Building house and outer surface hollow drone AI detection method, system and terminal

Abstract

The application relates to a building and outer facade hollow drone AI detection method, system and terminal, and relates to the technical field of drones, which comprises the following steps: acquiring the building range of a building; determining the flight height according to the building range and a preset shooting range; controlling a preset drone to fly from a preset reference parking position to the building range, and acquiring image detection information according to the flight height; determining the detection building specification according to the image detection information and a preset building feature; determining the inspection path according to the detection building specification, controlling the preset drone to fly along the inspection path, and acquiring inspection image information; forming a building model according to the inspection image information, determining the crack position according to the building model and a preset crack feature, and outputting preset abnormal information according to the crack position. The application has the effect of improving the accuracy of the inspection result.

Description

Technical Field

[0001] This invention relates to the field of drone technology, and in particular to drone AI detection methods, systems and terminals for detecting hollow areas on building facades and exterior walls. Background Technology

[0002] A drone is an unmanned aerial vehicle controlled by radio remote control equipment or its own program control device.

[0003] During the construction of a building, operators need to conduct inspections. When inspecting the exterior facade, operators first need to observe the bottom of the facade, then perform high-altitude work to inspect the facade from a higher position, and record the data. The recorded data is used to determine whether there are cracks or hollow areas on the facade.

[0004] During the inspection of the building's exterior facade, manual inspections may result in incomplete data recording, leading to errors in the inspection results. Summary of the Invention

[0005] To improve the accuracy of inspection results, this invention provides a drone AI detection method, system, and terminal for detecting hollow areas on building facades and exterior walls.

[0006] In a first aspect, the present invention provides a drone AI detection method for hollow areas on building facades and exterior walls, employing the following technical solution:

[0007] A drone-based AI method for detecting hollow areas in building facades and exterior walls includes:

[0008] Obtain the building's construction area;

[0009] The flight altitude is determined based on the building area and the preset shooting area;

[0010] Control the preset drone to fly from the preset reference docking position to the building area, and obtain image detection information according to the flight altitude;

[0011] The building specifications are determined based on image detection information and preset building features;

[0012] The inspection path is determined based on the building specifications, and the preset drone is controlled to fly along the inspection path and acquire inspection image information.

[0013] A building model is formed based on the inspection image information. The location of the crack is determined based on the building model and the preset crack features. Preset anomaly information is output based on the location of the crack.

[0014] By adopting the above technical solution, a drone flies to the building area and takes pictures of the building at the flight altitude to obtain the building specifications. Then, by detecting the building specifications, an inspection path is obtained, and the drone is controlled to obtain a building model. The model is then analyzed with crack features to determine the crack location and output anomaly information. In this way, drones can replace personnel to inspect buildings, improving the safety and efficiency of inspections, reducing the probability of incomplete data recording that may occur during human inspections, reducing labor and time costs, and improving the accuracy of inspection results.

[0015] Optionally, methods for controlling the pre-defined drone to fly along the inspection path include:

[0016] The vertical scanning position is determined based on the building specifications being inspected, and scanning information is obtained based on the vertical scanning position;

[0017] The location of the protrusion is determined based on the scan information;

[0018] The protrusion scanning path is determined based on the protrusion location and the inspection path, and the protrusion scanning information is obtained;

[0019] Update the building model based on the protrusion scan information;

[0020] The location of the marked protrusions is determined based on the updated building model and the preset protrusion features;

[0021] The system outputs a preset prompt message based on the location of the raised marker.

[0022] By adopting the above technical solution, the drone is controlled to perform a vertical scan of the vertical scanning position to obtain the protrusion position. Then, the protrusion position is scanned through the protrusion scanning path to obtain the marked protrusion position and output prompt information. In this way, the drone can be used to analyze the hollowness of the building facade and improve the accuracy of the inspection results.

[0023] Optional, also includes:

[0024] When the updated building model does not show any preset protrusion features, obtain the solar radiation information and current temperature of the building's location;

[0025] The detection range and exposure time are determined based on solar illumination information and the updated building model.

[0026] Obtain thermal image information based on the detection range;

[0027] The baseline thermal color is determined based on solar irradiation information, irradiation time, preset detection time points, and current temperature.

[0028] The location of abnormal colors is determined based on the thermal image information and the reference thermal color, and a preset prompt message is output.

[0029] By adopting the above technical solution, when the building model does not show any protruding features, the detection range and irradiation time are obtained by using solar irradiation information, current temperature, and the building model. Then, the reference thermal color is determined by using solar irradiation information, irradiation time, and manufacturing specifications. Based on the reference thermal color, the abnormal color position is selected from the thermal image information to output prompt information, thereby identifying the non-protruding hollow areas on the exterior of the building and improving the accuracy of the inspection results.

[0030] Optionally, methods after determining the location of the abnormal color include:

[0031] The irradiation temperature is determined based on the current air temperature, irradiation time, and solar irradiation information.

[0032] The thermal conductivity coefficient is determined according to the manufacturing specifications;

[0033] The heat consumption time is determined based on the current air temperature, the radiation temperature, and the preset thermal conductivity coefficient.

[0034] The heat dissipation range is determined based on the detection range and solar radiation information;

[0035] The detection time for heat dissipation is determined based on the range of heat dissipation.

[0036] When the detection time of heat dissipation coincides with the heat consumption time, the thermal image information is updated according to the heat dissipation range.

[0037] The location of the anomalous color is updated based on the updated thermal image information and the baseline thermal color.

[0038] By adopting the above technical solution, the heat consumption time is obtained by analyzing the current temperature, irradiation time, solar irradiation information and manufacturing specifications. Then, the heat dissipation range and solar irradiation information are used to obtain the heat dissipation time. When the heat dissipation time and the heat consumption time are consistent, new thermal image information and new abnormal color positions are obtained. This reduces the probability of the temperature in the hollow area being the same as the temperature on the exterior surface, thus reducing the possibility of deviations in the inspection results.

[0039] Optionally, methods after determining the detection range may also include:

[0040] The remaining detection range is determined based on the detection range and the updated building model;

[0041] The location of the marked cracks is determined based on the remaining detection range and the location of the cracks.

[0042] Crack prediction parameters are determined based on the marked crack locations and image detection information;

[0043] The baseline air pressure and blowing location are determined based on the crack prediction parameters.

[0044] Control the air pressure detection device pre-installed on the drone to blow air at the blowing position with a reference air pressure value and obtain the detected air pressure value;

[0045] When the detected air pressure value is less than the reference air pressure value, the marked crack position with the detected air pressure value less than the reference air pressure value is defined as the target crack position, and a preset prompt message is output according to the target crack position.

[0046] By adopting the above technical solution, the drone is controlled to blow air onto the cracks and obtain the detection air pressure value. When the detection air pressure value is inconsistent with the reference air pressure value, the prompt information is output according to the location of the target crack. This enables the detection of hollow areas with cracks on the facade, thereby improving the accuracy of the inspection results.

[0047] Optional, also includes:

[0048] When the remaining detection range does not include the crack location, the knocking path and initial detection location are determined based on the remaining detection range and the updated building model.

[0049] The preset detection device is controlled to adhere to the initial detection position and move according to the tapping path and the preset reference suction force.

[0050] The air pressure extension device between the tires on the detection device is controlled to tap at intervals according to the preset inflation pressure, and sound detection information is obtained.

[0051] Update sound detection information based on preset noise characteristics;

[0052] When the updated sound detection information matches the preset baseline hollow drum sound, the position of the hollow drum is determined based on the striking path, the updated sound detection information, and the baseline hollow drum sound, and a preset prompt message is output based on the position of the hollow drum.

[0053] By adopting the above technical solution, the remaining detection range is detected by controlling the detection device, and the detection device is controlled to tap at intervals and acquire sound detection information. The sound detection information is updated according to the noise characteristics. When the updated sound detection information is consistent with the reference hollow sound, the prompt information is output according to the hollow position. In this way, the hollow can be detected by sound, and the accuracy of the inspection results is improved.

[0054] Optional methods for determining inflation pressure include:

[0055] The wall specifications to be struck are determined based on the striking path and the preset manufacturing specifications.

[0056] The striking force is determined based on the specifications of the wall being struck and the striking specifications of the striking device pre-set on the detection device.

[0057] The distance to extend is determined by the force of the strike.

[0058] The inflation pressure is determined based on the extension distance.

[0059] The interval detection time is determined based on the striking force and the preset moving speed, and the air pressure extension device is controlled to inflate and deflate according to the interval detection time and the inflation pressure.

[0060] By adopting the above technical solution, the striking force and inflation pressure are obtained by measuring the striking path, manufacturing specifications, and striking specifications. The interval detection time is obtained by measuring the striking force and moving speed. The air pressure extension device is controlled to inflate and deflate the air according to the interval detection time and inflation pressure, thereby enabling the detection of hollow areas on the facade by sound.

[0061] Optionally, methods after determining the location of the void include:

[0062] The striking interval is determined based on the interval detection time and the moving speed;

[0063] The location of the sound source is determined by the striking path and striking interval;

[0064] The location of a sound source for which no sound detection information is found is defined as a recessed location.

[0065] The offset distance is determined based on the location of the dent and the preset tire position, and the drone is controlled to move the detection device by the offset distance.

[0066] Obtain pressure detection information from the gas extension device;

[0067] The force deviation value is calculated based on the pressure detection information and the preset benchmark pressure value, and the drone is controlled to move the detection device to the indentation position by the offset distance.

[0068] The extension length is determined based on the force deviation value, and the extension of the striking device preset on the detection device is controlled, while the sound detection information is reacquired.

[0069] By adopting the above technical solution, the offset distance is obtained by analyzing the sound source location and sound detection information, and the movement of the detection device is controlled. Then, the extension length is obtained by using pressure detection information and reference pressure value, and the striking device is controlled to extend to the extension length. This allows for striking of the dents on the facade, analysis of dents and dents caused by hollowness, and improvement of the accuracy of inspection results.

[0070] Secondly, this application provides a drone AI detection system for hollow areas in buildings and facades, employing the following technical solution:

[0071] A drone-based AI detection system for hollow areas in buildings and facades includes:

[0072] The acquisition module is used to acquire building range, image detection information, inspection image information, scanning information, protrusion scanning information, solar radiation information, current temperature, thermal image information, detection emission time, detection air pressure value, sound detection information, and pressure detection information;

[0073] Memory, used to store the drone AI detection method for hollow areas in buildings and facades;

[0074] A processor is used to load, execute, and implement programs stored in memory.

[0075] Thirdly, this application provides a terminal that adopts the following technical solution:

[0076] A terminal includes a memory and a processor, wherein the memory stores a drone AI detection method for detecting hollow areas in buildings and facades that can be loaded and executed by the processor.

[0077] In summary, this application includes at least one of the following beneficial technical effects:

[0078] 1. By using drones to inspect buildings to identify cracks and output abnormal information, drones can replace personnel in inspecting buildings, improving the safety and efficiency of inspections, reducing the probability of incomplete data recording that may occur during human inspections, reducing labor and time costs, and improving the accuracy of inspection results.

[0079] 2. By analyzing the current temperature, irradiation time, solar irradiation information, and manufacturing specifications, the heat consumption time is obtained. Then, by using the detection range and solar irradiation information, the heat dissipation range detection time is obtained. When the detection dissipation time is consistent with the heat consumption time, new thermal image information and new abnormal color positions are obtained, thereby reducing the probability of the temperature in the hollow area being the same as the temperature on the exterior surface and causing deviations in the inspection results.

[0080] 3. By analyzing the sound source location and sound detection information to obtain the offset distance and control the movement of the detection device, and then by using the pressure detection information and the reference pressure value to obtain the extension length, the striking device is controlled to extend to the extension length, thereby enabling the striking of the dents on the facade, analyzing the dents and dents caused by hollowness, and improving the accuracy of the inspection results. Attached Figure Description

[0081] Figure 1 This is a flowchart of the method for detecting hollow areas in buildings and facades using drone AI, according to an embodiment of the present invention.

[0082] Figure 2 This is a method flow of controlling a preset drone to fly along an inspection path according to an embodiment of the present invention. Figure 1 ;

[0083] Figure 3 This is a method flow of controlling a preset drone to fly along an inspection path according to an embodiment of the present invention. Figure 2 ;

[0084] Figure 4 This is a flowchart of the method for determining the location of abnormal colors according to an embodiment of the present invention;

[0085] Figure 5 This is the method flow after determining the detection range in this embodiment of the invention. Figure 1 ;

[0086] Figure 6 This is the method flow after determining the detection range in this embodiment of the invention. Figure 2 ;

[0087] Figure 7 This is a flowchart of the method for determining the inflation pressure according to an embodiment of the present invention;

[0088] Figure 8 This is a flowchart of the method for determining the location of the void in an embodiment of the present invention. Detailed Implementation

[0089] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments.

[0090] The drone AI detection method for hollow areas on building facades uses drones to inspect buildings and further analyzes the results based on sunlight conditions and detection devices. This allows drones to replace human inspectors, improving safety and efficiency, reducing the probability of incomplete data recording during human inspections, lowering labor and time costs, and increasing the accuracy of inspection results.

[0091] Reference Figure 1 This application discloses an AI-based drone method for detecting hollow areas on building facades and exterior walls, comprising the following steps:

[0092] Step S100: Obtain the building area of ​​the house.

[0093] The building range refers to the area of ​​buildings that the drone needs to inspect, which can be obtained by pre-entering information by the operator.

[0094] Step S101: Determine the flight altitude based on the building area and the preset shooting range.

[0095] The shooting range refers to the maximum area captured by the camera on the drone, as set by the technicians. Flight altitude refers to the minimum altitude at which the drone can capture the entire building area; the flight altitude is determined by analyzing the building area and the shooting range. The higher the flight altitude, the larger the area covered by the image captured by the drone's camera. The method for analyzing the image shooting range is common knowledge to those skilled in the art and will not be elaborated upon here.

[0096] Step S102: Control the preset drone to fly from the preset reference docking position to the building area, and obtain image detection information according to the flight altitude.

[0097] The baseline docking position is the initial docking location set by technicians for the drone. The drone is equipped with a barometric pressure monitoring device and a robotic arm for blowing air. The barometric pressure monitoring device includes pipes and an air pump. Image detection information is obtained by using the drone's camera to capture images of the building area at its flight altitude.

[0098] Step S103: Determine the building specifications based on the image detection information and preset building features.

[0099] Architectural features refer to the shape characteristics of a building during construction, as defined by technicians. Building specifications refer to the shape and dimensions of a building during construction, determined by identifying the shape and dimensions corresponding to architectural features from image detection information. Image recognition technology is common knowledge to those skilled in the art and will not be elaborated upon here.

[0100] Step S104: Determine the inspection path based on the building specifications, control the preset drone to fly along the inspection path, and acquire inspection image information.

[0101] The inspection path refers to the route taken by the drone to inspect a building. The inspection path is a spiral flight path around the building from bottom to top. The inspection path is generated by matching the detected building specifications with a pre-set inspection database, which contains the correspondence between detected building specifications and inspection paths. The inspection database is manually set and will not be elaborated upon here.

[0102] Step S105: Form a building model based on the inspection image information, determine the crack location based on the building model and preset crack features, and output preset anomaly information based on the crack location.

[0103] The facade refers to the visible wall portion of a building. Crack characteristics are features defined by technicians, including the shape and size of cracks on the facade. Anomaly information is information set by technicians to alert operators to the presence of cracks on the facade.

[0104] A building model is a three-dimensional model formed by virtual parameters of a building. It is obtained by analyzing inspection image information. The analysis methods for building models are common knowledge to those skilled in the art and will not be elaborated upon here. Crack location refers to the location of cracks on the exterior facade of the building. The crack location is determined by identifying the location corresponding to crack features from the building model, and the crack location along with the anomaly information is output to the terminal held by the operator.

[0105] Reference Figure 2 The methods for controlling a pre-set drone to fly along an inspection path include:

[0106] Step S200: Determine the vertical scanning position based on the building specifications and obtain scanning information based on the vertical scanning position.

[0107] The vertical scan position refers to the top position of the building's exterior facade. This is calculated by retrieving the reference height of the building's facade from the building specifications and then comparing the ground level with the height. The scan information refers to the dimensional information of the facade scanned vertically by the drone, using vertical distance parameters detected by an infrared device pre-installed on the drone.

[0108] Step S201: Determine the location of the protrusion based on the scan information.

[0109] A protruding location refers to a location on the facade where there is a hollow area. This is determined by retrieving the vertical distance from the scanned information and identifying locations where the vertical distance is less than the reference height.

[0110] Step S202: Determine the protrusion scanning path based on the protrusion position and the inspection path, and obtain the protrusion scanning information.

[0111] The protrusion scanning path refers to the inspection path along which the UAV scans protruding locations. It uses the protruding facade as a base, retrieves paths from the inspection path that can scan the facade, calculates the distance between the protruding location and each retrieved path, and selects the path with the smallest vertical distance to the protruding location as the protrusion scanning path. Protrusion scanning information refers to the distance parameters obtained when the UAV scans the protruding location along the protrusion scanning path during a second inspection along the inspection path and is located on the protrusion scanning path.

[0112] Step S203: Update the building model based on the protrusion scan information.

[0113] A new building model is obtained by analyzing the scan information of the protrusions. In this embodiment, if a hollow protrusion is found when the UAV scans the protrusion, the detected distance value will show an arc-shaped change trend.

[0114] Step S204: Determine the location of the marked protrusions based on the updated building model and the preset protrusion features.

[0115] A raised feature is a dimensional feature of a raised area that appears on the architectural model as defined by the technicians. Marking a raised area refers to the location of a raised area on the facade; this is done by identifying the location corresponding to the raised feature from the updated architectural model.

[0116] The warning message is set by technicians to alert operators when a facade tilts. If no protruding features appear on the building model, it indicates that the protruding facade is tilted, and a warning message is output to the operator's terminal.

[0117] Step S205: Output a preset prompt message based on the position of the raised mark.

[0118] The notification message is set by technicians to alert operators to the presence of hollow areas on the facade. The location of the raised markings and the notification message are output to the terminal held by the operator.

[0119] Reference Figure 3 The method of controlling the pre-set drone to fly along the inspection path also includes:

[0120] Step S300: When the updated building model does not have the preset protrusion features, obtain the solar radiation information and current temperature of the building's location.

[0121] Solar illumination information refers to the altitude angle, azimuth angle, and irradiance of the sun at the location of the building. This information is obtained by detecting the sun's position at the building's location using a solar tracker and a total solar radiation meter. Current temperature refers to the atmospheric temperature at the building's current location. This is determined by querying the temperature value from the meteorological station at the building's location.

[0122] Step S301: Determine the detection range and irradiation time based on the solar irradiation information and the updated building model.

[0123] The detection range refers to the area of ​​a building exposed to sunlight. It is determined by analyzing solar radiation information against an updated building model. The analysis method for the detection range is common knowledge to those skilled in the art and will not be elaborated upon here. The exposure time refers to the maximum duration of solar radiation exposure within the detection range. This is determined by timing the exposure range and using the timing result as the exposure time.

[0124] Step S302: Obtain thermal image information based on the detection range.

[0125] Thermal image information refers to thermal images of the exterior facade of buildings within the detection range. These images are obtained by using a thermal imager pre-installed on a drone to detect the area.

[0126] Step S303: Determine the baseline thermal color based on solar irradiation information, irradiation time, preset detection time point, and current temperature.

[0127] The detection time point is the time point set by the technicians for the drone to perform thermal imaging detection on the facade. In this embodiment, the system will dispatch drones with different detection functions to perform detection operations. When performing thermal imaging detection on the facade, multiple drones will be dispatched for detection.

[0128] The reference thermal color refers to the color of the facade in the thermal image information at the detection time point. It is obtained by performing thermal conduction analysis on solar irradiation information, irradiation time, and current temperature to determine the color of the facade in the thermal image information at various time points during solar irradiation. The color corresponding to the detection time point is then retrieved as the reference thermal color. The method of thermal conduction analysis is common knowledge to those skilled in the art and will not be elaborated upon here.

[0129] Step S304: Determine the location of the abnormal color based on the thermal image information and the reference thermal color, and output a preset prompt message.

[0130] Abnormal color location refers to the location in the thermal image information where the color is inconsistent with the reference thermal color. The abnormal color location is identified by the location of the color inconsistent with the reference thermal color in the thermal image information, and the prompt information is output to the operator's handheld terminal.

[0131] Reference Figure 4 Methods for determining the location of abnormal colors include:

[0132] Step S400: Determine the irradiation temperature based on the current air temperature, irradiation time, and solar irradiation information.

[0133] Manufacturing specifications refer to the materials, manufacturing processes, and specific heat capacity of the building structure as defined by technical personnel. Irradiation temperature refers to the temperature of the exterior facade after a certain period of irradiation. It is obtained by performing heat conduction analysis on the exterior facade based on the current air temperature, irradiation time, and solar radiation information to meet the manufacturing specifications. The methods for heat conduction analysis are common knowledge to those skilled in the art and will not be elaborated upon here.

[0134] Step S401: Determine the heat consumption time based on the current air temperature, irradiation temperature, and preset thermal conductivity coefficient.

[0135] The thermal conductivity coefficient is a coefficient set by technicians for heat conduction on the facade. Heat consumption time refers to the time required for the facade to reach the current temperature from the irradiated temperature. This is calculated by determining the temperature difference between the current temperature and the irradiated temperature, and then inputting this temperature difference and the thermal conductivity coefficient into a pre-set consumption database to match the heat consumption time. The consumption database contains the correspondence between temperature difference, thermal conductivity coefficient, and heat consumption time, which will not be elaborated upon here.

[0136] Step S402: Determine the heat dissipation range based on the detection range and solar irradiation information.

[0137] The heat dissipation range refers to the area on the exterior facade where heat begins to radiate per unit time. The detection range is updated by referring to the solar irradiation information at different time points in step S301, and the range corresponding to the difference between the detection range before and after the update is taken as the heat dissipation range.

[0138] Step S403: Obtain the detection time based on the heat dissipation range.

[0139] The detection dissipation time refers to the length of time it takes for the heat dissipation range to begin dissipating heat. When the heat dissipation range appears, timing begins, and the timing result is used as the detection dissipation time.

[0140] Step S404: When the detection dissipation time and heat consumption time are consistent, update the thermal image information according to the heat dissipation range.

[0141] When the detection time of heat dissipation coincides with the heat consumption time, it indicates that thermal imaging detection of the facade is possible, and thermal image information of the heat dissipation range is re-acquired.

[0142] Step S405: Update the location of the abnormal color based on the updated thermal image information and the reference thermal color.

[0143] The new abnormal color location is obtained by referring to step S304 using the updated thermal image information.

[0144] Reference Figure 5 After determining the detection range, the methods also include:

[0145] Step S500: Determine the remaining detection range based on the detection range and the updated building model.

[0146] The remaining detection range refers to the area on the facade that has not been exposed to sunlight. This is achieved by retrieving the area from the facade of the updated building model that is not part of the detection range.

[0147] Step S501: Determine the location of the marked crack based on the remaining detection range and the crack location.

[0148] Marking crack locations refers to the locations of cracks within the remaining detection range. Crack locations that fall within the remaining detection range are selected from the existing crack locations and used as the marked crack locations.

[0149] Step S502: Determine the crack prediction parameters based on the marked crack location and image detection information.

[0150] Crack prediction parameters refer to the predicted shape and size parameters of cracks. These parameters are obtained by identifying the shape and size of cracks marked at their locations from image detection information. Image recognition methods are common knowledge to those skilled in the art and will not be elaborated upon here.

[0151] Step S503: Determine the reference air pressure value and air blowing location based on the crack prediction parameters.

[0152] In this embodiment, when voids appear on the facade, cracks will form, connecting the facade and the voids and allowing air to flow between the facade and the outside environment. The reference air pressure value refers to the air pressure value when the blowing device on the drone blows air into cracks not caused by voids. This reference air pressure value is matched from a preset blowing database using crack prediction parameters. The blowing position refers to the center position of the crack. The center position of the crack shape is obtained by analyzing the crack prediction parameters and is used as the blowing position.

[0153] The air-blowing database contains the correspondence between the predicted crack parameters and the baseline air pressure value. The air-blowing database is set manually and will not be described in detail here.

[0154] Step S504: Control the air pressure detection device preset on the drone to blow air at the blowing position with a reference air pressure value and obtain the detected air pressure value.

[0155] The detection air pressure value refers to the air pressure value detected by the air pressure detection device when blowing air into the crack. When the control air pressure detection device blows air into the blowing position with the reference air pressure value, the parameter obtained by the pressure sensor preset on the air pressure detection device is used as the detection air pressure value.

[0156] Step S505: When the detected air pressure value is less than the reference air pressure value, the marked crack position with the detected air pressure value less than the reference air pressure value is defined as the target crack position, and a preset prompt message is output according to the target crack position.

[0157] The target crack location refers to the location of the crack on the facade caused by the hollow area. When the detected air pressure value is less than the reference air pressure value, it indicates that the air inside the hollow area is circulating with the outside. Therefore, the crack location marked by the detected air pressure value less than the reference air pressure value is defined as the target crack location. The target crack location and prompt information are output to the terminal held by the operator.

[0158] Reference Figure 6 After determining the detection range, the methods also include:

[0159] Step S600: If the remaining detection range does not include the crack location, determine the tapping path and initial detection location based on the remaining detection range and the updated building model.

[0160] The initial detection position refers to the highest point away from the ground in the remaining detection range. When the remaining detection range does not include the crack location, it indicates that the hollowness on the facade is not obvious. The highest point away from the ground in the remaining detection range is selected as the initial detection position.

[0161] Step S601: Based on the tapping path and the preset reference suction force, control the preset detection device to adhere to the initial detection position and move it.

[0162] The detection device is used to detect inconspicuous hollow areas on the facade. The device includes a main body, suction cups mounted on the main body for adhering to the facade, tires evenly distributed on the main body for moving the main body on the facade, and a tapping device mounted on the main body for tapping the facade. The tapping device is a hollow telescopic rod. A hollow telescopic rod is installed between the suction cups and the main body, and a marking telescopic rod is installed between the tires and the main body. The marking telescopic rod includes a hollow fixed rod and a driving rod. The fixed rod is mounted on the main body, and the driving rod is located at the end of the fixed rod furthest from the main body. A spring is installed between the tire and the fixed rod.

[0163] The main body is equipped with multiple air pumps. One air pump provides suction to the suction cup, one air pump controls the main body to move in a direction away from the exterior facade, and one air pump controls the extension of the striking device.

[0164] The reference suction force is the force set by the technician for the suction cup to adhere. The detection device is controlled to adhere at the initial detection position using the reference suction force and then move along a tapping path.

[0165] Step S602: Control the air pressure extension device between the tires on the detection device to strike at intervals according to the preset inflation pressure, and obtain sound detection information.

[0166] The air pressure extension device consists of a fixed rod and an air pump. The inflation pressure refers to the air pressure used to control the air pump connected to the fixed rod for inflation. This inflation pressure controls the air pressure extension device, which is pre-installed on the detection device, to perform intermittent tapping. Sound detection information is obtained by collecting sound parameters through a sound collection device pre-installed on the main body. The sound collection device is a microphone. The reference continuous air pressure is the air pressure set by the technician to keep the tires continuously pressed against the exterior surface. In this embodiment, when the detection device is attached to the external surface, the air pressure extension device outputs the reference continuous air pressure to keep the tires continuously pressed against the exterior surface.

[0167] Step S603: Update the sound detection information according to the preset noise characteristics.

[0168] Noise characteristics are defined by technicians as the timbre and other features of the sound produced when the exterior facade is struck by a non-impact device. Noise characteristics are removed from the sound detection information to generate new sound detection information.

[0169] Step S604: When the updated sound detection information matches the preset reference hollow drum sound, determine the hollow drum position based on the tapping path, the updated sound detection information, and the reference hollow drum sound, and output the preset prompt information based on the hollow drum position.

[0170] The baseline hollow sound is the timbre produced when a tapping device, set by technicians, strikes a hollow section of the facade. The hollow location refers to the position on the facade where a hollow area appears. When updated sound detection information matches the baseline hollow sound, it indicates a hollow area on the facade. The location where the updated sound detection information matches the baseline hollow sound is then selected from the tapping path as the hollow location, and the hollow location along with a notification message is output to the operator's terminal.

[0171] Reference Figure 7 The methods for determining inflation pressure include:

[0172] Step S700: Determine the wall specifications to be struck based on the striking path and the preset manufacturing specifications.

[0173] The wall-tapping specification refers to the specification that needs to be tapped. It is obtained by retrieving the specification of the exterior facade included in the tapping path from the manufacturing specification.

[0174] Step S701: Determine the striking force based on the wall specifications and the striking specifications of the striking device preset on the detection device.

[0175] The striking specifications refer to the material specifications of the striking device set by technicians. The striking force refers to the force required for the striking device to strike the exterior facade. The striking force is determined by matching the wall striking specifications with the striking specifications from a pre-set striking database. The striking database contains the correspondence between wall striking specifications, striking specifications, and striking forces. This database is manually set and will not be elaborated upon here.

[0176] Step S702: Determine the extension distance based on the striking force.

[0177] The spring constant is the value set by the technician to determine the spring's elasticity. The extension distance refers to the distance the spring needs to extend, which is obtained by analyzing the striking force against the preset spring constant. The method for analyzing the extension distance is common knowledge to those skilled in the art and will not be elaborated upon here.

[0178] Step S703: Determine the inflation pressure based on the extension distance, and control the air pressure extension device between the tires preset on the detection device to operate at the inflation pressure.

[0179] The inflation pressure refers to the air pressure required for the gas extension device to drive the spring to extend. The inflation pressure is matched from a preset inflation database based on the extension distance, and the gas extension device is controlled to operate at the inflation pressure. The inflation database contains the correspondence between extension distance and inflation pressure. The inflation database is manually set and will not be elaborated here.

[0180] Step S704: Determine the interval detection time based on the striking force and the preset moving speed, and control the air pressure extension device to inflate and deflate according to the interval detection time and the inflation pressure.

[0181] The moving speed is the speed at which the detection device moves as set by the technicians. The interval detection time refers to the length of time the striking device strikes at intervals. The diffusion distance refers to the range of vibration spread caused by the strike. The diffusion distance is matched with the striking force from the striking database, and the quotient of the diffusion distance and the moving speed is calculated as the interval detection time. The striking database also contains the correspondence between striking force and diffusion distance, which will not be elaborated here.

[0182] Reference Figure 8 After determining the location of the hollow area, the methods also include:

[0183] Step S800: Determine the striking interval based on the interval detection time and the moving speed.

[0184] The striking interval refers to the distance that the striking device moves when striking at intervals; the striking interval is the diffusion distance.

[0185] Step S801: Determine the location of the sound source based on the striking path and striking interval.

[0186] The sound source location refers to the point on the striking path where the striking device strikes. The striking path is divided into intervals by striking distances, and each interval is taken as the sound source location.

[0187] Step S802: Define the location of the sound source where no sound detection information appears as a recessed location.

[0188] A recessed location refers to a location on the exterior facade where a recess appears within the remaining detection range. This is defined as the location of a sound source where no sound detection information is generated.

[0189] Step S803: Determine the offset distance based on the dent location and the preset tire position, and control the drone to move the detection device by the offset distance.

[0190] The tire position is the location on the drone body where the tire is installed, as set by the technicians. The offset distance is the horizontal distance between the dented location and the tire position. The offset distance is calculated by controlling the suction cup to deflate, and then controlling the robotic arm on the drone to move the gripping and detection device according to the offset distance.

[0191] Step S804: Obtain pressure detection information from the gas extension device.

[0192] Pressure detection information refers to the air pressure value on the gas extension device, which is obtained by a pressure sensor pre-installed on the inner wall of the drive rod near the tire.

[0193] Step S805: Calculate the force deviation value based on the pressure detection information and the preset reference pressure value, and control the drone to move the detection device to the dented position by the offset distance.

[0194] When the tire is located in the depression, the reference pressure value will cause the tire to extend, resulting in an increase in the space between the fixed rod and the drive rod. The more gas contained, the lower the air pressure applied to the pressure sensor. The reference pressure value is the reference continuous air pressure in step S602. The force deviation value refers to the deviation between the pressure detection information and the reference pressure value. The force deviation value is calculated by the difference between the pressure detection information and the reference pressure value, and the drone is controlled to move the detection device to the depression position by an offset distance according to step S803.

[0195] Step S806: Determine the extension length based on the force deviation value, control the extension of the striking device preset on the detection device, and reacquire the sound detection information.

[0196] The extension length refers to the length that the striking device needs to extend. The extension length is used to control the striking device to inflate and extend, and then strike again to obtain sound detection information.

[0197] Based on the same inventive concept, embodiments of the present invention provide a drone AI detection system for hollow areas in buildings and facades, comprising:

[0198] The acquisition module is used to acquire building range, image detection information, inspection image information, scanning information, protrusion scanning information, solar radiation information, current temperature, thermal image information, detection emission time, detection air pressure value, sound detection information, and pressure detection information;

[0199] Memory, used to store the drone AI detection method for hollow areas in buildings and facades;

[0200] A processor is used to load, execute, and implement programs stored in memory.

[0201] Based on the same inventive concept, embodiments of the present invention provide a terminal, including a memory and a processor, wherein the memory stores a drone AI detection method for detecting hollow areas on building facades that can be loaded and executed by the processor.

[0202] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0203] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A drone AI detection method for hollow areas in buildings and facades, characterized in that, include: Obtain the building's floor area; The flight altitude is determined based on the building area and the preset shooting area; Control the preset drone to fly from the preset reference docking position to the building area, and obtain image detection information according to the flight altitude; The building specifications are determined based on image detection information and preset building features; The inspection path is determined based on the building specifications, and the preset drone is controlled to fly along the inspection path and acquire inspection image information. A building model is formed based on the inspection image information. The location of the crack is determined based on the building model and the preset crack features. Preset anomaly information is output based on the crack location. Methods for controlling a pre-set drone to fly along an inspection path include: The vertical scanning position is determined based on the building specifications being inspected, and scanning information is obtained based on the vertical scanning position; Determine the location of the protrusion based on the scan information; The protrusion scanning path is determined based on the protrusion location and the inspection path, and the protrusion scanning information is obtained; Update the building model based on the protrusion scan information; The location of the marked protrusions is determined based on the updated building model and the preset protrusion features; The preset prompt message is output based on the position of the raised mark; Also includes: When the updated building model does not show any preset protrusion features, obtain the solar radiation information and current temperature of the building's location; The detection range and exposure time are determined based on solar illumination information and the updated building model. Obtain thermal image information based on the detection range; The baseline thermal color is determined based on solar irradiation information, irradiation time, preset detection time points, and current temperature. The location of abnormal colors is determined based on the thermal image information and the reference thermal color, and a preset prompt message is output. Methods after determining the location of the abnormal color include: The irradiation temperature is determined based on the current air temperature, irradiation time, and solar irradiation information. The heat consumption time is determined based on the current air temperature, the radiation temperature, and the preset thermal conductivity coefficient. The heat dissipation range is determined based on the detection range and solar radiation information; The detection time for heat dissipation is determined based on the range of heat dissipation. When the detection time of heat dissipation coincides with the heat consumption time, the thermal image information is updated according to the heat dissipation range. The location of the abnormal color is updated based on the updated thermal image information and the baseline thermal color. Methods following the determination of the detection range also include: The remaining detection range is determined based on the detection range and the updated building model; The location of the marked cracks is determined based on the remaining detection range and the location of the cracks. Crack prediction parameters are determined based on the marked crack locations and image detection information; The baseline air pressure and blowing location are determined based on the crack prediction parameters. Control the air pressure detection device pre-installed on the drone to blow air at the blowing position with a reference air pressure value and obtain the detected air pressure value; When the detected air pressure value is less than the reference air pressure value, the marked crack position with the detected air pressure value less than the reference air pressure value is defined as the target crack position, and a preset prompt message is output according to the target crack position; Also includes: When the remaining detection range does not include the crack location, the knocking path and initial detection location are determined based on the remaining detection range and the updated building model. The preset detection device is controlled to adhere to the initial detection position and move according to the tapping path and the preset reference suction force. The air pressure extension device between the tires on the detection device is controlled to tap at intervals according to the preset inflation pressure, and sound detection information is obtained. Update sound detection information based on preset noise characteristics; When the updated sound detection information matches the preset baseline hollow sound, the position of the hollow sound is determined based on the striking path, the updated sound detection information, and the baseline hollow sound, and a preset prompt message is output based on the position of the hollow sound.

2. The drone AI detection method for hollow areas in buildings and facades according to claim 1, characterized in that, Methods for determining inflation pressure include: The wall specifications to be struck are determined based on the striking path and the preset manufacturing specifications. The striking force is determined based on the specifications of the wall being struck and the striking specifications of the striking device pre-set on the detection device. The distance to extend is determined by the force of the strike. The inflation pressure is determined based on the extension distance. The interval detection time is determined based on the striking force and the preset moving speed, and the air pressure extension device is controlled to inflate and deflate according to the interval detection time and the inflation pressure.

3. The drone AI detection method for hollow areas in buildings and facades according to claim 2, characterized in that, Methods following the determination of the hollow area include: The striking interval is determined based on the interval detection time and the moving speed; The location of the sound source is determined by the striking path and striking interval; The location of a sound source for which no sound detection information is found is defined as a recessed location. The offset distance is determined based on the location of the dent and the preset tire position, and the drone is controlled to move the detection device by the offset distance. Obtain pressure detection information from the gas extension device; The force deviation value is calculated based on the pressure detection information and the preset benchmark pressure value, and the drone is controlled to move the detection device to the indentation position by the offset distance. The extension length is determined based on the force deviation value, and the extension of the striking device preset on the detection device is controlled, while the sound detection information is reacquired.

4. A drone AI detection system for hollow areas in buildings and facades, characterized in that, include: The acquisition module is used to acquire building range, image detection information, inspection image information, scanning information, protrusion scanning information, solar radiation information, current temperature, thermal image information, detection emission time, detection air pressure value, sound detection information, and pressure detection information; The memory is used to store the drone AI detection method for hollow building facades as described in any one of claims 1 to 3; A processor is used to load, execute, and implement programs stored in memory.

5. A terminal, characterized in that, It includes a memory and a processor, wherein the memory stores a drone AI detection method for hollowing of buildings and facades that can be loaded by the processor and executed as described in any one of claims 1 to 3.

Images