Method for integrated detection and intelligent control of rotary drilling cast-in-place pile hole forming quality based on multiple parameters

Abstract

The application discloses a method for integrated detection and intelligent regulation of multiple parameters of hole-forming quality of rotary drilling bored pile, and relates to the technical field of intelligent monitoring of pile foundation construction. The method comprises system initialization and parameter presetting, loading of construction design parameters, completion of equipment communication connection and self-checking, setting of safety threshold and regulation rules; real-time acquisition of multiple parameters, synchronous acquisition of parameters by a sensor suite and transmission of the parameters to an edge computing gateway; data fusion and feature extraction, extraction of key features after processing of original data, transmission of the key features to a decision layer and a cloud platform; intelligent diagnosis and risk prediction, judgment of abnormalities and prediction of risks in combination with a rule base and a machine learning model; hierarchical intelligent regulation, execution of prompt warning according to the degree of abnormality, automatic fine adjustment or shutdown protection; hole-forming acceptance and data archiving, generation of a digital quality report. The application realizes real-time and accurate detection and intelligent regulation of multiple parameters, predicts risks in advance, adapts to complex strata and large-scale construction, and greatly improves hole-forming quality and construction efficiency.

Description

Technical Field

[0001] This invention relates to the field of intelligent monitoring technology for pile foundation construction, and in particular to a method for integrated detection and intelligent control of multiple parameters of the borehole quality of rotary drilled cast-in-place piles. Background Technology

[0002] Rotary drilling piles, as a core form of building foundation engineering, directly determine the bearing capacity of the pile foundation and the overall safety of the project through the quality of their drilling. They are widely used in infrastructure projects such as bridges, high-rise buildings, and large factories. Traditional drilling quality control relies primarily on "post-construction inspection," depending on methods such as ultrasonic borehole wall testing before drilling. This approach can only detect problems such as borehole diameter deviation, excessive verticality, and borehole wall instability after construction is complete, and cannot intervene during the construction process for real-time correction. This method is not only extremely inefficient, but by the time problems are discovered, irreversible damage such as borehole wall collapse and excessive sediment has often occurred, leading to extensive rework, increased construction costs and timelines, and potentially leaving hidden hazards that affect the long-term safety of the project.

[0003] Existing process monitoring solutions have significant shortcomings and fail to meet the demands of high-quality construction. These solutions often rely on single sensors to collect limited parameters, monitoring only a few indicators such as borehole depth or mud density, lacking simultaneous monitoring and correlation analysis of key parameters like verticality, drilling speed, and formation changes. Data processing remains at the level of simple acquisition and display, lacking refined processing such as time synchronization and filtering / noise reduction. Abnormal data interference is significant, making it impossible to extract effective features to support intelligent decision-making. The diagnostic and control processes lack systematic design, relying solely on preset thresholds for simple alarms, lacking risk prediction capabilities, and unable to anticipate potential problems such as borehole collapse and necking. Furthermore, control strategies are simplistic, heavily reliant on manual adjustments by the operator, heavily influenced by experience levels, resulting in low deviation correction accuracy and difficulty adapting to complex formations and variable construction environments.

[0004] Insufficient intelligence and collaborative management capabilities further constrain construction quality and efficiency. The existing system lacks a complete closed-loop system of "detection-diagnosis-control-archiving," with data stored in a scattered manner, lacking unified digital archives and visualization, and unable to achieve "one file per pile" traceability and big data analysis. Remote management functions are weak, only allowing viewing of basic data, unable to remotely intervene and control, making it difficult to adapt to unattended or cross-regional construction scenarios. When multiple machines are operating, the lack of a collaborative scheduling mechanism leads to mutual interference between adjacent drilling rigs, chaotic allocation of mud circulation and transportation resources, inconsistent quality standards, and overall low efficiency during large-scale construction. Furthermore, the system lacks self-learning capabilities and cannot optimize control parameters based on historical construction data, making it difficult to improve quality stability and adaptability over long-term use. Summary of the Invention

[0005] The present invention proposes a multi-parameter integrated detection and intelligent control method for the borehole quality of rotary drilling cast-in-place piles to solve the problems mentioned in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a multi-parameter integrated detection and intelligent control method for the borehole quality of rotary drilling cast-in-place piles, comprising the following steps: The system initialization and parameter preset steps include loading construction design drawings to obtain preset parameters, completing communication connections and self-tests of sensor kits, edge computing gateways, drilling rig control systems, and cloud monitoring platforms, setting multi-parameter safety thresholds, quality assessment standards, and hierarchical control rules, and constructing an intelligent diagnostic system that combines rule bases and machine learning models. The multi-parameter real-time acquisition process involves synchronously acquiring key parameters through the sensor suite integrated into the drill pipe, using a GNSS positioning antenna combined with a rotary encoder for dual verification to obtain hole depth and drilling speed, monitoring the X and Y tilt angles of the drill pipe through a dual-axis tilt sensor, and acquiring mud flow rate and density parameters using an online mud monitor. In the data fusion and feature extraction steps, the edge computing gateway performs time synchronization, filtering and noise reduction, and coordinate unification processing on the raw data, removes abnormal data points, extracts key features, and transmits the processed structured data to the decision-making layer and cloud monitoring platform. The intelligent diagnosis and risk prediction steps are based on a preset rule base to make real-time judgments on parameters exceeding limits. Through machine learning models, the drilling speed, drilling pressure, mud parameters and formation information are integrated to predict the probability of borehole stability risk and generate a borehole quality health score. The hierarchical intelligent control steps execute corresponding control strategies based on the diagnostic results. Minor anomalies are displayed on the HMI screen in the cab and a voice alarm is issued. Moderate anomalies trigger the drilling rig control system to automatically fine-tune the mast straightening cylinder or mud ratio. Severe anomalies immediately trigger the shutdown protection and initiate the emergency response process. After drilling to the design elevation, the entire process of inspection data and control records is automatically integrated and stored as a "one pile, one file" through the cloud monitoring platform.

[0007] Furthermore, it also includes a step for predicting the stability risk of the borehole wall, using a formula. Calculate the risk value of borehole wall instability, where This represents the risk value for the stability of the borehole wall. The drilling speed affects the weight. This represents the actual drilling speed. To correspond to the standard drilling speed of the formation, The index is affected by drilling speed. The weighting is determined by the influence of mud density. The actual mud density, To determine the optimal mud density for the corresponding formation, The mud density influence index, The weighting is determined by the impact of drilling pressure. This refers to the actual drilling pressure. To correspond to the standard drilling pressure of the formation, The drilling pressure impact index is divided into three risk levels: low, medium, and high, based on the risk value.

[0008] Furthermore, it also includes an adaptive adjustment step for verticality deviation, which combines data on drill pipe inclination angle, drill pipe length, and hole depth using a formula. Calculate the adjustment amount of the mast straightening cylinder, where For the adjustment amount of the hydraulic cylinder, The drill pipe extension length. For drill pipe Direction tilt angle, For drill pipe The tilt angle is adjusted automatically by controlling the extension and retraction of the straightening cylinder, and the drilling pressure distribution is corrected synchronously.

[0009] Furthermore, it also includes intelligent control steps for mud parameters. Based on mud flow and density detection data and formation characteristics, a mud performance optimization model is constructed to automatically calculate the required amount of fresh mud replenishment and the proportion of additives. The automatic mud preparation system is linked to control the mixing ratio of water, bentonite and additives in the mud tank, and the changing trend of mud parameters after adjustment is monitored in real time.

[0010] Furthermore, it also includes a formation adaptive adjustment step, which identifies the current drilling formation type by collecting multi-parameter data, calls the formation and construction parameter matching database, and automatically optimizes the drilling speed, drilling pressure, mud parameters and mixing frequency. In sandy formations, it increases mud density and drilling speed, in clay formations it reduces drilling pressure and optimizes mud fluidity, and predicts and smoothly transitions parameters at formation change interfaces in advance.

[0011] Furthermore, it also includes remote collaborative control steps, establishing a real-time communication link between on-site construction equipment and the remote control center through a cloud monitoring platform. Remote terminals can view real-time data of multiple parameters, hole formation quality scores, and control execution records. Remote operation commands are executed after identity verification, permission review, and encrypted transmission, supporting online collaborative analysis of abnormal issues by multiple professionals.

[0012] Furthermore, it also includes data visualization and traceability optimization steps, building a digital twin model of the hole-forming process on the cloud monitoring platform, mapping the dynamic changes of key indicators in real time, generating a three-dimensional hole-forming trajectory map and parameter trend curves, and the digital quality report includes three core contents: a full-process data time series table, abnormal event analysis, and control effect evaluation.

[0013] Furthermore, it also includes a self-learning optimization step for construction parameters, collecting detection data, control records and quality results of multiple pile drilling, constructing a database related to construction parameters and drilling quality, analyzing the advantages and disadvantages of parameter combinations under different working conditions through reinforcement learning algorithms, and automatically updating the parameter optimization model and control rule library.

[0014] Furthermore, it also includes safety interlock control steps, setting multi-parameter safety interlock thresholds. When the drill pipe tilt angle exceeds the limit, mud leakage or other emergency is detected, multi-level safety protection is automatically triggered, immediately cutting off the drilling rig power source, shutting down the mud delivery pump, activating on-site audible and visual alarms and emergency ventilation equipment, and simultaneously sending emergency alarm information to construction management personnel and regulatory departments, recording the time of the safety incident, parameter data, and handling process.

[0015] Furthermore, it also includes multi-machine collaborative operation control steps. When multiple drilling rigs are operating in the same construction area, multi-machine data sharing and collaborative scheduling are completed through the cloud monitoring platform. Based on the drilling progress, quality status, and formation distribution of each drilling rig, the resource allocation of the mud circulation system and transportation equipment is coordinated, data standards and quality requirements are unified, and a comprehensive regional construction quality report is generated.

[0016] Compared with existing technologies, the beneficial effects of this invention are: The multi-parameter integrated detection and intelligent control method for rotary drilling cast-in-place pile hole quality of this invention realizes a fundamental transformation in hole quality control from "post-event remediation" to "intelligent process management," with significant core advantages. The multi-parameter integrated detection mode breaks through the limitations of traditional single-parameter monitoring, simultaneously collecting key parameters such as hole depth, verticality, and mud indicators. Through dual verification, precise sensing, and refined data processing, it ensures that the detection data is comprehensive, real-time, and reliable, providing solid data support for subsequent diagnosis and control, and solving the pain points of traditional detection methods that are one-sided and data distortion.

[0017] The intelligent diagnostic and hierarchical control capabilities have been significantly improved. Through a diagnostic system combining a rule base and machine learning models, it can not only identify parameter anomalies in real time but also accurately predict potential risks such as borehole wall instability, thus identifying the root cause of problems in advance. The hierarchical control strategy flexibly executes measures such as alerts, automatic fine-tuning, and shutdown protection based on the severity of the anomaly, achieving an organic combination of manual operation and automatic control. This results in timely and precise control responses, reducing human intervention errors, effectively avoiding quality problems such as borehole collapse and necking, and improving the stability and consistency of borehole quality.

[0018] Data visualization and end-to-end traceability enhance construction management efficiency. A digital twin model is built through a cloud monitoring platform, mapping construction status in real time. The generated digital quality reports contain full-process data and control records. The "one pile, one file" storage mode supports multi-dimensional querying and traceability, providing a complete basis for project acceptance and process optimization. Remote collaborative control functions support real-time viewing and operation on multiple terminals, meeting the needs of cross-regional, unattended construction. A multi-machine collaborative scheduling mechanism optimizes resource allocation, reduces mutual interference, and improves the efficiency of large-scale construction. Self-learning optimization capabilities allow the system to continuously accumulate construction data, update control models and parameters, and gradually adapt to different geological formations and working conditions. Long-term use further reduces rework rates and construction costs, driving the development of rotary drilling grouting pile construction towards intelligence, efficiency, and high quality. Attached Figure Description

[0019] Figure 1 This is a schematic block diagram of the multi-parameter integrated detection and intelligent control method for the borehole quality of rotary drilling cast-in-place piles proposed in this invention; Figure 2 A bar chart comparing the accuracy of multi-parameter detection; Figure 3 A line graph showing the variation of borehole wall stability risk prediction accuracy with drilling depth; Figure 4 A line graph showing the relationship between response time and anomaly level. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0022] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, the terms "installed," "connected," and "linked" should be interpreted broadly; for example, they may refer to a fixed connection, a detachable connection, or an integral connection; they may refer to a mechanical connection or an electrical connection; they may refer to a direct connection or an indirect connection through an intermediate medium; and they may refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. The invention will now be described in further detail with reference to the accompanying drawings.

[0023] Reference Figures 1 to 4 A method for integrated detection and intelligent control of multi-parameter parameters for the quality of rotary drilling cast-in-place piles includes the following steps: The system initialization and parameter preset steps load the construction design drawings to obtain preset parameters such as hole depth, hole diameter, and pile position coordinates. It completes the communication connection and self-test of the sensor kit, edge computing gateway, drilling rig control system, and cloud monitoring platform. It sets multi-parameter safety thresholds, quality assessment standards, and hierarchical control rules, and builds an intelligent diagnostic system that combines rule base and machine learning model. The multi-parameter real-time acquisition process involves synchronously acquiring key parameters through the sensor suite integrated into the drill pipe, using a GNSS positioning antenna combined with a rotary encoder for dual verification to obtain hole depth and drilling speed, monitoring the X and Y tilt angles of the drill pipe through a dual-axis tilt sensor, and acquiring mud flow and density parameters using an online mud monitor. All parameters are transmitted to the edge computing gateway at a frequency of once per second. In the data fusion and feature extraction steps, the edge computing gateway performs time synchronization, filtering and noise reduction, and coordinate unification processing on the raw data, removes abnormal data points, and extracts key features such as verticality deviation trend, mud index fluctuation amplitude, and drilling speed change rate. The processed structured data is then transmitted to the decision-making layer and cloud monitoring platform. The intelligent diagnosis and risk prediction steps are based on a preset rule base to make real-time judgments on parameters exceeding limits. Through machine learning models, the drilling speed, drilling pressure, mud parameters and formation information are integrated to predict the probability of borehole stability risk, generate a borehole quality health score, analyze the root causes of abnormal problems and classify and mark them. The hierarchical intelligent control steps execute corresponding control strategies based on the diagnostic results. Minor anomalies are indicated by displaying prompts on the HMI screen in the cab and issuing voice alarms, guiding the operator to adjust the drilling speed and drilling pressure. Moderate anomalies trigger the drilling rig control system to automatically fine-tune the mast straightening cylinder or mud ratio. Severe anomalies immediately trigger the shutdown protection and initiate the emergency response process. The borehole acceptance and data archiving process automatically integrates all process testing data and control records after drilling to the design elevation, generating a digital borehole quality report. The report is stored in a "one-file-per-hole" manner through a cloud monitoring platform, supporting data traceability, visualization, and big data analysis applications.

[0024] This invention also includes a step for accurately predicting the stability risk of the pore wall, which involves constructing a risk prediction model based on multi-parameter fusion data and using formulas. Calculate the risk value of borehole wall instability, where The range of the hole wall stability risk value is 0-10. The drilling speed affects the weight. This represents the actual drilling speed. To correspond to the standard drilling speed of the formation, The index is affected by drilling speed. The weighting is determined by the influence of mud density. The actual mud density, To determine the optimal mud density for the corresponding formation, The mud density influence index, The weighting is determined by the impact of drilling pressure. This refers to the actual drilling pressure. To correspond to the standard drilling pressure of the formation, The drilling pressure impact index is divided into three risk levels: low, medium, and high. When the risk is low, the current parameters are maintained; when the risk is medium, the mud ratio and drilling speed are adjusted; and when the risk is high, the drilling is stopped immediately and the mud performance is optimized, so as to achieve early warning and precise prevention and control of hole collapse and necking risks.

[0025] This invention also includes a verticality deviation adaptive control step, which combines drill pipe inclination angle, drill pipe length, and hole depth data, and uses a formula... Calculate the adjustment amount of the mast straightening cylinder, where For the adjustment amount of the hydraulic cylinder, The drill pipe extension length. For drill pipe Direction tilt angle, For drill pipe The tilt angle is automatically controlled by adjusting the extension and retraction of the straightening cylinder according to the adjustment amount, and the drilling pressure distribution is corrected simultaneously. The verticality deviation is compensated in real time during drilling. Combined with the operator's operation, it forms a closed-loop control to ensure that the verticality of the hole meets the design requirements and reduce human intervention error.

[0026] This invention also includes an intelligent mud parameter control step. Based on mud flow and density detection data and formation characteristics, a mud performance optimization model is constructed. The required amount of fresh mud replenishment and the proportion of additives are automatically calculated. The automatic mud preparation system is linked to precisely control the mixing ratio of water, bentonite and additives in the mud tank. The changing trend of mud parameters after adjustment is monitored in real time. The mixing ratio scheme is dynamically corrected through a PID control algorithm to ensure that the mud always maintains optimal performance, taking into account borehole stability and sediment removal effect, and adapting to the drilling needs of different formations.

[0027] This invention also includes a formation adaptive adjustment step, which identifies the current drilling formation type by collecting multi-parameter data, calls the formation-construction parameter matching database, and automatically optimizes drilling speed, drilling pressure, mud parameters and stirring frequency. In sandy formations, it increases mud density and drilling speed, in clay formations it reduces drilling pressure and optimizes mud fluidity, and predicts and smoothly transitions parameters at formation change interfaces in advance, reducing hole quality fluctuations caused by sudden formation changes and improving hole stability and efficiency under complex formation conditions.

[0028] This invention also includes a remote collaborative control step, which establishes a real-time communication link between the on-site construction equipment and the remote control center through a cloud monitoring platform. The remote terminal can view real-time data of multiple parameters, hole formation quality scores, and control execution records. It has permissions such as parameter threshold modification, control strategy optimization, and emergency shutdown command issuance. Remote operation commands are executed after identity verification, permission review, and encrypted transmission. It supports online collaborative analysis of abnormal problems by multiple professionals, provides remote technical support, and realizes precise control and emergency response in unattended scenarios.

[0029] This invention also includes data visualization and traceability optimization steps. A digital twin model of the drilling process is constructed on a cloud monitoring platform to map the dynamic changes of key indicators such as hole depth, verticality, and mud parameters in real time, generating a three-dimensional drilling trajectory map and parameter trend curves. The digital quality report includes three core contents: a full-process data time series table, abnormal event analysis, and control effect evaluation. It supports multi-condition query and data export by station number, time, stratum, and other dimensions, providing complete data support for project acceptance, quality traceability, and construction process optimization.

[0030] This invention also includes a self-learning optimization step for construction parameters. It collects detection data, control records, and quality results of multiple pile drillings, constructs a database linking construction parameters and drilling quality, analyzes the advantages and disadvantages of parameter combinations under different working conditions using reinforcement learning algorithms, automatically updates the parameter optimization model and control rule library, prioritizes the use of the optimal parameter combination in subsequent construction, and adaptively adjusts control parameters for similar strata and working conditions to gradually improve the consistency and stability of drilling quality and reduce construction costs and rework rates.

[0031] This invention also includes a safety interlock control step, which sets multi-parameter safety interlock thresholds. When the drill pipe tilt angle exceeds the limit, mud leakage or other emergency is detected, multi-level safety protection is automatically triggered, immediately cutting off the drilling rig power source, shutting down the mud delivery pump, activating on-site audible and visual alarms and emergency ventilation equipment, and simultaneously sending emergency alarm information to construction management personnel and regulatory departments. The time of the safety incident, parameter data, and handling process are recorded to form a safety incident traceability file and prevent construction safety accidents.

[0032] This invention also includes a multi-machine collaborative operation control step. When multiple drilling rigs are operating in the same construction area, data sharing and collaborative scheduling of multiple rigs are realized through a cloud monitoring platform. Based on the drilling progress, quality status, and formation distribution of each drilling rig, the construction sequence and operation parameters are optimized to reduce mutual interference between adjacent drilling rigs, coordinate the resource allocation of mud circulation system and transportation equipment, unify data standards and quality requirements, generate a comprehensive regional construction quality report, improve the overall efficiency and quality control level of multi-machine operation, and adapt to the large-scale construction needs of large-scale infrastructure projects.

[0033] The following two examples further illustrate the specific implementation of this system: Example 1: Application in the foundation construction scenario of urban high-rise buildings This embodiment is applied to the foundation engineering of high-rise buildings in the core urban area. The strata in the construction area are alternating layers of silty clay and sand. The designed borehole depth is 80m and the borehole diameter is 1.2m. The allowable deviation of verticality is ≤0.8%. It is necessary to avoid disturbing the surrounding buildings during construction. The system operates according to the multi-parameter integrated detection and intelligent control process throughout the entire process, as follows: I. Execution of Core Processes and Key Steps System initialization and parameter preset: Construction design drawings are loaded via the vehicle-mounted industrial control computer to obtain preset parameters such as a hole depth of 80m, a hole diameter of 1.2m, and pile location coordinates X=32156.8m and Y=56789.3m. Communication connections are established between the drill rod integrated sensor kit, edge computing gateway, drilling rig control system, and cloud monitoring platform. Sensor response accuracy and communication link stability are self-checked. Multiple safety thresholds are set, including a verticality deviation threshold of 0.8% and an optimal mud density of 1.2g / cm³. 3 The standard drilling speed is 1.0 m / h, and an intelligent diagnostic system combining a rule base and a random forest machine learning model is constructed.

[0034] Real-time acquisition of multiple parameters: The drill pipe integrated sensor kit is installed according to a preset layout. The GNSS positioning antenna is fixed to the top of the drilling rig mast, and the rotary encoder is installed on the drill pipe telescopic mechanism for dual verification to obtain hole depth and drilling speed. A dual-axis tilt sensor is installed on the drill pipe near the power head to monitor the tilt angles in the X and Y directions in real time. An online mud monitor is installed on the mud circulation outlet pipeline to collect mud flow rate and density. All parameters are transmitted at a frequency of once per second. The initial data acquisition is: hole depth 10m, drilling speed 1.2m / h, X-direction tilt angle 0.5°, Y-direction tilt angle 0.3°, and mud density 1.25g / cm³. 3 .

[0035] Data fusion and feature extraction: After receiving the raw data, the edge computing gateway performs time synchronization calibration, uses Kalman filtering algorithm for noise reduction, and unifies the coordinate system to the construction coordinate system. Key features are extracted: verticality deviation trend of 0.3% / m, mud index fluctuation amplitude of 4.17%, and drilling speed change rate of 20%. The processed structured data is synchronously transmitted to the decision-making level and cloud monitoring platform to generate real-time parameter curves.

[0036] Intelligent diagnosis and risk prediction: Based on a preset rule base, parameters are judged in real time to exceed limits. A machine learning model integrates drilling rate, drilling pressure, mud parameters, and formation information. The current drilling formation is a silty clay layer. A formula is used... Calculate the risk value of borehole wall instability. =0.4, =1.2m / h, =1.0 m / h, =1.5, =0.3, =1.25g / cm 3 , =1.2g / cm 3 , =2.0, =0.3, =80kN, =75kN, =1.2, substituting gives

[0037] The risk level is low. The pore formation quality health score is 92, indicating the current status is normal.

[0038] Hierarchical intelligent control and formation self-adaptation: When drilling reached 30m, the drilling entered a sand layer, and the mud density dropped to 1.15g / cm³. 3The drilling speed increased to 1.5 m / h, and the calculated risk value R=3.2, classifying it as medium risk. The system was then activated by an automatic mud-making system, which adjusted the water, bentonite, and additive ratios using a PID control algorithm, replenishing fresh mud to restore the density to 1.22 g / cm³. 3 ; through formula Calculate the verticality adjustment amount, at this time =60m, =0.6°, =0.4°, sin0.6≈0.01047, cos0.6≈0.999945, sin0.4≈0.00698, substituting, we get

[0039] The automatic fine-tuning mast straightening cylinder corrects the drilling pressure distribution to 85kN, and the operator receives operation prompts through the HMI screen to adjust the drilling speed to 1.3m / h.

[0040] Remote collaboration and borehole acceptance: The remote control center views parameters and control records in real time through a cloud monitoring platform. Engineers remotely optimize mud mix parameters, and instructions are executed after identity verification, permission review, and encrypted transmission. After drilling to the 80m design elevation, the system automatically integrates all process data and generates a digital quality report, including time-series data such as hole depth, verticality, and mud parameters, as well as 12 control records. The report is stored in a "one-pile-one-file" format through the cloud platform and supports 3D visualization of the borehole trajectory.

[0041] II. Data Representation and Interpretation Table 1 Comparison of Hole Formation Quality Control Performance in Urban High-Rise Building Scenarios

[0042] Table 1 clearly demonstrates the advantages of this invention in urban high-rise building scenarios. Traditional control methods rely on manual inspection and experience-based adjustments, resulting in a verticality pass rate of only 82%, a hole wall instability rework rate as high as 15%, and a 45-second delay in control response that can easily lead to safety hazards. Furthermore, data records are scattered and difficult to trace. This invention, through real-time multi-parameter acquisition and intelligent diagnosis, increases the verticality pass rate to 98%, reduces the hole wall instability rework rate to 1%, and achieves precise control with a 3-second rapid response. The average health score reaches 93 points, and the entire process data is 100% traceable, effectively avoiding disturbance to surrounding buildings and fully meeting the high precision and high safety requirements of high-rise building foundation construction.

[0043] Example 2: Application in Bridge Pile Foundation Construction Scenarios This embodiment is applied to the pile foundation project of a cross-river bridge. The strata in the construction area are alternating layers of gravel and silty clay. The designed drilling depth is 100m and the hole diameter is 1.5m. Four drilling rigs are required to work together to address the problems of high drilling difficulty in complex strata and high risk of interference from multiple machines. The system operation process is as follows: I. Execution of Core Processes and Key Steps System initialization and multi-scenario adaptation: Load the bridge pile foundation construction design drawings, obtain parameters such as hole depth of 100m, hole diameter of 1.5m, and pile spacing of 5m, and complete the networking of sensor kits for 4 drilling rigs with the cloud monitoring platform. Select the bridge pile foundation scenario from the multi-scenario adaptation module, and the system automatically matches the drilling parameters for the gravel layer: the optimal mud density is 1.3g / cm³. 3 A multi-machine collaborative control rule base was constructed, with a standard drilling speed of 0.8 m / h and a safety threshold verticality deviation of ≤1.0%.

[0044] Multi-parameter real-time acquisition and data fusion: The sensor suite synchronously acquires parameters, and the GNSS and rotary encoder dual verification yields a hole depth of 20m and a drilling speed of 0.9m / h; the dual-axis tilt sensor monitors the X-axis tilt angle at 0.7° and the Y-axis tilt angle at 0.5°; the mud monitor collects the flow rate at 30m³ / h. 3 / h, density 1.28g / cm³ 3 The edge computing gateway performs time synchronization and filtering / denoising on data from four drilling rigs, extracting unique features of the pebble layer: drilling speed fluctuation rate of 12.5% ​​and mud density stability of 97.7%. The structured data is then transmitted to the decision-making layer and cloud platform.

[0045] Intelligent diagnosis and risk prediction: Based on a preset rule base, parameters are judged in real time to determine if they exceed limits. A machine learning model is used to comprehensively consider drilling rate, drilling pressure, mud parameters, and pebble layer characteristics, and a formula is employed to calculate the borehole instability risk value. =0.45, =0.9 m / h, =0.8m / h, =1.8, =0.35, =1.28g / cm 3 , =1.3g / cm 3 , =2.2, =0.2, =120kN, =110kN, =1.5, substituting gives

[0046] The risk level is low, resulting in a health score of 89.

[0047] Multi-machine coordination and graded control: When drilling reached 50m, the mud density of drilling rig No. 1 dropped to 1.22g / cm³. 3 The risk level rose to 4.8, turning it into a medium risk. The system initiated multi-machine collaborative control, coordinating with drilling rig No. 2 to temporarily adjust its working position to avoid interference, while drilling rig No. 1 calculated the verticality adjustment amount according to the formula. =80m, =0.8°, =0.6°, sin0.8≈0.01396, cos0.8≈0.999904, sin0.6≈0.01047, substituting, we get

[0048] The automatic fine-tuning straightening cylinder, in conjunction with the pulping system, replenishes bentonite, causing the slurry density to rise back to 1.29 g / cm³. 3 .

[0049] Self-learning optimization and borehole acceptance: The system collects construction data from four drilling rigs, constructs a database linking construction parameters and borehole quality, and optimizes the drilling speed in the pebble layer to 0.85 m / h and the drilling pressure to 115 kN through reinforcement learning algorithms. After drilling to the design elevation of 100 m, the system automatically integrates the full-process monitoring data and 32 control records from the four drilling rigs to generate a comprehensive regional construction quality report, which is stored in a "one pile, one file" format on the cloud platform, supporting multi-machine data comparison and analysis and process optimization.

[0050] II. Data Representation and Interpretation Table 2 Comparison of Multi-Machine Collaborative Construction Performance of Bridge Pile Foundations

[0051] Table 2 highlights the advantages of this invention in multi-machine collaborative scenarios for bridge pile foundations. Traditional methods lack multi-machine collaborative mechanisms, resulting in an operational interference rate of 28%, a borehole qualification rate of only 76% in complex strata, low collaborative control efficiency, and poor quality consistency. This invention achieves multi-machine data sharing and scheduling through a cloud platform, reducing the interference rate to 3% and increasing the borehole qualification rate in complex strata to 96%. Rapid collaborative control within 5 minutes significantly improves operational efficiency, short-cycle process optimization within 7 days adapts to the characteristics of pebble layers, and 92% quality consistency ensures uniform bearing capacity of bridge pile foundations, fully meeting the needs of large-scale, high-precision construction of cross-river bridges.

[0052] Reference Figure 2This diagram visually demonstrates the core breakthrough of this invention in multi-parameter detection accuracy. Traditional detection methods rely on a single sensor and lack data verification mechanisms. Hole depth detection depends on manual measurement or a single encoder, and verticality is judged solely by experience, resulting in significant errors in each parameter and failing to meet the demands of high-precision construction. This invention achieves simultaneous acquisition of multiple parameters through a drill pipe integrated sensor suite. Hole depth is verified using a dual-verification GNSS positioning antenna and rotary encoder, verticality is calculated geometrically using a dual-axis tilt sensor, and mud parameters are acquired in real-time by an online monitoring instrument. All data undergoes filtering, noise reduction, and feature extraction processing, significantly reducing errors. The accuracy errors of each parameter are controlled within an extremely small range, providing reliable data support for intelligent diagnosis and precise control, and solving the pain points of traditional detection methods, such as being one-sided and data distortion.

[0053] Reference Figure 3 This figure verifies the effectiveness and stability of the risk prediction model of this invention. Traditional methods lack risk prediction capabilities, only detecting problems after borehole instability occurs, resulting in a completely reactive approach. This invention constructs a risk prediction model by fusing multi-parameter data, introducing calculation formulas that incorporate multiple factors such as drilling speed, mud density, and drilling pressure, to dynamically assess borehole instability risk based on comprehensive formation information. Even as drilling depth increases and formation complexity rises, this invention maintains a prediction accuracy rate of over 94%, anticipating potential problems such as borehole collapse and necking. This proactive prediction allows for more targeted control strategies, enabling adjustments to mud ratios or drilling speeds in advance to avoid irreversible damage and significantly improve construction safety and quality stability.

[0054] Reference Figure 4 This diagram highlights the high efficiency of the hierarchical intelligent control system of this invention. Traditional control relies on manual detection and operation of anomalies, resulting in cumbersome response processes, high time costs, and the potential for escalating accidents due to delayed responses in the event of severe anomalies. This invention constructs a closed-loop system of "detection-diagnosis-control," with edge computing gateways processing data locally without waiting for cloud feedback. Minor anomalies are alerted to the operator via the HMI screen within 2 seconds, while moderate and severe anomalies automatically trigger the drilling rig control system to fine-tune parameters. The hierarchical control strategy matches the response method according to the anomaly level and accurately corrects deviations using the verticality adjustment calculation formula, significantly shortening response time. Rapid response allows anomalies to be resolved at an early stage, reducing borehole wall damage and rework probability, and improving construction efficiency.

[0055] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for integrated detection and intelligent control of multiple parameters for the quality of rotary drilled cast-in-place piles, characterized in that, Includes the following steps: The system initialization and parameter preset steps include loading construction design drawings to obtain preset parameters, completing communication connections and self-tests of sensor kits, edge computing gateways, drilling rig control systems, and cloud monitoring platforms, setting multi-parameter safety thresholds, quality assessment standards, and hierarchical control rules, and constructing an intelligent diagnostic system that combines rule bases and machine learning models. The multi-parameter real-time acquisition process involves synchronously acquiring key parameters through the sensor suite integrated into the drill pipe, using a GNSS positioning antenna combined with a rotary encoder for dual verification to obtain hole depth and drilling speed, monitoring the X and Y tilt angles of the drill pipe through a dual-axis tilt sensor, and acquiring mud flow rate and density parameters using an online mud monitor. In the data fusion and feature extraction steps, the edge computing gateway performs time synchronization, filtering and noise reduction, and coordinate unification processing on the raw data, removes abnormal data points, extracts key features, and transmits the processed structured data to the decision-making layer and cloud monitoring platform. The intelligent diagnosis and risk prediction steps are based on a preset rule base to make real-time judgments on parameters exceeding limits. Through machine learning models, the drilling speed, drilling pressure, mud parameters and formation information are integrated to predict the probability of borehole stability risk and generate a borehole quality health score. The hierarchical intelligent control steps execute corresponding control strategies based on the diagnostic results. Minor anomalies are displayed on the HMI screen in the cab and a voice alarm is issued. Moderate anomalies trigger the drilling rig control system to automatically fine-tune the mast straightening cylinder or mud ratio. Severe anomalies immediately trigger the shutdown protection and initiate the emergency response process. After drilling to the design elevation, the entire process of inspection data and control records is automatically integrated and stored as a "one pile, one file" through the cloud monitoring platform.

2. The method for integrated detection and intelligent control of multi-parameters of rotary drilling cast-in-place pile hole formation quality according to claim 1, characterized in that, It also includes a step for predicting the risk of hole wall stability, using a formula. Calculate the risk value of borehole wall instability, where This represents the risk value for the stability of the borehole wall. The drilling speed affects the weight. This represents the actual drilling speed. To correspond to the standard drilling speed of the formation, The index is affected by drilling speed. The weighting is determined by the influence of mud density. The actual mud density, To determine the optimal mud density for the corresponding formation, The mud density influence index, The weighting is determined by the impact of drilling pressure. This refers to the actual drilling pressure. To correspond to the standard drilling pressure of the formation, The drilling pressure impact index is divided into three risk levels: low, medium, and high, based on the risk value.

3. The method for integrated detection and intelligent control of multi-parameters of rotary drilling cast-in-place pile hole formation quality according to claim 1, characterized in that, It also includes a verticality deviation adaptive control step, which combines drill pipe inclination angle, drill pipe length, and hole depth data, and uses a formula... Calculate the adjustment amount of the mast straightening cylinder, where For the adjustment amount of the hydraulic cylinder, The drill pipe extension length. For drill pipe Direction tilt angle, For drill pipe The tilt angle is adjusted automatically by controlling the extension and retraction of the straightening cylinder, and the drilling pressure distribution is corrected synchronously.

4. The method for integrated detection and intelligent control of multi-parameters of rotary drilling cast-in-place pile hole formation quality according to claim 1, characterized in that, It also includes intelligent control steps for mud parameters. Based on mud flow and density detection data and formation characteristics, a mud performance optimization model is constructed to automatically calculate the required amount of fresh mud replenishment and the proportion of additives. The automatic mud preparation system is linked to control the mixing ratio of water, bentonite and additives in the mud tank, and the change trend of mud parameters after adjustment is monitored in real time.

5. The method for integrated detection and intelligent control of multi-parameters of rotary drilling cast-in-place pile hole formation quality according to claim 1, characterized in that, It also includes a formation adaptive adjustment step, which identifies the current drilling formation type by collecting data from multiple parameters, calls the formation and construction parameter matching database, and automatically optimizes the drilling speed, drilling pressure, mud parameters and mixing frequency. In sandy formations, it increases mud density and drilling speed, in clay formations, it reduces drilling pressure and optimizes mud fluidity, and predicts and smoothly transitions parameters at the formation change interface in advance.

6. The method for integrated detection and intelligent control of multi-parameters of rotary drilling cast-in-place pile hole formation quality according to claim 1, characterized in that, It also includes remote collaborative control steps, establishing a real-time communication link between on-site construction equipment and the remote control center through a cloud monitoring platform. Remote terminals can view real-time data of multiple parameters, hole formation quality scores, and control execution records. Remote operation commands are executed after identity verification, permission review, and encrypted transmission, supporting online collaborative analysis of abnormal issues by multiple professionals.

7. The method for integrated detection and intelligent control of multi-parameters of rotary drilling cast-in-place pile hole formation quality according to claim 1, characterized in that, It also includes data visualization and traceability optimization steps, building a digital twin model of the hole forming process on the cloud monitoring platform, mapping the dynamic changes of key indicators in real time, generating a three-dimensional hole forming trajectory map and parameter trend curves, and the digital quality report includes three core contents: a full-process data time series table, abnormal event analysis, and control effect evaluation.

8. The method for integrated detection and intelligent control of multi-parameters of rotary drilling cast-in-place pile hole formation quality according to claim 1, characterized in that, It also includes a self-learning optimization step for construction parameters, collecting detection data, control records and quality results of multiple pile drilling, constructing a database related to construction parameters and drilling quality, analyzing the advantages and disadvantages of parameter combinations under different working conditions through reinforcement learning algorithms, and automatically updating the parameter optimization model and control rule library.

9. The method for integrated detection and intelligent control of multiple parameters for the quality of rotary drilling cast-in-place piles according to claim 1, characterized in that, It also includes safety interlock control steps, setting multi-parameter safety interlock thresholds. When the drill pipe tilt angle exceeds the limit, mud leakage or other emergency is detected, multi-level safety protection is automatically triggered, immediately cutting off the drilling rig power source, shutting down the mud delivery pump, activating on-site audible and visual alarms and emergency ventilation equipment, and simultaneously sending emergency alarm information to construction management personnel and regulatory departments, recording the time of the safety incident, parameter data, and handling process.

10. The method for integrated detection and intelligent control of multi-parameters of rotary drilling cast-in-place pile hole formation quality according to claim 1, characterized in that, It also includes multi-machine collaborative operation control steps. When multiple drilling rigs are operating in the same construction area, the cloud monitoring platform completes multi-machine data sharing and collaborative scheduling. Based on the drilling progress, quality status, and formation distribution of each drilling rig, the platform coordinates the resource allocation of the mud circulation system and transportation equipment, unifies data standards and quality requirements, and generates a comprehensive regional construction quality report.

Images