An offshore wind power single pile intelligent sinking method and system
By constructing an adaptive hammering control system that combines a digital twin model with multi-source sensors, the problem of dynamic energy adjustment for offshore wind power piling equipment was solved, achieving an efficient and precise pile driving process, reducing the risk of hammer refusal and energy consumption, and improving construction efficiency and model adaptability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SINOHYDRO HARBOR CO LTD
- Filing Date
- 2026-03-10
- Publication Date
- 2026-06-05
AI Technical Summary
Existing offshore wind power piling equipment fails to dynamically adjust hammering parameters based on real-time soil response, resulting in over- or under-driving. It also lacks a forward-looking assessment of the cumulative effects on the soil, often leading to project delays.
A digital twin model integrating seabed geological exploration data and pile-soil interaction mechanism is constructed. Combined with data collected from multiple sources of sensors, the hammering energy is dynamically adjusted, and closed-loop control is achieved through adaptive hammering control and hammer rejection risk assessment.
It improved pile driving accuracy and construction efficiency, reduced the risk of hammer failure and equipment energy consumption, and enhanced the model's generalization ability.
Smart Images
Figure CN122147871A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of offshore wind power engineering technology, and in particular to an intelligent method and system for driving monopiles in offshore wind power. Background Technology
[0002] Offshore wind power engineering technology refers to a comprehensive set of professional technologies involved in the entire lifecycle of offshore wind power generation systems, including planning, design, construction, and operation and maintenance. It encompasses marine hydrological and meteorological analysis, wind turbine foundation design, submarine cable laying, offshore installation operations, corrosion protection, dynamic load response analysis, and marine environmental adaptability assessment. Its core objective is to achieve safe, stable, efficient, and economical operation of wind power facilities in the complex and ever-changing marine environment. This field highly integrates marine engineering, civil engineering, electrical engineering, materials science, and shipbuilding and marine structure technologies, and is a key supporting technology system for promoting the development of renewable energy in deep-sea areas.
[0003] Existing pile driving equipment mostly uses fixed or manually set hammering parameters, without dynamically adjusting the energy according to the real-time soil response, resulting in over-driving or under-driving. Moreover, the current hammer stopping standards are usually based only on the single penetration amount, lacking a forward-looking assessment of the cumulative effect on the soil. Often, the machine is only stopped passively after a hammer rejection occurs, delaying the construction period. Summary of the Invention
[0004] In view of the above-mentioned existing problems, the present invention provides an intelligent pile driving method for offshore wind power monopiles to solve the problems that existing pile driving equipment mostly uses fixed or manually set hammering parameters, and does not dynamically adjust the energy according to the real-time soil response, resulting in over-driving or under-driving. In addition, the current hammer stopping standard is usually based only on the single penetration amount, lacking a forward-looking assessment of the cumulative effect of the soil, and often only passively stops the machine after the hammer has failed to strike, thus delaying the construction period.
[0005] To solve the above problems, the present invention adopts the following technical solution: In a first aspect, the present invention provides a smart pile driving method for offshore wind power monopiles, the method comprising the following steps: S1: Construct an initial digital twin model that integrates seabed geological exploration data with the pile-soil interaction mechanism, and deploy multi-source sensors on the piling vessel and offshore wind turbine monopile to collect dynamic response data during the hammering process. S2: Based on the dynamic response data collected in S1, the soil mechanics laws and wave propagation characteristics are fused to reconstruct the current state of the pile-soil system, and the soil strength parameters and resistance distribution in the digital twin model are updated to obtain the dynamic pile driving resistance prediction results. S3: Calculate the optimal hammering energy required under the current working condition based on the dynamic pile driving resistance prediction results obtained in S2, and generate hammering control commands that match the pile-soil bearing capacity. S4: Execute the hammering control command to carry out pile driving operation, and simultaneously monitor pile driving efficiency, end bearing ratio and energy utilization attenuation trend to form risk assessment indicators; S5: When the risk assessment index exceeds the preset threshold, the intervention decision logic is invoked to generate pause waiting, energy adjustment or local scour auxiliary measures, and the hammering control command is regenerated based on the pile-soil state after the intervention. S6: Repeatedly execute hammering control and risk intervention operations until the offshore wind turbine monopile reaches the target penetration depth, and use the data from the entire process for iterative optimization of the digital twin model.
[0006] Furthermore, S1 specifically includes the following steps: S101: Collect the burial depth range, soil type identification, undrained shear strength, soil density, and permeability parameters of each soil layer; S102: Input the geometric and material parameters of the offshore wind turbine monopile into the geotechnical coupling modeling platform. The geometric parameters include the outer diameter. The material parameters include elastic modulus and yield strength, such as wall thickness and pile length. S103: Based on the above information, an initial digital twin model is established, which includes a side friction calculation module and a pile end bearing capacity calculation module distributed along the depth. S104: Install an impact force sensor and a triaxial accelerometer on the top of the single pile, arrange strain gauges and pore water pressure sensors in the middle of the pile body and near the pile end, and set a high-precision displacement monitoring device in the pile driving vessel hoisting system. S105: Activate the synchronous data acquisition system to continuously record time-series signals, including hammer force, during each hammering process. Pile top acceleration Pile strain pore water pressure and real-time displacement of the pile .
[0007] Furthermore, S2 specifically includes the following steps: S201: The collected pile top acceleration signal Numerical integration was performed to obtain the time history of the pile top velocity. ; S202: Combining the hammering force With pile resistance Calculate the downward stress wave for; ; Among them, the pile body impedance , The elastic modulus of the pile material. The cross-sectional area of the pile is... The velocity of a one-dimensional elastic wave in the pile; Simultaneously calculate the upward stress wave for: ; S203: Utilizing the aforementioned upward wave Inverse the depth to obtain the depth. Increment of side friction resistance at the location expression: ; S204: Introducing pore water pressure The effect on the effective stress of soil is defined by the effective stress reduction factor. : ; in, This represents the initial effective vertical stress of the soil at the current depth. S205: The effective stress reduction factor Used to correct the original adhesion coefficient The side friction resistance after the disturbance is obtained. : ; in, This represents the undrained shear strength of the corresponding soil layer. The pile end bearing capacity is simultaneously corrected as follows: ; in, This is the theoretical bearing capacity coefficient. The excess pressure reduction factor in the pile tip region. The undrained shear strength of the soil layer at the pile tip. This represents the projected area at the pile tip. S206: The final predicted value of total dynamic pile driving resistance is obtained through integration and superposition: ; in, This represents the total dynamic pile driving resistance experienced by a single offshore wind turbine pile at the current penetration depth. This indicates the current actual penetration depth of a single pile, that is, the vertical distance from the pile tip to the seabed surface. This represents the modified distribution function of side friction along depth, after considering soil disturbance, pore water pressure accumulation, and effective stress reduction. It represents the bearing capacity at the pile tip, that is, the resistance of the soil at the pile tip to the pile tip.
[0008] Furthermore, S3 specifically includes the following steps: S301: Establish the objective function for optimizing hammer impact energy, comprehensively considering construction efficiency and structural safety. The expression is: ; in, To input energy for a single hammer strike, For the desired penetration rate, The maximum tensile stress in the pile body is derived based on wave theory inversion. The allowable tensile stress of the pile material. and These are the normalized weighting coefficients; S302: The total dynamic pile driving resistance described in S206 As a physical constraint, the solution makes Maximize the optimal hammering energy and limited Within the capabilities of the hydraulic hammer equipment, i.e. ; S303: Apply the optimal hammering energy The stroke height and striking frequency of the hydraulic hammer are combined to generate an electronically controlled pulse sequence, which is then output to the hydraulic servo system to execute the next hammering action.
[0009] Furthermore, S4 specifically includes the following steps: S401: In the After each hammer blow, record the actual penetration depth increment. With the hammering energy consumed this time ; S402: Calculate the cumulative pile driving efficiency index : ; Simultaneously calculate the end load ratio. : ; when When the value exceeds 0.7, it indicates that the pile tip has entered a high-resistivity layer, the contribution of lateral resistance is weakened, and the risk of hammer failure increases. S403: Calculate the energy penetration per unit of the three most recent hammer blows. Linear regression was used to fit its changing trend to obtain the energy utilization decay slope. The expression is: ; like A value less than 0 and an absolute value that continues to increase indicates that soil hardening or pore pressure accumulation has led to a decrease in energy conversion efficiency. S404: Will , , These are combined into a three-dimensional risk assessment vector, which serves as the quantitative basis for the warning of hammer refusal.
[0010] Furthermore, S5 specifically includes the following steps: S501: Set the lower limit of pile driving efficiency index Upper limit of terminal resistance ratio and the negative threshold of the attenuation slope ; S502: When two consecutive hammering cycles satisfy... , and If this occurs, it is determined that there is a risk of the hammer being refused. S503: Initiating multi-level intervention decision-making logic: 1) If the excess pore water pressure measured by the pore water pressure sensor Exceeding the initial effective vertical stress at the current depth If the pore pressure dissipation rate reaches 60%, a pause and waiting operation will be performed. The pause duration will be dynamically determined based on the pore pressure dissipation rate, until... It has fallen back to a safe range; 2) If the pile tip is located in a sandy soil layer and the end bearing ratio is... If the value exceeds 0.75, the hammering energy for the next hammering cycle will be set to the optimal hammering energy of the previous cycle. 80% to reduce the intensity of impact disturbance; 3) If the soil around the pile is high-plasticity clay and the penetration depth increment of three consecutive hammer blows is less than 1 mm, then activate the annular high-pressure water jet device installed around the pile shoe to locally flush the pile end area with a constant flow rate to weaken the end resistance concentration effect. S504: After completing any of the above intervention measures, re-collect data on hammer force, pile top acceleration, and pore water pressure, input them into the dynamic resistance prediction process, and update the total dynamic pile driving resistance. The optimal hammering energy is recalculated based on the updated results. This generates the next hammer strike control command, achieving closed-loop control.
[0011] Furthermore, S6 specifically includes the following steps: S601: When the cumulative penetration depth of a single pile reaches the design depth Furthermore, the average penetration depth increase of the most recent ten hammer blows does not exceed the hammer-stopping standard. When the hammering operation is stopped; S602: The low-strain reflected wave method is used to conduct a final inspection of the pile integrity to confirm that the pile body has no fractures, necking or serious defects. S603: The entire process data from initial geological modeling, sensor deployment, dynamic resistance prediction, optimal hammer energy calculation, risk assessment to intervention execution will be encapsulated into a structured engineering sample. This sample includes timestamps, soil layer identification, original sensor signals, model update parameters, control command sequences, and final pile driving results. S604: Input the structured engineering sample described in S603 into a cross-project transfer learning network based on an attention mechanism to extract the mapping relationship between geological conditions, dynamic response, and control decisions; S605: Using the extracted mapping relationship, the initial digital twin model of the subsequent offshore wind power monopile driving project is initialized with prior parameters, and the threshold in the hammer failure risk criterion is adaptively calibrated. , and .
[0012] Secondly, the present invention provides an intelligent pile driving system for offshore wind power monopiles, used in the intelligent pile driving method for offshore wind power monopiles described in the first aspect. The system includes a geological digital twin modeling module, a multi-source sensor data acquisition module, a dynamic resistance prediction module, an adaptive hammering control module, a hammer rejection risk assessment module, and an intelligent intervention decision-making module. The specific uses of the modules are as follows: The geological digital twin modeling module is used to integrate seabed static cone penetration, multibeam bathymetry and seismic profile data, and combine single pile geometry and material parameters to construct an initial digital twin model that includes the ability to calculate side friction distribution and end resistance. The multi-source sensor data acquisition module is used to deploy impact force sensors, triaxial accelerometers, strain gauges, pore water pressure sensors and displacement monitoring devices on the piling vessel and offshore wind power monopile, and to simultaneously acquire high-frequency dynamic response signals during the hammering process. The dynamic resistance prediction module is used to reconstruct the pile-soil interface state in real time based on stress wave inversion and pore water pressure feedback, correct the soil adhesion coefficient and end bearing capacity, and output the dynamic total resistance of pile driving that takes into account soil disturbance and time-related softening. The adaptive hammering control module is used to solve for the optimal hammering energy that balances construction efficiency and structural safety, with the total dynamic pile driving resistance as a constraint, and to generate hydraulic hammer control commands that match the current pile-soil bearing capacity. The pile driving failure risk assessment module is used to calculate the pile driving efficiency index, end bearing ratio and energy utilization attenuation slope, construct a three-dimensional risk assessment vector, and quantify the pile driving failure tendency in the current pile driving process. The intelligent intervention decision module is used to automatically trigger pause and wait, energy reduction or local scour auxiliary measures when the risk assessment indicators exceed the limit, and regenerate hammering control commands based on the updated pile-soil state after intervention to achieve closed-loop intelligent control.
[0013] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the intelligent pile driving method for offshore wind power monopile as described in the first aspect of the present invention.
[0014] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein, when executed by a processor, the computer program implements any step of the intelligent pile driving method for offshore wind power monopiles as described in the first aspect of the present invention.
[0015] The beneficial effects of this invention are as follows: By constructing a digital twin model that integrates geological priors and real-time response, and combining dynamic resistance prediction driven by multi-source sensor data, adaptive hammer energy optimization, multi-dimensional hammer refusal risk quantification, and closed-loop intervention mechanism, the process of driving single piles for offshore wind power has achieved a fundamental transformation from experience-dependent and passive hammer stopping to state perception and active control. This effectively improves pile driving accuracy and construction efficiency, and effectively avoids the risk of hammer refusal caused by soil disturbance, pore water pressure accumulation, or sudden increase in end resistance, reducing the probability of pile damage and equipment energy consumption. At the same time, through full-process data feedback and cross-project knowledge transfer, the model's generalization ability is continuously optimized. Attached Figure Description
[0016] To more clearly illustrate the specific embodiments of the present invention, the accompanying drawings used in the description of the specific embodiments will be briefly introduced below. The accompanying drawings described below are example diagrams of the novel radio frequency front-end receiving surface acoustic wave filter module described above. Obviously, the accompanying drawings described below are merely exemplary. For those skilled in the art, other embodiment drawings can be derived from the provided drawings without creative effort.
[0017] Figure 1 A flowchart of the intelligent pile driving method for offshore wind power monopiles; Figure 2 This is a schematic diagram of an intelligent monopile driving system for offshore wind power. Detailed Implementation
[0018] Exemplary embodiments of the present patent will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present patent are shown in the drawings, it should be understood that the present patent can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present patent and to fully convey the scope of the present patent to those skilled in the art. It should be noted that, unless otherwise specified, the embodiments and features described in the present patent can be combined with each other. The present patent will now be described in detail with reference to the accompanying drawings and embodiments.
[0019] like Figure 1 As shown, as an embodiment of the present invention, this embodiment provides a smart pile driving method for offshore wind power monopiles, including the following steps: S1. Construct an initial digital twin model integrating seabed geological exploration data and pile-soil interaction mechanisms, and deploy multi-source sensors on the piling vessel and offshore wind turbine monopiles to collect dynamic response data during the hammering process. Specifically, this includes the following steps: S101: Obtain static cone penetration profiles, multibeam bathymetry results, and shallow seismic reflection data of the target sea area, and extract the burial depth range, soil type identification, undrained shear strength, soil density, and permeability parameters of each soil layer from them. S102: Input the geometric and material parameters of the offshore wind turbine monopile into the geotechnical coupling modeling platform. The geometric parameters include the outer diameter. The material parameters include elastic modulus and yield strength, such as wall thickness and pile length. S103: Based on the above information, an initial digital twin model is established, which includes a side friction calculation module and a pile end bearing capacity calculation module distributed along the depth. S104: Install an impact force sensor and a triaxial accelerometer on the top of the single pile, arrange strain gauges and pore water pressure sensors in the middle of the pile body and near the pile end, and set a high-precision displacement monitoring device in the pile driving vessel hoisting system. S105: Activate the synchronous data acquisition system to continuously record time-series signals, including hammer force, during each hammering process. Pile top acceleration Pile strain pore water pressure and real-time displacement of the pile .
[0020] It should be noted that by integrating high-resolution seabed geological exploration data with single-pile physical parameters to construct an initial digital twin model, and deploying a multi-source sensor network covering the entire hammer-pile-soil link, comprehensive perception of the pile driving environment and structural response was achieved. This provides a high-fidelity and highly synchronous data foundation for subsequent dynamic modeling and intelligent control, effectively solving the core problems of geological blind spots and invisible processes in traditional pile driving.
[0021] S2. Based on the dynamic response data fusion of soil mechanics laws and wave propagation characteristics, the current state of the pile-soil system is reconstructed, and the soil strength parameters and resistance distribution in the digital twin model are updated to obtain the dynamic pile driving resistance prediction results. Specifically, this includes the following steps: S201: The collected pile top acceleration signal Numerical integration was performed to obtain the time history of the pile top velocity. ; S202: Combining the hammering force With pile resistance Calculate the downward stress wave for; ; Among them, the pile body impedance , The elastic modulus of the pile material. The cross-sectional area of the pile is... The velocity of a one-dimensional elastic wave in the pile; Simultaneously calculate the upward stress wave for: ; S203: Utilizing the aforementioned upward wave Inverse the depth to obtain the depth. Increment of side friction resistance at the location expression: ; This formula shows that the side friction is determined by the time derivative of the upward wave, reflecting the dynamic damping effect of the soil on the pile motion; S204: Introducing pore water pressure The effect on the effective stress of soil is defined by the effective stress reduction factor. : ; in, This represents the initial effective vertical stress of the soil at the current depth. S205: Effective stress reduction factor Used to correct the original adhesion coefficient The side friction resistance after the disturbance is obtained. : ; in, This represents the undrained shear strength of the corresponding soil layer. The pile end bearing capacity is simultaneously corrected as follows: ; in, This is the theoretical bearing capacity coefficient. The excess pressure reduction factor in the pile tip region. The undrained shear strength of the soil layer at the pile tip. This represents the projected area at the pile tip. S206: The final predicted value of total dynamic pile driving resistance is obtained through integration and superposition: ; in, This represents the total dynamic pile driving resistance experienced by a single offshore wind turbine pile at the current penetration depth. This indicates the current actual penetration depth of a single pile, that is, the vertical distance from the pile tip to the seabed surface. This represents the modified distribution function of side friction along depth, after considering soil disturbance, pore water pressure accumulation, and effective stress reduction. It represents the bearing capacity at the pile tip, that is, the resistance of the soil at the pile tip to the pile tip.
[0022] It should be noted that, based on the stress wave propagation theory and measured data of pore water pressure, the side friction and end bearing capacity are dynamically corrected, upgrading the pile driving resistance prediction from a static empirical formula to a time-varying model that considers soil disturbance, excess pore pressure accumulation and age-related softening. This effectively improves the accuracy of resistance prediction and lays a physically reliable calculation basis for precise energy delivery and early risk warning.
[0023] S3. Calculate the optimal hammering energy required under the current working conditions based on the dynamic pile driving resistance prediction results, and generate hammering control commands that match the pile-soil bearing capacity. Specifically, this includes the following steps: S301: Establish the objective function for optimizing hammer impact energy, comprehensively considering construction efficiency and structural safety. The expression is: ; in, To input energy for a single hammer strike, For the desired penetration rate, The maximum tensile stress in the pile body is derived based on wave theory inversion. The allowable tensile stress of the pile material. and These are the normalized weighting coefficients; S302: The total dynamic pile driving resistance described in S206 As a physical constraint, the solution makes Maximize the optimal hammering energy and limited Within the capabilities of the hydraulic hammer equipment, i.e. ; S303: Apply the optimal hammering energy The stroke height and striking frequency of the hydraulic hammer are combined to generate an electronically controlled pulse sequence, which is then output to the hydraulic servo system to execute the next hammering action.
[0024] It should be noted that by introducing a multi-objective optimization function that takes into account both construction efficiency and structural safety, the optimal hammering energy is dynamically solved under the premise of satisfying the pile strength constraint. This avoids the over-driving damage or under-driving stagnation caused by traditional fixed-parameter pile driving, and realizes intelligent control of on-demand supply of hammering energy and precise matching of the real-time bearing capacity of the pile-soil system.
[0025] S4. Execute hammer control commands to carry out pile driving operations, and simultaneously monitor pile driving efficiency, end bearing ratio, and energy utilization attenuation trend to form risk assessment indicators. This specifically includes the following steps: S401: In the After each hammer blow, record the actual penetration depth increment. With the hammering energy consumed this time ; S402: Calculate the cumulative pile driving efficiency index : ; This index reflects the penetration depth achieved per unit of energy; a higher value indicates better pile driving efficiency. It also calculates the end bearing capacity ratio. : ; when When the value exceeds 0.7, it indicates that the pile tip has entered a high-resistivity layer, the contribution of lateral resistance is weakened, and the risk of hammer failure increases. S403: Calculate the energy penetration per unit of the three most recent hammer blows. Linear regression was used to fit its changing trend to obtain the energy utilization decay slope. The expression is: ; like A value less than 0 and an absolute value that continues to increase indicates that soil hardening or pore pressure accumulation has led to a decrease in energy conversion efficiency. S404: Will , , These are combined into a three-dimensional risk assessment vector, which serves as the quantitative basis for the warning of hammer refusal.
[0026] It should be noted that by constructing a three-dimensional risk assessment vector consisting of the pile driving efficiency index, the end bearing ratio, and the energy attenuation slope, the judgment of failure to hammer is upgraded from a single, crude standard to a multi-dimensional, trend-based, and quantitative intelligent criterion, which effectively enhances the sensitivity and accuracy of early signs of failure to hammer.
[0027] S5. When the risk assessment indicators exceed the preset threshold, the intervention decision logic is invoked to generate pause / wait, energy adjustment, or local scour auxiliary measures, and the hammering control command is regenerated based on the pile-soil state after the intervention. Specifically, the following steps are included: S501: Set the lower limit of pile driving efficiency index Upper limit of terminal resistance ratio and the negative threshold of the attenuation slope ; S502: When two consecutive hammering cycles satisfy... , and If this occurs, it is determined that there is a risk of the hammer being refused. S503: Initiating multi-level intervention decision-making logic: 1) If the excess pore water pressure measured by the pore water pressure sensor Exceeding the initial effective vertical stress at the current depth If the pore pressure dissipation rate reaches 60%, a pause and waiting operation will be performed. The pause duration will be dynamically determined based on the pore pressure dissipation rate, until... It has fallen back to a safe range; 2) If the pile tip is located in a sandy soil layer and the end bearing ratio is... If the value exceeds 0.75, the hammering energy for the next hammering cycle will be set to the optimal hammering energy of the previous cycle. 80% to reduce the intensity of impact disturbance; 3) If the soil around the pile is high-plasticity clay and the penetration depth increment of three consecutive hammer blows is less than 1 mm, then activate the annular high-pressure water jet device installed around the pile shoe to locally flush the pile end area with a constant flow rate to weaken the end resistance concentration effect. S504: After completing any of the above intervention measures, re-collect data on hammer force, pile top acceleration, and pore water pressure, input them into the dynamic resistance prediction process, and update the total dynamic pile driving resistance. The optimal hammering energy is recalculated based on the updated results. This generates the next hammer strike control command, achieving closed-loop control.
[0028] It should be noted that by establishing a multi-level intervention decision logic based on physical mechanisms and working condition characteristics, different response measures are automatically triggered for different causes of hammer failure, and control instructions are updated in a closed loop after intervention. This realizes an intelligent operation process from passive hammer stopping to active intervention, state recovery, and continued pile driving, reducing unplanned downtime.
[0029] S6. Continuously execute hammering control and risk intervention operations until the offshore wind turbine monopile reaches the target penetration depth, and use the entire process data for iterative optimization of the digital twin model. Specifically, this includes the following steps: S601: When the cumulative penetration depth of a single pile reaches the design depth Furthermore, the average penetration depth increase of the most recent ten hammer blows does not exceed the hammer-stopping standard. When the hammering operation is stopped; S602: The low-strain reflected wave method is used to conduct a final inspection of the pile integrity to confirm that the pile body has no fractures, necking or serious defects. S603: The entire process data from initial geological modeling, sensor deployment, dynamic resistance prediction, optimal hammer energy calculation, risk assessment to intervention execution will be encapsulated into a structured engineering sample. This sample includes timestamps, soil layer identification, original sensor signals, model update parameters, control command sequences, and final pile driving results. S604: Input the structured engineering sample described in S603 into a cross-project transfer learning network based on an attention mechanism to extract the mapping relationship between geological conditions, dynamic response, and control decisions; S605: Using the extracted mapping relationship, the initial digital twin model of the subsequent offshore wind power monopile driving project is initialized with prior parameters, and the threshold in the hammer failure risk criterion is adaptively calibrated. , and .
[0030] It should be noted that structuring the entire process of engineering data and using it for cross-project transfer learning not only completes the quality closed-loop verification of a single pile driving, but also realizes knowledge accumulation and model evolution, enabling the digital twin system to have continuous learning and generalization capabilities, which can shorten the deployment cycle of new sites and improve the adaptability and robustness of intelligent pile driving methods under complex and variable seabed conditions.
[0031] like Figure 2 As shown, this embodiment also provides an intelligent monopile driving system for offshore wind power, including: The system includes a geological digital twin modeling module, a multi-source sensor data acquisition module, a dynamic resistance prediction module, an adaptive hammering control module, a hammer rejection risk assessment module, and an intelligent intervention decision-making module. The following is a description of the included modules: 1) Geological digital twin modeling module, used to integrate seabed static cone penetration, multibeam bathymetry and seismic profile data, combined with single pile geometry and material parameters, to construct an initial digital twin model including side friction distribution and end resistance calculation capabilities; 2) Multi-source sensor data acquisition module, used to deploy impact force sensors, triaxial accelerometers, strain gauges, pore water pressure sensors and displacement monitoring devices on pile driving vessels and offshore wind power monopiles, to simultaneously acquire high-frequency dynamic response signals during the hammering process; 3) Dynamic resistance prediction module, which is used to reconstruct the pile-soil interface state in real time based on stress wave inversion and pore water pressure feedback, correct the soil adhesion coefficient and end bearing capacity, and output the dynamic total resistance of pile driving that takes into account soil disturbance and time-related softening. 4) Adaptive hammering control module, which is used to solve the optimal hammering energy that balances construction efficiency and structural safety with the total dynamic pile driving resistance as a constraint, and generate hydraulic hammer control commands that match the current pile-soil bearing capacity. 5) Refusal to hammer risk assessment module, used to calculate pile driving efficiency index, end bearing ratio and energy utilization attenuation slope, construct three-dimensional risk assessment vector, and quantify the refusal to hammer tendency in the current pile driving process; 6) Intelligent intervention decision module, which is used to automatically trigger pause and wait, energy reduction or local scour auxiliary measures when the risk assessment indicators exceed the limit, and regenerate hammering control commands based on the updated pile-soil state after intervention to achieve closed-loop intelligent control.
[0032] This embodiment also provides a computer device applicable to the intelligent pile driving method for offshore wind power monopiles, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the intelligent pile driving method for offshore wind power monopiles as proposed in the above embodiment.
[0033] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.
[0034] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the intelligent pile driving method for offshore wind power monopiles as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.
[0035] In summary, this invention, by constructing a digital twin model that integrates geological priors and real-time response, and combining dynamic resistance prediction driven by multi-source sensor data, adaptive hammer energy optimization, multi-dimensional quantification of hammer refusal risk, and a closed-loop intervention mechanism, achieves a fundamental transformation in the offshore wind power monopile driving process from experience-dependent and passive hammer stopping to state-aware and proactive control. This effectively improves pile driving accuracy and construction efficiency, and effectively avoids the risk of hammer refusal caused by soil disturbance, pore water pressure accumulation, or sudden increase in end resistance, reducing the probability of pile damage and equipment energy consumption. At the same time, through full-process data feedback and cross-project knowledge transfer, the model's generalization ability is continuously optimized.
[0036] It should be noted that the content and exemplary embodiments herein are only used to illustrate the technical solution of this patent, but the implementation of this patent is not limited to the above content. Any changes, modifications, substitutions, combinations, etc., made without departing from the innovative essence and principle of this patent are included within the protection scope of this patent. Those skilled in the art can understand the specific meaning of the above terms in the patent according to the specific circumstances.
Claims
1. A smart pile driving method for offshore wind power monopiles, characterized in that: The method includes the following steps: S1: Construct an initial digital twin model that integrates seabed geological exploration data with the pile-soil interaction mechanism, and deploy multi-source sensors on the piling vessel and offshore wind turbine monopile to collect dynamic response data during the hammering process. S2: Based on the dynamic response data collected in S1, the soil mechanics laws and wave propagation characteristics are fused to reconstruct the current state of the pile-soil system, and the soil strength parameters and resistance distribution in the digital twin model are updated to obtain the dynamic pile driving resistance prediction results. S3: Calculate the optimal hammering energy required under the current working condition based on the dynamic pile driving resistance prediction results obtained in S2, and generate hammering control commands that match the pile-soil bearing capacity. S4: Execute the hammering control command to carry out pile driving operation, and simultaneously monitor pile driving efficiency, end bearing ratio and energy utilization attenuation trend to form risk assessment indicators; S5: When the risk assessment index exceeds the preset threshold, the intervention decision logic is invoked to generate pause waiting, energy adjustment or local scour auxiliary measures, and the hammering control command is regenerated based on the pile-soil state after the intervention. S6: Repeatedly execute hammering control and risk intervention operations until the offshore wind turbine monopile reaches the target penetration depth, and use the data from the entire process for iterative optimization of the digital twin model.
2. The intelligent pile driving method for offshore wind power monopiles according to claim 1, characterized in that: S1 specifically includes the following steps: S101: Collect the burial depth range, soil type identification, undrained shear strength, soil density, and permeability parameters of each soil layer; S102: Input the geometric and material parameters of the offshore wind turbine monopile into the geotechnical coupling modeling platform. The geometric parameters include the outer diameter. The material parameters include elastic modulus and yield strength, such as wall thickness and pile length. S103: Based on the above information, an initial digital twin model is established, which includes a side friction calculation module and a pile end bearing capacity calculation module distributed along the depth. S104: Install an impact force sensor and a triaxial accelerometer on the top of the single pile, arrange strain gauges and pore water pressure sensors in the middle of the pile body and near the pile end, and set a high-precision displacement monitoring device in the pile driving vessel hoisting system. S105: Activate the synchronous data acquisition system to continuously record time-series signals, including hammer force, during each hammering process. Pile top acceleration Pile strain pore water pressure and real-time displacement of the pile .
3. The intelligent pile driving method for offshore wind power monopiles according to claim 2, characterized in that: S2 specifically includes the following steps: S201: The collected pile top acceleration signal Numerical integration was performed to obtain the time history of the pile top velocity. ; S202: Combining the hammering force With pile resistance Calculate the downward stress wave for; ； Among them, the pile body impedance , The elastic modulus of the pile material. The cross-sectional area of the pile is... The velocity of a one-dimensional elastic wave in the pile; Simultaneously calculate the upward stress wave for: ； S203: Utilizing the aforementioned upward wave Inverse the depth to obtain the depth. Increment of side friction resistance at the location expression: ； S204: Introducing pore water pressure The effect on the effective stress of soil is defined by the effective stress reduction factor. : ； in, This represents the initial effective vertical stress of the soil at the current depth. S205: The effective stress reduction factor Used to correct the original adhesion coefficient After obtaining the side friction resistance after the disturbance : ； in, This represents the undrained shear strength of the corresponding soil layer. The pile end bearing capacity is simultaneously corrected as follows: ； in, This represents the bearing capacity at the pile tip, which is the resistance of the soil at the pile tip to the pile. This is the theoretical bearing capacity coefficient. The excess pressure reduction factor in the pile tip region. The undrained shear strength of the soil layer at the pile tip. This represents the projected area at the pile tip. S206: The final predicted value of total dynamic pile driving resistance is obtained through integration and superposition: ； in, This represents the total dynamic pile driving resistance experienced by a single offshore wind turbine pile at the current penetration depth. This indicates the current actual penetration depth of a single pile, that is, the vertical distance from the pile tip to the seabed surface. This represents the modified distribution function of side friction along depth after considering soil disturbance, pore water pressure accumulation, and effective stress reduction.
4. The intelligent pile driving method for offshore wind power monopiles according to claim 3, characterized in that: S3 specifically includes the following steps: S301: Establish the objective function for optimizing hammer impact energy, comprehensively considering construction efficiency and structural safety. The expression is: ； in, To input energy for a single hammer strike, For the desired penetration rate, The maximum tensile stress in the pile body is derived based on wave theory inversion. The allowable tensile stress of the pile material. and These are the normalized weighting coefficients; S302: The total dynamic pile driving resistance described in S206 As a physical constraint, the solution makes Maximize the optimal hammering energy and limited Within the capabilities of the hydraulic hammer equipment, i.e. ; S303: Apply the optimal hammering energy The stroke height and striking frequency of the hydraulic hammer are combined to generate an electronically controlled pulse sequence, which is then output to the hydraulic servo system to execute the next hammering action.
5. The intelligent pile driving method for offshore wind power monopiles according to claim 4, characterized in that: S4 specifically includes the following steps: S401: In the After each hammer blow, record the actual penetration depth increment. With the hammering energy consumed this time ; S402: Calculate the cumulative pile driving efficiency index : ； Simultaneously calculate the end load ratio. : ； when When the value exceeds 0.7, it indicates that the pile tip has entered a high-resistivity layer, the contribution of lateral resistance is weakened, and the risk of hammer failure increases. S403: Calculate the energy penetration per unit of the three most recent hammer blows. Linear regression was used to fit its changing trend to obtain the energy utilization decay slope. The expression is: ； like A value less than 0 and an absolute value that continues to increase indicates that soil hardening or pore pressure accumulation has led to a decrease in energy conversion efficiency. S404: Will , , These are combined into a three-dimensional risk assessment vector, which serves as the quantitative basis for the warning of hammer refusal.
6. The intelligent pile driving method for offshore wind power monopiles according to claim 5, characterized in that: S5 specifically includes the following steps: S501: Setting a lower limit for pile driving efficiency index Upper limit of terminal resistance ratio and the negative threshold of the attenuation slope ; S502: When two consecutive hammering cycles satisfy... , and If this occurs, it is determined that there is a risk of the hammer being refused. S503: Initiating multi-level intervention decision-making logic: 1) If the excess pore water pressure measured by the pore water pressure sensor Exceeding the initial effective vertical stress at the current depth If the pore pressure dissipation rate reaches 60%, a pause and waiting operation will be performed. The pause duration will be dynamically determined based on the pore pressure dissipation rate, until... It has fallen back to a safe range; 2) If the pile tip is located in a sandy soil layer and the end bearing ratio is... If the value exceeds 0.75, the hammering energy for the next hammering cycle will be set to the optimal hammering energy of the previous cycle. 80% to reduce the intensity of impact disturbance; 3) If the soil around the pile is high-plasticity clay and the penetration depth increment of three consecutive hammer blows is less than 1 mm, then activate the annular high-pressure water jet device installed around the pile shoe to locally flush the pile end area with a constant flow rate to weaken the end resistance concentration effect. S504: After completing any of the above intervention measures, re-collect data on hammer force, pile top acceleration, and pore water pressure, input them into the dynamic resistance prediction process, and update the total dynamic pile driving resistance. The optimal hammering energy is recalculated based on the updated results. This generates the next hammer strike control command, achieving closed-loop control.
7. The intelligent pile driving method for offshore wind power monopiles according to claim 6, characterized in that: S6 specifically includes the following steps: S601: When the cumulative penetration depth of a single pile reaches the design depth Furthermore, the average penetration depth increment of the most recent ten hammer blows does not exceed the hammer-stopping standard. When the hammering operation is stopped; S602: The low-strain reflected wave method is used to conduct a final inspection of the pile integrity to confirm that the pile body has no fractures, necking or serious defects. S603: The entire process data from initial geological modeling, sensor deployment, dynamic resistance prediction, optimal hammer energy calculation, risk assessment to intervention execution will be encapsulated into a structured engineering sample. This sample includes timestamps, soil layer identification, original sensor signals, model update parameters, control command sequences, and final pile driving results. S604: Input the structured engineering sample described in S603 into a cross-project transfer learning network based on an attention mechanism to extract the mapping relationship between geological conditions, dynamic response, and control decisions; S605: Using the extracted mapping relationship, the initial digital twin model of the subsequent offshore wind power monopile driving project is initialized with prior parameters, and the threshold in the hammer failure risk criterion is adaptively calibrated. , and .
8. A smart pile driving system for offshore wind power monopiles, applicable to the smart pile driving method for offshore wind power monopiles as described in any one of claims 1 to 7, characterized in that: The system includes a geological digital twin modeling module, a multi-source sensor data acquisition module, a dynamic resistance prediction module, an adaptive hammering control module, a hammer rejection risk assessment module, and an intelligent intervention decision-making module. The geological digital twin modeling module is used to integrate seabed static cone penetration, multibeam bathymetry and seismic profile data, and combine single pile geometry and material parameters to construct an initial digital twin model that includes the ability to calculate side friction distribution and end resistance. The multi-source sensor data acquisition module is used to deploy impact force sensors, triaxial accelerometers, strain gauges, pore water pressure sensors and displacement monitoring devices on the piling vessel and offshore wind power monopile, and to simultaneously acquire high-frequency dynamic response signals during the hammering process. The dynamic resistance prediction module is used to reconstruct the pile-soil interface state in real time based on stress wave inversion and pore water pressure feedback, correct the soil adhesion coefficient and end bearing capacity, and output the dynamic total resistance of pile driving that takes into account soil disturbance and time-related softening. The adaptive hammering control module is used to solve for the optimal hammering energy that balances construction efficiency and structural safety, with the total dynamic pile driving resistance as a constraint, and to generate hydraulic hammer control commands that match the current pile-soil bearing capacity. The pile driving failure risk assessment module is used to calculate the pile driving efficiency index, end bearing ratio and energy utilization attenuation slope, construct a three-dimensional risk assessment vector, and quantify the pile driving failure tendency in the current pile driving process. The intelligent intervention decision module is used to automatically trigger pause and wait, energy reduction or local scour auxiliary measures when the risk assessment indicators exceed the limit, and regenerate hammering control commands based on the updated pile-soil state after intervention to achieve closed-loop intelligent control.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the intelligent pile driving method for offshore wind power monopile as described in any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the intelligent pile driving method for offshore wind power monopiles as described in any one of claims 1 to 7.