Health state determination method and device, storage medium and electronic device

Abstract

The invention discloses a health state determination method and device, a storage medium and an electronic device, and the method comprises the steps: obtaining state monitoring data of target equipment, and controlling an unmanned plane to obtain image information corresponding to the target equipment; determining a running state corresponding to the target equipment according to the state monitoring data, and performing fault assessment on the target equipment according to the running state to determine an assessment result; and inputting the image information into a missing recognition algorithm platform, and determining an inspection result corresponding to the target equipment according to an output result of the missing recognition algorithm platform, and determining the health state of the target equipment according to the evaluation result and the inspection result. By means of the method, the problem that in the related technology, in the process of evaluating the health state of the target equipment, only qualitative diagnosis of internal faults of the target equipment can be achieved, and quantitative inspection of the appearance of the target equipment cannot be achieved can be solved.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular, to a method and device for determining a health status, a storage medium, and an electronic device. Background Art

[0002] At present, the monitoring of wind turbines mainly involves installing various sensors at key parts of the wind turbines, such as wind speed sensors, wind direction sensors, temperature sensors, vibration sensors, current sensors, voltage sensors, speed sensors, and lubricating oil status sensors. These sensors collect data on various parameters during the operation of the wind turbine in real time. Through the data acquisition system, the data collected by the sensors is transmitted to the monitoring system in real time. The data acquisition system usually has high-frequency sampling capabilities to ensure that data under various operating conditions is captured. With the increase in data, how to deeply integrate and analyze various data and judge the health status of the equipment has become a major problem that needs to be solved urgently.

[0003] At present, when monitoring wind turbine equipment, it is necessary to obtain various equipment operation monitoring data, such as Supervisory Control and Data Acquisition data (SCADA data, such as wind speed, wind direction, generator speed, generator power, ambient temperature, pitch angle, gearbox oil temperature, pitch speed, pitch state, yaw speed, yaw direction, current, voltage, etc.), Condition Monitoring System data (CMS data, such as blade vibration data, tower shaking data, gearbox vibration data, pitch bearing vibration data, yaw bearing vibration data, tower foundation settlement data, etc.), oil data (such as hierarchical ferromagnetic particle count, non-ferromagnetic particle count, oil viscosity, oil water content), lightning current data (such as lightning strike time, lightning current peak value, lightning current polarity, lightning strike channel identification, lightning strike number charge, specific energy and steep wave maximum value). However, the acquisition of the above data can only achieve qualitative diagnosis of internal faults of the equipment, but cannot achieve quantitative inspection of appearance problems.

[0004] In the related art, in the process of health status assessment of the target device, only qualitative diagnosis of internal faults of the target device can be achieved, but quantitative inspection of the appearance of the target device cannot be achieved. No effective solution has been found yet. Summary of the invention

[0005] The embodiments of the present application relate to a method and device for determining a health status, a storage medium, and an electronic device. Through the embodiments of the present application, it is possible to solve the problem in the related art that, in the process of evaluating the health status of a target device, only a qualitative diagnosis of the internal faults of the target device can be achieved, but a quantitative inspection of the appearance of the target device cannot be achieved.

[0006] According to an embodiment of the embodiments of the present application, a method for determining a health status is provided, including: obtaining status monitoring data of a target device, and controlling a drone to obtain image information corresponding to the target device; determining an operating status corresponding to the target device according to the status monitoring data, and performing a fault assessment on the target device according to the operating status to determine an assessment result; and inputting the image information into a missing identification algorithm platform, and determining an inspection result corresponding to the target device according to an output result of the missing identification algorithm platform; and determining the health status of the target device according to the assessment result and the inspection result.

[0007] In an exemplary embodiment, the state monitoring data of the target device includes at least one of the following: first state monitoring data corresponding to the transmission chain of the target device; second state monitoring data corresponding to the blades of the target device; and third state monitoring data corresponding to the tower of the target device.

[0008] In an exemplary embodiment, determining the operating state corresponding to the target device according to the state monitoring data includes: standardizing the state monitoring data, and performing data fusion on the standardized state monitoring data to generate a state monitoring data set corresponding to the target device; determining characteristic parameters corresponding to the target device according to data in the state monitoring data set; determining the operating state corresponding to the target device according to the characteristic parameters, wherein the characteristic parameters include at least one of the following: degree of wear, fatigue condition, lightning protection performance and safe operating space of the target device.

[0009] In an exemplary embodiment, determining the operating state corresponding to the target device according to the characteristic parameter includes: comparing the characteristic parameter with a preset characteristic parameter threshold to determine a comparison result; when the comparison result indicates that the characteristic parameter is less than or equal to the characteristic parameter threshold, determining that the operating state is a normal state; when the comparison result indicates that the characteristic parameter is greater than the characteristic parameter threshold, determining that the operating state is an abnormal state.

[0010] In an exemplary embodiment, the state monitoring data is standardized, including: preprocessing the state monitoring data; aligning the preprocessed state monitoring data to obtain the standardized state monitoring data, wherein the data alignment includes: synchronizing the preprocessed state monitoring data in time and space.

[0011] In an exemplary embodiment, the image information is input into a defect recognition algorithm platform, and the inspection result corresponding to the target device is determined based on the output result of the defect recognition algorithm, including: determining the target part of the target device corresponding to the image information, and inputting the image information into the defect recognition algorithm platform corresponding to the target part, so that the defect recognition algorithm platform outputs the target defect corresponding to the target device based on the image information; and performing quantitative analysis on the target defect to determine the inspection result corresponding to the target device based on the first analysis result.

[0012] In an exemplary embodiment, the target defect is quantitatively analyzed to determine the inspection result corresponding to the target device based on a first analysis result, including: determining the geometric parameters corresponding to the target defect based on image processing technology, and determining the position information corresponding to the target defect; and determining the defect type corresponding to the target defect, wherein the first analysis result includes: the geometric parameters corresponding to the target defect, the position information and the defect type; and evaluating the defect degree corresponding to the target device based on the first analysis result to determine the inspection result, wherein the defect degree includes: mild defects, moderate defects and severe defects.

[0013] According to another embodiment of the embodiment of the present application, a device for determining a health status is also provided, including: an acquisition module, used to acquire status monitoring data of a target device, and control a drone to acquire image information corresponding to the target device; a first determination module, used to determine an operating status corresponding to the target device according to the status monitoring data, and perform a fault assessment on the target device according to the operating status to determine an assessment result; and, input the image information into a missing identification algorithm platform, and determine an inspection result corresponding to the target device according to an output result of the missing identification algorithm platform; a second determination module, used to determine the health status of the target device according to the assessment result and the inspection result.

[0014] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above method when running.

[0015] According to another aspect of the embodiments of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method through the computer program.

[0016] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, wherein the computer program is executed by a processor to perform the method.

[0017] In an embodiment of the present application, the state monitoring data of the target device is obtained, and the drone is controlled to obtain the image information corresponding to the target device. On the one hand, the operating state corresponding to the target device is determined according to the state monitoring data, and the target device is subjected to a fault assessment according to the operating state to determine the assessment result; on the other hand, the image information is input into the missing recognition algorithm platform, and the inspection result corresponding to the target device is determined according to the output result of the missing recognition algorithm platform. The health state of the target device is determined according to the assessment result and the inspection result set. That is to say, the embodiment of the present application can realize the qualitative diagnosis of the internal fault of the target device by determining the operating state of the target device according to the state monitoring data, and then performing a fault assessment on the target device according to the operating state to determine the assessment result; and then by inputting the image information into the missing recognition algorithm platform, and determining the inspection result corresponding to the target device according to the output result of the missing recognition algorithm platform, the appearance of the target device can be quantitatively inspected. Through the embodiment of the present application, the problem that in the process of evaluating the health state of the target device in the related art, only the qualitative diagnosis of the internal fault of the target device can be realized, but the quantitative inspection of the appearance of the target device cannot be realized. This can not only achieve qualitative diagnosis of internal faults of the target device, but also achieve quantitative inspection of the appearance of the target device. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 It is a hardware structure block diagram of a computer terminal of a method for determining a health status according to an embodiment of the present application;

[0020] Figure 2 is a flow chart of a method for determining a health status according to an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of a device for diagnosing fan status through external inspection and internal diagnosis according to an optional embodiment of the present application;

[0022] Figure 4is a structural block diagram of a device for diagnosing fan status through external inspection and internal diagnosis according to an optional embodiment of the present application;

[0023] Figure 5 is a flow chart of a method for diagnosing fan status based on external inspection and internal diagnosis based on multi-source data fusion according to an optional embodiment of the present application;

[0024] Figure 6 It is a structural block diagram of a device for determining a health status according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims 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 interchanged 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 device 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 units that are not clearly listed or inherent to these processes, methods, products, or devices; "plurality" means two or more.

[0027] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal or similar computing device or cloud platform or independent physical server or software platform, wherein the above software platform is run through one or more servers. Taking running on a computer terminal as an example, Figure 1 1 is a hardware structure block diagram of a computer terminal of a method for determining a health status according to an embodiment of the present application. Figure 1 As shown, the computer terminal may include one or more ( Figure 1Only one is shown in the figure) processor 102 and memory 104 for storing data. In an exemplary embodiment, the computer terminal may also include a transmission device 106 for communication functions and an input and output device 108, wherein the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. A person skilled in the art can understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Equivalent functions or comparisons shown Figure 1 A different configuration with more features is shown.

[0028] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as computer programs corresponding to the methods in the embodiments of the present application. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, that is, the above-mentioned methods are implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0029] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0030] In this embodiment, a method for determining a health status is provided, which is applied to the above-mentioned computer terminal. Figure 2 : is a flow chart of a method for determining a health status according to an embodiment of the present application, the flow chart comprising the following steps:

[0031] Step S202, obtaining status monitoring data of the target device, and controlling the drone to obtain image information corresponding to the target device;

[0032] The target device may be a wind turbine in a wind turbine generator system.

[0033] Step S204, determining the operating state corresponding to the target device according to the state monitoring data, and performing a fault assessment on the target device according to the operating state to determine an assessment result; and inputting the image information into a defect recognition algorithm platform, and determining the inspection result corresponding to the target device according to the output result of the defect recognition algorithm platform;

[0034] Step S206: determining the health status of the target device according to the evaluation result and the inspection result.

[0035] In an embodiment of the present application, the state monitoring data of the target device is obtained, and the drone is controlled to obtain the image information corresponding to the target device. On the one hand, the operating state corresponding to the target device is determined according to the state monitoring data, and the target device is subjected to a fault assessment according to the operating state to determine the assessment result; on the other hand, the image information is input into the missing recognition algorithm platform, and the inspection result corresponding to the target device is determined according to the output result of the missing recognition algorithm platform. The health state of the target device is determined according to the assessment result and the inspection result set. That is to say, the embodiment of the present application can realize the qualitative diagnosis of the internal fault of the target device by determining the operating state of the target device according to the state monitoring data, and then performing a fault assessment on the target device according to the operating state to determine the assessment result; and then by inputting the image information into the missing recognition algorithm platform, and determining the inspection result corresponding to the target device according to the output result of the missing recognition algorithm platform, the appearance of the target device can be quantitatively inspected. Through the embodiment of the present application, the problem that in the process of evaluating the health state of the target device in the related art, only the qualitative diagnosis of the internal fault of the target device can be realized, but the quantitative inspection of the appearance of the target device cannot be realized. This can not only achieve qualitative diagnosis of internal faults of the target device, but also achieve quantitative inspection of the appearance of the target device.

[0036] The above-mentioned defect recognition algorithm platform is a software platform for automatically detecting and identifying object defects or missing parts from data such as images, videos or three-dimensional models. In the wind power industry, especially in the field of wind turbine condition monitoring and maintenance, the defect recognition algorithm platform combines advanced computer vision technology and machine learning algorithms to automatically check the appearance defects of wind turbine blades, towers, nacelles and other components, such as cracks, corrosion, lightning damage, cracking, shedding or any other type of physical damage.

[0037] Optionally, the above S204 inputs the image information into a missing recognition algorithm platform, and determines the inspection result corresponding to the target device based on the output result of the missing recognition algorithm, which limits the application of the missing recognition algorithm platform in the embodiment of the present application, specifically: determining the target part of the target device corresponding to the image information, and inputting the image information into the missing recognition algorithm platform corresponding to the target part, so that the missing recognition algorithm platform outputs the target defect corresponding to the target device based on the image information; and performing quantitative analysis on the target defect to determine the inspection result corresponding to the target device based on the first analysis result.

[0038] That is, the specific application of the missing identification algorithm platform can include the following key steps:

[0039] (1) Data input: The missing recognition algorithm platform receives image or video data collected by drones, cameras, lidar and other equipment. This data may be obtained during regular inspections or continuously recorded by fixed monitoring systems.

[0040] In the embodiment of the present application, the data input to the missing identification algorithm platform is: image information.

[0041] (2) Preprocessing: The input raw data may require preprocessing, including image enhancement, denoising, size normalization, etc., to improve the accuracy and reliability of subsequent recognition algorithms.

[0042] In the embodiment of the present application, the image information to be input into the defect recognition algorithm platform may be preprocessed, for example, image enhancement and other operations may be performed on the image information.

[0043] (3) Defect detection algorithm: The core of the defect recognition algorithm platform is the defect detection algorithm, which can identify and locate abnormal areas in the image. Common algorithms corresponding to the defect recognition algorithm platform include but are not limited to:

[0044] 1) Deep learning algorithms, such as convolutional neural networks (CNNs) and object detection models (e.g., YOLO, FasterR-CNN), can automatically learn and identify various types of defect features.

[0045] 2) Computer vision techniques, such as edge detection, morphological processing, and feature matching, are used to identify specific types of defects, such as cracks and corrosion.

[0046] 3) 3D model analysis to identify structural defects, such as uneven settlement or physical damage.

[0047] In an embodiment of the present application, the defect recognition algorithm platform can identify the structural defects of the target device corresponding to the image information based on the input image information.

[0048] (4) Defect classification and quantification: The defect recognition algorithm platform is able to classify the detected defects according to the preset classification model and quantify the size, location and severity of the defects. For example, cracks on the blade are not only identified but also quantified into length, width and depth for more accurate evaluation.

[0049] Optionally, in an embodiment of the present application, after identifying the structural defects of the target device corresponding to the image information through the missing recognition algorithm platform, the target defects can also be quantitatively analyzed to determine the inspection results corresponding to the target device based on the first analysis result, specifically: determining the geometric parameters corresponding to the target defects based on image processing technology, and determining the position information corresponding to the target defects; and determining the defect type corresponding to the target defect, wherein the first analysis result includes: the geometric parameters corresponding to the target defect, the position information and the defect type; evaluating the defect degree corresponding to the target device based on the first analysis result to determine the inspection result, wherein the defect degree includes: mild defects, moderate defects and severe defects.

[0050] That is to say, the target defects can be classified. For example, the defects of the blades in the target equipment may include six major categories, including leading edge corrosion, surface defects, lightning damage, leading and trailing edge cracking, accessory shedding damage, and surface cracks, and 28 minor defect types. The geometric parameters corresponding to the target defects can be determined, that is, the length, width, and depth corresponding to the defects, as well as the specific location of the defects in the target equipment.

[0051] Then, the defect degree corresponding to the target device can be evaluated according to the first analysis result corresponding to the target defect. The above defect degree refers to the defect degree determined by external inspection of the target device, that is, the defect degree of the target device in the structure and other external aspects.

[0052] (5) Result output and report: The identified defect information is organized into a detailed report, including the defect image, location coordinates, type, and severity level. This information can be used for maintenance decision-making, helping operation and maintenance personnel to quickly locate problems and take appropriate actions.

[0053] (6) Continuous learning and optimization: The missing recognition algorithm platform often has the ability to learn and optimize the model from historical data and manual annotations to improve recognition accuracy and efficiency.

[0054] The application of the defect recognition algorithm platform in the wind power industry has greatly improved the inspection efficiency and safety, reduced the frequency and intensity of manual inspections, and helped to discover potential defects early, prevent failures, and ensure the long-term stable operation of wind turbines. Combined with the internal diagnosis system of multi-source data fusion, the platform can achieve comprehensive monitoring and intelligent diagnosis of the health status of wind turbine equipment, providing strong technical support for wind power operation and maintenance.

[0055] Optionally, the state monitoring data of the target device in the above step S202 includes at least one of the following: first state monitoring data corresponding to the transmission chain of the target device; second state monitoring data corresponding to the blades of the target device; and third state monitoring data corresponding to the tower of the target device.

[0056] It is understandable that the status monitoring data can be obtained through the transmission chain monitoring module, the blade monitoring module and the tower monitoring module, wherein:

[0057] The transmission chain monitoring module mainly monitors the transmission chain of the target equipment and is responsible for collecting the SCADA data, CMS data, oil data, equipment inherent parameters, etc. of the fan. That is, the first state monitoring data may include: SCADA data, CMS data, oil data, equipment inherent parameters, etc. of the fan.

[0058] The blade monitoring module mainly monitors the blades of the target equipment and is responsible for collecting the blade's SCADA data, CMS data, lightning current data, clearance data, pitch angle deviation, etc. That is, the second state monitoring data may include: blade's SCADA data, CMS data, lightning current data, clearance data, pitch angle deviation, etc.

[0059] The tower monitoring module mainly monitors the tower of the target equipment and is responsible for collecting the tower's tilt data, uneven settlement data, sway overrun data, etc. That is, the third state monitoring data may include: tower's tilt data, uneven settlement data, sway overrun data, etc.

[0060] Optionally, the above-mentioned step S204 of determining the operating state corresponding to the target device according to the state monitoring data includes: standardizing the state monitoring data, and performing data fusion on the standardized state monitoring data to generate a state monitoring data set corresponding to the target device; determining characteristic parameters corresponding to the target device according to the data in the state monitoring data set; determining the operating state corresponding to the target device according to the characteristic parameters, wherein the characteristic parameters include at least one of the following: the degree of wear, fatigue condition, lightning protection performance and safe operating space of the target device.

[0061] It can be understood that in the embodiment of the present application, the specific method for determining the operating status of the target device includes:

[0062] (1) Data standardization processing.

[0063] Optionally, the state monitoring data is standardized, including: preprocessing the state monitoring data; aligning the preprocessed state monitoring data to obtain the standardized state monitoring data, wherein the data alignment includes: time synchronization and space synchronization of the preprocessed state monitoring data.

[0064] It is understood that data standardization refers to converting condition monitoring data from different sensors and systems into a unified, comparable format or dimension. Since the original data may have different units, magnitudes, and measurement frequencies, standardization is a necessary step to ensure the comparability of the data and the effectiveness of subsequent analysis. Specific operations may include:

[0065] 1) Normalization or standardization: Scaling the condition monitoring data to a specific range (e.g., 0-1) or converting it to a format with zero mean and unit variance.

[0066] 2) Data cleaning: Remove outliers, missing values ​​or noise in condition monitoring data to ensure data quality and reliability.

[0067] 3) Data fusion to generate condition monitoring data set:

[0068] Data fusion refers to integrating data from multiple sources to form a unified condition monitoring data set to more comprehensively evaluate the equipment status. In the embodiment of the present application, the condition monitoring data may include:

[0069] <1> SCADA data: monitors wind turbine operating parameters such as wind speed, wind direction, power, temperature, etc.

[0070] <2> SCMS data: Vibration monitoring system data used to evaluate the vibration condition of components.

[0071] <3> Oil analysis data: monitor the condition of the lubricant, such as particle count, viscosity, water content, etc.

[0072] <4> Drone inspection data: including high-definition images, videos or 3D models for visual inspection of wind turbine appearance.

[0073] The purpose of data fusion is to improve the accuracy and comprehensiveness of fault diagnosis by integrating data from different systems and time points. The fusion process may include:

[0074] 4) Time alignment and spatial correspondence of condition monitoring data:

[0075] Time alignment: Ensure that all condition monitoring data are synchronized in time to analyze the correlation between condition monitoring data. Spatial correspondence: Correlate condition monitoring data at different locations to identify possible patterns or anomalies.

[0076] (2) Feature extraction: Extract characteristic parameters related to the health status of the equipment from the fused data. Specifically, a series of characteristic parameters can be determined from the fused status monitoring data set, which can reflect the operating status and health status of the equipment. The characteristic parameters include at least:

[0077] 1) Wear degree: By analyzing vibration data, oil analysis data, etc., the wear degree of blades, gearboxes and other components can be determined.

[0078] 2) Fatigue condition: Evaluate the fatigue state of blades or transmission chains under repeated stress.

[0079] 3) Lightning protection performance: Based on the lightning current data, determine whether the lightning protection system of the blades and tower is effective.

[0080] 4) Safe operating space: Analyze the distance between the blade and the tower and other blades to ensure sufficient safety space.

[0081] Among them, determining the operating status corresponding to the target device according to the characteristic parameter includes: comparing the characteristic parameter with a preset characteristic parameter threshold to determine a comparison result; when the comparison result indicates that the characteristic parameter is less than or equal to the characteristic parameter threshold, determining that the operating status is a normal state; when the comparison result indicates that the characteristic parameter is greater than the characteristic parameter threshold, determining that the operating status is an abnormal state.

[0082] It is understandable that these characteristic parameters can be analyzed by algorithms to determine the current operating status of the equipment. For example, if a parameter (such as vibration amplitude) exceeds a preset threshold, it may indicate that the equipment is faulty; if multiple parameters (such as vibration amplitude, oil metal particle count) indicate abnormalities at the same time, it may indicate more serious equipment health problems.

[0083] (3) Evaluation and judgment of operating status.

[0084] Based on the extracted characteristic parameters, the system will evaluate the operating status of the equipment to determine whether it exceeds the normal range and whether there are potential failures or risks. This evaluation process may use threshold comparison, pattern recognition or machine learning models to compare the current parameter value with the normal range or model prediction results to identify abnormal conditions.

[0085] Through this series of standardized processing, data fusion, feature parameter extraction and operating status evaluation, intelligent and comprehensive monitoring of the operating status of wind turbines can be achieved, which helps to identify faults at an early stage, reduce unplanned downtime, and improve the operating efficiency and safety of equipment.

[0086] In order to better understand the process of the above-mentioned method for determining the health status, the above-mentioned method for determining the health status is described below in combination with an optional embodiment, but it is not used to limit the technical solution of the embodiment of the present application.

[0087] Among them, the wind turbine is composed of a wind rotor, a generator, blades, a hub, a tower, etc. The main function of the wind turbine is to generate electricity by rotating the blades under wind force. During the operation of the wind turbine, in order to ensure the constant output frequency, the operation status and maintenance status of the wind turbine need to be monitored regularly.

[0088] In view of the problem in the related art that, in the process of health status assessment of the target equipment, only a qualitative diagnosis of the internal faults of the target equipment can be achieved, but a quantitative inspection of the appearance of the target equipment cannot be achieved, an optional embodiment of the present application provides a method for diagnosing the status of a fan based on external inspection and internal diagnosis based on multi-source data fusion. Specifically: using multi-source data fusion diagnosis technology, a method of fusing the multi-sensor monitoring data of the fan with the inspection result data of the appearance of the fan by a drone can realize a qualitative and quantitative dual analysis of the defects of the fan blades, tower, and cabin. Through the optional embodiments of the present application, it is possible to solve the problem that in the daily monitoring process of the fan, due to the dispersion of data, only a few faults can be monitored and warned, the information is one-sided, and some faults cannot be diagnosed through the data of a single monitoring system.

[0089] The optional embodiment of the present application provides a method for diagnosing the status of a fan based on external inspection and internal diagnosis based on multi-source data fusion, which mainly integrates, analyzes and processes various types of data from different sensors and different time points to obtain more comprehensive and accurate information. In the diagnosis of the status of the fan, multi-source data fusion can include vibration data, temperature data, current data, voltage data, oil analysis data, visual image data and other types of data.

[0090] Among them, internal diagnosis focuses on in-depth inspection and analysis of key components inside the wind turbine, including transmission chain monitoring module, blade monitoring module, and tower monitoring module. External inspection mainly uses external equipment such as drones to conduct non-contact inspections of wind turbines, including: drone autonomous inspection module.

[0091] In order to realize the internal diagnosis and external inspection of the wind turbine, the optional embodiment of the present application defines a wind turbine status diagnosis device for external inspection and internal diagnosis. Figure 3 is a schematic diagram of a device for diagnosing fan status by external inspection and internal diagnosis according to an optional embodiment of the present application, such as Figure 3 As shown, the external inspection and internal diagnosis device for the status of the wind turbine includes: a wind farm control room outside the wind turbine, wherein the wind farm control room includes a video server, a data server and an application server; a monitoring workstation; and a data monitoring module for the wind turbine, wherein the data monitoring module mainly includes: a transmission chain monitoring module, a blade monitoring module, a tower monitoring module and a drone autonomous inspection module. Figure 4 is a structural block diagram of a device for diagnosing fan status in external inspection and internal diagnosis according to an optional embodiment of the present application, Figure 4 The structural diagram of the transmission chain monitoring module, blade monitoring module, tower monitoring module and drone autonomous inspection module is defined in the figure. Figure 4 As shown:

[0092] Internal diagnosis of wind turbines usually needs to be performed when the wind turbine is shut down or running at low load, and internal status information is obtained by installing sensors and collecting data samples. The main purpose of internal diagnosis is to discover potential faults or performance degradation inside the wind turbine, such as bearing wear, gearbox failure, generator insulation aging, etc. The internal diagnosis of wind turbines includes three business modules: transmission chain monitoring module, blade monitoring module, and tower monitoring module. Specifically:

[0093] Step 1.1, collect data.

[0094] (1) The transmission chain monitoring module realizes the fault diagnosis capability of different fault types of the transmission chain (spindle, gearbox, generator) at different stages through the integration of multiple data sources.

[0095] The transmission chain monitoring module is mainly responsible for collecting SCADA data, CMS data, oil data, equipment inherent parameters, etc. (ie, first state monitoring data) of the fan (ie, the target device).

[0096] (2) The blade monitoring module can identify potential blade failures at the stage of subtle changes by integrating real-time data from different sensors and systems, thereby achieving earlier fault warning.

[0097] The blade monitoring module is mainly responsible for collecting SCADA data, CMS data, lightning current data, clearance data, pitch angle deviation, etc. (i.e., the first state monitoring data).

[0098] (3) The tower monitoring module mainly collects tower tilt data, uneven settlement data, and sway limit data to analyze the equipment status. The drone autonomous inspection module can automatically summarize and report the location and size information of defects, so as to achieve quantitative analysis and judgment of equipment appearance defects.

[0099] The tower monitoring module is mainly responsible for collecting tower tilt data, uneven settlement data, excessive shaking data, etc.

[0100] Step 1.2, after collecting the condition monitoring data, the data (i.e., condition monitoring data) can be preprocessed to clean the collected raw data to remove noise, outliers, and missing values.

[0101] Specific:

[0102] Data alignment is performed to ensure time synchronization and spatial correspondence (i.e. spatial synchronization) between different data sources. Data is normalized or standardized to eliminate the impact of dimensional differences on the analysis results.

[0103] Step 1.3, after preprocessing the data, data fusion and feature extraction can be performed to fuse SCADA data, CMS data and other data to form a comprehensive data set of blade operation (i.e., condition monitoring data set). Specifically:

[0104] During the fusion process, the correlation and complementarity between different data sources need to be considered to ensure that the fused data can more accurately reflect the operating status of the blades. Extract characteristic parameters related to the health status of the drive chain, blades, and tower from the fused data set. These characteristic parameters may include vibration spectrum characteristics, temperature change trends, lightning current peaks, clearance distance changes, and pitch angle deviations. The characteristic parameters are further processed and analyzed using methods such as statistical analysis, signal processing, or machine learning to extract higher-level information or patterns.

[0105] Step 1.4, after the data processing is completed, the fan fault diagnosis can be performed, and the current operating status of the equipment can be evaluated based on the extracted characteristic parameters. Specifically:

[0106] Fault diagnosis can include evaluating the blade's wear, fatigue, lightning protection, and safe operating space. By comparing with preset thresholds or models, it is determined whether the blade has potential faults or risks. Through fault diagnosis, the specific type, location, and severity of the fault can be determined.

[0107] After completing the internal diagnosis of the wind turbine, the wind turbine can be inspected externally. The external inspection mainly uses external equipment such as drones to conduct non-contact inspections of the wind turbine. These devices are equipped with high-definition cameras, infrared thermal imagers, lidar and other sensors, which can collect real-time data such as the appearance image, temperature distribution, and three-dimensional model of the wind turbine. The main purpose of the external inspection is to quickly discover obvious faults or abnormalities on the outside of the wind turbine, such as blade cracks, tower tilt, cable damage, etc. Specifically:

[0108] Step 2.1: After the equipment fault is diagnosed and confirmed in the final stage of internal diagnosis, an inspection command will be issued to the drone to carry out inspections of the wind turbine blades, tower, nacelle, etc. by mounting high-definition equipment.

[0109] Step 2.2: Import a large number of inspection pictures (connected image information) into the defect recognition algorithm platform of different components of the deployed wind turbine for defect recognition. For example, the blades include six major categories of defects, including leading edge corrosion, surface defects, lightning damage, leading and trailing edge cracking, accessory shedding damage, and surface cracks, and 28 subcategories of defects.

[0110] In step 2.3, in addition to discovering defects in the appearance of the fan equipment, the location information and size information of the defects can also be automatically summarized and reported to achieve quantitative analysis and judgment of the appearance defects of the equipment.

[0111] Another optional embodiment of the present application provides a method for diagnosing fan status based on external inspection and internal diagnosis based on multi-source data fusion, specifically:

[0112] Figure 5 is a flow chart of a method for diagnosing fan status based on external inspection and internal diagnosis based on multi-source data fusion according to an optional embodiment of the present application, such as Figure 5 As shown:

[0113] The fan status diagnosis method based on multi-source data fusion includes two operation processes: internal diagnosis and external inspection. The internal diagnosis includes:

[0114] Step S501 - 1 , obtaining monitoring data (ie, status monitoring data).

[0115] Among them, the transmission chain monitoring module is mainly responsible for collecting the wind turbine's SCADA data, CMS data, oil data, equipment inherent parameters, etc. The blade monitoring module is mainly responsible for collecting SCADA data, CMS data, lightning current data, clearance data, pitch angle deviation, etc. The tower monitoring module mainly collects tower tilt data, uneven settlement data, and sway limit data.

[0116] Step S501 - 2: data preprocessing.

[0117] Clean the collected raw data to remove noise, outliers and missing values. Align the data to ensure time synchronization and spatial correspondence between different data sources. Normalize or standardize the data to eliminate the impact of dimensional differences on the analysis results.

[0118] Step S501 - 3: data fusion and feature extraction.

[0119] Fuse SCADA data, CMS data and other data to form a comprehensive data set for blade operation. During the fusion process, the correlation and complementarity between different data sources need to be considered to ensure that the fused data can more accurately reflect the operating status of the blades. Extract characteristic parameters related to the health status of the drive chain, blades, and tower from the fused data set. These characteristic parameters may include vibration spectrum characteristics, temperature change trends, lightning current peaks, clearance distance changes, and pitch angle deviations. Use statistical analysis, signal processing, or machine learning methods to further process and analyze the characteristic parameters to extract higher-level information or patterns.

[0120] Step S501 - 4: Fault diagnosis.

[0121] Based on the extracted characteristic parameters, the current operating status of the equipment is evaluated. This may include evaluating the degree of wear, fatigue, lightning protection performance, and safe operating space of the blades. By comparing with the preset threshold or model, it is determined whether there is a potential fault or risk in the blade. Through fault diagnosis, the specific type, location, and severity of the fault are determined.

[0122] After confirming the fan defect through internal diagnosis, you can perform external inspection operations on the fan, specifically:

[0123] Step 502-1: The drone is equipped with a high-definition camera for inspection.

[0124] Step S502-2, obtaining a visible light high-definition image.

[0125] After the equipment fault is diagnosed and confirmed in the final stage of internal diagnosis, inspection instructions will be issued to the drone, which will then carry out inspections of the exterior of the wind turbine blades, tower, nacelle, etc. by mounting high-definition equipment.

[0126] Step S502-3: image defect (ie, target defect) identification.

[0127] A large number of inspection images are imported into the defect recognition algorithm platform of different components of the deployed wind turbine for defect recognition. For example, the blades include six major categories of defects, including leading edge corrosion, surface defects, lightning damage, leading and trailing edge cracking, accessory detachment damage, and surface cracks, and 28 subcategories of defects.

[0128] Step S502-4, determine the defect location information and size information.

[0129] In addition to discovering defects in the appearance of fan equipment, the location information and size information of the defects can also be automatically summarized and reported to achieve quantitative analysis and judgment of equipment appearance defects.

[0130] In summary, through the optional embodiments of the present application, it is possible to achieve both qualitative and quantitative dual analysis of defects in blades, towers, and nacelles. That is, the wind turbine can qualitatively determine what the problem is through CMS vibration monitoring, and can perform quantitative analysis after integrating inspection data, video data, and SCADA data to determine the specific location, specific size, and other information of the defect; it can also achieve different degrees of analysis and diagnosis of wind turbine faults. That is, through CMS vibration monitoring data, oil data, and SCADA data, it is possible to analyze gearbox faults to different degrees, determine the faults of the equipment at different periods of early, middle, and late, analyze different degrees, and guide the scientific and rigorous operation and maintenance decisions of the station. At the same time, the algorithm can be adjusted based on the scientific dynamic acquisition strategy of the fault. That is, based on the degree and time of the occurrence of the fault, the CMS acquisition strategy is dynamically adjusted. If the wind turbine does not fail or the fault is in the early stage, the sampling frequency is low; after the fault occurs, the sampling frequency is intelligently increased, and the system recording and broadcasting function is triggered at the same time, and the unit fault data analysis is intercepted and retained to ensure the accuracy of the later diagnosis. In turn, it is possible to achieve a comprehensive health assessment for the wind turbine. That is, various monitoring data basically describe equipment monitoring in a single way, and it is difficult to comprehensively judge the actual health of a unit. By integrating multi-source data, it is possible to effectively analyze and judge the health status of the unit both quantitatively and qualitatively, and to describe the equipment monitoring status more accurately, diversely and effectively.

[0131] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0132] The embodiment of the present application also provides a structural block diagram of a device for determining a health status. Figure 6 is a structural block diagram of a device for determining a health status according to an embodiment of the present application; Figure 6 As shown, including:

[0133] The acquisition module 62 is used to acquire the status monitoring data of the target device and control the UAV to acquire the image information corresponding to the target device;

[0134] A first determination module 64 is used to determine the operating state corresponding to the target device according to the state monitoring data, and to perform a fault assessment on the target device according to the operating state to determine an assessment result; and to input the image information into a defect recognition algorithm platform, and to determine an inspection result corresponding to the target device according to an output result of the defect recognition algorithm platform;

[0135] The second determination module 66 is used to determine the health status of the target device according to the evaluation result and the inspection result.

[0136] Through the above-mentioned device, the state monitoring data of the target device is obtained, and the drone is controlled to obtain the image information corresponding to the target device. On the one hand, the operating state corresponding to the target device is determined according to the state monitoring data, and the target device is subjected to a fault assessment according to the operating state to determine the assessment result; on the other hand, the image information is input into the missing recognition algorithm platform, and the inspection result corresponding to the target device is determined according to the output result of the missing recognition algorithm platform. The health state of the target device is determined according to the assessment result and the inspection result set. That is to say, the embodiment of the present application can realize the qualitative diagnosis of the internal fault of the target device by determining the operating state of the target device according to the state monitoring data, and then performing a fault assessment on the target device according to the operating state to determine the assessment result; and then by inputting the image information into the missing recognition algorithm platform, and determining the inspection result corresponding to the target device according to the output result of the missing recognition algorithm platform, the quantitative inspection of the appearance of the target device can be realized. Through the embodiment of the present application, the problem that in the process of evaluating the health state of the target device in the related art, only the qualitative diagnosis of the internal fault of the target device can be realized, but the quantitative inspection of the appearance of the target device cannot be realized. This can not only achieve qualitative diagnosis of internal faults of the target device, but also achieve quantitative inspection of the appearance of the target device.

[0137] In an exemplary embodiment, the state monitoring data of the target device acquired by the acquisition module 62 includes at least one of the following: first state monitoring data corresponding to the transmission chain of the target device; second state monitoring data corresponding to the blades of the target device; and third state monitoring data corresponding to the tower of the target device.

[0138] In an exemplary embodiment, the first determination module 64 is also used to standardize the status monitoring data and perform data fusion on the standardized status monitoring data to generate a status monitoring data set corresponding to the target device; determine characteristic parameters corresponding to the target device based on the data in the status monitoring data set; determine the operating state corresponding to the target device based on the characteristic parameters, wherein the characteristic parameters include at least one of the following: the degree of wear, fatigue condition, lightning protection performance and safe operating space of the target device.

[0139] In an exemplary embodiment, the first determination module 64 is further used to compare the characteristic parameter with a preset characteristic parameter threshold to determine a comparison result; when the comparison result indicates that the characteristic parameter is less than or equal to the characteristic parameter threshold, the operating state is determined to be a normal state; when the comparison result indicates that the characteristic parameter is greater than the characteristic parameter threshold, the operating state is determined to be an abnormal state.

[0140] In an exemplary embodiment, the first determination module 64 is further used to preprocess the state monitoring data; perform data alignment on the preprocessed state monitoring data to obtain the standardized state monitoring data, wherein the data alignment includes: performing time synchronization and space synchronization on the preprocessed state monitoring data.

[0141] In an exemplary embodiment, the first determination module 64 is also used to determine the target part of the target device corresponding to the image information, and input the image information into the defect recognition algorithm platform corresponding to the target part, so that the defect recognition algorithm platform outputs the target defect corresponding to the target device according to the image information; and quantitatively analyzes the target defect to determine the inspection result corresponding to the target device according to the first analysis result.

[0142] In an exemplary embodiment, the first determination module 64 is further used to determine the geometric parameters corresponding to the target defect and the position information corresponding to the target defect based on image processing technology; and to determine the defect type corresponding to the target defect, wherein the first analysis result includes: the geometric parameters corresponding to the target defect, the position information and the defect type; and to evaluate the defect degree corresponding to the target device based on the first analysis result to determine the inspection result, wherein the defect degree includes: mild defect, moderate defect and severe defect.

[0143] An embodiment of the present application further provides a storage medium, which includes a stored program, wherein the program executes any of the above methods when it is run.

[0144] Optionally, in this embodiment, the storage medium may be configured to store program codes for executing the following steps:

[0145] S1, obtain the status monitoring data of the target device and control the drone to obtain the image information corresponding to the target device;

[0146] S2, determining the operating state corresponding to the target device according to the state monitoring data, and performing a fault assessment on the target device according to the operating state to determine an assessment result; and inputting the image information into a defect recognition algorithm platform, and determining the inspection result corresponding to the target device according to an output result of the defect recognition algorithm platform;

[0147] S3: Determine the health status of the target device according to the evaluation result and the inspection result.

[0148] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0149] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0150] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0151] S1, obtain the status monitoring data of the target device and control the drone to obtain the image information corresponding to the target device;

[0152] S2, determining the operating state corresponding to the target device according to the state monitoring data, and performing a fault assessment on the target device according to the operating state to determine an assessment result; and inputting the image information into a defect recognition algorithm platform, and determining the inspection result corresponding to the target device according to an output result of the defect recognition algorithm platform;

[0153] S3: Determine the health status of the target device according to the evaluation result and the inspection result.

[0154] An embodiment of the present application further provides a computer program product, including a computer program, which is used by a processor to execute the steps in any of the above method embodiments.

[0155] Optionally, in this embodiment, the computer program product may be executed by a processor to perform the following steps:

[0156] S1, obtain the status monitoring data of the target device and control the drone to obtain the image information corresponding to the target device;

[0157] S2, determining the operating state corresponding to the target device according to the state monitoring data, and performing a fault assessment on the target device according to the operating state to determine an assessment result; and inputting the image information into a defect recognition algorithm platform, and determining the inspection result corresponding to the target device according to an output result of the defect recognition algorithm platform;

[0158] S3: Determine the health status of the target device according to the evaluation result and the inspection result.

[0159] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0160] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0161] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0162] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining a health status, characterized in that: include: Obtain status monitoring data of the target device and control the drone to obtain image information corresponding to the target device; Determine the operating state of the target device according to the state monitoring data, and perform a fault assessment on the target device according to the operating state to determine an assessment result; and input the image information into a defect recognition algorithm platform, and determine the inspection result of the target device according to the output result of the defect recognition algorithm platform; The health status of the target device is determined according to the evaluation result and the inspection result.

2. The method for determining health status according to claim 1, characterized in that: The state monitoring data of the target device includes at least one of the following: first state monitoring data corresponding to the transmission chain of the target device; second state monitoring data corresponding to the blade of the target device; The third state monitoring data corresponding to the tower of the target equipment.

3. The method for determining health status according to claim 1, characterized in that: Determining the operating state corresponding to the target device according to the state monitoring data includes: Standardizing the condition monitoring data, and fusing the standardized condition monitoring data to generate a condition monitoring data set corresponding to the target device; Determine characteristic parameters corresponding to the target device according to the data in the status monitoring data set; The operating state corresponding to the target device is determined according to the characteristic parameters, wherein the characteristic parameters include at least one of the following: the degree of wear, fatigue condition, lightning protection performance and safe operating space of the target device.

4. The method for determining health status according to claim 3, characterized in that: Determining the operating state corresponding to the target device according to the characteristic parameter includes: Comparing the characteristic parameter with a preset characteristic parameter threshold to determine a comparison result; if the comparison result indicates that the characteristic parameter is less than or equal to the characteristic parameter threshold, determining that the operating state is a normal state; When the comparison result indicates that the characteristic parameter is greater than the characteristic parameter threshold, it is determined that the operating state is an abnormal state.

5. The method for determining health status according to claim 3, characterized in that: The condition monitoring data is standardized, including: Preprocessing the condition monitoring data; The preprocessed state monitoring data is data aligned to obtain the standardized state monitoring data, wherein the data alignment includes: performing time synchronization and space synchronization on the preprocessed state monitoring data.

6. The method for determining health status according to claim 1, characterized in that: Inputting the image information into the missing recognition algorithm platform, and determining the inspection result corresponding to the target device according to the output result of the missing recognition algorithm, including: Determine the target part of the target device corresponding to the image information, and input the image information into a defect recognition algorithm platform corresponding to the target part, so that the defect recognition algorithm platform outputs the target defect corresponding to the target device according to the image information; The target defect is quantitatively analyzed to determine an inspection result corresponding to the target device according to the first analysis result.

7. The method for determining health status according to claim 6, characterized in that: Performing a quantitative analysis on the target defect to determine an inspection result corresponding to the target device according to the first analysis result includes: Determine the geometric parameters corresponding to the target defect and the position information corresponding to the target defect according to the image processing technology; and determine the defect type corresponding to the target defect, wherein the first analysis result includes: the geometric parameters corresponding to the target defect, the position information and the defect type; The defect degree corresponding to the target device is evaluated according to the first analysis result to determine the inspection result, wherein the defect degree includes: slight defect, medium defect and severe defect.

8. A device for determining health status, characterized in that: include: The acquisition module is used to obtain the status monitoring data of the target device and control the UAV to obtain the image information corresponding to the target device; A first determination module is used to determine the operating state corresponding to the target device according to the state monitoring data, and to perform a fault assessment on the target device according to the operating state to determine an assessment result; and to input the image information into a defect recognition algorithm platform, and to determine the inspection result corresponding to the target device according to an output result of the defect recognition algorithm platform; The second determination module is used to determine the health status of the target device according to the evaluation result and the inspection result.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 7 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.

Images