Method, device and equipment for monitoring pile sinking of pile foundation and storage medium

Abstract

According to the pile foundation pile sinking monitoring method, device and equipment and the storage medium, the pile foundation pile sinking image is obtained through the collecting equipment arranged at the preset position, the pile foundation pile sinking image comprises the to-be-monitored pile foundation, and the to-be-monitored pile foundation is provided with a pile body scale; calculating the actual size of a unit pixel according to the pile body scale so as to determine a vertical pixel calibration value; according to a preset mark point and the vertical pixel calibration value, pile foundation pile sinking parameters are determined; and the pile sinking parameters of the pile foundation are input into a bearing capacity prediction model, and the predicted bearing capacity of the to-be-monitored pile foundation is obtained. The image acquisition device arranged at the preset position is used for acquiring the pile sinking image of the pile foundation in real time, pixel calibration is carried out in combination with the pile body scale, and key parameters in the pile sinking process of the pile foundation can be accurately calculated, so that a reliable basis is provided for prediction of the bearing capacity of the pile foundation, the monitoring precision and efficiency are greatly improved, and the cost is reduced. And errors possibly caused by manual measurement are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of pile foundation sinking, and in particular to a monitoring method, device, equipment and storage medium for pile foundation sinking. Background Art

[0002] Pile foundation is an important infrastructure in construction projects, and the quality of its pile sinking process directly affects the stability and safety of the project. At present, the monitoring of pile foundation sinking quality mostly relies on manual detection methods, or uses traditional instruments and equipment to measure parameters such as pile sinking depth, penetration, and rebound value. These traditional methods have many disadvantages, such as being greatly affected by human factors, high measurement errors, and cumbersome operations, and cannot monitor and feedback dynamic changes in the pile sinking process in real time. Therefore, there is an urgent need for an efficient and accurate pile foundation sinking monitoring method to improve monitoring efficiency and accuracy.

[0003] With the development of digital image processing technology and deep learning algorithms, pile foundation monitoring methods based on image acquisition and analysis have gradually become a research hotspot. Although traditional image acquisition technology can provide rich image data, in practical applications, how to accurately extract pile sinking parameters from images and conduct predictive analysis based on actual engineering conditions is still a technical challenge.

[0004] In summary, the problems existing in the prior art need to be solved urgently. Summary of the invention

[0005] The present invention provides a monitoring method, device, equipment and storage medium for pile foundation sinking, which are used to solve the defects in the prior art and realize real-time monitoring of the pile foundation sinking process.

[0006] The present invention provides a method for monitoring pile foundation sinking, comprising: Acquire a pile foundation sinking image by means of a collection device arranged at a preset position, wherein the pile foundation sinking image includes a pile foundation to be monitored, and a pile body scale is arranged on the pile foundation to be monitored; Calculate the actual size of the unit pixel according to the pile body ruler to determine the vertical pixel calibration value; Determining pile foundation sinking parameters according to the preset marking points and the vertical pixel calibration values; The pile foundation driving parameters are input into a bearing capacity prediction model to obtain the predicted bearing capacity of the pile foundation to be monitored.

[0007] According to a pile foundation sinking monitoring method provided by the present invention, the step of calculating the actual size of a unit pixel according to the pile body scale to determine the vertical pixel calibration value specifically includes: Extracting a region including the pile body scale in the pile foundation sinking image; Extract the pixel positions of any two scale lines in the pile body scale in the image; The vertical pixel calibration value is determined according to the actual distance between the scale lines and the pixel distance, and the pixel distance is determined by the pixel position of each scale line in the image.

[0008] According to a pile foundation sinking monitoring method provided by the present invention, the pile foundation sinking parameters include hammer penetration, hammer rebound value and soil penetration depth.

[0009] According to a pile foundation sinking monitoring method provided by the present invention, the preset marking points include tracking points, and the step of determining the pile foundation sinking parameters according to the preset marking points and the vertical pixel calibration values ​​specifically includes: According to the current pile foundation sinking image, determine the vertical pixel coordinates of the current tracking point; According to the initial pile foundation sinking image, the vertical pixel coordinates of the initial tracking point are determined; Determine a pile penetration displacement variation curve according to the vertical pixel coordinates of each current tracking point and the vertical pixel coordinates of the initial tracking point, wherein the pile penetration displacement variation curve is used to characterize a variation curve of the pile penetration displacement over time; Determining the hammer penetration value and the hammer rebound value according to the pile penetration displacement variation curve; Wherein, the current tracking point and the initial tracking point are both set on the pile body scale; Determine the initial burial depth of the pile foundation to be monitored based on the scale value of the current tracking point, the absolute elevation of the scale position of the pile body where the tracking point is located, and the absolute elevation of the ground at the pile position; The pile body penetration depth value during the construction process is determined according to the initial penetration depth and the pile body penetration displacement variation curve.

[0010] According to a pile foundation sinking monitoring method provided by the present invention, before the step of determining the pile foundation sinking parameters according to the preset marking points and the vertical pixel calibration values, the method further includes: When the tracking point coordinates exceed the preset threshold When , the tracking point position is updated according to the preset formula, and the reference sub-area matrix is ​​updated according to the tracking point position; The preset formula is as follows:

[0011] in, is the vertical pixel coordinate of the updated tracking point, is the preset update distance, is the pixel calibration value, The vertical pixel coordinate of the current tracking point.

[0012] According to a method for monitoring pile foundation sinking provided by the present invention, after the step of acquiring a pile foundation sinking image by means of a collection device arranged at a preset position, the method further comprises: The pile foundation sinking image is preprocessed, and the preprocessing includes denoising, graying and contrast enhancement.

[0013] According to a pile foundation sinking monitoring method provided by the present invention, the bearing capacity prediction model is trained in the following way: Get historical pile foundation sinking parameters; Inputting the historical pile foundation sinking parameters into a pre-built bearing capacity prediction model for training until a convergence function is satisfied; The bearing capacity prediction model is constructed based on a multi-layer perception mechanism.

[0014] The present invention also provides a monitoring device for pile foundation sinking, comprising: An image acquisition module, used to acquire a pile foundation sinking image through an acquisition device arranged at a preset position, wherein the pile foundation sinking image includes a pile foundation to be monitored, and a pile body scale is arranged on the pile foundation to be monitored; A calibration determination module, used for calculating the actual size of a unit pixel according to the pile body scale to determine a vertical pixel calibration value; A parameter determination module, used to determine pile foundation sinking parameters according to preset marking points and the vertical pixel calibration values; The bearing capacity prediction module is used to input the pile foundation sinking parameters into the bearing capacity prediction model to obtain the predicted bearing capacity of the pile foundation to be monitored.

[0015] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a monitoring method for pile foundation sinking as described in any one of the above is implemented.

[0016] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for monitoring pile foundation sinking as described in any one of the above is implemented.

[0017] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for monitoring pile foundation sinking as described above is implemented.

[0018] The monitoring method, device, equipment and storage medium of pile foundation sinking provided by the present invention obtains a pile foundation sinking image by using an acquisition device set at a preset position, wherein the pile foundation sinking image includes a pile foundation to be monitored, and a pile body scale is provided on the pile foundation to be monitored; the actual size of a unit pixel is calculated according to the pile body scale to determine a vertical pixel calibration value; the pile foundation sinking parameters are determined according to a preset marking point and the vertical pixel calibration value; the pile foundation sinking parameters are input into a bearing capacity prediction model to obtain the predicted bearing capacity of the pile foundation to be monitored. The pile foundation sinking monitoring method provided by the present invention can accurately calculate the key parameters in the pile foundation sinking process, such as hammer penetration, hammer rebound value and burial depth, by using an image acquisition device set at a preset position to acquire a pile foundation sinking image in real time and combine the pile body scale for pixel calibration, thereby providing a reliable basis for the prediction of the bearing capacity of the pile foundation. The method can obtain pile sinking data in real time and non-destructively through digital image technology, greatly improving the monitoring accuracy and efficiency, and avoiding the errors that may be caused by manual measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 It is a schematic diagram of the flow of the pile foundation sinking monitoring method provided by the present invention; Figure 2 It is a structural schematic diagram of a monitoring device for pile foundation sinking provided by the present invention; Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] In order to solve the problems in the prior art, the present invention proposes a monitoring method for pile foundation sinking, which improves the monitoring accuracy and efficiency and avoids the errors that may be caused by manual measurement. The monitoring method for pile foundation sinking is described below. Figure 1 As shown, including but not limited to the following steps: Step 110: Acquire a pile foundation sinking image by using a collection device arranged at a preset position, wherein the pile foundation sinking image includes a pile foundation to be monitored, and a pile body scale is arranged on the pile foundation to be monitored.

[0023] In this step, you first need to select a suitable location to install the image acquisition device, which can usually be a high-definition camera or video camera. In order to ensure high accuracy of the monitoring process, the device should have sufficient resolution and a high video frame rate (for example, ≥100 frames / second) to avoid data loss and improve the real-time monitoring. The device should be set in a fixed preset position to ensure that the image acquisition angle can cover the entire process of pile foundation sinking.

[0024] The pile foundation to be monitored should be equipped with a pile body scale, which is usually a visible scale line set perpendicular to the pile body. The role of this scale is to calibrate the relationship between the pixels in the image and the actual size in the subsequent steps to ensure measurement accuracy. When collecting images, the image should be able to clearly contain the pile foundation and its pile body scale for subsequent processing.

[0025] Step 120: Calculate the actual size of the unit pixel according to the pile body ruler to determine the vertical pixel calibration value.

[0026] The core of this step is to calibrate the pile ruler through image processing technology to determine the actual size corresponding to the unit pixel in the image. First, the area containing the pile ruler is extracted from the pile foundation sinking image. Then, the position of each scale line on the ruler is identified through the image analysis algorithm, and the position of the scale line is extracted specifically through the pixel coordinates in the image.

[0027] Next, by calculating the actual distance between two adjacent scale lines on the ruler and the corresponding pixel distance in the image, the actual size of the unit pixel can be obtained. For example, if the actual spacing between adjacent scale lines is 1 meter, and the corresponding pixel distance in the image is 50 pixels, then the actual size represented by each pixel is 1 meter / 50 pixels, that is, 0.02 meters / pixel. Through this method, the vertical pixel calibration value, that is, the actual height value corresponding to the unit pixel, can be obtained.

[0028] Step 130: Determine pile foundation sinking parameters according to the preset marking points and the vertical pixel calibration values.

[0029] In this step, you first need to set multiple preset marking points in the image. Common marking points include tracking points and landmark points. Tracking points are generally selected from specific scale line corners on the pile body scale, while landmark points are selected from fixed points on the ground to help calculate the depth of soil penetration.

[0030] Then, the tracking points and landmark points in the image are identified, and their pixel coordinates in the image are determined by image processing technology. By comparing the images before and after hammering, the vertical pixel coordinates of the tracking points and landmark points before and after hammering, as well as in the initial and final states are obtained.

[0031] According to the vertical pixel calibration value, the pixel coordinates in the image can be converted into actual distance. For example, the depth of the pile before the hammering can be calculated by the pixel coordinate difference between the tracking point and the landmark point before the hammering. Similarly, the pixel coordinate difference between the tracking point and the landmark point after the hammering is used to calculate the hammering rebound value. By comparing the pixel coordinate difference between the initial state and the final state, the depth of the pile during the entire pile driving process can be calculated.

[0032] This step can further accurately determine the pile foundation sinking parameters, such as the scale value of the tracking point on the ruler, the initial absolute high-level value, the hammer penetration, the hammer rebound value and the depth of penetration into the soil, thereby providing basic data for the subsequent bearing capacity prediction.

[0033] Step 140: input the pile foundation driving parameters into a bearing capacity prediction model to obtain the predicted bearing capacity of the pile foundation to be monitored.

[0034] In this step, the pile foundation driving parameters obtained in the previous steps are input into a pre-trained bearing capacity prediction model. The prediction model can be a deep learning-based model, such as a multi-layer perceptron (MLP), which is trained with a large amount of historical pile foundation driving data. During the training process, the model learns the nonlinear relationship between pile foundation parameters (such as pile driving depth, penetration, etc.) and pile foundation bearing capacity.

[0035] The specific structure of the multi-layer perceptron (MLP) can be: (1) Number of input layer nodes: 7-12, corresponding to different input parameter types; (2) Number of hidden layers: 3-5; (3) Activation function: ReLU function; (4) Optimization algorithm: error back propagation algorithm.

[0036] After the pile driving parameters are input, the bearing capacity prediction model will calculate the predicted bearing capacity of the pile foundation in real time. The output of the model is the estimated bearing capacity of the pile foundation, which can help engineers evaluate whether the quality of the current pile driving meets the design requirements, and then adjust or optimize the construction process. In addition, an early warning is triggered when any of the following situations is detected: (1) the penetration of a single hammer blow exceeds the design threshold by ±30%; (2) the rebound value of three consecutive hammer blows exceeds the set safety value; so that the staff can handle it in time.

[0037] Through this series of steps, accurate monitoring of the pile foundation sinking process and prediction of bearing capacity can be achieved, effectively improving the accuracy and real-time performance of pile sinking construction and ensuring the quality and safety of the project.

[0038] As a further optional embodiment, the step of calculating the actual size of the unit pixel according to the pile body ruler to determine the vertical pixel calibration value specifically includes: Extracting a region including the pile body scale in the pile foundation sinking image; Extract the pixel positions of any two scale lines in the pile body scale in the image; The vertical pixel calibration value is determined based on the actual distance and pixel distance between adjacent scale lines, and the pixel distance is determined by the pixel position of each scale line in the image.

[0039] As a further optional embodiment, the present invention may also adopt the following technical solution to implement the step of calculating the actual size of the unit pixel according to the pile body ruler to determine the vertical pixel calibration value.

[0040] First, in the acquired pile foundation sinking image, the image area extraction operation is performed. The image usually contains the pile foundation sinking process and the pile body scale. In order to accurately calculate the vertical pixel calibration value, the pile body scale in the image needs to be accurately extracted. Image processing algorithms can be used to identify and extract the area related to the pile body scale in the image.

[0041] When extracting the scale area, the image segmentation, edge detection and other technologies can be used to accurately define the location of the scale area. In this way, the extracted image will only contain the pile body scale area, providing basic data for subsequent processing.

[0042] After the scale area is extracted, it is necessary to identify and extract any two scale lines in the pile scale. These scale lines are usually arranged in an equidistant manner and appear as a series of horizontal or vertical straight lines in the image. Try to extract scale lines that are more than the preset threshold to ensure accurate measurement.

[0043] Through image processing algorithms (such as edge detection, morphological transformation, etc.), the pixel coordinates of the scale lines can be identified and extracted. These pixel coordinates will provide key data for subsequent calculations. During the extraction process, special attention should be paid to the resolution of the scale lines and their precise positions in the image to ensure that the pixel position of each scale line can be accurately obtained.

[0044] After the scale lines of the pile body ruler are extracted, the vertical pixel calibration value is determined by comparing the actual distance between two adjacent scale lines and their pixel distance in the image.

[0045] Specifically, the actual distance between the scale lines is known, and can usually be obtained based on the actual size of the design drawing or ruler. For example, assume that the actual distance between every two adjacent scale lines is 10 cm. Then, through image processing software or algorithms, the pixel position difference between adjacent scale lines in the image is obtained to calculate the pixel distance. For example, assume that the pixel distance between two adjacent scale lines in the image is 50 pixels. Subsequently, based on the actual distance and the pixel distance, the actual size corresponding to each pixel is determined. If the actual distance between the scale lines is 10 cm and the pixel distance is 50 pixels, the vertical pixel calibration value is: 10 cm / 50 pixels = 0.2 cm / pixel. In this way, the vertical pixel calibration value is determined, which provides a benchmark for the subsequent calculation of pile sinking process parameters.

[0046] As a further optional embodiment, the pile foundation driving parameters include hammer penetration, hammer rebound value and soil penetration depth.

[0047] As a further optional embodiment, the preset marking point includes a tracking point, and the step of determining the pile foundation sinking parameter according to the preset marking point and the vertical pixel calibration value specifically includes: According to the current pile foundation sinking image, determine the vertical pixel coordinates of the current tracking point; According to the initial pile foundation sinking image, the vertical pixel coordinates of the initial tracking point are determined; Determine a pile penetration displacement variation curve according to the vertical pixel coordinates of each current tracking point and the vertical pixel coordinates of the initial tracking point, wherein the pile penetration displacement variation curve is used to characterize a variation curve of the pile penetration displacement over time; Determining the hammer penetration value and the hammer rebound value according to the pile penetration displacement variation curve; Wherein, the current tracking point and the initial tracking point are both set on the pile body scale; Determine the initial burial depth of the pile foundation to be monitored based on the scale value of the current tracking point, the absolute elevation of the scale position of the pile body where the tracking point is located, and the absolute elevation of the ground at the pile position; The pile body penetration depth value during the construction process is determined according to the initial penetration depth and the pile body penetration displacement variation curve.

[0048] First, the displacement of the pile body at different time points can be calculated by using the vertical pixel coordinates of the tracking points in the preset markers in each pile foundation sinking image, combined with the vertical pixel calibration value (i.e. the relationship between the pixel and the actual size). Through these displacement data, the pile body penetration displacement change curve can be drawn, which describes the change of displacement over time during the pile foundation sinking process.

[0049] The specific steps are as follows: Get the vertical pixel coordinates of the tracking point in each frame image Ttyi (i.e. the vertical coordinate of the tracking point in the current frame image), and according to the above formula, combined with the vertical pixel calibration value cp , calculate the displacement:

[0050] in R ty It is the vertical coordinate of the tracking point in the initial frame image (i.e., the 0th frame image).

[0051] Through the displacement data of all frame images, the displacement change curve of the pile body during the pile foundation sinking process can be obtained. This curve can reflect the change of the pile foundation sinking depth at each time point.

[0052] Step 2: Determine the hammer penetration and hammer rebound values According to the obtained pile penetration displacement change curve, the hammer penetration value and hammer rebound value of each hammer can be further determined: Hammer penetration value: When the pile foundation sinks with each hammer, the part of the displacement curve that indicates the sinking is the penetration. The part of the displacement curve from zero to the maximum value is the penetration during the hammering process.

[0053] Hammering rebound value: After the hammering is completed, the pile foundation will have a certain rebound. The part of the displacement curve that shows a negative value or rebound after the hammering is the rebound value.

[0054] On the displacement change curve, positive values ​​indicate penetration and negative values ​​indicate rebound. In this way, the penetration and rebound values ​​of each hammer can be accurately obtained.

[0055] Step 3: Determine the vertical pixel coordinates of the current tracking point According to the current pile foundation sinking image, identify and extract the vertical pixel coordinates of the tracking point T txy At this point, the vertical coordinate of the tracking point T tyi Indicates the vertical displacement of the pile body in the current image frame.

[0056] Step 4: Determine the vertical pixel coordinates of the initial tracking point According to the initial pile foundation sinking image (i.e. the 0th frame image), determine the vertical pixel coordinates of the initial tracking point T 0ty , as the reference coordinate. This coordinate represents the position of the pile body of the pile foundation to be monitored at time 0.

[0057] Step 5: Determine the depth of the soil Combined with the vertical pixel coordinate of the current tracking point T txy 、 The vertical pixel coordinate of the initial tracking pointT 0ty , the absolute construction elevation e1 of the initial tracking point and the scale value ht of the pile body scale where it is located, and the absolute construction elevation e0 of the ground at the pile position, the depth of the pile foundation can be calculated. Specifically, the calculation formula for the depth of the pile foundation is as follows:

[0058] in: h t It is the scale value corresponding to the tracking point on the pile body ruler, indicating the height position of the tracking point on the pile body.

[0059] cp is the vertical pixel calibration value.

[0060] Through the above steps, the soil penetration depth of the pile foundation can be obtained in real time at different time points, and the bearing capacity and construction quality of the pile foundation during the pile sinking process can be further analyzed.

[0061] As a preferred embodiment, for the displacement change curve of the pile body penetration, dynamic matching of tracking points can be achieved based on a digital image correlation algorithm, including: constructing a reference sub-area matrix and a search area matrix, achieving image feature matching through two-dimensional Fourier transform, and using a sub-pixel positioning algorithm to improve matching accuracy. Specifically: The image frame with the reference point is regarded as the reference image, denoted as frame 0 (F0), and the subsequent i-th frame is regarded as the target image, denoted as Fi. The digital image correlation algorithm is used to find the positions of the tracking point and the landmark point in the target image, denoted as Ti ( , ) and Gi ( , ). Taking the matching algorithm of tracking points as an example, the specific method is as follows: 1) In the pixel matrix of F0, a square matrix with a side length of (2M+1) is taken out with T0 as the center as the reference sub-area, represented by R; 2) Considering that the pile mainly moves vertically, the pixel coordinates of point T(i-1) in the pixel matrix of Fi are ( , ) is taken as the center to take out a matrix with a height of (6M+1) and a width of (4M+1) as the search area, represented by S, that is, S is the first -2M rows to +4M line, -2M columns to +Pixel matrix within 2M columns; 3) Insert M rows and M columns of zeros on the upper, lower, left and right sides of the S matrix to expand it into a matrix with (8M+1) rows and (6M+1) rows, and calculate its two-dimensional Fourier transform, recorded as S_FFT (complex matrix); 4) Flip the square matrix R 180 degrees, and insert 3M rows of 0 elements on its top and bottom, and 2M rows of 0 elements on its left and right sides, so that it is expanded to a matrix of (8M+1) rows and (6M+1) rows, and calculate its two-dimensional Fourier transform, recorded as R_FFT (complex matrix); 5) Perform dot multiplication on the matrices of S__FFT and R_FFT (i.e., multiply element by element, and the product of elements in the same position forms a new matrix), and perform inverse Fourier transform on the result. Then, the matrix obtained after the inverse transform is centered (i.e., the matrix is ​​divided into four quadrants with the center as the origin, and the elements of the first quadrant and the third quadrant are translated and exchanged, and the elements of the second quadrant and the fourth quadrant are translated and exchanged). The result is recorded as matrix C (complex matrix); 6) In the matrix C, a matrix with a starting point (M, M) and a height of (6M+1) and a width of (4M+1) is created, and only the real part of all elements is retained, denoted as Z_C; 7) Find the position of the maximum value in the Z_C matrix, recorded as ( , ), which is the integer pixel position with the greatest correlation with the reference sub-region R in the search area S of Fi; 8) In order to further improve the monitoring accuracy, the local quadratic surface fitting algorithm can be used to more accurately calculate the position of the peak point. The specific method is as follows: ① In the Z_C matrix, ( , ) is used as the center to take out a square matrix with a side length of 3, and reduce the dimension into a column vector by column, which is recorded as U; ② Calculate the fitting coefficient A by cross-product of matrix X and U:

[0062] in:

[0063] ③Calculate the fitting offset (sub-pixel)

[0064]

[0065] in:

[0066] ④ Calculate the sub-pixel peak point position ( , ):

[0067] 9) The peak value of the correlation coefficient calculated in step 8) is the local sub-pixel coordinate position of the tracking point in the search area S matrix in Fi. The pixel coordinate value of the tracking point in the global pixel matrix (Fi) can be calculated by the following formula, that is, ( , ):

[0068]

[0069] As a further optional embodiment, before the step of determining the pile foundation sinking parameters according to the preset marking points and the vertical pixel calibration values, the method further includes: When the tracking point coordinates exceed the preset threshold When , the tracking point position is updated according to the preset formula, and the reference sub-area matrix is ​​updated according to the tracking point position; The preset formula is as follows:

[0070] in, is the vertical pixel coordinate of the updated tracking point, is the preset update distance, is the pixel calibration value, The vertical pixel coordinate of the current tracking point.

[0071] In the actual pile foundation sinking monitoring process, due to environmental factors or image quality, the tracking points in the pile foundation sinking image may not be clearly identified. For example, the tracking points may not be accurately located due to shadows, occlusions, blur or image noise. At this time, in order to ensure the accurate calculation of the pile sinking parameters, the system needs to automatically update the position of the tracking points.

[0072] Specifically, first, the system evaluates the quality of the pile foundation sinking image to detect whether there are any tracking points that cannot be identified. Image processing technology (such as edge detection, brightness contrast analysis, etc.) can be used to determine whether the tracking points are clear.

[0073] When the system detects that the tracking point cannot be identified, that is, the tracking point coordinates exceed the preset threshold When the update mechanism is triggered, in the pile foundation sinking image, the system will automatically select a suitable position on the pile body scale and reset the position of the tracking point. Usually, a relatively obvious and unobstructed scale line position on the pile body scale can be selected as the new tracking point.

[0074] Once a new tracking point position is selected, the system will re-determine the pixel coordinates of the new tracking point in the image through image processing techniques such as image registration or feature matching algorithms. The new tracking point will be used for subsequent pile sinking parameter calculations.

[0075] To ensure the accuracy of the updated tracking point position, the updated tracking point can be accurately positioned in combination with the vertical pixel calibration value (such as the calibration process in the previous step) to ensure that it corresponds one-to-one with the actual position on the pile body ruler.

[0076] After the tracking point is updated, the step of determining the pile sinking parameters based on the preset marker points and vertical pixel calibration values ​​is continued. At this point, the updated tracking point will be used as one of the key marker points to participate in the calculation of the pile sinking parameters, ensuring that the monitoring data of the entire pile sinking process remains accurate and reliable.

[0077] As a further optional embodiment, after the step of acquiring the pile foundation sinking image by means of a collection device disposed at a preset position, the method further comprises: The pile foundation sinking image is preprocessed, and the preprocessing includes denoising, graying and contrast enhancement.

[0078] The purpose of preprocessing is to improve the quality of pile foundation sinking images, making the key features in the images more obvious and facilitating subsequent parameter calculation and feature extraction.

[0079] Denoising: Noise in images is often an important factor affecting image quality. Noise may come from shooting equipment, changes in ambient light, or image transmission. In the denoising of pile foundation sinking images, appropriate denoising algorithms, such as Gaussian filtering and median filtering, are used to remove random noise in the image. This can improve image clarity and prevent noise from interfering with subsequent processing.

[0080] Grayscale: The color information in the pile foundation sinking image has little effect on the extraction of pile sinking parameters, while the grayscale image has higher computational efficiency in subsequent edge detection and feature extraction tasks. Therefore, the color image can be converted into a grayscale image.

[0081] Contrast enhancement: The contrast of an image determines the brightness difference between different areas in the image, and high contrast helps to better identify features in the image (such as the edge of a pile foundation and the scale of a ruler). By enhancing contrast, the details of the image can be made clearer and the distinction between the target features and the background can be enhanced.

[0082] As a further optional embodiment, the bearing capacity prediction model is trained in the following manner: Get historical pile foundation sinking parameters; Inputting the historical pile foundation sinking parameters into a pre-built bearing capacity prediction model for training until a convergence function is satisfied; The bearing capacity prediction model is constructed based on a multi-layer perception mechanism.

[0083] Before training the bearing capacity prediction model, it is necessary to first collect and organize historical pile foundation sinking parameter data. Historical data refers to the known pile foundation sinking parameters and corresponding pile foundation bearing capacity data during past construction and monitoring. These data can be obtained through traditional testing methods, existing equipment, or an established pile foundation monitoring system.

[0084] Historical pile foundation sinking parameters usually include but are not limited to the following: Hammer penetration: the vertical settlement of the pile when the pile foundation is hit by a hammer.

[0085] Hammer rebound value: the degree of rebound of the pile foundation after being hammered, reflecting the elasticity of the pile foundation.

[0086] Depth of soil penetration: The depth of the pile foundation inserted into the soil, which is usually related to the settlement of the pile foundation and the bearing capacity of the soil.

[0087] Soil layer characteristics: including soil density, viscosity, particle size, etc.

[0088] When predicting the bearing capacity, in addition to the penetration rate, rebound value, and depth of penetration, static parameters such as hammer weight (i.e. the weight of the hammer), jump height (i.e. the height of the hammer drop), pile type (PHC pile, steel pipe pile), and pile diameter (pile size) are also required.

[0089] When performing pile foundation sinking operations, in addition to real-time monitoring of dynamic parameters during the pile sinking process, the following static parameters must also be recorded: Hammer weight: refers to the weight of the hammer used to hit the pile. Hammer weight has a direct impact on the settlement speed and sinking depth of the pile foundation. Therefore, it is an important factor in predicting the bearing capacity of the pile foundation.

[0090] Jump height: also known as the drop height, refers to the height of the hammer falling freely from a height. Jump height is related to the dynamic parameters of the pile foundation, such as the settlement and rebound value, and is another key factor affecting the bearing capacity of the pile foundation.

[0091] Pile type: Different types of pile foundations (such as PHC piles, steel pipe piles, concrete piles, etc.) have different materials, structures and bearing characteristics. Therefore, the pile type is an important static parameter that affects the bearing capacity prediction.

[0092] Pile diameter: The diameter or size of the pile directly affects the bearing area of ​​the pile foundation, and thus its bearing capacity. Piles of different pile diameters have different bearing capacity characteristics.

[0093] By collecting these historical pile foundation driving parameters and combining them with the corresponding bearing capacity measurement data, the input-output pair data of the pile foundation are obtained.

[0094] Once the historical data is prepared, these pile driving parameters are used as inputs, along with the known pile bearing capacity as outputs, into a pre-built bearing capacity prediction model, which can be a multi-layer perceptron (MLP) model based on an artificial neural network (ANN).

[0095] The basic steps of the training process are as follows: Data normalization: Normalize or standardize the input parameters to ensure that each feature contributes evenly to model training and avoid deviations between features of different dimensions. Common methods include maximum and minimum value normalization, Z-score standardization, etc.

[0096] Model initialization: In neural networks, it is very important to initialize network parameters (such as weights and biases). The initialization method can use random initialization or other more advanced techniques (such as Xavier initialization, He initialization) to ensure that the network is in a reasonable state when training begins.

[0097] Forward propagation: The normalized pile foundation sinking parameters are input into the multi-layer perceptron model, and forward propagation calculation is performed to obtain the predicted bearing capacity output.

[0098] Error calculation: Calculate the error between the predicted value and the actual value. Commonly used error functions include mean square error (MSE).

[0099] Backpropagation and parameter update: The weights and biases in the network are adjusted according to the error through the backpropagation algorithm, usually using a gradient descent optimization algorithm such as stochastic gradient descent (SGD) and Adam optimizer.

[0100] Training round: Repeat the process of forward propagation, error calculation, back propagation and parameter update until the predetermined stopping condition is met, such as reaching a certain number of training rounds or the error converges to a sufficiently small value.

[0101] During the training process, the model will continuously update parameters until the loss function reaches the preset convergence criteria. Common convergence criteria include: Loss function convergence: When the change in the loss function is less than a certain threshold, it means that the model has reached the optimal or near-optimal state.

[0102] Training rounds: Set the maximum number of training rounds. When the training reaches the preset number, the training will stop.

[0103] Validation set performance: Use the validation set to evaluate the generalization ability of the model. When the performance of the validation set no longer improves, the training can be stopped.

[0104] In this way, the bearing capacity prediction model is gradually optimized and can accurately predict the bearing capacity of the pile foundation from the input pile driving parameters.

[0105] In this embodiment, the bearing capacity prediction model is constructed based on a multi-layer perceptron (MLP). MLP is a feed-forward neural network that includes multiple layers of neurons, and each layer of neurons takes the output of the previous layer as input and finally outputs the predicted bearing capacity of the pile foundation.

[0106] The monitoring device for pile foundation sinking provided by the present invention is described below. Figure 2 As shown, the monitoring device for pile foundation sinking described below and the monitoring method for pile foundation sinking described above can correspond to each other.

[0107] A monitoring device for pile foundation sinking, comprising: An image acquisition module 210 is used to acquire a pile foundation sinking image by using an acquisition device arranged at a preset position, wherein the pile foundation sinking image includes a pile foundation to be monitored, and a pile body scale is arranged on the pile foundation to be monitored; The calibration determination module 220 is used to calculate the actual size of the unit pixel according to the pile body scale to determine the vertical pixel calibration value; A parameter determination module 230, for determining pile foundation sinking parameters according to preset marking points and the vertical pixel calibration values; The bearing capacity prediction module 240 is used to input the pile foundation sinking parameters into a bearing capacity prediction model to obtain the predicted bearing capacity of the pile foundation to be monitored.

[0108] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communications interface 320 and the memory 330 communicate with each other via the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the monitoring method for pile foundation sinking, the method comprising: Acquire a pile foundation sinking image by means of a collection device arranged at a preset position, wherein the pile foundation sinking image includes a pile foundation to be monitored, and a pile body scale is arranged on the pile foundation to be monitored; Calculate the actual size of the unit pixel according to the pile body ruler to determine the vertical pixel calibration value; Determining pile foundation sinking parameters according to the preset marking points and the vertical pixel calibration values; The pile foundation driving parameters are input into a bearing capacity prediction model to obtain the predicted bearing capacity of the pile foundation to be monitored.

[0109] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0110] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the pile foundation pile driving monitoring method provided by the above methods, the method includes: Acquire a pile foundation sinking image by means of a collection device arranged at a preset position, wherein the pile foundation sinking image includes a pile foundation to be monitored, and a pile body scale is arranged on the pile foundation to be monitored; Calculate the actual size of the unit pixel according to the pile body ruler to determine the vertical pixel calibration value; Determining pile foundation sinking parameters according to the preset marking points and the vertical pixel calibration values; The pile foundation driving parameters are input into a bearing capacity prediction model to obtain the predicted bearing capacity of the pile foundation to be monitored.

[0111] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the pile foundation sinking monitoring method provided by the above methods, the method comprising: Acquire a pile foundation sinking image by means of a collection device arranged at a preset position, wherein the pile foundation sinking image includes a pile foundation to be monitored, and a pile body scale is arranged on the pile foundation to be monitored; Calculate the actual size of the unit pixel according to the pile body ruler to determine the vertical pixel calibration value; Determining pile foundation sinking parameters according to the preset marking points and the vertical pixel calibration values; The pile foundation driving parameters are input into a bearing capacity prediction model to obtain the predicted bearing capacity of the pile foundation to be monitored.

[0112] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0113] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring pile foundation sinking, characterized in that: include: Acquire a pile foundation sinking image by means of a collection device arranged at a preset position, wherein the pile foundation sinking image includes a pile foundation to be monitored, and a pile body scale is arranged on the pile foundation to be monitored; Calculate the actual size of the unit pixel according to the pile body ruler to determine the vertical pixel calibration value; Determining pile foundation sinking parameters according to the preset marking points and the vertical pixel calibration values; Inputting the pile foundation sinking parameters into a bearing capacity prediction model to obtain the predicted bearing capacity of the pile foundation to be monitored; The preset marking points include tracking points, and the step of determining pile foundation sinking parameters according to the preset marking points and the vertical pixel calibration values ​​specifically includes: According to the current pile foundation sinking image, determine the vertical pixel coordinates of the current tracking point; According to the initial pile foundation sinking image, the vertical pixel coordinates of the initial tracking point are determined; Determine a pile penetration displacement variation curve according to the vertical pixel coordinates of each current tracking point and the vertical pixel coordinates of the initial tracking point, wherein the pile penetration displacement variation curve is used to characterize a variation curve of the pile penetration displacement over time; Determining the hammer penetration value and the hammer rebound value according to the pile penetration displacement variation curve; Wherein, the current tracking point and the initial tracking point are both set on the pile body scale; Determine the initial burial depth of the pile foundation to be monitored based on the scale value of the current tracking point, the absolute elevation of the scale position of the pile body where the tracking point is located, and the absolute elevation of the ground at the pile position; Determine the pile body penetration depth value during the construction process according to the initial penetration depth and the pile body penetration displacement change curve; Before the step of determining the pile foundation sinking parameters according to the preset marking points and the vertical pixel calibration values, the method further includes: When the tracking point coordinates exceed the preset threshold When , the tracking point position is updated according to the preset formula, and the reference sub-area matrix is ​​updated according to the tracking point position; The preset formula is as follows: in, is the vertical pixel coordinate of the updated tracking point, is the preset update distance, is the pixel calibration value, The vertical pixel coordinate of the current tracking point.

2. The method for monitoring pile foundation sinking according to claim 1, characterized in that: The step of calculating the actual size of a unit pixel according to the pile body scale to determine the vertical pixel calibration value specifically includes: Extracting a region including the pile body scale in the pile foundation sinking image; Extract the pixel positions of any two scale lines in the pile body scale in the image; The vertical pixel calibration value is determined according to the actual distance between the scale lines and the pixel distance, and the pixel distance is determined by the pixel position of each scale line in the image.

3. The method for monitoring pile foundation sinking according to claim 1, characterized in that: The pile foundation sinking parameters include hammer penetration, hammer rebound value and soil penetration depth.

4. The method for monitoring pile foundation sinking according to claim 1, characterized in that: After the step of acquiring the pile foundation sinking image by means of a collection device arranged at a preset position, the method further comprises: The pile foundation sinking image is preprocessed, and the preprocessing includes denoising, graying and contrast enhancement.

5. The method for monitoring pile foundation sinking according to claim 1, characterized in that: The bearing capacity prediction model is trained in the following way: Get historical pile foundation sinking parameters; Inputting the historical pile foundation sinking parameters into a pre-built bearing capacity prediction model for training until a convergence function is satisfied; The carrying capacity prediction model is constructed based on a multi-layer perception mechanism.

6. A monitoring device for pile foundation sinking, characterized in that: include: An image acquisition module, used to acquire a pile foundation sinking image through an acquisition device arranged at a preset position, wherein the pile foundation sinking image includes a pile foundation to be monitored, and a pile body scale is arranged on the pile foundation to be monitored; A calibration determination module, used for calculating the actual size of a unit pixel according to the pile body scale to determine a vertical pixel calibration value; A parameter determination module, used to determine pile foundation sinking parameters according to preset marking points and the vertical pixel calibration values; A bearing capacity prediction module, used for inputting the pile foundation sinking parameters into a bearing capacity prediction model to obtain the predicted bearing capacity of the pile foundation to be monitored; The preset marking points include tracking points, and the step of determining pile foundation sinking parameters according to the preset marking points and the vertical pixel calibration values ​​specifically includes: According to the current pile foundation sinking image, determine the vertical pixel coordinates of the current tracking point; According to the initial pile foundation sinking image, the vertical pixel coordinates of the initial tracking point are determined; Determine a pile penetration displacement variation curve according to the vertical pixel coordinates of each current tracking point and the vertical pixel coordinates of the initial tracking point, wherein the pile penetration displacement variation curve is used to characterize a variation curve of the pile penetration displacement over time; Determining the hammer penetration value and the hammer rebound value according to the pile penetration displacement variation curve; Wherein, the current tracking point and the initial tracking point are both set on the pile body scale; Determine the initial burial depth of the pile foundation to be monitored based on the scale value of the current tracking point, the absolute elevation of the scale position of the pile body where the tracking point is located, and the absolute elevation of the ground at the pile position; Determine the pile body penetration depth value during the construction process according to the initial penetration depth and the pile body penetration displacement change curve; Before the step of determining the pile foundation sinking parameters according to the preset marking points and the vertical pixel calibration values, the method further includes: When the tracking point coordinates exceed the preset threshold When , the tracking point position is updated according to the preset formula, and the reference sub-area matrix is ​​updated according to the tracking point position; The preset formula is as follows: in, is the vertical pixel coordinate of the updated tracking point, is the preset update distance, is the pixel calibration value, The vertical pixel coordinate of the current tracking point.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the pile foundation driving monitoring method as claimed in any one of claims 1 to 5 is implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for monitoring pile foundation sinking as claimed in any one of claims 1 to 5 is implemented.

Images