A device and method for dynamic monitoring of scour interface of offshore wind pile foundation

Abstract

The application discloses a kind of offshore wind power pile foundation scour interface dynamic monitoring device and method, and monitoring device includes inner heating temperature measurement optical cable, heating unit, optical fiber temperature measurement unit, monitoring error correction unit, thermal conductivity calculation unit and scour area detection unit;The application is monitored, and optical fiber temperature measurement unit will collect the temperature data of heating transmission to monitoring error correction unit;Monitoring error correction unit is corrected after using mixed attention neural network algorithm to realize monitoring data error, and data is transmitted to thermal conductivity calculation unit;Thermal conductivity calculation unit utilizes the thermal conductivity of each medium in the length direction of pile foundation calculated using corrected temperature data, and is transmitted to scour area detection unit;Scour area detection unit is monitored by calculating thermal conductivity gradient, and the length and state of scour area.This application's monitoring device and method make up the shortcomings of traditional monitoring means, and the precise dynamic feedback of offshore wind power pile foundation scour state is carried out.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of offshore wind power pile foundation scour monitoring, and particularly relates to a dynamic monitoring device and method for an offshore wind power pile foundation scour interface. BACKGROUND

[0002] Offshore wind power pile foundations are widely used in offshore engineering fields such as offshore platforms, wharfs, sea-crossing bridges and offshore wind power, and are one of the important engineering structural forms in offshore engineering. However, due to the fact that the seabed in the offshore area is mostly unconsolidated loose sediment such as silt, silty sand or fine sand, these special geological conditions make the seabed around the pile foundation prone to scour and erosion under the action of waves and currents. The scouring action not only weakens the bearing capacity of the soil around the pile foundation, but also can cause the pile foundation to be exposed, tilted or even unstable, which seriously threatens the long-term safety of offshore engineering facilities. Therefore, in order to ensure the safe operation of offshore engineering facilities, it is of great significance to conduct long-term and effective monitoring of the scouring conditions around the offshore wind power pile foundation.

[0003] There are various types of underwater pile foundation scour monitoring technologies, and the commonly used monitoring technologies include sonar, sliding magnetic ring, ground penetrating radar and fiber Bragg grating (FBG) sensors.

[0004] Sonar technology measures the shape and depth of the scour pit around the pile foundation by emitting sound waves and receiving their reflected waves. When sound waves encounter the interface of different densities (such as the junction of water and seabed), they will be reflected. By measuring the return time and intensity of the sound waves, detailed information about the seabed can be obtained. However, the resolution of sonar is limited by the wavelength of the sound waves. In complex marine environments, the multi-path propagation phenomenon can cause data distortion. In addition, this technology has poor real-time performance and is difficult to provide continuous scour dynamic monitoring.

[0005] The sliding magnetic ring monitoring technology is based on the principle of electromagnetic induction. By sensing the changes in the electromagnetic field in the water flow, the speed and direction of the water flow are monitored in real time, thereby indirectly inferring the movement of the soil. This method is suitable for monitoring the movement of soil during the scouring process. However, the sliding magnetic ring is very sensitive to soil type and water flow speed, which can easily lead to measurement errors. In addition, installation and maintenance are complex, and the reliability and stability of the equipment under water need to be ensured.

[0006] The working principle of ground penetrating radar is similar to that of sonar. It emits high-frequency electromagnetic waves to the seabed and uses reflected waves to obtain underground structure information. Its advantage is that it can provide high-resolution images and is suitable for various types of marine sediments. However, in seawater and saturated soil, the penetration ability of ground penetrating radar is limited, resulting in severe signal attenuation. In addition, weather and seasonal changes also affect the detection effect, leading to a decrease in the reliability of the data.

[0007] Fiber Bragg grating sensors utilize the propagation characteristics of light in optical fibers to obtain strain or temperature information along the fiber by measuring the wavelength change of the reflected light of the Bragg grating. This technology has high sensitivity and is resistant to electromagnetic interference, but its monitoring is point-based and cannot achieve distributed monitoring.

[0008] In summary, although the prior art can monitor the scouring condition of the offshore wind power pile foundation to a certain extent, it cannot achieve real-time and full-distributed monitoring. Therefore, how to achieve full-distributed real-time monitoring of the offshore wind power pile foundation has become a technical problem to be solved. SUMMARY

[0009] The present application aims to solve the technical problems in the prior art. The present application provides a device and method for dynamically monitoring the scouring interface of an offshore wind power pile foundation. The monitoring error correction unit in the present application corrects the temperature data using a hybrid attention neural network algorithm to obtain a corrected temperature change rate. The thermal conductivity calculation unit calculates the thermal conductivity of each medium in the length direction of the pile foundation based on the corrected temperature change rate. The scouring area detection unit obtains a thermal conductivity gradient curve based on the thermal conductivity and determines the scouring area based on the thermal conductivity gradient curve, while judging the scouring state of the pile foundation, thereby improving the accuracy of scouring detection.

[0010] The technical solution of the present application is as follows: The device for dynamically monitoring the scouring interface of an offshore wind power pile foundation comprises an internal heating temperature measurement optical cable, a heating unit, an optical fiber temperature measurement unit, a monitoring error correction unit, a thermal conductivity calculation unit, and a scouring area detection unit. The internal heating temperature measurement optical cable is composed of an internal heating resistance wire and a temperature sensing optical fiber. The internal heating temperature measurement optical cable is fixed on the offshore wind power pile foundation. The internal heating resistance wire is connected to the heating unit, and the temperature sensing optical fiber is connected to the optical fiber temperature measurement unit. The optical fiber temperature measurement unit collects temperature data during the heating process of the internal heating temperature measurement optical cable and transmits the data to the monitoring error correction unit.

[0011] The method for dynamically monitoring the scouring interface of an offshore wind power pile foundation comprises the following steps:

[0012] (1) After the offshore wind power pile foundation is manufactured, the internal heating temperature measurement optical cable is fixed on the offshore wind power pile foundation. After the offshore wind power pile foundation is constructed, the internal heating resistance wire in the internal heating temperature measurement optical cable is connected to the heating unit, and waterproof protection is done. The temperature sensing optical fiber in the internal heating temperature measurement optical cable is connected to the optical fiber temperature measurement unit through an optical fiber jumper;

[0013] (2) The heating unit is powered on, and the optical fiber temperature measurement unit collects temperature data of the temperature measurement optical cable during the heating time;

[0014] (3) The optical fiber temperature measurement unit transmits the temperature data to the monitoring error correction unit, which uses a hybrid attention neural network algorithm to correct the temperature data errors and obtain the corrected temperature change rate; and transmits the corrected temperature change rate to the thermal conductivity calculation unit, which calculates the thermal conductivity in the length direction of the pile foundation according to the corrected temperature change rate; the process is as follows:

[0015] (3.1) Measure and calculate the temperature change rate of medium i between heating time period t1 to t2 by the optical fiber temperature measurement unit

[0016]

[0017] Wherein, medium i includes seawater, seabed sediment and the interface of seawater and seabed sediment, T is the temperature corresponding to two time points, T i (t1) is the temperature of the linear source in medium i measured by the optical fiber temperature measurement unit at t1, T i (t2) is the temperature of the linear source in medium i measured by the optical fiber temperature measurement unit at t2.

[0018] Under laboratory conditions, the high-precision temperature measurement equipment is used to measure the accurate value of the temperature change rate of medium i in the same heating time period

[0019]

[0020] The obtained is taken as the target value of the supervised neural network; T i '(t1) is the temperature of the linear source in medium i measured in the laboratory at t1, T i '(t2) is the temperature of the linear source in medium i measured in the laboratory at t2.

[0021] Finally, the corrected temperature change rate K is obtained by using the following error correction formula:

[0022]

[0023] Wherein, is the error correction value of the temperature change rate predicted by the hybrid attention neural network.

[0024] The process of obtaining the temperature change rate error correction value of the hybrid attention neural network is as follows: the temperature change rate of each medium and the temperature change rate of the monitoring optical fiber along the line are taken as the input temperature change rate feature matrix X of the hybrid attention neural network, and the temperature change rate feature map F c:

[0025] F c =σ(W*X+b)

[0026] where W is the convolution kernel weight, b is the bias term, and σ is the activation function; X is the input temperature rate of change feature matrix of the neural network.

[0027] (3.2) The maximum pooling and average pooling operations are performed on the temperature rate of change feature map F c , to obtain the maximum pooling result F max and the average pooling result F avg :

[0028]

[0029] where c is the channel index, F c (X,c) represents the feature value on channel c after convolution and activation function processing on the input temperature rate of change feature matrix X; C is the total number of channels.

[0030] Based on the channel attention mechanism of global pooling, the weight matrix A c of the temperature rate of change feature map F c is calculated:

[0031] A c =σ(FC(GAP(F c )))

[0032] where GAP represents the average value of each channel of F c , generating a feature vector of a specific length. F C represents the weight of each channel generated by weighted learning of the feature vector through a fully connected layer.

[0033] The enhanced temperature rate of change feature map F e is obtained by dynamically adjusting each channel:

[0034] F e =A c ⊙F c

[0035] where ⊙ represents point-by-point multiplication of channels.

[0036] (3.3) The spatial attention mechanism is used to capture the correlation between different positions of the enhanced temperature rate of change feature map F e , and the process is as follows:

[0037] First, the spatial weight A s is generated by multi-scale convolution:

[0038] A sConv2D(Concat(F max , F avg )) where Concat denotes concatenating F max and F avg in the channel dimension to generate a joint temperature rate of change feature map; Conv2D denotes learning spatial attention weights from the concatenated joint temperature rate of change feature map by two-dimensional convolution to extract significant features and global distribution features.

[0039] Subsequently, the enhanced temperature rate of change feature map is optimized as F final :

[0040] F final = A s ⊙F e

[0041] Finally, the optimized temperature rate of change feature map F final is corrected by a second weighted integral to obtain the temperature rate of change error correction value K

[0042]

[0043] where W corr is a correction weight matrix, and Ω is a calculation region.

[0044] The loss function L is used to optimize the correction weight matrix Wcorr and the temperature rate of change error correction value K of the mixed attention neural network. The loss function is:

[0045]

[0046] where w i is the weight for medium i, λ is a parameter of the regularization strength, W corr is a correction weight matrix, and λ||W corr || 2 is a regularization term. The loss function L updates the correction weight matrix Wcorr at each iteration, and when the loss function L reaches a minimum value, the final corrected temperature rate of change K is output.

[0047] The thermal conductivity calculation unit calculates the medium thermal conductivity λ l at the pile foundation length l according to the corrected temperature rate of change.

[0048]

[0049] where λ lλ is the thermal conductivity coefficient at the length l, unit: W / (m·K); q is the heating power of the linear heat source, unit: W / m; K is the temperature change rate of the pile foundation length l after correction by the mixed attention neural network, unit: K.

[0050] (4) The scour area detection unit obtains the thermal conductivity coefficient gradient g in the length direction of the pile foundation according to the medium thermal conductivity coefficient l , determines the scour area according to the thermal conductivity coefficient gradient, and detects the scour state; the thermal conductivity coefficient gradient g l is:

[0051]

[0052] where λ l is the thermal conductivity coefficient at the length l, λx is the thermal conductivity coefficient at the length x adjacent to the length l, X is the distance between the two measuring points, and the value of X is L / S, where L is the total length of the monitoring section and S is the sampling resolution.

[0053] The scour area detection unit detects the position difference of the thermal conductivity coefficient gradient mutation point between the thermal conductivity coefficient gradient curve and the reference curve when the pile foundation is installed, obtains the scour area length d, and the formula is as follows:

[0054] d = L2-L1 where L2 is the mutation point position in the thermal conductivity coefficient gradient curve, and L1 is the mutation point position in the reference curve.

[0055] The scour area length d is compared with the original buried depth length D of the foundation to obtain the instability coefficient F:

[0056]

[0057] When the instability coefficient F is greater than the safety threshold f in the specification, the pile foundation scour state is unstable, and the upper structure has a risk of collapse; when the instability coefficient F is less than the safety threshold f in the specification, the pile foundation scour state is stable, and the upper structure is safe.

[0058] In step (3.3), the optimized temperature change rate feature map F final is corrected by twice weighted integration to obtain the temperature change rate error correction value

[0059] In step (3.3), the correction weight matrix Wcorr of the mixed attention neural network and the temperature change rate error correction value are optimized by using the loss function L. The loss function is:

[0060]

[0061] where w iis the weight for medium i, λ is the parameter of regularization intensity, W corr is the correction weight matrix, λ||W corr || 2 is the regularization term; the loss function L is updated for the correction weight matrix Wcorr at each iteration, and the corrected temperature rate K is output when the loss function L is minimum.

[0062] In step (1), the inner heating temperature measurement optical cable is fixed on the offshore wind pile foundation by waterproof glue.

[0063] In step (1), the optical cable needs to be protected by high-strength epoxy resin after being fixed.

[0064] In step (1), in order to ensure data quality, a section of inner heating temperature measurement optical cable is reserved at the bottom of the pile foundation.

[0065] In step (3), the heating power and heating time are set according to the design burial depth of the pile foundation and the average depth of the local seawater, and the resolution S and sampling frequency of the optical fiber temperature measurement unit when collecting data are determined according to the length of the pile foundation.

[0066] In step (4), in the monitoring error correction process, in order to improve the calculation accuracy of the temperature rate, the data based on laboratory calibration are used to train the hybrid attention neural network.

[0067] Working principle: the inner heating temperature measurement optical cable of the present application is composed of inner heating resistance wire and temperature sensing optical fiber. During the production of offshore wind pile foundation, the inner heating temperature measurement optical cable is fixed on the pile foundation, and then the tail ends of the inner heating resistance wire of the inner heating temperature measurement optical cable are welded together to form a passage. The head end of the inner heating resistance wire is connected with the heating unit. After the offshore wind pile foundation construction is completed, the inner heating temperature measurement optical cable is connected with the optical fiber temperature demodulator. The heating unit heats according to the set power for a certain time, and the optical fiber temperature demodulator collects the temperature data in this time period and transmits it to the monitoring error correction unit. The monitoring error correction unit uses the hybrid attention neural network algorithm to correct the temperature data, and obtains the corrected temperature rate. The thermal conductivity calculation unit calculates the thermal conductivity of each medium in the length direction of the pile foundation according to the corrected temperature rate. The scour area detection unit obtains the thermal conductivity gradient curve according to the thermal conductivity, and determines the scour area according to the thermal conductivity gradient curve, and judges the scour state of the pile foundation.

[0068] Advantages: compared with the prior art, the present application has the following advantages:

[0069] (1) The monitoring method adopted by the present application realizes an efficient heating process through self-heating technology. During the heating process, the heat loss is extremely low, ensuring the effectiveness of heating and reducing the influence of the external environment on the heating effect. At the same time, the present application combines the optical frequency domain reflectometry (OFDR) technology, which improves the temperature measurement accuracy to 0.01℃, further improving the measurement accuracy of the thermal conductivity coefficient and providing reliable data support for determining the scour area, thereby improving the accuracy and reliability of the scour detection.

[0070] (2) The present application adopts a hybrid attention neural network algorithm to correct the monitoring data error, further improving the accuracy of the thermal conductivity coefficient calculation. This algorithm extracts key features from monitoring data, eliminates noise and outliers, and ensures the reliability of the calculation results. The application of this technology provides strong support for accurate detection of scour areas, further ensuring the stability and practicality of the monitoring system.

[0071] (3) The monitoring method of the present application relies on optical fiber sensing technology, which has strong anti-interference ability, especially in areas with complex electromagnetic environment, and is not affected by electromagnetic interference, ensuring the stability of the monitoring data. In addition, through the application of optical fiber sensors, all-weather basic scour detection is realized, even in harsh weather conditions, the condition of offshore wind pile foundation is continuously detected. This all-weather real-time monitoring technology makes up for the shortcomings of traditional monitoring methods in real-time performance and environmental adaptability, making the scour condition of offshore wind pile foundation more accurately and dynamically feedback.

[0072] (4) The sensor used in the present application has high survival rate and can withstand harsh conditions in the marine environment, ensuring long-term stable operation. The design of the sensor enables distributed measurement along the length direction of the pile foundation, which can finely capture the scour condition of each position of the pile foundation, and is no longer limited to single-point monitoring. This distributed monitoring mode improves the comprehensiveness of the data, making it easier to understand the scour distribution around the pile foundation. The sensor is easy to install and does not require complex construction steps, making it suitable for monitoring needs of various offshore wind pile foundations. Especially after the completion of offshore wind pile foundation construction, the monitoring method of the present application can be immediately put into use for long-term monitoring of the local scour area of the pile foundation. This long-term monitoring capability not only provides continuous data support for the safety maintenance of offshore wind pile foundation, but also indirectly reduces subsequent engineering costs, with significant economic benefits. BRIEF DESCRIPTION OF DRAWINGS

[0073] Figure 1 Figure 1 is a structural schematic diagram of the offshore wind pile foundation scour interface dynamic monitoring device of the present application;

[0074] Figure 2 Figure 2 is a thermal conductivity coefficient curve in the length direction of the pile foundation in the present application;

[0075] Figure 3 This is the thermal conductivity gradient curve in this invention. Detailed Implementation

[0076] like Figure 1 As shown, the dynamic monitoring device for the scour interface of offshore wind power pile foundations of the present invention includes an internally heated temperature measuring optical cable 1, a heating unit 2, an optical fiber temperature measuring unit 3, a monitoring error correction unit 4, a thermal conductivity calculation unit 5, and a scour area detection unit 6. The internally heated temperature measuring optical cable 1 consists of two internally heated resistance wires 1-1 and one temperature sensing optical fiber 1-2.

[0077] The internally heated temperature-measuring optical cable 1 is fixed to the offshore wind turbine pile foundation. In this embodiment, the internally heated temperature-measuring optical cable 1 is pasted onto the surface of the offshore wind turbine pile foundation. The internal heating resistance wire 1-1 in the internally heated temperature-measuring optical cable 1 is connected to the heating unit 2, and the temperature sensing optical fiber 1-2 is connected to the optical fiber temperature measurement unit 3. The optical fiber temperature measurement unit 3 collects the temperature data during the heating process of the internally heated temperature-measuring optical cable 1 and transmits it to the monitoring error correction unit 4. The monitoring error correction unit 4 corrects the temperature data for errors and obtains the temperature change rate, and then transmits it to the thermal conductivity calculation unit 5. The thermal conductivity calculation unit 5 calculates the thermal conductivity of the medium along the length of the pile foundation and transmits it to the scour area detection unit 6. The scour area detection unit 6 obtains the thermal conductivity gradient curve based on the thermal conductivity, and then determines the scour area and detects the scour state.

[0078] The method for dynamic monitoring of the scour interface of offshore wind turbine pile foundations according to the present invention includes the following steps:

[0079] (1) The internal heating temperature measuring optical cable 1 is pasted and fixed on the offshore wind power pile foundation; the two internal heating resistance wires 1-1 in the internal heating temperature measuring optical cable 1 located at the tail of the pile foundation are welded together; the internal heating resistance wire 1-1 in the internal heating temperature measuring optical cable 1 located at the top of the pile foundation is connected to the heating unit 2.

[0080] (2) After the pile foundation construction is completed, the temperature sensing fiber 1-2 is connected to the fiber optic temperature measurement unit 3 through the fiber optic jumper; the heating unit 2 is powered on, and the fiber optic temperature measurement unit 3 collects the temperature data in the direction of the pile foundation length during the heating time.

[0081] (3) The temperature data collected by the fiber optic temperature measurement unit 3 is transmitted to the monitoring error correction unit 4. The monitoring error correction unit 4 uses a hybrid attention neural network algorithm to correct the temperature data and obtain the corrected temperature change rate. The thermal conductivity calculation unit 5 calculates the thermal conductivity of the medium at each location along the length of the pile foundation using the corrected temperature change rate.

[0082] (4) The scour area detection unit 6 obtains the thermal conductivity gradient in the pile foundation length direction according to the medium thermal conductivity, and determines the scour area length and the instability coefficient according to the result, and determines the scour state.

[0083] In step (1), the inner heating temperature measurement optical cable 1 is fixed on the offshore wind pile foundation by using waterproof quick-drying adhesive; secondly, the optical cable is protected by using high-strength epoxy resin.

[0084] In step (1), in order to ensure data quality, a section of inner heating temperature measurement optical cable is reserved at the bottom of the pile foundation. The inner heating resistance wire 1-1 is welded and waterproofed.

[0085] In step (2), the heating time and heating power of the heating unit 2 are set according to the design burial depth of the pile foundation and the average depth of the local seawater.

[0086] In step (2), the sampling resolution S and the acquisition frequency of the optical fiber temperature measurement unit 3 are determined according to the total length of the pile foundation.

[0087] In step (3), in the monitoring error correction process, in order to improve the calculation accuracy of the temperature change rate, the data based on laboratory calibration are used to train the mixed attention neural network:

[0088] (3.1) First, the temperature change rate of medium i between heating time period t1 and t2 is measured and calculated by the optical fiber temperature measurement unit

[0089]

[0090] Where, medium i includes seawater, seabed sediment and the interface of seawater and seabed sediment, T is the temperature corresponding to the two time points. i (t1) is the temperature corresponding to the linear source in medium i at t1 time point measured by the optical fiber temperature measurement unit 3, T i (t2) is the temperature corresponding to the linear source in medium i at t2 time point measured by the optical fiber temperature measurement unit;

[0091] Under laboratory conditions, the temperature change rate of medium i in the same heating time period is measured by using high-precision temperature measurement equipment, and the accurate value The formula is as follows:

[0092]

[0093] The obtained is taken as the target value of the supervised neural network. T i '(t1) is the temperature corresponding to the linear source in medium i at t1 time point measured in the laboratory, T i '(t2) is the temperature corresponding to the linear source in medium i at t2 time point measured in the laboratory;

[0094] Finally, the corrected rate of temperature change K is obtained using the following error correction formula:

[0095]

[0096] in, This is the error correction value for the prediction of the hybrid attention neural network.

[0097] Error correction values ​​are obtained using a hybrid attention neural network algorithm. The process is as follows: The rate of temperature change in each medium... The temperature change rate along the monitored optical fiber is used as the input temperature change rate feature matrix X of the hybrid attention neural network. The temperature change rate feature map F of the input features is extracted through a lightweight one-dimensional convolutional layer. c :

[0098] F c =σ(W*X+b)

[0099] Where W is the convolution kernel weight, b is the bias term, σ is the activation function, and X is the input temperature change rate feature matrix of the neural network.

[0100] (3.2) Subsequently, the characteristic graph of the rate of temperature change F was analyzed. c Perform channel-by-channel max pooling and average pooling operations respectively to obtain the max pooling result F. max and average pooling result F avg :

[0101]

[0102] Where c is the channel index, F c (X,c) represents the eigenvalues ​​on channel c after the input temperature change rate feature matrix X is processed by convolution and activation function, where C is the total number of channels.

[0103] Calculate the characteristic graph of temperature change rate F c Weight matrix A c :

[0104] A c =σ(FC(GAP(F) c )))

[0105] Wherein, GAP represents F c The average value of each channel is calculated to generate a feature vector of a specific length; F C This means that the feature vector is learned by weighting through a fully connected layer to generate the weights for each channel.

[0106] Dynamic adjustments were made to each channel to obtain the enhanced temperature change rate characteristic map F.e :

[0107] F e : c ⊙F c where ⊙ denotes channel-wise point multiplication.

[0108] (3.3) Capture enhanced temperature rate feature map F e The correlation between different positions is as follows:

[0109] First, generate spatial weight A s :

[0110] A s = σ(Conv2D(Concat(F max , F avg )))

[0111] where Concat denotes concatenating F max and F avg in the channel dimension to generate a joint temperature rate feature map, and Conv2D denotes learning spatial attention weights from the concatenated joint temperature rate feature map through two-dimensional convolution to extract significant features and global distribution features.

[0112] Subsequently, optimize the enhanced temperature rate feature map to F final :

[0113] F final = A s ⊙F e

[0114] Finally, correct the optimized temperature rate feature map F final by secondary weighted integral to obtain the temperature rate error correction value of medium i in the heating period

[0115]

[0116] where W is the correction weight matrix, and Ω is the calculation region.

[0117] The loss function L is used to optimize the correction weight matrix Wcorr and the temperature rate error correction value The loss function is:

[0118]

[0119] where w i is the weight for medium i, λ is the parameter of the regularization strength, W corr is the correction weight matrix, and λ||Wcorr || 2 is a regularization term; the loss function L is updated at each iteration to the corrected weight matrix Wcorr, and the output corrected temperature rate of change K when the loss function L is minimum.

[0120] In step (3), the medium thermal conductivity λ at the pile foundation length l l The following formula is used to calculate it:

[0121]

[0122] Wherein, λ l is the thermal conductivity at the pile foundation length l, the unit is W / (m·K), q is the heating power of the linear heat source, the unit is W / m, K is the mixed attention neural network corrected temperature rate of change at the pile foundation length l.

[0123] In step (4), the process of detecting the scouring area by the scouring area detection unit 6 according to the medium thermal conductivity gradient is as follows:

[0124] The present application adopts linear heat source heating method to measure the thermal conductivity of offshore wind power pile foundation length direction, because different types of media have different heat absorption capacity and different thermal conductivity, so the derivative of the thermal conductivity of the whole pile foundation length direction is obtained, and the thermal conductivity gradient is obtained. The thermal conductivity gradient will change at the junction of the seabed and the sea water. Therefore, the thermal conductivity gradient curve of the pile foundation just after installation is taken as a reference, the scouring area detection unit 6 compares the thermal conductivity gradient curve obtained in the monitoring process with the reference curve, and obtains the range of the scouring area according to the position difference of the mutation points between the two.

[0125] In step (4), the scouring area detection unit 6 calculates the thermal conductivity gradient g l of the thermal conductivity obtained in step (3) by using the following formula:

[0126]

[0127] Wherein, λ l is the thermal conductivity at the length l, λx is the thermal conductivity at the length x adjacent to the length l, X is the distance between the two measuring points, and the value of X is L / S, wherein L is the total length of the monitoring section, and S is the sampling resolution.

[0128] In step (4), the scouring area detection unit 6 detects the position difference of the thermal conductivity gradient mutation point between the thermal conductivity gradient curve and the reference curve, and obtains the scouring area length d, which is calculated by the following formula:

[0129] d=L2-L1

[0130] Wherein, L2 is the position of the mutation point in the thermal conductivity gradient curve, and L1 is the position of the mutation point in the reference curve.

[0131] The unstable coefficient F is obtained by comparing the length d of the scouring area with the length D of the original buried depth of the foundation:

[0132]

[0133] In combination with the safety threshold f in the specification, when the unstable coefficient F is greater than f, the scouring state of the pile foundation is unstable, and the upper structure has a risk of collapse; otherwise, the scouring state of the pile foundation is stable, and the upper structure is safe.

[0134] Embodiment

[0135] The scouring interface dynamic monitoring device and method for offshore wind power pile foundation of the application are used to monitor the scouring condition of a certain offshore wind power pile foundation. The offshore wind turbine has a capacity of 6MW, adopts a single pile foundation, the pile is made of steel material, the diameter of the pile foundation is 5m, the total length of the pile foundation is 50m, the buried depth of the foundation is 25m, the average water depth of the detection site is 20m, and the marine sediment type is fine sand with a particle size range of 0.063mm-0.1mm.

[0136] The scouring interface dynamic monitoring method for offshore wind power pile foundation of the application comprises the following steps:

[0137] (1) After the pile foundation is completed, two length-50m inner heating temperature measurement optical cables 1 are symmetrically pasted on both sides of the pile foundation by using waterproof quick-drying adhesive;

[0138] (2) The tail end of the inner heating temperature measurement optical cable 1 is cut open, two inner heating resistance wires 1-1 are welded together by using electric welding, and are tightly wrapped with waterproof insulating tape;

[0139] (3) After the pile foundation is completed, the inner heating resistance wire 1-1 in the inner heating temperature measurement optical cable at the top end of the pile foundation is connected with the heating unit 2, and the temperature sensing optical fiber 1-2 in the inner heating temperature measurement optical cable 1 is connected to the optical fiber temperature measurement unit 3 through an optical fiber jumper;

[0140] (4) The heating power q of the heating unit 2 is adjusted to 80W, the heating time is set to 1 minute, then power is supplied, the optical fiber temperature measurement unit 3 adopts a resolution of 1cm and a collection frequency of 10Hz to collect the temperature data in the heating time, and the data is taken as a reference;

[0141] (5) After the pile foundation is put into use, the local scouring state of the pile foundation is monitored regularly every day. The heating power of the heating unit 2 is adjusted to 80W, the heating time is set to 1 minute, then power is supplied, and the optical fiber temperature measurement unit 3 adopts a resolution of 1cm to collect the temperature data in the heating time.

[0142] (6) The temperature data collected by the optical fiber temperature measurement unit 3 is transmitted to the monitoring error correction unit 4, and the monitoring error correction unit 4 uses a hybrid attention neural network algorithm to correct the monitoring data, and obtains the temperature change rate K at each position after correction;

[0143] (4) The monitoring error correction unit 4 transmits the corrected temperature data to the thermal conductivity calculation unit 5, and the thermal conductivity calculation unit 5 calculates the medium thermal conductivity at the pile foundation length l according to the following formula (the result is as follows Figure 2 ):

[0144]

[0145] Where λ l is the thermal conductivity at the length l of the pile foundation, the unit is W / (m·K), q is the heating power of the linear heat source, the unit is W / m; K is the temperature change rate at the length l of the pile foundation after correction by the hybrid attention neural network, the unit is K;

[0146] (8) The scour area detection unit 6 calculates the thermal conductivity gradient according to the following formula (the result is as follows Figure 3 ):

[0147]

[0148] Where λ l is the thermal conductivity at the length l, λx is the thermal conductivity at the length x adjacent to the length l, and X is the distance between the two measuring points, which is L / S, where L is the total length of the monitoring section and S is the sampling resolution.

[0149] The results show that after one year of use of the pile foundation, the foundation scouring depth d is 7.5 m, and the instability coefficient F is 0.3, which has approached the instability coefficient 0.4 specified in the specification, and measures need to be taken to prevent scouring.

Claims

1. A method for dynamic monitoring of scour interface of offshore wind pile foundation, characterized in that: The application discloses a dynamic monitoring device for an erosion interface of a marine wind power pile foundation, and relates to the technical field of marine wind power pile foundation erosion interface monitoring. The method comprises the following steps: (1) fixing the inner heating temperature measuring optical cable (1) on the marine wind power pile foundation; connecting the inner heating resistance wire (1-1) to the heating unit (2) and connecting the temperature sensing optical fiber (1-2) to the optical fiber temperature measuring unit (3); (2) the heating unit (2) is powered on, and the optical fiber temperature measuring unit (3) collects the temperature data of the temperature measuring optical cable within the heating time; (3) the optical fiber temperature measuring unit (3) transmits the temperature data to the monitoring error correction unit (4), the monitoring error correction unit (4) corrects the temperature data by using a hybrid attention neural network algorithm, and transmits the corrected temperature change rate to the thermal conductivity coefficient calculation unit (5); the thermal conductivity coefficient calculation unit (5) calculates the thermal conductivity coefficient in the length direction of the pile foundation according to the corrected temperature change rate; the process is as follows: (3.1) measuring and calculating the temperature change rate of the medium i between the heating time period tl to t2 by the optical fiber temperature measuring unit (3) Wherein, the medium i includes seawater, seabed sediment and the interface of seawater and seabed sediment, T i (t1) is the temperature corresponding to the linear source in the medium i measured by the optical fiber temperature measurement unit at t1, T i (t2) is the temperature corresponding to the linear source in the medium i measured by the optical fiber temperature measurement unit at t2; The temperature change rate accurate value of the medium i in the same heating time period is measured in the laboratory The resulting as a target value for the supervised neural network; T i T'(t1) is the temperature of the line source in the medium i at the time t1, measured in the laboratory, i T'(t2) is the temperature of the line source in the medium i at the time t2, measured in the laboratory. The corrected temperature change rate K is obtained by using the following error correction formula: wherein, is a temperature rate of change error correction value predicted by the hybrid attention neural network; A temperature change rate error correction value is obtained The process is as follows: the temperature change rate The temperature change rate of each medium and the temperature change rate of the monitoring optical fiber along the line are taken as the input temperature change rate feature matrix X of the hybrid attention neural network, and the temperature change rate feature map F c : F c = σ(W * X + b) Wherein, W is the convolution kernel weight, b is the bias term, and sigma is the activation function; X is the input temperature change rate feature matrix of the neural network; (3.2) a temperature change rate feature map F c The maximum pooling and average pooling operations are performed on a channel-by-channel basis to obtain a maximum pooling result F max and an average pooling result F avg : F max = maxF c (X,c) where c is the channel index, F c (X,c) denotes the feature value on channel c after the input temperature rate of change feature matrix X is processed through convolution and an activation function; C is the total number of channels; The temperature change rate feature map F is calculated c The weight matrix A of the temperature change rate feature map F c : A c = σ(FC(GAP(F c ))) wherein GAP represents averaging each channel of F c to generate a feature vector of a specific length; F C represents generating a weight for each channel by fully connected layer learning on the feature vector. Adjusting each channel to obtain an enhanced temperature change rate feature map F e : F e = A c ☉F c Wherein, represents the point-by-point multiplication of each channel; (3.3) Capture enhanced temperature change rate feature map F using spatial attention mechanism e The correlation between different positions is as follows: Generating spatial weights A by multiscale convolution s : A s = σ(Conv2D(Concat(F max ,F avg ))) Wherein, Concat represents concatenating F max and F avg Splicing in the channel dimension generates a joint temperature change rate feature map; Conv2D represents learning spatial attention weights from the spliced joint temperature change rate feature map through two-dimensional convolution to extract significant features and global distribution features; Optimizing the temperature change rate feature map is F final : F final = A s ☉F e The optimized temperature change rate feature map F final The correction is made to obtain the temperature change rate error correction value of the medium i in the heating time period where W corr is the correction weight matrix, Ω is the calculation region; The thermal conductivity calculation unit (5) calculates the thermal conductivity λ of the medium at the pile foundation length 1 based on the corrected temperature change rate l ; Wherein, q is the heating power of the linear heat source, and the unit is W / m; K is the temperature change rate after the hybrid attention neural network correction at the length l of the pile foundation, and the unit is K; (4) The scour area detecting unit (6) obtains the thermal conductivity gradient g in the length direction of the pile foundation from the thermal conductivity of the medium l is: where λ l is the thermal conductivity at length l, λ x is the thermal conductivity at length x adjacent to length l, X is the distance between the two measurement points, X is L / S, L is the total length of the monitoring section, and S is the sampling resolution; The erosion area detection unit (6) detects the position difference of the thermal conductivity gradient mutation point between the thermal conductivity gradient curve and the reference curve when the pile foundation is installed, and obtains the erosion area length d: d = L2 - L1 Wherein, L2 is the mutation point position in the thermal conductivity gradient curve, and L1 is the mutation point position in the reference curve; The unstable coefficient F is obtained by comparing the erosion area length d with the original buried depth length D of the foundation: When the unstable coefficient F is greater than the safety threshold f, the pile foundation erosion state is unstable; when the unstable coefficient F is less than the safety threshold f, the pile foundation erosion state is stable.

2. The method according to claim 1, c h a r a c t e r i z e d i n that: In step (3.1), the temperature rate of change feature map F of the input feature is extracted by a lightweight one-dimensional convolutional layer c : F c = σ(W * X + b) Wherein, W is the convolution kernel weight, b is the bias term, and sigma is the activation function; X is the input temperature change rate feature matrix of the neural network.

3. The method according to claim 1, c h a r a c t e r i z e d i n that: In step (3.2), a temperature change rate feature map F is calculated based on a global pooling channel attention mechanism c weight matrix A c : A c = σ(FC(GAP(F c ))) where GAP represents averaging over each channel of F c to generate a feature vector of a specific length; and FC represents weighted learning of the feature vector by a fully connected layer to generate weights for each channel.

4. The method according to claim 1, c h a r a c t e r i z e d i n that: In step (3.3), the optimized temperature rate profile F final is corrected to obtain the temperature rate error correction value of the medium i in the heating period 5. The method according to claim 1, c h a r a c t e r i z e d i n that: In step (3.3), the loss function L is used to optimize the correction weight matrix W of the mixed attention neural network corr and the temperature rate of change error correction value The loss function is: where w i is the weight for medium i, λ is a parameter of the regularization intensity, W corr is the correction weight matrix, λ||W corr || 2 is the regularization term; the loss function L is updated on the correction weight matrix W corr at each iteration, and the output is the corrected temperature change rate K when the loss function L is minimized.

6. The method according to claim 1, wherein: In step (1), the inner heating temperature measuring optical cable (1) is fixed on the marine wind power pile foundation by using waterproof glue.

7. The method according to claim 1, wherein: In step (1), the inner heating temperature measuring optical cable (1) is protected by using epoxy resin after being fixed.

8. The method according to claim 1, c h a r a c t e r i z e d i n that: In step (1), the inner heating temperature measuring optical cable (1) is reserved at the bottom of the pile foundation.

9. The method according to claim 1, c h a r a c t e r i z e d i n that: In step (2), the heating time and heating power of the heating unit (2) are determined according to the design depth of the pile foundation and the average depth of seawater.

Images