Unmanned aerial vehicle cooperative inspection laser deicing system and method

Abstract

The application belongs to the technical field of wind power generation equipment maintenance, and particularly relates to a kind of unmanned aerial vehicle cooperative inspection laser deicing system and method, unmanned aerial vehicle cluster, the unmanned aerial vehicle cluster includes master unmanned aerial vehicle and slave unmanned aerial vehicle, the master unmanned aerial vehicle is equipped with binocular camera for taking pictures and laser radar for ranging, for constructing blade three-dimensional icing map, the slave unmanned aerial vehicle is equipped with pulse laser generator for heating ice layer and thermal infrared camera, the resolution of the thermal infrared camera is 640x512 pixels, and the temperature measurement accuracy is ±0.5 DEG C, and the thermal infrared camera is used for real-time acquisition of blade surface temperature field;The communication delay of the 5GMesh network is less than 100ms, supports dynamic node access and real-time data synchronization;The application is equipped with binocular camera and laser radar, which realizes three-dimensional accurate modeling of the icing area, has small positioning error, improves the detection efficiency compared with manual detection, and avoids the risk of high-altitude operation for workers.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of wind power equipment maintenance, and particularly relates to a UAV cooperative inspection laser deicing system and method. BACKGROUND

[0002] In the field of wind power generation, the surface icing of a wind turbine blade, as a core component for energy conversion, is an important inducement for the decline of power generation efficiency and equipment failure. According to statistics, when the thickness of the icing on the surface of the blade exceeds 2mm, the aerodynamic efficiency of the wind turbine can decrease by 15%-20%, and in extreme cases, it can cause blade rupture and other safety accidents. Therefore, an efficient and reliable blade deicing technology is the key to ensuring the stable operation of wind power equipment in cold and humid environments.

[0003] Problems of the prior art:

[0004] Traditional manual deicing requires climbing work, and the cost of single maintenance is more than 20,000 yuan, and there is a risk of falling; mechanical deicing equipment, such as helicopter sand blasting, can easily damage the blade coating, and the aerodynamic performance decreases after maintenance; the existing UAV liquid spraying deicing technology is greatly affected by environmental humidity, and the efficiency decreases sharply below-10℃, and the residual drug pollutes the blade; although the concept of laser deicing has been proposed, the existing scheme has defects such as insufficient energy control precision, high risk of thermal damage, large positioning error, lack of closed-loop verification, and is difficult to meet the engineering needs. SUMMARY

[0005] The purpose of the present application is to provide a UAV cooperative inspection laser deicing system and method, which can build an efficient, safe and low-consumption unmanned deicing system, and provide a breakthrough solution for the reliable operation of wind turbines in cold and humid environments, and has significant engineering application value and economic benefits.

[0006] The technical scheme adopted by the present application is as follows:

[0007] A UAV cooperative inspection laser deicing system, comprising:

[0008] A UAV cluster, the UAV cluster comprising a master UAV and a slave UAV, the master UAV being equipped with a binocular camera for taking pictures and a laser radar for ranging, for constructing a three-dimensional icing map of the blade, the slave UAV being provided with a pulsed laser generator for heating the ice layer and a thermal infrared camera, the thermal infrared camera having a resolution of 640x512 pixels and a temperature measurement accuracy of ±0.5℃, the thermal infrared camera being used for real-time acquisition of the temperature field of the blade surface; the communication delay of the 5GMesh network is less than 100ms, and the 5GMesh network supports dynamic node access and real-time data synchronization;

[0009] The central cooperative control deicing module includes a laser deicing module and a closed-loop verification module. The laser deicing module uses pulse width modulation technology to control the output of laser energy of the pulsed laser generator. The laser deicing module has a laser path planning algorithm based on an ice layer thickness cloud map, which is used to preferentially process areas with an icing probability greater than 80%, including the leading edge and tip of the blade. The closed-loop verification module includes a temperature field real-time monitoring unit and an ice layer residual discrimination unit. The temperature field real-time monitoring unit acquires the blade surface temperature field in real time through the thermal infrared camera. The ice layer residual discrimination unit determines whether deicing is completed based on the established "temperature gradient-ice layer residual" discrimination model, and the area that does not meet the standard automatically triggers secondary light compensation.

[0010] The wavelength of the pulsed laser generator is 1064 nm, the single pulse energy is less than 500 mJ, the power is less than 500 W, the laser beam divergence angle is less than 1.5 mrad, and the focused spot diameter is 5-10 mm.

[0011] In the "temperature gradient-ice layer residual" discrimination model, the threshold for determining whether deicing is completed is a local temperature difference of less than 2℃.

[0012] A method for cooperative inspection and laser deicing of unmanned aerial vehicles, comprising the following steps:

[0013] S1, deploy a cluster of unmanned aerial vehicles to a target wind farm, establish a communication link through a 5G Mesh network, and synchronize initial coordinate data;

[0014] S2, the master unmanned aerial vehicle scans the blade surface, constructs a three-dimensional point cloud model and identifies the icing area, generates an ice layer thickness cloud map and transmits it to the slave unmanned aerial vehicle;

[0015] S3, the slave unmanned aerial vehicle plans a laser path, adjusts the flight attitude to make the laser beam vertically incident on the surface to be processed, and starts the pulsed laser generator for deicing operation;

[0016] S4, the thermal infrared camera acquires temperature field data, analyzes the deicing effect based on the discrimination model, triggers secondary light compensation in the area that does not meet the standard, and repeats S3 until the thermal infrared image shows that the ice layer is completely removed;

[0017] S5, after completing the deicing of a single area, the cluster of unmanned aerial vehicles moves to the next icing area according to the preset path, repeats S2 to S4, and completes the deicing of the entire blade. The master unmanned aerial vehicle generates a report and uploads it;

[0018] S6, remote evaluation by ground personnel, adjustment of parameters or path if necessary, and start of secondary operation.

[0019] In the S2, when the three-dimensional point cloud model is constructed and the icing area is identified, the threshold is set to reflectivity greater than 80% and thickness greater than 2mm, and the generated ice layer thickness cloud map has an accuracy of ±0.2mm.

[0020] In the S3, in the laser deicing operation, the laser temperature rise rate is 5±1℃ / s, the laser beam incidence angle deviation is less than 5°, and the scanning speed is 10-50mm / s.

[0021] In the S6, the target for evaluating the deicing effect is that the residual ice layer is less than 0.5mm and the blade temperature rise is less than 10℃.

[0022] The technical effects achieved by the present application are:

[0023] In the present application, the collaborative innovation of the man-machine cluster and the laser deicing technology breaks through the safety and efficiency bottleneck of traditional high-altitude manual maintenance, and realizes the full-process automation of wind turbine blade icing treatment.

[0024] The specific technical effects are embodied in that the unmanned aerial vehicle carries a binocular camera and a laser radar to realize three-dimensional accurate modeling of the icing area, the positioning error is small, the detection efficiency is improved compared with manual detection, and the risk of high-altitude operation is also avoided for the workers.

[0025] The pulse laser set in the present application is accurately controlled in energy output through pulse width modulation technology, so that the temperature rise rate is maintained at 5±1℃ / s, the blade substrate is effectively prevented from overheating, the aerodynamic power loss after deicing is relatively small, the energy consumption is effectively reduced compared with traditional electric heating, and the energy utilization rate is also relatively high.

[0026] The thermal infrared camera set in the present application verifies the deicing effect in real time, can identify residual ice layer less than 0.5mm, realizes high accuracy of secondary light compensation combined with the "temperature gradient-ice layer residual" model, and makes the overall operation success rate relatively high.

[0027] The 5GMesh network set in the present application guarantees the data synchronicity of multiple machines, ensures the accuracy of laser path planning and light compensation operation, the system is suitable for use in low-temperature and high-humidity environments, effectively reduces the single maintenance cost, does not need chemical agents and is compatible with moderate rain conditions, and can cover a larger range of icing wind fields.

[0028] In summary, the present application constructs an unmanned deicing system with high efficiency, safety and low consumption, provides a breakthrough solution for reliable operation of wind turbines in cold and humid environments, and has significant engineering application value and economic benefits. BRIEF DESCRIPTION OF DRAWINGS

[0029] Fig. 1 is the deicing operation flowchart of the unmanned aerial vehicle cluster of the present application;

[0030] Fig. 2is a thermal infrared image ice layer residual discrimination logic diagram of the present application. DETAILED DESCRIPTION

[0031] In order to make the purpose and advantages of the present application more clear and apparent, the present application will be specifically described below in conjunction with embodiments. It should be understood that the following text is only used to describe one or several specific embodiments of the present application, and does not strictly limit the specific protection scope requested by the present application.

[0032] As shown in Figs. 1-2 A UAV cooperative inspection laser deicing system, comprising:

[0033] A UAV cluster, the UAV cluster comprising a master UAV and a slave UAV, the master UAV being equipped with a binocular camera for taking photos and a laser radar for ranging, for constructing a blade three-dimensional icing map, the slave UAV being equipped with a pulsed laser generator for heating ice layer and a thermal infrared camera, the thermal infrared camera having a resolution of 640x512 pixels and a temperature measurement accuracy of ±0.5℃, the thermal infrared camera being used for real-time acquisition of blade surface temperature field; the UAV cluster being equipped with a microcomputer for verifying ice melting effect and determining whether laser is needed;

[0034] The pulsed laser generator has a wavelength of 1064nm, a single pulse energy less than 500mJ, a power less than 500W, a laser beam divergence angle less than 1.5mrad, and a focused spot diameter of 5-10mm; the 5G Mesh network has a communication delay less than 100ms, supports dynamic node access and real-time data synchronization for ice melting;

[0035] A central cooperative control deicing module, comprising a laser deicing module and a closed-loop verification module, the laser deicing module using pulse width modulation technology to control the output of laser energy of the pulsed laser generator, the laser deicing module having a laser path planning algorithm based on ice layer thickness cloud map, for preferentially processing areas with an icing probability greater than 80%, the areas including blade leading edge and blade tip;

[0036] The closed-loop verification module comprises a temperature field real-time monitoring unit and an ice layer residual discrimination unit, the temperature field real-time monitoring unit acquiring blade surface temperature field in real time through the thermal infrared camera, the ice layer residual discrimination unit being based on an established "temperature gradient-ice layer residual" discrimination model, determining that deicing is completed when local temperature difference is less than 2℃, and automatically triggering secondary light supplement in areas that do not meet the standard.

[0037] According to the above structure, the safety and efficiency bottlenecks of traditional high-altitude manual maintenance are broken through, and full-process automation of wind turbine blade icing treatment is realized; the UAV is equipped with a binocular camera and a laser radar to realize three-dimensional accurate modeling of icing areas, reduce positioning error, improve detection efficiency compared with manual operation, and effectively eliminate high-altitude operation risks,

[0038] A method for unmanned aerial vehicle cooperative inspection and laser deicing, comprising the following steps:

[0039] S1, deploy the master unmanned aerial vehicle equipped with binocular camera and laser radar and the slave unmanned aerial vehicle equipped with pulse laser generator and thermal infrared camera to the target wind farm, establish communication link through 5GMesh network, and synchronize initial coordinate data;

[0040] S2, the master unmanned aerial vehicle flies along the preset inspection path and is 10-50 m away from the blade surface, scans the blade surface through the fusion of binocular camera and laser radar, constructs a three-dimensional point cloud model and identifies the icing area, the threshold is set to reflectivity greater than 80% and thickness greater than 2 mm, generates ice layer thickness cloud map with precision ±0.2 mm, and synchronously transmits to the slave unmanned aerial vehicle.

[0041] S3, the slave unmanned aerial vehicle plans laser path based on the ice layer thickness cloud map, preferentially covers key areas such as blade leading edge and blade tip, adjusts flight attitude to make laser beam vertically incident on the surface to be processed, the incidence angle deviation is less than 5°, starts the pulse laser generator, locally heats the ice layer at a temperature rise rate of 5±1 ℃ / s, the single pulse energy of the pulse laser generator is less than 500 mJ, the spot diameter is 5-10 mm, and the scanning speed is 10-50 mm / s;

[0042] S4, the thermal infrared camera collects temperature field data of the laser action area in real time, analyzes the deicing effect based on the "temperature gradient-ice layer residue" discrimination model, if it does not meet the standard, automatically triggers the secondary light compensation program, repeats the deicing operation of S3, and until the thermal infrared image shows that the ice layer is completely removed;

[0043] S5, after completing the deicing of a single area, the unmanned aerial vehicle cluster moves to the next icing area according to the preset path, repeats steps S2 to S4, and until the inspection and deicing of the whole blade are completed; the master unmanned aerial vehicle summarizes the deicing area, energy consumption, time consumption data in the operation, generates a three-dimensional visual report, and uploads it to the ground control center;

[0044] S6, the ground personnel remotely analyze the operation report and evaluate the deicing effect, the target for evaluating the deicing effect is that the residual ice layer is less than 0.5 mm and the blade temperature rise is less than 10℃, if necessary, adjust the laser parameters or inspection path, start the secondary operation to ensure the thoroughness of deicing.

[0045] Embodiment one

[0046] Scene: In winter, the temperature is around -30℃ for a long time, and the environmental humidity is as high as 90%. The extremely low temperature and high humidity conditions make the wind turbine blade icing quickly, and the ice layer thickness grows extremely fast.

[0047] Operation process:

[0048] After the master drone and the slave drone establish a communication link through the 5G Mesh network, the master drone starts scanning the blade at a height of 15 m from the blade surface along the planned inspection path, the binocular camera and the laser radar work stably, quickly build a three-dimensional point cloud model, accurately identify the qualified icing area, generate an ice layer thickness cloud map and transmit it to the slave drone;

[0049] After receiving the data from the slave drone, for the blade icing condition, the single pulse energy of the pulse laser generator is set to 420 mJ, the spot diameter is 7 mm, the scanning speed is adjusted to 20 mm / s, and the deicing operation is started at a temperature rise rate of 4 ℃ / s. In the deicing process, the thermal infrared camera collects temperature field data in real time. Due to the rapid heat dissipation in low temperature environment, the system quickly analyzes the temperature data through the "temperature gradient-ice layer residual" discrimination model. When the local temperature difference is greater than 2 ℃, the secondary light compensation is triggered immediately. After several rounds of fine operation, the ice layer of the whole blade is completely removed, and the residual ice layer thickness is only 0.3 mm. The blade temperature rise is controlled within 8 ℃, and the deicing task is completed efficiently in the extremely cold and humid environment.

[0050] Example two

[0051] Scenario:

[0052] The air temperature fluctuates between -20 ℃ and 0 ℃, and the environmental humidity is maintained at 80%-95%. The wind turbine blade icing here presents the characteristics of uneven distribution and large thickness difference.

[0053] Operation process:

[0054] After the master drone and the slave drone establish a communication link through the 5G Mesh network, the master drone starts scanning the blade at a height of 15 m from the blade surface along the planned inspection path, the binocular camera and the laser radar work stably, quickly build a three-dimensional point cloud model, accurately identify the qualified icing area, generate an ice layer thickness cloud map and transmit it to the slave drone;

[0055] According to the ice layer thickness cloud map, for the areas such as the leading edge of the blade where the icing is thicker, the single pulse energy is increased to 480 mJ, and the scanning speed is slowed down to 15 mm / s; for the areas where the icing is thinner, the single pulse energy is set to 380 mJ, and the scanning speed is increased to 25 mm / s for deicing. The thermal infrared camera monitors the temperature field change throughout the process, and accurately captures the temperature data in the high humidity environment. Based on the "temperature gradient-ice layer residual" discrimination model, the deicing effect is determined in real time, and the secondary light compensation is performed in time for the areas that do not meet the standard. All the deicing operations of the blades are successfully completed, the residual ice layer thickness is less than 0.5 mm, and the blade temperature rise does not exceed 10 ℃, effectively ensuring the normal operation of the wind turbine.

[0056] Example three

[0057] Scenario: Winter is often attacked by cold waves, the temperature drops to -25°C, and the humidity reaches 100%. The wind turbine blades not only freeze severely, but also have rime phenomenon.

[0058] Operation process:

[0059] After the master unmanned aerial vehicle and the slave unmanned aerial vehicle establish a communication link through the 5G Mesh network, the master unmanned aerial vehicle starts scanning the blade at a height of 15 m from the blade surface along the planned inspection path. The binocular camera and laser radar work stably, quickly build a three-dimensional point cloud model, accurately identify the qualified icing area, generate an ice layer thickness cloud map, and transmit it to the slave unmanned aerial vehicle.

[0060] After the slave unmanned aerial vehicle plans the laser path according to the cloud map, it starts the deicing program. Considering the influence of rime on deicing, the system optimizes the parameters of the pulsed laser generator, with a single pulse energy of 450 mJ and a spot diameter of 8 mm, and gradually melts the ice layer and rime at a temperature rise rate of 5°C / s.

[0061] The thermal infrared camera accurately collects temperature field data in a high-humidity and low-temperature environment, and the closed-loop verification module strictly checks the deicing effect according to the "temperature gradient-ice layer residual" discrimination model. Once it finds that the local temperature difference is not up to standard, it will trigger secondary light compensation. After several rounds of meticulous deicing and light compensation operations, the ice layer and rime on the entire blade are completely removed, with a residual ice layer thickness of less than 0.5 mm and a blade temperature rise of only 9°C. In the extreme low-temperature and high-humidity environment, it shows strong deicing ability and stability.

[0062] According to the above, the pulsed laser precisely controls the energy output through PWM technology, with a temperature rise rate of 5±1°C / s, and the maximum temperature rise on the blade surface is only 6.8°C. The aerodynamic power loss after deicing is less than 1.5%, and the energy consumption is reduced by more than 90% compared with traditional electric heating. The single pulse energy is less than 500 mJ, and the energy utilization rate is 85%. The thermal infrared camera verifies the deicing effect in real time, can identify residual ice layer less than 0.5 mm, and realizes 100% accuracy of secondary light compensation combined with the "temperature gradient-ice layer residual" model, with an overall operation success rate of 98.7%. The 5G Mesh network ensures that the data synchronization delay of multiple machines is less than 100 ms, and the positioning error is less than 5 cm, ensuring the accuracy of laser path planning and light compensation operation. The system is suitable for low-temperature environments of -30°C-0°C and humidity environments of 60%-100%, with a single maintenance cost reduced by 75% compared with manual operation, without the need for chemical agents and compatible with rain conditions, covering more than 90% of the global icing wind field.

[0063] The above merely describes the preferred embodiments of the present application, and it should be pointed out that those skilled in the art can make several improvements and refinements without departing from the principles of the present application, and these improvements and refinements should also be considered as the protection scope of the present application. The structures, devices and operation methods not specifically described and explained in the present application are implemented according to the conventional means in the art, unless specifically described and limited.

Claims

1. A UAV cooperative inspection laser de-icing system, characterized in that, The unmanned aerial vehicle cluster comprises a master unmanned aerial vehicle and a slave unmanned aerial vehicle, the master unmanned aerial vehicle is provided with a binocular camera for taking pictures and a laser radar for distance measurement, and the slave unmanned aerial vehicle is provided with a pulsed laser generator for heating ice layer and a thermal infrared camera for collecting a blade surface temperature field in real time; The central cooperative control deicing module comprises a laser deicing module and a closed-loop verification module, the laser deicing module controls the output of laser energy of the pulsed laser generator by using a pulse width modulation technology, and the closed-loop verification module comprises a temperature field real-time monitoring unit and an ice layer residue discrimination unit, the temperature field real-time monitoring unit collects a blade surface temperature field in real time through the thermal infrared camera, and the ice layer residue discrimination unit discriminates whether deicing is completed based on a "temperature gradient-ice layer residue" discrimination model, and when a local temperature difference is less than 2 DEG C, it is determined that deicing is completed, and a secondary light supplement is automatically triggered in a non-compliant area. The wavelength of the pulsed laser generator is 1064 nm, the single-pulse energy is less than 500 mJ, the power is less than 500 W, the laser beam divergence angle is less than 1.5 mrad, and the focused spot diameter is 5-10 mm. 2.The UAV cooperative inspection laser de-icing system of claim 1, wherein: The unmanned aerial vehicle cluster synchronizes data through a 5GMesh network. 3.The UAV cooperative inspection laser de-icing system of claim 1, wherein: The laser deicing module has a laser path planning algorithm based on an ice layer thickness cloud map.

4. The unmanned aerial vehicle coordinated inspection laser de-icing system of claim 1, wherein: The resolution of the thermal infrared camera is 640*512 pixels, and the temperature measurement accuracy is ±0.5 DEG C.

5. The unmanned aerial vehicle coordinated inspection laser de-icing system of claim 1, wherein: The method comprises the following steps:

6. A method for UAV cooperative inspection laser de-icing based on the UAV cooperative inspection laser de-icing system according to any one of claims 1-5, characterized in that, S1, deploying an unmanned aerial vehicle cluster to a target wind farm, establishing a communication link through a 5GMesh network, and synchronizing initial coordinate data; S2, the master unmanned aerial vehicle scans the blade surface, constructs a three-dimensional point cloud model and identifies the icing area, generates an ice layer thickness cloud map and transmits it to the slave unmanned aerial vehicle; S3, the slave unmanned aerial vehicle plans a laser path, adjusts the flight attitude to make the laser beam vertically incident on the surface to be processed, starts the pulsed laser generator for deicing operation; S4, the thermal infrared camera collects temperature field data, analyzes the deicing effect based on a discrimination model, triggers secondary light supplement in a non-compliant area, and repeats S3 until the thermal infrared image shows that the ice layer is completely removed; S5, after completing deicing of a single area, the unmanned aerial vehicle cluster moves to the next icing area according to a preset path, repeats S2 to S4 until the whole blade is inspected and deiced, the master unmanned aerial vehicle generates a report and uploads it; S6, remote evaluation by ground personnel, and adjustment of parameters or path as necessary to start secondary operation. In S2, when the three-dimensional point cloud model is constructed and the icing area is identified, the threshold is set to reflectivity greater than 80% and thickness greater than 2 mm, and the accuracy of the generated ice layer thickness cloud map is ±0.2 mm.

7. The method of claim 6, wherein: In S3, in the laser deicing operation, the laser temperature rise rate is 5±1 DEG C / s, the laser beam incidence angle deviation is less than 5 DEG, and the scanning speed is 10-50 mm / s. 8.The method of claim 6, wherein: In S6, the target for evaluating the deicing effect is residual ice layer less than 0.5 mm and blade temperature rise less than 10 DEG C. 9.The method of claim 6, wherein: ​

Images