Calcareous sand bank slope undercutting identification method and system based on fiber bragg grating monitoring

Abstract

The invention discloses a calcareous sand bank slope undermining identification method and system based on fiber bragg grating monitoring, and the method comprises the following steps: arranging a fiber bragg grating displacement sensor at the top of a calcareous sand bank slope, and obtaining the real-time deformation parameters of the calcareous sand bank slope through the fiber bragg grating displacement sensor; replacing a modified Cambridge elastic-plastic constitutive model in an original calcareous sand cumulative deformation elastic-plastic explicit calculation model HCA with a soil state related constitutive model, and simulating calcareous sand bank slope deformation parameters under different erosion parameter combinations by adopting the improved HCA model; fitting the mapping relation between the undercut parameters and the calcareous sand bank slope deformation parameters to obtain an undercut identification model; and according to the historical deformation parameters of the calcareous sand bank slope and the corresponding undermining condition, training an undermining identification model, and inputting the real-time deformation parameters into the trained undermining identification model to obtain the real-time undermining condition of the calcareous sand bank slope.

Description

Technical Field

[0001] The present invention relates to the technical field, and particularly relates to a method and system for identifying scouring of calcareous sand slopes based on fiber Bragg grating monitoring. Background Art

[0002] Calcareous sand is widely distributed in the South China Sea and other tropical and subtropical sea areas of China, and is an important basic material for the construction of reclaimed islands and reefs. In the construction of islands and reefs, calcareous sand slopes are usually artificial slopes formed by artificial stacking on the basis of the original reef flat. Engineers build concrete revetment facilities on its upper part and place tetrapods to reduce wave erosion and maintain the stability of the island and reef land area. However, since the foot of the slope is not completely within the protection range of the concrete revetment structure, under the long-term action of marine dynamic factors such as waves and tides, the calcareous sand slope is extremely prone to scouring disasters. Scouring disasters will not only lead to a decrease in slope stability and the sliding of revetment structure facilities, threatening the safety of infrastructure on the island and reef, but may also cause serious engineering problems such as a large-scale disappearance of the land area of the reclaimed island and reef.

[0003] At present, the monitoring methods for calcareous sand slope scouring disasters mainly include direct observation method and geophysical exploration method. The direct observation method relies on manual regular on-site observation. Although it is intuitive, its efficiency is low, and real-time monitoring cannot be achieved. The geophysical exploration method, through technical means such as monitoring technologies based on the fusion of sounding data and acoustic effects, microseismic technology, multi-beam mobile monitoring technology, etc., obtains the slope topography and geological information, which can make up for the deficiencies of the direct observation method to a certain extent. However, these methods generally have problems such as high equipment cost, complex operation, limited monitoring range, etc., and cannot detect in real time all day long.

[0004] Although the existing monitoring technologies can provide slope topography and geological information to a certain extent, they still have significant limitations in practical applications. First of all, both the direct observation method and the geophysical exploration method cannot achieve real-time and continuous monitoring of scouring disasters, resulting in a lag in disaster identification. Secondly, it is difficult for the existing technologies to accurately extract effective information related to scouring disasters from a large amount of monitoring data, and the misjudgment rate is relatively high, which cannot meet the engineering requirements. These problems make the existing monitoring technologies difficult to effectively cope with the complexity and dynamics of calcareous sand slope scouring disasters. Summary of the Invention

[0005] The present invention proposes a method and system for identifying scouring of calcareous sand slopes based on fiber Bragg grating monitoring, which solves the problem that the existing technologies are difficult to effectively cope with the complexity and dynamics of calcareous sand slope scouring disasters.

[0006] To solve the above technical problems, the present invention provides a method for identifying scouring of calcareous sand slopes based on fiber Bragg grating monitoring, including the following steps: Step S1: Fiber Bragg grating displacement sensors are arranged at the top of the calcareous sand slope, and the real-time deformation parameters of the calcareous sand slope are obtained through the fiber Bragg grating displacement sensors; Step S2: Replace the modified Cam clay elastoplastic constitutive model in the original HCA model for explicit calculation of the cumulative deformation of calcareous sand, which is a constitutive model related to the state of soil, with the improved HCA model to simulate the deformation parameters of the calcareous sand slope under different combinations of erosion parameters; Step S3: Fit the mapping relationship between the erosion parameters and the deformation parameters of the calcareous sand slope to obtain an erosion identification model; Step S4: Train the erosion identification model according to the historical deformation parameters of the calcareous sand slope and the corresponding erosion conditions, and input the real-time deformation parameters into the trained erosion identification model to obtain the real-time erosion conditions of the calcareous sand slope.

[0007] Preferably, the expression of the dilatancy equation of the constitutive model related to the state of soil in Step S2 is: ; ; ; In the formula, is the dilatancy ratio; is the increment of plastic volumetric strain; Increment of plastic shear strain; and are both model parameters with positive values; is the state parameter; is the stress ratio; is the critical stress ratio; is the void ratio; is the critical void ratio; 、 and are all material constants determined by the - plane critical state line; is the average normal stress of the soil mass; is the value obtained by normalizing the atmospheric pressure.

[0008] Preferably, the deformation parameters in Step S1 include the horizontal displacement and vertical displacement of the calcareous sand slope.

[0009] Preferably, after the deformation parameters of the calcareous sand slope are monitored in real time by the fiber Bragg grating displacement sensors in Step S1, data preprocessing is performed on the monitored deformation parameters, including the following steps: Step S11: Use the exponential moving average method to remove the environmental data noise in the deformation parameters; Step S12: Set the abnormal parameter threshold according to the historical deformation parameters, and identify and remove the abnormal deformation parameters; Step S13: Use the linear interpolation method to identify and interpolate the deformation parameter data with missing values.

[0010] Preferably, the erosion parameters described in step S2 include: erosion depth and erosion area.

[0011] Preferably, when training the erosion recognition model according to the historical monitoring data and the corresponding erosion situation in step S4, the 10-fold cross-validation method is used to evaluate the accuracy of the erosion recognition model, and the parameters of the erosion recognition model are adjusted according to the evaluation results.

[0012] Preferably, after obtaining the real-time erosion situation of the calcareous sand slope in step S4, a hierarchical early warning is carried out according to the real-time erosion situation. If there is no erosion, a green signal is output and continuous monitoring is carried out; if there is slight erosion, a yellow early warning is output and the operation and maintenance personnel are notified by text message; if there is severe erosion, a red alarm is output, with audible and visual alarms and emergency response.

[0013] The present invention also provides a calcareous sand slope erosion recognition system based on fiber Bragg grating monitoring, which is implemented based on the above-mentioned calcareous sand slope erosion recognition method based on fiber Bragg grating monitoring, and includes: a fiber Bragg grating monitoring module, a data preprocessing module, a model construction module and an erosion recognition module; The fiber Bragg grating monitoring module: Through the fiber Bragg grating displacement sensor arranged on the top of the calcareous sand slope, the horizontal displacement and vertical displacement of the calcareous sand slope are collected in real time, and the optical signal is converted into a digital signal through a demodulator and transmitted to the data preprocessing module through a communication cable; The data preprocessing module: Denoise, remove outliers and interpolate the data collected by the fiber Bragg grating monitoring module; The model construction module: Based on the improved HCA model, simulate the deformation parameters of the calcareous sand slope under different combinations of erosion parameters, fit the mapping relationship between the erosion parameters and the deformation parameters, construct an erosion recognition model, and train the erosion recognition model using historical monitoring data and the corresponding erosion situation; The erosion recognition module: Input the preprocessed fiber Bragg grating deformation monitoring data into the trained erosion recognition model, and output the erosion risk level of the current calcareous sand slope.

[0014] Preferably, the system further includes an early warning module, and the early warning and visualization module: Carry out hierarchical early warning according to the erosion risk level output by the erosion recognition module. If there is no erosion, a green signal is output and continuous monitoring is carried out; if there is slight erosion, a yellow early warning is output and the operation and maintenance personnel are notified by text message; if there is severe erosion, a red alarm is output, with audible and visual alarms and emergency response.

[0015] Preferably, the system further includes a power supply and communication module, which: powers the fiber Bragg grating displacement sensor and the demodulator, and uploads data to the cloud processing center through a communication cable or a 4G / 5G module.

[0016] The advantages of the present invention at least include: 1. By arranging fiber Bragg grating displacement sensors at the top of the calcareous sand slope, the deformation parameters of the slope can be monitored in real time without manual regular measurement, improving the monitoring efficiency and the timeliness of data. Once abnormal changes in the deformation parameters are detected, the erosion situation can be quickly detected and corresponding measures can be taken in a timely manner to effectively avoid the further deterioration of the erosion problem and reduce the possible losses. 2. Using the state-dependent constitutive model of soil to replace the modified Cambridge elastoplastic constitutive model in the HCA model for the cumulative deformation elastoplastic explicit calculation of calcareous sand, the improved HCA model can more accurately reflect the mechanical behavior of the calcareous sand slope under different erosion conditions under cyclic wave loading, making the simulation results closer to the actual engineering situation and improving the accuracy of erosion identification. 3. By fitting the mapping relationship between the erosion parameters and the deformation parameters of the calcareous sand slope, an erosion identification model is obtained, providing a scientific quantitative analysis basis for erosion identification, so that erosion identification no longer depends on empirical judgment or qualitative analysis, but is an objective evaluation based on data and models, improving the accuracy and reliability of erosion identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic flow chart of the method according to an embodiment of the present invention; Figure 2 is a schematic flow chart of the real-time disaster identification technology according to an embodiment of the present invention; Figure 3 is a schematic diagram of the arrangement position of the fiber Bragg grating displacement sensor according to an embodiment of the present invention; Figure 4 is a schematic installation structure diagram of the fiber Bragg grating displacement sensor according to an embodiment of the present invention; Figure 5 is a schematic system structure diagram according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0019] Such as Figure 1 and Figure 2As shown in the figure, an erosion identification method for calcareous sand slopes based on fiber Bragg grating monitoring is provided in an embodiment of the present invention, including the following steps: Step S1: Arrange fiber Bragg grating displacement sensors at the top of the calcareous sand slope, and obtain the real-time deformation parameters of the calcareous sand slope through the fiber Bragg grating displacement sensors.

[0020] Specifically, according to the requirements of specifications such as the "Code for Building Deformation Measurement", the "Technical Standard for Inspection and Evaluation of Water Transportation Engineering Buildings JTS304-2019", and the "Design Code for Breakwaters and Revetments", an arrangement plan for monitoring points on the calcareous sand slope of the revetment as shown in Table 1 is designed, and the fiber Bragg grating displacement sensors are arranged on the top of the calcareous sand slope of a typical slope-type revetment on a certain island reef. The fiber Bragg grating displacement sensors adopted in the embodiment of the present invention are corrosion-resistant special-grade fiber Bragg gratings with a grating spacing of 50 cm.

[0021] Table 1 Arrangement plan for monitoring points on the calcareous sand slope

[0022] As Figure 3 shown, taking the geometric characteristics of a representative actual cross-section of the calcareous sand slope as an example, the horizontal distance of the fiber Bragg grating displacement sensor from the breast wall is about 1500 mm, and the burial depth is about 500 mm. During installation, first, an installation pit with an appropriate depth of about 500 mm is excavated on the surface of the slope top; take two steel bars of HPB335 Φ6 type with a length of 600 mm, and insert them into the prefabricated drill holes of a PVC pipe with an outer diameter of 50 mm, an inner diameter of 40 mm, and a wall thickness of 5 mm in turn to prevent the PVC pipe from shaking. The connection method is to use glue bonding or pipe hoop connection to form a tight connection body, and the whole is placed in the installation pit; use a fixing device to fix the two fiber Bragg grating sensors around the vertical steel bar and the horizontal steel bar respectively, and the fixing force should be moderate to avoid damaging the sensors, forming an installation structure as Figure 4 shown.

[0023] Immediately connect the fiber Bragg grating demodulator, the wired transmission module, and the photovoltaic independent power supply device, and debug the sensors to ensure that they can collect and transmit deformation data normally. Finally, connect the demodulator to the data processing center through the wired transmission module. The data processing center includes a data receiving and processing platform, and corresponding data processing software and analysis tools are installed in the data receiving and processing platform. Pair and set the communication cables in the wired transmission module to ensure that the deformation monitoring data modulated by the demodulator can be accurately transmitted to the data processing center.

[0024] After the fiber Bragg grating displacement sensor is set, the fiber Bragg grating displacement sensor collects the deformation data of the bank slope every 5 minutes at the set time interval and transmits it to the data processing center in real time through the wired transmission module. The software system of the data processing center automatically stores and classifies the received bank slope deformation data, and preprocesses the received deformation data, including: 1. Adopt a data smoothing algorithm, such as the exponential moving average algorithm EMA, to denoise the collected data, remove the noise generated by environmental interference and other factors, and improve the data stability.

[0025] 2. Set an abnormal threshold according to the historical deformation parameter data, identify and correct the abnormal data. For example, if the deformation data of a certain monitoring point shows a large mutation in a short period of time and exceeds the set abnormal threshold, then judge the data as abnormal data, and correct the abnormal data through a data interpolation algorithm.

[0026] 3. Adopt a data interpolation algorithm such as the linear interpolation method LI or the nearest neighbor interpolation method NNI to identify and interpolate the deformation parameter data containing missing values, restore the original statistical information of the data, and ensure the continuity and reliability of the data.

[0027] Use the data analysis program to extract the characteristic parameters related to the scouring disaster, such as the displacement change rate, the cumulative displacement, and the periodic displacement of the bank slope from the preprocessed deformation data. For example, by calculating the ratio of the displacement difference between adjacent time points to the time interval, the displacement change rate can be obtained, such as the displacement rate in the first hour, the displacement rate in the second hour, etc.; by accumulating the displacement changes over a period of time, the cumulative displacement can be obtained, such as the displacement in 1 hour, the displacement in 2 hours, the displacement in 6 hours, etc. Calculate the periodic displacement according to the cumulative displacement of the bank slope, such as the daily / weekly displacement.

[0028] Step S2: Replace the modified Cambridge elastoplastic constitutive model in the original High Cycle Accumulation (HCA) elastoplastic explicit calculation model of calcareous sand cumulative deformation with a soil state-related constitutive model, and use the improved HCA model to simulate the deformation parameters of the calcareous sand bank slope under different scouring parameter combinations.

[0029] Specifically, the scouring parameters include the scouring depth and the scouring area, and the deformation parameters of the calcareous sand bank slope include the horizontal displacement and the settlement at the slope top. Apply the two-dimensional finite element numerical calculation theory, based on the High Cycle Accumulation (HCA) elastoplastic explicit calculation model of calcareous sand cumulative deformation, carry out numerical simulation calculations, generate the bank slope deformation data under different wave cycle numbers, different scouring parameter combinations, and different slope height / slope length combinations, and at the same time give the scouring degree score of the bank slope, including slight scouring and severe scouring.

[0030] The improvement of the elastoplastic explicit calculation model for the cumulative deformation of calcareous sand (High Cycle Accumulation, HCA) compared with the traditional elastoplastic constitutive calculation theory mainly lies in: directly using the explicit calculation module to replace the implicit calculation on a large time scale, which greatly reduces the calculation cost and the cumulative error caused by multiple implicit calculations. At the same time, the implicit calculation module of the HCA model can comprehensively and objectively reflect the influence of various factors on the long-term cumulative deformation of the soil mass, and has the advantages of clear parameters, rich data, and high reliability. The HCA model in the embodiments of the present invention is a type of elastoplastic explicit calculation model for the cumulative deformation of sand constructed and improved based on the original HCA model. The original HCA model includes two parts: implicit and explicit calculations. In the implicit calculation part, the quasi-static elastoplastic constitutive model is used instead of the elastoplastic dynamic constitutive model for calculation. On a short time scale, the stress-strain relationship within a single control cycle is calculated implicitly using the elastoplastic constitutive model, and the state parameters such as the soil stiffness are updated by updating the change in the soil strain amplitude. The explicit calculation part includes the flow rule and a series of function formulas considering various independent influencing factors. On a long time scale, the cumulative deformation of the soil mass within a certain number of cycles is calculated by the large-step explicit integration algorithm, without calculating the stress and strain of the soil mass within a single cycle. The implicit calculation part of the original HCA model introduces the modified Cambridge elastoplastic constitutive model. Since the modified Cambridge elastoplastic constitutive model adopts the associated flow rule, it can only consider the influence of the stress ratio on the dilatancy, and cannot consider the influence of the soil void ratio and the confining pressure on the dilatancy, resulting in that the original HCA model can only consider the loading history of the stress and simulate the strain hardening of the sand, cannot directly simulate the strain softening of the sand, and cannot consider the state dependence of the sand. Therefore, in the embodiments of the present invention, the implicit calculation part of the HCA model is improved, and the state-dependent constitutive model of the soil is used to replace the modified Cambridge elastoplastic constitutive model. The expression of the dilatancy equation adopted by this elastoplastic constitutive model is: ; ; ; In the formula, is the dilatancy ratio; is the increment of plastic volumetric strain; Increment of plastic shear strain; and are both model parameters with positive values; is the state parameter; is the stress ratio; is the critical stress ratio; is the void ratio; is the critical void ratio; , and are all from - Material constants determined by the plane critical state line; is the average normal stress of the soil mass; is a value obtained by normalizing the atmospheric pressure.

[0031] It can be seen from the above formula that dilatancy occurs when contraction occurs when . The dilatancy of sand is not only related to the stress ratio but also related to and Therefore, this constitutive model is particularly suitable for simulating the mechanical response of cohesionless sands such as calcareous sand.

[0032] By replacing the modified Cam clay elastoplastic constitutive model with a state-dependent constitutive model of soil, the improved HCA model can comprehensively consider the combined effects of stress ratio, void ratio, and confining pressure on the dilatancy of calcareous sand.

[0033] Specifically, in the embodiments of the present invention, the wave loading frequency is set to 0.1 Hz, and the number of cycles is selected as 3600 times, 7200 times, 10800 times, 21600 times, 43200 times, and 86400 times respectively, corresponding to time spans of 1 hour, 2 hours, 3 hours, 6 hours, 12 hours, and 24 hours. The scouring condition is realized by deleting the grid elements at the toe of the finite element slope numerical model. Through the above numerical simulation calculations, based on the HCA numerical calculation model, the slope deformation data when scouring occurs is obtained.

[0034] Similarly, applying the two-dimensional finite element numerical calculation theory and carrying out numerical simulation calculations based on the HCA model, the slope deformation data when scouring does not occur can be obtained.

[0035] Based on the slope deformation data when scouring does not occur, the slope deformation data when scouring occurs, and the corresponding scouring parameters, a numerical database of calcareous sand slope scouring disasters as shown in Table 2 is constructed, where the scouring degree score includes no scouring, slight scouring, and severe scouring.

[0036] Table 2 Numerical database of calcareous sand slope scouring disasters

[0037] Step S3: Fit the mapping relationship between the scouring parameters and the calcareous sand slope deformation parameters to obtain a scouring identification model.

[0038] Specifically, machine learning algorithms with excellent non-linear learning performance, such as Support Vector Machine (SVM), Neural Network, Random Forest, Gradient Boosting Decision Tree, etc., are adopted. Using the numerical database of calcareous sand slope erosion disasters as the training set, the deformation parameters of the calcareous sand slope in the training set are used as inputs, and the corresponding occurrence of erosion disasters is used as the output to train the model, fitting the mapping relationship between the slope deformation parameters and the erosion parameters, and constructing an erosion recognition model for calcareous sand slopes. During the training process, the optimal parameters of the erosion recognition model are obtained through 10-fold cross-validation. The adjustable parameters of the support vector machine are the penalty parameter c and the kernel function parameter; the adjustable parameters of the neural network are the learning rate, the number and layers of neurons in the hidden layer, etc.; the adjustable parameters of the random forest are the number of decision trees, the maximum depth, and the minimum number of samples for splitting, etc.; the adjustable parameters of the gradient boosting tree are the learning rate, the number of decision trees, the maximum depth, and the subsampling ratio.

[0039] Step S4: Train the erosion recognition model based on the historical deformation parameters of the calcareous sand slope and the corresponding erosion conditions, and input the real-time deformation parameters into the trained erosion recognition model to obtain the real-time erosion conditions of the calcareous sand slope.

[0040] Specifically, use the test set to evaluate the trained model and calculate evaluation indicators such as the accuracy rate and recall rate of the model. If the performance of the model does not meet the expected requirements, further adjust the model parameters or increase the training data, and retrain and evaluate until the performance of the model meets the requirements.

[0041] At the same time, collect the historical deformation monitoring data of the calcareous sand slopes in this area in the past 5 years and the corresponding records of the occurrence of erosion disasters to form a database of actual erosion cases of calcareous sand slopes, realizing the supplementation of the numerical database of calcareous sand slope erosion disasters and the calibration of the parameters of the erosion recognition model for calcareous sand slopes, further optimizing the performance of the erosion recognition model for calcareous sand slopes, and improving the recognition accuracy rate of the erosion recognition model.

[0042] Combining the numerical database of calcareous sand slope erosion disasters, the database of actual erosion cases of calcareous sand slopes, relevant specifications, and the investigation results of calcareous sand slope erosion disasters, three levels of erosion disaster warning levels are set. The no-erosion-risk warning is set as a green signal warning, the slight erosion disaster warning is set as a yellow signal warning, the severe erosion disaster warning is set as a red signal warning, and the corresponding three-dimensional disposal methods.

[0043] The deformation monitoring data of the calcareous sand slope collected in real time is transmitted to the data processing center for data processing to obtain deformation parameters. The deformation parameters are input into the erosion identification model, and the erosion identification model quickly determines whether there is a risk of erosion disaster in the current calcareous sand slope according to the deformation parameters. In the embodiment of the present invention, the erosion disaster label of no erosion is set to 0, the erosion disaster label of slight erosion is set to 1, and the erosion disaster label of severe erosion is set to 2. If the predicted erosion disaster label of the model is 0, it is determined that the current calcareous sand slope is operating safely; if the predicted erosion disaster label of the model is 1, it is determined that there is a risk of slight erosion disaster in the current calcareous sand slope; if the predicted erosion disaster label of the model is 2, it is determined that there is a risk of severe erosion disaster in the current calcareous sand slope.

[0044] Based on the prediction results of slight erosion and severe erosion, the system will send warning messages to the staff of the coastal zone management department through the SMS platform according to the pre-set warning levels, and at the same time send out audible and visual alarm signals on the monitoring interface of the data processing center to remind relevant personnel to take corresponding measures in time.

[0045] As Figure 5 shown, the embodiment of the present invention also provides a calcareous sand slope erosion identification system based on fiber Bragg grating monitoring, which is implemented based on the above-mentioned calcareous sand slope erosion identification method based on fiber Bragg grating monitoring, and includes: a fiber Bragg grating monitoring module, a data preprocessing module, a model construction module, an erosion identification module, a warning module, and a power supply and communication module.

[0046] Fiber Bragg grating monitoring module: The horizontal displacement and vertical displacement of the calcareous sand slope are collected in real time through the fiber Bragg grating displacement sensor arranged on the top of the calcareous sand slope, and the optical signal is converted into a digital signal through a demodulator and transmitted to the data preprocessing module through a communication cable.

[0047] Data preprocessing module: Denoise, remove outliers and interpolate the data collected by the fiber Bragg grating monitoring module.

[0048] Model construction module: Based on the improved HCA model, simulate the deformation parameters of the calcareous sand slope under different erosion parameter combinations, fit the mapping relationship between the erosion parameters and the deformation parameters, construct an erosion identification model, and train the erosion identification model using historical monitoring data and corresponding erosion conditions.

[0049] Erosion identification module: Input the preprocessed fiber Bragg grating data into the trained erosion identification model, and output the erosion risk level of the current calcareous sand slope.

[0050] Early warning and visualization module: Conduct hierarchical early warning based on the erosion risk level output by the erosion identification module. If there is no erosion, output a green signal and continue monitoring; if there is slight erosion, output a yellow early warning and notify the operation and maintenance personnel via SMS; if there is severe erosion, output a red alarm, with audible and visual alarms and emergency response.

[0051] Power supply and communication module: Supply power to the fiber Bragg grating displacement sensor and demodulator, and upload data to the cloud processing center through communication cables or 4G / 5G modules.

[0052] A method and system for identifying erosion of calcareous sand slopes based on fiber Bragg grating monitoring disclosed in an embodiment of the present invention can collect and process deformation monitoring data in real time through a data processing center and a fiber Bragg grating demodulator, can timely detect abnormal changes in the deformation of calcareous sand slopes, identify the early warning level of erosion disaster risk for the first time, and realize real-time monitoring and early warning of disasters.

[0053] Based on the numerical database of calcareous sand slope erosion disasters and the monitoring data of accurate fiber Bragg grating displacement sensors, an advanced data processing algorithm is used to obtain an erosion identification model trained with a large amount of data. This model can accurately extract feature information related to erosion disasters from deformation monitoring data, effectively reducing the false judgment rate and missed judgment rate of disaster identification.

[0054] At the same time, compared with the traditional geophysical exploration method, the technical solution of the present invention mainly relies on sensors such as fiber Bragg gratings and data processing algorithms, with low equipment cost, simple operation, and can realize large-area slope monitoring, having high cost-effectiveness. It is applicable to calcareous sand slopes under different geological conditions and marine environments, with strong versatility and adaptability.

[0055] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. Only the preferred embodiments of the present invention are expressed. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the present invention. As long as the combination of these technical features does not conflict, it should be considered as the scope described in this specification.

[0056] It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the appended claims.

Claims

1. A method for identifying calcareous sand bank erosion based on fiber Bragg grating monitoring, characterized in that: The following steps are involved: Step S1: arranging a fiber Bragg grating displacement sensor on the top of the calcareous sand bank slope, and obtaining real-time deformation parameters of the calcareous sand bank slope through the fiber Bragg grating displacement sensor; Step S2: using the state-dependent constitutive model of soil to replace the modified Cambridge elastoplastic constitutive model in the original calcareous sand cumulative deformation elastoplastic explicit calculation model HCA, and using the improved HCA model to simulate the deformation parameters of the calcareous sand bank slope under different erosion parameter combinations; Step S3: fitting the mapping relationship between the erosion parameters and the deformation parameters of the calcareous sand bank slope to obtain an erosion identification model; Step S4: training an erosion recognition model according to historical deformation parameters of the calcareous sand bank slope and corresponding erosion conditions, inputting the real-time deformation parameters into the trained erosion recognition model to obtain the real-time erosion conditions of the calcareous sand bank slope.

2. The method for identifying calcareous sand bank erosion based on fiber Bragg grating monitoring according to claim 1 is characterized by: The expression of the dilatancy equation of the state-dependent constitutive model of the soil in step S2 is: ； ； ； In the formula, is the dilatancy ratio; is the plastic volume strain increment; Plastic shear strain increment; , is a model parameter with a positive value; is the state parameter; is the stress ratio; is the critical stress ratio; is the void ratio; is the critical porosity ratio; , and All by - Material constants determined by the plane critical state line; is the average normal stress of soil; It is the value after normalization of atmospheric pressure.

3. The method for identifying calcareous sand bank erosion based on fiber Bragg grating monitoring according to claim 1 is characterized by: The deformation parameters in step S1 include horizontal displacement and vertical displacement of the calcareous sand bank slope.

4. The method for identifying calcareous sand bank erosion based on fiber Bragg grating monitoring according to claim 1 is characterized by: After the real-time deformation parameters of the calcareous sand bank slope are obtained by the fiber Bragg grating displacement sensor in step S1, the real-time deformation parameters are preprocessed, including the following steps: Step S11: using the exponential moving average method to remove environmental noise information in the deformation parameters; Step S12: setting an abnormal threshold according to historical deformation parameters, and identifying and removing abnormal deformation parameters; Step S13: using linear interpolation to identify and interpolate deformation parameter data containing missing values.

5. The method for identifying calcareous sand bank erosion based on fiber Bragg grating monitoring according to claim 1 is characterized by: The etching parameters in step S2 include: etching depth and etching area.

6. The method for identifying calcareous sand bank erosion based on fiber Bragg grating monitoring according to claim 1 is characterized by: In step S4, when the erosion recognition model is trained according to the historical monitoring data and the corresponding erosion conditions, a 10-fold cross validation method is used to evaluate the accuracy of the erosion recognition model, and the parameters of the erosion recognition model are adjusted according to the evaluation results.

7. The method for identifying calcareous sand bank erosion based on fiber Bragg grating monitoring according to claim 1 is characterized by: After obtaining the real-time erosion situation of the calcareous sand bank slope in step S4, a graded warning is issued according to the real-time erosion situation. If there is no erosion, a green warning is output and monitoring continues; if there is slight erosion, a yellow warning is output and the operation and maintenance personnel are notified by SMS; if there is severe erosion, a red alarm is output, an audible and visual alarm is issued, and an emergency response is carried out.

8. A system for identifying calcareous sand bank erosion based on fiber Bragg grating monitoring, which is implemented based on a method for identifying calcareous sand bank erosion based on fiber Bragg grating monitoring as claimed in any one of claims 1 to 7, characterized in that: include: Fiber Bragg grating monitoring module, data preprocessing module, model building module and erosion identification module, early warning and visualization module, power supply and communication module; The fiber grating monitoring module: through the fiber grating displacement sensor arranged on the top of the calcareous sand bank slope, the horizontal displacement and vertical displacement of the calcareous sand bank slope are collected in real time, the optical signal is converted into a digital signal through a demodulator, and transmitted to the data preprocessing module through a communication cable; The data preprocessing module is used to perform denoising, outlier removal and data interpolation processing on the data collected by the fiber grating monitoring module; The model building module simulates the deformation parameters of the calcareous sand bank slope under different erosion parameter combinations based on the improved HCA model, fits the mapping relationship between the erosion parameters and the deformation parameters, builds an erosion recognition model, and trains the erosion recognition model using historical monitoring data and corresponding erosion conditions; The erosion identification module inputs the pre-processed fiber Bragg grating data into a trained erosion identification model, and outputs the erosion risk level of the current calcareous sand bank slope.

9. The calcareous sand bank erosion identification system based on fiber Bragg grating monitoring according to claim 8 is characterized by: The system also includes an early warning module, and the early warning and visualization module performs graded early warning according to the erosion risk level output by the erosion identification module. If there is no erosion, a green signal is output and monitoring continues; if there is slight erosion, a yellow warning is output and an SMS message is notified to the operation and maintenance personnel; if there is severe erosion, a red alarm is output, an audible and visual alarm is issued, and an emergency response is carried out.

10. The calcareous sand bank slope erosion identification system based on fiber Bragg grating monitoring according to claim 8, characterized in that: The system also includes a power supply and communication module, which supplies power to the fiber grating demodulator and uploads data to a cloud processing center via a communication cable or a 4G / 5G module.

Images