Precise control method and system for centrifuge parameters of centrifugal process for tubular piles
By establishing a data-driven pipe pile strength prediction model and monitoring and correcting centrifuge parameters in real time, the problem of unstable strength in traditional pipe pile production was solved, and efficient pipe pile production control was achieved.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- CCCC THIRD HARBOR ENGINEERING CO LTD
- Filing Date
- 2025-05-13
- Publication Date
- 2026-04-23
AI Technical Summary
In traditional pipe pile production processes, the parameters of centrifuges lack scientific basis, resulting in unstable pipe pile strength, which makes it difficult to meet the engineering standards and safety requirements of modern buildings.
By acquiring historical production data, a long short-term memory network model is established to preprocess and clean centrifuge parameters, a pipe pile strength prediction model is established, and centrifuge parameters are monitored and corrected in real time to achieve precise control.
It improved the quality and safety of pipe pile production, reduced the scrap rate, enhanced the controllability and automation level of the production process, and reduced production costs.
Smart Images
Figure CN2025094484_23042026_PF_FP_ABST
Abstract
Description
Precise control method and system for centrifuge parameters used in pipe pile centrifugation process Technical Field
[0001] This invention relates to the field of pipe pile production technology, specifically to a method and system for precise control of centrifuge parameters in pipe pile centrifugation process. Background Technology
[0002] In modern construction and foundation engineering, pipe piles serve as an important foundation support structure, widely used in the construction of various buildings, bridges, and other infrastructure. The strength and density of pipe piles directly affect their load-bearing capacity and durability; therefore, strict control and prediction of their strength are necessary during the production process. Traditional pipe pile production processes rely heavily on experience and manual monitoring, lacking systematic parameter control. This results in unstable strength in the produced pipe piles, making it difficult to meet increasingly stringent engineering standards and safety requirements.
[0003] Especially in centrifugation processes, centrifuge parameters such as rotational speed, centrifugation time, and vibration frequency have a significant impact on the strength and density of the final product. However, specific parameter settings often lack scientific basis, easily leading to problems such as insufficient or excessive strength. With the development of building materials technology, the market's requirements for the strength of pipe piles are constantly increasing, making traditional production methods increasingly inadequate. Therefore, a new method is needed to achieve precise control of centrifuge parameters to ensure that the strength of pipe piles meets design standards.
[0004] In the prior art, CN114536541A discloses a method, equipment, and storage medium for producing pipe piles based on centrifugal technology. The method includes real-time acquisition of amplitude data at the centrifuge shaft during centrifugation, determining the deflection change characteristics of the shaft based on the amplitude data, judging whether the deflection change of the shaft tends to be constant based on the deflection change characteristics, and sending a stop command or speed adjustment command to the centrifuge when the deflection change is constant. This scheme relies solely on the deflection change characteristics of the shaft to determine the operating status, which may lead to insufficient sensitivity to vibration and resonance. The scheme focuses on the deflection change of the shaft while neglecting the monitoring of other key parameters (such as rotational speed, centrifugation time, and resonance frequency). These factors can significantly affect the strength and density of the pipe piles. Relying solely on deflection changes may not fully reflect the production status, leading to reduced system applicability and accuracy, resulting in unreliable quality of the produced pipe piles and weak controllability of the production process.
[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention
[0006] The purpose of this invention is to provide a precise control method and system for centrifuge parameters in the centrifugation process of pipe piles, so as to solve the problems mentioned in the background art.
[0007] To achieve the above objectives, the present invention provides the following technical solution:
[0008] A method for precise control of centrifuge parameters used in the centrifugation process of pipe piles, comprising the following steps:
[0009] S1. Obtain several sets of centrifuge parameters and strength data of the produced pipe piles from historical production. Preprocess the centrifuge parameters and corresponding strength data to generate a training sample set. The centrifuge parameters include rotation speed, centrifugation time, and vibration frequency.
[0010] S2. Establish a pipe pile strength prediction model. Use the centrifuge parameters in the training sample set as input data and the corresponding pipe pile strength data as labels to train the prediction model, so as to obtain a pipe pile strength prediction model with centrifuge parameters as input and pipe pile strength data as output.
[0011] S3. Input the real-time centrifuge parameters into the pipe pile strength prediction model to obtain the production prediction strength data of the pipe pile. Compare the production prediction strength data with the demand strength. If the production prediction strength data is greater than or equal to the demand strength, keep the current centrifuge parameters. If the production prediction strength data is less than the demand strength, proceed to step S4.
[0012] S4. Based on the compaction degree and resonance frequency of the pipe pile, the corresponding centrifuge parameters are corrected to obtain the corrected parameters of the centrifuge. The corrected parameters of the centrifuge are output to accurately control the centrifuge. The corrected parameters of the centrifuge include the speed correction value, the centrifugation time correction value, and the vibration frequency correction value.
[0013] Furthermore, the centrifuge parameters and corresponding intensity data are preprocessed. This preprocessing includes data standardization and data cleaning, wherein the formula used for data standardization is:
[0014] In the formula, N i For the standardized i-th rotational speed data, n i μ represents the i-th rotational speed data collected. n σ is the average value of the rotational speed data. n The variance of the rotational speed data;
[0015] Data cleaning is performed based on standardized data. The logic behind data cleaning is as follows: set an anomaly threshold Y.
[0016] In the formula, n iclRepresents the rotational speed data after the i-th cleaning, |N i | represents the absolute value of the i-th rotational speed data after standardization. The centrifugation time and vibration frequency are preprocessed in the same way to obtain the preprocessed centrifugation time, vibration frequency and pipe pile strength data.
[0017] Furthermore, a pipe pile strength prediction model is established based on a long short-term memory network model, and the hyperparameters of the LSTM model are set. The hyperparameters of the LSTM model include: number of network layers, number of iterations, learning rate, batch size, number of training iterations, number of batches, and number of hidden layer neurons.
[0018] The network is set to a 3-layer structure, the number of iterations is set to 100, the learning rate is set to 0.001, the batch size is set to 32, the number of training iterations is set to 100, and the number of hidden layer neurons is 64. After training, a pipe pile strength prediction model is obtained with inputs including centrifuge speed, centrifugation time and vibration frequency, and output as the predicted value of pipe pile strength.
[0019] Furthermore, the real-time collected centrifuge parameters, including the real-time rotational speed N, will be... s Real-time centrifugation time T s and real-time vibration frequency f s After preprocessing, the data is input into the trained pipe pile strength prediction model to obtain the predicted pipe pile strength value under the current parameters. The mean and variance used for data standardization are based on historical data, and the calibrated predicted pipe pile strength value is Q. for The intensity of demand is denoted as Q. tar ;
[0020] When Q for ≥Q tar At that time, the real-time rotational speed N is output. s Real-time centrifugation time T s and real-time vibration frequency f s To carry out the work;
[0021] When Q for tar At that time, for the real-time rotational speed N s Real-time centrifugation time T s and real-time vibration frequency f s Make corrections.
[0022] Further, step S4 includes the following steps:
[0023] S41, Based on the compaction and strength error of the pipe pile, the real-time rotational speed N s After correction, the speed correction value is obtained. The formula for calculating the speed correction value is: N corr =N s +k1*(ρp -ρ tar )-ω*(Q tar -Q for )
[0024] In the formula, N corr This represents the rotational speed correction value, k1 is the weighting coefficient for the compaction error of the pipe pile, and ρ p ρ represents the density of the pipe pile. tar Indicates reference density, (Q) tar -Q for ) represents the intensity error, and ω represents the weighting coefficient of the intensity error, where both ω and k1 are greater than 0;
[0025] S42, Based on the intensity error, the real-time centrifugation time T s After correction, the centrifugation time correction value is obtained. The formula used to calculate the centrifugation time correction value is: T corr =T s +ω*(Q tar -Q for )
[0026] In the formula, T corr This indicates the correction value for centrifugation time;
[0027] S43, Based on the resonance frequency and strength error of the pipe pile, the real-time vibration frequency f s After correction, the vibration frequency correction value is obtained. The formula used to calculate the vibration frequency correction value is as follows:
[0028] In the formula, f corr Here, k2 represents the vibration frequency correction value, and f is the safety factor. r This represents the resonant frequency of the pipe pile, where k2 is greater than 0.
[0029] Further, step S41 includes the following steps:
[0030] S411, the formula used to calculate the compaction of pipe piles based on the initial density of the pipe pile material and centrifugal force is as follows:
[0031] In the formula, ρ0 is the initial density of the pipe pile material, l is the compressibility coefficient of the material, F represents the centrifugal force, and g represents the gravitational acceleration.
[0032] The formula used to calculate the centrifugal force F is:
[0033] In the formula, m is the mass of the material, and R represents the centrifugal radius;
[0034] Meanwhile, step S43 includes the following steps:
[0035] S431, the formula used to calculate the resonance frequency of the pipe pile is:
[0036] In the formula, G represents the stiffness of the pipe pile;
[0037] The formula used to calculate the stiffness G of the pipe pile is as follows:
[0038] In the formula, E is the Young's modulus of the pipe pile material, I is the moment of inertia of the pipe pile section, and L is the length of the pipe pile.
[0039] This invention also provides a precise control system for centrifuge parameters in a pipe pile centrifugation process. The precise control system for centrifuge parameters in a pipe pile centrifugation process is used to execute the aforementioned precise control method for centrifuge parameters in a pipe pile centrifugation process, comprising:
[0040] The historical data preprocessing module is used to acquire several sets of centrifuge parameters and strength data of the produced pipe piles from historical production, preprocess the centrifuge parameters and corresponding strength data, and generate a training sample set. The centrifuge parameters include rotation speed, centrifugation time and vibration frequency.
[0041] The prediction model building module is used to build a pipe pile strength prediction model. It takes the centrifuge parameters in the training sample set as input data and the corresponding pipe pile strength data as labels to train the prediction model, resulting in a pipe pile strength prediction model with centrifuge parameters as input and pipe pile strength data as output.
[0042] The real-time parameter control module is used to input the real-time centrifuge parameters into the pipe pile strength prediction model to obtain the production prediction strength data of the pipe pile. The production prediction strength data is compared with the demand strength. If the production prediction strength data is greater than or equal to the demand strength, the current centrifuge parameters are maintained. If the production prediction strength data is less than the demand strength, the current centrifuge parameters are input into the centrifuge parameter correction module for correction.
[0043] The centrifuge parameter correction module is used to correct the current centrifuge parameters based on the compaction degree and resonance frequency of the pipe pile, obtain the corrected parameters of the centrifuge, and output the corrected parameters of the centrifuge for precise control of the centrifuge. The corrected parameters of the centrifuge include the speed correction value, the centrifugation time correction value, and the vibration frequency correction value.
[0044] Compared with the prior art, the beneficial effects of the present invention are:
[0045] Several sets of historical production pipe pile strength data and corresponding centrifuge parameters were acquired. The centrifuge parameters and corresponding strength data were preprocessed to produce a training sample set. The centrifuge parameters included rotational speed, centrifugation time, and vibration frequency. Multiple centrifuge parameters formed the basis for establishing a strength prediction model, improving data diversity and prediction accuracy. This pipe pile strength prediction model enables precise control of centrifuge parameters, effectively solving the problem of substandard pipe pile strength. Through the analysis and processing of historical production data, a data-driven strength prediction system was developed, allowing dynamic adjustment of centrifuge parameters during production, ensuring the quality and safety of the pipe piles. Simultaneously, the centrifuge parameters were corrected based on the pipe pile's density and resonance frequency, improving the automation and intelligence of pipe pile production and significantly reducing the scrap rate caused by improper parameter settings. This lowered production costs, improved resource utilization efficiency, and enhanced the controllability of the production process through real-time monitoring and feedback mechanisms. Attached Figure Description
[0046] Figure 1 is a schematic diagram of the overall method flow of the present invention;
[0047] Figure 2 is a schematic diagram of the overall system structure of the present invention. Detailed Implementation
[0048] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.
[0049] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0050] Example:
[0051] Please refer to Figure 1. This invention provides a technical solution:
[0052] A method for precise control of centrifuge parameters used in the centrifugation process of pipe piles, comprising the following steps:
[0053] S1. Obtain several sets of centrifuge parameters and strength data of the produced pipe piles from historical production. Preprocess the centrifuge parameters and corresponding strength data to generate a training sample set. The centrifuge parameters include rotation speed, centrifugation time, and vibration frequency.
[0054] The centrifuge parameters and corresponding intensity data are preprocessed, including data standardization and data cleaning. The formula used for data standardization is:
[0055] In the formula, N i For the standardized i-th rotational speed data, n i μ represents the i-th rotational speed data collected. n σ is the average value of the rotational speed data. n The variance of the rotational speed data;
[0056] Data cleaning is performed based on standardized data. The logic behind data cleaning is as follows: set an anomaly threshold Y.
[0057] In the formula, n icl Represents the rotational speed data after the i-th cleaning, |N i | represents the absolute value of the i-th speed data after standardization; let |N i Data exceeding the abnormal threshold Y are labeled as abnormal data, where the abnormal threshold Y is generally set to 3. Abnormal rotational speed data are cleared, along with the corresponding centrifugation time, vibration frequency, and intensity data. The preprocessing method for centrifugation time and vibration frequency is the same as that for rotational speed. The centrifugation time and vibration frequency are preprocessed using the same method to obtain preprocessed centrifugation time, vibration frequency, and pipe pile strength data. A training sample set is generated based on the preprocessed data, including rotational speed, centrifugation time, vibration frequency, and corresponding pipe pile strength data. The pipe pile strength data refers to compressive strength, which is the maximum pressure that concrete can withstand under compression and is an important indicator for evaluating concrete quality and structural safety.
[0058] S2. Establish a pipe pile strength prediction model. Use the centrifuge parameters in the training sample set as input data and the corresponding pipe pile strength data as labels to train the prediction model, so as to obtain a pipe pile strength prediction model with centrifuge parameters as input and pipe pile strength data as output.
[0059] A pipe pile strength prediction model is established based on a Long Short-Term Memory (LSTM) network model. The LSTM model selects an activation function and an optimization algorithm, with the Tanh function chosen as the activation function and Adam as the optimization algorithm for the LSTM model. The formula for the Tanh function is:
[0060] In the formula, f(x) represents the Tanh function, and the independent variable r represents the weighted sum of the neuron's inputs, that is, the result of the weighted sum of the inputs received by the neuron from the previous layer.
[0061] Simultaneously, the hyperparameters of the LSTM model are set, including: number of network layers, number of iterations, learning rate, batch size, number of training iterations, number of batches, and number of hidden layer neurons.
[0062] The network is set to a 3-layer structure, the number of iterations is set to 100, the learning rate is set to 0.001, the batch size is set to 32, the number of training iterations is set to 100, and the number of hidden layer neurons is 64. After training, a pipe pile strength prediction model is obtained with inputs including centrifuge speed, centrifugation time and vibration frequency, and output as the predicted value of pipe pile strength.
[0063] S3. Input the real-time centrifuge parameters into the pipe pile strength prediction model to obtain the production prediction strength data of the pipe pile. Compare the production prediction strength data with the demand strength. If the production prediction strength data is greater than or equal to the demand strength, keep the current centrifuge parameters. If the production prediction strength data is less than the demand strength, proceed to step S4.
[0064] The centrifuge parameters collected in real time include the real-time rotational speed N. s Real-time centrifugation time T s and real-time vibration frequency f s After preprocessing, the data is input into the trained pipe pile strength prediction model. The mean and variance used for data standardization are based on historical data to obtain the predicted pipe pile strength value under the current parameters. The calibrated predicted pipe pile strength value is Q. for The intensity of demand is denoted as Q. tar ;
[0065] When Q for ≥Q tar At that time, the real-time rotational speed N is output. s Real-time centrifugation time T s and real-time vibration frequency f s This indicates that the pipe piles produced under the current parameters can meet the actual working requirements, and no adjustment is needed. Production should continue to be carried out while maintaining the current parameters.
[0066] When Q for tar This indicates that under the current parameters, the strength of the produced pipe piles has not reached the actual required strength, and the current real-time rotational speed N needs to be adjusted. s Real-time centrifugation time T s and real-time vibration frequency f s Make adjustments to meet actual needs.
[0067] S4. Based on the compaction degree and resonance frequency of the pipe pile, the corresponding centrifuge parameters are corrected to obtain the corrected parameters of the centrifuge. The corrected parameters of the centrifuge are output to accurately control the centrifuge. The corrected parameters of the centrifuge include the speed correction value, the centrifugation time correction value, and the vibration frequency correction value.
[0068] Step S4 includes the following steps:
[0069] S41, Based on the compaction and strength error of the pipe pile, the real-time rotational speed N s After correction, the speed correction value is obtained. The formula for calculating the speed correction value is: N corr =N s +k1*(ρ p -ρ tar )-ω*(Q tar -Q for )
[0070] In the formula, N corr This represents the rotational speed correction value, k1 is the weighting coefficient for the compaction error of the pipe pile, and ρ p ρ represents the density of the pipe pile. tar Indicates reference density, (Q) tar -Q for ) represents the strength error, and ω represents the weighting coefficient of the strength error, where both ω and k1 are greater than 0; and since the strength error has a significant impact on the speed correction value, ω > k1, where k1*(ρ p -ρ tar This indicates the adjustment of rotational speed based on the deviation in the compaction degree of the pipe pile; when ρ p >ρ tar At this point, the system's density is high, meaning that the rotational speed needs to be appropriately reduced to minimize risk. When ρ p <ρ tar At this time, the system density is low, so the rotation speed can be appropriately increased.
[0071] When the strength of the produced pipe piles does not reach the expected set strength, the centrifuge speed should generally be reduced. Higher centrifuge speeds generate greater centrifugal force, which can lead to the separation of particles within the concrete, affecting the material's uniformity and density, thus reducing the strength of the pipe pile. Therefore, a speed correction value N is needed. corr It is inversely proportional to the strength error.
[0072] S42, Based on the intensity error, the real-time centrifugation time T s After correction, the centrifugation time correction value is obtained. The formula used to calculate the centrifugation time correction value is: T corr =T s+ω*(Q tar -Q for )
[0073] In the formula, T corr This indicates the correction value for centrifugation time;
[0074] When the strength of the produced pipe piles does not reach the expected set strength, the centrifugation time should usually be increased. Increasing the centrifugation time can make the concrete more fully compacted under the action of centrifugal force, help reduce pores, increase density, and thus improve the final strength. Therefore, the centrifugation time correction value is proportional to the strength error.
[0075] S43, Based on the resonance frequency and strength error of the pipe pile, the real-time vibration frequency f s After correction, the vibration frequency correction value is obtained. The formula used to calculate the vibration frequency correction value is as follows:
[0076] In the formula, f corr Here, k2 represents the vibration frequency correction value, and f is the safety factor. r This represents the resonant frequency of the pipe pile, where k2 is greater than 0, and k2 > ω to avoid the vibration frequency from approaching the resonant frequency.
[0077] When the strength of the produced pipe piles does not reach the expected set strength, the vibration frequency should generally be reduced, and the vibration frequency of the centrifuge should be adjusted to move it away from the resonance frequency to reduce the risk of resonance. Therefore, the vibration frequency correction value is related to the real-time vibration frequency f. s The resonant frequency f of the pipe pile r The ratio is inversely proportional. When the real-time vibration frequency is closer to the resonance frequency, the vibration frequency is reduced more by adjustment. The safety factor k2 can be calculated by the ratio of the maximum bearing capacity of the pipe pile to the maximum stress under dynamic response.
[0078] Step S41 includes the following steps:
[0079] S411, the formula used to calculate the compaction of pipe piles based on the initial density of the pipe pile material and centrifugal force is as follows:
[0080] In the formula, ρ0 is the initial density of the pipe pile material, l is the compressibility coefficient of the material, F represents the centrifugal force, and g represents the gravitational acceleration, which is usually taken as 9.8 m / s². 2 ;
[0081] The formula used to calculate the centrifugal force F is:
[0082] In the formula, m is the mass of the material, and R represents the centrifugal radius;
[0083] Meanwhile, step S43 includes the following steps:
[0084] S431, the formula used to calculate the resonance frequency of the pipe pile is:
[0085] In the formula, G represents the stiffness of the pipe pile;
[0086] The formula used to calculate the stiffness G of the pipe pile is as follows:
[0087] In the formula, E is the Young's modulus of the pipe pile material, I is the moment of inertia of the pipe pile section, and L is the length of the pipe pile.
[0088] Young's modulus (elastic modulus) is an inherent property of a material, reflecting the ratio of strain to stress when the material is subjected to force. Young's modulus can typically be obtained through several methods: obtaining stress-strain curves using standard compression or tensile tests, and then calculating the Young's modulus. For concrete, cubic or cylindrical specimens are usually used for testing. For common concrete types, empirical formulas for Young's modulus can be used for estimation, typically ranging from 25-30 GPa. Specific values will vary depending on the concrete's strength grade and mix proportions.
[0089] For hollow pipe piles, the moment of inertia can be calculated based on the outer diameter and inner diameter, using the following formula:
[0090] In the formula, D out D represents the outer diameter of the pipe pile. inn This indicates the inner diameter of the pipe pile.
[0091] Please refer to Figure 2.
[0092] This invention also provides a precise control system for centrifuge parameters in a pipe pile centrifugation process. The precise control system for centrifuge parameters in a pipe pile centrifugation process is used to execute the aforementioned precise control method for centrifuge parameters in a pipe pile centrifugation process, comprising:
[0093] The historical data preprocessing module is used to acquire several sets of centrifuge parameters and strength data of the produced pipe piles from historical production, preprocess the centrifuge parameters and corresponding strength data, and generate a training sample set. The centrifuge parameters include rotation speed, centrifugation time and vibration frequency.
[0094] The prediction model building module is used to build a pipe pile strength prediction model. It takes the centrifuge parameters in the training sample set as input data and the corresponding pipe pile strength data as labels to train the prediction model, resulting in a pipe pile strength prediction model with centrifuge parameters as input and pipe pile strength data as output.
[0095] The real-time parameter control module is used to input the real-time centrifuge parameters into the pipe pile strength prediction model to obtain the production prediction strength data of the pipe pile. The production prediction strength data is compared with the demand strength. If the production prediction strength data is greater than or equal to the demand strength, the current centrifuge parameters are maintained. If the production prediction strength data is less than the demand strength, the current centrifuge parameters are input into the centrifuge parameter correction module for correction.
[0096] The centrifuge parameter correction module is used to correct the current centrifuge parameters based on the compaction degree and resonance frequency of the pipe pile, obtain the corrected parameters of the centrifuge, and output the corrected parameters of the centrifuge for precise control of the centrifuge. The corrected parameters of the centrifuge include the speed correction value, the centrifugation time correction value, and the vibration frequency correction value.
[0097] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.
[0098] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.
[0099] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.
[0100] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.
Claims
1. A method for precise control of centrifuge parameters in a pipe pile centrifugation process, characterized in that, The specific steps include: S1. Obtain several sets of centrifuge parameters and strength data of the produced pipe piles from historical production. Preprocess the centrifuge parameters and corresponding strength data to generate a training sample set. The centrifuge parameters include rotation speed, centrifugation time, and vibration frequency. S2. Establish a pipe pile strength prediction model. Use the centrifuge parameters in the training sample set as input data and the corresponding pipe pile strength data as labels to train the prediction model, so as to obtain a pipe pile strength prediction model with centrifuge parameters as input and pipe pile strength data as output. S3. Input the real-time centrifuge parameters into the pipe pile strength prediction model to obtain the production prediction strength data of the pipe pile. Compare the production prediction strength data with the demand strength. If the production prediction strength data is greater than or equal to the demand strength, keep the current centrifuge parameters. If the production prediction strength data is less than the demand strength, proceed to step S4. S4. Based on the compaction degree and resonance frequency of the pipe pile, the corresponding centrifuge parameters are corrected to obtain the corrected parameters of the centrifuge. The corrected parameters of the centrifuge are output to accurately control the centrifuge. The corrected parameters of the centrifuge include the speed correction value, the centrifugation time correction value, and the vibration frequency correction value.
2. The method for precise control of centrifuge parameters in the centrifugation process of pipe piles according to claim 1, characterized in that: The centrifuge parameters and corresponding intensity data are preprocessed, including data standardization and data cleaning. The formula for data standardization is as follows: In the formula, N i is the standardized i th rotational speed data, n i represents the i th collected rotational speed data, μ n is the average of the rotational speed data, σ n is the variance of the rotational speed data; Data cleaning is performed based on standardized data. The logic behind data cleaning is as follows: set an anomaly threshold Y. In the formula, n icl Represents the rotational speed data after the i-th cleaning, |N i | represents the absolute value of the i-th rotational speed data after standardization. The centrifugation time and vibration frequency are preprocessed in the same way to obtain the preprocessed centrifugation time, vibration frequency and pipe pile strength data.
3. The method for precise control of centrifuge parameters in the centrifugation process for pipe piles according to claim 1, characterized in that: A pipe pile strength prediction model is established based on a long short-term memory network model. At the same time, the hyperparameters of the LSTM model are set. The hyperparameters of the LSTM model include: number of network layers, number of iterations, learning rate, batch size, number of training iterations, number of batches, and number of hidden layer neurons. The network structure is set to 3 layers, the number of iterations is set to 100, the learning rate is set to 0.001, the batch size is set to 32, the number of training iterations is set to 100, and the number of hidden layer neurons is 64. After training, a pipe pile strength prediction model is obtained with inputs including centrifuge speed, centrifugation time and vibration frequency, and output as the predicted value of pipe pile strength.
4. The method for precise control of centrifuge parameters in the centrifugation process of pipe piles according to claim 1, characterized in that: The centrifuge parameters collected in real time include the real-time rotational speed N. s Real-time centrifugation time T s and real-time vibration frequency f s After preprocessing, the data is input into the trained pipe pile strength prediction model to obtain the predicted pipe pile strength value under the current parameters. The mean and variance used for data standardization are based on historical data, and the calibrated predicted pipe pile strength value is Q. for The intensity of demand is denoted as Q. tar ; When Q for ≥Q tar At that time, the real-time rotational speed N is output. s Real-time centrifugation time T s and real-time vibration frequency f s To carry out the work; When Q for tar At that time, for the real-time rotational speed N s Real-time centrifugation time T s and real-time vibration frequency f s Make corrections. 5. The method for precise control of centrifuge parameters in the centrifugation process for pipe piles according to claim 4, characterized in that: Step S4 includes the following steps: S41, Based on the compaction and strength error of the pipe pile, the real-time rotational speed N s After making corrections, the speed correction value is obtained. The formula used to calculate the speed correction value is as follows: N corr =N s +k1*(ρ p -r tar )-ω*(Q tar -Q for ) In the formula, N corr This represents the rotational speed correction value, k1 is the weighting coefficient for the compaction error of the pipe pile, and ρ p ρ represents the density of the pipe pile. tar Indicates reference density, (Q) tar -Q for ) represents the intensity error, and ω represents the weighting coefficient of the intensity error, where both ω and k1 are greater than 0; S42, Based on the intensity error, the real-time centrifugation time T s After correction, the centrifugation time correction value is obtained. The formula used to calculate the centrifugation time correction value is as follows: T corr =T s +ω*(Q tar -Q for ) In the formula, T corr This indicates the correction value for centrifugation time; S43, Based on the resonance frequency and strength error of the pipe pile, the real-time vibration frequency f s After correction, the vibration frequency correction value is obtained. The formula used to calculate the vibration frequency correction value is as follows: In the formula, f corr Here, k2 represents the vibration frequency correction value, and f is the safety factor. r This represents the resonant frequency of the pipe pile, where k2 is greater than 0.
6. The method for precise control of centrifuge parameters in the centrifugation process for pipe piles according to claim 5, characterized in that: Step S41 includes the following steps: S411, the formula used to calculate the compaction of pipe piles based on the initial density of the pipe pile material and centrifugal force is as follows: In the formula, ρ0 is the initial density of the pipe pile material, l is the compressibility coefficient of the material, F represents the centrifugal force, and g represents the gravitational acceleration. The formula used to calculate the centrifugal force F is: In the formula, m is the mass of the material, and R represents the centrifugal radius; Meanwhile, step S43 includes the following steps: S431, the formula used to calculate the resonance frequency of the pipe pile is: In the formula, G represents the stiffness of the pipe pile; The formula used to calculate the stiffness G of the pipe pile is as follows: In the formula, E is the Young's modulus of the pipe pile material, I is the moment of inertia of the pipe pile section, and L is the length of the pipe pile.
7. A precise control system for centrifuge parameters used in the centrifugation process of pipe piles, characterized in that: The precise control system for centrifuge parameters in the pipe pile centrifugation process is used to execute the precise control method for centrifuge parameters in the pipe pile centrifugation process according to any one of claims 1-6, comprising: The historical data preprocessing module is used to acquire several sets of centrifuge parameters and strength data of the produced pipe piles from historical production, preprocess the centrifuge parameters and corresponding strength data, and generate a training sample set. The centrifuge parameters include rotation speed, centrifugation time and vibration frequency. The prediction model building module is used to build a pipe pile strength prediction model. It takes the centrifuge parameters in the training sample set as input data and the corresponding pipe pile strength data as labels to train the prediction model, resulting in a pipe pile strength prediction model with centrifuge parameters as input and pipe pile strength data as output. The real-time parameter control module is used to input the real-time centrifuge parameters into the pipe pile strength prediction model to obtain the production prediction strength data of the pipe pile. The production prediction strength data is compared with the demand strength. If the production prediction strength data is greater than or equal to the demand strength, the current centrifuge parameters are maintained. If the production prediction strength data is less than the demand strength, the current centrifuge parameters are input into the centrifuge parameter correction module for correction. The centrifuge parameter correction module is used to correct the current centrifuge parameters based on the compaction degree and resonance frequency of the pipe pile, obtain the corrected parameters of the centrifuge, and output the corrected parameters of the centrifuge for precise control of the centrifuge. The corrected parameters of the centrifuge include the speed correction value, the centrifugation time correction value, and the vibration frequency correction value.