand categories, multiple inspection zones are divided in combination with the location distribution of each functional zone.

3. The unmanned intelligent inspection method for a smart power plant according to claim 1, characterized in that: Receive real-time environmental monitoring data of the corresponding inspection zone, and adaptively optimize the multiple conventional inspection schemes, including: The plurality of conventional inspection schemes include conventional inspection equipment, conventional inspection paths and conventional inspection frequencies of each inspection equipment group; Based on the multiple edge processing nodes, receiving real-time environmental monitoring data of the corresponding inspection partitions, the real-time environmental monitoring data including multiple key environmental indicator sequences of each inspection partition; According to the multiple key environmental indicator sequences, environmental trend predictions are performed for each inspection zone respectively, and the multiple conventional inspection schemes are adaptively optimized according to the environmental trend prediction results to obtain multiple dynamic optimization schemes.

4. The unmanned intelligent inspection method for a smart power plant according to claim 3, characterized in that: Adaptively optimize the multiple conventional inspection plans according to the environmental trend prediction results to obtain multiple dynamic optimization plans, including: Generate multiple environmental indicator change curves according to the environmental trend prediction results, and extract multiple environmental critical nodes based on the multiple environmental indicator change curves; Based on the multiple environmental critical nodes, after aligning the time nodes with the multiple conventional inspection schemes, the inspection equipment, inspection path and inspection frequency are optimized respectively to obtain multiple dynamic optimization schemes.

5. The unmanned intelligent inspection method for a smart power plant according to claim 4, characterized in that: Based on the multiple environmental critical nodes, after aligning the time nodes with the multiple conventional inspection schemes, the inspection equipment, inspection path and inspection frequency are optimized respectively, including: Based on the multiple environmental critical nodes, extract critical indicators to obtain node critical indicators, where the node critical indicators may be independent indicators or mixed indicators; According to the critical index of the node, the inspection equipment, inspection path and inspection frequency corresponding to the conventional inspection plan are adjusted respectively to generate multiple adjustment optimization plans; For the multiple adjustment optimization schemes, global optimization is performed with the inspection balance of critical indicators and the total inspection cost as optimization targets to obtain corresponding dynamic optimization schemes.

6. The unmanned intelligent inspection method for a smart power plant according to claim 1, characterized in that: The multiple local inspection results are uploaded to the master control center, which performs zone correlation impact analysis based on the real-time environmental monitoring data of each inspection zone, including: The central control center receives the plurality of local inspection results and real-time environmental monitoring data of each inspection zone, performs normalization processing, and constructs a zone influence matrix; Based on the partition impact matrix, partition association impact analysis is performed to identify and obtain multiple abnormal propagation paths and multiple device interference factors; According to the multiple abnormal propagation paths and multiple equipment interference factors, local inspection results are corrected.

7. The unmanned intelligent inspection method for a smart power plant according to claim 6, characterized in that: According to the multiple abnormal propagation paths and the multiple device interference factors, a local inspection result correction is performed, including: The multiple abnormal propagation paths include electrical abnormal propagation paths, thermal conduction abnormal propagation paths, and environmental abnormal propagation paths, and the multiple equipment interference factors include electrical interference factors, thermal interference factors, and environmental interference factors; According to the multiple abnormal propagation paths and multiple equipment interference factors, the local inspection results are matched and screened to obtain multiple associated inspection areas and associated inspection equipment, and the local inspection results are corrected.

8. The unmanned intelligent inspection system for smart power plants is characterized by: The system comprises: An inspection partition division module, which is used to divide the inspection partitions according to the functional partition information and environmental attribute information of the target power plant to obtain multiple inspection partitions; An inspection equipment group deployment module, the inspection equipment group deployment module is used to deploy multiple inspection equipment groups and multiple edge processing nodes based on the multiple inspection zones, the multiple inspection equipment groups are configured with multiple conventional inspection schemes; An inspection scheme optimization module, wherein the inspection scheme optimization module is used to receive the real-time environmental monitoring data of the corresponding inspection partitions by the multiple edge processing nodes, adaptively optimize the multiple conventional inspection schemes, obtain multiple dynamic optimization schemes to perform intelligent inspection of the partitions, and obtain multiple inspection data sets; An independent inspection anomaly analysis module, the independent inspection anomaly analysis module is used to perform independent inspection anomaly analysis through the multiple edge processing nodes in combination with the inspection data set to obtain multiple local inspection results; The local inspection result correction module is used to upload the multiple local inspection results to the main control center, which performs partition correlation impact analysis based on the real-time environmental monitoring data of each inspection partition and corrects the local inspection results based on the analysis results.

9. An electronic device, characterized in that: include: A processor, the processor is coupled to a memory, the memory is used to store a program, when the program is executed by the processor, the system is enabled to perform the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method steps according to any one of claims 1 to 7 are implemented.

Images