Wind turbine generator cabin temperature field measuring device and method based on data fusion

Abstract

The invention discloses a wind turbine generator cabin temperature field measuring device and method based on data fusion, and belongs to the technical field of temperature measurement. The invention discloses a wind turbine generator cabin temperature field measuring device based on data fusion, and the device comprises a data collection module which is used for sensing and measuring the temperature in a wind turbine generator cabin; the data preprocessing module is used for carrying out processing and signal conversion on the thermal imaging data and the three-dimensional space data; and the data fusion module is used for correcting and fusing the preprocessed thermal imaging data and thermal resistance temperature data. According to the invention, the problem of inaccurate cabin temperature measurement in the prior art is solved. According to the method, data acquired by the thermal resistance sensor, the infrared camera and the binocular camera are fused twice, so that imaging errors can be reduced, conversion from two dimensions to three dimensions can be realized, and a more reliable basis is provided for internal temperature monitoring and heat dissipation structure optimization of a cabin of a wind turbine generator.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature measurement, and in particular to a device and method for measuring the temperature field of a wind turbine cabin based on data fusion. Background Art

[0002] With the rapid development of the wind energy industry, wind turbines, as important clean energy power generation equipment, have been widely used around the world. However, since the design of the wind turbine cabin is mostly a closed structure, although the key heat-generating components are equipped with a cooling system, under extreme conditions, such as high temperatures in summer, the heat inside the cabin is difficult to dissipate effectively, resulting in a temperature rise of up to 50 degrees Celsius. This not only affects the normal operation of the unit, but also causes safety hazards. Therefore, it is particularly important to accurately monitor the temperature field inside the cabin.

[0003] Traditional temperature measurement methods, such as thermal resistor temperature measurement and infrared thermal imaging temperature measurement, have met the needs to a certain extent, but they still have their own limitations. Although thermal resistor temperature measurement can directly measure the temperature, it is necessary to reconstruct the temperature field of the entire space through software interpolation fitting. This method is prone to errors in environments with large temperature changes such as wind turbine cabins. Although infrared thermal imaging can provide continuous temperature distribution, it is difficult to accurately determine the temperature conditions of different objects in the image due to the lack of geometric information of the object. Summary of the invention

[0004] The purpose of the present invention is to provide a device and method for measuring the temperature field in a wind turbine cabin based on data fusion. By fusing the data collected by the thermistor sensor, the infrared camera and the binocular camera twice, not only the imaging error can be reduced, but also the conversion from two-dimensional to three-dimensional can be realized, thereby providing a more reliable basis for the internal temperature monitoring and heat dissipation structure optimization of the wind turbine cabin, and solving the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A wind turbine nacelle temperature field measuring device based on data fusion, comprising:

[0007] The data acquisition module is used to sense and measure the temperature inside the wind turbine cabin. The data acquisition module includes an infrared camera, a thermal resistor sensor and a binocular camera, which respectively collect thermal imaging data, thermal resistor temperature data and three-dimensional space data;

[0008] A data preprocessing module, used to process the thermal imaging data and three-dimensional spatial data, and perform signal conversion on the temperature data collected by the thermal resistance sensor;

[0009] The data fusion module is used to correct and fuse the pre-processed thermal imaging data and the thermal resistance temperature data, and to fuse the corrected two-dimensional temperature data with the three-dimensional spatial information obtained based on the binocular camera, to construct a three-dimensional temperature field model inside the cabin, and to form a complete three-dimensional distributed temperature field through interpolation calculation.

[0010] Preferably, the data fusion module includes:

[0011] The temperature correction fusion unit is used to fuse the pre-processed thermal imaging data with the thermal resistance temperature data and correct the temperature results in the thermal imaging data;

[0012] A three-dimensional space construction unit, used to perform extreme correction and stereo matching on the left and right images acquired by the binocular camera, and construct a three-dimensional space model of the interior of the cabin after obtaining a disparity map and a depth map;

[0013] A temperature mapping fusion unit, used to fuse the corrected thermal imaging data with the three-dimensional space model, construct a correspondence between points on the three-dimensional model and pixel points in the temperature image, and map the temperature information to the three-dimensional model;

[0014] The interpolation processing unit is used to perform interpolation processing on the constructed three-dimensional temperature model to form a complete and smooth three-dimensional distribution model of the temperature field inside the cabin.

[0015] Preferably, the working process of the temperature correction fusion unit includes the following steps:

[0016] S11, fusing the pre-processed thermal image with the temperature data collected by the thermal resistance sensor, in this process using image processing technology to identify the positions of the thermal resistance measuring points in the thermal image and obtain the actual temperature values ​​of these measuring points;

[0017] S12. Based on the difference between the temperature value of the measuring point in the thermal image and the temperature value recorded by the thermal resistance sensor, a temperature compensation calibration is performed on the backlight surface of the device in the thermal image, that is, the part away from the heat source.

[0018] Preferably, the working process of the three-dimensional space construction unit includes the following steps:

[0019] S21, adjusting the images of the binocular camera so that corresponding points in the two images are located on the same straight line;

[0020] S22, by comparing the similarity of corresponding feature points in the left and right images of the binocular camera, find the corresponding points in each pair of images, so as to determine the relative positions of these points in space;

[0021] S23, based on the result of stereo matching, calculating the disparity value of each pixel, and then converting it into depth information to obtain a disparity map and a depth map;

[0022] S24, using the depth information and camera calibration parameters, mapping each pixel into a three-dimensional space to form a three-dimensional point cloud or mesh model, and performing post-processing and optimization.

[0023] Preferably, the data acquisition module also includes an environmental parameter sensor for collecting environmental parameter data, wherein the environmental parameters include but are not limited to humidity, air pressure, and wind speed.

[0024] Preferably, the temperature correction and fusion unit further includes an environmental parameter compensation subunit for performing compensation processing on the thermal imaging data according to the environmental parameter data.

[0025] Preferably, the temperature mapping fusion unit further includes an anomaly detection subunit for identifying abnormally high temperature areas in the three-dimensional temperature model and generating an alarm signal.

[0026] Preferably, the interpolation processing unit adopts one of a linear interpolation algorithm and a high-order interpolation algorithm.

[0027] A measurement method of a wind turbine cabin temperature field measurement device based on data fusion is implemented based on a wind turbine cabin temperature field measurement device based on data fusion, and includes the following steps:

[0028] Step 1: After the measuring equipment is installed, the thermal resistance sensor, infrared camera and binocular camera respectively collect and obtain three state data of the measuring object;

[0029] Step 2: Data fusion of the thermal image after denoising, enhancement and other preprocessing and the temperature of the thermal resistor after signal conversion, use image processing technology to identify the position of the thermal resistor measuring point in the thermal image and obtain the temperature value of the point, and perform temperature compensation calibration on the backlight surface of the device based on the difference between the thermal image temperature of the measuring point and the temperature of the sensor;

[0030] Step 3: Obtain the disparity map and depth map of the binocular camera through epipolar correction and stereo matching, perform three-dimensional space modeling on the disparity map and depth map, and perform post-processing and optimization;

[0031] Step 4: Map the 3D model to the temperature image based on the calibrated 2D thermal image and the spatial position information of the binocular camera, construct the correspondence between the points on the 3D model and the pixels of the thermal image, and return the temperature information to the 3D model;

[0032] Step 5: Interpolate the three-dimensional temperature model to construct a three-dimensional distribution model of the temperature field.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 1. The present invention effectively improves the accuracy of temperature measurement by fusing the data collected by thermistor sensors, infrared cameras and binocular cameras twice, overcomes the limitations of single sensor measurement, and the first fusion is for thermal images and thermal resistor temperature data, corrects the temperature results in the thermal images, and significantly reduces the imaging errors caused by differences in surface reflectivity of objects. The second fusion is to obtain the disparity map and depth map through extreme correction and stereo matching, and then map the temperature information in the two-dimensional thermal image to the three-dimensional space model, realizing the conversion from two-dimensional to three-dimensional, and improving the visualization and understanding of the temperature field.

[0035] 2. The three-dimensional temperature model constructed by the present invention through interpolation processing has a high degree of restoration and can better reflect the actual temperature distribution inside the cabin.

[0036] 3. The present invention can realize rapid temperature correction, high real-time data processing and good three-dimensional temperature field restoration. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is the overall module structure diagram of the measuring device of the present invention;

[0038] Figure 2 It is a temperature measurement flow chart of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0040] In order to solve the problem of inaccurate measurement of the temperature field inside the wind turbine cabin by the existing technology, please refer to Figure 1-2 , this embodiment provides the following technical solutions:

[0041] A wind turbine nacelle temperature field measuring device based on data fusion, comprising:

[0042] The data acquisition module is used to sense and measure the temperature inside the wind turbine cabin. The data acquisition module includes an infrared camera, a thermal resistor sensor and a binocular camera. The infrared camera is used to obtain the continuous temperature distribution in the field of view; the thermal resistor sensor is used to perform accurate temperature measurement at specific points of the equipment to provide a reference value for correcting the temperature measurement results of the infrared camera; the binocular camera is used to obtain the three-dimensional spatial information inside the wind turbine cabin; correspondingly collects thermal imaging data, thermal resistor temperature data and three-dimensional spatial data;

[0043] A data preprocessing module, used to process the thermal imaging data and three-dimensional spatial data, and perform signal conversion on the temperature data collected by the thermal resistance sensor;

[0044] The data fusion module is used to correct and fuse the pre-processed thermal imaging data and the thermal resistance temperature data, and to fuse the corrected two-dimensional temperature data with the three-dimensional spatial information obtained based on the binocular camera, to construct a three-dimensional temperature field model inside the cabin, and to form a complete three-dimensional distributed temperature field through interpolation calculation.

[0045] The data fusion module includes:

[0046] The temperature correction fusion unit is used to fuse the pre-processed thermal imaging data with the thermal resistance temperature data, and to correct the temperature results in the thermal imaging data to reduce the imaging error caused by the difference in reflectivity of the object surface;

[0047] A three-dimensional space construction unit, used to perform extreme correction and stereo matching on the left and right images acquired by the binocular camera, and construct a three-dimensional space model of the interior of the cabin after obtaining a disparity map and a depth map;

[0048] A temperature mapping fusion unit, used to fuse the corrected thermal imaging data with the three-dimensional space model, construct a correspondence between points on the three-dimensional model and pixel points in the temperature image, and map the temperature information to the three-dimensional model;

[0049] The interpolation processing unit is used to interpolate the constructed three-dimensional temperature model to fill in the possible data gaps and form a complete and smooth three-dimensional distribution model of the temperature field inside the cabin. This process ensures that the three-dimensional model not only has geometric shape information, but also contains detailed temperature distribution data, thus providing a reliable basis for temperature monitoring and heat dissipation structure optimization inside the wind turbine cabin.

[0050] The working process of the temperature correction fusion unit includes the following steps:

[0051] S11, fusing the pre-processed thermal image with the temperature data collected by the thermal resistance sensor, in this process using image processing technology to identify the positions of the thermal resistance measuring points in the thermal image and obtain the actual temperature values ​​of these measuring points;

[0052] S12. Based on the difference between the temperature value of the measuring point in the thermal image and the temperature value recorded by the thermal resistance sensor, the backlight surface of the device in the thermal image, that is, the part away from the heat source, is subjected to temperature compensation calibration. The purpose of this is to reduce the imaging error caused by the different reflectivity of the surface of the object, thereby improving the accuracy of the thermal imaging data. Through such a fusion and correction process, the temperature correction fusion unit can correct the temperature result in the thermal image to make it closer to the actual temperature distribution, thereby providing more reliable basic data for the subsequent three-dimensional temperature field construction.

[0053] The working process of the three-dimensional space construction unit includes the following steps:

[0054] S21, adjusting the images of the binocular camera so that the corresponding points in the two images are located on the same straight line, which helps to simplify the subsequent stereo matching process;

[0055] S22, by comparing the similarity of corresponding feature points in the left and right images of the binocular camera, find the corresponding points in each pair of images, so as to determine the relative positions of these points in space;

[0056] S23, based on the result of stereo matching, calculating the disparity value of each pixel, and then converting it into depth information to obtain a disparity map and a depth map;

[0057] S24. Utilize the depth information and the calibration parameters of the binocular camera to map each pixel into a three-dimensional space to form a three-dimensional point cloud or mesh model, and perform post-processing and optimization.

[0058] The data acquisition module also includes an environmental parameter sensor for collecting environmental parameter data, and the environmental parameters include but are not limited to humidity, air pressure, and wind speed.

[0059] The temperature correction fusion unit also includes an environmental parameter compensation subunit, which is used to perform compensation processing on the thermal imaging data according to the environmental parameter data.

[0060] The temperature mapping fusion unit also includes an anomaly detection subunit for identifying abnormally high temperature areas in the three-dimensional temperature model and generating an alarm signal.

[0061] The interpolation processing unit adopts one of a linear interpolation algorithm and a high-order interpolation algorithm to improve the smoothness and resolution of the temperature field.

[0062] A measurement method of a wind turbine cabin temperature field measurement device based on data fusion is implemented based on a wind turbine cabin temperature field measurement device based on data fusion, and includes the following steps:

[0063] Step 1: After the measuring equipment is installed, the thermal resistance sensor, infrared camera and binocular camera respectively collect and obtain three state data of the measuring object;

[0064] Step 2: Data fusion of the thermal image after denoising, enhancement and other preprocessing and the temperature of the thermal resistor after signal conversion, use image processing technology to identify the position of the thermal resistor measuring point in the thermal image and obtain the temperature value of the point, and perform temperature compensation calibration on the backlight surface of the device based on the difference between the thermal image temperature of the measuring point and the temperature of the sensor;

[0065] Step 3: Obtain the disparity map and depth map of the binocular camera through epipolar correction and stereo matching, perform three-dimensional space modeling on the disparity map and depth map, and perform post-processing and optimization;

[0066] Step 4: Map the 3D model to the temperature image based on the calibrated 2D thermal image and the spatial position information of the binocular camera, construct the correspondence between the points on the 3D model and the pixels of the thermal image, and return the temperature information to the 3D model;

[0067] Step 5: Interpolate the three-dimensional temperature model to construct a three-dimensional distribution model of the temperature field.

[0068] Working principle: The three-dimensional temperature field inside the wind turbine cabin is measured by integrating thermistor sensors, infrared cameras and binocular cameras. First, each sensor collects temperature, thermal imaging and three-dimensional spatial data; then, the thermal image is preprocessed and fused with thermistor temperature data to correct the temperature result and reduce imaging errors; next, the disparity map and depth map obtained by the binocular camera are used to construct a three-dimensional spatial model; on this basis, the corrected temperature information is mapped to the three-dimensional model to form a three-dimensional model with temperature information; finally, the three-dimensional model is interpolated to construct a complete three-dimensional model of the temperature distribution inside the cabin.

[0069] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0070] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A wind turbine cabin temperature field measurement device based on data fusion, characterized in that: include: The data acquisition module is used to sense and measure the temperature inside the wind turbine cabin. The data acquisition module includes an infrared camera, a thermal resistor sensor and a binocular camera, which respectively collect thermal imaging data, thermal resistor temperature data and three-dimensional space data; A data preprocessing module, used to process the thermal imaging data and three-dimensional spatial data, and perform signal conversion on the temperature data collected by the thermal resistance sensor; The data fusion module is used to correct and fuse the pre-processed thermal imaging data and the thermal resistance temperature data, and to fuse the corrected two-dimensional temperature data with the three-dimensional spatial information obtained based on the binocular camera, to construct a three-dimensional temperature field model inside the cabin, and to form a complete three-dimensional distributed temperature field through interpolation calculation.

2. A wind turbine cabin temperature field measurement device based on data fusion according to claim 1, characterized in that: The data fusion module comprises: The temperature correction fusion unit is used to fuse the pre-processed thermal imaging data with the thermal resistance temperature data and correct the temperature results in the thermal imaging data; A three-dimensional space construction unit, used to perform extreme correction and stereo matching on the left and right images acquired by the binocular camera, and construct a three-dimensional space model of the interior of the cabin after obtaining a disparity map and a depth map; A temperature mapping fusion unit, used to fuse the corrected thermal imaging data with the three-dimensional space model, construct a correspondence between points on the three-dimensional model and pixel points in the temperature image, and map the temperature information to the three-dimensional model; The interpolation processing unit is used to perform interpolation processing on the constructed three-dimensional temperature model to form a complete and smooth three-dimensional distribution model of the temperature field inside the cabin.

3. A wind turbine cabin temperature field measurement device based on data fusion according to claim 2, characterized in that: The working process of the temperature correction fusion unit includes the following steps: S11, fusing the pre-processed thermal image with the temperature data collected by the thermal resistance sensor, in this process using image processing technology to identify the positions of the thermal resistance measuring points in the thermal image and obtain the actual temperature values ​​of these measuring points; S12. Based on the difference between the temperature value of the measuring point in the thermal image and the temperature value recorded by the thermal resistance sensor, a temperature compensation calibration is performed on the backlight surface of the device in the thermal image, that is, the part away from the heat source.

4. A wind turbine cabin temperature field measurement device based on data fusion according to claim 3, characterized in that: The working process of the three-dimensional space construction unit includes the following steps: S21, adjusting the images of the binocular camera so that corresponding points in the two images are located on the same straight line; S22, by comparing the similarity of corresponding feature points in the left and right images of the binocular camera, find the corresponding points in each pair of images, so as to determine the relative positions of these points in space; S23, based on the result of stereo matching, calculating the disparity value of each pixel, and then converting it into depth information to obtain a disparity map and a depth map; S24, using the depth information and camera calibration parameters, mapping each pixel into a three-dimensional space to form a three-dimensional point cloud or mesh model, and performing post-processing and optimization.

5. A wind turbine cabin temperature field measurement device based on data fusion according to claim 4, characterized in that: The data acquisition module also includes an environmental parameter sensor for collecting environmental parameter data, and the environmental parameters include but are not limited to humidity, air pressure, and wind speed.

6. A wind turbine cabin temperature field measurement device based on data fusion according to claim 5, characterized in that: The temperature correction fusion unit also includes an environmental parameter compensation subunit, which is used to perform compensation processing on the thermal imaging data according to the environmental parameter data.

7. A wind turbine cabin temperature field measurement device based on data fusion according to claim 6, characterized in that: The temperature mapping fusion unit also includes an abnormality detection subunit, which is used to identify abnormally high temperature areas in the three-dimensional temperature model and generate an alarm signal.

8. The wind turbine cabin temperature field measurement device based on data fusion according to claim 7 is characterized in that: The interpolation processing unit adopts one of a linear interpolation algorithm and a high-order interpolation algorithm.

9. A method for measuring a temperature field in a wind turbine cabin based on data fusion, implemented based on the device for measuring a temperature field in a wind turbine cabin based on data fusion according to any one of claims 1 to 8, characterized in that: The following steps are involved: Step 1: After the measuring equipment is installed, the thermal resistance sensor, infrared camera and binocular camera respectively collect and obtain three state data of the measuring object; Step 2: Data fusion of the thermal image after denoising, enhancement and other preprocessing and the temperature of the thermal resistor after signal conversion, use image processing technology to identify the position of the thermal resistor measuring point in the thermal image and obtain the temperature value of the point, and perform temperature compensation calibration on the backlight surface of the device based on the difference between the thermal image temperature of the measuring point and the temperature of the sensor; Step 3: Obtain the disparity map and depth map of the binocular camera through epipolar correction and stereo matching, perform three-dimensional space modeling on the disparity map and depth map, and perform post-processing and optimization; Step 4: Map the 3D model to the temperature image based on the calibrated 2D thermal image and the spatial position information of the binocular camera, construct the correspondence between the points on the 3D model and the pixels of the thermal image, and return the temperature information to the 3D model; Step 5: Interpolate the three-dimensional temperature model to construct a three-dimensional distribution model of the temperature field.

Images