Automatic control system and method for punching pile driver based on big data

Abstract

The invention discloses a punching pile driver automatic control system and method based on big data, and relates to the technical field of punching pile driver automatic control, and the method specifically comprises the steps: 1, determining the operation area of a punching pile driver, collecting the working data of the punching pile driver in the operation area, setting the dynamic control coefficient of the punching pile driver, and setting the dynamic control coefficient of the punching pile driver; 2, determining stratum environment change factors of different pile holes, and constructing a prediction model for predicting a dynamic control coefficient calendar in a future time period based on a dynamic control coefficient historical sequence, and 3, judging whether a construction state in a current time period is normal or not through the prediction model of the dynamic control coefficient, and cooperatively adjusting an abnormal construction state through multiple parameters. According to the automatic control system and method for the punching pile driver based on the big data, a dynamic control coefficient prediction model is constructed by fusing three-dimensional coordinate data and multi-dimensional construction parameters of an operation area, and accurate regulation and control are achieved based on difference analysis of historical and real-time data.

Description

Technical Field

[0001] The present invention belongs to the technical field of automatic control of punching pile drivers, and particularly relates to an automatic control system and method for punching pile drivers based on big data. Background Art

[0002] With the rapid development of modern construction projects, as an important basic construction equipment, punching pile drivers have been widely used in the construction of large-scale infrastructure such as bridges, high-rise buildings, and subways. Traditional punching pile drivers mainly rely on manual operation or simple mechanized control, and their working efficiency and construction quality are greatly affected by the experience and technical level of operators. However, with the expansion of project scale and the increase in complexity, many problems have gradually emerged in traditional control methods. Most of the existing control systems for punching pile drivers use a single sensor for data acquisition and lack the ability to comprehensively analyze multi-source data. Due to the complex and changeable construction environment, a single data source often cannot fully reflect the actual situation of the construction site, resulting in a weak response ability of the system to unexpected situations. For example, in areas with complex geological conditions, relying solely on a single sensor may not be able to identify underground obstacles or geological changes in a timely manner, thus increasing construction risks.

[0003] In summary, the control methods of traditional punching pile drivers are difficult to meet the requirements of modern construction projects for efficient, accurate, and safe construction. Therefore, there is an urgent need for an automatic control system and method for punching pile drivers that can combine big data technology to achieve intelligent management, precise control, and efficient operation of the construction process. Such a system can not only significantly improve construction efficiency but also effectively reduce the uncertainties brought by human factors, providing more reliable technical support for engineering construction. Summary of the Invention

[0004] The purpose of the present invention is to provide an automatic control system and method for punching pile drivers based on big data, which are used to solve the technical problem that the actual situation of the construction site cannot be fully reflected in the prior art.

[0005] In order to achieve the above purpose, the present invention adopts the following technical solutions: An automatic control method for punching pile drivers based on big data, comprising: Step 1: Determine the operation area of the punching pile driver, and set the dynamic control coefficient of the punching pile driver by collecting the working data of the punching pile driver in the operation area. Step 2: Determine the formation environment change factors of different pile holes, and construct a prediction model for predicting the dynamic control coefficient history in the future time period based on the historical sequence of the dynamic control coefficient. Step 3: Judge whether the construction state in the current time period is normal through the prediction model of the dynamic control coefficient, and adjust the abnormal construction state through multi-parameter coordination.

[0006] Further, collect the working data of the punching pile driver in the operation area. The specific method is as follows: Divide the working time period of the punching pile driver by t duration, clarify the scope and boundary of the operation area of the punching pile driver, establish a three-dimensional coordinate system covering the entire operation area, mark the coordinate data of each pile hole punched by the punching pile driver, and use the relevant sensors pre-installed on the punching pile driver to collect the working data of the punching pile driver in real time. Record the working data collected within one time period as , where A(i) represents the average vibration amplitude of the punching pile driver in the i-th time period, F(i) represents the average impact force of the punching pile driver in the i-th time period, and f(i, k) represents the hammering frequency of the k-th hammering of the punching pile driver in the i-th time period, that is, the time interval length between the k-th hammering and the (k + 1)-th hammering, and k > 1.

[0007] Further, set the dynamic control coefficient of the punching pile driver. The specific method is as follows: Use the formula represents the dynamic control coefficient of the punching pile driver, where represents the average vibration amplitude of the punching pile driver in the i-th time period of the a-th pile hole, represents the average impact force of the punching pile driver in the i-th time period of the a-th pile hole, represents the hammering frequency of the k-th hammering of the punching pile driver in the i-th time period of the a-th pile hole, k ≥ 1, and n(i) represents the total number of hammerings of the punching pile driver in the i-th time period of the a-th pile hole, represents the maximum value of the hammering frequency of the punching pile driver in the i-th time period of the a-th pile hole, e represents the base of the natural logarithm. Quantify the dynamic balance of the construction state through the dynamic control coefficient, and determine the historical sequence of the dynamic control coefficient determined by the dynamic control coefficients of multiple historical time periods.

[0008] Further, determine the formation environment change factor of different pile holes. The specific method is as follows: Use the formula represents the formation environment change factor of different pile holes, where a represents the a-th pile hole, represents the formation environment change factor of the a-th pile hole changing with each time period, b is the basic factor, preset according to the engineering type. For example, for bridge pile foundation type, b = 0.25 is preset, and for building pile foundation type, b = 0.18 is preset, represents the sinking depth of the pile body of the a-th pile hole, represents the difference in the sinking depth of the pile body between the i-th time period and the (i - 1)-th time period of the a-th pile hole, It represents the total number of time periods when the punching pile driver works in the a-th pile hole, and i represents the i-th time period. It represents the average impact force of the punching pile driver in the i-th time period of the a-th pile hole. It represents all the time periods when the punching pile driver works in the a-th pile hole The average value.

[0009] Furthermore, a prediction model for predicting the dynamic control coefficient history in future time periods is constructed. The specific method is as follows: Using the formula It represents the prediction model of the dynamic control coefficient, where a represents the a-th pile hole, It represents the formation environment change factor of the a-th pile hole changing with each time period, It represents the dynamic control coefficient of the punching pile driver in the i-th time period of the a-th pile hole, It represents the predicted value of the dynamic control coefficient of the punching pile driver in the (i + 1)-th time period of the a-th pile hole. j represents the j-th time period when the punching pile driver works in the a-th pile hole, and j is not equal to i. It represents the control weight coefficient of the punching pile driver in the j-th time period of the a-th pile hole.

[0010] Furthermore, it is judged whether the construction state in the current time period is normal through the prediction model of the dynamic control coefficient. The specific method is as follows: Using the prediction model with verified accuracy, predict the dynamic control coefficient in the current time period through the dynamic control coefficient in the previous time period. In order to quantify the deviation between the current construction state and the predicted state, the difference degree is defined as the deviation characterization between the true value and the predicted value of the current dynamic control coefficient. When the difference degree in the i-th time period of the a-th pile hole is greater than or equal to the difference degree threshold, it is determined that the construction state deviates from the expectation and is in an abnormal state, and parameter adjustment is required.

[0011] Furthermore, the difference degree is defined as the deviation characterization between the true value and the predicted value of the current dynamic control coefficient. The specific method is as follows: Using the formula It represents the difference degree, where It represents the difference degree in the i-th time period of the a-th pile hole, It represents the dynamic control coefficient of the punching pile driver in the i-th time period of the a-th pile hole, It represents the predicted value of the dynamic control coefficient of the punching pile driver in the i-th time period of the a-th pile hole, It represents the total number of hammer blows of the punching pile driver in the i-th time period of the a-th pile hole, It represents the hammer blow frequency of the k-th hammer blow of the punching pile driver in the i-th time period of the a-th pile hole, It represents the average value of the hammering frequency of the impact pile driver during the i-th time period of the a-th pile hole.

[0012] Furthermore, the abnormal construction state is adjusted through multi-parameter coordination. The specific method is as follows: Using the formula According to the degree of difference, the adjustment reference values of the vibration amplitude, impact force and hammering frequency are calculated. Among them, sgn represents the sign function used to control the direction. It represents the adjustment reference value of the vibration amplitude during the i-th time period of the a-th pile hole. It represents the adjustment reference value of the impact force during the i-th time period of the a-th pile hole. It represents the adjustment reference value of the hammering frequency during the i-th time period of the a-th pile hole. xA represents the weight coefficient of the vibration amplitude, xF represents the weight coefficient of the impact force, xf represents the weight coefficient of the hammering frequency, and s, u and v are constant factors. According to the calculated adjustment amount, the vibration amplitude, impact force and hammering frequency of the impact pile driver are adjusted in the next time period.

[0013] The present invention also provides an automatic control system for an impact pile driver based on big data, which is applied to the automatic control method for an impact pile driver based on big data, and includes: A dynamic control coefficient setting module, which is used to determine the operation area of the impact pile driver, and set the dynamic control coefficient of the impact pile driver by collecting the working data of the impact pile driver in the operation area. A dynamic control coefficient prediction module, which is used to determine the formation environment change factors of different pile holes, and construct a prediction model for predicting the dynamic control coefficient history in the future time period based on the dynamic control coefficient historical sequence. A multi-parameter coordination adjustment module, which is used to judge whether the construction state in the current time period is normal through the prediction model of the dynamic control coefficient, and adjust the abnormal construction state through multi-parameter coordination.

[0014] To sum up, due to the adoption of the above technical solutions, the beneficial effects of the present invention are as follows: 1. By establishing a three-dimensional coordinate system covering the entire operation area and marking the coordinate data of the pile holes, the present invention facilitates subsequent data analysis and construction optimization. By comprehensively processing the working data in a time period, the dynamic control coefficient of the impact pile driver is set. By quantifying the dynamic balance of the construction state through the dynamic control coefficient, it helps to evaluate the stability and consistency of the impact pile driver during construction. Determining the dynamic control coefficient historical sequence can further analyze the change trend of the construction state and provide a basis for construction optimization and decision-making. 2. By determining the formation environment change factors, the present invention helps to accurately capture the change trend of the formation environment. Based on the historical sequence of the dynamic control coefficient and the formation environment change factors, the established prediction model can accurately predict the dynamic control coefficient in the future time period. The application of the prediction model also helps to reduce the uncertainty and risk during the construction process, improving the safety and controllability of the construction. 3. By combining the difference analysis with multi-parameter collaborative regulation, the present invention can monitor the construction state in real time and dynamically adjust the operation parameters of the punching pile driver, ensuring the efficiency and safety of the construction process. Combining the technical advantages of space-parameter fusion, precise prediction, high sensitivity, and stable regulation, the intelligent level of the punching pile driver is significantly improved, providing reliable technical support for the construction under complex geological conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 Shows the flowchart of the automatic control method for the punching pile driver based on big data; Figure 2 Shows the flowchart of the method for multi-parameter collaborative adjustment of abnormal construction states; Figure 3 Shows the module diagram of the automatic control system for the punching pile driver based on big data. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0018] Embodiment 1. The automatic control method for the punching pile driver based on big data as Figure 1 . Figure 2 shown specifically includes the following steps: Step 1. Determine the operation area of the punching pile driver, and set the dynamic control coefficient of the punching pile driver by collecting the working data of the punching pile driver in the operation area.

[0019] Divide the working time period of the punching pile driver by time t, and clarify the scope and boundary of the operation area of the punching pile driver within each working time period. The operation area is determined based on the engineering design drawings and on-site survey data. Through the GPS positioning system and the geographic information system, accurately delimit the boundary of the operation area, and mark the specific position of each pile hole of the punching pile driver. The determination of the operation area includes not only the planar position but also the depth range. Determine the data of the sinking depth of the pile body for each pile driving, establish a three-dimensional coordinate system covering the entire operation area, and mark the coordinate data of each pile hole of the punching pile driver. The specific coordinate data of the pile hole includes the planar coordinates (x, y). On the basis of establishing the three-dimensional coordinate system, use the relevant sensors pre-installed on the punching pile driver to collect the working data of the punching pile driver in real time, including collecting the vibration amplitude of the punching pile driver during the working process through the vibration sensor, measuring the impact force of the punching pile driver during the hammering process using the force sensor, and determining the hammering frequency by recording the time interval between adjacent hammerings of the punching pile driver within a time period. Record the working data collected within a time period as , where A(i) represents the average vibration amplitude of the punching pile driver in the i-th time period, F(i) represents the average impact force of the punching pile driver in the i-th time period, and f(i, k) represents the hammering frequency of the k-th hammering of the punching pile driver in the i-th time period, that is, the length of the time interval between the k-th hammering and the (k + 1)-th hammering, and k is greater than 1; Perform filtering and noise reduction on the collected working data, and eliminate the outliers in the working data to obtain the preprocessed working data. By comprehensively considering the preprocessed working data of the punching pile driver within a time period, set the dynamic control coefficient of the punching pile driver as a comprehensive characterization index of the construction state of the punching pile driver within this time period. The specific formula of the dynamic control coefficient is as follows: ; Among them, represents the average vibration amplitude of the punching pile driver in the i-th time period of the a-th pile hole, represents the average impact force of the punching pile driver in the i-th time period of the a-th pile hole, represents the hammering frequency of the k-th hammering of the punching pile driver in the i-th time period of the a-th pile hole, k is greater than or equal to 1, and n(i) represents the total number of hammerings of the punching pile driver in the i-th time period of the a-th pile hole, represents the maximum value of the hammering frequency of the punching pile driver in the i-th time period of the a-th pile hole, e represents the base of the natural logarithm. Quantify the dynamic balance of the construction state through the dynamic control coefficient, and determine the historical sequence of the dynamic control coefficient determined by the dynamic control coefficients of multiple historical time periods.

[0020] Step 2: Determine the formation environment change factors for different pile holes, and based on the historical sequence of dynamic control coefficients, construct a prediction model for the future time period of the dynamic control coefficient history.

[0021] Based on the impact force data and the pile body sinking depth data of the punching pile driver in each historical time period, determine the formation environment change factors for different pile holes. The specific formula is as follows: ; where a represents the a-th pile hole for pile driving, represents the formation environment change factor of the a-th pile hole for pile driving changing with each time period, b is the basic factor, preset according to the engineering type. For example, for bridge pile foundation type, b = 0.25 is preset, and for building pile foundation type, b = 0.18 is preset. represents the pile body sinking depth of the a-th pile hole for pile driving, represents the difference in pile body sinking depth between the i-th time period and the (i - 1)-th time period of the a-th pile hole for pile driving, represents the total number of time periods when the punching pile driver works in the a-th pile hole for pile driving, i represents the i-th time period, represents the average impact force of the punching pile driver in the i-th time period in the a-th pile hole for pile driving, represents all time periods when the punching pile driver works in the a-th pile hole for pile driving average value.

[0022] Integrate the historical sequence of dynamic control coefficients and the formation environment change factors of different pile holes in each time period to establish a prediction model for the dynamic control coefficient. The specific formula is as follows: ; where a represents the a-th pile hole for pile driving, represents the formation environment change factor of the a-th pile hole for pile driving changing with each time period, represents the dynamic control coefficient of the punching pile driver in the i-th time period in the a-th pile hole for pile driving, represents the predicted value of the dynamic control coefficient of the punching pile driver in the (i + 1)-th time period in the a-th pile hole for pile driving, j represents the j-th time period when the punching pile driver works in the a-th pile hole for pile driving, and j is not equal to i, represents the control weight coefficient of the punching pile driver in the j-th time period in the a-th pile hole for pile driving.

[0023] Set a prediction error threshold. When the error between the predicted value obtained from the prediction model and the actual value is greater than or equal to the prediction error threshold, it is necessary to adjust the parameters and weight coefficients of the prediction model until the error between the predicted value and the actual value is less than the error threshold. To further improve the accuracy of the prediction model, the real-time working data of the punching pile driver is used to dynamically correct the prediction model. Whenever the punching pile driver completes a working period, its working data during this period is input into the prediction model, and the prediction deviation is adjusted according to the real-time feedback, so as to optimize the performance of the prediction model.

[0024] Step 3: Judge whether the construction state in the current period is normal through the prediction model with dynamic control coefficients, and adjust the abnormal construction state through multi-parameter coordination.

[0025] Use a prediction model with verified accuracy to predict the dynamic control coefficient of the current period through the dynamic control coefficient of the previous period. To quantify the deviation between the current construction state and the predicted state, the difference degree is defined as the deviation characterization between the true value and the predicted value of the current dynamic control coefficient. The calculation formula of the difference degree is as follows: ; Among them, represents the difference degree in the i-th period of the a-th pile hole of pile driving, represents the dynamic control coefficient of the punching pile driver in the i-th period of the a-th pile hole of pile driving, represents the predicted value of the dynamic control coefficient of the punching pile driver in the i-th period of the a-th pile hole of pile driving, represents the total number of hammer blows of the punching pile driver in the i-th period of the a-th pile hole of pile driving, represents the hammering frequency of the k-th hammer blow of the punching pile driver in the i-th period of the a-th pile hole of pile driving, represents the average value of the hammering frequencies of the punching pile driver in the i-th period of the a-th pile hole of pile driving. The difference degree synthesizes the deviation of the dynamic control coefficient and the fluctuation of the vibration amplitude, which helps to comprehensively reflect the abnormal degree of the construction state.

[0026] Preset a difference degree threshold. When the difference degree in the i-th period of the a-th pile hole of pile driving is greater than or equal to the difference degree threshold, it is determined that the construction state deviates from the expectation and is in an abnormal state, and parameter adjustment is required; According to the difference degree, calculate the adjustment reference values of the vibration amplitude, impact force and hammering frequency. The specific formulas are as follows: ; Among them, sgn represents the sign function used to regulate the direction, represents the adjustment reference value of the vibration amplitude in the i-th period of the a-th pile hole of pile driving, represents the adjustment reference value of the impact force in the i-th period of the a-th pile hole of pile driving, It represents the adjustment reference value of the hammering frequency in the a-th piling hole during the i-th time period. xA represents the weight coefficient of the vibration amplitude, xF represents the weight coefficient of the impact force, xf represents the weight coefficient of the hammering frequency, and s, u, and v are constant factors. s is used to quickly suppress abnormal vibrations at high degrees of difference, u is used to smooth the impact force adjustment curve to avoid mutations, and v is used to gradually adjust the hammering frequency. In this embodiment, s is set to 1, u is set to -1, and v is set to 2. According to the calculated adjustment amount, the vibration amplitude, impact force, and hammering frequency of the punching pile driver are adjusted in the next time period.

[0027] By adjusting the operation parameters in real time, ensure that the construction state is always within the expected range, and avoid construction quality problems caused by sudden changes in the formation or equipment abnormalities.

[0028] Embodiment 2, as Figure 3 shown in the automated control system of the punching pile driver based on big data, specifically includes the following: The dynamic control coefficient setting module divides the working time period of the punching pile driver by t duration. In each working time period, the scope and boundary of the working area of the punching pile driver are defined. The working area is determined based on the engineering design drawings and on-site survey data. Through the GPS positioning system and geographic information system, the boundary of the working area is accurately delimited, and the specific position of each piling hole of the punching pile driver is marked. The determination of the working area includes not only the planar position but also the depth range. Determine the data of the sinking depth of the pile body for each piling, establish a three-dimensional coordinate system covering the entire working area, and mark the coordinate data of each piling hole of the punching pile driver. The specific coordinate data of the piling hole includes the planar coordinates (x, y). On the basis of establishing the three-dimensional coordinate system, use the relevant sensors pre-installed on the punching pile driver to collect the working data of the punching pile driver in real time, including collecting the vibration amplitude of the punching pile driver during the working process through the vibration sensor, measuring the impact force of the punching pile driver during the hammering process using the force sensor, and determining the hammering frequency by recording the time interval between adjacent hammerings of the punching pile driver within a time period. Denote the working data collected within a time period as , where A(i) represents the average vibration amplitude of the punching pile driver in the i-th time period, F(i) represents the average impact force of the punching pile driver in the i-th time period, and f(i, k) represents the hammering frequency of the k-th hammering of the punching pile driver in the i-th time period, that is, the time interval length between the k-th hammering and the (k + 1)-th hammering, and k > 1; Filter and reduce noise for the collected working data, and eliminate outliers in the working data to obtain the preprocessed working data. By synthesizing the preprocessed working data of the punching pile driver within a period of time, set the dynamic control coefficient of the punching pile driver as the comprehensive characterization index of the construction state of the punching pile driver within this period of time. The specific formula of the dynamic control coefficient is as follows: ; Among them, represents the average vibration amplitude of the punching pile driver within the i-th time period of the a-th pile hole, represents the average impact force of the punching pile driver within the i-th time period of the a-th pile hole, represents the hammering frequency of the k-th hammer blow of the punching pile driver within the i-th time period of the a-th pile hole, where k is greater than or equal to 1, and n(i) represents the total number of hammer blows of the punching pile driver within the i-th time period of the a-th pile hole, represents the maximum value of the hammering frequency of the punching pile driver within the i-th time period of the a-th pile hole, e represents the base of the natural logarithm. Quantify the dynamic balance of the construction state through the dynamic control coefficient, and determine the historical sequence of the dynamic control coefficient determined by the dynamic control coefficients of multiple historical time periods.

[0029] The dynamic control coefficient prediction module determines the formation environment change factors of different pile holes within each time period based on the impact force data and the pile body sinking depth data of the punching pile driver in each historical time period. The specific formula is as follows: ; Among them, a represents the a-th pile hole, represents the formation environment change factor of the a-th pile hole changing with each time period, b is the basic factor, preset according to the engineering type. For example, for bridge pile foundation type, b = 0.25 is preset, and for building pile foundation type, b = 0.18 is preset, represents the pile body sinking depth of the a-th pile hole, represents the difference in pile body sinking depth between the i-th time period and the (i - 1)-th time period of the a-th pile hole, represents the total number of time periods when the punching pile driver works in the a-th pile hole, i represents the i-th time period, represents the average impact force of the punching pile driver within the i-th time period of the a-th pile hole, represents all time periods when the punching pile driver works in the a-th pile hole average value.

[0030] Integrate the historical sequence of the dynamic control coefficient and the formation environment change factors of different pile holes within each time period to establish a prediction model of the dynamic control coefficient. The specific formula is as follows: ; wherein, a represents the a-th pile driving hole, represents the formation environment change factor of the a-th pile driving hole varying with each time period, represents the dynamic control coefficient of the punching pile driver at the i-th time period of the a-th pile driving hole, represents the predicted value of the dynamic control coefficient of the punching pile driver at the (i + 1)-th time period of the a-th pile driving hole, j represents the j-th time period when the punching pile driver works at the a-th pile driving hole, and j is not equal to i, represents the control weight coefficient of the punching pile driver at the j-th time period of the a-th pile driving hole.

[0031] Set a prediction error threshold. When the error between the predicted value obtained from the prediction model and the actual value is greater than or equal to the prediction error threshold, it is necessary to adjust the parameters and weight coefficients of the prediction model until the error between the predicted value and the actual value is less than the error threshold. To further improve the accuracy of the prediction model, the real-time working data of the punching pile driver is used to dynamically correct the prediction model. Whenever the punching pile driver completes a time period of work, its working data in this time period is input into the prediction model, and the prediction deviation is adjusted according to the real-time feedback, so as to optimize the performance of the prediction model.

[0032] The multi-parameter collaborative adjustment module uses a prediction model with verified accuracy to predict the dynamic control coefficient of the current time period through the dynamic control coefficient of the previous time period. To quantify the deviation between the current construction state and the predicted state, the difference degree is defined as the deviation characterization between the real value and the predicted value of the current dynamic control coefficient. The calculation formula of the difference degree is as follows: ; wherein, represents the difference degree at the i-th time period of the a-th pile driving hole, represents the dynamic control coefficient of the punching pile driver at the i-th time period of the a-th pile driving hole, represents the predicted value of the dynamic control coefficient of the punching pile driver at the i-th time period of the a-th pile driving hole, represents the total number of hammer blows of the punching pile driver within the i-th time period of the a-th pile driving hole, represents the hammering frequency of the k-th hammer blow of the punching pile driver within the i-th time period of the a-th pile driving hole, represents the average value of the hammering frequencies of the punching pile driver within the i-th time period of the a-th pile driving hole. The difference degree comprehensively considers the deviation of the dynamic control coefficient and the fluctuation of the vibration amplitude, and helps to comprehensively reflect the abnormal degree of the construction state.

[0033] Preset a difference threshold. When the difference in the $a$-th piling hole during the $i$-th time period is greater than or equal to the difference threshold, it is determined that the construction state deviates from the expectation and is in an abnormal state, and parameter adjustment is required; Calculate the adjustment reference values of the vibration amplitude, impact force, and hammering frequency according to the difference. The specific formulas are as follows: ; Among them, sgn represents the sign function used to regulate the direction, represents the adjustment reference value of the vibration amplitude in the $a$-th piling hole during the $i$-th time period, represents the adjustment reference value of the impact force in the $a$-th piling hole during the $i$-th time period, represents the adjustment reference value of the hammering frequency in the $a$-th piling hole during the $i$-th time period. $x_A$ represents the weight coefficient of the vibration amplitude, $x_F$ represents the weight coefficient of the impact force, $x_f$ represents the weight coefficient of the hammering frequency, and $s$, $u$, and $v$ are constant factors. $s$ is used to quickly suppress vibration anomalies at high differences, $u$ is used to smooth the impact force adjustment curve to avoid sudden changes, and $v$ is used to gradually adjust the hammering frequency. In this embodiment, $s$ is set to 1, $u$ is set to -1, and $v$ is set to 2.

[0034] By adjusting the operation parameters in real time, ensure that the construction state is always within the expected range, and avoid construction quality problems caused by sudden changes in the formation or equipment anomalies.

[0035] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

[0036] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the present invention to only the specific embodiments. Obviously, according to the content of this specification, many modifications and changes can be made. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the present invention, so that those skilled in the art can better understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. The automatic control method of punching pile driver based on big data is characterized in that: include: Step 1: determine the operating area of ​​the punching pile driver, and set the dynamic control coefficient of the punching pile driver by collecting the working data of the punching pile driver in the operating area; Step 2: Determine the stratum environment change factors of different pile holes, and build a prediction model for predicting the dynamic control coefficient history in future time periods based on the dynamic control coefficient history sequence; Step 3: Use the prediction model of the dynamic control coefficient to determine whether the construction status in the current time period is normal, and adjust the abnormal construction status through multi-parameter coordination.

2. The automatic control method for punching pile driver based on big data according to claim 1 is characterized in that: Collect the working data of the punching pile driver in the working area. The specific method is as follows: The working time period of the punching pile driver is divided into two parts according to the duration t. The scope and boundary of the working area of ​​the punching pile driver are clarified. A three-dimensional coordinate system covering the entire working area is established. The coordinate data of the pile holes driven by the punching pile driver each time are marked. The working data of the punching pile driver is collected in real time using the relevant sensors pre-installed on the punching pile driver. The working data collected in a time period is recorded as , where A(i) represents the average vibration amplitude of the punching pile driver in the i-th time period, F(i) represents the average impact force of the punching pile driver in the i-th time period, and f(i, k) represents the hammering frequency of the k-th hammering of the punching pile driver in the i-th time period, that is, the time interval between the k-th hammering and the k+1-th hammering, and k is greater than 1.

3. The automatic control method of punching pile driver based on big data according to claim 1 is characterized in that: Set the dynamic control coefficient of the punching pile driver. The specific method is: Using the formula represents the dynamic control coefficient of the punching pile driver, where represents the mean vibration amplitude of the punching pile driver in the a-th pile hole i time period, represents the mean impact force of the punching pile driver in the a-th pile hole i time period, represents the hammering frequency of the kth hammering of the punching pile driver in the i-th time period of the a-th pile hole, k is greater than or equal to 1, n(i) represents the total number of hammering times of the punching pile driver in the i-th time period of the a-th pile hole, It represents the maximum value of the hammer frequency of the punching pile driver in the a-th pile hole in the i-th time period, e represents the base of the natural logarithm, and the dynamic balance of the construction state is quantified by the dynamic control coefficient. The dynamic control coefficient historical sequence determined by the dynamic control coefficients of multiple historical time periods is determined.

4. The automatic control method of punching pile driver based on big data according to claim 1 is characterized in that: Determine the stratum environment change factor of different pile holes. The specific method is as follows: Using the formula represents the geological environment variation factor of different pile holes, where a represents the a-th pile hole, It represents the stratum environment change factor of the a-th pile hole as it changes in each time period. b is the basic factor, which is preset according to the project type. For example, b=0.25 is preset for bridge pile foundation type, and b=0.18 is preset for building pile foundation type. It indicates the sinking depth of the pile body in the a-th pile hole. It represents the difference between the depth of the pile body in the i-th time period and the i-1-th time period of the a-th pile hole. represents the total number of time periods in which the punching pile driver works in the ath pile hole, i represents the i-th time period, represents the mean impact force of the punching pile driver in the i-th time period of the a-th pile hole, Represents all the time periods during which the punching pile driver works in the a-th pile hole The average value of .

5. The automatic control method of punching pile driver based on big data according to claim 1 is characterized in that: Construct a prediction model for predicting the dynamic control coefficient of future time periods. The specific method is: Using the formula represents the prediction model of the dynamic control coefficient, where a represents the a-th pile hole, represents the stratum environment change factor of the a-th pile hole in each time period, represents the dynamic control coefficient of the punching pile driver in the i-th time period of the a-th pile hole, represents the predicted value of the dynamic control coefficient of the punching pile driver in the i+1th time period of the ath pile hole, j represents the jth time period of the punching pile driver working in the ath pile hole, and j is not equal to i, It represents the control weight coefficient of the punching pile driver in the jth time period of the ath pile hole.

6. The automatic control method of punching pile driver based on big data according to claim 1 is characterized in that: The prediction model of the dynamic control coefficient is used to determine whether the construction status in the current time period is normal. The specific method is as follows: Using a prediction model with verified accuracy, the dynamic control coefficient of the current time period is predicted by the dynamic control coefficient of the previous time period. In order to quantify the deviation between the current construction status and the predicted status, the difference is defined as the deviation between the true value and the predicted value of the current dynamic control coefficient. When the difference in the i-th time period of the a-th pile hole is greater than or equal to the difference threshold, it is determined that the construction status deviates from the expectation and is in an abnormal state, and parameter adjustment is required.

7. The automatic control method of punching pile driver based on big data according to claim 6 is characterized in that: The difference is defined as the deviation between the actual value and the predicted value of the current dynamic control coefficient. The specific method is: Using the formula represents the difference, where represents the difference in the i-th time period of the a-th pile hole, represents the dynamic control coefficient of the punching pile driver in the i-th time period of the a-th pile hole, represents the predicted value of the dynamic control coefficient of the punching pile driver in the i-th time period of the a-th pile hole, represents the total number of hammer blows of the punching pile driver in the a-th pile hole i time period, represents the hammering frequency of the kth hammering of the punching pile driver in the ath pile hole i time period, It represents the average hammer frequency of the pile driver in the a-th pile hole during the i-th time period.

8. The automatic control method of punching pile driver based on big data according to claim 7 is characterized in that: The abnormal construction status is adjusted through multi-parameter coordination. The specific method is as follows: Using the formula According to the difference, the vibration amplitude, impact force and hammer frequency are calculated to adjust the reference value, where sgn represents the sign function used to control the direction. represents the adjustment reference value of the vibration amplitude in the i-th time period of the a-th pile hole, It represents the adjustment reference value of the impact force in the i-th time period of the a-th pile hole. It represents the adjustment reference value of the hammer frequency in the i-th time period of the a-th piling hole, xA represents the weight coefficient of the vibration amplitude, xF represents the weight coefficient of the impact force, xf represents the weight coefficient of the hammer frequency, s, u and v are constant factors, and the vibration amplitude, impact force and hammer frequency of the punching pile driver are adjusted in the next time period according to the calculated adjustment amount.

9. A punching pile driver automation control system based on big data, applied to the punching pile driver automation control method based on big data as claimed in any one of claims 1 to 8, characterized in that: include: The dynamic control coefficient setting module is used to determine the working area of ​​the punching pile driver and set the dynamic control coefficient of the punching pile driver by collecting the working data of the punching pile driver in the working area; The dynamic control coefficient prediction module is used to determine the stratum environment change factors of different pile holes and build a prediction model for the dynamic control coefficient history in the future time period based on the dynamic control coefficient history sequence; The multi-parameter collaborative adjustment module is used to determine whether the construction status in the current time period is normal through the prediction model of the dynamic control coefficient, and to adjust the abnormal construction status through multi-parameter collaborative adjustment.

Images