Dry method precise positioning construction control system and method based on machine learning

Abstract

The present invention belongs to the field of construction control technology, and specifically discloses a dry-method precise positioning construction control system and method based on machine learning. The present invention uses a multi-source data acquisition module to obtain multi-dimensional data such as drilling resistance, vibration frequency, shovel head angle deviation, position, and soil hardness in real time. The deviation calculation module performs dynamic comparison and analysis based on the data corresponding to the preset sampling area. The dynamic adjustment module dynamically optimizes the drilling speed and angle through a multi-condition trigger mechanism and a turn-in adjustment rule. Finally, the control execution module generates a precise control instruction to drive the Luoyang shovel to perform the correction action. Furthermore, through multi-dimensional data fusion analysis and real-time dynamic adjustment strategies, the path accuracy and formation adaptability of the drilling operation are significantly improved, while the equipment's adaptability to sudden formation changes is improved, and the construction risk under complex geological conditions is reduced, and the coordinated optimization of drilling efficiency and operation safety is achieved.

Description

Technical Field

[0001] The present invention belongs to the field of construction control technology, and specifically relates to a dry-method precise positioning construction control system and method based on machine learning. Background Art

[0002] In the field of construction, traditional pile foundation construction methods have many drawbacks. Against this background, the Luoyang shovel dry construction method, with its own characteristics, brings new opportunities for dry precision positioning construction control. In order to ensure the quality of pile foundation construction, it is necessary to accurately position its construction process.

[0003] Prior art such as application number The Chinese invention patent application discloses a pile foundation construction control method, system, terminal and storage medium, which includes obtaining the current position and the preset position, matching through the control algorithm, leveling the pile driver, obtaining parameters for excavation, and performing pressure grouting after detecting the stop instruction, thereby improving accuracy through the preset algorithm and parameter adjustment.

[0004] Prior art such as application number The Chinese invention patent application discloses a fully automatic static pile driver positioning control system based on GPS technology. By combining GPS technology, especially carrier phase difference technology, it realizes automatic positioning and horizontal adjustment of the pile driver, emphasizing high-precision positioning and automatic adjustment.

[0005] Regarding the above technical solutions, it is obvious that the current pile foundation construction control still has the following deficiencies: 1. When predicting the soil layer, less attention is paid to the evaluation of the sampling area, and it is mainly based on past experience, which makes the effectiveness and accuracy of the soil layer prediction still have certain deviations and the reference is not strong.

[0006] 2. Excavation and correction rely on preset pile foundation parameters, but the real-time soil layer data and predicted soil layer data are not integrated to verify the comprehensive deviation under the depth sequence, resulting in certain deviations in the security of correction.

[0007] 3. Relying solely on external positioning data without combining the Luoyang shovel's own posture and soil resistance changes to perform multi-parameter coordinated adjustments can easily lead to cumulative errors in complex strata. Summary of the Invention

[0008] In view of this, in order to solve the problems raised in the above background technology, a dry method precise positioning construction control system and method based on machine learning is proposed.

[0009] The purpose of the present invention can be achieved through the following technical solutions: The present invention provides a dry precision positioning construction control system based on machine learning, which includes: a multi-source data acquisition module, which collects drilling resistance, vibration frequency, shovel head angle deviation and position in real time, and synchronously collects the hardness data of the current soil layer.

[0010] The deviation calculation module combines the drilling resistance, vibration frequency and hardness data to calculate the resistance, vibration frequency and hardness deviation of the soil layer corresponding to the preset sampling area.

[0011] The dynamic adjustment module combines the shovel head angle deviation value and the actual path position difference to dynamically adjust the drilling speed and drilling angle based on the drilling adjustment rules.

[0012] The control execution module generates control instructions based on the adjusted drilling speed and drilling angle, and drives the Luoyang shovel to perform correction actions.

[0013] The triggering conditions of the dynamic adjustment module include: any deviation exceeds a set threshold, or the actual path position difference exceeds a limit, or the shovel head angle deviation continues to time out.

[0014] The present invention also provides a dry precision positioning construction control method based on machine learning, which includes: S1, multi-source data acquisition: real-time acquisition of drilling resistance, vibration frequency, shovel head angle deviation value and position data, and synchronous acquisition of current soil layer hardness data.

[0015] S2. Construction deviation calculation: Combine the drilling resistance, vibration frequency and hardness data to calculate the resistance, vibration frequency and hardness deviation of the soil layer corresponding to the preset sampling area.

[0016] S3. Dynamic construction adjustment: Based on the shovel head angle deviation value and the actual path position difference, the drilling speed and drilling angle are dynamically adjusted based on the drilling adjustment rules.

[0017] S4, drilling control execution: Generate control instructions based on the adjusted drilling speed and drilling angle to drive the Luoyang shovel to perform correction actions.

[0018] Compared with the existing technology, the beneficial effects of the present invention are as follows: (1) The present invention acquires parameters such as drilling resistance, vibration frequency, angle deviation, position and soil hardness in real time through multi-source data acquisition. After the deviation calculation module dynamically compares the preset parameters, it triggers the dynamic adjustment module to optimize the drilling speed and angle based on multiple conditions. Finally, the control execution module generates precise instructions to drive the deviation correction, realizing multi-dimensional data fusion and real-time dynamic adjustment, significantly improving the drilling path accuracy and formation adaptability, and reducing the risk of complex geological construction.

[0019] (2) The present invention calculates the critical safety distance based on the planned borehole diameter and the elastic mechanics formula, scientifically calibrates the pre-selected area, breaks through the traditional reliance on experience, and integrates soil parameters such as spectral reflectance and moisture content to calculate the Jaccard similarity coefficient, thereby achieving quantitative comparison of soil characteristics between the planned drilling area and the pre-selected area, enhancing the effectiveness, accuracy and reference of soil layer prediction, and providing reliable data support for the dynamic adjustment of drilling parameters.

[0020] (3) The present invention constructs a depth sequence comparison between the actual resistance gradient / distribution curve and the preset sampling area control curve, combines it with the weight compensation of the historical accident database, quantitatively evaluates the drilling parameter deviation, realizes the dynamic verification of the correction action, and ensures the accuracy of the construction indicator adjustment in complex formations.

[0021] (4) The present invention integrates drilling resistance, vibration frequency, angle deviation, position and soil hardness, and dynamically adjusts the module to fuse angle deviation, position difference and multi-parameter deviation. It combines weighted summation with Sigmoid function mapping to solve the cumulative error problem caused by single external positioning, realize differentiated precision and coordinated control of drilling speed and angle in complex formations, and significantly improve the accuracy and safety of the construction path. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 This is a schematic diagram of the structural connection of each module of the system of the present invention.

[0024] Figure 2 The figure is a flow chart of the steps for implementing the method of the present invention.

[0025] Figure 3 Schematic diagram of the selection process of the preset sampling area of ​​the present invention. DETAILED DESCRIPTION

[0026] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0027] See also Figure 1As shown, the present invention provides a dry method precise positioning construction control system based on machine learning, which includes: a multi-source data acquisition module, a deviation calculation module, a dynamic adjustment module and a control execution module.

[0028] In the above, the deviation calculation module is connected to the multi-source data acquisition module and the dynamic adjustment module respectively, and the dynamic adjustment module is connected to the control execution module.

[0029] The multi-source data acquisition module collects drilling resistance, vibration frequency, shovel head angle deviation and position in real time, and simultaneously collects hardness data of the current soil layer.

[0030] Specifically, the multi-source data acquisition module includes: obtaining the three-dimensional coordinates of the Luoyang shovel in real time through the RTK positioning module installed on the shovel body, and generating the real-time position of the Luoyang shovel.

[0031] A dual-axis inclination sensor is used to detect the deviation between the shovel head and the set angle, which is used as the shovel head angle deviation.

[0032] The pressure sensor array and vibration sensor array are integrated on the blade of the shovel head to measure the drilling resistance value and drilling vibration frequency value of each soil layer in real time.

[0033] The deviation calculation module combines the drilling resistance, vibration frequency and hardness data to calculate the resistance, vibration frequency and hardness deviation of the soil layer corresponding to the preset sampling area.

[0034] Specifically, see Figure 3 As shown, the selection process of the preset sampling area is as follows: R1, import the planned aperture of the planned drilling area in the construction site, and calculate the critical safety distance using the elastic mechanics formula , based on the critical safety distance, the pre-selected areas are calibrated at the construction site.

[0035] Understandably, the reference formula for the critical safety distance is: ,in, represents the critical safety distance, represents the elastic modulus, Represents Poisson's ratio, the default value is 0.3, represents the planned aperture, It represents the tensile strength of soil. The elastic modulus and Poisson's ratio can be inverted by measuring the stress-strain relationship of soil with an expansion probe, and the tensile strength of soil can be obtained by direct tensile test.

[0036] It should be added that the critical safety distance will increase with the increase of the planned aperture. For example, assuming that the elastic modulus of a site is , Poisson's ratio , soil tensile strength , when the planned aperture d = 50cm, the critical safety distance is calculated by the formula , if the aperture is increased to d=80cm, , in order to avoid soil damage caused by the superposition of inter-hole stress.

[0037] It should also be added that the pre-selected areas are marked with To determine the interval distance, the diameter of the planned drilling area is used as the calibration diameter to calibrate each preselected area.

[0038] R2. Use the Voronoi diagram algorithm to divide the honeycomb grid and determine the sampling points in the planned drilling area and the pre-selected area.

[0039] It can be understood that each sampling point is composed of a grid center point and edge vertices, such as vertices of a hexagonal grid.

[0040] R3. Collect the spectral reflectance, moisture content and penetration index of each sampling point, perform standardization on them respectively, and output the standardized data.

[0041] It should be added that the spectral reflectance is collected using a portable spectrometer, the moisture content is collected using a TDR or FDR probe, and the penetration index needs to be collected using a static cone penetration instrument.

[0042] R4. Construct a standardized processed data set for the planned drilling area and each pre-selected area, and use the Jaccard similarity coefficient to calculate the similarity between the soil in each pre-selected area and the planned drilling area.

[0043] R5. For the same pre-selected area, the standardized processed data of each sampling point are mapped into weights, which are recorded as soil parameter consistency weights.

[0044] For example, the specific mapping formula for mapping to weight is: , represents the weight, Indicates standardized data.

[0045] It should be noted that when mapping to weights, the standard deviations of the standardized spectral reflectance, moisture content, and micro-penetration index need to be mapped separately to obtain the mapping weights of the spectral reflectance, moisture content, and micro-penetration index, and then the weights of the spectral reflectance, moisture content, and micro-penetration index are fused to obtain the soil parameter consistency weights.

[0046] It should be added that the weight of fusing spectral reflectance, moisture content and micro-penetration index includes setting the fusion ratio of the weights of fusing spectral reflectance, moisture content and micro-penetration index. Among them, the micro-penetration index directly reflects the mechanical strength and density of the soil, and plays a key role in the evaluation of pile foundation hole stability and bearing capacity. The moisture content significantly affects the soil physical state such as plasticity and permeability and mechanical properties such as shear strength and hole wall stability. It is a parameter that needs to be monitored during pile foundation construction. The spectral reflectance is mainly used to analyze soil components such as organic matter and minerals, and to assist in judging the soil type. Therefore, in the pile excavation scenario, the focus is on mechanical properties. Therefore, the micro-penetration index has the highest impact, followed by the moisture content, and the spectral reflectivity has the smallest impact. Correspondingly, the higher the fusion ratio of the micro-penetration index, the value of which can be 45%. The fusion ratio of the moisture content is second, the value of which can be 35%, and the fusion ratio of the spectral reflectance is the smallest, which can be 20%.

[0047] R6. Perform similarity correction based on the soil parameter consistency weight, and use the preselected area corresponding to the maximum similarity after correction as the preset sampling area.

[0048] The embodiment of the present invention calculates the critical safety distance based on the planned drilling aperture and the elastic mechanics formula, scientifically calibrates the preselected area, breaks through the traditional reliance on experience, and integrates soil parameters such as spectral reflectance and moisture content to calculate the Jaccard similarity coefficient, thereby realizing quantitative comparison of soil characteristics between the planned drilling area and the preselected area, enhancing the effectiveness, accuracy and reference of soil layer prediction, and providing reliable data support for dynamic adjustment of drilling parameters.

[0049] It can be understood that performing similarity correction based on the soil parameter consistency weight specifically refers to multiplying the soil parameter consistency weight by the corresponding similarity.

[0050] Specifically, the resistance, vibration frequency and hardness deviation of the soil layer corresponding to the preset sampling area are calculated, including: A1. For the current soil layer, the historical peak value of the drilling resistance collected in real time is taken as the target resistance value, and the output resistance gradient is calculated by the difference of the target resistance values ​​of adjacent soil layers.

[0051] A2. For each soil layer currently drilled, construct the resistance gradient under the current depth sequence, record it as the actual resistance gradient, and intercept the resistance gradient corresponding to the current soil layer from the preset sampling area, record it as the reference resistance gradient.

[0052] A3. Compare the actual and control resistance gradients and output the soil resistance gradient deviation.

[0053] A4. For each soil layer, a resistance-time curve is fitted based on the time series to generate the actual resistance distribution curve under the current depth sequence. At the same time, the resistance distribution curve under the current depth sequence is intercepted from the preset sampling area and recorded as the control resistance distribution curve.

[0054] A5. Compare the actual resistance distribution curve with the reference resistance distribution curve, output the soil layer resistance distribution deviation, and integrate the soil layer resistance gradient deviation and the soil layer resistance distribution deviation to obtain the resistance deviation of the current soil layer.

[0055] A6. For vibration frequency and hardness, repeat steps A1 to A5 to output the vibration frequency and hardness deviation of the current soil layer in sequence.

[0056] The embodiment of the present invention constructs a depth sequence comparison between the actual resistance gradient / distribution curve and the preset sampling area control curve, combines it with the weight compensation of the historical accident database, quantitatively evaluates the drilling parameter deviation, realizes the dynamic verification of the correction action, and ensures the accuracy of the adjustment of construction indicators in complex formations.

[0057] Understandably, the drilling resistance deviation directly reflects the reaction force of the current soil layer on the drill bit, which is related to the density and integrity of the formation. When the resistance is significantly different from the collection resistance of the preset sampling area, the drilling speed needs to be adjusted in a timely manner. The vibration frequency deviation represents the stability of the equipment operation and is related to drill bit wear and formation heterogeneity such as cracks and interlayers. When the vibration frequency is significantly different from the collection vibration frequency of the preset sampling area, it indicates that the equipment status or formation conditions are significantly different from expectations. At this time, in order to ensure the accuracy of the drilling path, the drilling speed needs to be adjusted in a timely manner. The soil layer hardness deviation reflects the physical strength of the formation material and is related to the rock and soil type and structure. If the hardness is higher or lower than the corresponding collection hardness of the preset sampling area, the drilling angle or drilling speed needs to be adjusted to ensure smooth drilling and drilling accuracy.

[0058] In summary, the integration of these three parameters can comprehensively evaluate the formation conditions and equipment status, so as to adjust the angle and speed, avoid equipment failure and improve efficiency.

[0059] It should also be added that the drilling resistance, vibration frequency and hardness data of each soil layer collected in real time corresponding to each soil layer in the sampling area are pre-synchronized according to the processing method of the currently collected drilling resistance, vibration frequency and hardness data of the current soil layer.

[0060] It should be noted that formation parameters have spatial correlation and temporal evolution, and need to be analyzed in combination with spatial and temporal dimensions. In actual engineering, formation heterogeneity and equipment status are coupled to affect parameters, and a single indicator is difficult to distinguish the source of anomalies. Therefore, a comprehensive analysis is conducted combining both space and time, that is, analysis is performed from the two dimensions of gradient and distribution.

[0061] Understandably, the gradient deviation focuses on sudden changes in parameters of adjacent soil layers, such as rock fractures and soft and hard interlayers, to identify local anomalies, while the distribution deviation captures the overall trend deviation of parameters over time or depth, such as progressive soil softening or equipment performance degradation. At the same time, the gradient deviation is susceptible to single-point noise, such as instantaneous resistance fluctuations, and the distribution deviation depends on the overall distribution form of the data, such as the trend after filtering. By combining the gradient deviation and the distribution deviation, the composite abnormal scenario of "local mutation + global trend" is covered, which can reduce the false alarm rate. For example, local noise will not significantly change the overall distribution deviation, thus avoiding misjudgment.

[0062] Furthermore, the output of the soil layer resistance gradient deviation in step A3 includes: A31, for each soil layer corresponding to the soil layer depth, in combination with the historical accident database, setting the resistance deviation influence weight of each soil layer.

[0063] It can be understood that the ability to quantitatively assess formation risks has been significantly improved through the fusion of depth weight differentiation and gradient accumulation, which is particularly suitable for deep complex formation projects.

[0064] A32. Calculate the difference between the actual resistance gradient and the control resistance gradient corresponding to each soil layer, and based on the resistance deviation influence weight, perform weighted summation to obtain the cumulative resistance gradient difference, which is used as the soil layer resistance gradient deviation.

[0065] Understandably, the specific setting process of setting the influence weight of the resistance deviation corresponding to each soil layer in combination with the historical accident database is as follows: the occurrence frequency of each accident type corresponding to each soil layer depth is extracted from the historical accident database, and the highest occurrence frequency is selected as the reference occurrence frequency of each soil layer depth.

[0066] Count the number of accident types whose occurrence frequency exceeds the set threshold at each soil layer depth, divide it by the total number of accident types, and output the effective accident type trigger ratio corresponding to each soil layer depth. , Indicates the Soil layer depth, .

[0067] The reference occurrence frequency of each soil layer depth is normalized and the processing result is marked as the accident occurrence ratio, which is recorded as .

[0068] Set the resistance deviation influence weight , the resistance deviation influence weight of each soil layer is screened out from the resistance deviation influence weight of each soil layer depth, among which the resistance deviation influence weight The specific formula is: , Indicates the preset The depth of each soil layer corresponds to a comprehensive construction risk weight, which is obtained by the weighted sum of the engineering importance weight, geological risk weight and construction feedback weight. Among them, the engineering importance weight measures the criticality of the soil layer in the engineering structure and reflects its direct contribution to the structural safety. Its specific value is obtained by comprehensively setting it in combination with the building foundation design specifications and the pile foundation form design requirements formulated by the structural engineer. The geological risk weight quantifies the geological risk attributes of the soil layer itself, and its value can be determined comprehensively based on the survey data and regional disasters. The construction feedback weight reflects the abnormal feedback monitored in real time during the drilling process, such as a sudden drop in drilling speed and a sudden change in torque. It is a dynamic weight. represents the accident risk weight, and Represent the proportion coefficients of the effective accident type trigger ratio and accident occurrence ratio, and They respectively represent the corresponding proportion coefficients of the comprehensive construction risk weight item and the construction risk weight item.

[0069] It should be added that the effective accident type trigger ratio is analyzed from the perspective of accident type coverage breadth, and the accident occurrence ratio is analyzed from the perspective of accident frequency. They can be set to 0.6 and 0.4 respectively, following the principle of coverage breadth priority to avoid missing a single accident type. and The values ​​can be 0.55 and 0.45 respectively.

[0070] It should also be added that the construction feedback weight is obtained by combining the preset baseline feedback weight and the risk trigger weight. For example, the baseline feedback weight can be 0.1. If the drilling speed drop rate exceeds the trigger threshold, the drilling speed drop rate and the corresponding trigger threshold are recorded as and ,Will As a risk trigger weight.

[0071] It should be noted that when screening the resistance deviation influence weight of each soil layer from the resistance deviation influence weight of each soil layer depth, when a certain soil layer matches the resistance deviation influence weights of multiple soil layer depths, the maximum value is taken as the influence weight of the corresponding soil layer.

[0072] Furthermore, the output of the soil layer resistance distribution deviation in step A5 includes: A51, projecting the actual resistance distribution curve to the position of the reference resistance distribution curve, and counting the total length of the curve in the projection overlapping area.

[0073] A52. Extract the slope, number of peak points and number of valley points from the actual resistance distribution curve and the control resistance distribution curve respectively, comprehensively project the total length, slope, number of peak points and number of valley points of the overlapping area curve, and set the curve morphology deviation compensation factor for each soil layer.

[0074] A53. For the same soil layer, extract the amplitude of the actual resistance distribution curve and the control resistance distribution curve respectively, and make the difference between the two to obtain the resistance change amplitude difference. At the same time, extract the maximum resistance respectively and make the difference to obtain the maximum resistance difference.

[0075] A54. Based on the curve shape deviation compensation factor, the resistance change amplitude difference of each soil layer is corrected, and the corrected resistance change amplitude difference of each current soil layer is output.

[0076] A55. The maximum resistance difference of each soil layer is combined to obtain the cumulative maximum resistance difference. The difference in the modified resistance change amplitude of each soil layer is averaged to obtain the average change amplitude difference. The cumulative maximum resistance difference and the average change amplitude difference are used as the soil layer resistance distribution deviation.

[0077] Regarding step A52, it is understandable that the specific setting process of setting the curve shape deviation compensation factor for each soil layer is as follows: if the signs of the slopes of the actual resistance distribution curve and the control resistance distribution curve are inconsistent, the curve shape deviation compensation factor is assigned a value of 1; otherwise, the slope difference between the two is recorded as The projection overlap ratio is obtained by dividing the total length of the projection overlap area curve by the total length of the control resistance distribution curve. The difference in the number of peak points and the difference in the number of valley points between the actual resistance distribution curve and the control resistance distribution curve are recorded as and and from and Filter out the maximum value as the target feature point number difference .

[0078] Set the curve shape deviation compensation factor, denoted as , , 、 and They represent the compensation ratio coefficients corresponding to the slope deviation, projection overlap ratio deviation and target feature point number deviation, respectively. and They are the slope difference and the number of feature points of the reference respectively.

[0079] In a specific embodiment, 、 and The values ​​can be 0.5, 0.3 and 0.2 respectively. At the same time, the reference slope difference can be set to 0.1, and the characteristic point number difference can be set to 20% of the peak point number of the control resistance distribution curve.

[0080] The dynamic adjustment module dynamically adjusts the drilling speed and drilling angle based on the drilling adjustment rules in combination with the shovel head angle deviation value and the actual path position difference.

[0081] Specifically, the specific confirmation process of the actual path position difference is as follows: F1. Vertically project the real-time collected position onto the planned path, and calculate the perpendicular distance between each projection point and the planned path.

[0082] It is understandable that the perpendicular distance between each projection point and the planned path can be calculated using the distance formula between two points, and the specific calculation formula will not be repeated here.

[0083] F2. If the number of projection points with continuous perpendicular distances not equal to 0 is within the set threshold, the maximum perpendicular distance is extracted and the average perpendicular distance of the projection points is calculated. The maximum perpendicular distance and the average perpendicular distance are combined to output the actual path position difference.

[0084] Understandably, the threshold value for the number of projection points whose distance between consecutive vertical lines is not 0 can be set to Times the total number of projection points, and the comprehensive maximum perpendicular distance and average perpendicular distance output the actual path position difference, which can be obtained by weighted summing the maximum perpendicular distance and the average perpendicular distance as the actual path position difference, where the weights of the maximum perpendicular distance and the average perpendicular distance can be 0.7 and 0.3 respectively.

[0085] F3. If the number of consecutive projection points whose perpendicular distance is not 0 is not within the set threshold, the sum of the perpendicular distances of each projection point corresponding to the planned path is taken as the actual path position difference.

[0086] It should be noted that, when traditionally performing path position deviation, on the one hand, the focus is on the current position, which is a static deviation. On the other hand, when performing dynamic tracking, the maximum position deviation is often considered. The continuous point threshold is used to distinguish between accidental fluctuations and systematic offsets, avoiding misjudgments caused by a single maximum value. At the same time, the global accumulation mode enhances the sensitivity to persistent small deviations and reduces the risk of missed reports. In addition, the combination of extreme values ​​and mean values ​​in the local mode can better reflect the deviation intensity than the simple maximum value.

[0087] In a specific embodiment, the maximum position deviation selection method is used as the existing method for comparison. At the same time, the position deviation limit value for triggering correction is set to 5 mm, the total number of projection points is set to 15, and the setting threshold of the number of continuous projection points is set to 5. In addition, three scenarios are set for comparison: local accidental deviation, systematic continuous deviation, and mixed deviation. The comparison results are shown in Table 1.

[0088] Table 1 Comparison data of position deviation selection methods

[0089]

[0090] As shown in Table 1, existing methods miss detections in scenarios with systematic and persistent drift (the actual deviation value of 20 mm exceeds the threshold, but the error is not triggered due to a single point maximum of 3 mm). However, the present invention accurately identifies errors through global accumulation, significantly improving the trigger rate. In scenarios with local and occasional drift, the existing method triggers a correction due to an extreme value of 5 mm, which may actually be a transient disturbance. The present invention identifies this as an accidental fluctuation, significantly reducing ineffective adjustments. Overall, compared with scenarios with local and occasional drift, the present invention can avoid over-response to transient disturbances. Compared with scenarios with systematic and persistent drift, the present invention can address the problem of gradual path deviation caused by the existing method's insensitivity to persistent small deviations. Compared with scenarios with mixed drift, the present invention maintains a high detection rate and combines extreme value response with trend judgment capabilities. In other words, through multi-dimensional error analysis, the present invention can significantly improve judgment rationality while ensuring sensitivity.

[0091] Furthermore, before dynamically adjusting the drilling speed and drilling angle, a drilling adjustment trigger assessment is performed, including: if the shovel head angle deviation exceeds a set threshold or the duration of the shovel head angle deviation exceeds a set time or the ratio of the actual path position difference to the planned path exceeds the limit, the drilling angle adjustment is triggered.

[0092] If any of the resistance, vibration frequency and hardness deviation exceeds the set threshold, the drilling speed adjustment is triggered.

[0093] It can be understood that angle deviation directly reflects the loss of direction control, and the posture needs to be corrected immediately to avoid path deviation. The lateral deviation of the path requires priority adjustment of the angle regression plan trajectory. The deviation of the soil resistance / hardness / vibration frequency exceeds the set threshold, which indicates a sudden change in the formation. Reducing the speed can alleviate the load. The present invention follows this principle to set the drilling adjustment trigger assessment conditions.

[0094] Furthermore, the dynamic adjustment of the drilling speed and drilling angle includes confirming the adjustment ratio. The specific confirmation process is: 1) the shovel head angle deviation, the duration of the shovel head angle deviation and the actual path position difference are standardized respectively, and the processing results are weighted and summed as the input variables of the Sigmoid function, and the adjustment ratio of the drilling angle is output.

[0095] Understandably, the shovel head angle deviation and actual path position difference can be processed using Min-Max normalization. The duration of the shovel head angle deviation can be processed using logarithmic normalization to address the long-tail distribution, that is, to avoid negative infinity at t = 0 and to compress the high value range. Min-Max normalization and logarithmic normalization are common processing methods, and their specific formulas are not shown here.

[0096] It should be added that the shovel head angle deviation indicates the urgency of the current deviation and is an instantaneous state quantity with the dominant influence. The deviation duration reflects the severity of the cumulative deviation and has the second greatest influence. The path position difference reflects the need for correction of the overall offset and is a long-term effect of the position error. The values ​​can be 0.5, 0.3, and 0.2, respectively.

[0097] 2) The resistance, vibration frequency, and hardness deviation are standardized, and the weighted sum of the processing results is input into the Sigmoid function to output the adjustment ratio of the drilling speed.

[0098] It can be understood that the resistance, vibration frequency and hardness deviation are normalized.

[0099] It should be added that the set threshold value of the deviation amount, the set limit value of the actual path position difference, and the exceeding time threshold value of the shovel head angle deviation amount are determined by comprehensive experiments based on historical experience data.

[0100] It should also be added that the weights of the resistance deviation, the vibration frequency deviation, and the hardness deviation can be 0.4, 0.2, and 0.4, respectively.

[0101] This embodiment of the present invention integrates drilling resistance, vibration frequency, angular deviation, position, and soil hardness. The dynamic adjustment module integrates angular deviation, position difference, and multi-parameter deviation, combining weighted summation with Sigmoid function mapping to address the cumulative error problem caused by single external positioning. This enables differentiated, precise, and coordinated control of drilling speed and angle in complex formations, significantly improving construction path accuracy and safety. It also enhances the smoothness of drilling parameter adjustment in complex formations, ensuring construction accuracy.

[0102] In a specific embodiment, dynamically adjusting the drilling speed and drilling angle also includes screening out corresponding drilling speed adjustment ranges and drilling angle adjustment ranges from pre-set adjustment rules based on the adjustment ratio, and taking the product of the adjustment ratio and the adjustment range corresponding to the adjustment ratio as the specific adjustment value.

[0103] For example, when the adjustment ratio is <0.3, the adjustment range of the drilling angle is ±2° of the current drilling angle, and the adjustment range of the drilling speed is ±5% of the current drilling speed. When 0.3≤adjustment ratio<0.7, the adjustment range of the drilling angle is ±5° of the current drilling angle, and the adjustment range of the drilling speed is ±15% of the current drilling speed. When the adjustment ratio is ≥0.7, the machine is shut down.

[0104] It should be added that the sign of the drilling angle adjustment direction is determined by the deviation direction of the actual parameter relative to the target state. For example, if the deviation of the actual drilling angle from the planned drilling angle is greater than 0, the actual direction is right and needs to be corrected to the left. The current adjustment coefficient is 0.3, that is, a negative adjustment is performed, such as .

[0105] It should be noted that if the vibration frequency deviation is greater than 0 and exceeds the set threshold, a forced deceleration is initiated to prevent equipment damage or accidents. When the vibration frequency deviation is less than or equal to 0, the resistance and hardness deviations are marked as ΔM and ΔH, respectively, and the sign of the drilling speed adjustment direction is confirmed to follow the table below.

[0106] Table 2 Schematic diagram of drilling speed adjustment direction.

[0107]

[0108] It should be noted that ΔM>0 indicates high resistance but soft formation, which may be a temporary obstacle. In this case, the speed reduction is conservative. The fixed speed reduction range is -5% to -10%, and it is confirmed in combination with the adjustment ratio. For example, As the specific speed reduction value, Indicates adjustment ratio.

[0109] The control execution module generates a control instruction based on the adjusted drilling speed and drilling angle, and drives the Luoyang shovel to perform a correction action.

[0110] The triggering conditions of the dynamic adjustment module include: any deviation exceeds a set threshold, or the actual path position difference exceeds a limit, or the shovel head angle deviation continues to time out.

[0111] The embodiment of the present invention acquires parameters such as drilling resistance, vibration frequency, angular deviation, position and soil hardness in real time through multi-source data collection. After the deviation calculation module dynamically compares the preset parameters, it triggers the dynamic adjustment module to optimize the drilling speed and angle based on multiple conditions. Finally, the control execution module generates precise instructions to drive correction, realizing multi-dimensional data fusion and real-time dynamic adjustment, significantly improving the drilling path accuracy and formation adaptability, and reducing the risk of complex geological construction.

[0112] See also Figure 2 As shown, the present invention also provides a dry precision positioning construction control method based on machine learning, which includes: S1, multi-source data acquisition: real-time acquisition of drilling resistance, vibration frequency, shovel head angle deviation value and position data, and synchronous acquisition of current soil layer hardness data.

[0113] S2. Construction deviation calculation: Combine the drilling resistance, vibration frequency and hardness data to calculate the resistance, vibration frequency and hardness deviation of the soil layer corresponding to the preset sampling area.

[0114] S3. Dynamic construction adjustment: Based on the shovel head angle deviation value and the actual path position difference, the drilling speed and drilling angle are dynamically adjusted based on the drilling adjustment rules.

[0115] S4, drilling control execution: Generate control instructions based on the adjusted drilling speed and drilling angle to drive the Luoyang shovel to perform correction actions.

[0116] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. A dry method precise positioning construction control system based on machine learning, characterized by: The system includes: Multi-source data acquisition module collects drilling resistance, vibration frequency, shovel head angle deviation and position in real time, and simultaneously collects the hardness data of the current soil layer; The RTK positioning module installed on the shovel body obtains the three-dimensional coordinates of the Luoyang shovel in real time and generates the real-time position of the Luoyang shovel; A dual-axis inclination sensor is used to detect the deviation between the shovel head and the set angle as the shovel head angle deviation; The pressure sensor array and vibration sensor array are integrated in the blade of the shovel head to measure the drilling resistance value and drilling vibration frequency value of each soil layer in real time; Deviation calculation module, combining drilling resistance, vibration frequency and hardness data to calculate the deviation of resistance, vibration frequency and hardness of the soil layer corresponding to the preset sampling area; The process of selecting the preset sampling area is as follows: Import the planned hole diameter of the planned drilling area in the construction site and calculate the critical safety distance using the elastic mechanics formula , calibrate each pre-selected area at the construction site based on the critical safety distance; Use the Voronoi diagram algorithm to divide the honeycomb grid and determine the sampling points in the planned drilling area and the pre-selected area; Collect the spectral reflectance, water content and penetration index of each sampling point, perform standardization processing on them respectively, and output the standardized processing data; Construct a standardized processed data set of the planned drilling area and each pre-selected area, and use the Jaccard similarity coefficient to calculate the similarity of the soil in each pre-selected area with the planned drilling area; For the same pre-selected area, the standardized processed data of each sampling point are mapped into weights, which are recorded as soil parameter consistency weights; Performing similarity correction based on the soil parameter consistency weight, and using the preselected area corresponding to the maximum similarity after correction as the preset sampling area; Calculate the resistance, vibration frequency and hardness deviation of the soil layer corresponding to the preset sampling area, including: A1. For the current soil layer, the historical peak value of the drilling resistance collected in real time is taken as the target resistance value, and the resistance gradient is calculated by the difference of the target resistance values ​​of adjacent soil layers; A2. For each soil layer currently drilled, construct the resistance gradient under the current depth sequence, record it as the actual resistance gradient, and intercept the resistance gradient corresponding to the current soil layer from the preset sampling area, record it as the reference resistance gradient; A3. Compare the actual and reference resistance gradients and output the soil resistance gradient deviation; A4. For each soil layer, a resistance-time curve is fitted based on the time series to generate an actual resistance distribution curve under the current depth series. At the same time, a resistance distribution curve under the current depth series is intercepted from a preset sampling area and recorded as a reference resistance distribution curve. A5. Compare the actual resistance distribution curve with the reference resistance distribution curve, output the soil layer resistance distribution deviation, and integrate the soil layer resistance gradient deviation and the soil layer resistance distribution deviation to obtain the resistance deviation of the current soil layer; A6. Repeat steps A1 to A5 for the vibration frequency and hardness, and output the vibration frequency and hardness deviation of the current soil layer in sequence; The dynamic adjustment module combines the shovel head angle deviation value and the actual path position difference to dynamically adjust the drilling speed and drilling angle based on the drilling adjustment rules; The control execution module generates control instructions based on the adjusted drilling speed and drilling angle, driving the Luoyang shovel to perform the correction action; The trigger conditions of the dynamic adjustment module include: any one of the three deviations of resistance deviation, vibration frequency deviation and hardness deviation exceeds the set threshold, or the actual path position difference exceeds the limit, or the shovel head angle deviation continues to time out; The specific confirmation process of the actual path position difference is as follows: Project the real-time acquired position vertically onto the planned path, and calculate the perpendicular distance of each projection point to the planned path; If the number of projection points with continuous perpendicular distances not equal to 0 is within the set threshold, the maximum perpendicular distance is extracted, and the average perpendicular distance of the projection points is calculated. The actual path position difference is output by combining the maximum perpendicular distance and the average perpendicular distance. If the number of consecutive projection points with non-zero perpendicular distances is not within the set threshold, the sum of the perpendicular distances of each projection point corresponding to the planned path is taken as the actual path position difference.

2. The dry method precise positioning construction control system based on machine learning according to claim 1 is characterized by: The output of the soil layer resistance gradient deviation includes: According to the depth of each soil layer, the resistance deviation influence weight of each soil layer is set in combination with the historical accident database; The difference between the actual resistance gradient and the control resistance gradient corresponding to each soil layer is calculated. Based on the resistance deviation influence weight, the weighted sum is used to obtain the cumulative resistance gradient difference, which is used as the soil layer resistance gradient deviation.

3. The dry method precise positioning construction control system based on machine learning according to claim 1 is characterized in that: The output of the soil layer resistance distribution deviation includes: Project the actual resistance distribution curve onto the position of the control resistance distribution curve, and calculate the total length of the curve in the overlapping area of ​​the projection; The slope, number of peak points and number of valley points are extracted from the actual resistance distribution curve and the control resistance distribution curve respectively, and the total length, slope, number of peak points and number of valley points of the curve in the projected overlapping area are comprehensively considered to set the curve morphological deviation compensation factor for each soil layer. For the same soil layer, the amplitudes of the actual resistance distribution curve and the control resistance distribution curve are extracted respectively, and the difference between the two is obtained to obtain the resistance change amplitude difference. At the same time, the maximum resistance is extracted respectively, and the difference is obtained to obtain the maximum resistance difference. Based on the curve shape deviation compensation factor, the resistance change amplitude difference of each soil layer is corrected, and the corrected resistance change amplitude difference of each soil layer is output; The maximum resistance difference of each soil layer is combined to obtain the cumulative maximum resistance difference. The difference in the change amplitude of the corrected resistance of each soil layer is averaged to obtain the average change amplitude difference. The cumulative maximum resistance difference and the average change amplitude difference are used as the deviation of the soil layer resistance distribution.

4. The dry method precise positioning construction control system based on machine learning according to claim 1 is characterized in that: The dynamic adjustment of the drilling speed and drilling angle includes performing a drilling adjustment trigger assessment, including: If the shovel head angle deviation exceeds the set threshold, or the duration of the shovel head angle deviation exceeds the set time, or the ratio of the actual path position difference to the planned path exceeds the limit, the drilling angle adjustment is triggered; If any of the resistance, vibration frequency and hardness deviation exceeds the set threshold, the drilling speed adjustment is triggered.

5. The dry method precise positioning construction control system based on machine learning according to claim 1 is characterized in that: The dynamic adjustment of the drilling speed and drilling angle includes confirming the adjustment ratio. The specific confirmation process is as follows: The shovel head angle deviation, the duration of the shovel head angle deviation, and the actual path position difference are standardized respectively, and the processing results are weighted and summed as the input variables of the Sigmoid function, and the adjustment ratio of the drilling angle is output; The resistance, vibration frequency and hardness deviation are standardized, and the processing results are weighted and summed before being input into the Sigmoid function to output the adjustment ratio of the drilling speed.

6. A dry method precise positioning construction control method based on machine learning, executed by a dry method precise positioning construction control system based on machine learning as described in any one of claims 1 to 5, characterized in that: The method includes: S1. Multi-source data acquisition: real-time acquisition of drilling resistance, vibration frequency, shovel head angle deviation and position data, and simultaneous acquisition of current soil layer hardness data; S2. Construction deviation calculation: Combine drilling resistance, vibration frequency and hardness data to calculate the resistance, vibration frequency and hardness deviation of the soil layer corresponding to the preset sampling area; S3. Dynamic construction adjustment: Based on the shovel head angle deviation value and the actual path position difference, the drilling speed and drilling angle are dynamically adjusted based on the drilling adjustment rules; S4, drilling control execution: Generate control instructions based on the adjusted drilling speed and drilling angle to drive the Luoyang shovel to perform correction actions.

Images