A Smart Control Method and System for Vibro-compacting Equipment Based on Ground Identification
By integrating multi-source data and employing an active verification mechanism, the problem of inaccurate formation identification by vibro-compaction equipment under communication failure was solved, enabling efficient construction in complex geological environments.
Patent Information
- Application Number
- CN202610470218.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-10
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2046-04-10
AI Technical Summary
In complex geological environments, when communication failures prevent the acquisition of borehole data, existing technologies cannot effectively utilize multi-parameter correlations, leading to inaccurate formation identification and affecting the adaptability of vibro-compaction control strategies and construction quality.
Single-point verification is performed by fusing multi-source data (current, advance speed, and tension), trend analysis is conducted by constructing a detection window, formation attributes are determined by combining active verification actions, and the control strategy is optimized by utilizing an interference memory bank to achieve autonomous formation identification.
It effectively filters out interference and misjudgments caused by gravel, improves the reliability of stratum identification, ensures the continuity and quality of construction, and increases construction efficiency.
Smart Images

Figure CN122467148B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of vibratory compaction data processing technology, specifically to an intelligent control method and system for vibratory compaction equipment based on stratum identification. Background Technology
[0002] In complex geological environments, the density of different soil layers varies significantly. According to geological survey data, the fifth stratum is mainly composed of sand and gravel, containing a large amount of boulders; the fourth stratum is mainly composed of silt, clay, and silty clay. Due to the depth of the fifth-generation sand and gravel layer, the high content of boulders, and their large particle size, vibratory compactors cannot penetrate it directly. Therefore, high-frequency impact equipment such as down-the-hole hammers are currently commonly used for pilot drilling to penetrate the fifth stratum and form a through hole. Then, the vibratory compactor is controlled to descend along the pilot hole to achieve vibratory borehole formation.
[0003] Since different soil layers have different control strategies for vibratory compactors, another core purpose of pilot borehole drilling is to accurately identify the depth of the top interface of the fourth stratum, so as to provide a basis for adaptive control of the stratum in the subsequent borehole drilling stage.
[0004] In existing technologies, after the pilot borehole is completed, the pilot borehole data is typically stored in a vibro-compaction quality management platform, and analysis can yield a relatively accurate depth of the top of the fourth formation. However, during the vibro-compaction drilling stage, the vibro-compaction equipment control system and the remote vibro-compaction quality management platform rely on network communication to transmit pilot borehole data. When pilot borehole data cannot be obtained due to communication failures, poor network signals, or data transmission delays, the vibro-compaction equipment loses formation reference information, necessitating the use of alternative strategies for autonomous formation identification.
[0005] Existing alternative strategies typically rely on depth ranges and a single current threshold for judgment. Specifically, they obtain the upper and lower limits of the estimated top depth of the fourth stratum within the target borehole location area from geological survey data. Between these limits, the borehole current is checked for an increase based on the current threshold; if it increases, it indicates that the vibratory borehole has reached the fourth stratum. This approach has the following technical drawbacks: Down-the-hole (DH) hammers break rocks with high-frequency impact and use high-pressure gas to expel the rock fragments from the borehole, thus creating a through-hole with a diameter slightly larger than the vibratory compactor's diameter in the Quaternary boulder layer. However, when encountering large-diameter boulders, the DH hammer's breaking action can easily lead to hole wall spalling, residual gravel, or localized protrusions. These residual disturbances cause small fluctuations in the borehole current and a phased slowdown in the drilling speed during the vibratory compactor's descent. These dynamic characteristics are highly similar to the warning signs (slow current increase, slowed drilling speed) when entering the Quaternary clay layer. Existing alternative strategies neither effectively utilize the correlation between multiple parameters nor possess proactive verification methods for the formation's physical response. This makes it highly susceptible to misinterpreting residual disturbances as formation changes, leading to inaccurate identification of the Quaternary stratum's top interface depth, which in turn affects the adaptability of subsequent vibratory compaction control strategies and construction quality. Summary of the Invention
[0006] The purpose of this invention is to provide an intelligent control method and system for vibro-compacting equipment based on stratum identification, in order to solve the technical problem of inaccurate stratum identification caused by residual interference from the pilot hole and the high similarity between the pilot hole and the clay interface characteristics when communication failure prevents the acquisition of pilot hole data, thus resulting in low scheduling efficiency of vibro-compacting equipment.
[0007] To solve the above-mentioned technical problems, the present invention adopts the following solution: A method for intelligent control of vibro-impact equipment based on stratum identification is applied after drilling the fifth stratum using a high-frequency impact device in a complex geological environment. The method includes: S0. Obtain the response to the request for fourth-layer stratum data of the target pilot hole sent to the vibratory drilling quality management platform. When the response is identified as a data missing signal, respond to the data missing signal and obtain the upper and lower limits of the estimated top depth of the fourth stratum within the range of the target pilot hole location from the geological exploration data. S1. After the vibratory compactor hole is lowered to the upper limit, multi-source data reflecting the working status of the vibratory compactor and the formation response are collected at each depth point with a preset depth step size. S2. Perform conditional analysis based on the multi-source data of the current depth point. When the feature parameters of the multi-source data simultaneously meet the preset conditions, mark the depth point as a candidate point. S3. Construct a detection window containing multiple previous depth points with the current depth point as the endpoint. Based on the multi-source data of multiple depth points within the detection window and the distribution of candidate points, analyze the continuous trend of the stratum features within the detection window, and dynamically update the confidence of the detection window based on the analysis results of historical detection windows. S4. When the current depth point is a candidate point and the confidence level reaches the preset value, control the vibratory impactor to perform an active verification action at the current depth point. Determine the formation attributes of the current depth point based on the dynamic response characteristics during the active verification action, and switch the vibratory impact control strategy. Adjust the confidence level of the detection window based on the judgment result.
[0008] Furthermore, the data missing signal is generated automatically by the vibratory compaction equipment control system after it sends a request for fourth-layer formation data to the vibratory compaction quality management platform and does not receive a response from the platform within a preset time.
[0009] Furthermore, several physical parameters reflecting the working status of the vibratory compactor and the formation response include borehole current, drilling speed, and borehole pull force; the drilling speed is calculated by real-time detection of the depth position change of the vibratory compactor by a depth encoder and combined with time parameters.
[0010] Furthermore, in step S2, the process of performing conditional analysis based on multi-source data at the current depth point is as follows: Determine whether the drilling current, drilling speed, and drilling pull force at the current depth point meet the corresponding preset conditions. If all three conditions are met, mark the depth point as a candidate point. The preset conditions include current rise condition, slow advance condition, and stable tension condition; The current rise condition is: the increment of the borehole current at the current depth point relative to the borehole current at the previous depth point is greater than the preset current rise threshold. The slow advance condition is: the advance speed at the current depth point is less than the preset low advance speed threshold. The condition for stable tension is that the standard deviation of the hole-making tension at the current depth point and the preset depth points before it is less than the preset stable tension threshold.
[0011] Furthermore, in step S3, the process of obtaining the confidence level of the detection window is as follows: Calculate the proportion of candidate points within the current detection window, the first trend slope of the hole-forming current as a function of depth, and the second trend slope of the advance speed as a function of depth. The current confidence level of the current detection window is generated based on the proportion, the first trend slope, and the second trend slope. The current confidence level of the current detection window is weighted and fused with the historical confidence levels of the historical detection windows to obtain the updated confidence level of the current detection window.
[0012] Furthermore, in step S4, the process of correcting the confidence level of the detection window based on the judgment result is as follows: Based on the stratigraphic attribute judgment results, different weights are assigned to the current depth point: if it is judged to be the top interface of the fourth stratigraphic layer, it is given the first weight; if it is judged to be a low confidence point, it is given the second weight; if it is judged to be a gravel interference point, it is given the third weight; the first weight is greater than the second weight, and the second weight is greater than the third weight. The weighted proportion of candidate points in the current detection window is recalculated using weights to update the proportion of candidate points in the detection window; The confidence level of the current detection window is adjusted based on the updated percentage.
[0013] Furthermore, in step S4, the active verification action includes: controlling the vibratory impactor to pause drilling at the current depth point and retaining the vibration for a preset time; the dynamic response characteristics include the fluctuation amplitude of the drilling current during the retention period, the cumulative value of the vibratory impactor's sinking depth, and the sinking rate.
[0014] Furthermore, in step S4, the process of determining the formation attributes of the current depth point based on the dynamic response characteristics during the active verification action is as follows: The fluctuation amplitude of the hole-forming current, the cumulative value of the sinking depth of the vibratory impactor, and the sinking rate were obtained during the vibration period. If the fluctuation amplitude of the borehole current is less than the preset fluctuation threshold, and the cumulative value of the sinking depth is greater than the preset depth threshold and the sinking rate remains positive, then the current depth point is determined to be the top interface of the fourth stratum, and the vibratory compactor is controlled to execute the vibratory compaction control strategy corresponding to the fourth stratum. If the fluctuation amplitude of the hole-forming current is greater than the preset fluctuation threshold, and the cumulative value of the sinking depth is less than the preset depth threshold or the sinking rate is negative, then the current depth point is determined to be a gravel interference point, and the vibratory impactor is controlled to perform an upward reverse insertion operation. If the dynamic response characteristics do not meet any of the above judgment conditions, the current depth point is judged to be a low confidence point, and the vibratory impactor is controlled to continue to descend to form a hole.
[0015] Furthermore, when the current depth point is a point of rock interference, the depth interval containing the current depth point is stored in the interference memory bank, which has a memory decay mechanism: After each preset number of piles is constructed, the number of processing times for the depth range recorded in the interference memory is reduced by 1, and the memory is automatically cleared when the number of processing times reaches zero. When the vibratory compactor re-enters the depth range recorded in the interference memory, the preset value of the confidence level for triggering the active verification action is increased.
[0016] A smart control system for vibro-compacting equipment based on stratum identification, employing the aforementioned smart control method for vibro-compacting equipment based on stratum identification, includes: The pilot hole data acquisition module: acquires the response to the request for fourth-layer stratum data of the target pilot hole sent to the vibratory compaction quality management platform. When the response is identified as a data missing signal, it responds to the data missing signal and obtains the upper and lower limits of the estimated top depth of the fourth stratum within the range of the target pilot hole location from the geological exploration data. Multi-source data acquisition module: After the vibratory compactor hole is lowered to the upper limit, multi-source data reflecting the working status of the vibratory compactor and the formation response are collected at each depth point with a preset depth step size; Candidate point determination module: Based on the multi-source data of the current depth point, condition analysis is performed. When the feature parameters of the multi-source data simultaneously meet the preset conditions, the depth point is marked as a candidate point. Confidence detection module: Construct a detection window containing multiple previous depth points with the current depth point as the endpoint. Based on the multi-source data of multiple depth points within the detection window and the distribution of candidate points, analyze the continuous trend of the stratum features within the detection window, and dynamically update the confidence of the detection window based on the analysis results of historical detection windows. Active verification module: When the current depth point is a candidate point and the confidence level reaches the preset value, the vibratory compactor is controlled to perform an active verification action at the current depth point. The formation attributes of the current depth point are determined based on the dynamic response characteristics during the active verification action, so as to switch the vibratory compaction control strategy; the confidence level of the detection window is corrected based on the judgment result.
[0017] The beneficial effects of this invention are: This invention proposes an intelligent control method for vibro-compacting equipment based on geological formation identification. Through an autonomous generation mechanism for missing data signals, the vibro-compacting equipment can still initiate an intelligent identification process based on local geological survey data even when it cannot obtain borehole data from a remote platform. This ensures construction continuity and overcomes the excessive reliance on network communication in existing technologies. Compared with existing technologies, this invention has the following significant advantages: (1) Multi-source data fusion (current, advance speed, and tension) was used for single-point verification. The correlation between the three was used to construct a clay interface feature pattern, which effectively filtered out misjudgments caused by gravel interference, operation pauses, and sensor noise. Windowed trend analysis further fused discrete point information into regional features, quantified the credibility of stratigraphic changes, and fundamentally solved the problem of misjudgment in scenarios with similar features.
[0018] (2) An active verification mechanism was proposed, which changed the passive observation concept in the existing technology to active confirmation. By controlling the vibratory impactor to pause drilling at the suspected depth point and retain vibration, evidence of the formation response was actively obtained. This design enables the system to make judgments based on the physical characteristics of the formation itself, rather than relying solely on passive observation data. It distinguishes between clay interfaces and gravel interference from a mechanistic perspective, and the reliability of identification is greatly improved.
[0019] (3) The confidence level of the active verification results is corrected by feedback, so that subsequent judgments can make use of the verification experience. The interference memory bank records the area of gravel interference and has a memory decay mechanism, which enables the system to learn from historical experience, avoid repeated misjudgments in the same area, and significantly improve construction efficiency.
[0020] (4) A differentiated control strategy was proposed for the results of the stratigraphic property judgment: the pile-making strategy was switched immediately when encountering clay interfaces to ensure construction quality; the upward and reverse insertion was triggered when encountering gravel interference to remove construction obstacles; and the pile continued to descend when encountering low confidence points to maintain construction continuity. This hierarchical control strategy enabled the system to take into account quality assurance, efficiency optimization and safety. Attached Figure Description
[0021] Figure 1 This is a schematic diagram of the fifth stratum after the borehole is completed in Embodiment 1 of the present invention.
[0022] Figure 2 This is a schematic diagram of the intelligent control method for vibratory impact equipment in Embodiment 1 of the present invention.
[0023] Figure 3 This is a comparative schematic diagram showing the relationship between the drilling current, the advance speed, and the drilling pull force when the vibratory compaction equipment encounters clay interface and gravel interference in Embodiment 1 of the present invention. Detailed Implementation
[0024] 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. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the present invention or its application or use. 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.
[0025] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values of the components and steps described in these embodiments do not limit the scope of the invention.
[0026] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.
[0027] Furthermore, for clarity and brevity, descriptions of well-known structures, functions, and configurations may have been omitted. Those skilled in the art will recognize that various changes and modifications can be made to the examples described herein without departing from the spirit and scope of this disclosure.
[0028] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.
[0029] In all examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.
[0030] The present invention will now be described in detail with reference to the accompanying drawings and embodiments: Example 1 In this embodiment, an intelligent control method for vibro-impact equipment based on stratum identification is provided. This method is applied after the fifth stratum has been drilled using a high-frequency impact device in a complex geological environment.
[0031] like Figure 1As shown, in a complex geological environment, the fifth stratum is mainly composed of sand, gravel, and pebbles, and contains a large amount of boulders; the fourth stratum is mainly composed of silt, clay, and silty clay. High-frequency impact equipment such as down-the-hole hammers are used for pilot drilling to penetrate the fifth stratum and form a pilot hole.
[0032] Specifically, the main body executing the intelligent control method for vibratory compaction equipment is the vibratory compaction equipment control system. This control system is used to achieve efficient scheduling of the vibratory compaction equipment and communicates with the vibratory compactor, winch, various sensors, and remote vibratory compaction quality management platform.
[0033] like Figure 2 As shown, the intelligent control method for the vibratory compaction equipment mainly includes the following steps: S0. Obtain the response to the request for fourth-layer stratum data of the target pilot hole sent to the vibratory drilling quality management platform. When the response is identified as a data missing signal, respond to the data missing signal and obtain the upper and lower limits of the estimated top depth of the fourth stratum within the range of the target pilot hole location from the geological exploration data. S1. After the vibratory compactor hole is lowered to the upper limit, multi-source data reflecting the working status of the vibratory compactor and the formation response are collected at each depth point with a preset depth step size. S2. Perform conditional analysis based on the multi-source data of the current depth point. When the feature parameters of the multi-source data simultaneously meet the preset conditions, mark the depth point as a candidate point. S3. Construct a detection window containing multiple previous depth points with the current depth point as the endpoint. Based on the multi-source data of multiple depth points within the detection window and the distribution of candidate points, analyze the continuous trend of the stratum features within the detection window, and dynamically update the confidence of the detection window based on the analysis results of historical detection windows. S4. When the current depth point is a candidate point and the confidence level reaches the preset value, control the vibratory impactor to perform an active verification action at the current depth point. Determine the formation attributes of the current depth point based on the dynamic response characteristics during the active verification action, and switch the vibratory impact control strategy. Adjust the confidence level of the detection window based on the judgment result.
[0034] Based on the above principles, the present invention will be further explained and described as follows: First, step S0 is used for autonomous initiation and prior information acquisition. Before the vibratory compactor begins its descent, the vibratory compaction equipment control system first sends a request for fourth-layer formation data for the target pilot hole to the remote vibratory compaction quality management platform. This request is used to obtain the depth data of the top interface of the fourth-layer formation obtained from the down-the-hole hammer pilot hole analysis. However, in actual construction environments, due to unstable network signals, communication equipment failures, or data transmission delays, the control system may not receive a response from the vibratory compaction quality management platform within a preset time threshold. When this occurs, the control system determines that it is currently in a communication failure state and autonomously generates a data missing signal. In response to this data missing signal, the control system immediately retrieves the estimated upper and lower limits of the top depth of the fourth-layer formation from the locally stored geological exploration data.
[0035] It should be noted that the geological survey data is basic data obtained through geological exploration before construction, which provides the estimated depth range of each stratum. Although this range is not as precise as the borehole data, in current technology, the estimated depth range is still used as an important reference for communication failure scenarios. The upper and lower limits together constitute the prior reference interval for subsequent stratum identification. It is assumed that if there is a significant increase in current within the prior reference interval, it is determined that the vibratory tapper has hit the bottom of the borehole, that is, reached the top of the fourth stratum.
[0036] After completing step S0, the vibratory compactor begins to descend along the pilot hole to perform hole-making operations. When the vibratory compactor descends to the upper limit value obtained in step S0, the control system initiates the multi-source data acquisition process, i.e., step S1.
[0037] In step S1, data acquisition is performed at preset depth step intervals. The depth step interval refers to the time interval at which data acquisition is triggered after a fixed descent. In this embodiment, the preset depth step interval is 0.1 meters, meaning that the system records multi-source data for the current depth point every time the vibratory impactor descends 0.1 meters. This depth-triggered data acquisition method ensures that all data points are aligned along the depth dimension in subsequent analysis, facilitating trend analysis as depth changes.
[0038] In this embodiment, the multi-source data collected includes three core parameters: borehole current, drilling speed, and borehole pull force. Specifically, these three parameters are collected in the following ways: Borehole current acquisition: A current sensor is installed on the vibratory compactor to monitor the operating current of the vibratory compactor motor in real time. When the formation density increases, the energy required for the vibratory compactor to break the formation increases, and the operating current rises accordingly; conversely, when the formation is loose, the operating current decreases. This allows the borehole current to directly reflect the load condition of the vibratory compactor and is used to determine formation changes.
[0039] Data Acquisition of Advance Speed: A depth encoder is installed on the winch or vibratory compactor. This encoder can obtain the depth position of the vibratory compactor in real time by detecting the number of winch rotations or the displacement of the cable. Specifically, the control system continuously acquires depth data at a high frequency, forming a depth-time series. Based on this, the system calculates the depth change per unit time to obtain the advance speed. This allows the advance speed to reflect the efficiency of the vibratory compactor in penetrating the formation. When the formation hardens or encounters resistance, the advance speed will decrease significantly.
[0040] Data collection of drilling tension: A tension sensor is installed on the winch to monitor the tension of the wire rope in real time. During normal drilling, the tension value is relatively stable; when encountering obstacles such as loose rocks, the tension may suddenly increase or decrease; when entering clay layers, the tension may slightly decrease and its fluctuations may be reduced due to the lubrication effect of the clay. This drilling tension data reflects the stress state of the vibratory compactor within the hole, including the vibratory compactor's own weight, hole wall friction, and any potential obstacles encountered.
[0041] It is important to emphasize that the acquisition of the above three parameters is carried out simultaneously. When the depth reaches the preset step size, the control system simultaneously reads the current value and tension value at the current moment, and calculates the advance speed at that point based on the depth changes within the recent time window. Then, these three data are packaged into multi-source data for that depth point.
[0042] Step S2 is used for single-point verification and candidate point marking. In this embodiment, the preset conditions include current rise condition, slow advance condition, and stable tension condition, which are specifically defined as follows: Current rise condition: The increment of the drilling current at the current depth point relative to the drilling current at the previous depth point is greater than the preset current rise threshold. This condition is used to capture the gradual current rise characteristic of the clay interface. It should be noted that "incremental" rather than "absolute value" is used here to distinguish between the continuous rise of the clay interface and the instantaneous spike of gravel interference. Gravel interference often manifests as a sudden increase in current followed by a rapid drop, with large but not continuous changes between points; while the clay interface shows a continuous small increase with increasing depth. In this embodiment, the preset current rise threshold is 0.5A / 0.1m, and this value can be dynamically adjusted based on historical construction data.
[0043] Slow drilling speed condition: The drilling speed at the current depth point is less than a preset low drilling speed threshold. This condition is used to capture the characteristic of decreased drilling efficiency at the clay interface. After entering the clay layer, even with continuous vibration of the vibratory compactor, the sinking speed will be significantly slowed down due to the viscosity of the clay. In this embodiment, the preset low drilling speed threshold can be set to 0.1 m / min, and this value can also be adjusted according to geological conditions.
[0044] Tensile force stability condition: The standard deviation of the drilling tensile force at the current depth point and the preset number of depth points preceding it is less than a preset tensile force stability threshold. The current depth point and the preset number of depth points preceding it can be three points: the current depth point and the two depth points preceding it. This condition is used to eliminate interference from gravel. Gravel interference is often accompanied by drastic fluctuations in tensile force, while the tensile force in clay layers is relatively stable. By calculating the standard deviation of the tensile force at three consecutive points, the stability of the tensile force can be quantified. In this embodiment, the preset tensile force stability threshold is set to 0.2.
[0045] The control system marks the current depth point as a candidate point only when all three conditions are met simultaneously. At the same time, the system records the number of consecutive candidate points, that is, the number of depth points that consecutively meet the candidate conditions, tracing back from the current point. If the current depth point does not meet the conditions, the number of consecutive candidate points is reset to zero.
[0046] like Figure 3 As shown, the current depth point d k If all three conditions above are met, then the current depth point d k The clay interface (normally entering the fourth stratum) is characterized by the following at the current depth point d. k The hole-forming current relative to the previous depth point d k-1 The increment of the borehole current is greater than the preset current rise threshold; at the current depth point d k The feed rate is less than the preset low feed rate threshold; current depth point d k and its previous depth point d k-1 If the standard deviation of the hole-forming tension is less than the preset tension stabilization threshold, then the current depth point d will be... k Marked as a candidate point. In contrast, if the current depth point d k If none of the above three conditions are met simultaneously, then the current depth point d k The interference is caused by gravel (residual interference within the fifth stratum), which manifests as: a sudden increase in drilling current followed by a rapid decrease, resulting in a current spike that is not continuous; a decrease in drilling speed followed by a decrease, resulting in a trough; and severe fluctuations in drilling pull force due to gravel interference, exhibiting unstable pull force.
[0047] Step S3 is used for window trend analysis and confidence update. Firstly, regarding steps S2 and S3, this invention essentially designs a single-point detection window and a trend detection window. A dual-window collaborative mechanism achieves accurate stratigraphic identification. The process is as follows: The single-point detection window performs multi-parameter joint verification based on multi-source data from the current depth point, marking points that simultaneously meet the conditions of rising current, slowing footage, and stable tension as candidate points, thus achieving preliminary extraction of stratigraphic features from raw data. The trend detection window constructs a sliding window containing multiple previous points, with the current point as the endpoint. By analyzing the proportion of candidate points, current change trends, and footage change trends within the window, the continuity and stability of stratigraphic features are quantified, and historical information is integrated to dynamically update the confidence level. The aforementioned single-point detection window is mainly used for point feature extraction, while the trend detection window is mainly used for regional confidence assessment of the extracted point features. This combination of point and surface verification avoids accidental misjudgments from single points and achieves a leap from qualitative labeling to quantitative confidence, providing a reliable decision-making basis for subsequent active verification.
[0048] Therefore, in order to avoid single-point misjudgment, the control system constructs a detection window containing multiple previous depth points with the current depth point as the endpoint. Based on the multi-source data of multiple depth points within the window and the distribution of candidate points, it analyzes the continuous trend of the stratum features within the detection window and dynamically updates the confidence level of the window.
[0049] In this embodiment, the length of the detection window is 10 depth points. Since the depth step is 0.1 meters, the depth range corresponding to the window is 1.0 meter. The window slides continuously as it advances to the current depth point, always maintaining data from the 10 most recent points. At each depth point, the control system calculates the following three indicators: First, the percentage of candidate points: The percentage of candidate points is calculated by dividing the number of points marked as candidate points within the current detection window by the total number of points in the window. This indicator reflects the density of clay features within the window. If multiple consecutive points within the window are marked as candidate points, it indicates that the stratigraphic features are persistent, and the percentage will be high; conversely, if candidate points are sparse, the percentage will be low.
[0050] Second, the slope of the first trend of current variation with depth: A linear regression is performed on the depth values and borehole current values at all depth points within the window to obtain the slope of the current-depth trend line. This indicator reflects the overall trend of current variation with depth. If the current continues to rise, the slope is positive and the value is large; if the current fluctuates or decreases, the slope may be close to zero or negative.
[0051] Third, the slope of the second trend of feed rate as a function of depth: A linear regression is performed on the depth and feed rate values at all depth points within the window to obtain the slope of the feed rate-depth trend line. This indicator reflects the overall trend of feed rate as a function of depth. If the feed rate continues to decrease, the slope is negative and has a large absolute value; if the feed rate is stable or fluctuates, the slope is close to zero.
[0052] Based on the above three indicators, the control system generates the current confidence level for the current detection window. The confidence level is a value between 0 and 1, used to quantify the degree of matching between the stratigraphic features and the clay interface features within the current window. In this embodiment, the confidence level is generated using a weighted fusion method, that is, different weights are assigned to the candidate point proportion, current trend slope, and advance speed trend slope, and then the weighted sums are performed. The weight coefficients can be calibrated based on historical data; for example, the candidate point proportion weight is 0.4, the current trend slope weight is 0.3, and the advance speed trend slope weight is 0.3.
[0053] Then, after obtaining the current confidence level, the control system further weights and fuses it with the confidence levels of historical detection windows to obtain an updated confidence level for the current detection window. Specifically, an exponentially weighted moving average method is used, where the new confidence level equals the forgetting factor multiplied by the confidence level of the previous depth point, plus one minus the forgetting factor multiplied by the current confidence level. The forgetting factor is set to 0.8, ensuring that recent data contributes a larger weight while retaining historical trend information. This accumulation method effectively smooths out single-point fluctuations, making the confidence level more stably reflect the overall characteristics of the region.
[0054] Step S4 is used for active verification and feedback correction. When the current depth point is a candidate point and the confidence level reaches a preset value, the control system triggers an active verification action. The specific process of the active verification action is as follows: The control system sends a command to the winch to pause the drilling action, causing the vibratory compactor to remain at the current depth point. During the dwell period, the vibratory compactor remains vibrating but is no longer forced to move downwards. In this state, the depth change of the vibratory compactor depends entirely on the physical response of the formation itself. In this embodiment, the dwell time is set to 5 seconds, which is sufficient to obtain stable dynamic response characteristics without significantly affecting construction efficiency.
[0055] During the vibration period, the control system continuously monitors the following dynamic response characteristics: The fluctuation amplitude of the borehole current: Calculate the standard deviation of the borehole current during the vibration period to reflect the stability of the current. In clay strata, due to uniform damping, the current usually remains stable with a small fluctuation amplitude; in gravelly strata, due to the intermittent contact and slippage of gravel, the current fluctuates violently with a large fluctuation amplitude. Cumulative sinking depth of the vibratory compactor: Record the depth at the start and end of vibration, and calculate the difference to obtain the cumulative sinking depth. In clay strata, the vibration softens the soil, and the vibratory compactor will sink slowly under its own weight, resulting in a relatively large cumulative sinking depth. In gravelly strata, the gravel can obstruct the vibratory compactor, preventing it from sinking or even causing it to bounce slightly. Sinking rate: The average sinking rate is obtained by dividing the cumulative sinking depth by the vibration time. This indicator reflects the sustainability of sinking.
[0056] Based on the above correspondence between stratigraphic properties and dynamic response characteristics, the control system will determine the stratigraphic properties at the current depth point according to the following rules: Rule 1: If the fluctuation amplitude of the borehole current during the vibration period is less than the preset fluctuation threshold, and the cumulative value of the subsidence depth is greater than the preset depth threshold, and the subsidence rate remains positive, then the current depth point is determined to be the top interface of the fourth stratum. In this embodiment, the preset fluctuation threshold is 5A, and the preset depth threshold is 0.02m. This judgment rule corresponds to the typical response mode of clay strata: stable current and continuous subsidence.
[0057] Rule 2: If the fluctuation amplitude of the borehole current during the vibration period exceeds a preset fluctuation threshold, and the cumulative sinking depth is less than a preset depth threshold or the sinking rate is negative, then the current depth point is determined to be a gravel interference point. In this embodiment, a negative sinking rate indicates that the vibratory compactor has rebounded. This judgment rule corresponds to the typical response mode of gravel strata: violent current fluctuations, inability to sink, or rebound.
[0058] Rule 3: If the dynamic response features do not meet any of the above judgment conditions, then the current depth point is judged as a low confidence point.
[0059] In another embodiment, the correlation analysis of the three indicators of current, depth, and advance rate can be performed, and the formation attributes at the current depth point can be determined by combining the correspondence between other formation attributes and dynamic response characteristics.
[0060] Based on the geological property assessment results, the control system executes corresponding subsequent actions: If the location is determined to be the top interface of the fourth stratum: the control system immediately switches the vibratory compaction control strategy, changing from the borehole drilling mode to the pile driving mode corresponding to the fourth stratum, adjusting parameters such as vibration retention time and lifting depth. Simultaneously, this depth point is recorded as the confirmed interface depth.
[0061] If the point is identified as a rock-related obstacle: the control system triggers an upward reverse insertion operation, that is, it controls the winch to raise the vibratory impactor to 0.5m above the current depth point, and then re-drills down to remove the rock obstruction. At the same time, the depth range where the point is located is stored in the interference memory bank, with the range extended forward and backward by 0.15m from the current point, for a total length of 0.3m.
[0062] If the point is determined to be of low confidence: the control system will not take any special action and will continue the normal hole formation and descent.
[0063] Regardless of the judgment result, the control system will assign different weights to the current depth point based on the formation attribute judgment result, in order to correct the confidence of the detection window. In this embodiment, the weight values are as follows: If it is determined to be the top interface of the fourth stratum, assign it a high weight of 1.0; If a point is determined to have low confidence, assign it a moderate weight of 0.5. If it is determined to be a point of interference from gravel, assign it a low weight of 0.1.
[0064] Using the aforementioned weights, the control system will recalculate the weighted proportion of candidate points within the current detection window. This involves multiplying the weight of each point by its candidate label, summing the results, and then dividing by the sum of the weights. Then, based on the updated weighted proportions, the confidence level of the current detection window is regenerated according to the method described in step S3, thus achieving feedback correction of the confidence level based on the active verification results.
[0065] In one embodiment, when the current depth point is a rock-related disturbance point, the depth interval containing the current depth point is stored in the disturbance memory bank, which has a memory decay mechanism: After each preset number of piles is constructed, the number of processing times for the depth range recorded in the interference memory is reduced by 1, and the memory is automatically cleared when the number of processing times reaches zero. When the vibratory compactor re-enters the depth range recorded in the interference memory, the preset value of the confidence level for triggering the active verification action is increased.
[0066] The interference memory database is used to store the depth ranges of points identified as gravel interference points. Each record contains three fields: starting depth, ending depth, and number of processing steps. The number of processing steps is initially 1, indicating the number of times the area was identified as gravel. The memory decay mechanism is as follows: after the construction of every 10 piles is completed, the system automatically traverses all records in the interference memory database and decrements the number of processing steps for each record by 1; when the number of processing steps for a record decreases to 0, the record is automatically removed from the interference memory database; when the vibratory compactor re-enters the depth range recorded in the interference memory database, the system increases the confidence preset value for triggering the active verification action, which in this embodiment is increased from 0.5 to 0.7, meaning that stronger evidence is required to trigger verification again.
[0067] This mechanism enables the system to learn from historical experience: occasional interferences will be automatically forgotten after the construction of several piles; for persistent interferences that recur, the number of processing times will accumulate, and the system will remain vigilant for a long time, while avoiding invalid repeated verifications by increasing the trigger threshold.
[0068] Example 2 In this embodiment, an intelligent control system for vibro-compacting equipment based on stratum identification is provided. The method for intelligent control of vibro-compacting equipment based on stratum identification includes: The pilot hole data acquisition module: acquires the response to the request for fourth-layer stratum data of the target pilot hole sent to the vibratory compaction quality management platform. When the response is identified as a data missing signal, it responds to the data missing signal and obtains the upper and lower limits of the estimated top depth of the fourth stratum within the range of the target pilot hole location from the geological exploration data. Multi-source data acquisition module: After the vibratory compactor hole is lowered to the upper limit, multi-source data reflecting the working status of the vibratory compactor and the formation response are collected at each depth point with a preset depth step size; Candidate point determination module: Based on the multi-source data of the current depth point, condition analysis is performed. When the feature parameters of the multi-source data simultaneously meet the preset conditions, the depth point is marked as a candidate point. Confidence detection module: Construct a detection window containing multiple previous depth points with the current depth point as the endpoint. Based on the multi-source data of multiple depth points within the detection window and the distribution of candidate points, analyze the continuous trend of the stratum features within the detection window, and dynamically update the confidence of the detection window based on the analysis results of historical detection windows. Active verification module: When the current depth point is a candidate point and the confidence level reaches the preset value, the vibratory compactor is controlled to perform an active verification action at the current depth point. The formation attributes of the current depth point are determined based on the dynamic response characteristics during the active verification action, so as to switch the vibratory compaction control strategy; the confidence level of the detection window is corrected based on the judgment result.
[0069] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Based on the technical essence of the present invention, any simple modifications, equivalent substitutions, and improvements made to the above embodiments within the spirit and principles of the present invention shall still fall within the protection scope of the present invention.
Claims
1. A method for intelligent control of vibratory compaction equipment based on stratum identification, characterized in that, Applications include drilling into the fifth stratum using high-frequency impact equipment in complex geological environments, including: S0. Obtain the response to the request for fourth-layer stratum data of the target pilot hole sent to the vibratory drilling quality management platform. When the response is identified as a data missing signal, respond to the data missing signal and obtain the upper and lower limits of the estimated top depth of the fourth stratum within the range of the target pilot hole location from the geological exploration data. S1. After the vibratory compactor hole is lowered to the upper limit, multi-source data reflecting the working status of the vibratory compactor and the formation response are collected at each depth point with a preset depth step size. S2. Perform conditional analysis based on the multi-source data of the current depth point. When the feature parameters of the multi-source data simultaneously meet the preset conditions, mark the depth point as a candidate point. S3. Construct a detection window containing multiple previous depth points with the current depth point as the endpoint. Based on the multi-source data of multiple depth points within the detection window and the distribution of candidate points, analyze the continuous trend of the stratum features within the detection window, and dynamically update the confidence of the detection window based on the analysis results of historical detection windows. S4. When the current depth point is a candidate point and the confidence level reaches the preset value, control the vibratory impactor to perform an active verification action at the current depth point. Determine the formation attributes of the current depth point based on the dynamic response characteristics during the active verification action, and switch the vibratory impact control strategy. Adjust the confidence level of the detection window based on the judgment result.
2. The intelligent control method for vibratory compaction equipment based on stratum identification according to claim 1, characterized in that, The data missing signal is generated automatically by the vibratory compaction equipment control system after it sends a request for fourth-layer formation data to the vibratory compaction quality management platform and does not receive a response from the platform within a preset time.
3. The intelligent control method for vibratory compaction equipment based on stratum identification according to claim 1, characterized in that, Several physical parameters reflecting the working status of the vibratory compactor and the formation response include borehole current, drilling speed, and borehole pull force; the drilling speed is calculated by real-time detection of the depth position change of the vibratory compactor by a depth encoder and combined with time parameters.
4. The intelligent control method for vibratory compaction equipment based on stratum identification according to claim 3, characterized in that, In step S2, the process of performing conditional analysis based on multi-source data at the current depth point is as follows: Determine whether the drilling current, drilling speed, and drilling pull force at the current depth point meet the corresponding preset conditions. If all three conditions are met, mark the depth point as a candidate point. The preset conditions include current rise condition, slow advance condition, and stable tension condition; The current rise condition is: the increment of the borehole current at the current depth point relative to the borehole current at the previous depth point is greater than the preset current rise threshold. The slow advance condition is: the advance speed at the current depth point is less than the preset low advance speed threshold. The condition for stable tension is that the standard deviation of the hole-making tension at the current depth point and the preset depth points before it is less than the preset stable tension threshold.
5. The intelligent control method for vibratory compaction equipment based on stratum identification according to claim 3, characterized in that, In step S3, the process of obtaining the confidence level of the detection window is as follows: Calculate the proportion of candidate points within the current detection window, the first trend slope of the hole-forming current as a function of depth, and the second trend slope of the advance speed as a function of depth. The current confidence level of the current detection window is generated based on the proportion, the first trend slope, and the second trend slope. The current confidence level of the current detection window is weighted and fused with the historical confidence levels of the historical detection windows to obtain the updated confidence level of the current detection window.
6. The intelligent control method for vibratory compaction equipment based on stratum identification according to claim 5, characterized in that, In step S4, the process of adjusting the confidence level of the detection window based on the judgment result is as follows: Different weights are assigned to the current depth point based on the stratigraphic attribute judgment results: if it is judged to be the top interface of the fourth stratigraphic layer, it is given the first weight; if it is judged to be a low confidence point, it is given the second weight. If a point is identified as a gravel interference point, a third weight is assigned; the first weight is greater than the second weight, and the second weight is greater than the third weight. The weighted proportion of candidate points in the current detection window is recalculated using weights to update the proportion of candidate points in the detection window; The confidence level of the current detection window is adjusted based on the updated percentage.
7. The intelligent control method for vibratory compaction equipment based on stratum identification according to claim 1, characterized in that, In step S4, the active verification action includes: controlling the vibratory impactor to pause drilling at the current depth point and retaining the vibration for a preset time; the dynamic response characteristics include the fluctuation amplitude of the drilling current during the vibration retention period, the cumulative value of the vibratory impactor's sinking depth, and the sinking rate.
8. The intelligent control method for vibratory compaction equipment based on stratum identification according to claim 7, characterized in that, In step S4, the process of determining the formation attributes of the current depth point based on the dynamic response characteristics during the active verification action is as follows: The fluctuation amplitude of the hole-forming current, the cumulative value of the sinking depth of the vibratory impactor, and the sinking rate were obtained during the vibration period. If the fluctuation amplitude of the borehole current is less than the preset fluctuation threshold, and the cumulative value of the sinking depth is greater than the preset depth threshold and the sinking rate remains positive, then the current depth point is determined to be the top interface of the fourth stratum, and the vibratory compactor is controlled to execute the vibratory compaction control strategy corresponding to the fourth stratum. If the fluctuation amplitude of the hole-forming current is greater than the preset fluctuation threshold, and the cumulative value of the sinking depth is less than the preset depth threshold or the sinking rate is negative, then the current depth point is determined to be a gravel interference point, and the vibratory impactor is controlled to perform an upward reverse insertion operation. If the dynamic response characteristics do not meet any of the above judgment conditions, the current depth point is judged to be a low confidence point, and the vibratory impactor is controlled to continue to descend to form a hole.
9. The intelligent control method for vibratory compaction equipment based on stratum identification according to claim 8, characterized in that, When the current depth point is a point of interference from loose rocks, the depth interval containing the current depth point is stored in the interference memory bank, which has a memory decay mechanism: After each preset number of piles is constructed, the number of processing times for the depth range recorded in the interference memory is reduced by 1, and the memory is automatically cleared when the number of processing times reaches zero. When the vibratory compactor re-enters the depth range recorded in the interference memory, the preset value of the confidence level for triggering the active verification action is increased.
10. An intelligent control system for vibratory compaction equipment based on stratum identification, characterized in that, The application of the intelligent control method for vibratory compaction equipment based on stratum identification as described in any one of claims 1-9 includes: The pilot hole data acquisition module: acquires the response to the request for fourth-layer stratum data of the target pilot hole sent to the vibratory compaction quality management platform. When the response is identified as a data missing signal, it responds to the data missing signal and obtains the upper and lower limits of the estimated top depth of the fourth stratum within the range of the target pilot hole location from the geological exploration data. Multi-source data acquisition module: After the vibratory compactor hole is lowered to the upper limit, multi-source data reflecting the working status of the vibratory compactor and the formation response are collected at each depth point with a preset depth step size; Candidate point determination module: Based on the multi-source data of the current depth point, condition analysis is performed. When the feature parameters of the multi-source data simultaneously meet the preset conditions, the depth point is marked as a candidate point. Confidence detection module: Construct a detection window containing multiple previous depth points with the current depth point as the endpoint. Based on the multi-source data of multiple depth points within the detection window and the distribution of candidate points, analyze the continuous trend of the stratum features within the detection window, and dynamically update the confidence of the detection window based on the analysis results of historical detection windows. Active verification module: When the current depth point is a candidate point and the confidence level reaches the preset value, the vibratory compactor is controlled to perform an active verification action at the current depth point. The formation attributes of the current depth point are determined based on the dynamic response characteristics during the active verification action, so as to switch the vibratory compaction control strategy; the confidence level of the detection window is corrected based on the judgment result.
Citation Information
Patent Citations
Intelligent vibroflotation stratum identification method and control system
CN114622538A
Exploration drilling parameter control method and system
CN120575835A
