New energy power plant inspection path planning method and system

Abstract

The invention provides a new energy power plant inspection path planning method and system, and the method comprises the steps: collecting multi-source data related to a new energy power plant, carrying out the data integration of the multi-source data, enabling the multi-source data to be collected based on a pre-constructed hierarchical multi-source data collection networking architecture, and enabling the multi-source data to be stored in a database; the parameters at least comprise equipment operation parameters, environment parameters and geographic parameters; carrying out data processing and analysis on the integrated multi-source data; based on an improved path planning algorithm, performing routing inspection path planning in combination with multi-source data and routing inspection requirements to generate an optimal routing inspection path; and according to the inspection path and the task instruction, monitoring in real time and dynamically adjusting the inspection path according to equipment operation and environment change. The method intelligently plans the inspection path according to the complex scene of the new energy power plant, significantly improves the inspection efficiency, reduces the operation and maintenance cost, enhances the system reliability, and promotes the ecological development of the operation and maintenance technology of the new energy power plant.

Description

Technical Field

[0001] The present application belongs to the field of intelligent operation and maintenance technology of new energy power plants, and in particular relates to a method and system for planning inspection routes of new energy power plants. Background Art

[0002] With the vigorous development of the new energy industry, the scale of new energy power plants continues to expand, the number of equipment is increasing day by day and is widely distributed. Traditional inspection route planning methods for new energy power plants rely heavily on manual experience or simple preset routes, which have many drawbacks. At the data processing level, the multi-source data generated by power plants, such as equipment operation data, meteorological data, and geographic information data, lack efficient integration and in-depth analysis, and cannot fully tap the value of data to assist in route planning. In terms of the application of route planning algorithms, existing algorithms are difficult to adapt to the complex terrain, dispersed equipment, and changing environment of new energy power plants. They are unable to quickly generate optimal or better inspection routes that meet actual needs, resulting in low inspection efficiency, high operation and maintenance costs, and difficulty in ensuring the reliability of power plant operations. Innovative solutions are urgently needed. Summary of the Invention

[0003] In view of this, the present application aims to propose a new energy power plant inspection path planning method and system to solve at least one of the above problems.

[0004] To achieve the above objectives, the technical solution of this application is implemented as follows: In a first aspect, the present application provides a method for planning inspection paths for a new energy power plant, comprising: Collecting multi-source data related to new energy power plants and integrating the multi-source data, wherein the multi-source data is collected based on a pre-built hierarchical multi-source data collection network architecture and includes at least equipment operating parameters, environmental parameters, and geographic parameters; Performing data processing and analysis on the integrated multi-source data; Based on an improved path planning algorithm, inspection path planning is performed in combination with the multi-source data and inspection requirements to generate an optimal inspection path, wherein the path planning algorithm includes constructing a weighted directed graph model based on the equipment operating parameters, environmental parameters, and geographical parameters, and generating the path plan through an algorithm fusion strategy; According to the inspection path and task instructions, real-time monitoring is performed and the inspection path is dynamically adjusted according to equipment operation and environmental changes.

[0005] In a second aspect, based on the same inventive concept, the present application also provides a new energy power plant inspection path planning system, comprising: a data acquisition module configured to collect multi-source data related to the new energy power plant and perform data integration on the multi-source data, wherein the multi-source data is collected based on a pre-built hierarchical multi-source data acquisition network architecture and includes at least equipment operating parameters, environmental parameters, and geographical parameters; A data processing module is configured to process and analyze the integrated multi-source data; a path planning module configured to perform inspection path planning based on an improved path planning algorithm and in combination with the multi-source data and inspection requirements to generate an optimal inspection path, wherein the path planning algorithm includes constructing a weighted directed graph model based on the equipment operating parameters, environmental parameters, and geographical parameters, and generating the path plan through an algorithm fusion strategy; The dynamic adjustment module is configured to monitor the inspection path and task instructions in real time and dynamically adjust the inspection path according to equipment operation and environmental changes.

[0006] In a third aspect, based on the same inventive concept, the present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the program.

[0007] In a fourth aspect, based on the same inventive concept, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method described in the first aspect.

[0008] Compared with the prior art, the new energy power plant inspection path planning method and system described in this application has the following beneficial effects: The inspection path planning method for a new energy power plant described in this application realizes intelligent planning of the inspection path of the new energy power plant through efficient collection, processing and analysis of multi-source data, combined with an innovative and improved path planning algorithm, thereby improving inspection efficiency, reducing operation and maintenance costs, enhancing system operation reliability, and providing advanced technical support for the operation and maintenance of new energy power plants. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings: Figure 1 This is a flow chart of a new energy power plant inspection route planning method described in an embodiment of the present application; Figure 2 This is a schematic diagram of the structure of a new energy power plant inspection path planning system according to an embodiment of the present application; Figure 3 This is a schematic diagram of the hardware structure of the electronic device described in an embodiment of the present application. DETAILED DESCRIPTION

[0010] In order to make the objectives, technical solutions and advantages of this application more clear, this application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0011] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should have the usual meanings understood by people with ordinary skills in the field to which this application belongs. The "first", "second" and similar words used in the embodiments of the present application do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0012] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0013] See also Figure 1 As shown, this embodiment provides a method for planning an inspection path for a new energy power plant, which specifically includes the following steps: Step S101: Collect multi-source data related to the new energy power plant and integrate the multi-source data, wherein the multi-source data is collected based on a pre-built hierarchical multi-source data collection network architecture and includes at least equipment operating parameters, environmental parameters and geographical parameters.

[0014] Specifically, in this embodiment, various sensors and data acquisition terminals are used to collect power plant equipment operation, environment and geographic information data, and the collected equipment operation, environment and geographic information data are preliminarily integrated and processed.

[0015] In some embodiments, a layered multi-source data acquisition network architecture includes a perception layer, a transmission layer, and a storage layer arranged from bottom to top; The perception layer is configured to collect equipment operating parameters, environmental parameters, and geographical parameters of new energy power plants; The transport layer is configured to encapsulate and transmit the collected parameter data; The storage layer is configured to classify and store the collected parameter data in a database.

[0016] Specifically, in this embodiment, the constructed layered multi-source data acquisition networking architecture is divided into a perception layer, a transmission layer, and a storage layer from bottom to top. Among them, the perception layer, as the basic link for data acquisition, deploys various sensors to achieve comprehensive perception of the operating data of new energy power plants; the transmission layer is responsible for building a high-speed and stable communication network to ensure efficient data transmission; the storage layer is used to centrally store the collected multi-source data, providing a data basis for subsequent processing.

[0017] 1.1 Perception Layer Device Deployment and Data Collection Within new energy power plants, a variety of sensors are deployed to meet the needs of different types of equipment and environmental monitoring. Temperature sensors, vibration sensors, current and voltage sensors, and speed sensors are installed in key locations such as the wind turbine nacelle, tower base, and gearbox. For example, temperature sensors collect real-time temperature data from various turbine components to monitor for overheating. Vibration sensors analyze the equipment's operating status by detecting vibration frequency and amplitude, promptly identifying problems such as bearing wear and gear failure. Current and voltage sensors acquire the turbine's electrical parameters to assess power generation efficiency and grid stability. Speed ​​sensors monitor rotor speed and assist in adjusting turbine operating parameters. For solar photovoltaic panels, light intensity sensors, temperature sensors, and current and voltage sensors are installed on each panel or array. The light intensity sensor measures the intensity of solar radiation received by the panel. Combined with current and voltage data, it can be used to calculate the panel's power generation efficiency and evaluate its performance. The temperature sensor monitors the panel's surface temperature, as excessive temperatures can affect the panel's power generation efficiency. Real-time temperature data allows for timely cooling measures. Meteorological sensors, including anemometers, temperature and humidity sensors, air pressure sensors, and rainfall sensors, are deployed around power plants to collect real-time meteorological data such as wind speed, direction, temperature, humidity, air pressure, and rainfall. This data not only directly impacts the operation of power plant equipment—for example, strong winds can affect the stability of wind turbines and high temperatures can reduce the efficiency of photovoltaic panels—but also provides environmental references for subsequent route planning.

[0018] At the same time, the Geographic Information System (GIS) is used to obtain geographic information data such as the power plant's topography, equipment distribution, etc., which are digitized and incorporated into the data collection system.

[0019] 1.2 Transport layer data transmission The transport layer utilizes a hybrid communication network architecture, flexibly selecting communication methods such as 5G and fiber optics based on data transmission requirements and site environments. For equipment operating data with high real-time requirements and large data volumes, such as high-frequency vibration data from wind turbines and real-time power generation data from photovoltaic panels, fiber optics or Industrial Ethernet are preferred for transmission, ensuring stable, high-speed data transmission and reducing latency and packet loss. For widely distributed areas with difficult cabling, such as remote photovoltaic arrays and dispersed meteorological monitoring points, 5G communication networks are used for wireless data transmission, improving the flexibility and convenience of data collection. During the data transmission process, data encapsulation and compression technology is used to process the collected raw data, and the data is encapsulated according to the data protocol, adding information such as source address, destination address, data type, etc., so as to accurately identify and route it during the transmission process.

[0020] 1.3 Storage Layer Data Integration The storage layer uses a distributed storage architecture, such as Ceph and GlusterFS, to store collected multi-source data across multiple storage nodes. Data is categorized and stored based on data type and application scenario. For example, device operation data is stored in a time series database to meet the needs of efficient query and analysis of time series data; geographic information data is stored in a spatial database to facilitate geospatial analysis and visualization; and unstructured or semi-structured data, such as meteorological data and equipment archives, is stored in a NoSQL database. At the same time, a data index and metadata management system is established to create corresponding indexes for each type of data to speed up data query; metadata information such as the source of the data, collection time, collection frequency, and data format are recorded to facilitate data management and tracing.

[0021] Through data cleaning and preprocessing, duplicate data and noise data are removed, missing data is marked or completed, and preliminary integration of multi-source data is achieved, providing a high-quality data foundation for subsequent data processing and analysis.

[0022] Step S102: Process and analyze the integrated multi-source data.

[0023] Specifically, in this embodiment, collected data is received, and distributed data transmission protocols and high-concurrency processing technologies are used to perform data transmission, storage, cleaning, preprocessing, and mining analysis, store processed data, and provide an interface.

[0024] In some embodiments, the integrated multi-source data is cleaned and preprocessed, and the preprocessed data is deeply analyzed, wherein the association relationship between equipment operating parameters, environmental parameters and geographical parameters is mined through an association rule mining algorithm, the power plant equipment is classified through a cluster analysis algorithm, and the operating status of the power plant equipment is detected in real time through an anomaly detection algorithm.

[0025] Specifically, in this embodiment, this step includes the following contents: 2.1 Distributed Computing Architecture Construction The distributed computing architecture combines Apache Hadoop and Apache Spark. Hadoop, as the foundational data storage and processing platform, utilizes the Hadoop Distributed File System (HDFS) for distributed data storage, breaking large-scale data into multiple blocks and storing them on different nodes. This provides highly reliable and scalable data storage capabilities. The MapReduce programming model is used to process offline batch data. By breaking down data processing tasks into two phases, Map and Reduce, it enables parallel computing and improves data processing efficiency. Spark is used to process real-time data and complex data analysis tasks. Its in-memory computing model enables rapid processing of large amounts of data and supports multiple data processing paradigms, such as batch processing, stream processing, machine learning, and graph computing. Spark Streaming enables real-time data streaming, enabling real-time analysis and processing of sensor data. Spark SQL enables structured data query and analysis, facilitating operations on data stored in databases. Spark MLlib enables the application of data mining algorithms for machine learning and data analysis. 2.2 Data processing flow Data access and buffering: Message queue systems like Kafka are used to receive multi-source data from the transport layer. As a data buffer, Kafka processes data at high throughput, enabling asynchronous and decoupled data transmission, avoiding congestion and loss during data transmission and ensuring the stability and reliability of the data processing system. Kafka also partitions and replicates data, improving data availability and fault tolerance. Data cleaning and preprocessing: Clean and preprocess the incoming data. Use data cleaning tools such as OpenRefine and Trifacta to identify and remove noise and outliers, such as unreasonably high temperatures in wind turbine temperature data and sudden changes in photovoltaic panel current and voltage data. For missing data, use different completion methods based on data characteristics and application requirements. For example, linear interpolation and polynomial interpolation can be used for time series data, while methods such as mode filling can be used for categorical data. Furthermore, standardize and normalize the data, converting data of different types and magnitudes into a unified format and range to facilitate subsequent data analysis and mining.

[0026] Data mining and analysis: Utilize various data mining algorithms to conduct in-depth analysis of pre-processed data. Use association rule mining algorithms, such as the Apriori algorithm and FP-Growth algorithm, to uncover relationships between equipment operating parameters and between equipment operating parameters and environmental parameters. Cluster analysis algorithms, such as K-Means and hierarchical clustering, are used to classify equipment. Wind turbines are divided into different categories based on parameters such as power output, vibration characteristics, and temperature fluctuations. Differentiated inspection strategies and maintenance plans are then developed for each type of equipment. Photovoltaic panels are clustered to identify groups with similar performance, facilitating centralized management and troubleshooting. Anomaly detection algorithms, such as the Isolation Forest algorithm and One-Class Support Vector Machine (SVM), monitor device operating status in real time to promptly identify abnormal device behavior and potential failures. When device operating parameters deviate from normal ranges, a fault warning mechanism is triggered, notifying operations and maintenance personnel for action. 2.3 Data Storage and Management Processed and analyzed data is stored in different databases based on its purpose and characteristics. Structured data, such as analysis results and mined knowledge, is stored in relational databases like MySQL and PostgreSQL to facilitate data query and report generation. Raw data, intermediate processed data, and unstructured data are stored in distributed file systems or NoSQL databases to meet the needs of long-term data storage and large-scale access. Establish a data warehouse to integrate and manage multi-source data. Use ETL (Extract, Transform, Load) tools to extract and transform data from different data sources and load it into the data warehouse, enabling unified data management and sharing. Simultaneously, utilize data version management technology to record and trace data changes, ensuring data accuracy and consistency. Implement data security management measures, including data encryption, access control, and user authentication, to protect data security and privacy. Step S103: Based on the improved path planning algorithm, inspection path planning is performed in combination with multi-source data and inspection requirements to generate the optimal inspection path. The path planning algorithm includes constructing a weighted directed graph model based on equipment operating parameters, environmental parameters and geographical parameters, and generating path planning through an algorithm fusion strategy.

[0027] Specifically, in this embodiment, by constructing a weighted directed graph model, algorithm fusion, and adaptive parameter optimization strategy, this path planning algorithm can effectively combine the actual situation of the new energy power plant and quickly and accurately generate the optimal or relatively optimal inspection path to meet the needs of efficient operation and maintenance of the new energy power plant. Specifically, it includes the following contents: 3.1 Constructing a weighted directed graph model Converting geographic information data of new energy power plants into weighted directed graphs Among them, the node set Contains all equipment locations, important monitoring points, and necessary route nodes in the power plant; edge set Represents a feasible path between nodes. For each edge Assign comprehensive weight , which is determined by the base distance weight , weight of environmental factors and device priority weights Composition, the calculation formula is: Where, 、 、 is the weight coefficient, and These coefficients are trained through machine learning using a large amount of data, including historical power plant inspection data, equipment failure records, and environmental impact analysis, and are continuously optimized through actual scenario testing to balance the impact of various factors on path weights.

[0028] Among them, the basic distance weight is: According to the node and The actual geographical distance between them can be determined by calculating the cost of the basic length of the path using Geographic Information System (GIS) data.

[0029] Environmental factor weight: Dynamic adjustment based on real-time meteorological data. Taking wind speed as an example, when the wind speed Exceeding the threshold hour, The calculation method is: in, The wind speed impact coefficient is determined experimentally based on the degree to which different types of equipment are affected by wind speed. Similarly, corresponding weight calculation models are established for other environmental factors such as heavy rain and high temperatures, allowing path planning to fully consider the impact of environmental changes.

[0030] Device priority weight: Score based on device importance and failure risk score OK, the formula is as follows: Where, is the priority adjustment coefficient. Equipment importance score Evaluate the role of comprehensive equipment in the power plant's power generation system (such as core power generation equipment, key transmission equipment, etc.), the impact of shutdown on the overall operation of the power plant, and other factors; Failure risk scoring It is calculated through statistical analysis of historical equipment failure data and judgment of the degree of abnormality of real-time operating parameters, thereby ensuring that the inspection paths corresponding to important equipment and high-risk equipment have higher priority.

[0031] 3.2 Algorithm Fusion Strategy The advantages of Dijkstra algorithm and genetic algorithm are integrated to address the limitations of traditional algorithms in path planning of new energy power plants.

[0032] Dijkstra algorithm preliminary screening: Using Dijkstra algorithm as the basic framework, starting from the starting node, calculate the shortest path to other nodes (based on the basic distance weight ), generating an initial set of paths. This process leverages the accuracy and efficiency of the Dijkstra algorithm in small-scale path search to preliminarily screen the paths and obtain locally optimal feasible paths, providing a higher-quality initial population for the subsequent genetic algorithm.

[0033] Genetic Algorithm Global Optimization: The initial set of paths generated by the Dijkstra algorithm is used as the initial population for the genetic algorithm. In the genetic algorithm, each path individual is represented by a chromosome, with the genes in the chromosome corresponding to the node sequence in the path. The population is evolved through genetic operations such as selection, crossover, and mutation.

[0034] Among them, the selection operation is based on the individual fitness value. The fitness function comprehensively considers factors such as the total weight of the path (that is, the sum of the weights of each edge on the path), the device priority coverage, and the impact of environmental factors. Designed to: Where, 、 is the adjustment coefficient, and the device priority satisfaction is calculated based on the situation that the path covers the high-priority device.

[0035] Furthermore, environmental friendliness is used to evaluate the adaptability of a path in adverse environments. The operating environment of a new energy power plant is complex and changeable. Severe weather such as strong winds, heavy rains, and high temperatures will increase the difficulty and risk of inspections. The calculation of environmental friendliness can be evaluated by combining the real-time environmental factor weights of the areas involved in the path. For example, the sum of the environmental factor weights of each edge in the path is calculated. , and the preset environmental weight threshold For comparison, if Lower than , it means that the path is less affected by the environment and has a higher environmental friendliness; otherwise, it is lower. The proportion of environmental friendliness in the fitness function can be adjusted to highlight the importance of environmental factors in path planning.

[0036] The device priority satisfaction is used to measure the coverage of high-priority devices on the path. In a new energy power plant, different devices have different levels of importance and failure risks. To ensure that important and high-risk equipment can be inspected in a timely manner, it is necessary to give priority to covering these devices during path planning. The calculation method of device priority satisfaction can be designed according to actual needs. For example, a priority level (such as high, medium, and low) can be set in advance for each device, and the number of high-priority devices covered in the path can be counted. Total number of high-priority equipment in the power plant As a calculation method of device priority satisfaction, the ratio of The higher the ratio, the better the coverage of the path for high-priority devices, and the higher the corresponding adaptability. , the importance of device priority satisfaction in the fitness function can be adjusted to adapt to different inspection needs and scenarios.

[0037] Individuals with high fitness are more likely to be selected, thus preserving excellent path individuals into the next generation.

[0038] Crossover operation: Perform a crossover operation on the selected individuals to generate new path individuals by exchanging some genes (node ​​sequences), thereby increasing the diversity of the population and exploring better path combinations.

[0039] Mutation operation: mutate the individual's genes with a certain probability, randomly change some nodes in the path, prevent the algorithm from falling into local optimality, and further expand the search space.

[0040] During the execution of the genetic algorithm, the adaptive crossover probability and mutation probability Strategy to adapt to the needs of different evolutionary stages of the algorithm. The calculation formula is as follows: in, 、 are the maximum and minimum values ​​of the crossover probability, 、 are the maximum and minimum values ​​of the mutation probability, is the fitness value of the individual, is the average fitness value of the population, is the maximum fitness value in the population.

[0041] When an individual's fitness is higher than the population average, it indicates that the individual is superior. In this case, the crossover probability is reduced and the mutation probability is increased. Lowering the crossover probability reduces the likelihood of damaging the genes of superior individuals, while increasing the mutation probability helps explore new path combinations based on superior individuals, preventing the algorithm from converging prematurely. Conversely, when an individual's fitness is lower than the population average, increasing the crossover probability and reducing the mutation probability accelerates the algorithm's convergence and encourages the population to rapidly evolve toward a more optimal solution.

[0042] Step S104: Based on the inspection path and task instructions, monitor in real time and dynamically adjust the inspection path according to equipment operation and environmental changes.

[0043] Specifically, in this embodiment, inspection paths and task instructions are received, inspection personnel and equipment are scheduled to perform tasks, real-time monitoring is performed based on equipment operation and environmental changes, and the inspection path is dynamically adjusted based on the feedback inspection status and result data to generate the optimal inspection path.

[0044] Based on the above, this method has the following advantages: 1) Improve inspection efficiency: Combine multi-source data integration and analysis with improved algorithms to quickly generate optimal or better paths, reduce ineffective walking distance, and improve inspection efficiency.

[0045] 2) Reduced operation and maintenance costs: Intelligent task distribution and dynamic path adjustment rationally allocate resources, reduce equipment repair and replacement costs, and lower overall operation and maintenance costs.

[0046] 3) Enhance system reliability: Real-time monitoring and path adjustment ensure timely inspection and maintenance of equipment, reduce the probability of failure, and enhance system stability.

[0047] 4) Promote the development of the technology ecosystem: Integrate multiple technologies to provide innovative solutions and promote the development of the technology ecosystem for operation and maintenance of new energy power plants.

[0048] Example 1 (1) Implementation of multi-source data collection and network integration At a large offshore wind farm, temperature, vibration, current, and voltage sensors are installed in the nacelle and at the base of each wind turbine tower to collect operating parameters. Meteorological sensors are deployed in the surrounding waters to collect meteorological data such as wind speed, direction, and wave height. A geographic information system (GIS) is used to capture geographic information such as topography and equipment distribution. This data is then transmitted to a data storage server via a 5G communication network, where it is stored and consolidated.

[0049] 2. Implementation of High-Concurrency Data Processing and Mining A data processing platform was built using the Hadoop distributed computing framework, and stored data was imported into the Hadoop cluster. The MapReduce programming model was used for parallel data processing. The Apriori algorithm was employed to identify correlations between equipment operation and meteorological data, and the K-Means clustering algorithm was used to classify wind turbines. Furthermore, data cleaning tools were used to clean the data, and linear interpolation was used to fill in missing data.

[0050] 3. Improved Implementation of Path Planning Algorithms In this offshore wind farm, wind turbines, booster stations, and submarine cable connection points are constructed as a weighted directed graph. Equipment importance scores are determined based on equipment maintenance manuals and historical fault records. Fault risk scores are calculated in combination with real-time operating parameters to derive equipment priority weights. Environmental factor weights are calculated using meteorological monitoring data. The Dijkstra algorithm is used to generate an initial path set as the initial population for the genetic algorithm. The population size is set to 50, and the number of generations is set to 100. , , , The optimal inspection path is generated through iterative optimization using genetic algorithms.

[0051] (IV) Task distribution and implementation of intelligent decision-making A database of inspection personnel and equipment information is established to record relevant status information. After route planning is complete, the task distribution module uses the Hungarian algorithm to assign tasks. During the inspection process, real-time data collection and transmission are analyzed. When equipment failure warnings or environmental changes (such as sudden strong winds) are detected, dynamic route adjustments are triggered, and the route is replanned and executed.

[0052] (V) Implementation of the Inspection Route Planning System for New Energy Power Plants Based on the system architecture design, we developed modules for data acquisition, transmission processing, route planning, and inspection execution. We deployed sensors, communication equipment, servers, and inspection equipment, and wrote program codes in programming languages ​​such as Java and Python. Integrated debugging ensured stable system operation.

[0053] It should be noted that the above description is limited to some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the above embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0054] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the embodiment of the present application also provides a new energy power plant inspection path planning system.

[0055] like Figure 2 As shown, the new energy power plant inspection path planning system includes: The data acquisition module 11 is configured to collect multi-source data related to the new energy power plant and integrate the multi-source data, wherein the multi-source data is collected based on a pre-built hierarchical multi-source data acquisition network architecture and includes at least equipment operating parameters, environmental parameters, and geographical parameters; The data processing module 12 is configured to process and analyze the integrated multi-source data; The path planning module 13 is configured to perform inspection path planning based on an improved path planning algorithm and in combination with multi-source data and inspection requirements to generate an optimal inspection path; The dynamic adjustment module 14 is configured to monitor the inspection path and task instructions in real time and dynamically adjust the inspection path according to equipment operation and environmental changes.

[0056] For the convenience of description, the above system is described as being divided into various modules according to their functions. Of course, when implementing the embodiments of the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0057] The system of the above embodiment is used to implement the corresponding method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0058] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, an embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein when the processor executes the program, the method described in any of the above embodiments is implemented.

[0059] Figure 3 10 is a schematic diagram showing a more specific hardware structure of an electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other within the device via the bus 1050.

[0060] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0061] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage devices, dynamic storage devices, etc. The memory 1020 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0062] The input / output interface 1030 is used to connect to an input / output module to enable information input and output. The input / output module can be configured as a component within the device (not shown) or can be externally connected to the device to provide corresponding functions. Input devices may include a keyboard, mouse, touch screen, microphone, various sensors, etc. Output devices may include a display, speaker, vibrator, indicator light, etc.

[0063] The communication interface 1040 is used to connect to a communication module (not shown) to enable communication between the device and other devices. The communication module can communicate via wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, Wi-Fi, Bluetooth, etc.).

[0064] The bus 1050 comprises a pathway for transmitting information between various components of the device, such as the processor 1010 , the memory 1020 , the input / output interface 1030 , and the communication interface 1040 .

[0065] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, it will be understood by those skilled in the art that the above device may only include the components necessary to implement the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0066] The electronic device of the above embodiment is used to implement the corresponding method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0067] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method described in any of the above embodiments.

[0068] The computer-readable media of this embodiment includes permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0069] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0070] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. Within the scope of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0071] In addition, to simplify the description and discussion, and to avoid obscuring the understanding of the embodiments of the present application, well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided figures. Furthermore, devices may be shown in block diagram form to avoid obscuring the understanding of the embodiments of the present application, and this also takes into account the fact that the implementation details of these block diagram devices are highly dependent on the platform on which the embodiments of the present application will be implemented (i.e., these details should be fully understood by those skilled in the art). Where specific details (e.g., circuits) are set forth to describe the exemplary embodiments of the present application, it will be apparent to those skilled in the art that the embodiments of the present application can be implemented without these specific details or with variations therefrom. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0072] Although the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may utilize the embodiments discussed.

[0073] The embodiments of the present application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of this application.

Claims

1. A new energy power plant inspection path planning method, characterized in that: include: Collecting multi-source data related to new energy power plants and integrating the multi-source data, wherein the multi-source data is collected based on a pre-built hierarchical multi-source data collection network architecture and includes at least equipment operating parameters, environmental parameters, and geographic parameters; Performing data processing and analysis on the integrated multi-source data; Based on an improved path planning algorithm, inspection path planning is performed in combination with the multi-source data and inspection requirements to generate an optimal inspection path, wherein the path planning algorithm includes constructing a weighted directed graph model based on the equipment operating parameters, environmental parameters, and geographical parameters, and generating the path plan through an algorithm fusion strategy; According to the inspection path and task instructions, real-time monitoring is performed and the inspection path is dynamically adjusted according to equipment operation and environmental changes.

2. The method according to claim 1, wherein: The hierarchical multi-source data acquisition network architecture includes a perception layer, a transmission layer, and a storage layer arranged from bottom to top; The perception layer is configured to collect equipment operating parameters, environmental parameters, and geographical parameters of the new energy power plant; The transmission layer is configured to encapsulate and transmit the collected parameter data; The storage layer is configured to classify and store the collected parameter data in a database.

3. The method according to claim 1, characterized in that The processing and analysis of the integrated multi-source data includes: The integrated multi-source data is cleaned and preprocessed, and the preprocessed data is deeply analyzed, wherein the association relationship between equipment operating parameters, environmental parameters and geographical parameters is mined through an association rule mining algorithm, the power plant equipment is classified through a cluster analysis algorithm, and the operating status of the power plant equipment is detected in real time through an anomaly detection algorithm.

4. The method according to claim 1, wherein The path planning algorithm includes: Construct a weighted directed graph model to convert the geographical parameter data of new energy power plants into a weighted directed graph , where the node set Contains all equipment locations, important monitoring points and necessary route nodes in the power plant, edge collection Represents a feasible path between nodes; For each edge Assign comprehensive weight , and its calculation formula is: ； in, represents the basic distance weight, represents the weight of environmental factors, Indicates the device priority weight, 、 Represents different nodes, 、 、 represents the weight coefficient, and ; Perform preliminary screening of paths using the Dijkstra algorithm to generate an initial path set; Global optimization is performed through a genetic algorithm, the generated initial path set is used as the initial population of the genetic algorithm, and the population is evolved through multiple genetic operations.

5. The method according to claim 4, characterized in that: The base distance weight is determined by the node and The actual geographical distance between them is determined; The environmental factor weight calculation formula is: ； Where, Indicates wind speed, represents the wind speed influence coefficient, Indicates the wind speed threshold; The device priority weight calculation formula is: ； Where, Indicates the importance score of the equipment. represents the equipment failure risk score, Indicates the priority adjustment coefficient.

6. The method according to claim 4, characterized in that It also includes a selection operation based on the individual fitness value, and the fitness function formula is: ； in, , Indicates the number of high-priority devices covered in the statistical path. Indicates the total number of high-priority equipment in the power plant, 、 Represents the adjustment coefficient.

7. The method according to claim 6, characterized in that: During the execution of the genetic algorithm, the adaptive crossover probability and mutation probability Strategy to adapt to the needs of different evolutionary stages of the algorithm. Its calculation formula is as follows: ； ； Where, 、 represent the maximum and minimum values ​​of the crossover probability, respectively. 、 The maximum and minimum values ​​of the teacher mutation probability, represents the fitness value of the individual, represents the average fitness value of the population, Represents the maximum fitness value in the population.

8. A new energy power plant inspection path planning system, characterized in that: include: a data acquisition module configured to collect multi-source data related to the new energy power plant and perform data integration on the multi-source data, wherein the multi-source data is collected based on a pre-built hierarchical multi-source data acquisition network architecture and includes at least equipment operating parameters, environmental parameters, and geographical parameters; A data processing module is configured to process and analyze the integrated multi-source data; a path planning module configured to perform inspection path planning based on an improved path planning algorithm and in combination with the multi-source data and inspection requirements to generate an optimal inspection path, wherein the path planning algorithm includes constructing a weighted directed graph model based on the equipment operating parameters, environmental parameters, and geographical parameters, and generating the path plan through an algorithm fusion strategy; The dynamic adjustment module is configured to monitor the inspection path and task instructions in real time and dynamically adjust the inspection path according to equipment operation and environmental changes.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the program.

10. A non-transitory computer-readable storage medium, characterized in that in, The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 7.

Images