Environmental protection equipment operation and maintenance behavior analysis method and system based on image analysis

Abstract

The invention discloses an environmental protection equipment operation and maintenance behavior analysis method and system based on image analysis, and particularly relates to the technical field of equipment operation and maintenance behavior analysis. Illumination sensors and camera IMU sensors are arranged at different positions of a wind driven generator to obtain illumination intensity and camera vibration data, abnormal jitter features of illumination rate change and camera vibration are extracted through feature extraction, and the features are input into a machine learning model to obtain a machine learning model. Judging the interference degree of the image and classifying the image into a high-quality image or a low-quality image; for a low-quality image, an optimization method is adopted to improve the quality of the low-quality image, and detection precision evaluation is performed on an optimization effect to ensure that the image meets a preset precision requirement; the operation and maintenance behavior analysis of the environmental protection equipment is carried out through the optimized image, whether the equipment has an abnormal condition can be accurately identified, and scientific decision support is provided for subsequent repair and maintenance, so that the operation and maintenance efficiency and reliability of the wind driven generator are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment operation and maintenance behavior analysis, and in particular to an environmental protection equipment operation and maintenance behavior analysis method and system based on image analysis. Background Art

[0002] Environmental protection equipment operation and maintenance behavior analysis based on image analysis refers to the use of image recognition and analysis technology to monitor and evaluate the operation and maintenance (operation and maintenance) process of environmental protection equipment. By obtaining real-time images or video data of the equipment, the system can analyze the status of the equipment, abnormal conditions during operation, and even track the maintenance and repair records of the equipment. This method uses computer vision technology to automatically identify whether the equipment is operating normally and whether maintenance or repair is required, thereby improving operation and maintenance efficiency and reducing the risk of human oversight.

[0003] As an environmental protection device, wind turbines can convert wind energy into electrical energy and are a type of clean energy device. Unlike traditional fossil fuel power generation, wind power generation does not emit harmful gases or pollutants, so it has the environmental protection characteristics of reducing air pollution, reducing greenhouse gas emissions, and promoting sustainable development. In the prior art, image analysis technology is used to monitor the operation and maintenance of wind turbines. Through images taken by high-definition cameras or drones installed on the wind turbines, the system can detect wear, cracks or other damage on the blades of wind turbines in real time. Combined with machine learning algorithms, the image analysis system can automatically identify problems on the surface of the blades and provide early warnings, helping operation and maintenance personnel to perform maintenance in advance and avoiding the tediousness and inefficiency of manual inspections. This image analysis-based technology greatly improves the efficiency of operation and maintenance, reduces the incidence of equipment failures, ensures the stable operation of the equipment, and reduces maintenance costs.

[0004] The prior art has the following deficiencies: Wind turbines are usually located in open environments, where lighting and weather changes (such as strong winds, haze, rain and snow, etc.) may seriously affect the quality of images. Especially under strong sunlight or backlight conditions, the contrast and details of the image may not be clear, resulting in the inability to accurately identify minor damage such as cracks and wear. In addition, wind turbines are often located in remote areas, and severe weather conditions will affect the stability and shooting effect of drones or cameras, thereby affecting the accuracy of data collection. Summary of the invention

[0005] The purpose of the present invention is to provide an environmental protection equipment operation and maintenance behavior analysis method and system based on image analysis to solve the shortcomings of the background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a method for analyzing the operation and maintenance behavior of environmental protection equipment based on image analysis, comprising the following steps: S1: Obtaining light intensity data and camera vibration data in different time periods; S2: extracting features from the light intensity data and the camera vibration data, extracting the light rate change features in the light intensity data and the abnormal jitter features in the camera vibration data; S3: Input the extracted light rate change features and abnormal jitter features into the machine learning model for calculation, calculate the interference degree of each image, and divide the images into high-quality images and low-quality images according to the calculation results; S4: Optimize the low-quality image and evaluate the detection accuracy of the optimized image. After the evaluation result reaches the predetermined detection accuracy, continue to analyze the image; S5: Use the optimized images to analyze the operation and maintenance behavior of environmental protection equipment.

[0007] Preferably, in S2, the spectrum of the illumination rate is analyzed to generate an illumination rate fluctuation index, and the illumination rate fluctuation index is obtained by: Get the light intensity data sequence and its corresponding time tag, set the sequence of light intensity changing with time, perform fast Fourier transform on the light rate change data to get the complex output in the frequency domain, calculate the amplitude of each frequency component, and the fluctuation of light rate is represented by the energy distribution in the spectrum, that is, the square of the amplitude of the frequency component. Calculate the ratio of the sum of the energy of the high-frequency components to the sum of the energy of the low-frequency components, that is, calculate the light rate fluctuation index.

[0008] Preferably, in S2, after analyzing and identifying the periodicity of the camera vibration, a camera jitter frequency abnormality index is generated, and the method for obtaining the camera jitter frequency abnormality index is: The vibration signal of the camera is obtained, and the discrete wavelet transform is used to perform multi-scale analysis on the vibration signal to obtain wavelet coefficients at multiple scales and displacements. The coefficients at each scale represent the signal characteristics in different frequency ranges. The coefficients at each scale are analyzed and the energy of the coefficients at different scales is calculated. According to the extracted energy value, the frequency at which the wavelet coefficient energy exceeds the set threshold is regarded as the abnormal frequency, and the weighted average summation of the abnormal frequency components at all scales is calculated to generate the camera jitter frequency abnormality index.

[0009] Preferably, in S3, the extracted light rate change characteristics and abnormal jitter characteristics are input into a machine learning model for calculation, and the machine learning model calculates the interference degree of each image according to the input characteristics, and divides the image quality into high-quality images and low-quality images. Specifically, the light rate fluctuation index and the camera jitter frequency abnormality index are converted into a comprehensive feature vector, and the comprehensive feature vector is used as the input of the machine learning model, and the machine learning model is trained, and the interference degree value of each image is determined according to the model output results.

[0010] Preferably, the interference level value of each acquired image is compared with an interference level reference threshold value pre-set based on historical data; if the interference level value of the image is greater than or equal to the interference level reference threshold value, it indicates that the interference level of the image is high, and the image quality is classified as a low-quality image; if the interference level value of the image is less than the interference level reference threshold value, it indicates that the interference level of the image is low, and the image quality is classified as a high-quality image.

[0011] Preferably, in S4, the low-quality image is optimized and the detection accuracy of the optimized image is evaluated, specifically: for the low-quality image, that is, the interference degree value generated within a fixed time period is greater than or equal to the interference degree reference threshold, the interference degree values ​​greater than or equal to the interference degree reference threshold generated by the optimized low-quality image in a subsequent fixed time period are collected, and a data set is established, the mean and standard deviation of the data set are calculated, and after analyzing the data set, the detection accuracy of the optimized image is evaluated according to the analysis results.

[0012] Preferably, if the mean value of the interference degree values ​​in the data set is greater than or equal to the reference threshold value of the mean value of the interference degree values, and the standard deviation of the interference degree values ​​is less than the reference threshold value of the standard deviation of the interference degree values, it indicates that the optimized image is stable and of good quality, and the detection accuracy is high; If the mean value of the interference level is greater than or equal to the reference threshold of the mean value of the interference level, and the standard deviation of the interference level is greater than or equal to the reference threshold of the standard deviation of the interference level, it indicates that the image quality is unstable and needs further optimization; If the mean value of the interference level is less than the reference threshold value of the mean value of the interference level, and the standard deviation of the interference level is greater than or equal to the reference threshold value of the standard deviation of the interference level, it means that the image quality is poor and has large fluctuations, and more stringent optimization is required; If the mean of the interference degree values ​​is less than the reference threshold of the mean of the interference degree values, and the standard deviation of the interference degree values ​​is less than the reference threshold of the standard deviation of the interference degree values, the image quality is poor and the stability is good, but further improvement is still needed to improve the detection accuracy.

[0013] The present invention also provides an environmental protection equipment operation and maintenance behavior analysis system based on image analysis, including a data acquisition module, a feature extraction module, a machine learning calculation module, an image optimization module and an operation and maintenance analysis module; Data acquisition module: Through the light sensors deployed at different positions of the wind turbine and the IMU sensor of the camera, the light intensity data and camera vibration data in different time periods are obtained respectively; Feature extraction module: extracts features from the acquired light intensity data and camera vibration data, and respectively extracts the light rate change features in the light intensity data and the abnormal jitter features in the camera vibration data; Machine learning calculation module: inputs the extracted light rate change features and abnormal jitter features into the machine learning model for calculation. The machine learning model calculates the interference degree of each image according to the input features and divides the image quality into high-quality images and low-quality images; Image optimization module: optimizes low-quality images and evaluates the detection accuracy of the optimized images. After the evaluation results reach the predetermined detection accuracy, continue image analysis; Operation and maintenance analysis module: Use optimized images to analyze the operation and maintenance behavior of environmental protection equipment, analyze whether there are any abnormal conditions in the equipment, and provide decision support for subsequent repairs and maintenance.

[0014] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. The present invention deploys light sensors and camera IMU sensors on wind turbines, combines light intensity data and camera vibration data, and performs image quality assessment and optimization processing. By analyzing the light rate fluctuation and camera vibration characteristics, the light rate fluctuation index and camera jitter frequency abnormality index are generated, and input into the machine learning model to automatically classify and optimize the image quality. This method can effectively identify and optimize low-quality images, thereby improving the detection accuracy of the image and providing more accurate analysis results for subsequent environmental protection equipment operation and maintenance.

[0015] 2. The present invention can solve the problem of image quality interference under harsh environmental conditions, especially under extreme conditions of light and weather changes, and can achieve optimization and quality assessment of low-quality images by accurately quantifying the degree of image interference. Through this method, the operating status of wind turbines can be efficiently identified, potential abnormalities can be discovered in a timely manner, and accurate decision support can be provided for equipment maintenance and repair, which not only improves operation and maintenance efficiency, but also effectively reduces the risk of equipment failure and extends the service life of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0017] Figure 1 The figure is a flow chart of the method of the present invention.

[0018] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Example 1, please refer to Figure 1 As shown, the environmental protection equipment operation and maintenance behavior analysis method based on image analysis described in this embodiment includes the following steps: S1: Obtaining light intensity data and camera vibration data in different time periods; S2: extracting features from the light intensity data and the camera vibration data, extracting the light rate change features in the light intensity data and the abnormal jitter features in the camera vibration data; S3: Input the extracted light rate change features and abnormal jitter features into the machine learning model for calculation, calculate the interference degree of each image, and divide the images into high-quality images and low-quality images according to the calculation results; S4: Optimize the low-quality image and evaluate the detection accuracy of the optimized image. After the evaluation result reaches the predetermined detection accuracy, continue to analyze the image; S5: Use the optimized images to analyze the operation and maintenance behavior of environmental protection equipment.

[0021] Light sensors generally use sensors such as light-dependent resistors (LDRs) or photodiodes, which can measure ambient light intensity with high accuracy. Light sensors should be installed at multiple key locations of wind turbines (such as in front of the blades, on the top of the blades, on the top of the tower, etc.). This ensures that data on changes in light intensity are obtained at different time periods (morning, evening, cloudy days, etc.), and the impact of light conditions on the image is comprehensively evaluated through data from multiple locations.

[0022] Light sensors collect light intensity values ​​at different locations in real time, usually recording data every second, every minute, or at time intervals based on actual needs. The data is expressed as changes in light intensity per unit time, which can be expressed in numerical values ​​(such as lux units) and stored locally or in a cloud server. By acquiring light data at multiple different locations, it is possible to identify changes in light around wind turbines, such as changes in the position of the sun, cloud cover, changes in weather, etc., and provide accurate light data for subsequent image quality assessment.

[0023] IMU (Inertial Measurement Unit) sensors are generally composed of accelerometers, gyroscopes, and magnetometers, and are used to monitor the motion status of the device in real time (such as vibration, tilt, rotation, etc.). IMU sensors are usually integrated into cameras or drone systems. It can be installed in different parts of the wind turbine, especially on the camera or drone platform to monitor the movement caused by wind speed changes or equipment vibration. In order to better capture the dynamic situation of the camera, you can consider installing IMU sensors in the front and back, left and right sides of the camera system.

[0024] The IMU sensor collects the vibration data of the camera in real time, and records the camera's acceleration, angle change, vibration frequency and other information. Based on this data, it can be known whether the camera vibrates or shakes when the wind speed is high, thereby affecting the clarity of the image. Vibration data is generally expressed in the form of acceleration (m / s²), angular velocity (° / s), etc., and the amplitude, frequency and direction of the vibration can be calculated. Especially in strong wind weather or during equipment operation, the sensor can provide real-time feedback on the equipment status.

[0025] When acquiring data, it is necessary to divide it according to time periods. Usually, the following time periods can be selected: daytime (strong light conditions), evening (low light conditions), nighttime (no light or extremely low light conditions), and different meteorological conditions (such as foggy weather, cloudy days, snowy weather, etc.).

[0026] The light intensity data and vibration data corresponding to each time period can be collected through light sensors and IMU sensors. These data can reflect the impact of light and wind speed changes on the device status under different environmental conditions.

[0027] Based on the light intensity data collected by the light sensor at different time periods, it is possible to determine the lighting conditions of the environment in which the wind turbine is located. For example, in strong light or backlight conditions, the image quality may be poor and it may be difficult to identify details.

[0028] The data from the IMU sensor can be used to analyze the impact of increased wind speed or equipment vibration. If the wind speed is high, the camera may vibrate violently, which will affect the image clarity and cause blur or distortion.

[0029] All collected light intensity data and camera vibration data can be transmitted to the cloud or local data center via wireless transmission technology (such as Wi-Fi, LoRa, 5G, etc.). These data can be stored in real time and synchronized with image data for subsequent image analysis systems to conduct environmental impact assessments.

[0030] S2: performing feature extraction on the acquired light intensity data and camera vibration data, respectively extracting light rate variation features in the light intensity data and abnormal jitter features in the camera vibration data.

[0031] The light rate change refers to the rate of change of light intensity per unit time. Calculating the rate of change of light intensity in the time dimension can reflect the dynamic changes of the lighting environment. By analyzing the light rate change in continuous time periods, it is possible to identify the trend of light intensity changes and whether there are rapid changes or stable changes. For example, rapid light changes may be related to sudden weather changes (such as cloud cover, sunlight penetration, etc.) or the influence of objects around the device (such as flocks of birds, flying objects).

[0032] For the time series data of the light rate change, some statistical features can be calculated: Mean: reflects the overall light change speed. Variance: reflects the degree of fluctuation of light change. A large variance means unstable light change. Maximum and minimum values: can identify the moments of extreme changes (for example, drastic fluctuations in light).

[0033] By analyzing the time domain of the change in the illumination rate, we can find the moment of sudden change and the stable time period. A sudden change may mean that the illumination environment has a great impact on the image quality. The spectrum of the illumination rate is analyzed by frequency domain analysis methods such as Fourier transform. High-frequency components may represent frequent fluctuations in illumination changes, while low-frequency components represent a relatively stable illumination environment.

[0034] After analyzing the spectrum of the illumination rate, the illumination rate fluctuation index is generated. The method for obtaining the illumination rate fluctuation index is as follows: Get the light intensity data sequence and its corresponding time tag, set the sequence of light intensity changing with time L(t), and calculate its rate change LICR(t), that is: ; where Δt is the time interval, usually seconds or minutes, depending on the frequency of data acquisition.

[0035] Perform fast Fourier transform on the light rate change data LICR(t) to convert the time domain signal into a frequency domain signal to reveal its frequency component. For a signal x(t) with a length of N, the Fourier transform result X(f) is expressed as: ;in, is the kernel function of Fourier transform, x(n) is the value of the signal at the nth sampling point, N is the total number of samplings of the signal, and through FFT, the complex output in the frequency domain is obtained , where each Corresponding to the amplitude and phase of a frequency component, calculate the amplitude of each frequency component: ;in, are the real and imaginary parts of the complex output, respectively.

[0036] Fluctuations in the rate of illumination are distributed through the energy in the spectrum It is expressed as the square of the amplitude of the frequency component: ; This energy spectrum reflects the intensity of each frequency component. Higher energy means that the frequency component accounts for a larger proportion in the change of light rate.

[0037] Calculate the light rate fluctuation index, the expression is: ; In the formula, represents the total energy of high-frequency components, represents the sum of the energy of the low-frequency components, is the frequency threshold, used to separate the low-frequency part from the high-frequency part, and QAS is the light rate fluctuation index.

[0038] The vibration amplitude indicates the maximum acceleration of the camera in a certain period of time. It can be measured by the accelerometer of the IMU sensor. The vibration frequency reflects the periodicity of the camera vibration. The frequency spectrum can be obtained by performing a fast Fourier transform (FFT) on the acceleration signal to extract the frequency components. Frequency analysis can help identify whether there is high-frequency jitter (such as fast vibration caused by wind speed) or low-frequency vibration (such as slow vibration caused by equipment failure).

[0039] By analyzing the changes in vibration amplitude and frequency, you can determine whether there is abnormal jitter. For example, when the wind speed is too high, the camera may be severely affected by the wind, resulting in large jitters, which need to be treated as abnormal conditions. By calculating the standard deviation, mean, and maximum value of the vibration amplitude and frequency, you can determine whether there is abnormal fluctuation. For example, if the vibration amplitude suddenly increases and the frequency changes significantly, this is usually abnormal jitter caused by extreme weather conditions or equipment instability. Identify the periodicity of camera vibration through frequency analysis. If the vibration frequency fluctuates within a specific range and exceeds the normal threshold, it indicates that there may be abnormal jitter.

[0040] After analyzing and identifying the periodicity of camera vibration, the camera jitter frequency abnormality index is generated. The method for obtaining the camera jitter frequency abnormality index is as follows: The vibration signal V(t) of the camera is obtained. This is usually time domain data captured by an acceleration sensor or an IMU sensor installed on the camera. The signal V(t) represents vibration data in the time domain.

[0041] Use discrete wavelet transform (DWT) to perform multi-scale analysis on vibration signals and decompose time domain signals into different frequency bands. Wavelet transform can extract high-frequency and low-frequency components in the signal and help identify the characteristics of periodic jitter. The expression is: ;in, is the wavelet basis function, j and k represent the scale and displacement parameters respectively.

[0042] Choose a suitable wavelet basis function. Common wavelet basis functions include Haar wavelet, Daubechies wavelet, Symlet wavelet, etc. The criteria for selecting wavelet basis functions usually depend on the characteristics of the signal. Haar wavelet: For simple changes, Haar wavelet may be a good choice. Daubechies wavelet: For complex signals and periodic features, Daubechies wavelet can provide better decomposition effects.

[0043] After wavelet transformation, wavelet coefficients W(j,k) at multiple scales and displacements are obtained. The coefficients at each scale represent the signal characteristics in different frequency ranges. By analyzing these coefficients, possible periodic and sudden jitter characteristics can be identified. The coefficients at each scale are analyzed and the energy of coefficients at different scales is calculated: ;in, is the wavelet coefficient energy at scale j, and M is the number of sample points at that scale.

[0044] According to the extracted energy value, it is judged whether there is abnormal frequency in the vibration signal. If the frequency component exceeds the set threshold (usually obtained based on statistical analysis of historical data), it is considered that the frequency component is abnormal. The camera jitter frequency abnormality index is generated by taking the weighted average sum of the abnormal frequency components at all scales.

[0045] S3, converts the illumination rate fluctuation index and the camera jitter frequency anomaly index into a comprehensive feature vector, and uses the comprehensive feature vector as the input of the machine learning model. The machine learning model predicts the interference degree value label of each image with each group of comprehensive feature vectors as the prediction target, and takes minimizing the sum of the prediction errors of the interference degree value labels of all images as the training target. The machine learning model is trained until the sum of the prediction errors converges, and the model training is stopped. The interference degree value of each image is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0046] The method for obtaining the interference degree value of each image is as follows: from the comprehensive feature vector training data of the trained machine learning model, the corresponding function expression is obtained: ; In the formula, is the output function of the model, QAS is the light rate fluctuation index, GH is the camera jitter frequency anomaly index, is the interference degree value of each image.

[0047] The interference degree value of each image obtained is compared with the interference degree reference threshold pre-set according to historical data. If the interference degree value of the image is greater than or equal to the interference degree reference threshold, it means that the interference degree of the image is high, and the image quality is classified as a low-quality image; if the interference degree value of the image is less than the interference degree reference threshold, it means that the interference degree of the image is low, and the image quality is classified as a high-quality image.

[0048] S4, for the optimization of low-quality images, first of all, image enhancement technology can be used to improve image quality, especially in the case of insufficient lighting or jitter. Common methods include histogram equalization, local contrast enhancement, denoising, etc., especially when processing low-contrast images caused by harsh environments (such as strong light, haze, rain and snow, etc.), by increasing the contrast and brightness of the image, the details can be made clearer, thereby improving the accuracy of subsequent image analysis. In addition, denoising techniques, such as Gaussian filtering or median filtering, can effectively remove image noise caused by environmental interference and reduce the impact on the image analysis model.

[0049] Secondly, image stabilization technology can be used to optimize the blurring caused by vibration and shaking in the image. For example, using image alignment methods or optical flow methods based on feature point matching, the image clarity can be restored by correcting the translation and rotation of the image. These image optimization steps help improve image quality, allowing the image analysis system to more accurately identify cracks, wear or other damage in the image, ensuring that subsequent machine learning models can make more accurate judgments.

[0050] For low-quality images, that is, the interference level value generated within a fixed time period is greater than or equal to the interference level reference threshold, the interference level values ​​generated by the optimized low-quality images within a subsequent fixed time period that are greater than or equal to the interference level reference threshold are collected, and a data set is established. The mean and standard deviation of the data set are calculated. After analyzing the data set, the detection accuracy of the optimized image is evaluated based on the analysis results.

[0051] If the mean value of the interference degree values ​​in the data set is greater than or equal to the reference threshold of the mean value of the interference degree values, and the standard deviation of the interference degree values ​​is less than the reference threshold of the standard deviation of the interference degree values, it indicates that the optimized image is stable and of good quality, and the detection accuracy is high; If the mean value of the interference level is greater than or equal to the reference threshold of the mean value of the interference level, and the standard deviation of the interference level is greater than or equal to the reference threshold of the standard deviation of the interference level, it indicates that the image quality is unstable and needs further optimization; If the mean value of the interference level is less than the reference threshold value of the mean value of the interference level, and the standard deviation of the interference level is greater than or equal to the reference threshold value of the standard deviation of the interference level, it means that the image quality is poor and has large fluctuations, and more stringent optimization is required; If the mean of the interference degree values ​​is less than the reference threshold of the mean of the interference degree values, and the standard deviation of the interference degree values ​​is less than the reference threshold of the standard deviation of the interference degree values, the image quality is poor and the stability is good, but further improvement is still needed to improve the detection accuracy.

[0052] When the optimized image passes the evaluation and the evaluation result reaches the predetermined detection accuracy (for example, the error rate is less than a certain threshold, and the recall rate and precision rate meet the requirements), the subsequent image analysis process can continue. This includes further processing of the optimized image, such as target detection, defect identification, etc., to provide more accurate data support for subsequent operation and maintenance behavior analysis.

[0053] S5, the optimized images can provide important support for the analysis of the operation and maintenance behavior of environmental protection equipment. Through high-precision image analysis, the system can detect potential abnormalities of the equipment in real time, such as cracks, wear, corrosion and other problems on the surface of the equipment. These problems are often precursors to equipment failure. Through accurate analysis of the images, the system can provide early warning before the equipment fails, helping operation and maintenance personnel to identify and solve problems in advance, thereby reducing downtime and maintenance costs.

[0054] During the analysis process, the image processing system combined with machine learning algorithms can identify abnormal behaviors of the equipment at various stages according to the equipment's operating status and environmental conditions. For example, by monitoring the surface condition of wind turbine blades, it can be analyzed whether there is abnormal vibration caused by wind speed changes or external damage, and then it can be inferred whether the blades need to be repaired or replaced. Using historical data and the results of image analysis, the system can track the health status of the equipment in real time, form an equipment health file, and provide an accurate basis for decision support.

[0055] For subsequent repairs and maintenance, the system's analysis results can not only provide detailed reports on equipment problems, but also provide decision support for maintenance personnel. According to the degree of damage, failure frequency and maintenance history of the equipment, the system can automatically generate a maintenance plan and propose the most appropriate maintenance cycle or replacement suggestions. Through data-driven analysis, operation and maintenance personnel can formulate more accurate maintenance strategies, avoid unnecessary maintenance work, optimize resource utilization, and extend the service life of equipment.

[0056] In this embodiment, by deploying light sensors and IMU sensors of cameras at different positions of wind turbines, light intensity data and camera vibration data are obtained respectively. On this basis, the characteristics of light rate change and abnormal jitter characteristics of camera vibration are extracted, and these characteristics are input into the machine learning model to calculate the interference degree of each image, and divide the images into high quality and low quality. After optimizing the low-quality images, the detection accuracy is evaluated to ensure that the images reach the predetermined accuracy before further analysis. Finally, the optimized images are used to analyze the operation and maintenance behavior of environmental protection equipment, detect whether there are abnormalities in the equipment, provide decision support, help formulate effective repair and maintenance plans, and ensure the efficient operation of the equipment.

[0057] Example 2, please refer to Figure 2 As shown, the environmental protection equipment operation and maintenance behavior analysis system based on image analysis described in this embodiment includes a data acquisition module, a feature extraction module, a machine learning calculation module, an image optimization module and an operation and maintenance analysis module; Data acquisition module: Through the light sensors deployed at different positions of the wind turbine and the IMU sensor of the camera, the light intensity data and camera vibration data in different time periods are obtained respectively; Feature extraction module: extracts features from the acquired light intensity data and camera vibration data, and respectively extracts the light rate change features in the light intensity data and the abnormal jitter features in the camera vibration data; Machine learning calculation module: inputs the extracted light rate change features and abnormal jitter features into the machine learning model for calculation. The machine learning model calculates the interference degree of each image according to the input features and divides the image quality into high-quality images and low-quality images; Image optimization module: optimizes low-quality images and evaluates the detection accuracy of the optimized images. After the evaluation results reach the predetermined detection accuracy, continue image analysis; Operation and maintenance analysis module: Use optimized images to analyze the operation and maintenance behavior of environmental protection equipment, analyze whether there are any abnormal conditions in the equipment, and provide decision support for subsequent repairs and maintenance.

[0058] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0059] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0060] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0061] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for analyzing operation and maintenance behavior of environmental protection equipment based on image analysis, characterized in that: The following steps are involved: S1: Obtaining light intensity data and camera vibration data in different time periods; S2: extracting features from the light intensity data and the camera vibration data, extracting the light rate change features in the light intensity data and the abnormal jitter features in the camera vibration data; S3: Input the extracted light rate change features and abnormal jitter features into the machine learning model for calculation, calculate the interference degree of each image, and divide the images into high-quality images and low-quality images according to the calculation results; S4: Optimize the low-quality image and evaluate the detection accuracy of the optimized image. After the evaluation result reaches the predetermined detection accuracy, continue to analyze the image; S5: Use the optimized images to analyze the operation and maintenance behavior of environmental protection equipment.

2. According to claim 1, a method for analyzing operation and maintenance behavior of environmental protection equipment based on image analysis is characterized in that: In S2, the spectrum of the illumination rate is analyzed to generate an illumination rate fluctuation index, and the illumination rate fluctuation index is obtained as follows: Get the light intensity data sequence and its corresponding time tag, set the sequence of light intensity changing with time, perform fast Fourier transform on the light rate change data to get the complex output in the frequency domain, calculate the amplitude of each frequency component, and the fluctuation of light rate is represented by the energy distribution in the spectrum, that is, the square of the amplitude of the frequency component. Calculate the ratio of the sum of the energy of the high-frequency components to the sum of the energy of the low-frequency components, that is, calculate the light rate fluctuation index.

3. The method for analyzing operation and maintenance behavior of environmental protection equipment based on image analysis according to claim 2 is characterized in that: In S2, the camera vibration periodicity is analyzed and identified to generate a camera jitter frequency anomaly index. The camera jitter frequency anomaly index is obtained as follows: The vibration signal of the camera is obtained, and the discrete wavelet transform is used to perform multi-scale analysis on the vibration signal to obtain wavelet coefficients at multiple scales and displacements. The coefficients at each scale represent the signal characteristics in different frequency ranges. The coefficients at each scale are analyzed and the energy of the coefficients at different scales is calculated. According to the extracted energy value, the frequency at which the wavelet coefficient energy exceeds the set threshold is regarded as the abnormal frequency, and the weighted average summation of the abnormal frequency components at all scales is calculated to generate the camera jitter frequency abnormality index.

4. The method for analyzing operation and maintenance behavior of environmental protection equipment based on image analysis according to claim 3 is characterized by: In S3, the extracted light rate change features and abnormal jitter features are input into the machine learning model for calculation. The machine learning model calculates the interference degree of each image according to the input features, and divides the image quality into high-quality images and low-quality images. Specifically, the light rate fluctuation index and the camera jitter frequency abnormality index are converted into a comprehensive feature vector, the comprehensive feature vector is used as the input of the machine learning model, the machine learning model is trained, and the interference degree value of each image is determined according to the model output results.

5. The method for analyzing operation and maintenance behavior of environmental protection equipment based on image analysis according to claim 4 is characterized in that: The interference degree value of each image obtained is compared with the interference degree reference threshold pre-set according to historical data. If the interference degree value of the image is greater than or equal to the interference degree reference threshold, it means that the interference degree of the image is high, and the image quality is classified as a low-quality image; if the interference degree value of the image is less than the interference degree reference threshold, it means that the interference degree of the image is low, and the image quality is classified as a high-quality image.

6. The method for analyzing operation and maintenance behavior of environmental protection equipment based on image analysis according to claim 5 is characterized in that: In S4, the low-quality image is optimized and the detection accuracy of the optimized image is evaluated. Specifically, for the low-quality image, that is, the interference level value generated within a fixed time period is greater than or equal to the interference level reference threshold, the interference level values ​​greater than or equal to the interference level reference threshold generated by the optimized low-quality image within a subsequent fixed time period are collected, and a data set is established, the mean and standard deviation of the data set are calculated, and after analyzing the data set, the detection accuracy of the optimized image is evaluated according to the analysis results.

7. The method for analyzing operation and maintenance behavior of environmental protection equipment based on image analysis according to claim 6 is characterized by: If the mean value of the interference degree values ​​in the data set is greater than or equal to the reference threshold value of the mean value of the interference degree values, and the standard deviation of the interference degree values ​​is less than the reference threshold value of the standard deviation of the interference degree values, it indicates that the optimized image is stable and of good quality, and the detection accuracy is high; If the mean value of the interference level is greater than or equal to the reference threshold of the mean value of the interference level, and the standard deviation of the interference level is greater than or equal to the reference threshold of the standard deviation of the interference level, it indicates that the image quality is unstable and needs further optimization; If the mean value of the interference level is less than the reference threshold value of the mean value of the interference level, and the standard deviation of the interference level is greater than or equal to the reference threshold value of the standard deviation of the interference level, it means that the image quality is poor and has large fluctuations, and more stringent optimization is required; If the mean of the interference degree values ​​is less than the reference threshold of the mean of the interference degree values, and the standard deviation of the interference degree values ​​is less than the reference threshold of the standard deviation of the interference degree values, the image quality is poor and the stability is good, but further improvement is still needed to improve the detection accuracy.

8. An environmental protection equipment operation and maintenance behavior analysis system based on image analysis, used to implement an environmental protection equipment operation and maintenance behavior analysis method based on image analysis according to any one of claims 1 to 7, characterized in that: It includes data acquisition module, feature extraction module, machine learning calculation module, image optimization module and operation and maintenance analysis module; Data acquisition module: Through the light sensors deployed at different positions of the wind turbine and the IMU sensor of the camera, the light intensity data and camera vibration data in different time periods are obtained respectively; Feature extraction module: extracts features from the acquired light intensity data and camera vibration data, and respectively extracts the light rate change features in the light intensity data and the abnormal jitter features in the camera vibration data; Machine learning calculation module: inputs the extracted light rate change features and abnormal jitter features into the machine learning model for calculation. The machine learning model calculates the interference degree of each image according to the input features and divides the image quality into high-quality images and low-quality images; Image optimization module: optimizes low-quality images and evaluates the detection accuracy of the optimized images. After the evaluation results reach the predetermined detection accuracy, continue image analysis; Operation and maintenance analysis module: Use optimized images to analyze the operation and maintenance behavior of environmental protection equipment, analyze whether there are any abnormal conditions in the equipment, and provide decision support for subsequent repairs and maintenance.

Images