Full-automatic intelligent ultrasonic detection system and method for cast-in-place pile

Abstract

The invention provides a full-automatic intelligent ultrasonic detection system and method for a cast-in-place pile. The detection system comprises a walking device, a mechanical arm, a camera and a control system. The walking device is provided with an automatic winding and unwinding device for winding a wire. The mechanical arm is arranged on the walking device, the ultrasonic detection device is movably arranged in the tail end guiding clamping groove, and the wire penetrates through the internal channel to be connected with the detection device. The camera is arranged on the mechanical arm and collects pile top image data; the control system recognizes the pixel coordinates of the pile center and the sounding pipe orifice according to the image, converts the physical coordinates, compares the pile center deviation, judges whether the walking equipment is in place or not, controls the mechanical arm to align after the walking equipment is in place, and drives the winding and unwinding equipment to put down the wire, so that the detection equipment vertically enters the sounding pipe to contact the bottom under the cooperation of the clamping groove and the dead weight. According to the full-automatic intelligent ultrasonic detection system and method for the cast-in-place pile, the problems that ultrasonic detection of the cast-in-place pile is high in manual dependence degree, low in efficiency and insufficient in detection data quality can be solved.

Description

Technical Field

[0001] This invention relates to the field of ultrasonic testing technology for cast-in-place piles, and in particular to a fully automated intelligent ultrasonic testing system and method for cast-in-place piles. Background Technology

[0002] With rapid economic development, the application of cast-in-place concrete piles in engineering construction is becoming increasingly widespread. As a crucial part of safety and quality inspection in engineering construction, ultrasonic testing of the integrity of cast-in-place concrete piles is required after construction. Especially in large-scale building and bridge projects, a large number of cast-in-place piles are usually constructed in a concentrated period of time. Therefore, the number of piles requiring ultrasonic testing each time is large, and the length of the cast-in-place piles is also relatively long. Furthermore, the position and number of each pile must correspond accurately with the design drawings.

[0003] Traditional ultrasonic testing methods typically require inspectors to verify drawings and confirm the location and number of the test piles. During ultrasonic testing, two inspectors are usually needed: one lowers and raises the ultrasonic transducer inside the sonic logging tube of the pile, while the other operates the data acquisition device to collect data. After the test, the ultrasonic transducer's lead wire must be retracted and wound tightly. The testing process is time-consuming, and coupled with weather and construction site factors, the work is extremely strenuous for the inspectors. Therefore, the shortcomings of traditional testing methods include: low efficiency in manual operation, high labor intensity, poor standardization, easy confusion of pile location information, and interference with data acquisition quality, affecting the authenticity and validity of the test data.

[0004] There is currently no effective solution to the problems of high reliance on manual labor, low efficiency, and insufficient data quality in ultrasonic testing of cast-in-place piles in related technologies. Summary of the Invention

[0005] The present invention provides a fully automated intelligent ultrasonic testing system and method for cast-in-place piles, which at least solves the problems of high reliance on manual labor, low efficiency, and insufficient quality of test data in ultrasonic testing of cast-in-place piles.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] This invention provides a fully automated intelligent ultrasonic testing system for cast-in-place piles, comprising: a walking device equipped with an automatic deployment and retraction device; the automatic deployment and retraction device having a wire wound around it; a robotic arm mounted on the walking device; the robotic arm having a wire routing channel inside, and a guide slot connected to the wire routing channel at its end; an ultrasonic testing device movably mounted in the guide slot; the end of the wire being connected to the ultrasonic testing device via the wire routing channel; a camera mounted on the robotic arm for real-time acquisition of pile top image data of each cast-in-place pile; and a control system mounted on the walking device for controlling the data acquisition based on the pile top image data. According to the method, the pixel coordinates of the core of each of the cast-in-place piles and the pixel coordinates of the sonic logging pipe inlet pre-embedded in the cast-in-place pile are identified. Based on the deviation between the physical coordinates obtained by converting the pixel coordinates of the core and the theoretical coordinates of the core in the cast-in-place pile drawing, it is determined whether the walking device has reached the target position. When the walking device moves to the target position, the robotic arm is controlled to move the ultrasonic testing device to the physical coordinates obtained by converting the pixel coordinates of the sonic logging pipe inlet, and the automatic take-up and put-down device is driven to lower the wire, so that the ultrasonic testing device, under the combined action of the guide slot and its own weight, vertically enters the interior of the corresponding sonic logging pipe until it touches the bottom.

[0008] Preferably, the control system includes: an image processing module connected to the camera, used to convert the color pile top image data into corresponding grayscale image data and extract gradient amplitude; a feature extraction module connected to the image processing module, used to extract the top surface target contour of each cast-in-place pile and the quantized features of each connected region in the top surface target contour based on each grayscale image data and the gradient amplitude; and a target recognition module connected to the feature extraction module, used to identify the pile body region and the sonic logging pipe region of the cast-in-place pile from each connected region based on the quantized features, and to determine the pixel coordinates of the pile core and the sonic logging pipe region of the corresponding cast-in-place pile based on the center coordinates of the pile body region and the sonic logging pipe region.

[0009] Preferably, the feature extraction module further includes: an edge detection module connected to the image processing module, used to extract the top surface target contour of each of the cast-in-place piles based on each of the grayscale image data, and output a binary edge image with a single pixel width; a repair module connected to the edge detection module, used to perform edge morphological closing operations on the binary edge image to obtain an edge image with a continuous and complete contour; and a contour feature quantization module connected to the repair module, used to perform connected component analysis and quantization processing on the edge image to extract the quantization features of each connected component; the quantization features include: size features, position features, morphological features, and grayscale features.

[0010] Preferably, the target recognition module includes: a pile body recognition module, connected to the feature extraction module, used to select regions with an average gray value greater than a first set threshold and the largest area from each of the connected components based on the quantized features, and determine them as candidate pile body regions; and a pile body determination module, connected to the pile body recognition module, used to select regions from the candidate pile body regions whose roundness and equivalent diameter both meet the set range, determine them as pile body regions, and determine the centroid of the pile body region as the pixel coordinates of the corresponding pile center.

[0011] Preferably, the target recognition module further includes: a pipe opening recognition module, connected to the feature extraction module, used to filter regions with an average gray value less than a second set threshold and an area that meets the restriction range from each of the connected components based on the quantization features, and determine them as the initial candidate set of pipe openings; and a pipe opening determination module, connected to the pipe opening recognition module, used to filter regions from the initial candidate set of pipe openings whose roundness, equivalent diameter, center position, and each center connection pattern all meet the set range, determine them as the acoustic testing pipe opening region, and determine the center coordinates of the acoustic testing pipe opening region as the pixel coordinates of the corresponding acoustic testing pipe opening.

[0012] Preferably, the control system further includes: an information extraction module, used to extract the theoretical coordinates of the pile core of each cast-in-place pile in the construction coordinate system based on the input cast-in-place pile drawings; a coordinate transformation module, connected to the information extraction module and the target recognition module, used to convert the pixel coordinates of the pile core and the sonic logging nozzle into the corresponding physical coordinates in the construction coordinate system based on the BeiDou coordinates of the walking device and the transformation matrix between the camera and the walking device and the end effector of the robotic arm; a deviation calculation module, connected to the information extraction module and the coordinate transformation module, used to calculate the planar deviation distance between the physical coordinates of the pile core and the theoretical coordinates of the pile core; and a pile position confirmation module, connected to the deviation calculation module, used to compare the planar deviation distance with a set deviation threshold, and confirm that the walking device has reached the target position when the planar deviation distance is less than or equal to the set deviation threshold.

[0013] Preferably, the control system further includes: a multi-source data acquisition module for acquiring encoder data of the automatic deployment and retraction device, ultrasonic detection data of the ultrasonic testing device, video stream data of the camera, and operating status data of the walking device, the robotic arm, and the automatic deployment and retraction device; and a display module connected to the multi-source data acquisition module for visually displaying the theoretical parameters of each cast-in-place pile, the lowering progress of the ultrasonic testing device, the ultrasonic detection data, the video footage captured by the camera, and the operating status data; wherein the lowering progress is calculated based on the encoder data and the pile length in the theoretical data of the cast-in-place pile.

[0014] Preferably, the automatic winding and unwinding device includes: a drum, a servo cable guide, and a servo motor; the drum is rotatably mounted on the traveling device; the servo cable guide is mounted on the traveling device and is parallel to the drum; the wire is wound onto the drum after being guided by the servo cable guide; the servo motor is mounted on the traveling device, and its output end is coaxially and fixedly connected to the central axis of the drum; both the servo motor and the servo cable guide are connected to the control system.

[0015] Preferably, at least two ultrasonic testing devices are provided, and the number corresponds one-to-one with the number of robotic arms and automatic take-up and take-down devices; each ultrasonic testing device is connected to one of the automatic take-up and take-down devices through a wire passing through the wiring channel of the corresponding robotic arm, forming a set of testing components.

[0016] Another aspect of the present invention provides a fully automated intelligent ultrasonic testing method for cast-in-place piles, comprising the following steps: controlling the movement of a traveling device by setting a route through a control system, and acquiring real-time image data of the pile tops of each cast-in-place pile to be tested; wherein the traveling device is equipped with an automatic deployment and retraction device, the automatic deployment and retraction device being wound with a wire; based on the pile top image data, identifying the pixel coordinates of the pile core and the sonic logging nozzle of each cast-in-place pile in real time, and converting the pixel coordinates into corresponding physical coordinates; determining whether the traveling device has reached the target position based on the deviation between the physical coordinates corresponding to the pile core and the theoretical coordinates of the pile core in the cast-in-place pile drawings; if the target position has been reached, the device is operated... The robotic arm is controlled to move the ultrasonic testing device to the physical coordinates corresponding to the acoustic tube opening. The robotic arm is mounted on a traveling device. A wiring channel is provided inside the robotic arm, and a guide slot connected to the wiring channel is provided at the end of the robotic arm. The ultrasonic testing device is movably mounted within the guide slot. The end of the wire is connected to the ultrasonic testing device via the wiring channel. Upon reaching the physical coordinates corresponding to the acoustic tube opening, the automatic take-up and release device is controlled to lower the wire, causing the ultrasonic testing device to vertically enter the corresponding acoustic tube until it touches the bottom under the combined action of the guide slot and its own weight.

[0017] Compared with the prior art, the above-described technical solution of the present invention has the following advantages:

[0018] This invention provides a fully automated intelligent ultrasonic testing system and method for cast-in-place piles. By setting up a control system combined with a camera on a robotic arm to collect real-time image data of the pile top, the system automatically identifies the pixel coordinates of the pile core and the sonic logging tube opening based on the image data and converts them into physical coordinates. These coordinates are then compared with the theoretical coordinates on the drawings to determine if the traveling device is in position. This completely replaces the manual verification of drawings, eliminates confusion in pile location numbers, and significantly improves the standardization of positioning. After the traveling device moves to the target position, the control system manipulates the robotic arm, guiding the ultrasonic testing device, originally located inside the robotic arm, to precisely align with the physical coordinates of the sonic logging tube opening under the guidance of the guide slot. Simultaneously, the automatic retractor lowers the lead wire, allowing the ultrasonic testing device to vertically enter the corresponding sonic logging tube until it touches the bottom under the combined effect of the guide slot constraint and its own weight. The entire process requires no manual lowering of the transducer, eliminating the need for an on-site operator and significantly reducing labor intensity. Secondly, the automatic deployment and retraction device of this invention can automatically complete the lowering and retraction of the wire, replacing the tedious manual wire retrieval operation, improving detection efficiency, and realizing the full automation of the detection process. It can reduce data acquisition interference caused by human intervention, ensure the verticality and stability of ultrasonic testing, and greatly improve the authenticity and validity of the detection data. At the same time, it is suitable for application scenarios of concentrated construction of a large number of long piles, solving the problems of high dependence on manual labor, low efficiency and insufficient detection data quality of traditional methods. Attached Figure Description

[0019] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention, and those skilled in the art can obtain other embodiments based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the structure of a fully automatic intelligent ultrasonic testing system for cast-in-place piles, according to an embodiment of the present invention.

[0021] Figure 2 This is a structural block diagram of the control system of the fully automatic intelligent ultrasonic testing system for cast-in-place piles, which is an embodiment of the present invention.

[0022] Figure 3 This is a schematic flowchart of a fully automated intelligent ultrasonic testing method for cast-in-place piles, according to an embodiment of the present invention.

[0023] Figure reference numerals:

[0024] 100. Walking equipment; 101. Automatic deployment and retraction equipment; 102. Positioning device; 200. Robotic arm; 201. Guide slot; 300. Camera; 400. Ultrasonic testing equipment; 500. Acoustic logging tube; 600. Cast-in-place pile; 700. Ground. Detailed Implementation

[0025] Embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0026] To address the problems of high reliance on manual labor, low efficiency, and insufficient data quality in ultrasonic testing of cast-in-place piles, this invention provides a fully automated intelligent ultrasonic testing system and method for cast-in-place piles.

[0027] Among them, such as Figure 1 As shown, the embodiment of the present invention provides a fully automatic intelligent ultrasonic testing system for cast-in-place piles, comprising: a walking device 100, equipped with an automatic retraction device 101; the automatic retraction device 101 is wound with a wire; a robotic arm 200, mounted on the walking device 100; the robotic arm 200 has a wire routing channel inside, and a guide slot 201 connected to the wire routing channel is provided at the end of the robotic arm 200; an ultrasonic testing device 400 is movably mounted in the guide slot 201; the end of the wire is connected to the ultrasonic testing device 400 through the wire routing channel; a camera 300, mounted on the robotic arm 200, is used to acquire real-time image data of the pile top of each cast-in-place pile 600; and a control system, mounted on the walking device 100. The backup device 100 is used to identify the pixel coordinates of the core of each cast-in-place pile 600 and the pixel coordinates of the sonic logging pipe inlet pre-embedded in the cast-in-place pile based on the image data of the pile top. It determines whether the walking device 100 has reached the target position based on the deviation between the physical coordinates obtained by converting the pixel coordinates of the core and the theoretical coordinates of the core in the cast-in-place pile drawings. When the walking device 100 moves to the target position, the robotic arm 200 is controlled to move the ultrasonic testing device 400 to the physical coordinates obtained by converting the pixel coordinates of the sonic logging pipe inlet, and the automatic take-up and release device 101 is driven to lower the wire, so that the ultrasonic testing device 400, under the combined action of the guide slot 201 and its own weight, vertically enters the interior of the corresponding sonic logging pipe 500 until it touches the bottom.

[0028] Specifically, the cast-in-place pile 600 is buried 700 meters below the ground. The pile body of the cast-in-place pile 600 is formed by concrete pouring, and the top of the pile is slightly higher than the ground. The sonic logging tube 500 is pre-embedded inside the pile body along the length of the cast-in-place pile 600. The detection pipe opening at the top of the tube is higher than the top of the cast-in-place pile 600, forming a detection channel that allows the ultrasonic testing equipment 400 to enter.

[0029] The walking device 100 is a carrying and moving platform with automatic walking capability and equipped with core components such as automatic retraction device 101, robotic arm 200, and control system. It can move automatically according to the instructions of the control system and accurately reach the location of the target grouting pile, providing a stable working benchmark for subsequent ultrasonic testing operations.

[0030] Furthermore, the walking device 100 can be a wheeled automated walking device 100 (such as an AGV, Automated Guided Vehicle, or AMR, Autonomous Mobile Robot), a tracked automated walking device 100 (such as a tracked robot chassis or a tracked AGV), or a multi-legged bionic walking device 100 (such as a quadruped robot dog or a hexapod bionic robot).

[0031] The automatic deployment and retraction device 101 is installed on the walking device 100. It can cooperate with the operation requirements of the ultrasonic testing device 400 to precisely control the length and speed of the wire being lowered, so as to achieve the smooth lowering of the ultrasonic testing device 400 and the safe recovery after the operation is completed. At the same time, it ensures that the wire is neatly stored and avoids tangling and messiness that may affect the operation.

[0032] The automatic winding and unwinding device 101 can be an electric winch (which drives the drum to rotate via a motor to wind up and unwind the conductor, and can precisely control the speed and stroke), an automatic winding reel (with a built-in elastic reset mechanism or motor drive, and has an automatic wire laying function, suitable for winding up and unwinding small and medium-sized conductors), a winch (a heavy-duty winding and unwinding device, adapted to the winding and unwinding needs of large-diameter, long-stroke conductors, and suitable for deep pile detection scenarios), or a servo-controlled winding and unwinding reel (equipped with a position sensor, which can provide real-time feedback on the winding and unwinding length of the conductor, and link with the control system to achieve closed-loop control).

[0033] The robotic arm 200 is mounted on the walking device 100 and has multi-degree-of-freedom motion capabilities. It is a mechanical actuator with an integrated wiring channel and a guide slot 201 at the end. According to the control system instructions, it can adjust the spatial position and attitude of the ultrasonic testing device 400 and the camera 300 at the end, so as to achieve precise alignment between the ultrasonic testing device 400 and the sonic logging pipe of the grouting pile, while providing a stable shooting angle for the camera 300.

[0034] The robotic arm 200 typically includes a base, an arm assembly, and an actuator. The base serves as the fixed foundation for the robotic arm 200, usually rigidly fixed to the traveling device 100 via bolts, welding, or a custom flange. One end of the arm assembly (composed of multiple arm sections connected by joints) is hinged to the base, and the other end is hinged to the actuator. The actuator is the end effector of the robotic arm 200, and it is equipped with a guide slot 201.

[0035] The control system sends electrical signal commands to the drive mechanisms (such as servo drives) of each joint of the robotic arm 200 to control the rotation angle, speed, and movement sequence of each joint. Each joint drive mechanism moves its corresponding arm assembly according to the commands. Through multi-joint coordinated operation, the spatial coordinates of the actuator are adjusted (to match the physical coordinates of the acoustic probe port). Simultaneously, the position sensors (such as encoders) built into the robotic arm 200 feed back the actual position of each joint to the control system in real time, forming a closed-loop control system. This ensures that the actuator drives the ultrasonic testing equipment 400 to move precisely to the target position, avoiding alignment deviations.

[0036] The ultrasonic testing device 400 is a core testing component that can move vertically along the sonic logging tube and uses the principle of ultrasonic reflection to detect the quality of the cast-in-place pile. It is connected to and guided by a conductor for signal transmission. During its movement within the sonic logging tube, the ultrasonic testing device 400 emits ultrasonic signals and receives reflected signals from the gap between the pile concrete and the logging tube, as well as from pile defects (such as voids, cracks, and mud inclusions). The detection signals are then transmitted to the control system via the conductor, providing raw data for the quality assessment of the cast-in-place pile.

[0037] Furthermore, the ultrasonic testing equipment 400 can be an ultrasonic pile transducer (divided into single-transmitter single-receiver, single-transmitter dual-receiver, etc., adapted to different diameter acoustic tubes), an integrated ultrasonic testing probe (integrating transmitting and receiving units, compact in size, and easy to move inside the acoustic tube), or a multi-channel ultrasonic testing equipment 400 (capable of simultaneously testing multiple acoustic tubes, improving testing efficiency).

[0038] Camera 300 can be an industrial color camera 300, a CCD (Charge-Coupled Device) vision camera 300, etc. Camera 300 can be directly mounted on the end of the actuator or mounted on the actuator with the aid of a bracket.

[0039] The lens of camera 300 is oriented perpendicular to the ground 700. It is used to capture real-time image data of the pile top area under a constant light source (such as a ring LED supplemental light) while the mobile device 100 is moving. The pile top image data mainly includes the outline shape and boundary range of the pile top, the flatness of the pile top surface, the location, quantity, and shape of the pre-embedded sonic logging pipes, the identification or characteristics of the central area of ​​the pile top, and auxiliary environmental information surrounding the pile top.

[0040] The control system includes at least a core processor, a drive control module, a communication module, a storage module, and a sensor feedback unit. The core processor can be an industrial-grade CPU (Central Processing Unit) or a PLC (Programmable Logic Controller), responsible for instruction processing and logic control. The drive control module can be a servo driver or a motor controller, connecting to and controlling the drive mechanisms of the walking device 100, the robotic arm 200, and the automatic retraction device 101. The communication module, such as Ethernet, CAN (Controller Area Network) bus, or a wireless communication unit, enables data transmission between components. The storage module stores drawings, test data, image data, etc., of the cast-in-place pile.

[0041] The mobile device 100 is also equipped with a positioning device 102, such as a GPS (Global Positioning System) / BeiDou positioning unit and an inertial navigation module, to assist the mobile device 100 in positioning. The positioning device 102 is electrically connected to the core processor and realizes bidirectional data interaction to transmit the spatial position coordinates and motion attitude data of the mobile device 100 to the core processor in real time. This provides a reference positioning basis for the core processor to accurately convert the pixel coordinates of the pile center and sonic logging pipe opening obtained by image recognition into physical coordinates under the construction coordinate system, by combining the intrinsic parameters of the camera 300 and the transformation matrix between the camera 300, the mobile device 100, and the robotic arm 200.

[0042] The control system sends a shooting command to the camera 300. The camera 300 continuously acquires image data of the pile top as the mobile device 100 moves and transmits it to the control system in real time. The core processor of the control system preprocesses the acquired raw images (including noise reduction, contrast enhancement, and distortion correction) to eliminate the influence of environmental interference such as construction site dust, strong light, and shadows on the images, improving image clarity and quality. Then, based on the preprocessed images, a preset algorithm (such as an edge detection algorithm to identify the pile top contour and the edge of the sonic logging pipe, a Hough circle transform algorithm to locate the center of the sonic logging pipe, and a centroid algorithm to calculate the centroid of the pile top contour, which is the pile center pixel coordinate) accurately identifies the pile center pixel coordinates and sonic logging pipe pixel coordinates of each cast-in-place pile 600. The identification results are fed back to the core processor, achieving automated and precise positioning of the pile center and sonic logging pipe, replacing manual positioning, improving positioning efficiency and accuracy, and avoiding subjective human error.

[0043] The core processor triggers the drawing input process of the control system, importing the pile drawings into the control system. The core processor of the control system autonomously identifies and extracts key engineering data such as the theoretical coordinates of the pile core from the drawings, and then stores them in the storage module. After data storage is completed, the core processor calls the aforementioned key data in the storage module and uses a preset pixel coordinate to physical coordinate conversion algorithm (combining the intrinsic parameters of camera 300, the Beidou coordinates of the walking device 100, and the conversion matrix between camera 300, walking device 100, and robotic arm 200) to convert the pixel coordinates of the pile core obtained from image recognition into actual physical coordinates in the construction coordinate system. Subsequently, the core processor calculates the deviation value between the actual physical coordinates and the theoretical coordinates of the pile core in the drawings. If the deviation value is within a preset threshold range, it is determined that the walking device 100 has reached the target position; if the deviation value exceeds the threshold, the core processor sends a position adjustment command to the drive control module of the walking device 100, driving the walking device 100 to move precisely until the deviation value meets the preset requirements.

[0044] Once the walking device 100 reaches the target position, the core processor converts the pixel coordinates of the acoustic logging port into corresponding physical coordinates. Combining this with the current posture data of the robotic arm 200, it plans the motion trajectory of the robotic arm 200 using forward and inverse kinematics algorithms. Subsequently, it sends trajectory commands to the drive control module of the robotic arm 200, controlling the coordinated movement of each joint of the robotic arm 200 to move the ultrasonic testing device 400 at the end effector to the physical coordinates of the acoustic logging port. This achieves precise alignment between the testing device and the acoustic logging port, ensuring accurate and stable movement of the robotic arm 200. It also enables automated alignment of the ultrasonic testing device 400 and the acoustic logging port, avoiding the tediousness and errors of manual alignment and improving operational efficiency.

[0045] The core processor sends a lowering command to the drive module of the automatic retracting device 101, driving the device to lower the conductor at a preset speed. The conductor moves the ultrasonic testing device 400. At this time, the guide slot 201 at the end of the robotic arm 200 restricts the lateral displacement of the testing device. Combined with the device's own weight, this allows the device to enter the sonic logging tube vertically, preventing tilting and jamming. When the bottom-contact sensor at the bottom of the ultrasonic testing device 400 detects a signal indicating contact with the bottom of the sonic logging tube (or the lowering length of the conductor reaches a preset depth threshold for the sonic logging tube), the bottom-contact signal is fed back to the core processor. The core processor then sends a stop lowering command, and the automatic retracting device 101 stops working, ensuring that the testing device reaches the designated starting position for testing and guaranteeing the accuracy of subsequent pile quality testing.

[0046] Therefore, the fully automatic intelligent ultrasonic testing system for cast-in-place piles provided by the present invention uses a control system combined with a camera 300 on a robotic arm 200 to collect real-time image data of the top of the cast-in-place pile 600. Based on the image data, the system automatically identifies the pixel coordinates of the pile core and the sonic logging pipe opening and converts them into physical coordinates. These coordinates are then compared with the theoretical coordinates on the drawings to determine whether the traveling device 100 is in position. This completely replaces the manual verification of drawings, eliminates confusion in pile position numbers, and significantly improves the standardization of positioning.

[0047] After the walking device 100 moves to the target position, the control system controls the robotic arm 200, so that the ultrasonic testing device 400, which is originally set inside the robotic arm 200, accurately corresponds to the physical coordinates of the acoustic tube opening under the guidance of the actuator guide slot 201. At the same time, the automatic take-up and put-down device 101 is driven to lower the wire, so that the ultrasonic testing device 400, under the combined action of the constraint of the guide slot 201 and its own weight, vertically enters the corresponding acoustic tube until it touches the bottom. The entire process does not require manual lowering of the transducer, saving a testing personnel on site and significantly reducing labor intensity.

[0048] Secondly, the automatic deployment and retraction device 101 provided in this invention can automatically complete the lowering and retraction of the wire, replacing the tedious manual wire retrieval operation, improving detection efficiency, and realizing the full automation of the detection process. It can reduce data acquisition interference caused by human intervention, ensure the verticality and stability of ultrasonic testing, and greatly improve the authenticity and effectiveness of detection data. At the same time, it is suitable for application scenarios of concentrated construction of a large number of long piles, solving the problems of high dependence on manual labor, low efficiency, and insufficient detection data quality of traditional methods.

[0049] Furthermore, such as Figure 2 As shown, the core processor of the control system preferably includes: an image processing module, a feature extraction module, and a target recognition module.

[0050] The image processing module is connected to the camera 300 and is used to convert the color pile top image data into the corresponding grayscale image data and extract the gradient magnitude.

[0051] The feature extraction module, connected to the image processing module, is used to extract the top surface target contour of each 600-meter-long cast-in-place pile and the quantized features of each connected region in the top surface target contour based on each grayscale image data and gradient magnitude.

[0052] The target recognition module, connected to the feature extraction module, is used to identify the pile body region and sonic logging pipe region of the cast-in-place pile 600 from each connected domain based on quantized features, and to determine the pixel coordinates of the pile center and sonic logging pipe region of the corresponding cast-in-place pile 600 based on the center coordinates of the pile body region and sonic logging pipe region.

[0053] Specifically, the camera 300 in this embodiment of the invention is preferably an industrial color camera 300, and the pile top image data directly captured by it is RGB (Red Green Blue) image data. The image processing module is used to preprocess the pile top image data captured by the camera 300, including at least image contrast enhancement processing. Preferably, Contrast Limited Adaptive Histogram Equalization (CLAHE) is used to enhance the contrast between the concrete, the pipe opening, and the soil. The processing steps preferably include the following steps:

[0054] (1) Input and Conversion. A high-resolution RGB image of the pile top surface is acquired and converted into a grayscale image according to the standard luminance perception coefficients (0.299, 0.587, 0.114). The perception coefficients conform to the ITU-R BT.601 standard and can most accurately reflect the human eye's perception of luminance, which is beneficial for subsequent luminance-based segmentation.

[0055] (2) Local contrast adaptive enhancement. The CLAHE algorithm is applied to the grayscale image. The image is divided into M×N local blocks (preferably M=N=8), and the histogram of each block is equalized after contrast limiting (Clip Limit 2.0-3.0), and the block artifact is eliminated by bilinear interpolation to obtain the enhanced image.

[0056] (3) Morphological noise suppression. In order to eliminate isolated noise and fine texture interference that may be introduced by enhancement in the enhanced image, a circular structuring element with a radius of 2 pixels is used to perform morphological opening operation to obtain the optimized grayscale image.

[0057] (4) Gradient feature extraction. Calculate the pixel gradient magnitude map of the optimized grayscale image. Use the Sobel operator to calculate the gradients in the x and y directions respectively, and obtain the comprehensive gradient magnitude by taking the square root of the sum of squares (or summing the absolute values). This step can significantly enhance the input features for subsequent edge detection.

[0058] (5) Output. The preprocessing module finally outputs the optimized grayscale image and its corresponding gradient magnitude map for use by the subsequent recognition module.

[0059] The above steps provided by the embodiments of the present invention accurately match the brightness perception characteristics of the human eye to complete the image grayscale conversion, effectively improve the regional differentiation of concrete, pipe opening and soil and eliminate block effect, suppress isolated noise and fine texture interference, significantly enhance the image edge features, and finally output the optimized grayscale image and gradient amplitude map, which greatly improves the accuracy and reliability of subsequent pile body and sonic logging pipe opening area identification.

[0060] Furthermore, the feature extraction module preferably includes: an edge detection module, connected to the image processing module, used to extract the top surface target contour of each grouting pile 600 based on each grayscale image data, and output a binary edge image with a single pixel width; a repair module, connected to the edge detection module, used to perform edge morphological closing operations on the binary edge image to obtain an edge image with a continuous and complete contour; and a contour feature quantization module, connected to the repair module, used to perform connected component analysis and quantization processing on the edge image, and extract the quantization features of each connected component; the quantization features include: size features, position features, morphological features, and grayscale features.

[0061] Specifically, the edge detection module preferably employs the Canny edge detection algorithm. Canny edge detection is performed on the preprocessed optimized grayscale image to extract the salient contours of all targets on the top surface of the cast-in-place pile. The specific implementation steps include: Gaussian smoothing. Standard deviation is used. A 5×5 Gaussian kernel is used to convolve the optimized grayscale image to suppress high-frequency noise, resulting in a smooth image. Gradient calculation: The Sobel operator is used to calculate the gradients of the smoothed image in the x and y directions, obtaining the gradient magnitude map and direction map. Non-maximum suppression: The gradient magnitude map is traversed, retaining only the pixels with the largest local magnitudes in the gradient direction, and setting the magnitudes of other pixels to zero, resulting in a refined edge response map. Double-threshold hysteresis connection: A high threshold is set to 20% of the maximum magnitude of the edge response map, and a low threshold is set to 40%. Pixels in the edge response map with magnitudes higher than the high threshold are marked as strong edges, and pixels with magnitudes between the low and high thresholds and connected to the neighborhood of strong edges are marked as weak edges and connected, finally outputting a binary edge image with a single pixel width.

[0062] The edge detection module provided in the embodiments of the present invention effectively suppresses high-frequency noise in the image by standardizing the Canny edge detection process, refines the edges to a single pixel width, and accurately filters and connects strong and weak edges of the target on the top surface of the grouting pile through dual threshold hysteresis connection. The output binary edge image can extract the significant contours of all targets with high precision, providing a reliable edge basis for subsequent connected component quantization feature extraction.

[0063] Furthermore, the repair module preferably employs edge morphological closing operations to process edge contours in binary edge images that are broken due to insignificant local grayscale changes. The specific implementation process includes: structuring element definition: Define a circular structuring element with a radius of 2 pixels. Dilation and erosion: Dilate the binary edge image using the circular structuring element to moderately thicken the edges and connect adjacent breakpoints, obtaining an intermediate image. Then, erode the intermediate image using the same circular structuring element to roughly restore the edges to their original thickness, while maintaining the connection of already connected breakpoints, ultimately obtaining the connected edge image.

[0064] The repair module provided in the embodiments of the present invention performs morphological closing operations of dilation and erosion on the binary edge image through a circular structuring element with a radius of 2 pixels. This effectively connects the edge contours that are broken due to insignificant local gray-scale changes, and outputs a continuous and complete edge image while roughly restoring the original thickness of the edge. This provides a complete edge foundation for subsequent connected component analysis and quantitative feature extraction.

[0065] Furthermore, the contour feature quantization module preferably employs contour closure and region labeling to perform connected component analysis on the edge image, identifying all connected regions formed by white pixels. For each connected region, its minimum bounding rectangle, area, and contour point set are calculated. At this point, the concrete pile body, ultrasonic testing nozzle, and surrounding soil are typically segmented into independent closed or approximately closed contour regions, i.e., connected regions. Next, through quantization processing, the quantization features of each connected region are extracted. These quantization features include: size features (pixel area, equivalent diameter, minimum bounding rectangle size), positional features (centroid pixel coordinates, bounding rectangle center coordinates), morphological features (circularity, eccentricity, compactness), and grayscale features (average grayscale value, grayscale variance, grayscale extreme values, and gradient mean).

[0066] The contour feature quantization module provided in the embodiments of the present invention performs connected component analysis on the edge image through contour closure and region marking, realizing independent connected component segmentation of the concrete pile body, sonic logging pipe opening and surrounding soil. At the same time, it calculates the minimum bounding rectangle, area and contour point set of each connected component, and extracts four types of quantization features: size, position, shape and gray level, providing structured feature data support for the accurate identification of the pile body and pipe opening in the subsequent target recognition module.

[0067] The feature extraction module provided in the embodiments of this invention, through the collaborative operation of edge detection, repair, and contour feature quantization sub-modules, first uses the Canny algorithm to accurately extract the single-pixel binary edge of the target on the top surface of the cast-in-place pile and effectively suppress noise. Then, it connects the broken contours through morphological closing operations to obtain a continuous and complete edge image. Finally, it achieves independent segmentation of the concrete pile body, the sonic logging pipe opening, and the surrounding soil through connected component analysis, and extracts four core quantification features: size, position, shape, and grayscale. This provides a complete and reliable structured feature data foundation for the subsequent target recognition module to accurately distinguish and locate the pile body and the sonic logging pipe opening area.

[0068] Furthermore, the target recognition module preferably includes: a pile body recognition module, connected to the feature extraction module, used to select regions with an average gray value greater than a first set threshold and the largest area from each connected component based on quantized features, and determine them as candidate pile body regions; and a pile body determination module, connected to the pile body recognition module, used to select regions from the candidate pile body regions whose roundness and equivalent diameter both meet the set range, determine them as pile body regions, and determine the centroid of the pile body region as the pixel coordinates of the corresponding pile center.

[0069] Furthermore, the pile body recognition module filters the concrete pile body by selecting candidate regions from all connected domains. Specifically, this includes the following steps: based on the average gray value of each connected domain in the quantification features, combined with the difference in gray value characteristics between the concrete pile body and the surrounding soil and the sonic logging pipe opening, a high threshold is preset (preferably 80%~90% of the average gray value of the concrete pile body based on sample statistics). A set of regions with an average gray value greater than the preset high threshold is selected from all connected domains. Since the concrete pile body usually appears as the largest high gray value connected domain in the pile top image, while the soil area is mostly low gray value and the sonic logging pipe opening is a small area low gray value connected domain, a set number of regions with the largest area are further selected from this set of regions as candidate regions for the pile body.

[0070] The pile body determination module first calculates the roundness of the candidate pile body region. If the value is greater than 0.8, the pile cross-section is determined to be circular. Its equivalent diameter is calculated and converted to physical dimensions using a pre-calibrated pixel-to-millimeter ratio. The module then verifies whether this falls within the allowable error range of the designed pile diameter (e.g., ±5%). If the verification passes, the candidate pile body region is confirmed as a concrete pile body region, and its centroid (Cx_p, Cy_p) is recorded as the pixel coordinates of the pile center.

[0071] The pile identification module and pile determination module provided in the embodiments of the present invention work together to efficiently screen out candidate areas of the pile body and effectively eliminate interference and false targets. After double verification, the concrete pile body area is accurately confirmed, and its centroid is accurately recorded as the pile center pixel coordinates, providing high-precision data support for the subsequent positioning and coordinate transformation of the walking equipment.

[0072] Furthermore, the target recognition module preferably includes: a pipe opening recognition module, connected to the feature extraction module, used to select regions with an average gray value less than a second set threshold and an area that meets the restriction range from each connected component based on quantized features, and determine them as the initial candidate set of pipe openings; and a pipe opening determination module, connected to the pipe opening recognition module, used to select regions from the initial candidate set of pipe openings whose roundness, equivalent diameter, center position, and the connection of each center all meet the set range, determine them as the acoustic pipe opening region, and determine the center coordinates of the acoustic pipe opening region as the pixel coordinates of the corresponding acoustic pipe opening.

[0073] The pipe opening recognition module, based on the differences in grayscale characteristics between the acoustic pipe opening and the concrete pile body and surrounding soil, first filters out areas with an average grayscale value lower than a preset low threshold (preferably 30%~50% of the average grayscale value of the concrete pile body) for all connected regions output by the contour feature quantization module. Then, combining the commonly used pipe opening size of 50mm~60mm ultrasonic testing pipes, the pixel area range [A_tube_min, A_tube_max] is calculated using the pixel-to-millimeter ratio calibrated by the camera 300, and further filters out areas whose area falls within this range. Finally, the areas that simultaneously meet the grayscale and area conditions constitute the initial candidate set of acoustic pipe openings.

[0074] The preferred steps for determining the nozzle are: circular precision detection, whereby for each initial candidate region of the acoustic nozzle, a Hough circle transform is performed on the original grayscale image within its pixel neighborhood to detect a circular contour; during the transform, the pixel radius of the circle must be strictly limited. ,in, This refers to the minimum pixel radius corresponding to the opening radius of a 50mm ultrasonic testing tube. The maximum pixel radius corresponds to the orifice radius of a 60mm ultrasonic testing tube, both calculated from the pixel-to-millimeter ratio pre-calibrated by the camera at 300. Comprehensive verification shows that for each circular contour detected by the Hough circle transform (denoted as the i-th circle, with parameters...),... ,in The x-coordinate of the circle's center is... The ordinate of the center of the circle, (where is the radius of the circle, and all three are pixel coordinates), and then perform the following triple verification in sequence:

[0075] 1. Size verification: Measure the pixel radius of the circle. 1. **Physical Diameter Verification:** The pixel-to-millimeter ratio is converted to a physical radius, and the physical diameter is calculated. This verifies whether the physical diameter falls within the commonly used 50mm~60mm diameter range for ultrasonic testing tube openings. 2. **Position Verification:** After converting the pixel boundary range of the identified candidate pile area into a physical range, the physical coordinates of the center of the i-th circle are verified to be located within the physical range of the pile, or that the straight-line distance between the center and the physical boundary of the pile does not exceed 50mm. 3. **Topology Verification:** When the number of sonic logging tubes for the 600-ton pile to be inspected is greater than or equal to 3, the physical coordinates of the center of all circular outlines that have passed size and position verifications are extracted and used to form a geometric point set. The physical side length and physical angle of the geometric figure formed by this point set are verified to be consistent with the dimensions and angle requirements of the pre-set sonic logging tube arrangement (such as a square, equilateral triangle, etc.) in the pile design drawings.

[0076] Finally, based on the results of the above triple verification, the pixel coordinates of the center of the acoustic logging nozzles that have passed all verifications were selected and compiled into a set. Where n is the final confirmed number of sonic logging nozzles, Let be the center pixel coordinates of the k-th acoustic logging nozzle, and use this to obtain the final pixel coordinates of each acoustic logging nozzle.

[0077] The pipe opening identification module and pipe opening determination module provided in the embodiments of the present invention, through collaborative operation, efficiently screen out the initial candidate set of sonic logging pipe openings and effectively eliminate irrelevant interference areas such as soil and concrete protrusions. After accurate verification, the specific location of the sonic logging pipe opening is determined, and its core pixel coordinates are accurately recorded, providing key positioning basis for the accurate alignment and automated detection operation of the subsequent ultrasonic testing device.

[0078] Furthermore, after obtaining the pixel coordinates of the pile core and sonic logging nozzle of each of the 600 cast-in-place piles, the target recognition module of this embodiment of the invention also creates a mask of the same size as the image, subtracts the candidate areas of the pile body and the small circular areas of each verified nozzle, and performs connected component analysis on the remaining pixels. The top N areas with the largest areas (usually N=1 or 2) are identified as the surrounding soil areas, thus completing scene understanding. Finally, the pixel coordinates of the pile core and sonic logging nozzle, as well as the pile body boundary contour, are output uniformly, providing an absolute spatial reference for subsequent navigation of the walking device and transducer alignment.

[0079] Furthermore, combined Figure 2 As shown, the control system of this invention preferably includes: an information extraction module, used to extract the theoretical coordinates of the pile core of each pile in the construction coordinate system based on the input pile drawings; a coordinate transformation module, connected to the information extraction module and the target recognition module, used to convert the pixel coordinates of the pile core into the corresponding physical coordinates in the construction coordinate system based on the Beidou coordinates of the walking device 100, the transformation matrix between the camera 300 and the walking device 100 and the end effector of the robotic arm; a deviation calculation module, connected to the information extraction module and the coordinate transformation module, used to calculate the planar deviation distance between the physical coordinates and the theoretical coordinates of the pile core; and a pile position confirmation module, connected to the deviation calculation module, used to compare the planar deviation distance with a set deviation threshold, and confirm that the walking device 100 has reached the target position when the planar deviation distance is less than or equal to the set deviation threshold.

[0080] Furthermore, the information extraction module receives pile drawings (such as pile foundation CAD design drawings, supporting mainstream engineering drawing formats such as DXF and DWG). Based on preset drawing layer definition rules and attribute field mapping relationships, it automatically identifies and locates target layers in the drawings, such as the pile position number layer and the pile core design coordinate layer. It then reads the unique pile position number of the currently inspected pile 600 from the attribute database associated with the layer, as well as its corresponding theoretical plane coordinates in the design and construction coordinate system. , The module also has a coordinate validity verification function. By comparing the extracted coordinates with the preset coordinate range of the project, it ensures the accuracy of the data. Combined with the inspection task list issued by the system, it completes the accurate matching of the pile position number to be inspected with the theoretical coordinates. Finally, it outputs the structured pile position number and theoretical plane coordinate data for subsequent coordinate transformation module and deviation calculation module to call.

[0081] The coordinate transformation module is also connected to the positioning device 102. After receiving the pixel coordinates of the pile center, it first performs distortion correction and normalization of the pixel coordinates based on the pre-calibrated intrinsic parameter matrix and distortion coefficients of the camera 300, converting them into coordinates in the camera 300 coordinate system. Then, through the transformation matrix between the camera 300, the walking device 100, and the actuator, it realizes the coordinate mapping from the camera 300 coordinate system to the walking device 100 coordinate system. Finally, combined with the BeiDou coordinates of the walking device 100 sent by the positioning device 102 (i.e., the pose of the walking device 100 in the construction coordinate system), it transforms the pile center coordinates in the walking device 100 coordinate system into physical coordinates in the construction coordinate system through coordinate system transformation, completing the coordinate transformation from the pixel dimension to the physical construction dimension.

[0082] The transformation matrices between camera 300, mobile device 100, and actuator are all 4×4 homogeneous transformation matrices describing the rigid transformation relationship between the two coordinate systems. Their core function is to establish a precise mapping between the coordinate systems of camera 300, mobile device 100, and actuator, enabling cross-system coordinate transformation. Specifically, the transformation matrix between camera 300 and mobile device 100 is used to correlate the relative poses of the two carriers. This can be achieved through static calibration, where a standard calibration plate is fixed at a known construction coordinate position. The mobile device 100 is controlled to stop, and the camera 300 photographs the calibration plate. By combining the physical dimensions of the calibration plate and the image pixel coordinates, the rotation and translation parameters of camera 300 relative to the coordinate system of mobile device 100 are calculated, thus obtaining the transformation matrix between camera 300 and mobile device 100.

[0083] The transformation matrix between the camera 300 and the actuator (i.e., the hand-eye transformation matrix) is used to associate the relative pose of the camera 300 and the actuator (such as the ultrasonic detection probe drive mechanism). The actuator can drive the calibration target to move in different poses through the hand-eye calibration method (such as the Tsai-Lenz algorithm). The camera 300 simultaneously captures images of the target. The relative transformation relationship between the camera 300 and the actuator end is calculated through multiple sets of pose data. After calibration, the data is stored in the system as fixed parameters for subsequent coordinate transformations.

[0084] The deviation calculation module calculates the planar deviation distance between the physical coordinates and the theoretical coordinates of the pile core using the following formula:

[0085] .

[0086] .

[0087] .

[0088] in, , These are the theoretical coordinate components of the core of the cast-in-place pile in the construction coordinate system. , The visual physical coordinate components of the pile core pixel coordinates in the construction coordinate system after being transformed by the coordinate transformation module; , The components representing the positional deviations between the visual physical coordinates and theoretical coordinates of the pile core along the X-axis and axial direction of the construction coordinate system. This is the combined planar deviation distance between the visual physical coordinates and the theoretical coordinates of the pile core.

[0089] The pile location confirmation module uses a threshold judgment method to confirm the pile location. The specific logic is as follows: First, set the allowable positioning tolerance threshold according to the engineering specifications. (The preferred value is 100mm), then the deviation calculation module outputs the pile core comprehensive plane deviation distance. With this positioning tolerance threshold Perform a comparison and judgment; if satisfied If the signal is received, the mobile device 100 is determined to have accurately reached the target pile position. The module then outputs a "pile position confirmed successfully" signal, which will serve as a trigger command to start the subsequent fully automatic ultrasonic testing process.

[0090] The embodiments of this invention provide a control system that, through the coordinated operation of an information extraction module, a coordinate transformation module, a deviation calculation module, and a pile position confirmation module, realizes the extraction of theoretical pile positions of cast-in-place piles, the conversion of pixel coordinates to construction physical coordinates, the calculation of pile position deviations, and the automatic confirmation of the target pile position of the walking equipment. This provides high-precision and high-reliability pile position positioning support for the smooth start of the subsequent fully automatic ultrasonic testing process.

[0091] Furthermore, the control system of the present invention preferably includes: a multi-source data acquisition module for acquiring encoder data of the automatic deployment and recovery device 101, ultrasonic detection data of the ultrasonic testing device 400, video stream data of the camera 300, and operating status data of the walking device 100, the robotic arm 200, and the automatic deployment and recovery device 101; and a display module connected to the multi-source data acquisition module for visually displaying the theoretical parameters of each cast-in-place pile 600, the lowering progress of the ultrasonic testing device 400, ultrasonic detection data, video footage captured by the camera 300, and operating status data; wherein the lowering progress is calculated based on the encoder data and the pile length in the theoretical data of the cast-in-place pile 600.

[0092] Furthermore, the encoder data of the automatic take-up and unwinding device 101. The encoder is integrated into the drum drive motor shaft or cable tension detection shaft of the automatic take-up and unwinding device 101. The multi-source data acquisition module acquires the encoder's pulse count or absolute position data in real time through the encoder's pulse output interface or digital communication interface (such as RS485). The module has built-in equipment transmission ratio and drum diameter parameters, and can synchronously correlate the acquired data with the cable unwinding length calculation, providing a basis for subsequent unwinding progress derivation.

[0093] The ultrasonic testing data of the ultrasonic testing equipment 400 includes: the acoustic time-domain waveform and acoustic parameters of the ultrasonic host; the multi-source data acquisition module establishes a connection with the ultrasonic host through Ethernet or RS232 / 485 dedicated communication interface, and reads the digital quantization data of the acoustic time-domain waveform (i.e., the voltage signal time series of ultrasonic echo) generated by the ultrasonic host in real time according to the preset device communication protocol, as well as the acoustic parameters (including acoustic time, amplitude, dominant frequency, acoustic attenuation coefficient, etc.) calculated by the host's built-in algorithm; during the acquisition process, the module performs real-time caching and format standardization of the data to ensure data integrity.

[0094] The industrial camera 300 connects to the multi-source data acquisition module via a dedicated industrial interface such as GigE Vision or USB 3.0. The module acquires the raw video stream data output by the camera 300 in real time (supporting formats such as RAW and JPEG) according to the camera 300's communication protocol (such as the GigE Vision protocol). During the acquisition process, the module can perform real-time decoding or frame buffering of the video stream according to system requirements to ensure the continuity and clarity of the video image and meet the visualization presentation requirements of the display module.

[0095] The system collects operational status data for the mobile device 100, robotic arm 200, and automatic take-up and take-down device 101, including the battery level, temperature, and servo status signals of each device. Specifically, the battery level data is acquired by having the battery management system (BMS) of the mobile device 100, the power management modules of the robotic arm 200, and the automatic take-up and take-down device 101 output data such as remaining battery power, bus voltage, and operating current via RS485 / Modbus communication interfaces. The multi-source data acquisition module then reads this data in real time through the corresponding communication interface.

[0096] Temperature data is obtained by installing temperature sensors (such as PT100 RTDs and DS18B20 digital temperature sensors) on key components such as motors, controllers, and drive units of the three types of equipment. The analog or digital signals output by the sensors are connected to the analog input channel or digital communication interface of the acquisition module, and the module collects and converts them into temperature values ​​in real time.

[0097] The servo status signals are acquired as follows: the drive motor of the walking device 100, the joint servo motor of the robotic arm 200, and the drum servo motor of the automatic take-up and untake-down device 101 will output digital status signals such as ready, running, fault, and limit. These signals are connected to the multi-source data acquisition module through the switch input interface. The module obtains the servo status of the device in real time by detecting the high and low levels of the signals.

[0098] The lowering progress is calculated based on the encoder data of the automatic lowering and retracting device 101 and the pile length in the theoretical data of the cast-in-place pile. The display module interface adopts a structured layout with different functional areas as follows: Static information area, which persistently displays the number of the currently inspected pile, design coordinates, geometric parameters, and inspection tube layout diagram, intuitively presenting the theoretical parameters of the cast-in-place pile; Dynamic progress area, which displays the current depth H of the transducer and the progress according to the formula in real time and animation using a virtual ruler and progress bar. The system calculates the percentage of the detection progress P (where L is the theoretical pile length of the cast-in-place pile). When the transducer touches the bottom, the percentage of progress P automatically returns to zero, dynamically displaying the lowering progress of the ultrasonic testing equipment 400. The data visualization area displays the real-time received waveform window and the acoustic parameter-depth growth curve window side by side. The curve extends and is drawn in real time as the transducer is raised, visually presenting the ultrasonic testing data. The equipment status area uses color icons and an instrument panel to display the total power of the device, the servo status of each axis, and the status of the alignment mechanism, centrally displaying the operating status data. The scene video area embeds real-time video footage captured by the camera 300, and can overlay the identified augmented reality (AR) marker boxes of the pile body and pipe opening, clearly presenting the video footage from the camera 300.

[0099] The multi-source data acquisition module and display module of this invention work together to achieve comprehensive acquisition and integrated visualization of key data throughout the entire detection system process, providing core support for real-time monitoring, progress tracking and status control of the detection process, and greatly improving the human-computer interaction efficiency and overall controllability of the detection operation.

[0100] Furthermore, the control system in this embodiment of the invention also includes an alarm module. During the operation of the detection system, the background monitoring thread continuously compares real-time data with rule thresholds: if the torque of any servo motor exceeds 150% of its rated value, a "stuck" alarm is triggered, and the system automatically stops. When the alarm is triggered, a warning window pops up on the interface, a log with timestamps and complete context data is recorded, and the video module is activated to capture images of the scene.

[0101] Furthermore, the control system synchronizes and stores all monitoring data (depth, progress, waveform, status, video frames, alarms) with high precision along a unified timeline. Users can click on alarm records or abnormal curve points to retrieve the depth, waveform screenshots, and on-site video footage at that moment with a single click, enabling full-chain traceability.

[0102] Furthermore, the automatic winding and unwinding device 101 of this invention includes: a drum, a servo cable guide, and a servo motor. The drum is rotatably mounted on the traveling device 100; the servo cable guide is mounted on the traveling device 100 and parallel to the drum; the wire is wound onto the drum after being guided by the servo cable guide; the servo motor is mounted on the traveling device 100, and its output end is coaxially and fixedly connected to the central axis of the drum; both the servo motor and the servo cable guide are connected to the control system.

[0103] Specifically, the drum is made of high-strength, lightweight alloy material and is rotatably supported on the dedicated frame of the traveling device 100 via high-precision deep groove ball bearings. The surface of the drum is machined with spiral grooves that match the specifications of the wires to constrain the winding trajectory of the wires. The servo wire guide is a screw-slide-table precision wire guiding structure, with wear-resistant ceramic wire guiding wheels mounted at the end of the slide. The entire structure is parallel to the axis of the drum and fixed to the frame of the traveling device 100, maintaining a preset distance from the drum to ensure wire guiding accuracy. The signal transmission line of the ultrasonic detection probe and the power integrated wire are guided by the guide wheels of the servo wire guide and completed in an orderly manner before being wound into the spiral grooves of the drum. The servo motor is a high-response permanent magnet synchronous servo motor, which is coaxially fixedly connected to the central shaft of the drum through a rigid coupling. The output torque can directly drive the drum to rotate. Both the servo motor and the servo wire guide communicate bidirectionally with the control system through a digital pulse command interface and an encoder feedback interface. The control system can achieve synchronous motion control based on the encoder feedback data of both, ensuring precise matching between the wire guiding action and the drum speed during the wire winding and unwinding process.

[0104] The automatic take-up and take-up device 101 provided by the present invention realizes the orderly take-up and take-up of the detection wire and precise length control, effectively avoiding the problems of wire tangling, knotting or messy wires, ensuring that the ultrasonic detection probe is lowered and raised synchronously and smoothly with the wire, accurately responding to the action commands of the control system, and providing reliable equipment support for the real-time calculation of the lowering progress of the ultrasonic detection equipment 400 and the automated advancement of the entire detection process.

[0105] Furthermore, at least two ultrasonic testing devices 400 are provided, and their number corresponds one-to-one with the number of robotic arms 200 and automatic take-up and take-down devices 101. Each ultrasonic testing device 400 is connected to an automatic take-up and take-down device 101 through a wire passing through the wiring channel of the corresponding robotic arm 200, forming a set of testing components.

[0106] Specifically, the number of ultrasonic testing devices 400 matches the design number of acoustic logging tubes 500 for the cast-in-place pile to be inspected, and at least two are set up. During the inspection process, each ultrasonic testing device 400 works in concert with the transmitting probe and the receiving probe to realize the quality inspection of the cast-in-place pile by utilizing the propagation characteristics of ultrasonic waves in the concrete medium.

[0107] The number of ultrasonic testing devices 400 corresponds strictly one-to-one with the number of robotic arms 200 and automatic take-up and take-down devices 101 configured on the walking device 100. Each ultrasonic testing device 400 is independently connected to a dedicated wear-resistant integrated wire. The wire passes through the pre-set smooth wear-resistant wire routing channel inside the corresponding robotic arm 200 (the inner wall of the channel is embedded with a polytetrafluoroethylene wear-resistant bushing to reduce wire wear and friction resistance), and finally winds and connects to the spiral wire groove of the reel of an automatic take-up and take-down device 101 to form an independent testing component. The servo motor, servo cable guide and joint servo drive unit of each testing component are independently connected to the control system, supporting independent motion control of a single component and synchronous collaborative control of multiple components.

[0108] The detection system provided by the embodiments of the present invention realizes independent and precise control of each group of detection components and synchronous collaborative operation of multiple groups of components, ensuring that each ultrasonic detection device 400 can accurately correspond to the target acoustic tube, while completely avoiding the mutual interference between the conductors, greatly improving the operation efficiency, alignment accuracy and overall fault tolerance of multi-channel ultrasonic detection, and providing core structural guarantee for the synchronous and batch intelligent detection of cast-in-place piles 600.

[0109] like Figure 3 As shown in the figure, the present invention provides a fully automatic intelligent ultrasonic testing method for cast-in-place piles, which can be applied to the fully automatic intelligent ultrasonic testing system for cast-in-place piles provided in the above embodiments, including the following steps S1 to S5.

[0110] Step S1: The walking device 100 is moved by setting a route through the control system, and the pile top image data of each cast-in-place pile 600 to be tested are collected in real time; wherein, the walking device 100 is equipped with an automatic take-up and take-down device 101, and the automatic take-up and take-down device 101 is wound with a wire.

[0111] Step S2: Based on the pile top image data, identify the pixel coordinates of the pile core and sonic logging nozzle of each 600-meter-long cast-in-place pile in real time, and convert the pixel coordinates into the corresponding physical coordinates.

[0112] Step S3: Based on the deviation between the physical coordinates corresponding to the pile core and the theoretical coordinates of the pile core in the pile drawing, determine whether the traveling device 100 has reached the target position.

[0113] Step S4: Upon reaching the target position, the robotic arm 200 is manipulated to move the ultrasonic testing device 400 to the physical coordinates corresponding to the acoustic tube opening. The robotic arm 200 is mounted on the walking device 100. The robotic arm 200 has a wiring channel inside, and the end of the robotic arm 200 has a guide slot 201 that communicates with the wiring channel. The ultrasonic testing device 400 is movably mounted in the guide slot 201. The end of the wire is connected to the ultrasonic testing device 400 through the wiring channel.

[0114] Step S5: Upon reaching the physical coordinates corresponding to the acoustic tube opening, the automatic take-up and take-down device 101 is operated to lower the lead wire, so that the ultrasonic testing device 400, under the combined action of the guide slot 201 and its own weight, vertically enters the interior of the corresponding acoustic tube 500 until it touches the bottom.

[0115] The fully automated intelligent ultrasonic testing method for cast-in-place piles provided in this invention relies on the hardware architecture and control logic of the testing system described in the previous embodiment. Similar features can be found in the previous testing system embodiment. This method effectively solves technical problems in traditional ultrasonic testing of cast-in-place piles, such as large deviations between manual pile positioning and acoustic logging nozzles, insufficient alignment accuracy of the robotic arm 200, and easy tilting and jamming during probe lowering. It achieves fully automated operation from path planning and pile top image acquisition by the walking device 100, coordinate identification and conversion of the pile core and acoustic logging nozzle, automatic pile position confirmation, to precise alignment of the robotic arm 200 and vertical and stable lowering of the probe. This significantly improves the positioning accuracy, operational efficiency, and process stability of the testing operation, providing core methodological support for the intelligent and unmanned implementation of ultrasonic testing for cast-in-place piles.

[0116] Furthermore, the ultrasonic testing device 400 of this invention, taking an ultrasonic transducer as an example, includes the following configuration process: In standby mode, the ultrasonic transducer is pre-placed in the guide slot 201 inside the end effector of the robotic arm 200. Upon receiving a "successful pile position confirmation" signal, this signal triggers the subsequent automatic acoustic wave testing process. The robotic arm 200 first moves, precisely aligning the slot outlet with the acoustic logging pipe opening according to the physical coordinates of each pipe opening through rotation and extension. Then, through the release wire action of the servo winch mechanism, the transducer is vertically inserted from the slot into the acoustic logging pipe along a preset trajectory. After testing, it is pulled back into the slot. The specific implementation steps include:

[0117] (1) Parametric motion planning. The acquisition device receives pile parameters (pile length, diameter, number of pipes) from the image recognition system and the data monitoring system. Based on the principle of high efficiency of pile length L, the optimal lowering speed V_down (V_down=k / L+b, where k and b are efficiency coefficients) is calculated, and the lifting speed V_up is constrained to ≤0.5m / s. At the same time, an S-shaped speed curve is generated to ensure smooth start and stop of the equipment.

[0118] (2) Precise Depth Determination and Synchronous Lowering. The transducer is positioned at the pipe opening under the guidance of the alignment device. N sets of servo winches are controlled to start synchronously, lowering the transducer at a speed of V_down. The high-resolution encoder provides real-time feedback of the depth value Hi. The pile bottom is determined by comparing the drive current (torque) of each motor with the depth value Hi in real time: when all motor currents show a characteristic jump and Hi≈L, it is determined that the pile has reached the bottom synchronously, the lowering is stopped, and the pile bottom depth reference Hb is recorded.

[0119] (3) Synchronous Lifting and Adaptive Detection. Start the ultrasonic transmitter / receiver. The controller drives all servo motors to synchronously lift the transducer at a speed of V_up in electronic gear synchronization mode. Depth-Data Binding: The depth information Hi fed back by the encoder is bound and stored in real time with the acoustic parameters (acoustic time, amplitude) collected by the ultrasonic instrument in a one-to-one correspondence. Speed ​​Adaptation: If the signal-to-noise ratio of the received waveform monitored in real time is lower than the threshold, V_up is automatically reduced by one level (e.g., from 0.5m / s to 0.3m / s) to obtain denser and more stable data.

[0120] (4) Neat recovery and status reset. When the transducer is raised to the nozzle, the photoelectric sensor is triggered and the speed is switched to low.

[0121] After the transducer is completely removed from the pipe opening, the alignment device moves away, and the automatic cable reeling device 101 continues to reel in the cable. The servo cable guide integrated into the drum axis works synchronously to ensure the cable is tightly and neatly arranged. The device resets to the standby state, ready to move to the next pile location for testing.

[0122] In summary, the technical effects achieved by the fully automated intelligent ultrasonic testing system and method for cast-in-place piles provided by the embodiments of the present invention include:

[0123] (1) Full-process automatic intelligent detection enables industrial upgrading, avoids human intervention, improves quality and efficiency, and facilitates supervision.

[0124] (2) The pile position is automatically confirmed by the Beidou positioning system, which solves the problems of complex, time-consuming and labor-intensive confirmation of pile position and number in the traditional ultrasonic testing of cast-in-place piles and easy confusion.

[0125] (3) The number and position of the ultrasonic detection tubes preset on the grouting pile are identified by the image recognition system, and the ultrasonic transducer is aligned with the ultrasonic detection tube to facilitate the lowering and lifting of the ultrasonic transducer.

[0126] (4) Solve the problems of numerous devices and high labor intensity in traditional ultrasonic testing by using an intelligent system that enables automatic walking.

[0127] (5) The automatic acquisition system solves the problems of asynchronous lifting and unstable speed of ultrasonic transducers affecting the quality of detection data acquisition in traditional detection, and the problem that the traditional hand-cranked wire reel can easily tangle the wires, affecting the detection efficiency.

[0128] (6) The data terminal system can set different numbers of ultrasonic transducers, ultrasonic wave velocity, lowering and lifting speeds based on information such as the diameter, length, number of ultrasonic testing tubes, and concrete strength of the cast-in-place pile 600. It can also automatically judge the data acquisition quality and solve the problem that the detection quality is limited by the experience of the testing personnel.

[0129] It should be noted that the term "comprising" and its variations used in the embodiments of this invention are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The modifications of "one" and "a plurality" mentioned in the embodiments of this invention are illustrative and not restrictive, and those skilled in the art should understand that unless explicitly indicated otherwise in the context, they should be understood as "one or more".

[0130] The steps described in the method embodiments provided by the present invention can be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of protection of the present invention is not limited in this respect.

[0131] The term "embodiment" in this specification refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily imply the same embodiment, nor does it imply independence or alternativeity from other embodiments. The various embodiments in this specification are described in a related manner, with reference to each other for similar or identical parts. In particular, for apparatus, device, and system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, and relevant details are referred to in the description of the method embodiments.

[0132] The above-described embodiments are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of protection. It should be noted that those skilled in the art can make various modifications and improvements without departing from the inventive concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the appended claims.

Claims

1. A fully automated intelligent ultrasonic testing system for cast-in-place piles, characterized in that, include: The walking device is equipped with an automatic retraction and deployment device; the automatic retraction and deployment device is wound with a wire. A robotic arm is mounted on the walking device; the robotic arm has a wiring channel inside, and the end of the robotic arm has a guide slot that communicates with the wiring channel; an ultrasonic testing device is movably mounted in the guide slot; the end of the wire is connected to the ultrasonic testing device through the wiring channel. A camera, mounted on the robotic arm, is used to collect real-time image data of the top of each cast-in-place pile. The control system, installed on the walking device, is used to identify the pixel coordinates of the core of each of the cast-in-place piles and the pixel coordinates of the sonic logging pipes embedded in the cast-in-place piles based on the image data of the pile top, and to determine whether the walking device has reached the target position based on the deviation between the physical coordinates obtained by converting the pixel coordinates of the core and the theoretical coordinates of the core in the drawing of the cast-in-place pile. When the walking device moves to the target position, the robotic arm is manipulated to move the ultrasonic testing device to the physical coordinates obtained by converting the pixel coordinates of the acoustic tube opening, and the automatic take-up and put-down device is driven to lower the wire, so that the ultrasonic testing device, under the combined action of the guide slot and its own weight, vertically enters the interior of the corresponding acoustic tube until it touches the bottom.

2. The detection system according to claim 1, characterized in that, The control system includes: An image processing module, connected to the camera, is used to convert the color image data of the pile top into corresponding grayscale image data and extract the gradient magnitude. The feature extraction module, connected to the image processing module, is used to extract the top surface target contour of each of the cast-in-place piles and the quantized features of each connected component in the top surface target contour based on each of the grayscale image data and the gradient magnitude. The target recognition module, connected to the feature extraction module, is used to identify the pile body region and the sonic logging pipe region of the cast-in-place pile from each of the connected domains based on the quantized features, and to determine the pixel coordinates of the pile core and the sonic logging pipe region of the cast-in-place pile based on the center coordinates of the pile body region and the sonic logging pipe region.

3. The detection system according to claim 2, characterized in that, The feature extraction module further includes: An edge detection module, connected to the image processing module, is used to extract the top surface target contour of each of the cast-in-place piles based on the grayscale image data, and output a binary edge image with a single pixel width. The repair module, connected to the edge detection module, is used to perform edge morphological closing operations on the binary edge image to obtain an edge image with continuous and complete contours. The contour feature quantization module, connected to the repair module, is used to perform connected component analysis and quantization processing on the edge image and extract the quantization features of each connected component; the quantization features include: size features, position features, morphological features and grayscale features.

4. The detection system according to claim 3, characterized in that, The target recognition module includes: The pile body recognition module is connected to the feature extraction module and is used to select the region with the largest average gray value and the largest area from each of the connected components based on the quantized features, and determine it as the pile body candidate region. The pile body determination module, connected to the pile body recognition module, is used to filter out areas from the pile body candidate areas where both the roundness and equivalent diameter dimensions meet the set range, determine them as pile body areas, and determine the centroid of the pile body area as the pixel coordinates of the corresponding pile center.

5. The detection system according to claim 4, characterized in that, The target recognition module further includes: The pipe opening identification module is connected to the feature extraction module and is used to select regions with an average gray value less than a second set threshold and an area that meets the restriction range from each of the connected components based on the quantized features, and determine them as the initial candidate set of pipe openings. The pipe opening determination module, connected to the pipe opening recognition module, is used to filter areas from the initial candidate set of pipe openings where the circularity, equivalent diameter, center position, and the connection of each center all meet the set range, and determine them as the acoustic pipe opening area, and determine the center coordinates of the acoustic pipe opening area as the pixel coordinates of the corresponding acoustic pipe opening.

6. The detection system according to claim 2, characterized in that, The control system further includes: The information extraction module is used to extract the theoretical coordinates of the pile core of each pile in the construction coordinate system based on the input pile drawings. The coordinate transformation module, connected to the information extraction module and the target recognition module, is used to convert the pixel coordinates of the pile center and the sonic logging pipe opening into the corresponding physical coordinates under the construction coordinate system based on the Beidou coordinates of the walking device and the transformation matrix between the camera and the walking device and the end effector of the robotic arm. The deviation calculation module, connected to the information extraction module and the coordinate transformation module, is used to calculate the planar deviation distance between the physical coordinates of the pile core and the theoretical coordinates of the pile core; The pile position confirmation module is connected to the deviation calculation module and is used to compare the plane deviation distance with a set deviation threshold. When the plane deviation distance is less than or equal to the set deviation threshold, the module confirms that the walking device has reached the target position.

7. The detection system according to claim 1, characterized in that, The control system further includes: The multi-source data acquisition module is used to acquire encoder data of the automatic take-up and take-down device, ultrasonic detection data of the ultrasonic detection device, video stream data of the camera, and operating status data of the walking device, the robotic arm and the automatic take-up and take-down device. The display module, connected to the multi-source data acquisition module, is used to visually display the theoretical parameters of each of the cast-in-place piles, the lowering progress of the ultrasonic testing equipment, the ultrasonic testing data, the video footage captured by the camera, and the operating status data; wherein, the lowering progress is calculated based on the encoder data and the pile length in the theoretical data of the cast-in-place pile.

8. The detection system according to claim 1, characterized in that, The automatic take-up and unwinding device includes: a reel, a servo cable tray, and a servo motor; The drum is rotatably mounted on the traveling device; the servo cable guide is mounted on the traveling device and is parallel to the drum; the wire is wound onto the drum after being guided by the servo cable guide; the servo motor is mounted on the traveling device, and its output end is coaxially and fixedly connected to the central axis of the drum; both the servo motor and the servo cable guide are connected to the control system.

9. The detection system according to claim 1, characterized in that, At least two ultrasonic testing devices are provided, and their number corresponds one-to-one with the number of the robotic arm and the automatic take-up and take-down device. Each of the ultrasonic testing devices is connected to an automatic take-up and take-down device via a wire that passes through the wiring channel of the corresponding robotic arm, forming a set of testing components.

10. A fully automated intelligent ultrasonic testing method for cast-in-place piles, characterized in that, Includes the following steps: The control system sets the route to control the movement of the walking equipment and collects real-time image data of the top of each cast-in-place pile to be tested; wherein, the walking equipment is equipped with an automatic retraction device, and the automatic retraction device is wound with a wire. Based on the pile top image data, the pixel coordinates of the pile core and sonic logging pipe opening of each of the cast-in-place piles are identified in real time, and the pixel coordinates are converted into corresponding physical coordinates. Based on the deviation between the physical coordinates of the pile core and the theoretical coordinates of the pile core in the pile drawing, it is determined whether the walking equipment has reached the target position. Upon reaching the target location, the robotic arm is manipulated to move the ultrasonic testing device to the physical coordinates corresponding to the acoustic probe opening. The robotic arm is mounted on a traveling device. An internal wiring channel is provided within the robotic arm, and a guide slot connected to the wiring channel is located at the end of the robotic arm. The ultrasonic testing device is movably mounted within the guide slot. The end of the lead wire is connected to the ultrasonic testing device via the wiring channel. Upon reaching the physical coordinates corresponding to the acoustic tube opening, the automatic take-up and take-down device is operated to lower the wire, so that the ultrasonic testing device, under the combined action of the guide slot and its own weight, vertically enters the interior of the corresponding acoustic tube until it touches the bottom.

Images