Methods, devices, equipment, and storage media for monitoring the corrosion rate of steel pipe piles at wharves.

Abstract

This application provides a method, apparatus, equipment, and storage medium for monitoring the corrosion rate of steel pipe piles at wharves. The method first collects and preprocesses environmental data and steel pipe pile thickness data for the target area to obtain average environmental physicochemical parameters and average steel pipe pile thickness. Then, it calculates the risk index and corrosion rate based on these parameters. Finally, it dynamically updates the model in a digital twin model according to the risk index, performing routine updates for low or medium risk scenarios and emergency updates for high risk scenarios. This application achieves real-time perception and accurate early warning of corrosion status by combining real-time data acquisition and processing, calculation of the risk index and corrosion rate, and dynamic updates of the digital twin model, thereby improving monitoring efficiency and accuracy.

Description

Technical Field

[0001] This application belongs to the field of steel pipe pile monitoring, and particularly relates to a method, device, equipment and storage medium for monitoring the corrosion rate of wharf steel pipe piles. Background Technology

[0002] As a crucial hub for maritime transport and logistics, the safety and stability of a wharf's infrastructure directly impacts the efficiency and safety of its overall operations. Steel pipe piles, as the core load-bearing components of the wharf structure, are constantly exposed to the complex and harsh marine environment, enduring the combined effects of high salinity, high humidity, alternating wet and dry conditions, and wave erosion. These environmental factors work together to expose steel pipe piles to a continuous and severe threat of corrosion. The impact of corrosion on steel pipe piles cannot be ignored. As corrosion progresses, the thickness of the steel pipe piles gradually decreases, significantly reducing their structural strength. This not only reduces the load-bearing capacity of the piles but can also lead to major safety accidents such as pile fracture and wharf collapse, causing incalculable losses to personnel, property, and the environment. Therefore, accurate monitoring and risk warning of the corrosion status of steel pipe piles have become a key link in ensuring the safe and stable operation of the wharf.

[0003] However, traditional methods for monitoring corrosion of steel pipe piles have many limitations. Currently, manual inspection is one of the main monitoring methods, but this method heavily relies on divers operating underwater. It is not only greatly constrained by natural factors such as tides and weather, but also has limited effective working time each day, resulting in low inspection frequency and limited coverage. Furthermore, data collected through manual inspection often exhibits discrete characteristics, making it difficult to form continuous monitoring records, thus failing to comprehensively and accurately reflect the corrosion status of the steel pipe piles. On the other hand, while electrochemical monitoring technology, as an important means of assessing the corrosion resistance of steel pipe piles, can provide some corrosion information, it is still generally conducted periodically by hand using a multimeter.

[0004] This approach is not only inefficient and has long data acquisition intervals, but also struggles to maintain stable circuit connectivity in special areas such as splash zones and tidal zones due to the alternating wet and dry conditions. This makes traditional electrochemical methods unsuitable and creates significant monitoring blind spots. More critically, existing monitoring systems generally suffer from data silos, meaning environmental parameters and equipment status data are collected separately, lacking an effective fusion and analysis mechanism. This makes it difficult for managers to extract valuable information from massive amounts of data for accurate corrosion status assessment and risk warning. Furthermore, existing monitoring methods primarily output discrete numerical values ​​or text reports, lacking dynamic displays and intuitive presentations, making it difficult for managers to quickly locate high-risk areas and take timely and effective maintenance measures. Summary of the Invention

[0005] The purpose of this application is to overcome the deficiencies in the prior art and provide a method, device, equipment and storage medium for monitoring the corrosion rate of wharf steel pipe piles.

[0006] This application also provides a method for monitoring the corrosion rate of steel pipe piles at wharves, including:

[0007] Collect environmental data and steel pipe pile thickness data for the target wharf steel pipe pile inspection sub-area;

[0008] The environmental data and steel pipe pile thickness data are preprocessed to obtain the average environmental physicochemical parameters and the average steel pipe pile thickness.

[0009] The risk index is calculated based on the average physicochemical parameters of the environment.

[0010] The corrosion rate was calculated based on the average steel pipe pile thickness and the initial thickness.

[0011] In the digital twin model, the model is dynamically updated according to the risk index, including: when the risk index indicates low risk or medium risk, a regular update is performed to update the model thickness and corrosion rate at a preset frequency; when the risk index indicates high risk, an emergency update is triggered to update the model thickness of the corresponding high-risk area in the digital twin model, wherein the high-risk area is determined based on the risk index reaching a preset threshold.

[0012] Optionally, the preprocessing of the environmental data and the steel pipe pile thickness data includes:

[0013] Identify abnormal environmental data, wherein the abnormal environmental data meets any of the following conditions:

[0014] If the pH value fluctuates beyond the acid-base fluctuation threshold within a continuous preset number of sampling periods, or the temperature fluctuates beyond the temperature change threshold for a short period of time.

[0015] The thickness data deviates from the initial thickness value by more than the proportional tolerance threshold.

[0016] When abnormal environmental data is identified, the abnormal data point is replaced with the moving average of adjacent valid period data.

[0017] Optionally, the calculation of the risk index based on the average environmental physicochemical parameters includes:

[0018] Four sub-parameters—salinity, pH, temperature, and dissolved oxygen—are extracted from the average physicochemical parameters of the environment.

[0019] Each of the sub-parameters is mapped to a standardized contribution value using an independent nonlinear transformation function;

[0020] The standardized contribution values ​​are weighted and fused, wherein the weight coefficient of the salinity sub-parameter is higher than that of other sub-parameters;

[0021] The discrete risk level signal is output based on the weighted fusion result.

[0022] Optionally, triggering an emergency update when the risk index indicates a high risk includes:

[0023] The spatial coordinate clusters for locating high-risk areas in the digital twin model;

[0024] Perform multi-level resolution enhancement operations on the high-risk area based on the spatial coordinate cluster;

[0025] In the three-dimensional view of the digital twin model, a dynamic color-changing warning boundary layer is generated based on the display effect after the enhancement operation.

[0026] Optionally, after triggering the emergency update, the process further includes:

[0027] The time interval for collecting the environmental data and the steel pipe pile thickness data is adjusted to a first cycle value, which is less than the original time interval.

[0028] The monitoring data of the high-risk area is obtained based on the first periodic value;

[0029] The risk index is updated based on the monitoring data.

[0030] When the risk index remains below the downgrade threshold: restore the data collection time interval to the original time interval; update the dynamic warning sign of the high-risk area in the digital twin model.

[0031] Optionally, the model thickness corresponding to the high-risk area in the updated digital twin model includes:

[0032] Monitor the magnitude of changes in the risk index, and increase the update frequency of the digital twin model when the magnitude of changes exceeds a preset sensitivity threshold;

[0033] The spatiotemporal evolution trajectory of the steel pipe pile thickness is recorded synchronously each time the digital twin model is updated;

[0034] Corrosion acceleration is calculated based on the recorded spatiotemporal evolution trajectory. When the corrosion acceleration exceeds a critical threshold, an embedded hardening scheme instruction is generated and the visual marker status of high-risk areas in the digital twin model is updated.

[0035] Optionally, it also includes:

[0036] The corrosion rate is converted into the thickness variation rate parameter of the steel pipe pile in the digital twin model;

[0037] Predict the remaining lifespan of the structure based on the thickness change rate parameter;

[0038] When the remaining lifespan of the structure is less than the maintenance safety threshold, a forced update of the digital twin model is triggered;

[0039] Based on the deviation rate between the measured corrosion rate and the predicted value after forced update, the prediction algorithm parameters are dynamically calibrated.

[0040] This application also provides a device for monitoring the corrosion rate of steel pipe piles at wharves, comprising:

[0041] The data acquisition module collects environmental data and steel pipe pile thickness data for the target wharf steel pipe pile inspection sub-area;

[0042] The preprocessing module preprocesses the environmental data and steel pipe pile thickness data to obtain the average environmental physicochemical parameters and the average steel pipe pile thickness.

[0043] The index module calculates the risk index based on the average physicochemical parameters of the environment;

[0044] The corrosion module calculates the corrosion rate based on the average steel pipe pile thickness and the initial thickness.

[0045] The update module dynamically updates the model in the digital twin model according to the risk index, including: when the risk index indicates low or medium risk, performing a regular update to update the model thickness and corrosion rate at a preset frequency; when the risk index indicates high risk, triggering an emergency update to update the model thickness of the corresponding high-risk area in the digital twin model, wherein the high-risk area is determined based on the risk index reaching a preset threshold.

[0046] This application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0047] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the above-described method.

[0048] The beneficial effects of this application are:

[0049] This application also provides a method for monitoring the corrosion rate of steel pipe piles at wharf sites, comprising: collecting environmental data and steel pipe pile thickness data of a target wharf steel pipe pile detection sub-area; preprocessing the environmental data and steel pipe pile thickness data to obtain average environmental physicochemical parameters and average steel pipe pile thickness; calculating a risk index based on the average environmental physicochemical parameters; calculating the corrosion rate based on the average steel pipe pile thickness and initial thickness; and dynamically updating the model in a digital twin model according to the risk index, including: performing a regular update when the risk index indicates low or medium risk, updating the model thickness and corrosion rate at a preset frequency; and triggering an emergency update when the risk index indicates high risk, updating the model thickness of the corresponding high-risk area in the digital twin model, wherein the high-risk area is determined based on the risk index reaching a preset threshold. This application, through real-time data acquisition and processing, risk index and corrosion rate calculation, and combined with dynamic updating of the digital twin model, achieves real-time perception and accurate early warning of corrosion status, improving monitoring efficiency and accuracy. Attached Figure Description

[0050] Figure 1 This is a schematic diagram of the corrosion rate monitoring process for wharf steel pipe piles in this application;

[0051] Figure 2 This is a schematic diagram of the corrosion rate monitoring system for steel pipe piles at the wharf in this application;

[0052] Figure 3 This is a schematic diagram of the data preprocessing process in this application. Detailed Implementation

[0053] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it is to be understood that various forms of implementation of the present disclosure are intended and should not be limited to the embodiments set forth herein. Rather, the embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0054] Please refer to Figures 1-3 As shown, this application provides a method for monitoring the corrosion rate of steel pipe piles at wharves. This method achieves closed-loop monitoring through steps such as data acquisition, preprocessing, risk calculation, corrosion rate calculation, and model updating.

[0055] S101. Collect environmental data and steel pipe pile thickness data for the target wharf steel pipe pile detection sub-area;

[0056] This application involves collecting environmental data and steel pipe pile thickness data for the target wharf steel pipe pile testing sub-area.

[0057] The target wharf steel pipe pile inspection sub-area is a one-meter-circular area centered on the target wharf steel pipe piles. Environmental data includes the measured electrical conductivity, pH value, temperature, and dissolved oxygen content of seawater within the target wharf steel pipe pile inspection area. The steel pipe pile thickness data is obtained by measuring the thickness at multiple points on each steel pipe pile using an ultrasonic thickness gauge.

[0058] Environmental data acquisition involves using conductivity sensors deployed around the steel pipe piles to collect the conductivity of the surrounding seawater to obtain measured conductivity values, using glass electrode sensors deployed around the steel pipe piles to collect the pH values ​​of the surrounding seawater to obtain measured pH values, using platinum resistance temperature sensors deployed around the steel pipe piles to collect the temperature of the surrounding seawater to obtain measured temperature, and using electrochemical dissolved oxygen sensors deployed around the steel pipe piles to collect the dissolved oxygen content of the surrounding seawater to obtain measured dissolved oxygen content.

[0059] The optional conductivity sensor is the LianCe TDS-8002 large-range digital electrode, with a measurement range of 0.1 ms / cm to 500 ms / cm; the optional glass electrode sensor is the Miko Sensing MIK-PH-5013A, with a measurement range of 0-14 pH; the optional platinum resistance temperature sensor is the HuaKong XingYe HSTL-WZP, with a measurement range of -50 to 200℃; and the optional electrochemical dissolved oxygen sensor is the Miko Sensing intelligent digital electrode. The optional ultrasonic thickness gauge is the SMART-SENSOR AS860, with a measurement range of 1.0-300 mm.

[0060] There are three electrical conductivity sensors, glass electrode sensors, platinum resistance temperature sensors, and electrochemical dissolved oxygen sensors around each steel pipe pile, distributed at different depths of the steel pipe pile, 1m, 5m, and 10m from the sea surface, respectively; the system is preset to collect data once every 6 hours, triggering the sensors to collect data synchronously.

[0061] The sensor housing at 1m above the sea surface is made of PVDF UV-resistant material, with a 1.5m redundant cable length to handle minor swaying of the pile due to wave impact. The sensor at 10m above the sea surface requires an additional 5cm diameter stainless steel anti-collision mesh. The sensor surfaces are coated with anti-fouling paint and cleaned regularly every 3 months using an underwater robot, especially the probes of the dissolved oxygen and conductivity sensors, which must be kept clean to prevent shellfish and algae from affecting measurement accuracy. Conductivity, pH, temperature, and dissolved oxygen levels collected by each sensor are transmitted to the temporary storage unit of the data preprocessing module via a waterproof cable, along with a sensor number used to distinguish different depth locations. The thickness of the steel pipe pile collected by the ultrasonic thickness gauge is transmitted to the temporary storage unit of the data preprocessing module via a waterproof cable, along with a data acquisition timestamp accurate to the second and the sensor number, which is also used to distinguish different depth locations.

[0062] S102. Preprocess the environmental data and steel pipe pile thickness data to obtain the average environmental physicochemical parameters and the average steel pipe pile thickness.

[0063] This application relates to preprocessing environmental data and steel pipe pile thickness data to obtain average environmental physicochemical parameters and average steel pipe pile thickness. The preprocessing process includes labeling the collected environmental data and steel pipe pile data, identifying data outside the reasonable range and marking them as invalid values; after labeling, the data sampled by the sensors is averaged to obtain the average environmental physicochemical parameters and the average thickness of the steel pipe piles within the target wharf steel pipe pile detection sub-area; and the conductivity is converted to salinity using a conversion formula.

[0064] The marking process involves removing outliers. Values ​​exceeding the normal range or with a sudden change exceeding ±2 units, temperatures below -6℃ or above 40℃ or with short-term fluctuations exceeding ±5℃, negative values ​​or salinity values ​​exceeding 50%, and dissolved oxygen contents measured at high temperatures exceeding 12 mg / L or exceeding 120% of the saturation value should all be deleted. Steel pipe pile thicknesses with negative values ​​or exceeding the initial thickness by ±20% should also be deleted.

[0065] Under ideal conditions, the formula for calculating the average thickness of a steel pipe pile is:

[0066]

[0067] in, This represents the average thickness of the steel pipe pile. , , This indicates the thickness of the steel pipe pile as measured by three thickness gauges.

[0068] The average physicochemical parameters of the environment include average conductivity, average pH value, average temperature, and average dissolved oxygen content; the formula for calculating average conductivity is:

[0069]

[0070] Where C(t) is the average conductivity, , , This represents the conductivity measured by three conductivity sensors; the formula for calculating the average pH value is:

[0071]

[0072] Where pH is the average pH value. , , This represents the pH value measured by three glass electrode sensors; the formula for calculating the average temperature is:

[0073]

[0074] Where T is the average temperature. , , This represents the temperature measured by three platinum resistance temperature sensors; the formula for calculating the average dissolved oxygen content is:

[0075]

[0076] Wherein, DO represents the average dissolved oxygen content. , , This represents the dissolved oxygen content measured by three electrochemical dissolved oxygen sensors.

[0077] The conversion formula for salinity using electrical conductivity includes the following steps:

[0078] Step 1: Calculate the temperature correction factor:

[0079]

[0080] Where K(t, 15) is the temperature correction coefficient, which is a function of temperature t, and a is an empirical constant;

[0081] Step 2: Correct the equivalent conductivity at temperature 15°C:

[0082]

[0083] Where C(15) is the equivalent conductivity at temperature 15, and C(t) is the average conductivity obtained at temperature t;

[0084] Step 3: Calculate the salinity using the conversion formula between conductivity and salinity:

[0085]

[0086] Where S is salinity. , is the ratio of the conductivity of the seawater sample to that of the standard KCl solution, and the coefficient. , , , , , It is a fixed value. Coefficient , , , , , The specific value is =0.0080、 =-0.1692、 =25.3851、 =14.0941、 =-7.0261、 =2.7081.

[0087] Identify abnormal environmental data, wherein the abnormal environmental data meets any of the following conditions:

[0088] Within a continuous preset number of sampling periods, the pH value fluctuates beyond the acidity / alkalinity fluctuation threshold, or the temperature fluctuates beyond the temperature change threshold for a short period; or the thickness data deviates from the initial thickness value beyond the proportional tolerance threshold.

[0089] When abnormal environmental data is identified, the abnormal data point is replaced with the moving average of adjacent valid period data.

[0090] Abnormal environmental data is identified during preprocessing, and abnormal data points are replaced.

[0091] Abnormal environmental data are defined as pH fluctuations exceeding ±2 units of the acid-base fluctuation threshold within three consecutive collection cycles, or short-term temperature fluctuations exceeding ±5°C of the temperature change threshold; and thickness data deviating from the initial thickness value by more than ±20% of the proportional tolerance threshold.

[0092] When abnormal environmental data is detected, the abnormal data point is replaced with the moving average of data from adjacent valid periods. For example, if the pH value fluctuates by more than ±2 units within three consecutive periods, the system uses the moving average (i.e., the arithmetic mean) of the pH values ​​from the previous two valid periods to replace the current abnormal point; similarly, when the thickness data deviates from the initial thickness by ±20%, the moving average of the thickness from the two adjacent valid periods is used to replace it.

[0093] S103. Calculate the risk index based on the average physicochemical parameters of the environment;

[0094] The formula for calculating the risk index is:

[0095]

[0096] Where W is the risk index and S is the average salinity. The safe salinity threshold is given by pH (average pH) and T (average temperature). The safe temperature threshold is given, and DO is the average dissolved oxygen content. To ensure a safe dissolved oxygen threshold, , , , These are the weighting coefficients, and + + + =1.

[0097] The value is 40%. The value is 40℃. The value was 8 mg / L.

[0098] =0.30, salinity is the most significant factor affecting corrosion in the ocean, and therefore a high weight is assigned to salinity. =0.20. Unless there are extremely acidic or alkaline environments, pH value has little impact on corrosion, and pH is assigned a low weight. Temperature and dissolved oxygen are assigned certain weights. = =0.25.

[0099] Four sub-parameters—salinity, pH, temperature, and dissolved oxygen—are extracted from the average environmental physicochemical parameters. Each sub-parameter is mapped to a standardized contribution value using an independent nonlinear transformation function. The standardized contribution values ​​are then weighted and fused, with the salinity sub-parameter having a higher weight coefficient than the other sub-parameters. A discretized risk level signal is output based on the weighted fusion result.

[0100] Parameter extraction, transformation, and fusion when calculating the risk index.

[0101] Four sub-parameters—salinity, pH, temperature, and dissolved oxygen—were extracted from the average environmental physicochemical parameters. Salinity was calculated from conductivity, pH from the average value, temperature from the average temperature, and dissolved oxygen from the average dissolved oxygen content. Each sub-parameter was mapped to a standardized contribution value using independent nonlinear transformation functions. Specifically, the salt sub-parameter was mapped using the following formula: Mapping, pH sub-parameters using formulas Mapping, temperature sub-parameters using formulas Mapping, dissolved oxygen sub-parameters using formulas Mapping, each mapping function transforms the original value into a normalized contribution value in the range of 0-1.

[0102] The standardized contribution values ​​are weighted and fused, with the salinity sub-parameter having a weight coefficient of 0.30, higher than the weights of acidity (0.20), temperature (0.25), and dissolved oxygen (0.25). Based on the weighted fusion results, a discrete risk level signal is output, including low-risk warning (risk index W < 0.6), medium-risk warning (risk index W > 0.6 and < 0.8), and high-risk warning (risk index W > 0.8).

[0103] S104. Calculate the corrosion rate based on the average steel pipe pile thickness and the initial thickness;

[0104] The formula used in the corrosion rate calculation module is:

[0105]

[0106] Where v is the corrosion rate, This represents the initial thickness of the steel pipe pile. t represents the average thickness of the steel pipe pile, and t represents the corrosion time. The actual thickness at the time of installation; t is the cumulative time from when the steel pipe pile was put into use to the present.

[0107] S105. In the digital twin model, the model is dynamically updated according to the risk index, including: when the risk index indicates low risk or medium risk, a regular update is performed to update the model thickness and corrosion rate at a preset frequency; when the risk index indicates high risk, an emergency update is triggered to update the model thickness of the corresponding high-risk area in the digital twin model, wherein the high-risk area is determined based on the risk index reaching a preset threshold.

[0108] This application relates to dynamically updating a model in a digital twin model based on a risk index.

[0109] The digital twin modeling module is used to achieve bidirectional mapping between the model and the physical entity. It dynamically updates the thickness and corrosion rate of the steel pipe piles in the model based on the average thickness of the steel pipe piles, and marks them on the model with three colors according to the risk index.

[0110] The initial model of the digital twin modeling module is built based on the material and specification parameters of the steel pipe piles; the average thickness and corrosion rate of each steel pipe pile in the model are dynamically updated; and the risk index is marked with three colors on the model to display the risk index and locate high-risk areas.

[0111] From the perspective of basic modeling, the Unity 3D engine can be used to construct an initial geometric model based on the material, diameter, length, and wall thickness parameters of the steel pipe pile. The dimensional accuracy between the model and the physical entity can be ensured by importing CAD drawings. For the dynamic update function, a data interface can be developed using the Python programming language to receive the average thickness from the data preprocessing module, the rate value from the corrosion rate calculation module, and the index from the risk warning module in real time. The changes in model parameters, such as thickness reduction and dynamic changes in color markings, can be driven by the engine's script system.

[0112] At the data interaction level, the WebSocket lightweight communication protocol is adopted to realize real-time bidirectional mapping between physical sensor data and virtual models. When the sensor uploads thickness data, the geometric dimensions of the corresponding position in the model are updated synchronously. At the same time, the time series database InfluxDB is integrated to store historical data, supporting the model to retrospectively display the corrosion status at different time periods.

[0113] In terms of visualization, a browser-based interactive interface was developed using WebGL technology. The corresponding risk levels are mapped using three colors: blue, yellow, and red. The corrosion rate distribution is displayed using a heat map, allowing users to intuitively view the three-dimensional morphology, corrosion trend, and high-risk areas of the steel pipe piles. Ultimately, this achieves a deep integration from physical entities to virtual models.

[0114] The triggering condition for dynamic model updates is usually a regular update. The interval between regular updates is consistent with the acquisition frequency. Every 6 hours, the thickness and corrosion rate of the steel pipe piles are updated based on the measured data. When a red alert is triggered in a certain area, the model undergoes an emergency update. The model immediately changes the color marker of that area from yellow to red and magnifies the display of the three-dimensional details of that location.

[0115] When the risk index indicates low or medium risk, a regular update is performed, updating the model thickness and corrosion rate every 6 hours at a preset frequency. When the risk index indicates high risk, an emergency update is triggered, updating the model thickness of the corresponding high-risk area in the digital twin model. High risk is determined based on the risk index reaching a preset threshold of 0.8.

[0116] Multi-level early warning signals include low-risk warnings:

[0117] If the risk index W is less than the first preset threshold of 0.6, a low-risk warning signal is output, indicating normal monitoring; if the risk index W is greater than or equal to the first preset threshold of 0.6 and less than the second preset threshold of 0.8, a medium-risk warning signal is output, indicating that the data collection frequency in key areas should be increased; if the risk index W is greater than or equal to the second preset threshold of 0.8, a high-risk warning signal is output, which is immediately pushed to the management personnel and the corresponding high-risk area in the digital twin model is marked.

[0118] When W=0.6, the corresponding environmental data is in the range of slight impact. At this time, the salinity is about 60% of the safe threshold (24‰), the pH value deviates from neutral by about 1.2 units, the temperature is about 60% of the safe threshold (24℃), and the dissolved oxygen is about 60% of the safe threshold (4.8mg / L). The corrosion rate is slow and no additional intervention is required. When W=0.8, the corresponding environmental data enters the range of significant impact. At this time, the salinity reaches 80% of the safe threshold (32‰), the pH value deviates from neutral by about 1.6 units, the temperature reaches 80% of the safe threshold (32℃), and the dissolved oxygen reaches 80% of the safe threshold (6.4mg / L). The corrosion rate is significantly accelerated and emergency intervention is required to avoid structural damage.

[0119] The spatial coordinate clusters for locating high-risk areas in the digital twin model;

[0120] Perform multi-level resolution enhancement operations on the high-risk area based on the spatial coordinate cluster;

[0121] In the three-dimensional view of the digital twin model, a dynamic color-changing warning boundary layer is generated based on the display effect after the enhancement operation.

[0122] In the digital twin model, spatial coordinate clusters are used to locate high-risk areas. These clusters are determined based on sensor numbers and the positions of steel pipe piles. Multi-level resolution enhancement operations are then performed on the high-risk areas based on these clusters. These enhancements progressively magnify the geometric details of the high-risk areas, from a base resolution to a higher resolution. In the 3D view of the digital twin model, a dynamically changing color warning boundary layer is generated based on the enhanced display effect. This boundary layer is a flashing red border surrounding the high-risk areas, with the color gradually transitioning from yellow to red.

[0123] The time interval for collecting the environmental data and the steel pipe pile thickness data is adjusted to a first cycle value, which is less than the original time interval; monitoring data of the high-risk area is obtained based on the first cycle value; the risk index is updated based on the monitoring data; when the risk index continues to be lower than the downgrade threshold: the collection time interval is restored to the original time interval; the dynamic warning sign of the high-risk area is updated in the digital twin model.

[0124] After triggering an emergency update, the data collection interval for environmental data and steel pipe pile thickness data is adjusted to the first cycle value, which is every 1 hour, less than the original interval of every 6 hours. Monitoring data for high-risk areas is acquired based on the first cycle value, including real-time environmental and thickness data for these areas. The risk index is updated based on the monitoring data, and the updated risk index is calculated using the same formula. When the risk index remains below the downgrade threshold of 0.6: the data collection interval is restored to the original interval of every 6 hours; the dynamic warning signs for high-risk areas are updated in the digital twin model, changing from red back to yellow.

[0125] Monitor the change range of the risk index, and increase the update frequency of the digital twin model when the change range exceeds a preset sensitivity threshold; synchronously record the spatiotemporal evolution trajectory of the steel pipe pile thickness each time the digital twin model is updated; calculate the corrosion acceleration based on the recorded spatiotemporal evolution trajectory, and when the corrosion acceleration exceeds a critical threshold: generate an embedded reinforcement scheme instruction and update the visualization marker status of high-risk areas in the digital twin model.

[0126] The risk index is monitored for changes. When the change exceeds a preset sensitivity threshold of 0.1, the update frequency of the digital twin model is increased from every 6 hours to every 2 hours. The spatiotemporal evolution trajectory of the steel pipe pile thickness is recorded synchronously with each digital twin model update. This trajectory includes thickness and location data at different time points. Corrosion acceleration is calculated based on the recorded spatiotemporal evolution trajectory. The formula for calculating corrosion acceleration is:

[0127]

[0128] When the corrosion acceleration exceeds the critical threshold of 0.05 mm / h²: an embedded reinforcement scheme instruction is generated, which is to send a maintenance suggestion to add an anti-corrosion coating; and the visualization marking status of high-risk areas in the digital twin model is updated, and the visualization marking status changes from static marking to dynamic flashing.

[0129] The corrosion rate is converted into the thickness change rate parameter of the steel pipe pile in the digital twin model; the remaining life of the structure is predicted based on the thickness change rate parameter; when the remaining life of the structure is less than the maintenance safety threshold, the digital twin model is forcibly updated; the prediction algorithm parameters are dynamically calibrated according to the deviation rate between the measured corrosion rate and the predicted value after the forced update.

[0130] The corrosion rate is converted into the thickness change rate parameter of the steel pipe pile in the digital twin model, where the thickness reduction rate is the variable in the model. The remaining life of the structure is predicted based on the thickness change rate parameter. The formula for calculating the remaining life of the structure is as follows:

[0131]

[0132] The minimum safe thickness is 50% of the initial thickness. When the remaining lifespan of the structure is less than the maintenance safety threshold of one year, a forced update of the digital twin model is triggered. This forced update involves immediately updating the model data, ignoring the normal frequency. Based on the deviation rate between the measured corrosion rate and the predicted value after the forced update, the prediction algorithm parameters are dynamically calibrated. The deviation rate is calculated using the formula |measured value - predicted value| / predicted value. Dynamic calibration involves adjusting the weighting coefficients. , , , .

[0133] This application also provides a device for monitoring the corrosion rate of steel pipe piles at wharves, comprising:

[0134] The data acquisition module collects environmental data and steel pipe pile thickness data for the target wharf steel pipe pile inspection sub-area;

[0135] The preprocessing module preprocesses the environmental data and steel pipe pile thickness data to obtain the average environmental physicochemical parameters and the average steel pipe pile thickness.

[0136] The index module calculates the risk index based on the average physicochemical parameters of the environment;

[0137] The corrosion module calculates the corrosion rate based on the average steel pipe pile thickness and the initial thickness.

[0138] The update module dynamically updates the model in the digital twin model according to the risk index, including: when the risk index indicates low or medium risk, performing a regular update to update the model thickness and corrosion rate at a preset frequency; when the risk index indicates high risk, triggering an emergency update to update the model thickness of the corresponding high-risk area in the digital twin model, wherein the high-risk area is determined based on the risk index reaching a preset threshold.

[0139] This application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0140] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the above-described method.

[0141] The above description of the embodiments is provided to enable those skilled in the art to understand and apply this application. Those skilled in the art will readily make various modifications to the above embodiments and apply the general principles described herein to other embodiments without inventive effort. Therefore, this application is not limited to the above embodiments, and any improvements and modifications made to this application based on the disclosure thereof should be within the scope of protection of this application.

Claims

1. A method for monitoring the corrosion rate of steel pipe piles at wharves, characterized in that, include: Collect environmental data and steel pipe pile thickness data for the target wharf steel pipe pile inspection sub-area; The environmental data and steel pipe pile thickness data are preprocessed to obtain the average environmental physicochemical parameters and the average steel pipe pile thickness. The risk index is calculated based on the average environmental physicochemical parameters, including: extracting four sub-parameters—salinity, pH, temperature, and dissolved oxygen—from the average environmental physicochemical parameters; mapping each sub-parameter to a standardized contribution value using an independent nonlinear transformation function; weighting and fusing the standardized contribution values, wherein the weight coefficient of the salinity sub-parameter is higher than that of the other sub-parameters; and outputting a discrete risk level signal based on the weighted fusion result. The corrosion rate was calculated based on the average steel pipe pile thickness and the initial thickness. In the digital twin model, the model is dynamically updated according to the risk index, including: when the risk index indicates low or medium risk, a regular update is performed to update the model thickness and corrosion rate at a preset frequency; when the risk index indicates high risk, an emergency update is triggered to update the model thickness of the corresponding high-risk area in the digital twin model, including: monitoring the change amplitude of the risk index, and increasing the update frequency of the digital twin model when the change amplitude exceeds a preset sensitivity threshold; synchronously recording the spatiotemporal evolution trajectory of the steel pipe pile thickness each time the digital twin model is updated; calculating the corrosion acceleration based on the recorded spatiotemporal evolution trajectory, and when the corrosion acceleration exceeds a critical threshold: generating an embedded reinforcement scheme instruction and updating the visualization marker status of the high-risk area in the digital twin model, wherein the high-risk area is determined based on the risk index reaching a preset threshold; The triggering of emergency updates includes: locating a spatial coordinate cluster of high-risk areas in the digital twin model; performing multi-level resolution enhancement operations on the high-risk areas based on the spatial coordinate clusters; and generating a dynamic color-changing warning boundary layer in the three-dimensional view of the digital twin model based on the display effect after the enhancement operations.

2. The method according to claim 1, characterized in that, The preprocessing of the environmental data and steel pipe pile thickness data includes: Identify abnormal environmental data, wherein the abnormal environmental data meets any of the following conditions: If the pH value fluctuates beyond the acid-base fluctuation threshold within a continuous preset number of sampling periods, or the temperature fluctuates beyond the temperature change threshold for a short period of time. The thickness data deviates from the initial thickness value by more than the proportional tolerance threshold. When abnormal environmental data is identified, the abnormal data point is replaced with the moving average of adjacent valid period data.

3. The method according to claim 1, characterized in that, The process of triggering an emergency update also includes: The time interval for collecting the environmental data and the steel pipe pile thickness data is adjusted to a first cycle value, which is less than the original time interval. The monitoring data of the high-risk area is obtained based on the first periodic value; The risk index is updated based on the monitoring data. When the risk index remains below the downgrade threshold: restore the data collection time interval to the original time interval; update the dynamic warning sign of the high-risk area in the digital twin model.

4. The method according to claim 1, characterized in that, Also includes: The corrosion rate is converted into the thickness variation rate parameter of the steel pipe pile in the digital twin model; Predict the remaining lifespan of the structure based on the thickness change rate parameter; When the remaining lifespan of the structure is less than the maintenance safety threshold, a forced update of the digital twin model is triggered; Based on the deviation rate between the measured corrosion rate and the predicted value after forced update, the prediction algorithm parameters are dynamically calibrated.

5. A device for monitoring the corrosion rate of steel pipe piles at wharves, characterized in that, The apparatus is used to perform the method of claim 1, comprising: The data acquisition module collects environmental data and steel pipe pile thickness data for the target wharf steel pipe pile inspection sub-area; The preprocessing module preprocesses the environmental data and steel pipe pile thickness data to obtain the average environmental physicochemical parameters and the average steel pipe pile thickness. The index module calculates the risk index based on the average physicochemical parameters of the environment; The corrosion module calculates the corrosion rate based on the average steel pipe pile thickness and the initial thickness. The update module dynamically updates the model in the digital twin model according to the risk index, including: when the risk index indicates low or medium risk, performing a regular update to update the model thickness and corrosion rate at a preset frequency; when the risk index indicates high risk, triggering an emergency update to update the model thickness of the corresponding high-risk area in the digital twin model, wherein the high-risk area is determined based on the risk index reaching a preset threshold.

6. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed in a computer, causes the computer to perform the method described in any one of claims 1-4.

Images