Pile foundation pore-forming quality intelligent management and control method and system based on drilling machine working parameters

Abstract

The invention relates to the technical field of pile foundation construction, in particular to a pile foundation pore-forming quality intelligent management and control method and system based on drilling machine working parameters, and the method comprises the following steps: constructing a data acquisition array, and obtaining key working parameters of a drilling machine and pile foundation pore-forming quality index data based on the data acquisition array; establishing a standard time sequence database; building a dynamic correlation model based on the standard time sequence database, and building a quality judgment standard of the pile foundation pore-forming based on the dynamic correlation model; dynamically predicting the pile foundation formed hole according to the dynamic correlation model to obtain the quality state of the pile foundation formed hole, and obtaining a quality deviation result of the pile foundation formed hole in combination with the quality judgment standard; and a regulation and control strategy of the drilling machine is constructed based on the quality deviation result, the key working parameters are adjusted according to the regulation and control strategy, and intelligent control over the quality of pile foundation hole forming is achieved. Intelligent control over the pile foundation hole forming quality is achieved through driving of the working parameters of the drilling machine.

Description

Technical Field

[0001] The present invention relates to the technical field of pile foundation construction, in particular to an intelligent control method and system for the quality of pile hole formation based on the working parameters of a drilling rig. Background Art

[0002] The quality of pile hole formation directly affects the structural safety and durability of a building. At present, the construction of pile holes mainly relies on manual experience judgment and post - construction inspection, making it difficult to detect problems generated during the construction process in a timely manner, and there are deficiencies such as lagging response, low efficiency, and high repair costs. In addition, during the pile foundation construction process, the formation conditions are complex and changeable, and traditional construction monitoring methods are difficult to accurately grasp the real - time dynamics of the construction site, resulting in difficulty in effectively controlling the quality of pile hole formation.

[0003] Although the existing technology has introduced the monitoring of drilling rig operation parameters, most of them are still limited to single - parameter or simple linear correlation analysis, lacking effective means for comprehensive dynamic analysis of multiple parameters, resulting in insufficient prediction accuracy. In addition, traditional models are difficult to adapt to the changes in complex geological conditions and cannot achieve real - time optimization and adjustment of construction parameters. Some existing monitoring technologies often only focus on a single independent parameter during the operation of the drilling rig (such as only monitoring torque or rotational speed), or only conduct data analysis for a specific state, without comprehensively considering the mutual influence between multiple key parameters at the same time. In addition, the analysis process is not updated or feedback in real - time and dynamically according to the changes in the construction situation. Usually, only the completed data is analyzed afterwards, lacking the ability of immediate response and intelligent dynamic adjustment during the pile hole formation construction process. This method limits the effective response to complex geological and construction condition changes and is difficult to achieve comprehensive control of the quality of pile hole formation.

[0004] Based on this current situation, the present invention proposes an intelligent control method and system for the quality of pile hole formation based on the working parameters of a drilling rig. By comprehensively analyzing the dynamic correlation between the key parameters of the drilling rig and the quality of pile hole formation in real - time, using a dynamic correlation model to achieve real - time and accurate prediction of the quality of pile hole formation, and conducting closed - loop real - time feedback adjustment, the timeliness, accuracy, and economy of pile hole formation quality control are significantly improved, overcoming the deficiencies of the existing technology. Summary of the Invention

[0005] Aiming at the defects in the existing technology, the present invention provides an intelligent control method and system for the quality of pile hole formation based on the working parameters of a drilling rig.

[0006] To achieve the above object, in a first aspect, the present invention provides an intelligent control method for the quality of pile foundation hole formation based on the working parameters of a drilling rig. The method includes the following steps: constructing a data acquisition array, obtaining the key working parameters of the drilling rig and the quality index data of the pile foundation hole formation based on the data acquisition array, and establishing a standard time series database; constructing a dynamic association model based on the standard time series database, and establishing a quality determination standard for the pile foundation hole formation based on the dynamic association model; dynamically predicting the pile foundation hole formation according to the dynamic association model to obtain the quality state of the pile foundation hole formation, and combining the quality determination standard to obtain the quality deviation result of the pile foundation hole formation; constructing a regulation strategy for the drilling rig based on the quality deviation result, and adjusting the key working parameters according to the regulation strategy to achieve intelligent control of the quality of the pile foundation hole formation. The present invention realizes closed-loop control of the quality of pile foundation hole formation through data driving; eliminates manual recording errors through multi-source parameter real-time acquisition and standardization, and supports dynamic analysis; the dynamic association model quantifies the parameter coupling relationship, and the constructed quality determination standard breaks through the limitation of the traditional experience threshold, realizes accurate deviation positioning, and effectively avoids quality accidents such as hole deviation and hole collapse; the automatic regulation strategy based on the model shortens the parameter adjustment cycle, significantly reduces the rework rate and material waste, and saves the comprehensive construction cost.

[0007] Optionally, the constructing a data acquisition array, obtaining the key working parameters of the drilling rig and the quality index data of the pile foundation hole formation based on the data acquisition array, and establishing a standard time series database includes: constructing the data acquisition array based on high-frequency sensors and intelligent perception devices; conducting a trial drill on the construction area to be constructed, obtaining the initial real-time operation parameters of the drilling rig as historical key working parameters through the data acquisition array, and obtaining the historical quality index data of the pile foundation hole formation by using the data acquisition array; establishing a basic database based on the historical key working parameters and the historical quality index data; during the construction process, obtaining the real-time key working parameters of the drilling rig through the data acquisition array to construct a real-time construction database, and collecting the real-time quality index data of the pile foundation hole formation through the data acquisition array to establish a quality index database; performing standardization processing on the basic database, the real-time construction database, and the quality index database to establish the standard time series database. The present invention realizes all-round acquisition of construction parameters and hole formation quality through a high-frequency intelligent sensor array, and the established historical and real-time dual database architecture not only forms a construction experience benchmark but also realizes dynamic monitoring; the standardized time series database enables the working parameters of the drilling rig and the hole formation quality index to form a spatio-temporal association, provides data-driven support for construction parameter optimization, quality early warning, and process improvement, significantly improves the refined control level of pile foundation construction, and reduces the quality risk.

[0008] Optionally, constructing a dynamic association model based on the standard time series database, and establishing a quality determination standard for the pile foundation hole forming based on the dynamic association model, including: establishing a model data set based on the basic database, and constructing the dynamic association model between the key working parameters and the quality index data according to the model data set. The dynamic association model includes a verticality deviation model, a hole position deviation model, and a drilling depth model; the key working parameters are used as input parameters of the dynamic association model, and the quality index data is used as an output index of the dynamic association model. The correlation analysis is performed on the input parameters and the output index by a statistical method to obtain a correlation analysis result; determining the model form of the dynamic association model according to the correlation analysis result, and the model form includes a linear model or a non-linear model; optimizing and validating the model of the dynamic association model, and establishing the quality determination standard by using the model output of the dynamic association model. The present invention establishes a quantitative mapping relationship between parameters and quality indexes through historical data driving, realizes the interpretable deduction from construction parameters to hole forming quality, intelligently identifies the parameter coupling law based on statistical methods, automatically adapts to the linear or non-linear model structure, improves the prediction accuracy, and the model optimization and validation mechanism ensures the prediction reliability. Finally, a quality determination standard is constructed, converting empirical judgment into data-driven decision-making, turning quality control to process pre-control, significantly improving the early warning ability of quality anomalies, and providing a scientific basis for the dynamic adjustment of construction parameters.

[0009] Optionally, determining the model form of the dynamic association model according to the correlation analysis result, and the model form includes a linear model or a non-linear model, including: the linear model satisfies the following relationship: Where, is the dependent variable, is the regression coefficient to be fitted, is the independent variable, is the intercept term; the non-linear model includes a quadratic polynomial or a cubic polynomial and a non-linear exponential model: the quadratic polynomial satisfies the following relationship: The cubic polynomial satisfies the following relationship: Where, is the dependent variable, is the regression coefficient to be fitted, is the independent variable, is the intercept term; the non-linear exponential model satisfies the following relationship: Where, is the dependent variable, is the baseline parameter, is the exponential growth rate, is the independent variable, is the offset. Through correlation analysis, the present invention realizes the accurate selection of the model form. The linear model quantifies the multi-parameter synergistic effect in the form of a simple weighted sum. The quadratic or cubic polynomial expansion can capture the influence of the square term and interaction term of the independent variable. The non-linear exponential model adapts to the quality evolution characteristics with exponential laws, ensuring the calculation efficiency under simple working conditions and retaining the fitting ability for complex scenarios through high-order terms and exponential terms. The dynamic correlation model can adapt to the parameter coupling laws of different geological conditions and construction stages, significantly improving the universality and accuracy of quality prediction.

[0010] Optionally, the model optimization and model verification of the dynamic correlation model include: performing parameter fitting optimization on the linear model and the non-linear model through an optimization algorithm to obtain the optimal model parameters; performing validity test on the dynamic correlation model, and the validity test includes model fitting effect evaluation, residual analysis and cross-validation. The present invention improves the model accuracy through a parameter optimization algorithm, ensures that the parameter configuration reaches the optimal fitting state, and significantly reduces the prediction deviation; uses the fitting effect evaluation to quantify the model explanatory power, uses residual analysis to diagnose system deviation and abnormal points, and uses cross-validation to ensure the generalization performance of the model; effectively prevents overfitting, ensures the stability and prediction reliability of the dynamic correlation model under complex working conditions, provides a strictly verified scientific basis for the quality judgment standard, and significantly improves the accuracy of construction parameter regulation and the confidence level of quality early warning.

[0011] Optionally, the dynamic prediction of the pile foundation hole formation according to the dynamic correlation model to obtain the quality state of the pile foundation hole formation, and combining the quality judgment standard to obtain the quality deviation result of the pile foundation hole formation includes: using the real-time construction database as the model input of the dynamic correlation model, and performing real-time prediction through the dynamic correlation model based on the model input to obtain the model output, and the model output is the predicted quality state of the pile foundation hole formation; comparing the quality state of the pile foundation hole formation with the quality judgment standard in real time to obtain the quality deviation result. The present invention drives the iterative calculation of the model by real-time input of construction parameters, realizes the prediction of the quality of pile foundation hole formation, and forms a closed-loop control of monitoring, prediction and evaluation; feeds back the construction state in real time through the quality deviation result, converts the quality control from passive detection to active intervention, significantly shortens the problem response cycle, combines the parameter sensitivity analysis ability of the dynamic correlation model, accurately locates the root cause of the quality deviation, guides the dynamic optimization of the drill parameters, effectively reduces the rework rate and material waste, and at the same time, the accumulated deviation data continuously improves the quality judgment standard, promoting the intelligent iterative upgrade of the construction technology.

[0012] Optionally, taking the real-time construction database as the model input of the dynamic association model, and performing real-time prediction through the dynamic association model based on the model input to obtain a model output, where the model output is the predicted pile foundation hole forming quality status, including: Wherein, is the prediction index of the pile foundation hole forming quality, is the time, is the mapping function of the dynamic association model, is the real-time key working parameter, is the model parameter of the dynamic association model. Through the coupled calculation of real-time input of construction parameters and optimal model parameters, the present invention realizes the prediction of the pile foundation quality status; the introduction of the time variable enables the prediction to have the ability of time series evolution, and can capture the continuity characteristics of the construction process; the mapping function accurately depicts the complex association between the working parameters and the quality status, provides a quantitative decision-making basis for the dynamic optimization of the drilling rig parameters, and promotes the evolution of the construction technology towards a data-driven intelligent mode.

[0013] Optionally, constructing the regulation strategy of the drilling rig based on the quality deviation result, and adjusting the key working parameters according to the regulation strategy to realize the intelligent control of the quality of the pile foundation hole forming, including: the quality deviation result includes the quality deviation type and the quality deviation degree of the pile foundation hole forming; constructing the regulation strategy according to the quality deviation type and the quality deviation degree, and the regulation strategy includes the regulation of the over-limit verticality, the regulation of the hole position deviation and the regulation of the depth error. Through the classification and grading of the quality deviation, the present invention realizes the precise intervention of the construction parameters. The regulation of the over-limit verticality, the regulation of the hole position deviation and the regulation of the depth error form a multi-dimensional rectification system, which significantly improves the response accuracy of the quality abnormality; the dynamic adjustment mechanism based on the deviation degree can avoid over-correction, optimize the construction energy consumption on the premise of ensuring the quality compliance; realize the early warning and active repair of quality problems, effectively reduce the rework risk, and at the same time, the accumulated regulation cases can continuously optimize the regulation strategy to realize the intelligent iteration of the construction technology.

[0014] Optionally, the regulation of the over-limit verticality includes: Wherein, is the rotational speed adjustment amount of the drilling rig, is the proportional coefficient, is the verticality deviation amount, is the maximum allowable deviation amount of the verticality, is the integral coefficient, For the differential coefficient, the present invention realizes the precise regulation of the drilling rig attitude through the dynamic compensation of the perpendicularity deviation. The control mechanism of multi-parameter coordination endows the perpendicularity regulation with self-adaptive ability, significantly improves the vertical accuracy of hole formation, reduces the frequency of manual intervention. At the same time, the quantitative output of the rotational speed adjustment provides precise control instructions for the actuator of the drilling rig, forming a complete closed-loop from quality monitoring to parameter optimization.

[0015] In a second aspect, the present invention provides an intelligent control system for the quality of pile foundation hole formation based on the working parameters of the drilling rig. The system executes the intelligent control method for the quality of pile foundation hole formation based on the working parameters of the drilling rig provided by the present invention. The system includes an input device, an output device, a processor, and a memory. Its advantage lies in that: the hardware facilities integrated in the present invention have excellent performance. The input device, the output device, the processor, and the memory are interconnected with each other, and the information transmission between each component is smooth. Through the interaction of multiple hardware facilities, an efficient information processing system is constructed. Through the efficient information processing architecture of the present invention, the parallel processing ability of data acquisition, model training, and real-time prediction is guaranteed, the monitoring of the drilling rig parameters and the hole formation quality is realized, the real-time prediction of the dynamic correlation model is effectively supported, the quality deviation warning is realized, the regulation instruction is generated, the control closed-loop cycle is significantly shortened, the quality control is upgraded from manual experience-driven to data intelligent-driven, the construction accuracy and the abnormal response efficiency are greatly improved, and at the same time, the dependence on manual intervention is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of the intelligent control method for the quality of pile foundation hole formation based on the working parameters of the drilling rig according to an embodiment of the present invention; Figure 2 It is a framework diagram of the intelligent control system for the quality of pile foundation hole formation based on the working parameters of the drilling rig according to an embodiment of the present invention; Figure 3 It is a closed-loop flowchart of the intelligent control system for the quality of pile foundation hole formation based on the working parameters of the drilling rig according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] Specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described here are only for illustrative purposes and are not intended to limit the present invention. In the following description, in order to provide a thorough understanding of the present invention, a large number of specific details are set forth. However, it will be apparent to those of ordinary skill in the art that: it is not necessary to employ these specific details to practice the present invention. In other instances, well-known circuits, software, or methods have not been specifically described to avoid obscuring the present invention.

[0018] Throughout the specification, references to "an embodiment", "embodiments", "an example", or "examples" mean that the specific features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment of the present invention. Thus, the phrases "in an embodiment", "in embodiments", "an example", or "examples" appearing throughout the specification do not necessarily all refer to the same embodiment or example. In addition, the specific features, structures, or characteristics may be combined in any suitable combination and / or sub-combination in one or more embodiments or examples. Moreover, those of ordinary skill in the art should understand that the diagrams provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0019] Please refer to Figure 1 , an embodiment of the present invention provides an intelligent control method for the quality of pile foundation hole formation based on the working parameters of a drilling rig, and the method includes the following steps: S1. Construct a data acquisition array, obtain the key working parameters of the drilling rig and the quality index data of the pile foundation hole formation based on the data acquisition array, and establish a standard time series database.

[0020] In this embodiment, data collection is performed on the key working parameters of the drilling rig related to the quality index of the pile foundation hole formation, including the historical construction data and the real-time collected data of the drilling rig.

[0021] Before the formal construction, a trial drill is carried out in the area to be constructed, and the key parameters of the drilling rig operation under different geological conditions are collected. The initial real-time operation parameter data during the trial drill is used as the historical key working parameters, and the corresponding measured data of the pile foundation hole formation quality is used as the historical quality index data, so as to establish a basic database. According to this data, the model or functional relationship is corrected, and the relationship between the working parameters of the drilling rig and the quality index of the pile foundation hole formation and the pile foundation quality judgment standard are established.

[0022] During the formal construction process, high-frequency sensors installed on the drilling rig are used to collect the key operation parameters of the drilling rig in real time, and the collection frequency of the real-time data is set to ensure the real-time and integrity of all key data during the construction process.

[0023] The quality index of the pile foundation hole formation includes hole position deviation, verticality, and drilling depth. An intelligent sensing device is installed at the front end of the drilling rig to collect the quality index data of the hole formation.

[0024] The historical data provides a stable basis for the establishment of a dynamic association model. By reviewing the construction data under various geological conditions, the system can establish a relatively accurate association model before entering the formal construction. These data reflect the influence relationship between the working parameters of the drilling rig and the pile foundation quality under different environments. Using these historical data, the system can establish preliminary quality standards to ensure the effective docking of subsequent construction data with the standards.

[0025] The introduction of real-time data enables the model to continuously optimize and update during the construction process. As the construction progresses, new real-time construction data is continuously collected and stored. Each newly collected data can provide additional calibration and adjustment for the model. The model learns based on these data to continuously update and optimize, ensuring that it can cope with changes in the geological environment and construction conditions. This can more effectively adjust parameters and ensure the stability of the hole-forming quality.

[0026] Specifically, at the pile foundation construction site, data is collected on the key working parameters of the drill rig related to the pile foundation hole-forming quality indicators. High-frequency sensors installed at key parts of the drill rig are used to collect the key operating parameters of the drill rig in real time, and the collection frequency of real-time data is set to ensure the real-time and integrity of all key data during the construction process. The specific sensor layout is as follows: A rotational speed sensor (encoder) is installed on the power head of the drill rig to measure the rotational speed, with the unit of revolutions per minute. The collected data can be used to analyze the rotational condition of the drill bit and the construction efficiency; a torque sensor is installed at the torsional part of the drill pipe or drill bit to obtain the resistance torque, with the unit of Newton-meter (N·m); a pressure sensor is arranged on the hydraulic cylinder circuit to convert the propulsion stroke pressure (axial pressure); a displacement sensor or a sounding line is used to record the lifting and lowering displacement of the drill tool to calculate the drilling depth and speed; an inclination sensor is installed on the mast of the drill rig to monitor the verticality of the pile frame, with the unit of degree (°). The real-time collection frequency is not less than once per second.

[0027] In this embodiment, the characteristic value of the foundation bearing capacity is a design parameter given based on the investigation and specifications after comprehensively considering factors such as the shear strength, compressibility, and groundwater of the stratum. It directly reflects the ultimate pressure that the stratum can bear per unit area and is closely related to the resistance of the pile foundation to enter the soil, with the unit of kilopascal (kPa). In the present invention, the parameter represents the characteristic value of the foundation bearing capacity of the th layer of foundation soil. This value can be extracted from the engineering geological investigation report. The characteristic value of the foundation bearing capacity comprehensively reflects the strength and deformation properties of the soil layer and can effectively represent the comprehensive resistance of the rock and soil of this layer, serving as the basis for the composition of the rock and soil strength parameters in the model.

[0028] When the borehole penetrates multiple soil layers, the equivalent rock and soil strength can be calculated according to the weighted formula, satisfying the following relationship: where, is the rock and soil strength, is the total amount of rock layers, is the index variable of the rock layer, currently entering the th layer of rock layer thickness, is the current drilling depth, is the characteristic value of the bearing capacity of the foundation layer.

[0029] By collecting data on the construction process of drilling rigs under various geological conditions in historical construction projects, a historical construction database is formed. The database content includes drilling rig parameters such as bit rotation speed, torque, axial pressure, drilling displacement (speed), and drill pipe inclination angle, as well as corresponding measured quality indicators such as pile hole verticality, hole position deviation, and drilling depth error. These data will be used for subsequent model training and the establishment of quality judgment criteria.

[0030] Furthermore, for historical construction data collection, historical data of past pile foundation construction projects under various typical geological conditions are collected. The specific drilling rig parameters collected include rotation speed, torque, axial pressure, drilling displacement, and drill pipe inclination angle, and the corresponding hole-forming quality indicators, including pile hole verticality, hole position deviation, drilling depth error, etc., as well as the corresponding measured data of pile foundation hole-forming quality, to construct the basic database of historical construction, providing basic data for model training and verification. Through historical data analysis, a preliminary correlation model and quality judgment criteria between drilling rig parameters and hole-forming quality are established.

[0031] Furthermore, for real-time construction data collection, key operating parameters of the drilling rig are monitored in real time at the construction site. The drilling rig is equipped with sensors such as rotation speed sensors, torque sensors, axial pressure sensors, displacement sensors, and drill pipe inclination sensors. The real-time collection frequency is not less than once per second. Based on the collected real-time data, a real-time construction database is constructed for real-time prediction of hole-forming quality of the model, and an immediate comparison and analysis is carried out with the judgment criteria established from historical construction data to monitor the construction status in real time. At the same time, data on pile foundation hole-forming quality indicators (verticality, hole position deviation, drilling depth) are collected to establish a quality indicator database.

[0032] In this embodiment, all collected data should be stored in the database. The real-time construction data and historical construction data together form a data set. Each newly collected data needs to be combined with the historical data set. To ensure the effectiveness of the data, a time series database is used for data storage to ensure the high efficiency of data query and update. During the data collection process, all real-time data needs to be standardized to eliminate the dimensional differences of data from different sensors; for example, data such as rotation speed, torque, and pressure need to be transformed into a unified dimension through a standardization method; the standardization method satisfies the following relationship: where, is the standardized data, is the original data, is the mean of the original data, is the standard deviation of the original data.

[0033] S2. Build a dynamic association model based on the standard time series database, and establish the quality judgment criteria for the pile foundation hole forming based on the dynamic association model.

[0034] In this embodiment, based on historical construction data, the relationship between various working parameters of the drilling rig and the pile foundation hole forming quality indicators is analyzed through correlation analysis and statistical modeling methods to clarify the strength and form of the influence of parameters on the quality. Subsequently, a linear or non-linear model is used to fit and optimize the model parameters through the least squares method or the Levenberg-Marquardt algorithm (abbreviated as LM), and through cross-validation and residual analysis, the accuracy and reliability of the model prediction are ensured. Finally, a reliable dynamic association model between the operating parameters of the drilling rig and the hole forming quality is established, and the pile foundation quality judgment criteria are established based on the model output for real-time construction quality assessment.

[0035] Specifically, using historical construction data covering different geological conditions, changes in drilling rig parameters, and corresponding measured hole forming quality indicators, a dynamic association model between the working parameters of the drilling rig and the pile foundation hole forming quality indicators (verticality, hole position deviation, drilling depth) is established to learn the specific influence law of the changes in drilling rig parameters on the construction quality.

[0036] The specific implementation steps are as follows: S21. Based on physical mechanics and drilling technology principles, put forward the basic assumptions of the model: the higher the rotational speed, usually the faster the drilling speed, but too high a rotational speed may cause an increase in the swing of the drill pipe, affecting the verticality; the torque size is proportional to the formation properties, and too large a torque may cause uneven wear on the inner wall of the borehole, affecting the borehole position deviation and verticality; too large an axial pressure may cause uneven compression of the drill pipe, causing the drill pipe to bend, resulting in an increase in the inclination angle of the drill pipe, and further affecting the verticality and hole position deviation; too fast a drilling speed is likely to cause a decrease in the borehole verticality because the drill pipe is prone to swing during rapid drilling; the drill pipe inclination angle is directly strongly linearly or non-linearly correlated with the hole forming verticality.

[0037] It is assumed that the geotechnical strength parameters directly affect the resistance of the drill bit during the drilling process and the stability of the borehole, and thus affect the response relationship of parameters such as torque and axial pressure. In high-strength formations, if the axial pressure is insufficient, it may cause the drill bit to slip and the hole forming to be uneven; in low-strength soil layers, an unreasonable ratio of axial pressure to drilling speed is likely to cause borehole collapse. Therefore, there is an interaction relationship between the geotechnical strength and other construction parameters, and it needs to be incorporated as an independent feature into the dynamic association modeling to enhance the adaptability and accuracy of the model under complex geological conditions. The value of the geotechnical strength comprehensively considers the formation characteristics such as the compressive strength, shear strength, and friction force of the soil layer, and is specifically quantified by the characteristic value of the foundation bearing capacity.

[0038] S22. Establish a model data set. Use the data set that has collected and sorted out the drilling rig working parameters and the corresponding pile foundation hole forming quality indicators under different geological conditions as the training set to establish a dynamic correlation model. The historical data set includes the drilling rig working parameters and the pile foundation hole forming quality indicators: the drilling rig working parameters include rotational speed, torque, pressure, drilling displacement (speed), and drill pipe inclination angle, and these parameters will affect the quality of the drilled hole; the pile foundation hole forming quality indicators include hole position deviation, verticality, and drilling depth error, and these indicators are used to measure the hole forming quality. Assuming there are 𝑁 historical data records, the data set can be expressed as: Among them, is the drilling rig working parameter in the th historical data record, is the hole forming quality indicator in the historical data record, 𝑁 is the total amount of historical data records, is the index variable of the historical data record, is the rotational speed, is the torque, is the pressure, is the drilling displacement, is the drill pipe inclination angle, is the hole position deviation, is the verticality, is the drilling depth error.

[0039] S23. Parameter correlation analysis. To clarify the influence degree and relationship form of each input parameter (rotational speed, torque, axial pressure, drilling displacement (speed), and drill pipe inclination angle) on the output indicators (verticality, hole position deviation, and drilling depth), use statistical methods to quantitatively analyze the relationship between parameters. Use Pearson correlation coefficient and Spearman rank correlation coefficient for analysis.

[0040] Pearson correlation coefficient analysis is applicable to data sets where the relationship between parameters is approximately linear and the variables follow a normal distribution; it satisfies the following relationship: Among them, is the Pearson correlation coefficient, is the th measured value of the input parameter, is the mean value of the input parameter, is the th measured value of the output parameter, is the mean value of the output parameter.

[0041] Spearman rank correlation coefficient analysis is applicable to cases of non - linear relationships or non - normal distribution of data; it satisfies the following relationship: where, is the Spearman rank correlation coefficient, is the difference in the ranks of each group of data, is the total number of samples.

[0042] Specifically, the criteria for judging the strength of correlation are shown in Table 1: Table 1 S24. Model form and equation determination: After completing the correlation analysis, determine the mathematical form of the associated model, clarify the physical meanings of each parameter and the possible influence paths. For example, the rotational speed is related to the lateral swing of the drill pipe, and a non - linear relationship can be assumed; the torque and axial pressure have a more direct influence on the bending stiffness and drilling stability of the drill pipe, and a linear relationship or exponential relationship can be assumed; the inclination angle of the drill pipe directly reflects the deviation degree of the hole formation, and a linear or non - linear relationship with the verticality can be assumed; the drilling speed is directly related to the borehole stability and hole wall quality, and may be linear or non - linear.

[0043] Based on physical assumptions and preliminary analysis, select the model form. If the correlation analysis shows an obvious linear relationship, select a linear model, which satisfies the following relationship: where, is the dependent variable, is the regression coefficient to be fitted, is the independent variable, is the intercept term.

[0044] If there is an obvious non - linear relationship, use a quadratic polynomial or a cubic polynomial and a non - linear exponential model.

[0045] The quadratic polynomial satisfies the following relationship: The cubic polynomial satisfies the following relationship: where, is the dependent variable, is the regression coefficient to be fitted, is the independent variable, is the intercept term.

[0046] The non - linear exponential model (physical model - oriented) satisfies the following relationship: where, is the dependent variable, is the baseline parameter, is the exponential growth rate, is the independent variable, is the offset.

[0047] Specifically, the dynamic correlation model includes a verticality deviation model, a hole position deviation model, and a drilling depth model.

[0048] S241. Verticality deviation model; The verticality deviation refers to the verticality of the drill hole, that is, the degree of deviation between the actual drill axis and the designed axis. Assuming that the verticality deviation is affected by the rotational speed, torque, axial pressure, drilling speed, drill pipe inclination angle, and the properties of the rock and soil layer, it satisfies the following relationship: Linear model: Non-linear model (such as quadratic model): Among them, is the verticality deviation, are the regression coefficients to be fitted, is the rotational speed, is the torque, is the pressure, is the speed, is the drill pipe inclination angle, is the rock and soil strength, is the intercept term.

[0049] S242. Hole position deviation model; The hole position deviation refers to the deviation between the actual drill hole position and the designed position, which usually affects the hole forming quality and structural safety, and satisfies the following relationship: Linear model: Non-linear model (such as quadratic model): Among them, is the hole position deviation, are the regression coefficients to be fitted, is the rotational speed, is the torque, is the pressure, is the speed, is the drill pipe inclination angle, is the rock and soil strength, is the intercept term.

[0050] S243. The drilling depth model satisfies the following relationship: Linear model: Nonlinear model (such as quadratic model): where is the drilling depth error, is the regression coefficient to be fitted, is the rotational speed, is the torque, is the pressure, is the drill pipe inclination angle, is the velocity, is the geotechnical strength, is the intercept term.

[0051] S25, Determination of the optimal model parameters.

[0052] S251, Determination of the linear model parameters by the least squares method, satisfying the following relationship: where is the sum of squared residuals, is the total number of data samples, is the index variable of the data sample, is the parameter of the actual measured pile hole formation quality index, is the regression coefficient to be fitted, is the data sample, is the intercept term.

[0053] Furthermore, the pile hole formation quality index parameters include: establishing a linear model for each quality index separately, and each represents a single pile hole formation quality index, that is, constructing three independent equations, satisfying the following relationship: where represents the verticality model, is the regression coefficient to be fitted for the verticality model, is the data sample, represents the hole position deviation model, is the regression coefficient to be fitted for the hole position deviation model, represents the drilling depth model, is the regression coefficient to be fitted for the drilling depth model, is the intercept term.

[0054] Let the above function take the partial derivative with respect to each regression coefficient to be fitted and set it to 0, and establish a system of equations, satisfying the following relationship: where is the sum of squared residuals, is the regression coefficient to be fitted.

[0055] By solving the above linear equations, the parameter values of the regression coefficients can be obtained.

[0056] S252. Determine the parameters of the non - linear model using the LM algorithm.

[0057] S2521. Taking the deviation of the pile foundation verticality as an example, first, given the initial parameter values. The initial parameter values are generally determined according to empirical rules (such as obtained approximately by linear fitting) or randomly set within a small range, and satisfy the following relationship: where is the initial parameter vector, is the initial model parameter.

[0058] S2522. Construct the error function and the objective function. Define the error term as the difference between the actual measured value and the predicted value, and satisfy the following relationship: The objective function satisfies the following relationship: where is the error term of the th data group, is the model parameter, is the parameter of the actual measured pile foundation hole - forming quality index, is the prediction function of the non - linear model, is the sample, is the objective function, is the number of data groups, is the index variable of the data group.

[0059] S2523. The algorithm updates the parameters in each iteration. The specific steps are as follows: Calculate the Jacobian matrix. The Jacobian matrix represents the matrix of partial derivatives of the error function with respect to each parameter, and satisfies the following relationship: where is the Jacobian matrix, is the model parameter, is the error term of the th data group, is the regression coefficient to be fitted, is the number of data groups; is the number of parameters.

[0060] The algorithm iteratively updates the parameters and satisfies the following relationship: Among them, is the model parameter of the th iteration, is the model parameter of the th iteration, is the Jacobian matrix, represents the transpose, is the damping coefficient, is the identity matrix, is the error vector, is the th error term of the data group.

[0061] When the error function drops significantly, reduce the damping coefficient to approach the Gauss-Newton method; when the error function drops insignificantly or even increases, increase the damping coefficient to approach the gradient descent method.

[0062] S2524. Judgment of iteration termination condition.

[0063] When both the parameter convergence condition and the objective function convergence condition are satisfied, it is considered that the model has converged and the iteration update process is stopped. If only one of them is satisfied, the iteration still needs to continue until both are satisfied or the preset maximum number of iterations is reached.

[0064] Parameter convergence condition: The difference between two iterations of the parameter is less than the set threshold, satisfying the following relationship: Among them, is the model parameter of the th iteration, is the model parameter of the th iteration, is the threshold.

[0065] Objective function convergence condition: The change of the objective function between two iterations is less than the set threshold, satisfying the following relationship: Among them, is the objective function of the th iteration, is the objective function of the th iteration, is the threshold.

[0066] As the construction progresses, new real-time construction data is continuously collected and stored. When new data enters the system, incremental learning is carried out based on this data to continuously update and optimize the model. The core step of incremental learning is the update of the existing model. Whenever new real-time data is input, the model will gradually adjust its parameters through the incremental update algorithm without the need to perform full-scale training again.

[0067] The relationship between the working parameters of the drill rig and the hole forming quality is analyzed through correlation analysis and statistical modeling methods, and the fitting and optimization of the model parameters are carried out through optimization methods such as the least squares method and the LM algorithm. This process actually involves the determination of the model parameters, that is, how to determine the optimal parameters of the model through the training data. Incremental learning will calculate the impact of the data on the model parameters in real time without retraining the entire model, which enables the model to continuously optimize the model parameters and adjust according to the new data after each data collection.

[0068] S26. After the model parameters are fitted, it cannot be guaranteed that the model is completely effective. It is necessary to conduct an effectiveness test through model verification, and further adjust and optimize the model to improve its prediction accuracy. The model verification includes the following steps: S261. Model fitting effect evaluation; statistical indicators are used to evaluate the fitting effect, and the coefficient of determination satisfies the following relationship: Among them, is the coefficient of determination, is the actual value, is the model predicted value, is the mean of the actual values.

[0069] S262. Residual analysis, which satisfies the following relationship: Among them, is the error term of the th data group, is the actual value, is the model predicted value.

[0070] In an optional embodiment, a residual scatter plot is drawn to observe the distribution. The residuals should be randomly distributed around 0, and no obvious trend or pattern should appear; a residual histogram or a quantile-quantile plot (abbreviated as Q-Q plot) is drawn to test whether it is approximately normally distributed. A normal distribution indicates good model effectiveness, and a non-normal distribution requires re-examining the model.

[0071] S263. Cross-validation; an independent data set (test set) is used to evaluate the model prediction performance. The data is randomly divided into a training set and a test set; the parameters are fitted with the training set, and the prediction accuracy is tested with the test set.

[0072] The root mean square error satisfies the following relationship: The mean absolute percentage error satisfies the following relationship: Among them, is the root mean square error, is the total amount of data, is the index variable, is the actual value, is the model prediction value, is the mean absolute percentage error.

[0073] S27. Based on the trained dynamic association model, establish the judgment criteria for the quality of pile hole formation, which is used to judge whether the quality predicted in real time during the construction meets the requirements.

[0074] Specifically, the output of the model will be compared with the preset quality tolerance error range. For example, set the tolerance error range of verticality, the tolerance error range of hole position deviation, and the tolerance error range of drilling depth; if the model prediction result exceeds these tolerance ranges, it means that there is a quality deviation, and an alarm needs to be triggered and enter the subsequent feedback regulation stage.

[0075] The model output satisfies the following relationship: Among them, is the model output, is the predicted value of hole position deviation, is the predicted error of verticality, is the predicted value of drilling depth error.

[0076] The tolerance error range of hole position deviation satisfies the following relationship: Among them, is the predicted value of hole position deviation, is the minimum allowable amount of hole position deviation, is the maximum allowable amount of hole position deviation.

[0077] The tolerance error range of verticality satisfies the following relationship: Among them, is the predicted error of verticality, is the minimum allowable deviation of verticality, is the maximum allowable deviation of verticality.

[0078] The tolerance error range of drilling depth satisfies the following relationship: Among them, is the predicted value of drilling depth error, is the minimum allowable amount of drilling depth error, is the maximum allowable amount of drilling depth error.

[0079] The updated dynamic association model will better adapt to the changes in the construction environment and improve the accuracy of real-time prediction. The above-mentioned historical construction data collection and real-time construction data collection are interrelated through data standards. Specifically, during the construction process, the real-time data collected is immediately compared and analyzed with the initial dynamic association model and quality determination criteria established for the historical construction data, so as to realize the real-time and accurate judgment of the quality of pile foundation hole formation.

[0080] S3. Dynamically predict the pile foundation hole formation according to the dynamic association model to obtain the quality state of the pile foundation hole formation, and combine the quality determination criteria to obtain the quality deviation result of the pile foundation hole formation.

[0081] In this embodiment, the working parameters of the drill rig monitored in real time are input into the dynamic association model, and the dynamic association model is used to dynamically predict the current quality state of the pile foundation hole formation in real time and identify possible quality deviations. The real-time prediction results are compared and analyzed with the established quality standards. If the limit is exceeded, an early warning is triggered, and the data review or correction mechanism is used to ensure the prediction accuracy, providing a basis for dynamic regulation.

[0082] Specifically, the working parameters of the drill rig (such as rotation speed, torque, pressure, speed (displacement), drill pipe inclination angle) collected in real time are used as input data and input into the previously trained dynamic association model. The input of the model is the real-time data of the working parameters of the drill rig, and the output is the predicted quality state of the pile foundation hole formation, including quality indicators such as hole position deviation, verticality, and drilling depth. The input data satisfies the following relationship: Among them, is the real-time key working parameter, is the time, is the rotation speed, is the torque, is the pressure, is the speed, is the drill pipe inclination angle.

[0083] Specifically, for each real-time collected sample, real-time prediction is carried out through the model to obtain the predicted value of the quality index of the pile foundation hole formation at the current moment. The predicted value represents the quality state of the pile foundation hole formation under the current construction state; the prediction frequency is synchronized with the data collection frequency (not less than once per second) to ensure real-time performance.

[0084] The predicted value of the quality index satisfies the following relationship: Among them, is the predicted value of the quality index, is the time, is the predicted value of the hole position deviation, is the verticality prediction error, is the predicted value of the drilling depth error.

[0085] The prediction process satisfies the following relationship: Among them, is the prediction index of the pile foundation hole forming quality, is the time, is the mapping function of the dynamic correlation model, is the real-time key working parameter, is the model parameter of the dynamic correlation model.

[0086] In an optional embodiment, a sliding window mechanism is adopted. According to the dynamic characteristics of the construction process (such as the change frequency of the drill rig parameters), the time span of the sliding window is defined, and short-term trend analysis is carried out in combination with recent historical data to reduce instantaneous noise interference. In the conventional soil layer, the window length is set to 10 seconds (1 sampling per second, and the window contains 10 groups of data). The real-time data is stored in the time series database according to the time stamp.

[0087] Each time new data arrives, the moment to the moment of 10 groups of data is extracted to form a window data set. The window slides forward with the arrival of new data (removing the oldest data , adding ), and the window content is updated dynamically.

[0088] The window data set satisfies the following relationship: Among them, is the window data set, is the drill rig parameter at the moment, is the rotational speed, is the torque, is the pressure, is the speed, is the drill pipe inclination angle.

[0089] Specifically, for trend feature extraction, a straight line is fitted to the parameter sequence within the window, and the slope is calculated as the trend intensity, which satisfies the following relationship: Among them, is the trend intensity, is the relative time within the window, is the parameter value.

[0090] Further, calculate the difference between the first and last data within the calculation window to measure the parameter change range, which satisfies the following relationship: Wherein, is the parameter change range, is the data value at the first position of the window, is the data value at the last position of the window.

[0091] Furthermore, calculate the moving average, which satisfies the following relationship: Wherein, is the moving average, are the data values within the window.

[0092] Expand the original input to satisfy the following relationship: Wherein, is the trend prediction value within the window, is the drilling rig parameters at time is the rotational speed, is the torque, is the pressure, is the speed, is the drill pipe inclination angle, is the window average value of the rotational speed, is the dynamic change rate of the rotational speed, is the parameter change range, is the standard deviation of the pressure, is the window average value of the drill pipe inclination angle, is the dynamic change rate of the drill pipe inclination angle.

[0093] The abnormal point determination condition satisfies the following relationship: Wherein, is the drilling rig parameters at time is the trend prediction value within the window, is the standard deviation within the window.

[0094] If the above abnormal point determination condition is satisfied, it is determined as an abnormal point, and data review or model prediction result correction is triggered.

[0095] In this embodiment, compare the quality index predicted in real time with the preset quality determination criteria to determine whether there is a quality deviation. The preset quality determination criteria include the allowable error range of the perpendicularity, the allowable error range of the hole position deviation, and the allowable error range of the drilling depth.

[0096] Immediately compare the predicted quality indicators with the pre-established standards in real time. Once the prediction results show that there may be a risk of quality deviation, such as the pile hole may be skewed or the hole position is significantly deviated, the system immediately triggers an automatic warning prompt and is ready to enter the feedback regulation stage.

[0097] S4. Construct the regulation strategy of the drilling rig based on the quality deviation result, and adjust the key working parameters according to the regulation strategy to realize the intelligent control of the quality of the pile foundation hole forming.

[0098] In this embodiment, for the predicted hole forming quality problems or deviations, through a closed-loop feedback control system, a dynamic feedback regulation strategy and regulation instructions are automatically generated, the adjustment scheme of the drilling rig operation parameters is determined, and the drilling rig parameters are adjusted in real time automatically to quickly correct the hole forming quality deviation and correct the quality problems. The closed-loop control architecture forms an adaptive regulation closed-loop through the linkage of sensors, model prediction and execution devices.

[0099] Specifically, the intelligent control system automatically generates a dynamic feedback regulation strategy for the operation parameters of the drilling rig. For example, it is necessary to reduce the drilling speed or adjust the drill bit rotation speed to correct the hole inclination, or adjust the axial pressure to correct the hole position deviation, etc. It is implemented in a timely manner through a closed-loop feedback control system to automatically correct the quality deviation in the construction process. The system automatically issues the generated regulation instructions directly to the automatic closed-loop control execution device of the drilling rig, and immediately implements the real-time adjustment of the parameters to quickly and efficiently solve the quality deviation problem in the construction process and ensure the hole forming quality.

[0100] According to the type and degree of the hole forming quality deviation predicted in real time, generate regulation instructions through a rule engine and an optimization algorithm: S41. Regulation for over-limit verticality.

[0101] If the predicted value of the verticality is greater than the maximum allowable deviation of the verticality, give priority to reducing the rotation speed to reduce the lateral swing, and finely adjust the inclination angle of the drill pipe through a hydraulic deviation correction system.

[0102] Based on the Proportional-Integral-Derivative Control Algorithm (PID for short), adjust the parameters according to the deviation ratio to satisfy the following relationship: Among them, is the adjustment amount of the rotation speed of the drilling rig, is the proportional coefficient, is the verticality deviation amount, is the maximum allowable deviation of the verticality, is the integral coefficient, is the differential coefficient.

[0103] It should be noted that the proportional coefficient, integral coefficient, and differential coefficient are empirical tuning parameters, which are optimized and determined through historical data.

[0104] S42. Hole position deviation control.

[0105] If the predicted value of the hole position deviation is greater than the maximum allowable amount of the hole position deviation, reduce the axial pressure to reduce the lateral force of the drill bit, and adjust the drilling direction.

[0106] S43. Depth error control.

[0107] If the predicted value of the drilling depth error is greater than the maximum allowable amount of the drilling depth error, increase the calibration frequency of the displacement sensor, and dynamically correct the drilling speed.

[0108] Please refer to Figure 2 , in an optional embodiment, the present invention provides an intelligent control system for the quality of pile foundation hole formation based on the working parameters of the drilling rig. The system includes an input device, an output device, a processor, and a memory, and the hardware facilities are interconnected. Among them, the memory is used to store computer programs, and the computer programs include program instructions. The processor is configured to call the program instructions to execute the specific steps of the related embodiments of the intelligent control method for the quality of pile foundation hole formation based on the working parameters of the drilling rig provided by the present invention. The intelligent control system for the quality of pile foundation hole formation based on the working parameters of the drilling rig provided by the present invention has a complete structure, is objective and stable, and improves the overall applicability and practical application ability of the present invention.

[0109] Please refer to Figure 3 , in an optional embodiment, the rotation speed, torque, pressure, speed, and inclination angle obtained by the drilling rig sensors are used as the original signals. The real-time data acquisition system acquires the original signals and uses them as data inputs, which are input into the dynamic model for hole formation quality prediction. Subsequently, according to the prediction results, the intelligent control algorithm generates control commands, and the control commands are transmitted to the drilling rig actuator to adjust the rotation speed, torque, axial pressure, speed, and inclination angle, so as to realize the intelligent adjustment of drilling parameters and continuously monitor in real time to form a closed loop. The intelligent control system goes further on the basis of real-time monitoring. Through closed-loop control, it dynamically adjusts the drilling parameters to ensure that the hole formation quality is in a controlled state. It collects the drilling rig parameters through sensors, uses the intelligent control algorithm to predict the quality, and feedback-controls the drilling device to achieve closed-loop adaptive control.

[0110] In summary, the intelligent control method and system for the pile hole forming quality based on the working parameters of the drilling rig provided by the method of the present invention, by comprehensively analyzing the dynamic correlation between the key parameters of the drilling rig and the pile hole forming quality in real time, uses the dynamic correlation model to realize the real-time and accurate prediction of the pile hole forming quality, and performs closed-loop real-time feedback adjustment, thereby significantly improving the timeliness, accuracy and economy of the pile hole forming quality control. The method of the present invention is easy to understand, simple in calculation, small in workload, and convenient for engineering application, providing a theoretical basis and technical support for the further development of the pile foundation construction technology.

[0111] 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 them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the various embodiments of the present invention, and they should all be covered by the scope of the claims and the specification of the present invention.

Claims

1. An intelligent control method for the quality of pile foundation hole formation based on the working parameters of a drilling rig, characterized in that, Including the following steps: Construct a data acquisition array, obtain the key working parameters of the drilling rig and the quality index data of the pile foundation hole formation based on the data acquisition array, and establish a standard time series database; Construct a dynamic association model based on the standard time series database, and establish a quality determination standard for the pile foundation hole formation based on the dynamic association model; Dynamically predict the pile foundation hole formation according to the dynamic association model to obtain the quality status of the pile foundation hole formation, and combine the quality determination standard to obtain the quality deviation result of the pile foundation hole formation; Construct a regulation strategy for the drilling rig based on the quality deviation result, and adjust the key working parameters according to the regulation strategy to realize intelligent quality control of the pile foundation hole formation.

2. The intelligent control method for the quality of pile foundation hole formation based on the working parameters of the drilling rig according to claim 1, characterized in that The construction of the data acquisition array, obtaining the key working parameters of the drilling rig and the quality index data of the pile foundation hole formation based on the data acquisition array, and establishing a standard time series database include: Construct the data acquisition array based on high-frequency sensors and intelligent sensing devices; Conduct a trial drill on the construction area to be drilled, obtain the initial real-time operation parameters of the drilling rig as historical key working parameters through the data acquisition array, and obtain the historical quality index data of the pile foundation hole formation by using the data acquisition array; Establish a basic database based on the historical key working parameters and the historical quality index data; During the construction process, construct a real-time construction database based on the real-time key working parameters of the drilling rig obtained by the data acquisition array, and establish a quality index database by collecting the real-time quality index data of the pile foundation hole formation through the data acquisition array; Perform standardization processing on the basic database, the real-time construction database, and the quality index database to establish the standard time series database.

3. The intelligent control method for the pile hole forming quality based on the working parameters of the drilling rig according to claim 2, characterized in that, The construction of the dynamic association model based on the standard time series database, and the establishment of the quality determination standard for the pile foundation hole formation based on the dynamic association model include: Establish a model data set based on the basic database, and construct the dynamic association model between the key working parameters and the quality index data according to the model data set. The dynamic association model includes a verticality deviation model, a hole position deviation model, and a drilling depth model; The key working parameters serve as the input parameters of the dynamic association model, and the quality index data serves as the output index of the dynamic association model. Perform a correlation analysis on the input parameters and the output index through statistical methods to obtain a correlation analysis result; Determine the model form of the dynamic association model according to the correlation analysis result. The model form includes a linear model or a non-linear model; Perform model optimization and model verification on the dynamic association model, and establish the quality determination standard by using the model output of the dynamic association model.

4. The intelligent control method for pile foundation hole forming quality based on the working parameters of the drilling rig according to claim 3, wherein, The determination of the model form of the dynamic association model according to the correlation analysis result, and the model form includes a linear model or a non-linear model, includes: The linear model satisfies the following relationship: Among them, is the dependent variable, is the regression coefficient to be fitted, is the independent variable, is the intercept term; The non-linear model includes a quadratic polynomial or a cubic polynomial and a non-linear exponential model: The quadratic polynomial satisfies the following relationship: The cubic polynomial satisfies the following relationship: wherein, is the dependent variable, is the regression coefficient to be fitted, is the independent variable, is the intercept term; The non - linear exponential model satisfies the following relationship: Among them, is the dependent variable, is the baseline parameter, is the exponential growth rate, is the independent variable, is the offset.

5. The intelligent control method for the quality of pile foundation hole formation based on the working parameters of the drilling rig according to claim 3, characterized in that, The model optimization and model verification of the dynamic correlation model include: Using an optimization algorithm to perform parameter fitting optimization on the linear model and the non - linear model to obtain the optimal model parameters; Performing validity tests on the dynamic correlation model, and the validity tests include model fitting effect evaluation, residual analysis, and cross - validation.

6. The intelligent control method for the pile hole forming quality based on the working parameters of the drilling rig according to claim 2, wherein, Based on the dynamic correlation model, dynamically predicting the pile foundation hole forming to obtain the quality status of the pile foundation hole forming, and combining with the quality judgment standard to obtain the quality deviation result of the pile foundation hole forming, including: Taking the real - time construction database as the model input of the dynamic correlation model, and performing real - time prediction through the dynamic correlation model based on the model input to obtain the model output, where the model output is the predicted quality status of the pile foundation hole forming; Comparing the quality status of the pile foundation hole forming with the quality judgment standard in real - time to obtain the quality deviation result.

7. The intelligent control method for the quality of pile foundation hole forming based on the working parameters of the drilling rig according to claim 6, characterized in that Taking the real - time construction database as the model input of the dynamic correlation model, and performing real - time prediction through the dynamic correlation model based on the model input to obtain the model output, where the model output is the predicted quality status of the pile foundation hole forming, including: Among them, is the prediction index for the quality of pile foundation hole formation, is the time, is the mapping function of the dynamic correlation model, is the real-time key working parameter, is the model parameter of the dynamic correlation model.

8. The intelligent control method for pile foundation hole forming quality based on the working parameters of the drilling rig according to claim 1, characterized in that, Constructing a regulation strategy for the drilling rig based on the quality deviation result, and adjusting the key working parameters according to the regulation strategy to achieve intelligent quality control of the pile foundation hole forming, including: The quality deviation result includes the quality deviation type and the quality deviation degree of the pile foundation hole forming; Constructing the regulation strategy according to the quality deviation type and the quality deviation degree, and the regulation strategy includes verticality over - limit regulation, hole position deviation regulation, and depth error regulation.

9. The intelligent control method for the pile hole forming quality based on the working parameters of the drilling rig according to claim 8, wherein The verticality over - limit regulation includes: Among them, is the rotational speed adjustment amount of the drill rig, is the proportionality coefficient, is the perpendicularity deviation amount, is the maximum allowable deviation amount of perpendicularity, is the integral coefficient, is the differential coefficient.

10. An intelligent control system for the quality of pile foundation hole formation based on the working parameters of the drilling rig, characterized in that, The system includes an input device, an output device, a processor, and a memory. The input device, the output device, the processor, and the memory are interconnected. Among them, the memory is used to store computer programs, the computer programs include program instructions, and the processor is configured to call the program instructions to execute the intelligent quality control method for pile foundation hole forming based on the working parameters of the drilling rig as described in any one of claims 1 - 9.

Images