Anti-corrosion protection method and system for propeller in deep sea environment

Abstract

The invention relates to the technical field of data processing, and discloses an anti-corrosion protection method and system for a propeller in a deep sea environment. The method comprises the steps that seawater corrosion data are collected through a sensor array, risk grading is conducted through a genetic algorithm, current distribution is optimized through a Lagrange algorithm, a self-adaptive protection potential field is constructed to respond to chloride ion concentration changes, the corrosion trend is analyzed based on a prediction model, and anti-corrosion control is executed. The intelligent level and the protection effect of anti-corrosion protection of the propeller in the deep sea environment are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for protecting a thruster from corrosion in a deep-sea environment. Background Art

[0002] In existing technology, deep-sea propeller corrosion protection primarily relies on passive protection strategies, including applying a single coating system such as epoxy resin coating or polyurethane coating to the propeller surface, and simultaneously installing sacrificial anodes or impressed current cathodic protection devices. These devices electrochemically place the propeller metal in a cathodic state to prevent electrochemical corrosion. After the equipment is put into operation, regular manual inspections and maintenance are primarily used to assess corrosion conditions. If coating damage or signs of corrosion are found, the equipment must be salvaged and brought ashore for coating repair or replacement of the sacrificial anodes.

[0003] The existing technology has the following technical deficiencies: the protection effect is not long-lasting enough, and the single coating system is prone to failure phenomena such as blistering, peeling and penetration in complex marine environments; there is a lack of targeted design, and unified anti-corrosion measures are adopted for different components of the thruster, ignoring the differences in corrosion risks faced by each component; the monitoring methods are backward, mainly relying on manual visual inspection, and cannot grasp the development of corrosion in real time; the maintenance cost is high, and frequent equipment recovery and re-coating are required; the protection parameters are fixed, and the anti-corrosion strategy cannot be automatically adjusted according to changes in actual marine environmental conditions.

[0004] Because existing technologies are unable to monitor and process data on corrosion factors in deep-sea environments in real time, changes in corrosion risk cannot be detected promptly, making it impossible to conduct differentiated corrosion risk grading assessments. This lack of differentiated risk assessments also prevents current distribution optimization from accurately configuring areas of varying risk levels, making it impossible to construct adaptive protective potential fields to respond to environmental changes. Ultimately, due to the lack of predictive analysis capabilities based on data processing, existing technologies are unable to predict corrosion trends or intelligently optimize protection parameters, forcing them to resort to passive, post-event maintenance. Summary of the Invention

[0005] The present application provides a method and system for thruster corrosion protection in a deep-sea environment, which is used to solve the problem in the existing technology that deep-sea thruster corrosion protection cannot achieve real-time monitoring, differentiated risk assessment, adaptive potential field control and predictive parameter optimization, and improves the intelligence level and protection effect of thruster corrosion protection in a deep-sea environment.

[0006] In a first aspect, the present application provides a method for protecting a propeller from corrosion in a deep-sea environment, the method comprising: The corrosion monitoring sensor array collects and processes real-time data of the seawater around the deep-sea thruster to obtain an environmental corrosion dataset containing chloride ion concentration, dissolved oxygen concentration, pH value, and corrosion potential. Performing corrosion risk classification calculation on the propeller surface using a genetic algorithm based on the environmental corrosion data set to obtain corrosion risk levels for the propeller blade area, the bearing seal area, and the housing static area; The corrosion risk level is subjected to current distribution optimization processing using a Lagrangian algorithm to obtain current density distribution parameters of each protective electrode; The thruster surface potential field is reconstructed and regulated according to the current density distribution parameters of each protection electrode to obtain an adaptive protection potential field based on chloride ion concentration. The adaptive protection potential field is subjected to corrosion trend analysis and processing through a prediction model to obtain protection parameter optimization instructions and perform anti-corrosion control.

[0007] In a second aspect, the present application provides a propeller anti-corrosion protection system in a deep-sea environment, the propeller anti-corrosion protection system in a deep-sea environment comprising: The acquisition module is used to collect and process real-time data of the seawater around the deep-sea thruster through a corrosion monitoring sensor array to obtain an environmental corrosion data set containing chloride ion concentration, dissolved oxygen concentration, pH value, and corrosion potential; a grading module, configured to perform corrosion risk grading calculation processing on the propeller surface using a genetic algorithm based on the environmental corrosion data set, and obtain corrosion risk levels for the propeller blade area, the bearing seal area, and the casing static area; A distribution module, configured to perform current distribution optimization processing on the corrosion risk level using a Lagrangian algorithm to obtain current density distribution parameters of each protective electrode; A control module is used to reconstruct and control the surface potential field of the thruster according to the current density distribution parameters of each protection electrode to obtain an adaptive protection potential field based on the chloride ion concentration; The analysis module is used to perform corrosion trend analysis on the adaptive protection potential field through a prediction model, obtain protection parameter optimization instructions and execute anti-corrosion control.

[0008] In a third aspect, a thruster anti-corrosion protection device in a deep-sea environment is provided, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the thruster anti-corrosion protection device in the deep-sea environment executes the above-mentioned thruster anti-corrosion protection method in the deep-sea environment.

[0009] In a fourth aspect, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium, which, when executed on a computer, enables the computer to execute the above-mentioned method for protecting a thruster from corrosion in a deep-sea environment.

[0010] The technical solution provided in this application uses a corrosion monitoring sensor array to collect and process real-time data from the seawater surrounding the deep-sea propeller to obtain an environmental corrosion data set. This overcomes the limitations of existing technologies that rely on periodic manual inspections and enables continuous monitoring of key corrosion factors such as chloride ion concentration, dissolved oxygen concentration, pH value, and corrosion potential, providing a reliable data foundation for subsequent intelligent corrosion prevention decisions. The application of genetic algorithms in corrosion risk grading calculations optimizes weight parameters by simulating natural selection and genetic mechanisms, making the corrosion risk level assessment of the propeller blade area, bearing seal area, and casing static area more accurate and objective, avoiding the subjectivity and inconsistency of traditional methods that rely on engineers' experience. The application of Lagrangian algorithms in current distribution optimization uses a constrained optimization mathematical model to achieve the optimal configuration of the current density distribution parameters of each protective electrode while satisfying the total current conservation condition. Compared with the traditional uniform distribution method, it can differentiate current distribution according to the actual protection needs of different areas, ensuring sufficient protection in high-risk areas while avoiding overprotection and energy waste in low-risk areas.

[0011] The technical feature of constructing an adaptive protective potential field based on chloride ion concentration enables the corrosion protection system to automatically adjust its protection intensity based on real-time changes in chloride ion concentration in the seawater environment. This overcomes the technical bottleneck of fixed protection parameters in existing technologies and achieves a fundamental shift from passive protection to active adaptation. The application of predictive models in corrosion trend analysis and processing, particularly the introduction of long-short-term memory network algorithms, enables the system to learn historical corrosion evolution patterns and predict future corrosion trends. This predictive analysis capability shifts corrosion control from traditional post-remediation to pre-emptive prevention, significantly extending the service life of thrusters in deep-sea environments. The application of particle swarm optimization algorithms in the protection parameter adjustment process automatically finds the optimal current density and potential adjustment values through a swarm intelligence optimization mechanism, enabling the entire corrosion protection system to maintain optimal protection in the complex and changing deep-sea environment. Compared with traditional manual adjustment methods, it not only has a faster response speed, but also higher adjustment accuracy and better system stability, thus achieving intelligent, automated, and efficient corrosion protection for deep-sea thrusters. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 This is a schematic diagram of an embodiment of a method for protecting a propeller from corrosion in a deep-sea environment according to an embodiment of the present application; Figure 2 This is a schematic diagram of an embodiment of a propeller anti-corrosion protection system in a deep-sea environment in an embodiment of the present application; Figure 3 It is a schematic block diagram of the structure of a thruster anti-corrosion protection device in a deep-sea environment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0014] The embodiments of the present application provide a method and system for anti-corrosion protection of a thruster in a deep-sea environment. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0015] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In one embodiment of the present application, a method for protecting a propeller from corrosion in a deep-sea environment includes: Step S101: Real-time data collection and processing of the seawater surrounding the deep-sea thruster is performed using a corrosion monitoring sensor array to obtain an environmental corrosion data set including chloride ion concentration, dissolved oxygen concentration, pH value, and corrosion potential; Step S102: performing corrosion risk classification calculation on the propeller surface using a genetic algorithm based on the environmental corrosion data set to obtain corrosion risk levels for the propeller blade area, the bearing seal area, and the housing static area; Step S103: performing current distribution optimization processing on the corrosion risk level using the Lagrangian algorithm to obtain the current density distribution parameters of each protective electrode; Step S104: reconstructing and regulating the propeller surface potential field according to the current density distribution parameters of each protection electrode to obtain an adaptive protection potential field based on chloride ion concentration; Step S105: Perform corrosion trend analysis on the adaptive protection potential field through a prediction model to obtain protection parameter optimization instructions and execute anti-corrosion control.

[0016] It is understandable that the execution subject of this application can be a thruster anti-corrosion protection system in a deep-sea environment, or a terminal or a server, which is not limited here. The embodiment of this application is described by taking a server as the execution subject as an example.

[0017] Specifically, real-time data acquisition is performed using a corrosion monitoring sensor array deployed on the thruster surface. This sensor array includes a chloride ion-selective electrode sensor, a dissolved oxygen fluorescence sensor, a pH glass electrode sensor, and a corrosion potential reference electrode sensor. The chloride ion-selective electrode sensor operates on the principle of an ion-selective membrane. When chloride ions in seawater come into contact with the electrode membrane, a potential difference is generated. The magnitude of this potential difference is logarithmically related to the chloride ion concentration. The dissolved oxygen fluorescence sensor utilizes the principle of fluorescence quenching: oxygen molecules reduce the fluorescence intensity of the fluorescent dye, and the dissolved oxygen concentration is calculated by measuring this change in fluorescence intensity. The pH glass electrode sensor operates on the principle of glass membrane potential: changes in hydrogen ion concentration cause changes in the potential difference across the glass membrane. The corrosion potential reference electrode sensor uses a silver-silver chloride electrode as a reference and measures the potential of the thruster metal surface relative to the reference electrode. Data acquisition is performed at 30-second intervals, and the analog signals output by each sensor are converted to digital signals via an analog-to-digital converter. The raw data is processed using a Kalman filter to eliminate noise interference and then calibrated with standard solutions to obtain accurate values. Outlier rejection is based on the 3σ criterion: data outside the range of plus or minus three standard deviations from the mean are marked as outliers and rejected. The valid data are combined in time series to form an environmental corrosion dataset. The data structure contains fields such as timestamp, sensor location coordinates, chloride ion concentration, dissolved oxygen concentration, pH value, and corrosion potential.

[0018] A genetic algorithm is used to stratify the corrosion risk of propeller surfaces. A genetic algorithm, an optimization algorithm that mimics biological evolution, seeks the optimal solution through selection, crossover, and mutation. First, the environmental corrosion dataset is mapped to three regions based on the propeller geometry: the propeller blade area, the bearing seal area, and the casing static area. This geometric mapping establishes a coordinate system based on the propeller's three-dimensional model, assigning each sensor data point to a corresponding region based on its spatial coordinates. A deep-sea pressure correction factor is used to correct for the effects of high-pressure environments on corrosion parameters. The correction formula is: the pressure correction factor equals 1 plus the pressure correction factor multiplied by the current depth pressure. The risk index for each region is calculated using a weighted summation method: chloride ion concentration, dissolved oxygen concentration, pH value, and stress factor are multiplied by their corresponding weight coefficients and then added together. The genetic algorithm population is initialized by randomly generating multiple combinations of weight coefficients as initial individuals. The fitness function evaluates the contribution of each weight coefficient set to the accuracy of the risk assessment. The selection operation retains individuals with high fitness. The crossover operation combines the weight coefficients of two individuals. The mutation operation randomly changes some of the weight coefficients. After multiple generations of evolution, the optimal weight parameters are obtained. The final risk index of each area is calculated based on the weight parameters, and the area is divided into three corrosion risk levels: high, medium, and low according to the preset threshold.

[0019] The Lagrangian algorithm is used to optimize current distribution. The Lagrangian algorithm is a constrained optimization method used to find the optimal solution to the objective function while satisfying constraints. The number of protective electrodes is configured based on the corrosion risk level, with more electrodes allocated to high-risk areas to provide adequate protection. Electrode weights are assigned based on risk level differences, with higher electrode weights in high-risk areas, followed by medium-risk areas, and the lowest in low-risk areas. The protected area is allocated based on the surface area and risk level of each region, with larger areas and higher risks receiving larger protected areas. The constrained optimization model is established using the Lagrangian multiplier method. The objective function is to minimize the sum of squared currents to reduce energy consumption, and the constraints are conservation of total current and the minimum protective current requirement for each region. The optimal current distribution coefficient that satisfies the constraints is obtained by solving a set of equations whose partial derivatives of the Lagrangian function are zero. This distribution coefficient is multiplied by the protected area of each region to obtain the current density distribution parameter for each protective electrode, ensuring that each region receives a protection intensity that matches its corrosion risk.

[0020] The thruster surface potential field is reconstructed and regulated based on the current density distribution parameters. The potential distribution calculation is based on the principle of electric field superposition. The potential fields generated by each protective electrode are superimposed in space to form a total potential field. The calculation process takes into account the electrode position coordinates, output current intensity, seawater resistivity, and distance factors. The chloride ion concentration gradient is corrected by establishing a relationship model between chloride ion concentration and potential correction. When the chloride ion concentration increases, the protective potential needs to be lowered to maintain effective protection. The correction coefficient is calculated based on the change in chloride ion concentration and the sensitivity coefficient. Each protective electrode dynamically adjusts its output current based on the correction coefficient. The adjustment algorithm adopts a proportional-integral control method. The proportional term responds to the current concentration deviation, and the integral term eliminates steady-state errors. The adjusted electrode output current parameters are recalculated through potential field superposition to generate a reconstructed potential distribution on the thruster surface. The adaptive protective potential field forms a dynamically responsive anti-corrosion protection system by monitoring changes in chloride ion concentration in real time and adjusting the potential distribution accordingly.

[0021] A predictive model is used to analyze and process corrosion trends. The Long Short-Term Memory (LSTM) network algorithm is a specialized recurrent neural network capable of processing time series data and long-term dependencies. The network structure consists of input, forget, and output gates, with gating mechanisms controlling information flow. Adaptive protection potential field data is compared with historical corrosion evolution data in time series to extract characteristic parameters of corrosion trends, including corrosion rate gradients, potential fluctuation amplitudes, and periodicity. LSTM network training uses historical data to establish a corrosion rate prediction model. The input layer receives current potential field data and environmental parameters, the hidden layer learns corrosion development patterns, and the output layer predicts corrosion rates for the next 24 hours. The remaining protection time is calculated based on the current coating thickness, predicted corrosion rate, and safety threshold, using division to determine the remaining protection time for each region. A particle swarm optimization algorithm simulates the foraging behavior of a flock of birds. Each particle represents a set of protection parameter adjustment options, and the optimal adjustment strategy is found through velocity and position updates. The algorithm optimizes to extend the remaining protection time and reduce energy consumption, outputting current density adjustment and potential adjustment. Each protection electrode adjusts its output parameters based on the optimization results, achieving closed-loop optimization of corrosion control.

[0022] In a specific embodiment, the process of executing step S101 may specifically include the following steps: The chloride ion selective electrode sensor, dissolved oxygen fluorescence sensor, pH glass electrode sensor and corrosion potential reference electrode sensor are deployed at key positions on the thruster surface according to a preset array layout; The data of each sensor is read and processed based on a 30-second time interval to obtain the original values of chloride ion concentration, dissolved oxygen concentration, pH value and corrosion potential; Inputting the original values of chloride ion concentration, dissolved oxygen concentration, pH value and corrosion potential into a data preprocessing module for filtering and calibration processing to obtain chloride ion concentration calibration data, dissolved oxygen concentration calibration data, pH value calibration data and corrosion potential calibration data; The chloride ion concentration calibration data, dissolved oxygen concentration calibration data, pH value calibration data and corrosion potential calibration data were processed to eliminate outliers and obtain effective corrosion parameter data; The effective corrosion parameter data are combined and processed according to the time series to obtain the environmental corrosion data set.

[0023] Specifically, the sensor array deployment is based on the thruster's geometric structural characteristics and analysis of corrosion-sensitive areas. The chloride ion selective electrode sensor utilizes ion-sensitive field-effect transistor technology. Its core is an electrode head containing a chloride ion-sensitive membrane. When chloride ions in seawater come into contact with the sensitive membrane, an ion exchange reaction occurs, generating a potential difference that is logarithmically related to the chloride ion concentration. This potential difference is converted to a voltage signal output by a high-impedance amplifier. The dissolved oxygen fluorescence sensor operates based on the principle of fluorescence quenching. The sensor is coated with a fluorescent dye. Excitation light illuminates the fluorescent dye, producing fluorescence. When dissolved oxygen molecules in seawater collide with the fluorescent dye, the fluorescence intensity decreases. The dissolved oxygen concentration is calculated by measuring the attenuation of the fluorescence intensity. The pH glass electrode sensor uses a special glass membrane as the sensitive element. The difference in hydrogen ion concentration on both sides of the glass membrane generates a membrane potential that is proportional to the logarithm of the hydrogen ion activity. The corrosion potential reference electrode sensor uses a silver-silver chloride electrode as a stable reference point. It measures the potential difference between the thruster metal surface and the reference electrode, reflecting the metal's corrosion tendency. The preset array layout deploys chloride ion selective electrode sensors on the leading and trailing edges of the propeller blades, dissolved oxygen fluorescence sensors are installed around the bearing sealing area, pH glass electrode sensors are distributed on the surface of the static area of the casing, and corrosion potential reference electrode sensors are evenly distributed in various areas to form a potential monitoring grid.

[0024] Data reading and processing utilizes a synchronous sampling mode with a 30-second interval. The analog signals output by each sensor are simultaneously fed into a multi-channel analog-to-digital converter, which discretizes the continuous analog voltage signals into digital quantities with 16-bit accuracy and a sampling frequency of 10 Hz. The raw value of chloride ion concentration is calculated using the potential difference across the ion-selective electrode. The relationship between potential difference and chloride ion concentration follows the Nernst equation, with temperature correction factors and the cell constant factored into the calculation. The raw value of dissolved oxygen concentration is based on fluorescence intensity measurements. Fluorescence intensity is inversely proportional to dissolved oxygen concentration, and a calibration curve is used to convert the fluorescence intensity values into dissolved oxygen concentration values. The raw value of pH is calculated from the membrane potential of the glass electrode. The membrane potential and pH have a linear relationship with a slope of approximately 59.16 millivolts per pH unit. The raw value of corrosion potential is derived directly from the potential difference measured by the reference electrode. The value, expressed in millivolts, represents the electrochemical state of the thruster metal surface.

[0025] After receiving the four types of raw values, the data preprocessing module performs filtering and calibration. The filtering process uses a digital low-pass filter to eliminate high-frequency noise interference. The filter cutoff frequency is set to 0.1 Hz to retain useful information on corrosion parameter changes while filtering out electromagnetic interference and mechanical vibration noise. The calibration process establishes a calibration equation based on the known parameter values of the standard solution. The chloride ion selective electrode uses a standard seawater sample with a known chloride ion concentration to establish a calibration relationship between concentration and potential. The dissolved oxygen fluorescence sensor determines the zero and full-scale calibration points using nitrogen-saturated water samples and air-saturated water samples. The pH glass electrode performs a two-point calibration using a standard buffer solution to determine the slope and intercept. The corrosion potential reference electrode is calibrated using a standard electrode potential to ensure measurement accuracy. The calibration process substitutes the raw values into the calibration equation to calculate the chloride ion concentration calibration data, the dissolved oxygen concentration calibration data, the pH value calibration data, and the corrosion potential calibration data.

[0026] The outlier removal process uses statistical methods to identify and remove abnormal data points. First, the mean and standard deviation of each type of calibration data within a sliding time window are calculated. The sliding time window length is set to 10 minutes and contains 20 data points. The outlier judgment adopts the criterion of 3 times the standard deviation. When the difference between a data point and the mean value exceeds 3 times the standard deviation, it is marked as an outlier. The causes of outliers include measurement deviations caused by factors such as transient sensor failure, electromagnetic interference, and marine biological adhesion. The outlier removal algorithm checks each data point one by one and deletes the data points marked as abnormal from the data sequence. At the same time, the time and location information of the outlier occurrence are recorded for sensor health status assessment. The effective corrosion parameter data obtained after removing the outliers has higher reliability and continuity.

[0027] Time series data combination processing arranges and integrates valid corrosion parameter data according to a unified time base, using the UTC time format to ensure synchronization between sensor data. The data combination process first establishes a time index, with each time point corresponding to a complete set of corrosion parameter data, including chloride ion concentration, dissolved oxygen concentration, pH value, and corrosion potential. When sensor data is missing at a particular time point, linear interpolation is used to fill in the missing data. The interpolation calculation is based on a linear fit of the data values at adjacent time points. Data combination also includes the addition of spatial coordinate information, with each data point annotated with the corresponding sensor's three-dimensional coordinate location, forming a multidimensional data structure encompassing time, space, and parameter dimensions. The environmental corrosion dataset is stored in a relational database format. The data table structure includes fields for timestamp, sensor number, coordinate location, chloride ion concentration, dissolved oxygen concentration, pH value, and corrosion potential. The data table supports querying and filtering by time range, spatial region, and parameter range.

[0028] In a specific embodiment, the process of executing step S102 may specifically include the following steps: The environmental corrosion data set is processed by regional mapping according to the propeller geometry to obtain the partition parameters of the propeller blade area, bearing seal area and casing static area; Perform environmental correction on the partition parameters based on the pressure correction coefficient to obtain the corrected corrosion parameters; The risk index of each area is obtained by performing weighted sum calculation on chloride ion concentration, dissolved oxygen concentration, pH value and stress factor; The risk index is initialized and evaluated for fitness using a genetic algorithm to obtain weight parameters; The risk index is graded based on the weight parameters to obtain the corrosion risk levels of the propeller blade area, bearing seal area, and casing static area.

[0029] Specifically, the region mapping process establishes a spatial coordinate system based on the propeller's three-dimensional geometric model. The propeller's geometry includes the complex curved surfaces of the propeller blades, the cylindrical structure of the bearing seal area, and the regular surface of the housing's static zone. The mapping algorithm first reads the sensor's spatial coordinate information and then assigns the sensor data to corresponding zones based on pre-set zone boundary conditions. The propeller blade zone boundary is defined as the curved surface from the leading edge to the trailing edge of the blade; the bearing seal zone boundary is defined as the cylindrical region within a radius around the bearing center; and the housing's static zone boundary is defined as the remaining surface of the propeller's housing after excluding the propeller and bearing areas. The mapping process uses a nearest neighbor algorithm to calculate the Euclidean distance from each sensor location to the center of each zone and assign the sensor data to the zone with the closest distance. The partition parameters include the values of chloride ion concentration, dissolved oxygen concentration, pH value, and corrosion potential measured by all sensors within each zone. The number and distribution density of sensors within each zone are also recorded. The data aggregation process statistically processes the data from multiple sensors within the same zone, calculating statistical characteristics such as mean, maximum, minimum, and standard deviation to form a comprehensive corrosion parameter profile for each zone.

[0030] The calculation of the pressure correction factor is based on the mechanism by which deep-sea high-pressure environments affect corrosion processes. Increased deep-sea pressure alters the physical and chemical properties of seawater, affecting ion diffusion rates and electrochemical reaction rates. The pressure correction factor is calculated using a piecewise linear function, with different correction parameters applied across different depth ranges. For depths less than 1000 meters, the correction factor is 1 plus a linear term multiplied by the depth times 0.00005; for depths between 1000 and 3000 meters, the correction factor is 1 plus a linear term multiplied by the depth times 0.0001; and for depths greater than 3000 meters, the correction factor is 1 plus a linear term multiplied by the depth times 0.00015. Environmental correction multiplies each corrosion parameter in the zone parameter by the corresponding pressure correction factor to produce a corrected corrosion parameter that accounts for the effects of deep-sea pressure. Chloride ion concentration correction accounts for the change in ion activity coefficients under high pressure; dissolved oxygen concentration correction accounts for the effect of pressure on gas solubility; pH correction accounts for the effect of pressure on the water ionization constant; and corrosion potential correction accounts for the effect of pressure on electrode potential. These corrected corrosion parameters more accurately reflect the actual corrosion conditions in deep-sea environments.

[0031] The risk index calculation uses a weighted summation method to combine multiple corrosion factors into a single risk assessment indicator. Chloride ion concentration, as the primary corrosive agent, is given a higher weight, followed by dissolved oxygen concentration, as an oxidant. pH, which affects the corrosion reaction rate, has a lower weight. The stress factor reflects the effect of mechanical stress on corrosion, and its weight is differentiated based on regional characteristics. The stress factor is calculated based on an analysis of the stress distribution during propeller operation. The propeller blade area is subject to complex dynamic stresses, including centrifugal force, fluid dynamic pressure, and vibration stress. The bearing seal area experiences stress concentrations caused by radial and axial loads. The static area of the casing is primarily subject to hydrostatic pressure. The weighted summation calculation multiplies the corrected chloride ion concentration by a weight of 0.4, the dissolved oxygen concentration by a weight of 0.3, the square of the pH deviation by a weight of 0.2, and the stress factor by a weight of 0.1. These four products are added together to produce the initial risk index for each region.

[0032] A genetic algorithm, an optimization algorithm that mimics natural selection and genetic mechanisms, is used to find the optimal weight parameter combination to improve the accuracy of risk assessment. The population initialization process randomly generates multiple individuals, each representing a set of weight parameter combinations. The number of individuals is set to 50, and each individual contains four weight parameters, corresponding to chloride ion concentration, dissolved oxygen concentration, pH value, and stress factor. The fitness assessment process defines a fitness function to measure the quality of each weight parameter combination. This fitness function is based on the degree of match between the risk assessment results and historical corrosion damage data. Weight combinations with a higher degree of match have higher fitness values. The fitness calculation process applies the current weight parameter combination to historical data to calculate a risk index. This is then compared with the actual corrosion damage level, and the predicted accuracy is calculated as the fitness value. The selection process uses a roulette wheel selection method, where individuals with higher fitness are more likely to be selected. The crossover operation recombines the weight parameters of two parent individuals to produce offspring individuals, with a crossover probability set to 0.8. The mutation operation randomly changes some of the weight parameters in an individual, with a mutation probability set to 0.1. After multiple generations of evolution, the weight parameter combination represented by the individual with the highest fitness is determined as the optimal weight parameter combination.

[0033] The level determination process recalculates the final risk index of each area based on the optimized weight parameters, and then divides the risk index into different levels according to the preset threshold range. The risk level division adopts a three-level system. When the risk index is less than 0.3, it is determined to be a low risk level. When the risk index is between 0.3 and 0.7, it is determined to be a medium risk level. When the risk index is greater than 0.7, it is determined to be a high risk level. The threshold setting is based on the statistical analysis of a large amount of historical corrosion data. The low risk level corresponds to areas with slower corrosion rates, the medium risk level corresponds to areas with medium corrosion rates, and the high risk level corresponds to areas with faster corrosion rates. The determination process compares the risk index of each area with the threshold range one by one to determine the corrosion risk level of the propeller blade area, the bearing seal area, and the casing static area.

[0034] In a specific embodiment, the process of executing step S103 may specifically include the following steps: The number of protective electrodes is configured according to the corrosion risk level, and the layout plan of the electrodes in the propeller blade area, the bearing seal area and the casing static area is obtained; The layout plan is processed according to the regional risk level to allocate electrode weights, and the electrode weights of high-risk areas, medium-risk areas and low-risk areas are obtained; Based on the corrosion risk level of each area, the protection area is allocated and calculated to obtain the area of high-risk area, medium-risk area and low-risk area; According to the protection area, the current constraint is solved by Lagrange multiplier method to obtain the distribution coefficient that meets the total current conservation condition; The distribution coefficient is multiplied by the area of each region to obtain the current density distribution parameter of each protective electrode.

[0035] Specifically, the electrode density configuration process determines the electrode deployment density for each area based on the differentiated corrosion risk level. The electrode density is calculated using the density coefficient corresponding to the risk level. The propeller blade area, designated as a high-risk area, has an electrode density coefficient of 1.5 electrodes per square meter; the bearing seal area, designated as a medium-risk area, has an electrode density coefficient of 1.0 electrodes per square meter; and the casing static area, designated as a low-risk area, has an electrode density coefficient of 0.5 electrodes per square meter. The electrode count calculation multiplies the surface area of each area by the corresponding density coefficient to determine the required number of electrodes. The propeller blade area's surface area includes the complex surface integral of the front, back, and edge of the blade; the bearing seal area's surface area is the sum of the lateral and end areas of the cylindrical seal surface; and the casing static area's surface area is the regular geometric surface area of the propeller casing. The electrode layout scheme considers the uniformity of electrode spacing and the continuity of current distribution, using a grid-based layout to establish a regular electrode distribution grid across the surface of each area. Electrodes in the propeller blade area are evenly distributed along the blade's radial and circumferential directions; electrodes in the bearing seal area are evenly distributed along the circumferential and axial directions; and electrodes in the casing static area are distributed in a rectangular grid pattern. The layout plan also needs to consider the mechanical compatibility of the electrode and the thruster structure to avoid interference between the electrode installation position and the thruster moving parts, while ensuring the reasonable direction and fixing method of the electrode connection cable.

[0036] The electrode weighting process determines the weights of electrodes in current distribution based on the relative importance of each area's risk level. The weighting reflects the differences in protective current requirements across risk levels. Electrode weights in high-risk areas are assigned based on their rapid corrosion rates and severe damage, with larger weights to ensure adequate electrochemical protection. Electrode weights in medium-risk areas are assigned based on their moderate corrosion rates and need for moderate protection, with medium weights. Electrode weights in low-risk areas are assigned based on their slow corrosion rates and relatively low protection requirements, with smaller weights. Weighting calculations use normalization to ensure the sum of all electrode weights equals 1. Normalization divides each electrode's initial weight by the sum of all electrode weights to obtain a standardized weight. Weighting also considers the interaction between electrodes and the superposition of current fields. Weighting adjacent electrodes balances local protection strength with overall protection effectiveness. A dynamic electrode weighting mechanism fine-tunes weights based on real-time monitored corrosion status changes. When the corrosion risk level in a particular area changes, the weights of the electrodes in that area are adjusted accordingly.

[0037] The effective area to be protected is determined based on the geometric characteristics and corrosion risk level of each area. The protected area is not equivalent to the surface area of the area, but rather takes into account the effective protection range required based on corrosion sensitivity and protection requirements. The high-risk area calculation includes the entire surface area of the propeller blades, as the entire surface faces a severe corrosion threat due to high-speed rotation and complex flow fields. The medium-risk area calculation includes the critical sealing area of the bearing seal area, with a focus on protecting the sealing interface between the bearing and seawater and stress concentration areas. The low-risk area calculation includes corrosion-sensitive localized areas within the static area of the casing, such as weld joints, material transition zones, and geometric discontinuities. Area allocation also considers the overlap of the electrode protection radius. The effective protection radius of each electrode is calculated based on current density and seawater resistivity. Appropriate overlap is required between the protection areas of adjacent electrodes to ensure that there are no blind spots. Dynamic adjustment of the protected area is based on feedback from corrosion monitoring data. If the actual corrosion situation in certain areas deviates from expectations, the protected area allocation ratio is adjusted promptly.

[0038] The Lagrange multiplier method, a classic mathematical approach for constrained optimization, is used to find the optimal solution for current distribution. This method seeks a current distribution solution that minimizes the objective function while satisfying the total current conservation constraint. The objective function for current constraint solving is to minimize the sum of the squares of the currents at each electrode. The physical meaning of this objective function is to minimize the total power consumption of the system. Constraints include the total current conservation condition, which states that the sum of all electrode currents equals the total system output current, and the minimum protection current requirement for each area, which states that the current in each area must not fall below the minimum required to maintain effective protection. The Lagrange function construction combines the objective function and constraints using Lagrange multipliers to form an unconstrained optimization problem. The solution process involves taking the partial derivatives of the Lagrange function with respect to each electrode current and the Lagrange multiplier and setting them to zero, resulting in a system of linear equations. The linear equations are solved using Gaussian elimination or matrix inversion to obtain the optimal current value for each electrode. The distribution coefficient is calculated by dividing the optimal current value for each electrode by the corresponding protected area to obtain the unit area current distribution coefficient, which reflects the current intensity required per square meter of protected area.

[0039] The current density distribution parameters are calculated by multiplying the distribution coefficient by the area of each zone to obtain the specific current output requirement for each protection electrode. The current density distribution parameters serve as direct control instructions for the electrochemical protection system. The distribution coefficient for each zone is multiplied by the area protected by the corresponding electrode to obtain the total current output required by that electrode. This total current is then divided by the electrode's effective area to determine the current density on the electrode surface. The current density is measured in milliamperes per square meter, and its value directly determines the cathodic protection effectiveness of the electrode. The distribution parameters also include the temporal characteristics of the current, adjusting the temporal distribution of the current output based on the dynamics of the corrosion environment. The spatial distribution of the current density considers the coordination between the electrodes, ensuring a smooth transition between the current densities of adjacent electrodes to avoid localized over- or under-protection. Current density is verified through potential field simulation to verify that the distribution results meet the protection potential requirements for each zone. If the simulation results indicate that the protection potential in certain zones does not meet the requirements, the current density distribution parameters of the corresponding electrodes need to be adjusted.

[0040] In a specific embodiment, the process of performing the step of configuring the number of protective electrodes according to the corrosion risk level may specifically include the following steps: The corrosion risk level is calculated and processed according to the risk degree to obtain the electrode density of the high-risk area, the medium-risk area and the low-risk area. The number of electrodes is distributed to each area according to the electrode density, and the number of electrodes in the propeller blade area, the bearing seal area and the casing static area are obtained. Based on the geometric characteristics of each area, the electrode positions are optimized and distributed to obtain the electrode positions at the leading edge of the blade, around the bearing, and on the surface of the casing. The electrode positions are processed for connection path planning according to the current transmission distance to obtain the cable connection path of each electrode; The electrodes are finally arranged and integrated according to the cable connection path to obtain the layout scheme of the electrodes in the propeller blade area, the bearing seal area and the casing static area.

[0041] Specifically, the electrode density calculation process determines the electrode distribution density required for each area based on the correspondence between the corrosion risk level and the electrode protection strength requirement. The electrode density reflects the number of electrodes that need to be configured per unit area to meet the corresponding anti-corrosion protection requirements. The electrode density in high-risk areas is calculated by multiplying the base density by the high-risk coefficient. The base density is set to 1 electrode per square meter, and the high-risk coefficient is set to 2.0. Therefore, the electrode density in high-risk areas is 2 electrodes per square meter. The electrode density in medium-risk areas is calculated by multiplying the base density by the medium-risk coefficient. The medium-risk coefficient is set to 1.2, resulting in an electrode density of 1.2 electrodes per square meter in medium-risk areas. The electrode density in low-risk areas is calculated by multiplying the base density by the low-risk coefficient. The low-risk coefficient is set to 0.6, resulting in an electrode density of 0.6 electrodes per square meter in low-risk areas. The setting of electrode density takes into account the attenuation characteristics of current transmission in deep-sea environments and the influence of seawater resistivity. The density calculation also needs to consider the overlapping coverage requirements of the effective protection radius of the electrodes to ensure that there are no blind spots in each area. The dynamic adjustment mechanism of density calculation modifies the density parameters according to the corrosion monitoring feedback in actual operation. When it is found that the protection effect of a certain area does not meet the standard, the electrode density of that area is appropriately increased.

[0042] The electrode allocation process multiplies the surface area of each zone by the corresponding electrode density to determine the total number of electrodes required for each zone. This allocation takes into account the standard electrode specifications and actual installation space constraints. The propeller blade area is calculated using 3D modeling software to accurately represent the complex curved surface of the blade, including the front, back, leading, and trailing edges. The calculated area is 3.5 square meters. Multiplying this by the high-risk electrode density of 2 per square meter yields a total of 7 electrodes required for the propeller blade area. The bearing seal area, including the cylindrical area of the bearing outer ring and the seal end area, is geometrically calculated to be 2.1 square meters. Multiplying this by the medium-risk electrode density of 1.2 per square meter yields a total of 3 electrodes required for the bearing seal area. This is rounded up to the nearest 3 electrodes to account for actual installation space constraints. The casing static area is the remaining area after subtracting the propeller and bearing areas from the regular surface of the propeller casing. This is calculated to be 8.0 square meters. Multiplying this by the low-risk electrode density of 0.6 per square meter yields a total of 5 electrodes required for the static area. This is rounded up to ensure complete coverage. The quantity allocation also needs to consider the backup redundancy of electrodes, adding a backup electrode to each area to deal with possible electrode failures during operation.

[0043] Optimizing electrode placement determines the optimal electrode location based on geometric characteristics and corrosion susceptibility analysis of each region. This optimization balances multiple factors, including protection effectiveness, installation feasibility, and ease of maintenance. Blade leading edge electrode placement optimization considers the complex stress distribution and fluid impact experienced by blades during rotation. Electrode installation is selected near the stagnation point on the blade leading edge, where flow velocity is relatively low and stress concentration is moderate. Blade leading edge electrodes are embedded, with the electrode tips flush with the blade surface to minimize impact on fluid dynamics. Electrode placement optimization around bearings is based on an analysis of key bearing seal locations. Electrodes are installed at equally spaced locations around the bearing outer ring to ensure uniform protection across the entire bearing seal area. Electrodes around bearings are distributed in a circular array, with three electrodes evenly spaced at 120-degree angles around the bearing outer ring. Optimizing the housing surface electrode placement utilizes a grid layout principle, dividing the housing surface into a regular rectangular grid and installing electrodes at the grid intersections. The housing surface electrode placement also needs to avoid the propeller's water inlet, drain, and other functional openings, while also considering accessibility for electrode maintenance and inspection. The location optimization algorithm uses a genetic algorithm to find the electrode location combination that optimizes the protection effect. The optimization goal is to minimize the maximum distance from any point to the nearest electrode in each area.

[0044] The connection path planning process determines the cable connection path between each electrode and the control unit. Path planning must consider requirements such as minimizing cable length, ensuring a safe and reliable path, and ensuring easy maintenance. The current transmission distance is calculated based on the three-dimensional distance between the electrode and control unit coordinates. The theoretical shortest path is calculated using the Euclidean distance formula. Practical path planning must consider the geometric constraints of the thruster structure. Cables cannot pass through moving parts or high-temperature areas and must be laid along fixed surfaces. The path planning algorithm uses the Dijkstra shortest path algorithm, modeling the thruster structure as a graph network. Nodes represent accessible locations, and edges represent cable path segments. The algorithm finds the shortest path from the electrode to the control unit. Cable path design also considers mechanical protection, including the addition of cable protective sleeves to sections of the path susceptible to impact and wear. The path planning results generate a cable routing diagram for each electrode, noting the cable's starting point, end point, intermediate nodes, and total length. Key locations requiring protective devices are also identified. Cable routing redundancy is implemented by configuring backup cable paths for critical electrodes. This allows for rapid failover to the backup path in the event of a failure in the primary path to maintain protection.

[0045] Layout integration comprehensively considers electrode location, number, configuration, and connection paths to develop a complete electrode layout plan and perform overall optimization. Layout integration begins by checking for interference between electrode locations to ensure installation conflicts and compatibility with other propeller components. The propeller blade area electrode layout integration considers dynamic balancing requirements during blade rotation. Seven electrodes are symmetrically distributed based on the number and angle of blades, with two electrodes installed on each blade's leading edge and one electrode at the blade's root. The bearing seal area electrode layout integration distributes three electrodes at equal angles on the bearing outer ring, with an angle of 120 degrees between them, forming a uniform annular protection array. The casing static area electrode layout integration utilizes a rectangular grid layout, with five electrodes arranged in two rows and three columns on the casing surface. Row and column spacing is determined by the casing dimensions and protection radius. Layout integration also considers electrode numbering and control circuit grouping, assigning functionally related electrodes to the same control circuit for centralized control and troubleshooting. The final layout plan generates detailed installation drawings, including complete information such as the electrode's three-dimensional coordinates, installation method, cable routing, control connections, and maintenance requirements.

[0046] In a specific embodiment, the process of executing step S104 may specifically include the following steps: The current density distribution parameters of each protection electrode are processed according to the spatial position to calculate the potential distribution, and the initial potential value of each point on the thruster surface is obtained; Based on the chloride ion concentration monitoring data, the initial potential value is corrected by concentration gradient to obtain the chloride ion concentration correction coefficient; Dynamically adjust the output current of each protection electrode according to the chloride ion concentration correction coefficient to obtain the adjusted electrode output current parameters; The adjusted electrode output current parameters are processed by potential field superposition calculation to obtain the reconstructed potential distribution on the thruster surface; Based on the reconstructed potential distribution on the thruster surface, the change of chloride ion concentration is responded to and regulated, and an adaptive protection potential field based on chloride ion concentration is obtained.

[0047] Specifically, the potential distribution calculation is based on the principle of potential field superposition in electrochemical theory. The potential fields generated by each guard electrode are mathematically superimposed in three-dimensional space to obtain the potential value at any point on the thruster surface. The potential distribution calculation uses the Green's function method to solve the Laplace equation. Each guard electrode is treated as a point current source, and the potential field it generates follows the point source potential distribution law. The spatial potential calculation takes into account factors such as the electrode's three-dimensional coordinates, output current intensity, seawater conductivity, and spatial distance. The potential value is directly proportional to the current intensity and inversely proportional to the distance. The numerical calculation of the potential distribution discretizes the thruster surface into triangular grid cells. The grid density is adaptively adjusted based on the degree of potential gradient change, with a denser grid used in areas with drastic potential changes. The potential value at each grid node is obtained by algebraically summing the potential contributions of all guard electrodes. This summation process takes into account the potential directionality and linearity of superposition. The potential distribution calculation also needs to consider the boundary conditions of the thruster metal material. The potential distribution on the metal surface is affected by the material's electrochemical properties and geometry. The calculation results of the initial potential values form a potential distribution map of the thruster surface. The potential map shows the potential height and gradient changes in each area, providing basic data for subsequent concentration correction and dynamic adjustment.

[0048] The concentration gradient correction process establishes a quantitative relationship between chloride ion concentration and potential correction based on the mechanism by which chloride ion concentration affects electrochemical reaction rates and potential distribution. Chloride ion concentration monitoring data comes from chloride ion selective electrode sensors distributed on the thruster surface. The monitoring data includes the chloride ion concentration value and spatial coordinate information for each monitoring point. The concentration gradient is calculated using the finite difference method, where the concentration difference between adjacent monitoring points is divided by the spatial distance to obtain the concentration gradient vector. The effect of chloride ion concentration on potential is based on the theoretical foundation of the Nernst equation, and the potential correction is proportional to the logarithm of the chloride ion concentration. The concentration correction coefficient is calculated using a piecewise function method. When the chloride ion concentration is lower than the standard seawater concentration, a negative correction coefficient indicates a need to lower the protection potential. When the chloride ion concentration is higher than the standard seawater concentration, a positive correction coefficient indicates a need to increase the protection potential. The numerical calculation formula for the correction coefficient is: the correction coefficient equals the concentration sensitivity parameter multiplied by the natural logarithm of the ratio of the chloride ion concentration to the standard concentration. The concentration sensitivity parameter is determined based on the metal material type and corrosion mechanism. Concentration gradient correction also needs to consider the spatial inhomogeneity of concentration distribution. The discrete monitoring point data are extended to the entire thruster surface through spatial interpolation method. The interpolation method uses Kriging interpolation algorithm to ensure spatial continuity and data accuracy.

[0049] Dynamic regulation adjusts the output current of each protection electrode in real time based on the chloride ion concentration correction factor. The regulation algorithm utilizes a proportional-integral-derivative controller to achieve precise current control. The electrode output current adjustment is calculated based on the correction factor and the electrode's current regulation range. The adjustment is equal to the correction factor multiplied by the electrode's rated current and the regulation gain factor. The proportional control term calculates the immediate adjustment based on the deviation between the current chloride ion concentration and the setpoint. The proportional gain factor is set based on the system's response speed requirements. The integral control term accumulates historical deviations to eliminate steady-state errors. The integral time constant is set based on the system's stability requirements. The differential control term calculates a predictive adjustment based on the rate of change of the chloride ion concentration. The differential time constant is set based on the system's overshoot suppression requirements. Dynamic regulation of the electrode output current also considers the physical limitations of the electrode, including maximum and minimum output currents and current change rate limits. The adjusted electrode output current parameters include each electrode's real-time current value, current change trends, and regulation status information. The parameter update frequency is set every minute to ensure timely response to changes in chloride ion concentration. A current regulation safety mechanism monitors the electrode's operating status and automatically limits current output and activates an alarm when an electrode overload or abnormality is detected.

[0050] The potential field superposition calculation process re-substitutes the adjusted output currents of each electrode into the potential distribution calculation model and solves the updated potential field distribution using numerical calculation methods. The potential field superposition uses the finite element method to establish a three-dimensional potential field model of the seawater region surrounding the thruster. The model boundary conditions include the current density boundary on the thruster surface and the zero potential boundary in the far field. The superposition calculation process first updates the current source intensity of each electrode and then re-solves the Poisson equation to obtain the new potential distribution. The calculation process uses an iterative solution method to obtain a converged potential field solution through stepwise approximation. The convergence criterion is that the potential difference between adjacent iterations is less than a set error threshold. The reconstructed potential distribution results show the potential changes in each region after adjustment. The potential distribution diagram intuitively reflects the spatial distribution characteristics of the potential field and the adjustment effect. Potential field superposition also needs to consider the spatial variation of seawater conductivity and the influence of temperature. The uneven distribution of conductivity can affect the distribution of the potential field. The accuracy and reliability of the reconstructed potential distribution are verified by comparing it with measured potential data.

[0051] The response control process establishes a closed-loop control relationship between the reconstructed potential distribution on the thruster surface and changes in chloride ion concentration, enabling dynamic optimization of the adaptive protective potential field. The response control algorithm monitors the potential values of each region in the reconstructed potential distribution and activates the control mechanism when the potential value deviates from the target protective potential. The target protective potential is set based on the optimal range between the corrosion potential and the overprotection potential of the metal material, with different target potentials set for different regions based on the corrosion risk level. The control process utilizes a model predictive control algorithm to predict future potential changes based on the current potential distribution and chloride ion concentration trends, adjusting the electrode output in advance to maintain a stable protective effect. The adaptive protective potential field is formed through continuous monitoring feedback and control adjustments, allowing the potential field distribution to automatically adapt to changes in chloride ion concentration. The adaptive nature of the potential field is reflected in its rapid response to environmental changes and automatic optimization of the protective effect. When the chloride ion concentration suddenly increases, the potential field automatically strengthens the protective strength, while when the concentration decreases, the potential field automatically weakens to save energy. The adaptive control learning mechanism continuously optimizes control parameters by accumulating operational data. The learning algorithm uses a neural network approach to establish a nonlinear mapping relationship between changes in chloride ion concentration and the optimal potential adjustment.

[0052] In a specific embodiment, the process of executing step S105 may specifically include the following steps: The adaptive protection potential field data and historical corrosion evolution data are compared in time series to obtain the characteristic parameters of corrosion development trend; The corrosion rate in the next 24 hours is predicted based on the long short-term memory network algorithm based on the characteristic parameters of the corrosion development trend to obtain the predicted corrosion rate value. The remaining protection time of each area is calculated and evaluated based on the predicted corrosion rate value, and the remaining protection time of the propeller blade area, the remaining protection time of the bearing seal area, and the remaining protection time of the casing static area are obtained; The remaining protection time is processed by particle swarm optimization algorithm to adjust the protection parameters and obtain the current density adjustment amount and potential adjustment amount; Based on the current density adjustment amount and the potential adjustment amount, output control processing is performed on each protection electrode to obtain protection parameter optimization instructions and perform anti-corrosion control.

[0053] Specifically, time series comparison processing systematically compares and analyzes current adaptive protection potential field data with stored historical corrosion evolution data to extract temporal patterns and trend characteristics of corrosion development. Adaptive protection potential field data includes parameters such as real-time potential values, potential change rates, potential fluctuation amplitudes, and potential distribution uniformity for each region. Data is collected hourly to form a continuous time series. Historical corrosion evolution data, derived from long-term corrosion monitoring records, includes information such as corrosion rate changes, corrosion depth development, corrosion area expansion, and corrosion morphology evolution. The data spans at least one year of operation. Time series comparison utilizes a dynamic time warping algorithm to match data at different time scales. The algorithm maximizes the similarity between the two time series by finding the optimal temporal correspondence. The comparison process identifies causal relationships between potential field changes and corrosion development, analyzing association patterns such as potential drop and corrosion acceleration, potential fluctuation and corrosion heterogeneity, and potential gradient and localized corrosion concentration. Corrosion trend characteristic parameters extracted include key indicators such as corrosion rate gradient, corrosion acceleration, the frequency and amplitude of periodic corrosion fluctuations, and the spatial propagation speed of corrosion development. The numerical representation of characteristic parameters uses statistical methods to calculate statistical characteristics such as mean, variance, skewness and kurtosis, and the frequency domain analysis method is used to extract the periodic characteristics and spectral characteristics of corrosion development.

[0054] The Long Short-Term Memory (LSTM) network algorithm, a neural network architecture specialized for processing time series data in deep learning, is capable of learning long-term dependencies and processing sequential patterns of change. The network structure consists of an input layer, multiple layers of LSTM units, and an output layer. The input layer receives time series data of corrosion trend characteristic parameters, with each time step containing a multidimensional feature vector. The LSTM units control the flow of information through a gating mechanism consisting of input, forget, and output gates. The input gate determines which new information is stored in the cell state, the forget gate determines which old information is discarded, and the output gate determines which part of the cell state is output. The network training process uses historical corrosion data to establish a mapping between characteristic parameters and future corrosion rates. The training data includes examples of corrosion evolution under different marine environmental conditions. The training algorithm uses backpropagation through time, and the loss function is the mean squared error between the predicted and actual corrosion rates. Network hyperparameters include three hidden layers, 128 neurons per layer, a learning rate of 0.001, and a batch size of 32 samples. The prediction process inputs the characteristic parameters of the corrosion development trend in the current 24 hours into the trained network model, and the network outputs the predicted corrosion rate values of each area in the next 24 hours. The prediction accuracy reaches more than 85% through cross-validation evaluation.

[0055] The remaining protection time (RPT) calculation and assessment is based on the predicted corrosion rate and the current status of the protection system to determine the remaining time each area can maintain effective protection under existing protection conditions. This calculation is based on the corrosion allowance divided by the predicted corrosion rate. The corrosion allowance is the remaining thickness of the protective coating or the allowable corrosion depth of the metal substrate. The corrosion allowance for the propeller blade area, measured using an ultrasonic thickness gauge, shows a current residual thickness of 0.8 mm. The predicted corrosion rate is 0.02 mm / hour, resulting in a calculated RPT of 40 hours. The corrosion allowance for the bearing seal area, taking into account sealing performance requirements, has a maximum allowable corrosion depth of 0.3 mm. The predicted corrosion rate is 0.015 mm / hour, resulting in a calculated RPT of 20 hours. The corrosion allowance for the static area of the casing, based on structural strength requirements, has a permissible corrosion depth of 1.2 mm. The predicted corrosion rate is 0.008 mm / hour, resulting in a calculated RPT of 150 hours. The RPT calculation also takes into account the uncertainty and prediction error of the corrosion rate. Monte Carlo simulation is used to assess the confidence interval of the predicted results. The introduction of a safety factor multiplies the calculated remaining protection time by a factor of 0.8, ensuring reliable protection despite forecast errors and environmental changes. The remaining protection time is dynamically updated every six hours based on real-time monitoring data and changes in forecast results.

[0056] The particle swarm optimization algorithm, simulating the intelligent behavior of foraging birds, is used to find the optimal protection parameter adjustment plan to extend the remaining protection time and optimize protection effectiveness. The algorithm initializes the swarm to 50 particles, each representing a set of protection parameter adjustment plans, including current density and potential adjustments for each region. The particle position vector contains 15 dimensions, corresponding to parameters such as current density and potential adjustments for five regions, as well as adjustment timing. The fitness function is designed to comprehensively consider multiple objectives, including remaining protection time extension, energy consumption increase, and system stability. The function is expressed as the remaining protection time weight multiplied by the time extension minus the energy consumption weight multiplied by the energy consumption increase minus the stability weight multiplied by the system fluctuation. Particle velocity updates use the standard particle swarm algorithm formula, which includes an inertia term, an individual optimal term, and a global optimal term. The inertia weight is set to 0.9 to indicate the degree of maintenance of the current motion direction, and the learning factor is set to 2.0 to indicate the intensity of learning towards the optimal solution. Position updates are obtained by adding the velocity vector to the current position vector to obtain the new position. Position bounds ensure that the adjustment parameters remain within a reasonable range. The optimization process continues for 100 generations, and the global optimal solution is selected through fitness evaluation as the final protection parameter adjustment plan. The adjustment plan output includes a current density adjustment, which represents the required increase or decrease in current output at each electrode, and a potential adjustment, which represents the adjustment range of the target protection potential in each area.

[0057] The output control process converts the adjustment parameters derived from particle swarm optimization into specific electrode control instructions, enabling precise regulation of the output current and potential of each protection electrode. Current density adjustment is implemented by adjusting the output current of each electrode through a current controller, with an adjustment accuracy of 1 mA and a response time of less than 5 seconds. Potential adjustment is implemented by adjusting the electrode's operating potential setpoint, with a potential control accuracy of 1 mV and a control stability error of less than 2%. Protection parameter optimization instructions include detailed information such as the adjustment target value, adjustment rate, adjustment sequence, and safety limits. The instruction format utilizes a standardized digital communication protocol to ensure accurate interpretation and execution of the control system. A step-by-step adjustment strategy is employed during execution to prevent sudden parameter changes from impacting system stability. Each adjustment is limited to within 10% of the target value. The closed-loop feedback loop for corrosion control verifies the execution of optimization instructions by real-time monitoring the protection effectiveness of the adjusted parameters. A secondary optimization adjustment is initiated if the adjustment does not meet expectations. The control system's fault protection mechanism monitors the operating status of each electrode and automatically switches to a backup electrode or safety mode when an electrode failure or anomaly is detected, ensuring continuous and reliable corrosion protection.

[0058] The above describes the anti-corrosion protection method for a propeller under a deep-sea environment in the embodiment of the present application. The following describes the anti-corrosion protection system for a propeller under a deep-sea environment in the embodiment of the present application. Figure 2 In the embodiment of the present application, an embodiment of the propeller anti-corrosion protection system in a deep-sea environment includes: The acquisition module is used to collect and process real-time data of the seawater around the deep-sea thruster through a corrosion monitoring sensor array to obtain an environmental corrosion data set containing chloride ion concentration, dissolved oxygen concentration, pH value, and corrosion potential; a grading module, configured to perform corrosion risk grading calculation processing on the propeller surface using a genetic algorithm based on the environmental corrosion data set, and obtain corrosion risk levels for the propeller blade area, the bearing seal area, and the casing static area; A distribution module, configured to perform current distribution optimization processing on the corrosion risk level using a Lagrangian algorithm to obtain current density distribution parameters of each protective electrode; A control module is used to reconstruct and control the surface potential field of the thruster according to the current density distribution parameters of each protection electrode to obtain an adaptive protection potential field based on the chloride ion concentration; The analysis module is used to perform corrosion trend analysis on the adaptive protection potential field through a prediction model, obtain protection parameter optimization instructions and execute anti-corrosion control.

[0059] above Figure 2The thruster anti-corrosion protection system in the medium and deep sea environment in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The thruster anti-corrosion protection equipment in the deep sea environment in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0060] Reference Figure 3 In an embodiment of the present invention, a propeller anti-corrosion protection device in a deep-sea environment is also provided. The propeller anti-corrosion protection device in a deep-sea environment can be a server, and its internal structure can be as follows: Figure 3 As shown. The thruster anti-corrosion protection device in the deep-sea environment includes a processor, a memory, a display screen, an input device, a network interface and a database connected via a system bus. Among them, the computer-designed processor is used to provide computing and control capabilities. The memory of the thruster anti-corrosion protection device in the deep-sea environment includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the thruster anti-corrosion protection device in the deep-sea environment is used to store the corresponding data in this embodiment. The network interface of the thruster anti-corrosion protection device in the deep-sea environment is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0061] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the thruster corrosion protection equipment in the deep-sea environment to which the solution of the present invention is applied.

[0062] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the steps of the method for protecting the propeller from corrosion in a deep-sea environment.

[0063] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0064] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a thruster corrosion protection device in a deep-sea environment (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0065] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for protecting a propeller from corrosion in a deep-sea environment, characterized in that: The method comprises: The corrosion monitoring sensor array collects and processes real-time data of the seawater around the deep-sea thruster to obtain an environmental corrosion dataset containing chloride ion concentration, dissolved oxygen concentration, pH value, and corrosion potential. Performing corrosion risk classification calculation on the propeller surface using a genetic algorithm based on the environmental corrosion data set to obtain corrosion risk levels for the propeller blade area, the bearing seal area, and the housing static area; The corrosion risk level is subjected to current distribution optimization processing using a Lagrangian algorithm to obtain current density distribution parameters of each protective electrode; The thruster surface potential field is reconstructed and regulated according to the current density distribution parameters of each protection electrode to obtain an adaptive protection potential field based on chloride ion concentration. The adaptive protection potential field is subjected to corrosion trend analysis and processing through a prediction model to obtain protection parameter optimization instructions and perform anti-corrosion control.

2. The method for anti-corrosion protection of a propeller in a deep-sea environment according to claim 1, characterized in that: The corrosion monitoring sensor array is used to collect and process real-time data of the seawater surrounding the deep-sea thruster to obtain an environmental corrosion data set containing chloride ion concentration, dissolved oxygen concentration, pH value and corrosion potential, including: The chloride ion selective electrode sensor, dissolved oxygen fluorescence sensor, pH glass electrode sensor and corrosion potential reference electrode sensor are deployed at key positions on the thruster surface according to a preset array layout; The data of each sensor is read and processed based on a 30-second time interval to obtain the original values of chloride ion concentration, dissolved oxygen concentration, pH value and corrosion potential; Inputting the original values of chloride ion concentration, dissolved oxygen concentration, pH value and corrosion potential into a data preprocessing module for filtering and calibration processing to obtain chloride ion concentration calibration data, dissolved oxygen concentration calibration data, pH value calibration data and corrosion potential calibration data; performing outlier elimination processing on the chloride ion concentration calibration data, the dissolved oxygen concentration calibration data, the pH value calibration data, and the corrosion potential calibration data to obtain effective corrosion parameter data; The effective corrosion parameter data are combined and processed according to a time series to obtain the environmental corrosion data set.

3. The method for anti-corrosion protection of a propeller in a deep-sea environment according to claim 1, characterized in that: The corrosion risk classification calculation and processing of the propeller surface is performed by a genetic algorithm based on the environmental corrosion data set to obtain the corrosion risk levels of the propeller blade area, the bearing seal area, and the casing static area, including: Performing regional mapping processing on the environmental corrosion data set according to the propeller geometry to obtain partition parameters of the propeller blade area, the bearing seal area, and the casing static area; Performing environmental correction processing on the partition parameters based on the pressure correction coefficient to obtain corrected corrosion parameters; The risk index of each area is obtained by performing weighted sum calculation on chloride ion concentration, dissolved oxygen concentration, pH value and stress factor; Performing population initialization and fitness evaluation processing on the risk index according to a genetic algorithm to obtain a weight parameter; The risk index is graded based on the weight parameters to obtain the corrosion risk grades of the propeller blade area, the bearing seal area, and the casing static area.

4. The method for anti-corrosion protection of a propeller in a deep-sea environment according to claim 1, characterized in that: The corrosion risk level is subjected to current distribution optimization processing using a Lagrangian algorithm to obtain current density distribution parameters of each protective electrode, including: The number of protective electrodes is configured according to the corrosion risk level to obtain a layout plan of electrodes in the propeller blade area, electrodes in the bearing seal area, and electrodes in the casing stationary area; Performing electrode weight distribution processing on the layout plan according to the regional risk level to obtain electrode weights in high-risk areas, medium-risk areas, and low-risk areas; Based on the corrosion risk level of each area, the protection area is allocated and calculated to obtain the area of high-risk area, medium-risk area and low-risk area; Performing a current constraint solving process using a Lagrange multiplier method according to the protection area to obtain a distribution coefficient that satisfies a total current conservation condition; The distribution coefficient is multiplied by the area of each region to obtain the current density distribution parameter of each protective electrode.

5. The method for anti-corrosion protection of a propeller in a deep-sea environment according to claim 4, characterized in that: The number of protective electrodes is configured according to the corrosion risk level to obtain a layout plan of the propeller blade area electrodes, the bearing seal area electrodes, and the casing static area electrodes, including: The electrode density of the corrosion risk level is calculated according to the risk degree to obtain the electrode density of the high risk area, the electrode density of the medium risk area and the electrode density of the low risk area; Performing electrode quantity allocation processing on the surface area of each region according to the electrode density to obtain the number of electrodes in the propeller blade region, the number of electrodes in the bearing seal region, and the number of electrodes in the housing static region; Based on the geometric characteristics of each area, the electrode positions are optimized and distributed to obtain the electrode positions at the leading edge of the blade, around the bearing, and on the surface of the casing. The electrode positions are processed for connection path planning according to the current transmission distance to obtain the cable connection path of each electrode; The electrodes are finally layout-integrated according to the cable connection path to obtain a layout scheme for the propeller blade area electrodes, the bearing seal area electrodes, and the casing static area electrodes.

6. The method for anti-corrosion protection of a propeller in a deep-sea environment according to claim 1, characterized in that: The reconstructing and regulating the propeller surface potential field according to the current density distribution parameters of each protection electrode to obtain an adaptive protection potential field based on chloride ion concentration includes: Performing potential distribution calculation on the current density distribution parameters of each protective electrode according to the spatial position to obtain the initial potential value of each point on the thruster surface; Performing concentration gradient correction processing on the initial potential value based on the chloride ion concentration monitoring data to obtain a chloride ion concentration correction coefficient; Dynamically adjusting the output current of each protective electrode according to the chloride ion concentration correction coefficient to obtain an adjusted electrode output current parameter; The adjusted electrode output current parameters are processed by potential field superposition calculation to obtain a reconstructed potential distribution on the thruster surface; Based on the reconstructed potential distribution on the thruster surface, a response control process is performed on the change in chloride ion concentration to obtain the adaptive protection potential field based on chloride ion concentration.

7. The method for anti-corrosion protection of a propeller in a deep-sea environment according to claim 1, characterized in that: The method of performing corrosion trend analysis on the adaptive protection potential field through a prediction model, obtaining protection parameter optimization instructions and executing anti-corrosion control includes: Performing time series comparison processing on the adaptive protection potential field data and historical corrosion evolution data to obtain characteristic parameters of corrosion development trend; Based on the long short-term memory network algorithm, the corrosion rate of the corrosion development trend characteristic parameters in the next 24 hours is predicted to obtain a predicted corrosion rate value; Calculating and evaluating the remaining protection time of each area based on the predicted corrosion rate value to obtain the remaining protection time of the propeller blade area, the remaining protection time of the bearing seal area, and the remaining protection time of the casing static area; The remaining protection time is processed by a particle swarm optimization algorithm to adjust the protection parameters to obtain a current density adjustment amount and a potential adjustment amount; Based on the current density adjustment amount and the potential adjustment amount, output control processing is performed on each protection electrode to obtain the protection parameter optimization instruction and perform anti-corrosion control.

8. A propeller anti-corrosion protection system in a deep-sea environment, characterized in that: For implementing the method for protecting a propeller against corrosion in a deep-sea environment according to any one of claims 1 to 7, the propeller against corrosion in a deep-sea environment comprises: The acquisition module is used to collect and process real-time data of the seawater around the deep-sea thruster through a corrosion monitoring sensor array to obtain an environmental corrosion data set containing chloride ion concentration, dissolved oxygen concentration, pH value, and corrosion potential; a grading module, configured to perform corrosion risk grading calculation processing on the propeller surface using a genetic algorithm based on the environmental corrosion data set, and obtain corrosion risk levels for the propeller blade area, the bearing seal area, and the casing static area; A distribution module, configured to perform current distribution optimization processing on the corrosion risk level using a Lagrangian algorithm to obtain current density distribution parameters of each protective electrode; A control module is used to reconstruct and control the surface potential field of the thruster according to the current density distribution parameters of each protection electrode to obtain an adaptive protection potential field based on the chloride ion concentration; The analysis module is used to perform corrosion trend analysis on the adaptive protection potential field through a prediction model, obtain protection parameter optimization instructions and execute anti-corrosion control.

9. A propeller anti-corrosion protection device in a deep sea environment, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the method for anti-corrosion protection of a thruster in a deep-sea environment according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the processor is caused to execute the propeller anti-corrosion protection method in a deep-sea environment according to any one of claims 1 to 7.

Images