Ecological bank protection system and self-repairing method and device of ecological bank protection system

Abstract

The invention provides an ecological bank protection system and a self-repairing method and device of the ecological bank protection system, and relates to the technical field of river bank revetment. The ecological bank protection system comprises a light response repairing surface layer, a piezoelectric power generation middle layer, an ecological concrete bottom layer and an edge intelligent gateway; wherein the light response repair surface layer comprises a light absorption enhancement layer, a repair agent storage layer and an interface bonding layer; the piezoelectric power generation middle layer comprises a piezoelectric ceramic piece array and is used for generating electric energy when the bank protection system is impacted by water flow or vibrates; the ecological concrete bottom layer comprises a porous ecological concrete layer pore structure; and the edge intelligent gateway is used for dynamically adjusting a repair trigger threshold by combining historical crack data and sensor data fed back by the low-power-consumption sensor network, and sending a repair instruction to the ultraviolet lamp when monitoring that the crack width is not less than the repair trigger threshold, so that the ultraviolet lamp irradiates the dynamic photoresponse material, and the dynamic photoresponse material is repaired. And releasing the repairing agent to fill the crack. The environmental adaptability of the bank protection system can be remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of river revetment, and in particular to an ecological revetment system, a self-repairing method and device of the ecological revetment system. BACKGROUND

[0002] The revetment is a key measure to protect the stability of the river bank, which can effectively prevent water and soil loss and bank collapse by reinforcing the bank slope, and protect the vegetation and biological habitat, promote soil conservation and ecological balance. At present, the related technology proposes that the three kinds of revetment structures of rigidity, flexibility and ecology can be used, but the existing revetment structure mainly uses solar cells to power the sensor, which is easy to fail in long-term rain or extreme environment, and the traditional revetment is a whole cast structure, so it is difficult to adapt to the change of terrain or local repair demand, and the environmental adaptability of different revetment environments is poor. SUMMARY

[0003] Therefore, the purpose of the present application is to provide an ecological revetment system, a self-repairing method and device of the ecological revetment system, which can significantly improve the environmental adaptability of the revetment system.

[0004] In a first aspect, the present application provides an ecological revetment system, which comprises a light response repair surface layer, a piezoelectric power generation middle layer, an ecological concrete bottom layer and an edge intelligent gateway. The light response repair surface layer comprises a light absorption enhancement layer, a repair agent storage layer and an interface bonding layer, and is used to soften the dynamic light response material when the natural light or ultraviolet light of the ultraviolet lamp irradiates. The piezoelectric power generation middle layer comprises an array of piezoelectric ceramic sheets, and is used to generate electric energy when the water flow impacts or the revetment system vibrates, so as to drive the edge intelligent gateway and the low-power sensor network. The ecological concrete bottom layer comprises a porous ecological concrete layer pore structure, which is used to set nitrifying bacteria and aquatic plant seeds in the pores for water quality purification and biological habitat treatment. The edge intelligent gateway is used to dynamically adjust the repair trigger threshold in combination with the historical crack data and the sensor data fed back by the low-power sensor network, and sends a repair instruction to the ultraviolet lamp when the crack width is not less than the repair trigger threshold, so that the ultraviolet lamp irradiates the dynamic light response material to release the repair agent to fill the cracks.

[0005] In an embodiment, the low-power sensor network comprises a structure monitoring sensor, an environment monitoring sensor and a biological monitoring sensor. The structure monitoring sensor comprises a strain sensor and a crack sensor, and is used to feed back structure data to the edge intelligent gateway. The environment monitoring sensor comprises an illumination intensity sensor, a water level and flow rate sensor and a water quality sensor, and is used to feed back environment data to the edge intelligent gateway. The biological monitoring sensor comprises a biological membrane activity sensor, and is used to feed back biological detection data to the edge intelligent gateway.

[0006] In an embodiment, the edge intelligent gateway comprises a lightweight AI model; wherein the lightweight AI model comprises a convolutional neural network and a long short-term memory network, and the lightweight AI model is configured to determine the repair trigger threshold and the repair mode according to the historical crack data and the sensor data.

[0007] In a second aspect, the embodiments of the present application also provide a self-repairing method of an ecological revetment system. The method is applied to an edge intelligent gateway of the ecological revetment system, and the method comprises the following steps: obtaining historical crack data of the ecological revetment system, structure data, environment data and biological detection data fed back by a low-power sensor network, and energy data fed back by a piezoelectric power generation middle layer, and determining input data of a unified data structure by aligning each data according to a time stamp; performing feature extraction processing on the input data to determine a model input vector, and sending the model input vector to a lightweight AI model to perform dynamic threshold prediction processing and mode selection processing, so as to determine a repair trigger threshold and a repair mode; when it is detected that a crack width collected by a crack sensor is not less than the repair trigger threshold, sending a repair instruction to an ultraviolet lamp through a low-power wide area network communication protocol, so that the ultraviolet lamp irradiates a dynamic light response material to release a repair agent to repair the crack.

[0008] In an embodiment, after the step of determining the input data of the unified data structure, the method comprises the following steps: performing denoising processing on the input data by using a sliding window average denoising method, and performing temperature drift calibration on the denoised data to determine target input data.

[0009] In an embodiment, the step of performing feature extraction processing on the input data to determine the model input vector comprises the following steps: performing feature extraction processing on a crack propagation rate, an illumination trend and a water flow impact frequency in the target input data to determine a feature vector; performing standardization processing on the feature vector by using a preset Z-Score normalization processing model and a preset maximum-minimum scaling model, performing data fusion processing on the feature vector after the standardization processing, and determining a model input vector.

[0010] In an implementation manner, the model input vector is sent to the lightweight AI model for dynamic threshold prediction processing and mode selection processing, and the steps of determining the repair triggering threshold and the repair mode include: performing dynamic threshold prediction processing on the model input vector by using a convolutional neural network and a long short-term memory network in the lightweight AI model to determine the repair triggering threshold; performing mode selection processing according to the energy storage capacity in the energy data and the water flow velocity in the environmental data, determining the repair mode as passive repair when the energy storage capacity and the water flow velocity are within a preset parameter threshold range, and starting crack repair by using natural light, and determining the repair mode as active repair when the energy storage capacity and the water flow velocity are not within the preset parameter threshold range, and starting crack repair by using an ultraviolet lamp.

[0011] In a third aspect, the embodiment of the present application further provides a self-repairing device of an ecological revetment system, the device being applied to an edge intelligent gateway of the ecological revetment system, and the device comprising: a data acquisition module, which acquires historical crack data of the ecological revetment system, structural data, environmental data and biological detection data fed back by a low-power sensor network, and energy data fed back by a piezoelectric power generation middle layer, and determines input data of a unified data structure by aligning each data according to a time stamp; a data analysis module, which performs feature extraction processing on the input data, determines a model input vector, and sends the model input vector to a lightweight AI model for dynamic threshold prediction processing and mode selection processing, to determine a repair triggering threshold and a repair mode; and a repair control module, which sends a repair instruction to an ultraviolet lamp through a low-power wide-area network communication protocol when detecting that a crack width collected by a crack sensor is not less than the repair triggering threshold, so that the ultraviolet lamp irradiates a dynamic light response material to release a repair agent for crack repair processing.

[0012] In a fourth aspect, the embodiment of the present application further provides a server, comprising a processor and a memory, the memory storing computer executable instructions capable of being executed by the processor, and the processor executes the computer executable instructions to implement the method of any one of the first aspect.

[0013] In a fifth aspect, the embodiment of the present application further provides a computer readable storage medium, the computer readable storage medium storing computer executable instructions, and the computer executable instructions, when called and executed by a processor, cause the processor to implement the method of any one of the first aspect.

[0014] The embodiment of the present application brings the following beneficial effects: The ecological revetment system, the self-repairing method and the device of the ecological revetment system provided by the embodiment of the present application, the system comprises: a light response repair surface layer, a piezoelectric power generation middle layer, an ecological concrete bottom layer and an edge intelligent gateway; wherein the light response repair surface layer comprises: a light absorption enhancement layer, a repair agent storage layer and an interface bonding layer, and the light response repair surface layer is used for softening the dynamic light response material when the ultraviolet light of the natural light or the ultraviolet lamp irradiates; the piezoelectric power generation middle layer comprises: a piezoelectric ceramic sheet array, and the piezoelectric power generation middle layer is used for generating electric energy when the water flow impacts or the revetment system vibrates, so as to drive the edge intelligent gateway and the low-power sensor network; the ecological concrete bottom layer comprises: a porous ecological concrete layer pore structure, and the nitrifying bacteria group and the aquatic plant seeds are arranged in the pores, so as to perform water quality purification and biological habitat treatment; the edge intelligent gateway is used for dynamically adjusting the repair trigger threshold in combination with the historical crack data and the sensor data fed back by the low-power sensor network, and when it is monitored that the crack width is not less than the repair trigger threshold, the edge intelligent gateway sends a repair instruction to the ultraviolet lamp, so that the ultraviolet lamp irradiates the dynamic light response material, to release the repair agent to fill the cracks, and the embodiment of the present application can make the ultraviolet light trigger the rapid release of the repair agent to fill the cracks based on the light response repair surface layer, break through the limitation of the traditional temperature and salt environment, significantly improve the repair efficiency and the environmental adaptability, and through the integration of the lightweight AI model, the multi-source data is analyzed in real time and the repair threshold is dynamically adjusted, the repair time and mode are optimized, the dependence on the cloud is reduced, and the response real-time performance and the energy efficiency ratio are improved.

[0015] Other features and advantages of the present application will be set forth in the descriptions below, and in part will become apparent to those skilled in the art upon examination of the following or can be learned by practice of the present application. The objects and other advantages of the present application can be realized and attained by the structure particularly pointed out in the description, claims and drawings.

[0016] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are described in detail as follows. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creating any inventive labor.

[0018] Figure 1 The structural schematic diagram of the self-repairing system of the ecological revetment system provided by the embodiment of the present application is provided. Figure 2 The structural schematic diagram of another self-repairing system of the ecological revetment system provided by the embodiment of the present application is provided. Figure 3 A flowchart of a self-repairing method of an ecological revetment system provided by an embodiment of the present application is shown in the figure; Figure 4 A structural diagram of a self-repairing device of an ecological revetment system provided by an embodiment of the present application is shown in the figure; Figure 5 A structural diagram of a server provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be described below in connection with the embodiments. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0020] At present, revetment is a key measure to protect the stability of river banks. It can effectively prevent water and soil loss and bank collapse, avoid damage to farmland and buildings, adjust water flow patterns, reduce flood erosion risk, and maintain river flood safety. At the same time, ecological revetment takes into account vegetation restoration and biological habitat protection, promotes soil and water conservation and ecological balance, and plays an important role in disaster prevention and reduction, protection of the lives and property of residents along the coast, and sustainable development. Related technologies are proposed. Existing revetments are mainly rigid (concrete, masonry, etc.), flexible (stone cage, ecological bag, etc.), and ecological (vegetation revetment, fish nest brick, etc.). The rigid structure has strong erosion resistance, the ecological type takes into account protection and natural restoration, and the flexible type has stability and water permeability, which adapts to different river requirements.

[0021] However, the existing revetment technology still has the following deficiencies: (1) limited self-repairing efficiency: existing microbial induced repair relies on specific environment (such as pH, temperature), and the repair effect significantly decreases in low temperature or high salinity water; (2) monitoring system relies on external power supply: existing sensor network relies on solar energy and battery, which is easy to fail in long-term rain or extreme environment; (3) single ecological function: revetment structure only focuses on protection and repair, lacking of collaborative design for water purification and biodiversity improvement; (4) poor construction flexibility: traditional revetment is casted as a whole, which is difficult to adapt to topographic changes or local repair needs. Based on this, the ecological revetment system, the self-repairing method and device of the ecological revetment system provided by the embodiments of the present application can repair the surface layer based on light response, release repair agent to fill cracks triggered by ultraviolet rays, break through the traditional temperature and salinity environment limitation, significantly improve the repair efficiency and environmental adaptability, integrate lightweight AI model to analyze multi-source data in real time and dynamically adjust the repair threshold, optimize the repair time and mode, reduce the dependence on the cloud, and improve the real-time response and energy efficiency ratio.

[0022] For the convenience of understanding the present embodiment, first, a self-repairing method of an ecological revetment system disclosed by the present embodiment is introduced in detail, which is applied to the ecological revetment system. In order to facilitate the understanding of the ecological revetment system, the present embodiment provides a structural schematic diagram of the ecological revetment system, as shown in Figure 1 The system comprises a light response repair surface layer, a piezoelectric power generation middle layer, an ecological concrete bottom layer and an edge intelligent gateway. The planar size of the modular revetment unit composed of the light response self-repairing surface layer, the piezoelectric power generation middle layer and the ecological concrete bottom layer is 1m×1m, and the thickness can be 10-20cm. In addition, referring to the structural schematic diagram of another self-repairing system of the ecological revetment system as shown in Figure 2 Each module is connected through a mortise and tenon structure. The top of the revetment unit is connected with the existing terrain by using a concrete coping. The bottom is supported and reinforced by using a concrete chamfer foundation. The modular revetment unit is embedded with a through-pore structure (pore diameter 0.1-5mm) inside. Nitrobacteria and aquatic plant seeds are embedded inside. Water quality purification and biological habitat functions are realized synchronously.

[0023] The light response repair surface layer comprises a light absorption enhancement layer, a repair agent storage layer and an interface bonding layer. The light response repair surface layer is used to soften the dynamic light response material when the natural light or the ultraviolet light of the ultraviolet lamp irradiates. The light response self-repairing surface layer takes a photosensitive polymer as a matrix, wraps repair agents (nanometer silicon dioxide and plant extraction adhesive), triggers material softening and releases repair agents under ultraviolet irradiation, and fills cracks. The material composition comprises: photosensitive polymer (polycaprolactone-PCL, 40%), nanometer silicon dioxide (particle size 20-50nm, 20%), plant extraction adhesive (such as natural polysaccharide, 20%), toughening fiber (length 1-3mm, carbon fiber, 10%), photoinitiator (benzophenone, 10%), and auxiliary agent mainly plasticizer (glycerol, 5%) for improving material flexibility. Specifically, it comprises the following (1) to (4): (1) Pretreatment and dispersion: 1. Nanometer silicon dioxide modification: ultrasonic treatment of nanometer silicon dioxide in a silane coupling agent (such as KH-550) ethanol solution for 30 minutes to improve its compatibility with the polymer matrix; 2. Plant adhesive activation: dissolve the plant extraction adhesive in deionized water (concentration 20%) and stir at 60°C until completely dissolved; 3. Carbon fiber surface treatment: oxidize the surface of carbon fiber with nitric acid to enhance the interfacial bonding force with the matrix material.

[0024] (2) Mixing and blending: 1, melt blending: PCL particles are heated to 160°C to melt, and modified nano-silica, activated plant adhesive solution, carbon fiber and benzophenone are added in turn, and constant temperature stirring (speed 200 rpm, time 30 minutes) is kept; 2, plasticizer addition: add glycerol and continue to stir for 10 minutes to ensure homogenization of the system; 3, vacuum degassing: transfer the mixed material to a vacuum reaction kettle, vacuum to-0.1 MPa to remove bubbles, and continue for 20 minutes.

[0025] (3) Molding and curing: 1, mold forming: the degassed melt is injected into a pre-made mold (thickness 1-2 mm), cooled to room temperature and solidified; 2, UV pre-activation: short-time UV irradiation (wavelength 365 nm, intensity 50 mW / cm², time 5 minutes) is performed on the formed material to initiate partial crosslinking of the photoinitiator and form a light-responsive network; 3, post-curing treatment: placed in a 50°C oven for 24 hours to eliminate internal stress and stabilize the material structure.

[0026] (4) Performance verification and optimization: 1, repair efficiency test: a 2mm crack is artificially created, and a UV lamp (intensity 200W / m²) is used to irradiate for 10 minutes to observe the crack closure rate and the formation of the silica gel network; 2, mechanical property test: the elongation at break (≥200%) and compressive strength (≥5MPa) of the material are measured by a tensile testing machine; 3, environmental adaptability verification: simulate low temperature (-20°C) and high salt (3% NaCl solution) environments to detect the release rate of the repair agent and the durability of the material.

[0027] In a real-time manner, after the crack is generated, UV irradiation softens PCL, releases nano-silica and adhesive; the adhesive swells when it comes into contact with water, and forms a silica gel network with the silica to quickly fill the crack. The thickness parameter can be determined according to the Beer-Lambert law, and the material thickness d needs to satisfy the UV transmittance T≥50%, and the calculation formula is:

[0028] wherein, is the attenuation coefficient of the photosensitive polymer, which can be taken as 0.7~0.8mm-1.

[0029] Therefore, the material thickness mm, which can generally be taken as 0.8mm.

[0030] The light response structure adopts a gradient composite structure, including a surface layer (light absorption enhancement layer), an intermediate layer (repair agent storage layer), and a bottom layer (interface bonding layer). The surface layer (light absorption enhancement layer) has a thickness of 0.1 mm, is doped with titanium dioxide nanoparticles (5 wt%) of a photosensitive polymer, improves the ultraviolet light absorption efficiency, and concentrates ultraviolet light energy on the surface layer to accelerate material softening. The intermediate layer (repair agent storage layer) has a thickness of 0.6 mm, and is doped with repair agent microcapsules (nanosilicon dioxide + plant adhesive) with a diameter of 50-100 μm, and a volume ratio of 30%. The photosensitive polymer is compounded with carbon fibers (10 wt%) as a supporting matrix to improve the crack resistance. The microcapsules are arranged in a hexagonal close-packed arrangement with a density of 1.2×104 / cm2 to ensure uniform distribution of the repair agent. The bottom layer (interface bonding layer) has a thickness of 0.1 mm and is mainly an epoxy resin adhesive layer (containing a silane coupling agent) to enhance the bonding strength with the piezoelectric power generation layer.

[0031] The ecological concrete bottom layer includes a porous ecological concrete layer pore structure for setting nitrifying bacteria and aquatic plant seeds in the pores to purify water quality and process biological habitat; The edge intelligent gateway is used to dynamically adjust the repair trigger threshold based on historical crack data and sensor data fed back by a low-power sensor network, and sends a repair instruction to the ultraviolet lamp when the crack width is not less than the repair trigger threshold, so that the ultraviolet lamp irradiates the dynamic light response material to release the repair agent to fill the cracks. The edge intelligent gateway includes a lightweight AI model. The lightweight AI model includes a convolutional neural network and a long short-term memory network. The lightweight AI model is used to determine the repair trigger threshold and the repair mode according to the historical crack data and the sensor data. The edge intelligent gateway adopts an STM32F7 series microcontroller (main frequency 216 MHz, memory ≥1 MB) integrated with a LoRaWAN communication module. One gateway is configured for every 50 revetment modules and is fixed on the top of the revetment or adjacent structures.

[0032] The low-power sensor network includes structure monitoring sensors, environment monitoring sensors, and biological monitoring sensors. The low-power sensor network can adopt ultra-low-power LoRaWAN sensors to monitor strain, cracks, water quality (COD, pH), and biological membrane activity. The structure monitoring sensors include strain sensors and crack sensors. The structure monitoring sensors are used to feed back structure data to the edge intelligent gateway. Specifically, the strain sensors are located at the four corners and the center point (a total of 5 per module) of each revetment unit to monitor unit deformation and stress distribution and identify local overload areas. The crack sensors are linearly arranged along the module joints at an interval of 20 cm (4 joints per module, with 2 arranged for each joint) to detect crack width and expansion rate in real time, and preferentially cover mortise and tenon joints.

[0033] Environmental monitoring sensors include: light intensity sensors, water level and flow rate sensors, and water quality sensors. These sensors are used to feed environmental data to the edge intelligent gateway. Specifically, the light intensity sensor, one at the top center of each module, is located in the light-responsive material area on the revetment surface. It monitors UV intensity and triggers a response in the self-healing material. Water quality sensors (COD and pH) are located at the bottom of the porous bio-carrier layer, with two sensors evenly spaced per module (near the water inlet and outlet). They assess water purification effectiveness and provide feedback on ecological restoration efficiency. Water level and flow rate sensors are located on the waterfront surface of the revetment, spaced 10 meters apart, to monitor hydrological dynamics and optimize piezoelectric power generation efficiency.

[0034] Biological monitoring sensors include: biofilm activity sensors, which are used to feed back biological detection data to the edge intelligent gateway. Specifically, the biofilm activity sensors are located in the ecological concrete layer (microorganism enrichment area), with one arranged in each module to detect the metabolic activity of nitrifying bacteria and evaluate the ecological synergistic effect.

[0035] That is to say, a single module corresponds to 17 sensors, including: structural monitoring: strain sensors (5) + crack sensors (8), a total of 13 / module; environmental monitoring: light (1) + water quality (2), a total of 3 / module; biological monitoring: biofilm activity sensor (1), 1 / module.

[0036] The piezoelectric power generation middle layer includes: a piezoelectric ceramic sheet array. The piezoelectric power generation middle layer is used to generate electricity when water impacts or the bank protection system vibrates to drive the edge intelligent gateway and low-power sensor network. Among them, the average daily power generation of a single module is ≥5Wh. The total thickness is about 3mm, including the piezoelectric sheet and the packaging layer. The packaging layer includes an upper protective layer and a lower support layer. The piezoelectric sheet uses PZT-5H ceramic sheet with a single layer thickness of 1.5~2.0 mm (taking into account both power generation efficiency and mechanical strength). Experimental verification shows that the power density of 1.0 mm thick PZT-5H reaches 0.8 mW / cm² under a water flow of 2 m / s; the upper protective layer of the packaging layer is 0.5~0.6 mm thick and is a silicone layer for waterproofing and impact resistance; the lower support layer is 1.5~2.0 mm thick and is made of glass fiber reinforced epoxy resin to improve bending stiffness.

[0037] In summary, the minimum thickness of the piezoelectric power generation layer is 8 mm. According to the power generation efficiency model, the relationship between the output power P of the piezoelectric sheet and the thickness t is:

[0038] in, is the piezoelectric constant, is the dielectric constant, f is the vibration frequency, and A is the area.

[0039] The piezoelectric sheets are arranged in a diamond grid (with a spacing of 5 mm), and a single module (1 m x 1 m) contains 400 PZT-5H sheets (with a size of 50 mm x 20 mm x 1.0 mm). The circuit connection is parallel wiring, which can reduce the impedance and improve the current output (the peak current of a single module is greater than or equal to 20 mA).

[0040] The piezoelectric layer and the light-responsive material layer are bonded by epoxy (with a peel strength greater than or equal to 30 N / cm) and connected to the ecological concrete layer.

[0041] In an embodiment, for the piezoelectric power generation energy distribution, a dual-super-capacitor parallel (single-capacitor 10 F, 5.5 V) energy storage design can be used to achieve redundant power supply (maintaining power supply capability when a single-capacitor fails). The priority of the intelligent power distribution strategy is set as the highest for the crack sensor and the gateway power supply, followed by the water quality sensor, and the dynamic adjustment can be performed according to the energy storage capacity (only power supply to the key nodes when the remaining energy is less than 20%). The dual-super-capacitor parallel energy storage maintains 70% of the power supply capability when a single-capacitor fails, and only power supply to the key sensor nodes when the remaining energy is less than 20%.

[0042] In another embodiment, a low-power mode design is also used, and the sensor sleep mechanism is switched to a sleep mode during an inactive period (such as night without light), and the power consumption is reduced to 0.1 mW. The data acquisition period is set to wake up once every 10 minutes by default, and the system is switched to real-time monitoring in an emergency state (such as crack expansion rate greater than 0.1 mm / h).

[0043] The ecological revetment system provided by the embodiment of the present application adopts a modular revetment unit, which can be quickly assembled and adapted to complex terrain, and only a single module needs to be replaced when a local damage occurs, thereby significantly reducing the construction and maintenance costs. The surface layer of the revetment is made of a light-responsive self-repairing material, which is composed of a photosensitive polymer (polycaprolactone-PCL), nano-silicon dioxide, a plant extract adhesive, and a toughening fiber. Under ultraviolet irradiation, the material is softened and releases a repair agent to complete crack filling. The piezoelectric power generation device is integrated in the system, which uses water flow fluctuation and revetment vibration to generate electricity and supply power to the low-power sensor network and edge computing gateway, thereby realizing energy self-sufficiency. The porous ecological concrete layer has a pore structure, and nitrobacteria and aquatic plant seeds are embedded therein, thereby simultaneously realizing water quality purification and biological habitat functions. The edge intelligent gateway is provided with a lightweight AI model, which dynamically adjusts the repair threshold in combination with historical data and real-time environmental parameters, thereby optimizing the repair trigger timing. The system has the advantages of strong environmental adaptability, zero external power supply, and ecological multi-functional integration, and is suitable for various water environments, especially showing excellent stability and practicality under extreme climate conditions, thereby providing an innovative solution for the field of river ecological revetment.

[0044] Based on Figure 1 Fig. 1 shows a structure schematic diagram of a self-repairing system of an ecological revetment system, andFigure 2 The structural schematic diagram of another self-repairing system of the provided ecological revetment system is shown, and the self-repairing method of the ecological revetment system is introduced in detail in the embodiment of the application, referring to Figure 3 The flowchart of the self-repairing method of the ecological revetment system is shown, and the method mainly includes the following steps S302 to S306: In step S302, the historical crack data of the ecological revetment system, the structural data, the environmental data and the biological detection data fed back by the low-power sensor network, and the energy data fed back by the piezoelectric power generation middle layer are acquired, and the input data of the unified data structure are determined by aligning each data according to the time stamp, wherein the data types include: structural data. Strain sensor (monitoring deformation), crack sensor (crack width, expansion speed). Environmental data. Illumination intensity sensor (ultraviolet intensity), water level sensor, water quality sensor (COD, pH), water flow velocity sensor. Energy data. Piezoelectric layer power generation, energy storage battery remaining power, in an embodiment, each sensor data is aligned according to the time stamp, and converted into a unified data structure:

[0045] Wherein t is the time stamp, x is the value of each sensor, is the strain, is the crack, is the illumination, is the water flow, is the voltage.

[0046] In an embodiment, the input data also needs to be denoised by adopting the sliding window average denoising method, and the target input data is determined after temperature drift calibration of the denoised data, specifically, the sliding window average denoising method is adopted, the window length N=10 (corresponding to 1s frequency, 10Hz sampling rate) is taken, the sliding step S=1, and then the denoised data is:

[0047] For example, the original data sequence of the strain sensor is , ,……, , the 10th data point data after denoising is:

[0048] Temperature drift calibration. The linear relationship between temperature T and sensor reading x is established:

[0049] Wherein the coefficients a, b are determined by calibration experiment (collecting sensor reference values at different temperatures in a constant temperature box, fitting a straight line).

[0050] Step S304, feature extraction processing is performed on the input data, the model input vector is determined, and the model input vector is sent to the lightweight AI model for dynamic threshold prediction processing and mode selection processing to determine the repair trigger threshold and the repair mode. In an embodiment, the embodiment of the present application also provides an embodiment of an automatic repair ecological revetment system. For details, see (A) to (C) below: (A) The crack propagation rate, light trend and water flow impact frequency in the target input data are subjected to feature extraction processing to determine the feature vector, and the feature vector is subjected to standardization processing using a preset Z-Score normalization processing model and a preset maximum-minimum scaling model. The standardized feature vector is subjected to data fusion processing to determine the model input vector, which specifically includes (1) to (5) as follows: (1) Crack propagation rate. The crack width is subjected to first-order difference to calculate the instantaneous propagation rate:

[0051] The exponentially weighted moving average is applied to obtain:

[0052] (2) Light intensity trend analysis. The moving average line method is used to calculate the average of the light intensity in the past 5 minutes: (Sampling interval 1s) The least squares method is used to fit a linear trend to obtain:

[0053] (3) Water flow impact frequency. The water flow velocity signal is processed using Fourier transform to extract the main frequency component as:

[0054] The frequency with the largest amplitude in the spectrum is: .

[0055] (4) Data standardization The Z-Score normalization method is used to scale each feature to a distribution with a mean of 0 and a standard deviation of 1:

[0056] wherein is the mean of the historical data; is the standard deviation.

[0057] The light intensity and other environmental parameters are subjected to maximum-minimum scaling:

[0058] (5) Data fusion and output, integrate the preprocessed data into a model input vector:

[0059] (B) Using a convolutional neural network and a long short-term memory network in a lightweight AI model, dynamic threshold prediction processing is performed on the model input vector to determine the repair trigger threshold. In an embodiment, the lightweight AI model adopts a convolutional neural network (CNN) and a long short-term memory network (LSTM) fusion architecture, and through model pruning, quantization and hardware acceleration technology, efficient inference is achieved. The input layer receives the preprocessed feature vector, , a lightweight CNN branch and a lightweight LSTM branch are constructed, specifically including the following (1) to (3): (1) Lightweight CNN branch. Depth separable convolution is used instead of standard convolution, and the computational amount can be reduced to 1 / N (N is the number of input channels).

[0060]

[0061] wherein, is the convolution size, M is the output channel number, is the feature map size.

[0062] (2) Lightweight LSTM branch The LSTM hidden layer is divided into 4 groups, each group is calculated independently, and the parameter amount is reduced.

[0063]

[0064] wherein, is the input dimension, is the hidden layer size.

[0065] (3) Branch fusion The CNN and LSTM outputs are spliced and reduced in dimension through 1x1 convolution.

[0066] In an embodiment, the CNN branch: the input feature is extracted through 3 layers of depth separable convolution (convolution kernel size 3x3, channel number 16-32-64); the LSTM branch: the input time series data is output through grouped LSTM (hidden layer size 64-16*4 groups); feature fusion: after the CNN and LSTM outputs are spliced, 1x1 convolution (channel number 128-64) is used to reduce the dimension, and the full connection layer is input.

[0067] According to the historical crack data (maximum width in 72 hours, frequency of occurrence), real-time light intensity, water flow velocity, energy storage capacity, etc., if the light intensity continues to be <200 W / m² (rainy environment), the full connection layer output dynamic threshold :

[0068] wherein, is a Sigmoid function, W, b are weights and biases, for example, the threshold is reduced from the default 0.5 mm to 0.3 mm, when the crack reaches 0.3 mm, the repair is triggered in advance.

[0069] (C) According to the energy storage capacity in the energy data and the water flow velocity in the environmental data, the mode selection process is carried out, when the energy storage capacity and the water flow velocity are within the preset parameter threshold range, it is determined that the repair mode is passive repair, and the natural light is used to start the crack repair, when the energy storage capacity and the water flow velocity are not within the preset parameter threshold range, it is determined that the repair mode is active repair, and the ultraviolet lamp is used to start the crack repair, in one real-time mode, according to the energy storage capacity E and the water flow velocity, the repair mode is selected:

[0070] Therefore, when the energy storage capacity is ≥50% and the flow velocity is ≤2 m / s, the crack repair is realized through the module "passive repair" (dependent on natural light) mode; under other conditions, the "active repair" (calling the standby power supply to start the UV lamp) is started to realize the crack repair.

[0071] Step S306, when it is detected that the crack width collected by the crack sensor is not less than the repair trigger threshold, a repair instruction is sent to the ultraviolet lamp through a low-power wide-area network communication protocol, so that the ultraviolet lamp irradiates the dynamic light response material to release the repair agent for crack repair processing, in one embodiment, when the crack width is ≥ the dynamic threshold, the gateway generates a repair instruction, which includes the following parameters: 1, repair range: according to the crack distribution to locate the damaged module number; 2, repair intensity: classified according to crack width (0.3~0.5 mm: single repair; >0.5 mm: multiple cycle repair); 3, energy distribution: if the energy storage capacity is <20%, only trigger key area repair, send instructions to the target module through the LoRaWAN protocol (i.e., low-power wide-area network communication protocol) to trigger the light response material repair or start the UV lamp auxiliary.

[0072] In addition, within 1 hour after repair, secondary monitoring is performed, the crack sensor continuously collects the closed state, the repair efficiency (closure rate = repaired width / original width x 100%) is calculated, local incremental learning: if the repair efficiency < 80%, the current environmental parameters and the repair result are taken as new samples to update the local model weight; cloud collaboration: synchronize the gateway data to the cloud every month, optimize the global model and distribute it to the edge node, if the same module triggers repair for more than 3 times within 72 hours, it is determined as a "high damage area", an alarm is pushed to the maintenance personnel, so that the maintenance personnel can view the three-dimensional damage atlas through the cloud platform, carry the portable UV lamp and replacement module to reinforce the site.

[0073] Therefore, the edge intelligent decision makes real-time collection of structural deformation, cracks, illumination and hydrological data through the lightweight AI model deployed in the revetment unit, inputs the fusion CNN and LSTM algorithm after denoising and feature extraction, dynamically analyzes the damage risk and adjusts the repair threshold (such as reducing the crack trigger threshold from 0.5mm to 0.3mm in rainy days), the decision result is distributed through the LoRaWAN protocol to trigger the light-responsive material self-repair or start the UV lamp auxiliary, and the model parameters are optimized according to the repair effect feedback. The purpose is to realize the self-perception-analysis-response closed loop of the revetment system, reduce the dependence on the cloud and communication delay, improve the real-time performance and energy efficiency ratio of repair, and adapt to the dynamic demand in complex environment, and ensure the safe and long-term operation of the revetment structure and ecological function.

[0074] In summary, the present application designs a modular mortise and tenon structure, so that the revetment unit adopts mortise and tenon connection, supports rapid assembly and local replacement, adapts to complex terrain, reduces construction and maintenance cost, and improves flexibility and material utilization rate; through the dynamic light-responsive self-repairing material, based on photosensitive polymer and nanomaterial, ultraviolet light triggers rapid release of repair agent to fill cracks, breaks through the traditional temperature-salt environment limitation, and significantly improves the repair efficiency and environmental adaptability; through the piezoelectric power generation self-power supply system, the water flow fluctuation and vibration drive the piezoelectric ceramic to generate electricity, realize the energy self-sufficiency of the sensor network, ensure the stable operation of the system in extreme climate, and do not need external power supply; through the edge intelligent dynamic decision, integrate the lightweight AI model, real-time analyze multi-source data and dynamically adjust the repair threshold, optimize the repair time and mode, reduce the dependence on the cloud, and improve the response real-time performance and energy efficiency ratio.

[0075] The above scheme of the present invention is applicable to ecological restoration projects in urban rivers, lakes and other water bodies. It is efficient, economical and environmentally friendly. Specifically, it has the following advantages: (1) Stronger environmental adaptability: The light-responsive restoration mechanism breaks through the environmental temperature and salinity limitations and is applicable to a variety of water environments; (2) No external energy supply: Piezoelectric power generation achieves energy self-sufficiency, ensuring the continuous operation of the system in extreme environments; (3) It combines ecological improvement and water purification functions. The ecological collaborative design simultaneously strengthens the bank protection, water purification and biological habitat functions; (4) Reduced construction and maintenance costs: The modular structure improves construction flexibility, reduces material waste, and partial replacement saves maintenance costs.

[0076] Regarding the self-repair method of the ecological revetment system provided in the above embodiment, the embodiment of the present invention provides a self-repair device for the ecological revetment system, see Figure 4 The structure diagram of a self-repairing device for an ecological revetment system shown in FIG. 1 includes the following parts: Data acquisition module 402 acquires historical crack data of the ecological revetment system, structural data, environmental data, and biological detection data fed back by the low-power sensor network, and energy data fed back by the piezoelectric power generation middle layer, and determines input data with a unified data structure by aligning the data by timestamp; The data analysis module 404 performs feature extraction on the input data to determine the model input vector, and sends the model input vector to the lightweight AI model for dynamic threshold prediction and mode selection to determine the repair trigger threshold and repair mode; When the repair control module 406 detects that the crack width collected by the crack sensor is not less than the repair trigger threshold, it sends a repair instruction to the ultraviolet lamp through the low-power wide area network communication protocol, causing the ultraviolet lamp to irradiate the dynamic light-responsive material to release a repair agent to repair the crack.

[0077] The self-repairing device of the ecological revetment system provided in the embodiment of the present application can significantly improve the environmental adaptability of the revetment system.

[0078] In one embodiment, after the step of determining the input data of the unified data structure, the data analysis module 404 is further used to: perform denoising on the input data by adopting a sliding window average denoising method, and perform temperature drift calibration on the denoised data to determine the target input data.

[0079] In an implementation form, when performing the step of performing feature extraction processing on the input data to determine the model input vector, the data analysis module 404 is further configured to: perform feature extraction processing on the crack propagation rate, the light trend and the water flow impact frequency in the target input data to determine a feature vector; perform standardization processing on the feature vector using a preset Z-Score normalization processing model and a preset maximum-minimum scaling model, perform data fusion processing on the feature vector after the standardization processing to determine the model input vector.

[0080] In an implementation form, when performing the step of performing dynamic threshold prediction processing and mode selection processing on the model input vector using the lightweight AI model to determine the repair trigger threshold and the repair mode, the data analysis module 404 is further configured to: perform dynamic threshold prediction processing on the model input vector using a convolutional neural network and a long short-term memory network in the lightweight AI model to determine the repair trigger threshold; perform mode selection processing according to the energy storage capacity in the energy data and the water flow speed in the environmental data, when the energy storage capacity and the water flow speed are within a preset parameter threshold range, determine that the repair mode is passive repair, and use natural light to start crack repair, when the energy storage capacity and the water flow speed are not within the preset parameter threshold range, determine that the repair mode is active repair, and use ultraviolet light to start crack repair.

[0081] The device provided by the embodiments of the present application has the same implementation principle, generated technical effects and the foregoing method embodiments. For brevity, the part not mentioned in the device embodiment part can be referred to the corresponding content in the foregoing method embodiments.

[0082] The embodiments of the present application provide a server, specifically, the server includes a processor and a storage device; the storage device stores a computer program, and the computer program performs the method of any one of the above embodiments when being run by the processor.

[0083] Figure 5 A structural diagram of a server provided by the embodiments of the present application is shown in the figure, the server 100 includes a processor 50, a memory 51, a bus 52 and a communication interface 53, the processor 50, the communication interface 53 and the memory 51 are connected through the bus 52; the processor 50 is used for executing the executable modules stored in the memory 51, such as a computer program.

[0084] The memory 51 can include a high-speed random access memory (RAM), and can also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 53 (which can be wired or wireless), and the Internet, a wide area network, a local area network, a metropolitan area network, etc. can be used.

[0085] The bus 52 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one bidirectional arrow is used in the figure to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0086] The memory 51 is used to store programs, and the processor 50 executes the programs after receiving execution instructions. The method executed by the device defined by the flow process disclosed in any of the embodiments of the present application can be applied to the processor 50 or implemented by the processor 50.

[0087] The processor 50 can be an integrated circuit chip with signal processing capability. In the implementation process, each step of the above method can be completed by the integrated logic circuit of hardware in the processor 50 or the instruction in the form of software. The processor 50 described above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. It can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware code processor for execution, or a combination of hardware and software modules in the code processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium in the art. The storage medium is located in the memory 51, and the processor 50 reads the information in the memory 51 and combines the hardware to complete the steps of the above method.

[0088] The computer program product of the readable storage medium provided by the embodiment of the present application comprises a computer readable storage medium storing program codes, and the program codes comprise instructions for executing the method described in the foregoing method embodiments. The specific implementation can be referred to the foregoing method embodiments, and will not be described here.

[0089] The function, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part of the prior art that contributes to the present application or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0090] Finally, it should be noted that: the above-described embodiments are merely specific implementations of the present application, used to illustrate the technical solutions of the present application, rather than limit them. The protection scope of the present application is not limited thereto, even though the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features thereof; and these modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An ecological revetment system, characterized in that, The system comprises a light response repair surface layer, a piezoelectric power generation middle layer, an ecological concrete bottom layer and an edge intelligent gateway; wherein The light response repair surface layer comprises a light absorption enhancement layer, a repair agent storage layer and an interface bonding layer, and is used for softening the dynamic light response material when the natural light or the ultraviolet light of the ultraviolet lamp irradiates; The piezoelectric power generation middle layer comprises a piezoelectric ceramic sheet array, and is used for generating electric energy when the water flow impacts or the revetment system vibrates, so as to drive the edge intelligent gateway and the low-power sensor network; The ecological concrete bottom layer comprises a porous ecological concrete layer pore structure, and is used for arranging nitrifying bacteria and aquatic plant seeds in the pores to purify water quality and process biological habitat; The edge intelligent gateway is used for dynamically adjusting the repair trigger threshold in combination with historical crack data and sensor data fed back by the low-power sensor network, and sends a repair instruction to the ultraviolet lamp when the crack width monitored is not less than the repair trigger threshold, so that the ultraviolet lamp irradiates the dynamic light response material to release the repair agent to fill the crack.

2. The eco-shore protection system according to claim 1, characterized in that, The low-power sensor network comprises structure monitoring sensors, environment monitoring sensors and biological monitoring sensors; wherein The structure monitoring sensors comprise strain sensors and crack sensors, and are used for feeding back structure data to the edge intelligent gateway; The environment monitoring sensors comprise illumination intensity sensors, water level and flow rate sensors and water quality sensors, and are used for feeding back environment data to the edge intelligent gateway; The biological monitoring sensors comprise biological membrane activity sensors, and are used for feeding back biological detection data to the edge intelligent gateway.

3. The eco-shore protection system of claim 1, wherein, The edge intelligent gateway comprises a lightweight AI model; wherein The lightweight AI model comprises a convolutional neural network and a long short-term memory network, and is used for determining a repair trigger threshold and a repair mode according to the historical crack data and the sensor data.

4. A method for self-repairing of an ecological revetment system, characterized in that, The method is applied to the edge intelligent gateway of the ecological revetment system, and the method comprises: Obtaining historical crack data of the ecological revetment system, structure data, environment data and biological detection data fed back by a low-power sensor network, and energy data fed back by a piezoelectric power generation middle layer, and determining input data of a unified data structure by aligning the data according to time stamps; Performing feature extraction processing on the input data, determining a model input vector, and sending the model input vector to a lightweight AI model for dynamic threshold prediction processing and mode selection processing to determine a repair trigger threshold and a repair mode; When detecting that the crack width collected by a crack sensor is not less than the repair trigger threshold, sending a repair instruction to an ultraviolet lamp through a low-power wide area network communication protocol, so that the ultraviolet lamp irradiates the dynamic light response material to release the repair agent to repair the crack.

5. The self-repair method of the ecological revetment system according to claim 4, characterized in that: After the step of determining the input data of the unified data structure, comprising: Performing denoising processing on the input data by using a sliding window average denoising method, and performing temperature drift calibration on the denoised data to determine target input data.

6. The self-repairing method of the eco-shore protection system according to claim 4, characterized in that, The step of performing feature extraction processing on the input data to determine a model input vector includes: The crack propagation rate, light trend and water flow impact frequency in the target input data are subjected to feature extraction processing to determine a feature vector; The feature vector is subjected to standardization processing using a preset Z-Score normalization processing model and a preset maximum-minimum scaling model, and the feature vector after standardization processing is subjected to data fusion processing to determine the model input vector.

7. The self-repairing method of the eco-shore protection system according to claim 4, characterized in that, The step of sending the model input vector to a lightweight AI model for dynamic threshold prediction processing and mode selection processing to determine a repair trigger threshold and a repair mode includes: The model input vector is subjected to dynamic threshold prediction processing using a convolutional neural network and a long short-term memory network in the lightweight AI model to determine a repair trigger threshold; According to the energy storage capacity in the energy data and the water flow speed in the environmental data, when the energy storage capacity and the water flow speed are within a preset parameter threshold range, the repair mode is determined to be passive repair, and the natural light is turned on for crack repair; when the energy storage capacity and the water flow speed are not within the preset parameter threshold range, the repair mode is determined to be active repair, and the ultraviolet lamp is turned on for crack repair.

8. A self-repairing device for an ecological revetment system, characterized in that The device is applied to an edge intelligent gateway of the ecological revetment system, and the device includes: A data acquisition module acquires historical crack data of the ecological revetment system, structural data, environmental data and biological detection data fed back by a low-power sensor network, and energy data fed back by a piezoelectric power generation middle layer, and determines input data of a unified data structure by aligning each data according to a time stamp; A data analysis module performs feature extraction processing on the input data to determine a model input vector, and sends the model input vector to a lightweight AI model for dynamic threshold prediction processing and mode selection processing to determine a repair trigger threshold and a repair mode; A repair control module sends a repair instruction to an ultraviolet lamp through a low-power wide-area network communication protocol when detecting that the crack width collected by a crack sensor is not less than the repair trigger threshold, so that the ultraviolet lamp irradiates a dynamic light response material to release a repair agent for crack repair processing.

9. A server, characterized by The device includes a processor and a memory, the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method of any one of claims 4 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions, and when the computer executable instructions are called and executed by the processor, the computer executable instructions cause the processor to implement the method of any one of claims 4 to 7.

Images