Aircraft icing detection methods, devices and aircraft

Abstract

This application provides a method, apparatus, and aircraft for detecting aircraft icing, relating to the field of icing detection technology. The method includes: acquiring a first dataset and a second dataset at a first time point, and simultaneously acquiring total temperature data at the second time point; comparing the second dataset with the first dataset to detect changes in the aircraft's external environment or windshield field of view; if the changes in the aircraft's external environment and windshield field of view indicate visible moisture, and the total temperature data is below a preset threshold, then it is determined that the changes in the aircraft's external environment and windshield field of view meet a first icing condition. This application can reduce the workload of pilots in icing judgment and further improve flight safety performance.

Description

Technical Field

[0001] This application relates to the field of icing detection technology, and in particular to a method, device and aircraft for detecting icing in aircraft. Background Technology

[0002] Civil aircraft flight manuals (AFM) or crew operating manuals (FCOM) clearly define icing conditions: when the total temperature (TAT) of an aircraft is equal to or below 10°C (50°F) and visible water vapor (such as clouds, fog, rain, snow, sleet, and ice crystals) is present in the environment, the aircraft may encounter icing conditions. In actual flight operations, pilots must make subjective judgments based on whether the TAT is below or equal to 10°C and whether they are passing through cloud cover to determine whether the aircraft has entered an icing weather environment.

[0003] However, this method of judgment has certain drawbacks because it increases the pilot's workload. Pilots not only need to visually identify the presence of icing conditions, but also need to continuously monitor the total temperature and manually activate the anti-icing system after confirming that icing conditions have occurred. This system, which relies on the pilot's subjective judgment and manual operation, is known in the industry as a consultative detection system. This system requires pilots to assume more judgment and operational responsibility during flight, which to some extent increases the complexity and potential risks of flight. Summary of the Invention

[0004] This application provides a method, device, and aircraft for detecting aircraft icing, aiming to solve the problem of how to automatically identify aircraft icing conditions, thereby reducing the workload of pilots in icing judgment and anti-icing operations, and further improving flight safety performance.

[0005] In a first aspect, this application provides a method for detecting icing on an aircraft, the method comprising:

[0006] Acquire a first dataset of the aircraft at a first time point and a second dataset at a second time point, and simultaneously acquire total temperature data at the second time point; wherein, the first dataset and the second dataset include field-of-view images of the cockpit main windshield and side windshields, as well as external images or video data of the aircraft acquired through external camera devices;

[0007] The second dataset was compared with the first dataset to detect changes in the external environmental surface of the aircraft and within the windshield's field of view;

[0008] If changes in the external environment of the aircraft and the windshield's field of vision indicate visible moisture, and the total temperature data is below a preset threshold, then the changes in the external environment of the aircraft and the windshield's field of vision are determined to meet the first icing condition.

[0009] In one embodiment of this application, the step of comparing the second dataset with the first dataset includes:

[0010] By comparing the grayscale distribution of the second dataset with that of the first dataset, the grayscale changes caused by the passage of humid airflow in the external environment of the aircraft and within the field of view of the windshield are identified and quantified.

[0011] If a region in the second dataset that is greater than or equal to a preset proportion exhibits grayscale changes, it is determined that there is visible moisture in the changes within the external environment of the aircraft and the field of view of the windshield.

[0012] In one embodiment of this application, the method further includes:

[0013] If the changes in the external environment of the aircraft and the field of vision of the windshield do not meet the first icing condition, then determine whether the first icing detection alarm corresponding to the first icing condition is activated.

[0014] If the first icing alarm has been activated, cancel the first icing detection alarm and prompt the pilot to leave the icing weather conditions that meet the first icing conditions.

[0015] If changes in the external environment of the aircraft and within the windshield's field of vision meet the first icing conditions, a first icing detection alarm will be issued, prompting the pilot to enter icing weather conditions that meet the first icing conditions.

[0016] In one embodiment of this application, the method further includes:

[0017] Obtain the third dataset and the fourth dataset at the second time point from the cockpit side windshield;

[0018] Compare the fourth dataset with the third dataset to detect changes within the side windshield field of view or at a preset reference surface;

[0019] If the changes within the side windshield's field of vision show the presence of supercooled large water droplets, then the current situation is determined to meet the second icing condition. The second icing condition is a further judgment based on the first icing condition, specifically the presence of supercooled large water droplets within the side windshield's field of vision.

[0020] In one embodiment of this application, the step of comparing the fourth dataset with the third dataset includes:

[0021] If the fourth dataset shows an icing area, and the area of ​​the icing area is greater than or equal to a preset threshold, then the changes within the field of view of the side windshield indicate the presence of supercooled large water droplets.

[0022] In one embodiment of this application, the method further includes:

[0023] If the changes within the field of view of the side windshield do not meet the second icing condition, then determine whether the second icing detection alarm corresponding to the second icing condition is activated.

[0024] If the second icing detection alarm has been activated, cancel the second icing detection alarm and prompt the pilot to leave the icing weather conditions that meet the second icing conditions.

[0025] In one embodiment of this application, the method further includes:

[0026] If the changes within the field of vision of the side windshield meet the second icing condition, a second icing detection alarm will be issued and the pilot will be prompted to enter the icing weather conditions that meet the second icing condition, and then enter the operating procedure that meets the second icing condition.

[0027] In one embodiment of this application, a light source and at least three sets of camera devices are installed at a preset position on the aircraft. One set of camera devices is used to capture the view from the main windshield, one set of camera devices is used to capture the view from the side windshields, and another set is used to capture the external surface of the aircraft. The light source is used to provide light for the camera devices.

[0028] In one embodiment of this application, acquiring a first dataset and a second dataset of the aircraft at a first time point and at a second time point, while simultaneously acquiring total temperature data at the second time point, includes:

[0029] Use a camera to mark the shooting position;

[0030] The video images captured within the field of view are reconstructed on a two-dimensional plane through projection;

[0031] The reconstructed two-dimensional planar image is converted into an editable and recognizable grayscale image to obtain the first dataset;

[0032] The video signal transmitted at the next moment is converted into an editable and recognizable grayscale image on a two-dimensional plane to obtain the second dataset.

[0033] In one embodiment of this application, comparing the second dataset with the first dataset to detect changes in the aircraft's external environment and the windshield's field of vision includes:

[0034] Compare the first dataset with the second dataset to determine if there are any differences.

[0035] In one embodiment of this application, determining that the changes in the external environment of the aircraft and the changes in the windshield's field of vision satisfy the first icing condition if the changes show visible moisture and the total temperature data is below a preset threshold includes:

[0036] If there is a difference, it indicates a change in the field of vision;

[0037] Determine whether the contours in the second dataset are greater than or equal to the recognition line;

[0038] If the contour of the second dataset is greater than or equal to the recognition line, then determine whether the temperature transmitted by the total temperature sensor is less than the preset temperature threshold.

[0039] If the temperature transmitted by the total temperature sensor is lower than the preset temperature threshold, it is determined that the environment has been encountered by a supercooled large water droplet, and the pilot is prompted to leave immediately.

[0040] Secondly, this application also provides an aircraft icing detection device, which includes:

[0041] The data acquisition module acquires a first dataset and a second dataset of the aircraft at a first time point and a second time point, respectively, and also acquires the total temperature data at the second time point. The first and second datasets include field-of-view images of the cockpit main windshield and side windshields, as well as external images or video data of the aircraft acquired through external camera devices.

[0042] The image analysis module is used to compare the second dataset with the first dataset to detect changes in the aircraft's external environment and the windshield's field of view;

[0043] The icing judgment module is used to judge the icing conditions based on the detection results of the image analysis module and the total temperature data. If the changes in the external environment of the aircraft and the windshield field of view show visible moisture, and the total temperature data is lower than a preset threshold, then the changes in the external environment of the aircraft and the windshield field of view are determined to meet the first icing condition.

[0044] Thirdly, this application also provides an aircraft comprising the aircraft icing detection method as described in any of the first aspects.

[0045] The aircraft icing detection method, device, and aircraft provided in this application first automatically acquire field-of-view images of the aircraft at two different time points and total temperature data at a second time point; then, by comparing the second dataset with the first dataset, automatically detect changes in the external environment and windshield field of view of the aircraft to identify whether visible moisture exists; finally, based on the detected field-of-view changes and total temperature data, automatically determine whether the changes in the external environment and windshield field of view of the aircraft meet a preset first icing condition, namely, the total temperature is lower than a preset threshold and there is visible moisture in the external environment and windshield field of view of the aircraft.

[0046] Therefore, this application, through these automated steps, reduces the workload of pilots in icing assessment and anti-icing operations, as pilots no longer need to continuously monitor total temperature or visually identify icing conditions, nor do they need to manually activate the anti-icing system. This automated icing detection method improves flight safety by reducing the possibility of human error and ensuring that icing conditions are identified and responded to promptly and accurately. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart of the aircraft icing detection method provided in this application;

[0049] Figure 2 This is a schematic diagram of the main windshield and side windshields provided in the embodiments of this application;

[0050] Figure 3 This is a flowchart of an embodiment of an aircraft icing detection method provided in this application;

[0051] Figure 4 This is a schematic diagram illustrating the changes within the field of view of the main windshield provided in an embodiment of this application;

[0052] Figure 5 This is a schematic diagram illustrating the changes within the field of vision of the side windshield provided in an embodiment of this application;

[0053] Figure 6 This is a schematic diagram of a data processing flow provided in an embodiment of this application;

[0054] Figure 7 This is a flowchart of an aircraft icing detection method provided in another embodiment of this application;

[0055] Figure 8 This is a schematic diagram of the aircraft icing detection device provided in this application. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0057] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein.

[0058] Pilots experience significant changes in visibility before and after encountering visible moisture and supercooled water droplets. Utilizing this physical principle, this application provides a method, device, and aircraft for detecting aircraft icing. The aim is to reduce the pilot's operational burden under icing weather conditions and eliminate safety hazards caused by human error by introducing a dominant icing detection device. The core design of this method lies in using image recognition technology to replace traditional visual observation by the pilot, automatically analyzing and determining whether the aircraft has passed through an environment containing visible moisture and automatically identifying whether it has entered icing conditions. This application can automatically perform icing weather detection tasks without pilot intervention, greatly improving detection accuracy and response speed.

[0059] The following description, in conjunction with the accompanying drawings, describes the methods, devices, and aircraft for detecting aircraft icing.

[0060] Please refer to Figure 1 , Figure 1 This is a flowchart of the aircraft icing detection method provided in this application. The aircraft icing detection method provided in this application includes the following steps:

[0061] S110: Acquire the first dataset of the aircraft at the first time point and the second dataset at the second time point, and simultaneously acquire the total temperature data at the second time point.

[0062] The first and second datasets include field-of-view images of the cockpit main windshield and side windshields, as well as external images or video data of the aircraft acquired through external camera devices.

[0063] Specifically, the system records a first dataset of images from the main and side windshields of the aircraft's cockpit at a first time point (i.e., a certain initial time point), as well as images of the aircraft's external environment acquired through external cameras. It also records a second dataset from the main windshield at a second time point (i.e., a later time point). Simultaneously, the system records the aircraft's total air temperature at the second time point. Total air temperature is the air temperature experienced by the aircraft during flight, including both static temperature (ambient temperature) and the temperature rise due to the aircraft's speed. This data (i.e., the two field-of-view images and the total air temperature data) will be used for subsequent analysis.

[0064] S120, compare the second dataset with the first dataset to detect changes in the aircraft's external environment and the windshield's field of vision.

[0065] Specifically, by comparing a second dataset of the aircraft's external environment and windshield acquired at a second time point with a first dataset acquired at a first time point, the aim is to detect whether changes have occurred in the aircraft's external environment and windshield field of view. These changes include the appearance of moisture, fog, clouds, or other meteorological conditions that may lead to icing. Changes in the field of view can be identified, for example, by calculating grayscale differences, texture changes, or other features in the images. If significant changes are detected, it indicates that the aircraft is traversing or has entered a meteorological environment that leads to icing. Such information is crucial for pilots because it helps them take timely measures, such as activating the aircraft's anti-icing system, to ensure flight safety.

[0066] S130, if the changes in the external environment of the aircraft and the windshield's field of vision show visible moisture, and the total temperature data is lower than a preset threshold, then it is determined that the changes in the external environment of the aircraft and the windshield's field of vision meet the first icing condition.

[0067] Specifically, if a comparison of the second and first datasets detects visible moisture (such as clouds, fog, or rain) in the aircraft's external environment and windshield field of view, and the total temperature data is simultaneously below a pre-set threshold (this threshold can be set based on the temperature conditions of icing weather, such as 10°C or 50°F), then the system will determine that the changes in the aircraft's external environment and windshield field of view meet the first icing condition. This means that the system considers the current environment of the aircraft to be likely to cause icing because of the presence of visible moisture and suitable temperature conditions. This determination is an important warning signal for pilots, prompting them to take appropriate anti-icing measures, such as activating the aircraft's anti-icing system, to ensure flight safety.

[0068] Therefore, the purpose of steps S110 to S130 is to use image recognition technology to automatically identify whether the current environment of the aircraft meets the icing conditions, reduce the workload of the pilot in icing judgment, improve the accuracy and efficiency of icing detection, and thus enhance flight safety.

[0069] The following is a detailed description of the embodiments.

[0070] Please refer to Figure 2 , Figure 2This is a schematic diagram of the main windshield and side windshields provided in the embodiments of this application. A light source and at least three sets of camera devices are installed at a preset position on the aircraft. One set of camera devices is used to capture the view from the main windshield, one set of camera devices is used to capture the view from the side windshields, and another set is used to capture the external surface of the aircraft. The light source is used to provide light for the camera devices.

[0071] Specifically, cameras and light sources can be installed in appropriate locations within the cockpit, based on its design features. For typical civilian aircraft, for example, three cameras and corresponding light sources can be installed on each side. One camera captures the view through the main windshield (the windshield directly in front of the pilot), one camera captures the view through the side windshields (the windshields to the pilot's side), and the other camera captures the view of the aircraft's external surfaces. During flight, these cameras and light sources monitor the views through the main and side windshields in real time. This means the system continuously records and updates these images. The system adjusts the brightness or angle of the light sources according to the flight scenario (e.g., different lighting conditions) to ensure that the images recorded by the cameras remain clear and accurate, unaffected by external light intensity.

[0072] Therefore, the camera and light source are designed to provide pilots with clear, unaffected images of the surrounding environment, facilitating flight monitoring and icing detection. In this way, the system helps pilots better understand the environment around the aircraft, especially in weather conditions where icing is possible.

[0073] Please refer to Figure 3 , Figure 3 This is a flowchart of an aircraft icing detection method according to an embodiment of this application. The aircraft icing detection method provided in this application includes the following steps:

[0074] S301, during the flight of the aircraft, the camera performs real-time monitoring.

[0075] Specifically, during flight, the camera system installed on the aircraft performs real-time monitoring. This means the cameras continuously capture and record images of the aircraft's external environment, as well as the view through the cockpit's main and side windshields, to capture any potential visual changes. The purpose of real-time monitoring is to ensure the pilot has timely access to the latest information about the aircraft's surroundings, especially in weather conditions where icing is possible. Through this continuous image recording, the system can help the pilot or automated icing detection system identify changes in the field of view, such as the presence of visible moisture, thereby determining whether anti-icing measures are necessary. This step ensures the camera system continues to operate during flight, providing the pilot with immediate visual feedback.

[0076] S302 compares the first dataset recorded by the aircraft at the first time point with the second dataset recorded at the second time point to detect changes in the aircraft's external environment and the windshield's field of vision.

[0077] Specifically, by comparing the grayscale distribution of the second dataset with that of the first dataset, the grayscale changes caused by the flow of humid air in the external environment and windshield field of view of the aircraft can be identified and quantified.

[0078] For example, please refer to Figure 4 , Figure 4 This diagram illustrates the changes in the main windshield's field of view as provided in this application embodiment. The left-hand diagram shows the main windshield camera's field of view before icing conditions, and the right-hand diagram shows the main windshield camera's field of view during icing conditions. When an aircraft traverses a visible humid environment (such as clouds, fog, or rain), the aircraft's speed relative to the water vapor causes the water vapor to flow forward relative to the aircraft. Because the water vapor flows over the main windshield, the pilot's view through the windshield becomes unclear due to the obstruction of the water vapor, resulting in reduced image brightness and grayscale changes. If the water vapor density is high enough or the aircraft speed is high enough, the water vapor can cover the entire main windshield, causing the pilot's view to become completely gray, affecting visibility and judgment of the surrounding environment. This phenomenon is an important visual signal for pilots because it indicates that the aircraft is entering or is already in weather conditions that may lead to icing. Therefore, pilots need to closely monitor changes in the field of view and take appropriate anti-icing measures as needed.

[0079] S303, determine whether the current meteorological conditions meet the first icing condition.

[0080] If a region in the second dataset with a proportion greater than or equal to a preset value exhibits grayscale changes, it is determined that visible moisture exists in the changes within the aircraft's external environment and windshield field of view, and the total temperature data is below a preset threshold. Therefore, it is determined that the changes within the aircraft's external environment and windshield field of view meet the first icing condition, and step S306 is executed. If the changes within the aircraft's external environment and windshield field of view do not meet the first icing condition, step S304 is executed.

[0081] Specifically, the preset proportion is a pre-defined threshold that indicates what percentage of an image's area must show grayscale changes to be considered as having visible moisture. This proportion can be set based on experimental or empirical data to ensure the accuracy and reliability of the detection. Grayscale changes refer to changes in the brightness of pixels in an image, which can be caused by moisture such as water vapor, fog, or clouds obscuring light. Grayscale changes can be a transition from sharp to blurry, or from color to gray. If a sufficiently large proportion of the image shows grayscale changes, the system will consider this evidence of visible moisture. The total temperature data is the air temperature sensed by the aircraft, including both static temperature and temperature rise due to aircraft speed. If the total temperature data is below a preset threshold, the system considers the ambient temperature suitable for icing.

[0082] The system considers the aircraft to be in an icing environment when both visible moisture and suitable icing temperatures are met. This determination is an important signal for the pilot, as it indicates that the aircraft is traversing or has entered a weather environment that may lead to icing. This step is an automated judgment process based on image analysis and temperature data to detect whether the aircraft is in a weather environment that could cause icing. If both conditions are met, the system will issue a warning to the pilot, prompting them to take anti-icing measures.

[0083] For example, if in the second dataset, an area showing grayscale changes at a rate greater than or equal to a pre-defined percentage (e.g., 80%), the system will determine that the changes within the main windshield's field of view indicate the presence of visible moisture. Figure 4 The attached image on the right shows a 100% area displaying grayscale changes.

[0084] S304, determine whether the first icing detection alarm corresponding to the first icing condition is activated.

[0085] If the first freezing alarm has been activated, execute S305; otherwise, return to execute S301.

[0086] Specifically, the first icing condition is a predefined condition that includes the presence of visible moisture in the field of view and suitable temperature conditions for icing. If both conditions are met, the system considers the aircraft to be in an icing environment. The first icing detection warning is an alert signal issued by the system when it detects that the first icing condition is met. Its purpose is to remind the pilot of the risk of icing and recommend appropriate anti-icing measures.

[0087] S305, if the first icing alarm has been activated, then when the first icing detection alarm disappears, the pilot is prompted to leave the icing weather that meets the first icing conditions.

[0088] In other words, if the current changes in the aircraft's external environment, windshield visibility, and total temperature data do not meet the first icing conditions, the system will check whether a first icing detection alarm has already been activated based on these conditions. If so, the system will cancel the alarm, as the current conditions no longer indicate a risk of icing. The purpose of this step is to provide a logical judgment and operational process to ensure that the system's alarm mechanism matches the current flight environment conditions, avoids unnecessary alarms, and provides feedback to the pilot on environmental changes when appropriate.

[0089] S306 issues the first icing detection warning and prompts the pilot to enter icing weather conditions that meet the first icing conditions.

[0090] In other words, if the system determines that the changes in the aircraft's external environment and the windshield's field of vision, as well as the total temperature data, meet the pre-set first icing condition, then the system will issue the first icing detection alarm and alert the pilot, indicating that they have entered an icing weather environment that meets the first icing condition. The purpose of this step is to provide a logical judgment and operational process to promptly alert the pilot when icing conditions are detected and to provide feedback on environmental changes so that the pilot can take appropriate action to ensure flight safety.

[0091] S307, acquire the third dataset at the second time point and the fourth dataset at the third time point for the cockpit side windshield, and compare the fourth dataset with the third dataset to detect changes in the field of view of the side windshield or a preset reference surface.

[0092] Specifically, the system compares the fourth dataset at the third time point with the third dataset at the second time point. By comparing the field-of-view images at these two different times, the system detects whether changes have occurred within the side windshield's field of view or on a preset reference surface. For example, it detects the presence of supercooled large water droplets. Supercooled large water droplets are water droplets that remain liquid at temperatures below freezing; their presence can cause rapid icing on the aircraft surface, posing a threat to flight safety. By comparing the field-of-view images at different times, the system can identify potentially supercooled large water droplets within the field of view.

[0093] S308, determine whether the current meteorological conditions meet the second icing condition.

[0094] If changes within the side windshield's field of vision indicate the presence of large, supercooled water droplets, the current situation is determined to meet the second icing condition, and step S311 is executed. The second icing condition is based on the first icing condition, and further determines the presence of large, supercooled water droplets within the side windshield's field of vision. If changes within the side windshield's field of vision do not meet the second icing condition, step S309 is executed.

[0095] Specifically, if the fourth dataset shows an icing area, and the area of ​​the icing area is greater than or equal to a preset threshold, then the changes within the field of view of the side windshield indicate the presence of supercooled large water droplets.

[0096] Please refer to Figure 5 , Figure 5 This is a schematic diagram illustrating the changes within the field of vision of the side windshield provided in an embodiment of this application. Figure 5 This paper presents icing criteria for supercooled large droplets (SLDs), which relate to specific conditions and thresholds for icing on aircraft windshields. Supercooled large droplets are water droplets that remain liquid at temperatures below freezing, with diameters, for example, greater than 50 micrometers. Figure 5 The left-hand appendix shows the side-windshield camera view under icing conditions in Appendix C, and the right-hand appendix shows the side-windshield camera view under icing conditions in Appendix O. Appendices C and O are technical documents or specifications in aircraft manufacturers' or aviation standards, describing different types of icing conditions. Appendix C refers to general icing conditions, while Appendix O specifically addresses icing conditions for supercooled large water droplets, i.e., more stringent icing conditions.

[0097] This application analyzes the impact limit of supercooled large water droplets (Appendix O) based on their size and physical properties, finding it to be lower than that of conventional icing conditions (Appendix C). Therefore, both Appendix C and Appendix O icing conditions have an icing limit threshold. Figure 5 The red dotted lines represent the icing thresholds for Appendix C and Appendix O. The white area (the right side) indicates windshield icing; exceeding the red dotted lines indicates sidewinder icing due to Appendix O icing conditions. The left side, mostly gray, represents conditions where visible moisture obscures the view, but not yet icing occurs, and is consistent with Appendix C icing conditions. When flight conditions exceed the red dotted lines, localized icing caused by supercooled large water droplets forms on the sidewinders. This localized icing appears as a specific icing morphology in the image, consistent with Appendix O icing conditions, indicating that sidewinder icing is caused by the supercooled large water droplet conditions of Appendix O.

[0098] S309, determine whether the second icing detection alarm corresponding to the second icing condition is activated.

[0099] If the second icing detection alarm is activated, proceed to step S310; if the second icing detection alarm is not activated, return to step S301.

[0100] S310 cancels the second icing detection warning and instructs the pilot to leave the icing weather conditions that meet the second icing conditions.

[0101] In other words, if a second icing detection alarm has already been activated based on the second icing condition, the system will cancel the alarm when it detects that the current conditions no longer meet the second icing condition. The system will also notify the pilot that they have left the icing weather environment that met the second icing condition. This step provides a logical judgment and operational procedure to ensure that the system's alarm mechanism matches the current flight environment conditions, avoids unnecessary alarms, and provides feedback to the pilot on environmental changes when appropriate.

[0102] S311 issues a second icing detection warning and prompts the pilot to enter icing weather conditions that meet the second icing conditions, and then enters the operating procedure that meets the second icing conditions.

[0103] In other words, if the system determines, through analysis of changes and relevant data within the side windshield's field of vision, that these conditions meet the pre-set second icing conditions, then the system will issue a second icing detection alarm and alert the pilots, indicating that they have entered an icing weather environment that meets the second icing conditions. Furthermore, the system will instruct the pilots to initiate appropriate operating procedures to address the icing risk.

[0104] It should be noted that the first icing condition mentioned above refers to the icing condition that meets Appendix C, and the second icing condition refers to the icing condition that meets Appendix O.

[0105] Please refer to Figure 6 , Figure 6 This is a schematic diagram of the data processing flow provided in an embodiment of this application. Multiple cameras are installed at specific locations on the aircraft, forming a camera array. These cameras capture images not only from the main windshield but also from the side windshields, as well as images or videos of the aircraft's external environment. By distributing cameras at different angles and positions, comprehensive field-of-view information is ensured. To maintain image clarity and quality under low-light conditions, light sources can be provided to illuminate the field of view. Sensors on the aircraft, such as temperature sensors, are responsible for measuring and recording the total temperature data of the air surrounding the aircraft. The field-of-view image data acquired by the camera array and the total temperature data recorded by the sensors are transmitted to the aircraft's computer system. The computer system contains one or more processors responsible for receiving and processing the input data. The processors perform in-depth analysis of the data, including using image processing techniques to identify changes in the field-of-view images and monitoring the total temperature data in real time to determine whether icing conditions are met. The analysis results are presented to the pilot via a display in the cockpit. The display can show the results of image analysis, total temperature data, and any relevant alarms or prompts, helping the pilot to fully understand the current flight environment and take appropriate action as needed.

[0106] Please refer to Figure 7 , Figure 7 This is a schematic diagram of a data processing flow provided in another embodiment of this application; the aircraft icing detection method provided in this application includes the following steps:

[0107] The S701 uses a camera to calibrate the shooting position.

[0108] Specifically, during aircraft flight, to ensure the accuracy and reliability of subsequent image acquisition, the camera's shooting position needs to be precisely calibrated. First, a series of calibration objects with known spatial coordinates are selected and placed within the camera's field of view. Then, images of the calibration objects at different angles and positions are acquired using a specific calibration algorithm. Based on the feature point information of the calibration objects in these images, combined with the camera's imaging model, the camera's internal parameters (such as focal length, principal point coordinates, etc.) and external parameters (such as rotation matrix, translation vector, etc.) are mathematically calculated to determine the camera's precise position and attitude in space. This clarifies the primary field of view, which serves as the foundation for subsequent image acquisition and processing, ensuring that the acquired images accurately reflect the actual external conditions of the aircraft.

[0109] The S702 reconstructs video images captured within the field of view onto a two-dimensional plane through projection.

[0110] Specifically, after acquiring the video image within the field of view, it needs to be transformed from three-dimensional space to a two-dimensional plane for subsequent processing. According to the imaging principle of a camera, light is focused onto the image sensor through the lens to form a two-dimensional image. Based on this principle, relevant projection transformation formulas, such as those used in a pinhole camera model, are employed to transform the coordinates of the video image pixels in three-dimensional space. In the specific calculation process, considering both the camera's internal and external parameters, the coordinates of each pixel in three-dimensional space are mapped to their corresponding positions on the two-dimensional plane, thus forming a two-dimensional planar image that facilitates subsequent processing. This two-dimensional planar image retains key information from the original video image within the field of view, including the shape, size, and positional relationships of objects, providing a foundation for subsequent image analysis.

[0111] S703 converts the reconstructed two-dimensional planar image into an editable and recognizable grayscale image, and names it the field of view t0.

[0112] Specifically, after obtaining a two-dimensional planar image, it needs to be converted into a grayscale image to facilitate subsequent image analysis and processing. A grayscale image is an image that contains only grayscale information; the grayscale value of each pixel represents the brightness of that point. The conversion process employs a specific grayscale conversion algorithm, with common algorithms including weighted average, maximum value, and average value methods. Taking the weighted average method as an example, based on the human eye's sensitivity to different colors, different weights are assigned to the red, green, and blue color channels. Then, the three color channel values ​​of each pixel are summed according to their weights to obtain the grayscale value of that pixel. In this way, the color information of each pixel in the two-dimensional planar image is converted into its corresponding grayscale value, ensuring that the image contains only grayscale information, facilitating subsequent image analysis and processing. After the conversion is complete, this image is named the field of view t0.

[0113] S704 converts the video signal transmitted in the next moment into an editable and recognizable grayscale image on a two-dimensional plane, and names it field of view t1.

[0114] In other words, the video signal transmitted at the next moment is converted into an editable and identifiable grayscale image on a two-dimensional plane using the same steps as S701-S703, and named the field of view t1. Specifically, as time progresses, the camera continuously acquires new video signals. For the video signal transmitted at the next moment, its corresponding shooting position is first calibrated according to the method in S701, that is, the spatial position and attitude of the camera at that moment are determined by the calibration algorithm and known calibration objects, thereby clarifying the new field of view. Next, according to the projection transformation method in S702, the video image pixels within the field of view are mapped from three-dimensional space to a two-dimensional plane to form a two-dimensional planar image. Finally, according to the grayscale algorithm in S703, this two-dimensional planar image is converted into a grayscale image containing only grayscale information and named the field of view t1. In this way, grayscale images of the aircraft's external environment at different times are obtained, providing a data foundation for subsequent comparative analysis.

[0115] S705, compare the grayscale images t1 and t0 to determine if there is a difference.

[0116] Specifically, to detect changes in the aircraft's external environment, it's necessary to compare grayscale images from different times. The comparison process involves comparing the grayscale values ​​of corresponding pixels in grayscale images t1 and t0, pixel by pixel. In practice, starting from the top-left pixel of the image, the grayscale values ​​of pixels at the same position in both grayscale images are compared sequentially. A difference threshold is set; if the absolute value of the difference between the grayscale values ​​of two pixels is greater than this threshold, then the two pixels are considered to have a difference. When there are pixels with different grayscale values ​​and this number or proportion reaches a certain level—for example, the number of differing pixels exceeds 10% of the total number of pixels—a difference is determined to exist. Through this comparison, changes in the image can be accurately detected, providing a basis for subsequent judgments.

[0117] If there are differences, execute S706;

[0118] If there is no difference, it means that the external environment of the aircraft is relatively stable. At this time, continue to collect and process video signals at certain time intervals, that is, return to step S704 and continuously monitor the changes in the external environment of the aircraft.

[0119] S706 indicates a change in the field of view, at which point it is determined that there may be a process of passing through clouds.

[0120] Specifically, when a difference exists between grayscale images t1 and t0, based on pre-set rules, extensive flight experiment data, and meteorological knowledge, it is assumed that the field of view has changed. During aircraft flight, cloud penetration typically causes significant changes in light and scenery within the field of view, which are reflected in the image's grayscale values. Therefore, when a difference is detected in the image, combined with relevant meteorological and flight environment characteristics, it is inferred that the aircraft may be experiencing cloud penetration.

[0121] S707 compares the position of image t1 with the built-in side windshield recognition line, that is, determines whether the outline of image t1 is greater than or equal to the recognition line.

[0122] Specifically, after determining that a cloud-crossing process may occur, to further determine whether the aircraft has entered a specific icing environment, it is necessary to compare the positional relationship between image t1 and the built-in sidewinder identification line. First, the contour information of image t1 is extracted using an image recognition algorithm. This contour information reflects the boundaries of objects in the aircraft's external environment. Then, the extracted contour of image t1 is compared with the built-in sidewinder identification line. Specific comparison methods could include calculating the distance between key points on the contour and the identification line, or determining whether the contour intersects with the identification line. Through this comparison, the relative position of the contour of image t1 and the identification line can be determined, providing a basis for subsequent icing environment assessment.

[0123] If the contour of image t1 is greater than or equal to the recognition line, then execute S708;

[0124] If the outline of image t1 is smaller than the recognition line, it indicates that the current external environment of the aircraft does not quite match the characteristics of a supercooled large water droplet icing environment. At this time, video signal acquisition and processing will continue at certain time intervals, i.e., return to step S704 to continuously monitor the changes in the external environment of the aircraft.

[0125] S708 indicates that the aircraft may have entered a supercooled environment where large water droplets are icing.

[0126] Specifically, based on the comparison between the contour of image t1 and the identification line, when the contour is greater than or equal to the identification line, and according to relevant meteorological and flight environment judgment criteria, it is inferred that the aircraft may have entered a supercooled large water droplet icing environment. In a supercooled large water droplet icing environment, due to the presence of water droplets and special meteorological conditions, the external scenery of the aircraft will exhibit specific characteristics, which will be reflected in the contour of the image. When the contour of image t1 is greater than or equal to the identification line, it indicates that the external scenery of the aircraft conforms to the characteristics of a supercooled large water droplet icing environment, and therefore it can be preliminarily determined that the aircraft may have entered this icing environment. This judgment method combines image features and meteorological knowledge, and can more accurately identify possible icing environments, providing pilots with timely early warning information.

[0127] S709 determines whether the temperature transmitted by the total temperature sensor is less than a preset temperature threshold.

[0128] If the temperature transmitted by the total temperature sensor is less than the preset temperature threshold (e.g., 10℃), proceed to step S710; if the temperature transmitted by the total temperature sensor is greater than or less than the preset temperature threshold (e.g., 10℃), it indicates that the current environment does not meet the temperature conditions of the supercooled large water droplet environment. At this time, continue to collect and process video signals at certain time intervals, i.e., return to step S704 to continuously monitor the changes in the external environment of the aircraft.

[0129] S710 determined that it had encountered a supercooled environment with large water droplets and advised the pilot to leave immediately.

[0130] Specifically, after initially determining that the aircraft may have entered a supercooled environment with large water droplets forming, a comprehensive judgment needs to be made based on temperature data transmitted by the total temperature sensor to further confirm the situation and ensure flight safety. The total temperature sensor measures the total temperature of the air surrounding the aircraft in real time. After acquiring the real-time temperature data transmitted by the sensor, it is compared with a preset temperature threshold (10°C). When this temperature data is less than 10°C, the aircraft is finally confirmed to have encountered a supercooled environment with large water droplets by combining the previous image judgment results, namely changes in the field of view and the relationship between the image outline and the recognition line. Once this environment is confirmed, the pilot is immediately alerted to leave the environment via appropriate warning devices, such as warning lights in the cockpit and a voice prompt system, to ensure flight safety.

[0131] Understandably, steps S701-S710 above, through camera calibration of the shooting position, image projection reconstruction, grayscale conversion, comparative analysis, and comprehensive judgment combined with total temperature sensor data, can monitor changes in the aircraft's external environment in real time, solving the problem of accurate detection and early warning of icing environments during flight. Its advantages are twofold: firstly, by combining image analysis technology with sensor data, the accuracy and reliability of icing detection are improved, enabling timely detection of potential icing risks; secondly, by issuing timely alerts to the pilot, it helps the pilot take appropriate measures to ensure flight safety and avoid flight accidents caused by icing problems.

[0132] Figure 7 The illustrated embodiment, compared to Figure 3 Regarding the illustrated embodiment: Figure 3 The system primarily compares the field-of-view images from the main cockpit windshield at different times, determining whether the first icing condition is met based on grayscale changes and total temperature data. It then assesses whether the second icing condition is met based on changes in the field-of-view images from the side windshields, and alerts the pilot according to the warning status. Figure 7 The system first uses camera calibration, projection reconstruction, and conversion to obtain grayscale images at different times. It then compares these grayscale images to determine if the field of view has changed and if there is a possible cloud penetration. Next, it compares the image with the position of the built-in sidewinder recognition line and uses the total temperature sensor to determine if the system has encountered an environment with excessively cold water droplets and alerts the pilot to leave. Figure 7 It focuses more on the pre-processing of images and the comprehensive judgment based on contour and temperature.

[0133] so, Figure 3 The advantage lies in its direct focus on changes in the cockpit's main windshield and side windshield views and the assessment of weather conditions. It clearly defines icing conditions through grayscale changes and total temperature data, and promptly alerts the pilot based on warning status. The logic for judging and alerting about icing weather is clear and closely integrated with actual flight operations. Figure 7The advantage is that it focuses on accurate image processing in the early stage of the judgment process, such as shooting position calibration, projection reconstruction and grayscale conversion. By comparing the differences in grayscale images, the relationship between image contours and recognition lines and the temperature of the total temperature sensor, it can make a comprehensive judgment, monitor changes in the external environment of the aircraft more comprehensively and meticulously, and thus more accurately identify supercooled large water droplet environments.

[0134] Please refer to Figure 8 , Figure 8 This is a schematic diagram of the aircraft icing detection device provided in this application. This application also provides an aircraft icing detection device 700, including a data acquisition module 710, an image analysis module 720, and an icing judgment module 730.

[0135] The data acquisition module 710 acquires a first dataset and a second dataset of the aircraft at a first time point and a second time point, respectively, and acquires total temperature data at the second time point. The first and second datasets include field-of-view images of the cockpit main windshield and side windshields, as well as external images or video data of the aircraft acquired by external camera devices.

[0136] Image analysis module 720 is used to compare the second dataset with the first dataset to detect changes in the aircraft's external environment and the windshield's field of view.

[0137] The icing judgment module 730 is used to judge the icing conditions based on the detection results of the image analysis module and the total temperature data. If the changes in the external environment of the aircraft and the windshield field of view show visible moisture, and the total temperature data is lower than a preset threshold, then the changes in the external environment of the aircraft and the windshield field of view are determined to meet the first icing condition.

[0138] For example, the image analysis module 720 is also used for:

[0139] By comparing the grayscale distribution of the second dataset with that of the first dataset, the grayscale changes caused by the passage of humid airflow in the external environment of the aircraft and within the field of view of the windshield are identified and quantified.

[0140] If a region in the second dataset that is greater than or equal to a preset proportion exhibits grayscale changes, it is determined that there is visible moisture in the changes within the external environment of the aircraft and the field of view of the windshield.

[0141] For example, the icing detection module 730 is also used for:

[0142] If the changes in the external environment of the aircraft and the field of vision of the windshield do not meet the first icing condition, then determine whether the first icing detection alarm corresponding to the first icing condition is activated.

[0143] If the first icing alarm has been activated, cancel the first icing detection alarm and prompt the pilot to leave the icing weather conditions that meet the first icing conditions.

[0144] If changes in the external environment of the aircraft and within the windshield's field of vision meet the first icing conditions, a first icing detection alarm will be issued, prompting the pilot to enter icing weather conditions that meet the first icing conditions.

[0145] For example, the image analysis module 720 is also used for:

[0146] Obtain the third dataset and the fourth dataset at the second time point from the cockpit side windshield;

[0147] Compare the fourth dataset with the third dataset to detect changes within the side windshield field of view or at a preset reference surface;

[0148] If the changes within the side windshield's field of vision show the presence of supercooled large water droplets, then the current situation is determined to meet the second icing condition. The second icing condition is a further judgment based on the first icing condition, specifically the presence of supercooled large water droplets within the side windshield's field of vision.

[0149] For example, the icing detection module 730 is also used for:

[0150] If the fourth dataset shows an icing area, and the area of ​​the icing area is greater than or equal to a preset threshold, then the changes within the field of view of the side windshield indicate the presence of supercooled large water droplets.

[0151] For example, the icing detection module 730 is also used for:

[0152] If the changes within the field of view of the side windshield do not meet the second icing condition, then determine whether the second icing detection alarm corresponding to the second icing condition is activated.

[0153] If the second icing detection alarm has been activated, cancel the second icing detection alarm and prompt the pilot to leave the icing weather that meets the second icing conditions;

[0154] For example, the icing detection module 730 is also used for:

[0155] If the changes within the field of vision of the side windshield meet the second icing condition, a second icing detection alarm will be issued and the pilot will be prompted to enter the icing weather conditions that meet the second icing condition, and then enter the operating procedure that meets the second icing condition.

[0156] For example, the aircraft icing detection device 700 is also used for:

[0157] A light source and at least three sets of cameras are installed at a predetermined location on the aircraft. One set of cameras is used to capture the view from the main windshield, one set is used to capture the view from the side windshields, and another set is used to capture the external surface of the aircraft. The light source is used to provide light for the camera devices.

[0158] For example, the aircraft icing detection device 700 is also used for:

[0159] The process of acquiring the first dataset of the aircraft at a first time point and the second dataset at a second time point, while simultaneously acquiring the total temperature data at the second time point, includes:

[0160] Use a camera to mark the shooting position;

[0161] The video images captured within the field of view are reconstructed on a two-dimensional plane through projection;

[0162] The reconstructed two-dimensional planar image is converted into an editable and recognizable grayscale image to obtain the first dataset;

[0163] The video signal transmitted at the next moment is converted into an editable and recognizable grayscale image on a two-dimensional plane to obtain the second dataset.

[0164] For example, comparing the second dataset with the first dataset to detect changes in the aircraft's external environment and the windshield's field of vision includes:

[0165] Compare the first dataset with the second dataset to determine if there are any differences.

[0166] For example, the step of determining that the changes in the external environment of the aircraft and the changes in the windshield's field of vision satisfy the first icing condition if the changes show visible moisture and the total temperature data is below a preset threshold includes:

[0167] If there is a difference, it indicates a change in the field of vision;

[0168] Determine whether the contours in the second dataset are greater than or equal to the recognition line;

[0169] If the contour of the second dataset is greater than or equal to the recognition line, then determine whether the temperature transmitted by the total temperature sensor is less than the preset temperature threshold.

[0170] If the temperature transmitted by the total temperature sensor is lower than the preset temperature threshold, it is determined that the environment has been encountered by a supercooled large water droplet, and the pilot is prompted to leave immediately.

[0171] In some embodiments, this application also provides an aircraft that includes the aircraft icing detection method described above.

[0172] Specifically, the aircraft is equipped with a cluster of sensors and cameras capable of capturing and analyzing real-time images of the main and side windshields, as well as total temperature data around the aircraft. This data is transmitted to the aircraft's computer system, which uses image processing technology to automatically identify changes within the field of view, such as the presence of visible moisture and whether the temperature is below the icing threshold. Through a built-in icing detection module, the aircraft can evaluate the collected data in real time and quickly determine whether icing conditions are met. This real-time detection capability allows the aircraft to react immediately when icing risks arise, without requiring manual pilot intervention.

[0173] Furthermore, the aircraft utilizes image processing technology to identify supercooled large water droplets (such as those larger than 50 micrometers in diameter). These droplets are not easily frozen in low-temperature environments, but they can rapidly ic up upon impact with the aircraft's surface. The aircraft's icing detection module considers not only conventional icing conditions, such as total temperature data and visible humidity, but also specifically targets supercooled large water droplets. When the system detects the presence of supercooled large water droplets and the ambient temperature and humidity conditions are suitable, it determines that the icing conditions for supercooled large water droplets are met. Once the icing conditions for supercooled large water droplets are determined, the aircraft automatically activates targeted anti-icing measures. These measures include, for example, an enhanced windshield heating system, special de-icing fluid spraying, or adjusting the flight path to avoid areas with a high concentration of supercooled large water droplets. In addition, when supercooled large water droplet icing conditions are detected, the aircraft provides clear prompts and operational instructions to the pilot through displays in the cockpit.

[0174] Automated icing detection and assessment systems can handle not only routine icing conditions but also effectively address the unique icing risks posed by large, supercooled water droplets, reducing the workload for pilots in icing assessment and anti-icing operations. Pilots can rely on real-time system feedback to focus on other critical flight missions, thereby improving overall flight efficiency and safety. Furthermore, through automated and real-time icing detection systems, aircraft can quickly activate anti-icing measures when icing conditions occur, such as activating windshield heating systems or adjusting flight attitude to prevent icing from impacting flight safety. This proactive anti-icing strategy significantly enhances the overall safety performance of aircraft.

[0175] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for detecting icing on an aircraft, characterized in that, The method includes: Acquire a first dataset of the aircraft at a first time point and a second dataset at a second time point, and simultaneously acquire total temperature data at the second time point; wherein, the first dataset and the second dataset include field-of-view images of the cockpit main windshield and side windshields, as well as external images or video data of the aircraft acquired through external camera devices; The second dataset was compared with the first dataset to detect changes in the aircraft's external environment and the windshield's field of vision. If changes in the external environment of the aircraft and the windshield's field of vision indicate visible moisture, and the total temperature data is below a preset threshold, then the changes in the external environment of the aircraft and the windshield's field of vision are determined to meet the first icing condition.

2. The aircraft icing detection method according to claim 1, characterized in that, The steps for comparing the second dataset with the first dataset include: By comparing the grayscale distribution of the second dataset with that of the first dataset, the grayscale changes caused by the passage of humid airflow in the external environment of the aircraft and within the field of view of the windshield are identified and quantified. If a region in the second dataset that is greater than or equal to a preset proportion exhibits grayscale changes, it is determined that there is visible moisture in the changes within the external environment of the aircraft and the field of view of the windshield.

3. The aircraft icing detection method according to claim 1, characterized in that, The method further includes: If the changes in the external environment of the aircraft and the field of vision of the windshield do not meet the first icing condition, then determine whether the first icing detection alarm corresponding to the first icing condition is activated. If the first icing alarm has been activated, cancel the first icing detection alarm and prompt the pilot to leave the icing weather conditions that meet the first icing conditions. If changes in the external environment of the aircraft and within the windshield's field of vision meet the first icing conditions, a first icing detection alarm will be issued, prompting the pilot to enter icing weather conditions that meet the first icing conditions.

4. The aircraft icing detection method according to claim 1, characterized in that, The method further includes: Obtain the third dataset and the fourth dataset at the second time point from the cockpit side windshield; Compare the fourth dataset with the third dataset to detect changes within the side windshield field of view or at a preset reference surface; If the changes within the side windshield's field of vision show the presence of supercooled large water droplets, then the current situation is determined to meet the second icing condition. The second icing condition is a further judgment based on the first icing condition, specifically the presence of supercooled large water droplets within the side windshield's field of vision.

5. The aircraft icing detection method according to claim 4, characterized in that, The steps for comparing the fourth dataset with the third dataset include: If the fourth dataset shows an icing area, and the area of ​​the icing area is greater than or equal to a preset threshold, then the changes within the field of view of the side windshield indicate the presence of supercooled large water droplets.

6. The aircraft icing detection method according to claim 4, characterized in that, The method further includes: If the changes within the field of view of the side windshield do not meet the second icing condition, then determine whether the second icing detection alarm corresponding to the second icing condition is activated. If the second icing detection alarm has been activated, cancel the second icing detection alarm and prompt the pilot to leave the icing weather conditions that meet the second icing conditions.

7. The aircraft icing detection method according to claim 4, characterized in that, The method further includes: If the changes within the field of vision of the side windshield meet the second icing condition, a second icing detection alarm will be issued and the pilot will be prompted to enter the icing weather conditions that meet the second icing condition, and then enter the operating procedure that meets the second icing condition.

8. The aircraft icing detection method according to claim 1, characterized in that, A light source and at least three sets of cameras are installed at a predetermined location on the aircraft. One set of cameras is used to capture the view from the main windshield, one set is used to capture the view from the side windshields, and another set is used to capture the external surface of the aircraft. The light source is used to provide light for the camera devices.

9. The aircraft icing detection method according to claim 1, characterized in that, The process of acquiring the first dataset of the aircraft at a first time point and the second dataset at a second time point, while simultaneously acquiring the total temperature data at the second time point, includes: Use a camera to mark the shooting position; The video images captured within the field of view are reconstructed on a two-dimensional plane through projection; The reconstructed two-dimensional planar image is converted into an editable and recognizable grayscale image to obtain the first dataset; The video signal transmitted at the next moment is converted into an editable and recognizable grayscale image on a two-dimensional plane to obtain the second dataset.

10. The aircraft icing detection method according to claim 9, characterized in that, The comparison of the second dataset with the first dataset to detect changes in the aircraft's external environment and the windshield's field of vision includes: Compare the first dataset with the second dataset to determine if there are any differences.

11. The aircraft icing detection method according to claim 10, characterized in that, If changes in the external environment of the aircraft and the windshield's field of vision indicate visible moisture, and the total temperature data is below a preset threshold, then determining that changes in the external environment of the aircraft and the windshield's field of vision satisfy the first icing condition includes: If there is a difference, it indicates a change in the field of vision; Determine whether the contours in the second dataset are greater than or equal to the recognition line; If the contour of the second dataset is greater than or equal to the recognition line, then determine whether the temperature transmitted by the total temperature sensor is less than the preset temperature threshold. If the temperature transmitted by the total temperature sensor is lower than the preset temperature threshold, it is determined that the environment has been encountered by a supercooled large water droplet, and the pilot is prompted to leave immediately.

12. An aircraft icing detection device, characterized in that, The device includes: The data acquisition module acquires a first dataset and a second dataset of the aircraft at a first time point and a second time point, respectively, and also acquires the total temperature data at the second time point. The first and second datasets include field-of-view images of the cockpit main windshield and side windshields, as well as external images or video data of the aircraft acquired through external camera devices. The image analysis module is used to compare the second dataset with the first dataset to detect changes in the aircraft's external environment and the windshield's field of view; The icing judgment module is used to judge the icing conditions based on the detection results of the image analysis module and the total temperature data. If the changes in the external environment of the aircraft and the windshield field of view show visible moisture, and the total temperature data is lower than a preset threshold, then the changes in the external environment of the aircraft and the windshield field of view are determined to meet the first icing condition.

13. An aircraft, characterized in that, The aircraft includes the aircraft icing detection method as described in any one of claims 1-11.

Images