Marine pH value detection and analysis method and system

Abstract

The invention discloses an ocean pH value detection and analysis method and system, and relates to the field of ocean pH value detection.The analysis method comprises the steps that ocean areas are divided, seawater samples in all the ocean areas are obtained, the seawater samples react with a sensitive indicator, the absorbance ratio is measured through a spectrophotometric method, and the seawater pH value in all the ocean areas is detected; predicting the oxygen generation capacity of the seaweeds based on the data of the seaweeds in each region of the ocean, and analyzing the change trend of the pH value of the seawater in each region of the ocean in a set time period according to the prediction result and the illumination intensity change; building an electrochemical impedance test model, analyzing the corrosion behavior of the nano coating in each region of the ocean by taking the change trend of the pH value of the seawater as a test condition, and determining a target installation and arrangement path of the underwater pipeline. According to the method, the oxygen generation capacity of the seaweed is predicted according to the seaweed data and the illumination intensity change, the influence of the oxygen generation capacity on the seawater pH value is analyzed, and prediction support is provided for dynamic change of a marine ecosystem.

Description

Technical Field

[0001] The present invention relates to the field of ocean pH value detection, and in particular to an ocean pH value detection and analysis method and system. Background Art

[0002] The pH value of seawater is the core parameter for measuring the acidity and alkalinity of the ocean. It is directly related to the dynamic regulation of the carbonate balance system and the ocean carbon cycle. It reflects the acidification process that occurs after the ocean absorbs atmospheric CO2. The detection of ocean pH value is an important means to assess the degree of ocean acidification and ecological and environmental changes. Among them, electroanalysis and electrochemical techniques play a key role in this detection process. The electrochemical method is widely used because of its high sensitivity, fast response, ease of automation and real-time monitoring. Electrochemical measurement usually uses glass electrodes or solid-state electrodes. Its core principle is to infer the pH value by measuring the change in the electrode's potential response to hydrogen ions in seawater, which conforms to the Nernst equation.

[0003] However, the existing marine pH detection technology cannot effectively predict the changing trend of pH value during application, so the detection results will remain in a static or instantaneous state, lacking the ability to make forward-looking judgments on the dynamic evolution of the marine environment. In addition, due to the lack of the ability to predict the pH changing trend, it is impossible to dynamically predict the corrosion response of facility structures in the ocean, resulting in high corrosion of marine facility structures in a short period of time, which reduces the maintenance of marine infrastructure.

[0004] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0005] In response to the problems in the related art, the present invention proposes a method and system for detecting and analyzing ocean pH values ​​to overcome the above-mentioned technical problems existing in the existing related art.

[0006] To this end, the specific technical solutions adopted in the present invention are as follows:

[0007] In a first aspect, the present invention provides a method for detecting and analyzing ocean pH, the method comprising:

[0008] Divide the ocean into regions, obtain seawater samples from each region, react the seawater samples with sensitive indicators, use photometry to measure the absorbance ratio, and detect the pH value of seawater in each region of the ocean;

[0009] Based on the seaweed data in various ocean regions, the oxygen production capacity of seaweed is predicted. The pH value trend of seawater in various ocean regions during a set period is analyzed based on the predicted results and changes in light intensity.

[0010] An electrochemical impedance spectroscopy (EIS) test model was constructed, and the pH trend of seawater was used as the test condition to analyze the corrosion behavior of the nanocoating in various areas of the ocean, and to determine the target installation and arrangement path of the underwater pipeline.

[0011] Preferably, dividing the ocean into regions, obtaining seawater samples from each ocean region, reacting the seawater samples with a sensitive indicator, and measuring the absorbance ratio using a photometric method to detect the pH value of seawater in each ocean region includes:

[0012] Divide the ocean test area into several square grids, map the sea level height and ocean depth data into the grids, and calculate the average ocean depth and height of each grid in the initial test area;

[0013] Grids with average depth and height less than the target values ​​are eliminated to obtain the final ocean state distribution map. The clustering algorithm is used to determine the target number of clusters and the ocean test area is divided according to height and depth characteristics.

[0014] Collect seawater samples from various areas of the ocean, select sensitive indicators and mix them into the seawater samples for reaction, and use a photometer to analyze the absorbance of the seawater samples at a specific wavelength;

[0015] The absorbance ratio of marine samples is calculated based on the absorbance, and the absorbance ratio is mapped to the standard pH curve to determine the pH value of seawater in various areas of the ocean.

[0016] Preferably, the oxygen production capacity of seaweed is predicted based on seaweed data in various ocean regions, and the pH value change trend of seawater in various ocean regions during a set period of time is analyzed based on the prediction results and changes in light intensity, including:

[0017] Based on the mean clustering technology, historical operation correlation data is classified and the sample space is output. Then, based on the optimization algorithm and the sample space, the optimal weight solution is selected and a wavelet neural network prediction model is constructed.

[0018] The wavelet neural network prediction model was used to establish the mapping relationship between algae quantity and organic matter production, and the linear relationship between algae quantity and organic matter conversion rate was analyzed based on the mapping relationship.

[0019] Based on the linear relationship results, the oxygen production capacity is analyzed. At the same time, the seaweed distribution and biomass data of each area of ​​the ocean are extracted and input into the wavelet neural network prediction model to predict the oxygen production capacity of the seaweed.

[0020] The changes in light intensity in various ocean regions within a set time period are obtained and combined with the predicted results of oxygen production capacity to analyze the formation trend of carbonic acid in various ocean regions. The trend of seawater pH changes is determined based on the analysis results.

[0021] Preferably, the historical operation correlation data is classified based on the mean clustering technology, the sample space is output, and the optimal solution of the weight is screened based on the optimization algorithm and the sample space, and the wavelet neural network prediction model is constructed, including:

[0022] Extract seaweed chlorophyll concentration and seaweed biomass as sample data based on historical operation correlation data, and define the number of cluster groups to analyze the Euclidean distance between sample data and cluster centers;

[0023] Classify the sample data based on the Euclidean distance to obtain the sample space, and use the sample space to measure the clustering effect. Repeat the classification of the sample data according to the measurement results until the target sample space is obtained;

[0024] The structural parameters of the wavelet neural network are set to train the wavelet neural network. Based on the training results, the optimization algorithm and the target sample space are used to screen the optimal solution of the wavelet neural network to construct a seaweed organic matter relationship prediction model.

[0025] Preferably, obtaining the change in light intensity in each ocean region within a set time period, combining it with the oxygen production capacity prediction result, analyzing the formation trend of carbonic acid in each ocean region, and judging the change trend of seawater pH based on the analysis result includes:

[0026] The light intensity change value within a set period is obtained and combined with the oxygen production capacity prediction result to generate sensitive characteristic parameters as the input of the integrated learning model, and the photosynthesis intensity inversion model is established using historical data;

[0027] The carbon dioxide fixation capacity sequence of the seaweed is used as the output to obtain the mapping relationship between the light intensity change value and the oxygen production capacity, and the carbon dioxide fixation capacity of the seaweed, and output the real-time fixation capacity sequence;

[0028] Modal decomposition technology is used to decompose the real-time fixed capacity sequence into modal components. Based on the modal components, a trend prediction model is constructed using the attention memory network mechanism to analyze the reaction trend between carbon dioxide and seawater calcium ions.

[0029] The prediction results of each modal component are superimposed to deduce the formation rate and concentration change of carbonic acid, determine the formation trend of carbonic acid in various ocean regions, and judge the decreasing trend of carbon dioxide concentration based on the formation trend, and analyze the change trend of seawater pH.

[0030] Preferably, an electrochemical impedance spectroscopy (EIS) test model is constructed, and the pH trend of seawater is used as a test condition to analyze the corrosion behavior of the nanocoating in various areas of the ocean, and to determine the target installation arrangement path of the underwater pipeline, including:

[0031] The temperature and salinity of different sea areas are obtained through marine environmental monitoring data, combined with the pH change trend as test input conditions, and the test input conditions are standardized;

[0032] An experimental system was designed based on electrochemical impedance spectroscopy (EIS) technology. The test input conditions were used as variables, and impedance testing was performed on nano-coating materials for underwater pipelines to obtain impedance spectrum data on the changing trends of the nano-coating under seawater pH.

[0033] Combining impedance spectroscopy data with the equal-dimensional gray number recursive filling technique, a coating barrier performance prediction model was constructed. Based on the coating barrier performance prediction results, the corrosion behavior of nano-coatings in various marine areas was analyzed.

[0034] After numbering each ocean area according to its corrosion behavior, it performs convex segmentation and constructs an ocean topology map. The ocean topology map is processed and the locations where the corrosion behavior meets the target requirements are output as the target installation locations of the underwater pipeline.

[0035] Preferably, the impedance spectrum data is combined with the equal-dimensional gray number complementation technology to construct a coating barrier performance prediction model, and based on the coating barrier performance prediction results, the corrosion behavior of the nanocoating in various marine areas is analyzed, including:

[0036] Based on the impedance spectrum data, a grey prediction model is constructed to implement the initial prediction, output the coating barrier performance evaluation results, remove the first item in the impedance spectrum data, and add the coating barrier performance evaluation results to the last item of the impedance spectrum data to update the impedance spectrum data and obtain the initial sequence;

[0037] A supplementary prediction model is constructed based on the primary sequence to implement secondary prediction, output the secondary evaluation results of the coating barrier performance, remove the first item in the primary sequence, and add the secondary evaluation results of the coating barrier performance to the last item of the primary sequence to update the primary sequence to obtain the supplementary sequence;

[0038] The performance prediction model is constructed three times according to the complement sequence to implement three predictions, and the three evaluation results of the coating barrier performance are output. The prediction accuracy of the three evaluation results of the coating barrier performance is determined, and the update process is repeated based on the prediction accuracy until the accuracy of the performance prediction model meets the target requirements;

[0039] Based on the prediction results of the coating barrier performance, the damage points generated on the surface of the nanocoating during the contact between the nanocoating and seawater are analyzed, and the corrosion behavior of the nanocoating in various areas of the ocean is judged.

[0040] Preferably, after numbering each ocean area according to the corrosion behavior, a convex subdivision process is performed and an ocean topology map is constructed. The ocean topology map is processed to output location points where the corrosion behavior meets the target requirements as target installation location points of the underwater pipeline, including:

[0041] Based on the corrosion behavior of nano-coatings, the marine areas are divided into corrosion levels, each marine area is assigned a unique number, and the regional numbers are spatially displayed through a visual graph to form a regional classification map;

[0042] Convex subdivision is performed on the regional classification map to establish an ocean topology map. Based on the ocean topology map, a search heuristic algorithm is used to generate initial location points whose corrosion behavior meets the target requirements.

[0043] The elastic band algorithm is used to optimize the initial position points to obtain the local target position points, and the initial tree is constructed based on the ocean topology map. The dynamic sampling domain is constructed by combining the segmentation line constraint and the informed constraint set.

[0044] Based on the dynamic sampling domain optimization of the initial tree, the local target location points are adjusted to generate target location points whose corrosion behavior meets the target requirements. The target location points are used as the target installation location points of the underwater pipeline.

[0045] Preferably, the expression of the informed constraint set is:

[0046]

[0047] Where, Denotes the subconvex subdivision process and the process parameter d proc The set of location points that meet the heuristic optimization criteria is: a represents the sampling point of the ocean topology map, A area represents the free space in the ocean topology, a start represents the initial position point, a end represents the local target location point, f(c / b) represents the ratio of the c-th branch point to the total branch points b in the initial tree structure, and f(c-1 / b) represents the ratio of the c-1-th branch point to the total branch points b in the initial tree structure.

[0048] In a second aspect, the present invention further provides an ocean pH value detection and analysis system, the analysis system comprising:

[0049] The seawater pH detection module is used to divide the ocean into regions, obtain seawater samples from each region, react the seawater samples with a sensitive indicator, and use photometry to measure the absorbance ratio to detect the pH value of seawater in each region of the ocean;

[0050] The pH trend prediction module is used to predict the oxygen production capacity of seaweed based on the seaweed data in various ocean areas, and analyze the pH trend of seawater in various ocean areas during a set period of time based on the prediction results and changes in light intensity;

[0051] The corrosion behavior analysis module is used to build an electrochemical impedance spectroscopy (EIS) test model, using the pH trend of seawater as a test condition to analyze the corrosion behavior of nanocoatings in various ocean regions and determine the target installation and arrangement paths for underwater pipelines.

[0052] The beneficial effects of the present invention are:

[0053] 1. The present invention divides the ocean into regions and collects seawater samples, combining sensitive indicators with photometry to determine absorbance ratios. This allows for precise monitoring of seawater pH in each region. Simultaneously, the oxygen production capacity of seaweed is predicted based on seaweed data and changes in light intensity, and its impact on seawater pH is analyzed, providing predictive support for dynamic changes in marine ecosystems. Furthermore, the corrosion behavior of nanocoatings is analyzed using an electrochemical impedance spectroscopy (EIS) test model combined with seawater pH change trends. This provides a reliable basis for corrosion protection of underwater pipelines, optimizes pipeline layout, and avoids the formation of high-corrosion areas in the ocean, greatly enhancing the scientific nature and efficiency of marine ecological protection, environmental monitoring, and infrastructure maintenance.

[0054] 2. The neural network model constructed by the present invention using mean clustering technology can accurately capture the nonlinear mapping relationship between seaweed production and organic matter production. By further analyzing the linear correlation between its conversion rate and oxygen release, the oxygen production capacity of each region can be accurately predicted. At the same time, combined with the dynamic change data of light intensity within a set time period, the reaction trend of carbon dioxide and calcium ions in seawater is further analyzed, the carbonic acid formation rate is deduced, and finally the changing trend of pH value in each region is determined. This not only improves the real-time prediction of ocean pH value, but also lays the foundation for the formulation of environmental intervention measures.

[0055] 3. The present invention tests the performance of nano-coating materials under different environments based on an electrochemical impedance spectroscopy experimental system and obtains its impedance spectrum data, which provides a quantitative basis and high-resolution experimental foundation for analyzing the corrosion behavior of the coating under real marine conditions. The impedance spectrum data is combined with the equal-dimensional gray number supplementation technology to achieve accurate prediction of the corrosion trend of the nano-coating in different sea areas, thereby improving the scientific nature of pipeline service life management. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 This is a flow chart of a method for detecting and analyzing ocean pH values ​​according to an embodiment of the present invention;

[0058] Figure 2 This is a principle block diagram of a system for detecting and analyzing ocean pH values ​​according to an embodiment of the present invention.

[0059] In the picture:

[0060] 1. Seawater pH value detection module; 2. pH value trend prediction module; 3. Corrosion behavior analysis module. DETAILED DESCRIPTION

[0061] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention. They are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. By referring to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and the advantages of the present invention.

[0062] According to an embodiment of the present invention, a method and system for detecting and analyzing ocean pH values ​​are provided.

[0063] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the ocean pH value detection and analysis method of an embodiment of the present invention, the analysis method includes:

[0064] Step S1, divide the ocean into regions, obtain seawater samples in each ocean region, react the seawater samples with a sensitive indicator, measure the absorbance ratio using photometry, and detect the pH value of seawater in each ocean region.

[0065] In one embodiment, when dividing the ocean area, obtaining seawater samples in each ocean area, reacting the seawater samples with a sensitive indicator, determining the absorbance ratio by photometry, and detecting the pH value of seawater in each ocean area, the ocean test area can be divided into a number of square grids, and the sea level height and ocean depth data are mapped into the grids, and the average ocean depth and height of each grid in the initial test area are calculated; grids with average depths and heights less than target values ​​are eliminated to obtain a final ocean state distribution map, and the number of target clusters is determined by a clustering algorithm, and the ocean test area is divided according to height and depth characteristics; seawater samples in each ocean area are collected, and a sensitive indicator is selected and mixed into the seawater samples for reaction, and the absorbance of the seawater samples at a specific wavelength is analyzed by a photometer; the absorbance ratio of the ocean samples is calculated based on the absorbance, and the absorbance ratio is mapped to a standard pH value curve to determine the pH value of seawater in each ocean area.

[0066] It should be explained that in the process of detecting the pH value of seawater, the ocean area to be detected must first be gridded on a two-dimensional plane, for example, divided into 100×100 square grids, each grid represents a sea unit, and its spatial scale can be set to 1km×1km or finer granularity according to actual conditions. In each grid unit, the sea level height and the maximum water depth at that location are obtained, and the average ocean height and average depth of each grid are obtained by averaging over multiple time periods.

[0067] For example, assuming that the observed sea level height data in a certain grid is (1.8, 2.0, 1.9) meters and the depth data is (12, 14, 3) meters, then the average height of the grid is 1.9 meters and the average depth is 13 meters. At the same time, target standards are set, such as the average depth is not less than 10 meters and the average height is not less than 1.5 meters. After eliminating the grid cells that do not meet the conditions, a valid ocean area map that meets the basic physical conditions is obtained, and a clustering algorithm is applied to the valid grids (specifically, K-means or DBSCAN can be used), and an appropriate cluster number k value is selected (determined by the silhouette coefficient or elbow method, such as k = 4). The ocean area is classified according to the two characteristics of average depth and height, and several areas with obvious structural differences are divided.

[0068] Representative grids are selected in each cluster area to collect seawater samples. Each sample needs to be collected in a clean glass bottle and marked with location coordinates and depth information to avoid cross contamination. Sensitive indicators are added to each sample in the laboratory. pH-sensitive dyes such as phenolphthalein and bromophenol blue are commonly used. Their color and light absorption characteristics are different at different pH values. After sufficient reaction, the samples are measured using a photometer. Usually, a cuvette is selected to load the sample. The absorbance values ​​A1 and A2 are measured at specific wavelengths such as 550nm or 620nm. For example, A1=0.30, A2=0.50, then the absorbance ratio is A1 / A2=0.60. According to the standard pH absorbance curve of the indicator, the absorbance ratio is mapped to the corresponding pH value, for example, 0.60 corresponds to pH=7.8. After measuring the samples in each area one by one in this way, a pH spatial distribution map of the entire ocean area can be established to achieve quantitative monitoring of the acidity and alkalinity of seawater in different sea areas.

[0069] Step S2: predicting the oxygen production capacity of seaweed based on the seaweed data in each ocean area, and analyzing the pH value change trend of seawater in each ocean area during a set period of time according to the prediction results and the change of light intensity.

[0070] In one embodiment, in the process of predicting the oxygen production capacity of seaweed based on seaweed data in various ocean regions, and analyzing the trend of seawater pH value changes in various ocean regions during a set period of time based on the prediction results and changes in light intensity, historical operation correlation data can be classified based on mean clustering technology, and the sample space can be output. The optimal solution of weights can be screened based on the optimization algorithm and the sample space to construct a wavelet neural network prediction model; the wavelet neural network prediction model is used to establish a mapping relationship between seaweed amount and organic matter generation, and the linear relationship between seaweed amount and organic matter conversion rate is analyzed based on the mapping relationship; the oxygen production capacity is analyzed based on the linear relationship results, and the seaweed data on seaweed distribution and biomass in various ocean regions are extracted and input into the wavelet neural network prediction model to predict the oxygen production capacity of seaweed; the changes in light intensity in various ocean regions during a set period of time are obtained, and combined with the oxygen production capacity prediction results, the formation trend of carbonic acid in various ocean regions is analyzed, and the trend of seawater pH changes is judged based on the analysis results.

[0071] Among them, the historical operation correlation data is classified based on the mean clustering technology, the sample space is output, and the optimal solution of the weight is screened based on the optimization algorithm and the sample space, and the wavelet neural network prediction model is constructed, including: extracting the seaweed chlorophyll concentration and seaweed biomass as sample data according to the historical operation correlation data, and defining the number of cluster groups to analyze the Euclidean distance between the sample data and the cluster center; classifying the sample data based on the Euclidean distance to obtain the sample space, and using the sample space to measure the clustering effect, and repeatedly classifying the sample data according to the measurement results until the target sample space is obtained; setting the structural parameters of the wavelet neural network to train the wavelet neural network, and based on the training results, using the optimization algorithm and the target sample space to screen the optimal solution of the wavelet neural network to construct a seaweed organic matter relationship prediction model.

[0072] It should be explained that in the process of predicting the oxygen production capacity of seaweed, key features need to be extracted from historical operating data, including but not limited to seaweed chlorophyll concentration and seaweed biomass. Seaweed chlorophyll concentration and seaweed biomass are core indicators that affect seaweed growth and oxygen production capacity. Assume that the historical data of a certain ocean area contains seaweed chlorophyll concentrations under different light conditions and water temperatures, such as (2.5, 3.1, 3.4, 2.9), and biomass, such as (100, 120, 140, 130), and the seaweed chlorophyll concentration and seaweed biomass are used as initial sample inputs, and the mean clustering technique is applied according to the preset number of clusters. Seaweed chlorophyll concentration and seaweed biomass are classified, and the Euclidean distance from each sample point to the cluster center is calculated for clustering. Assuming that three cluster centers are randomly selected, and then the cluster centers are iteratively adjusted to minimize the distance between each sample point and its cluster center, after several rounds of iterations, the clustering results are as follows: Cluster 1 contains chlorophyll concentration (2.5, 2.9) and biomass (100, 130), Cluster 2 contains chlorophyll concentration (3.1, 3.4) and biomass (120, 140), and Cluster 3 contains some outliers. The final sample space obtained is the distribution of seaweed data under different cluster centers.

[0073] By measuring the effect of each cluster and evaluating the quality of the current clustering effect, if the effect is not good, the number of clusters is adjusted or the cluster centers are reinitialized until the optimal clustering result is obtained. After obtaining the optimized sample space, a wavelet neural network (WNN) model is constructed for prediction. The structural parameters of the wavelet neural network are defined, including the number of nodes in the input layer, hidden layer and output layer, the activation function of the hidden layer, etc., and the wavelet neural network is trained using historical sample data to learn the mapping relationship between seaweed chlorophyll concentration, biomass and oxygen production capacity. At the same time, the optimization algorithm is used to adjust the network weights to find the optimal solution. Based on the optimization algorithm, the weights are updated according to the changes in the loss function during training, thereby ensuring that the network can more accurately predict oxygen production capacity.

[0074] The trained model was used to further analyze the linear relationship between algae production and organic matter production. For example, when algae biomass increased, oxygen production increased linearly. Based on this linear relationship, the oxygen production capacity of different regions was calculated. The data was input into the wavelet neural network model to predict the oxygen production capacity of different ocean regions. The pH value trend of each ocean region was also inferred based on the change in light intensity. Assuming that the model predicts that the algae biomass in a certain area is 120 and the chlorophyll concentration is 3.2, the oxygen production capacity is 5.6 (unit: mgO2 / m 2 / day), and combined with the change in light intensity (such as the increase in sunlight intensity from 400 lux to 800 lux), it is inferred that when the light in this area is enhanced, the photosynthesis of seaweed is enhanced, the oxygen production capacity is improved, and the pH value of seawater may increase.

[0075] Furthermore, based on the combination of mean clustering technology and wavelet neural network prediction model, the data dimension and complexity can be reduced through cluster analysis. At the same time, the nonlinear relationship is processed by wavelet neural network, which can more accurately capture the complex relationship between seaweed growth and oxygen production.

[0076] Specifically, in the process of obtaining the changes in light intensity in various ocean regions within a set time period and combining them with the prediction results of oxygen production capacity, analyzing the formation trend of carbonic acid in various ocean regions, and judging the change trend of seawater pH based on the analysis results, the light intensity change value within the set time period can be obtained and combined with the oxygen production capacity prediction results to generate sensitive characteristic parameters as the input of the integrated learning model, and the photosynthesis intensity inversion model can be established using historical data; the seaweed's ability to fix carbon dioxide is used as the output, and the mapping relationship between the light intensity change value and the oxygen production capacity, and the seaweed's ability to fix carbon dioxide is obtained, and a real-time fixation capacity sequence is output; the real-time fixation capacity sequence is decomposed into modal components using modal decomposition technology, and a trend prediction model is constructed based on the modal components using the attention memory network mechanism to analyze the reaction trend of carbon dioxide and seawater calcium ions; the prediction results of each modal component are superimposed to deduce the formation rate and concentration change of carbonic acid, determine the formation trend of carbonic acid in various ocean regions, and judge the decreasing trend of carbon dioxide concentration based on the formation trend, and analyze the change trend of seawater pH.

[0077] It should be explained that the process of analyzing the trend of seawater pH change is to analyze the formation trend of carbonic acid in the ocean through the prediction results of light intensity and oxygen production capacity, and to infer the trend of seawater pH change. Assuming that the set time period is 6:00 to 18:00 every day, the light intensity change values ​​of various regions of the ocean are collected. The light intensity in different time periods is 200lux, 400lux, 600lux, 800lux, 600lux, and 400lux. At the same time, the aforementioned wavelet neural network model is called to obtain the predicted value of seaweed oxygen production capacity in the corresponding time period, which is assumed to be (1.2, 2.5, 3.8, 4.5, 3.2, 2.0) mgO2 / m 2 / h, and combines the light intensity change value with the oxygen production capacity, and uses standardized or nested feature generation methods to construct sensitive characteristic parameters. For example, the normalized difference product is used to generate a feature vector for each time period, such as feature1 = (400 / 800) × (2.5 / 4.5) = 0.277, to form a time series feature set. The time series feature set is input into the ensemble learning model for training, and its target output is the real-time carbon dioxide fixation capacity of seaweed (the unit can be mgO2 / m 2 / h), and at the same time collect historical data including light intensity, oxygen release and CO2 fixation capacity records of the corresponding time period, to build a photosynthesis intensity inversion model, so that the input is the characteristic parameter and the output is a real-time CO2 fixation capacity sequence, such as (1.1, 2.3, 3.5, 4.2, 3.0, 1.7). At the same time, the fixation capacity sequence is modally decomposed into multiple modal components, each of which represents the change characteristics at different time scales.

[0078] Based on the modal components, the data is input into a memory network model with an attention mechanism to capture long-term dependencies through time series learning and analyze the trend of CO2 fixation rate under each modality. 2+ The formation reaction of calcium carbonate (CaCO3) occurs, and the trend model is used to indirectly reflect the carbonation generation process. The prediction results of each mode are superimposed to obtain the carbonation formation rate and concentration changes. For example, the total formation rate prediction sequence is (0.8, 1.7, 2.6, 3.1, 2.2, 1.3) mmol / m 2 / h, the CO2 consumption ratio can be estimated by comparing the formation rate with the original carbon dioxide input, and the downward trend of CO2 concentration can be further analyzed. Since CO2 dissolves in water to form carbonic acid, it releases H + The decrease in CO2 concentration usually means that the pH value of seawater will increase. Combined with the trend of carbonic acid formation, the trend of seawater pH value in each region can be inferred. For example, in a certain area, the light intensity is the highest at 12:00, the oxygen and CO2 fixation is also the highest, and the carbonic acid formation rate is 3.1mmol / m 2 / h, the predicted CO2 concentration decrease rate is 0.5mmol / h, and the corresponding pH value increases by about +0.2, indicating that the pH in this area tends to increase during the high light period.

[0079] Furthermore, by integrating multiple physical, biochemical parameters, the accuracy and biological explanatory power of the prediction model can be improved, and modal decomposition can be used to separate trends and disturbance signals, thereby enhancing the ability to identify long-term changes. The final pH change trend map can guide ocean acidification analysis and underwater structure site selection, providing a scientific basis for marine environmental protection.

[0080] Step S3: construct an electrochemical impedance spectroscopy (EIS) test model, use the pH trend of seawater as a test condition to analyze the corrosion behavior of the nanocoating in various areas of the ocean, and determine the target installation and arrangement path of the underwater pipeline.

[0081] In one embodiment, in the process of building an electrochemical impedance test model, taking the trend of seawater pH value change as the test condition to analyze the corrosion behavior of the nanocoating in various areas of the ocean, and determining the target installation arrangement path of the underwater pipeline, the temperature and salinity of different sea areas can be obtained through marine environmental monitoring data, combined with the pH change trend as the test input condition, and the test input condition is standardized; based on the electrochemical impedance spectroscopy experimental technology, an experimental system is designed, the test input condition is used as a variable, the nanocoating material of the underwater pipeline is selected for impedance testing, and the impedance spectrum data of the nanocoating in the trend of seawater pH value change is obtained; the impedance spectrum data is combined with the equal-dimensional gray number complement technology to construct a coating barrier performance prediction model, and based on the coating barrier performance prediction results, the corrosion behavior of the nanocoating in various areas of the ocean is analyzed; after numbering each area of ​​the ocean according to the corrosion behavior, a convex subdivision process is performed and an ocean topology map is constructed, the ocean topology map is processed, and the location points where the corrosion behavior meets the target requirements are output as the target installation location points of the underwater pipeline.

[0082] It should be explained that in the process of obtaining impedance spectrum data, the corresponding temperature (such as 15℃~30℃ range) and salinity (such as 30‰~38‰) are obtained in combination with the marine environmental monitoring data, and combined with the pH change trend to form a triplet input condition (pH, T, S). For example, a set of original inputs in a certain area is: pH = (7.9, 8.1, 8.3), T = (18, 21, 24)℃, S = (32, 34, 36)‰, and the Z-score standardization or normalization method is used to map each variable to [0, 1] or a distribution with a mean of 0 and a variance of 1.

[0083] An experimental system was established based on electrochemical impedance spectroscopy technology. Different types of nano-coating materials for underwater pipelines (such as zinc oxide-based, graphene composite, silane-modified, etc.) were selected. Based on the controlled variable method, the standardized pH, T, and S combinations were input as independent variables into the experimental setup. The experiment used a three-electrode system. The nano-coating sample was used as the working electrode, and a reference electrode and an auxiliary electrode were set. It was immersed in the corresponding synthetic seawater environment. An AC voltage was applied through a potential control instrument, and the impedance response data at different frequencies were recorded. The frequency range was from 10 5 Hz to 10 -2 Hz, a complete electrochemical impedance spectrum is obtained. The impedance spectrum data obtained under each set of environmental conditions is a set of complex number pairs. For example, a sample exhibits a real impedance Z' = 120Ω and an imaginary impedance Z" = 30Ω at a frequency of f = 10 Hz, which forms a characteristic semicircle or linear structure when plotted in the Nyquist plot.

[0084] By fitting the impedance spectrum data with an equivalent circuit (such as the Randle circuit model), the corrosion-related parameters of the coating, such as the polarization resistance R, are extracted. p , charge transfer resistance R ct , capacitor C dl These parameters reflect the protective performance of the coating in a specific environment, such as a higher R ct Represents good corrosion resistance. Combining all experimental data, the coating performance is visualized and analyzed under different sea conditions to determine which pH-TS combination is the most stable for the nano-coating, and each sea area is assigned a corrosion risk level label, such as low risk area R p >1000Ω·cm2, medium risk R p =500~1000Ω·cm 2 , high risk R p <500Ω·cm 2 .

[0085] Furthermore, a unified testing system can be established through standardized environmental data to improve the comparability under multiple sea conditions. Combined with electrochemical impedance spectroscopy, highly sensitive electrochemical response analysis of coatings can be provided to quantify corrosion trends.

[0086] Among them, in the process of combining impedance spectrum data with equal-dimensional gray number repetitive complement technology to construct a coating barrier performance prediction model, and analyzing the corrosion behavior of the nanocoating in various ocean regions based on the coating barrier performance prediction results, a gray prediction model can be constructed based on the impedance spectrum data to implement the initial prediction, output the coating barrier performance evaluation results, and remove the first item in the impedance spectrum data. At the same time, the coating barrier performance evaluation results are added to the last item of the impedance spectrum data to update the impedance spectrum data to obtain the initial sequence; based on the initial sequence, a repetitive complement prediction model is constructed to implement the secondary prediction, output the coating barrier performance secondary evaluation results, and remove the first item in the initial sequence. At the same time, the coating barrier performance secondary evaluation results are added to the last item of the initial sequence to update the initial sequence to obtain the repetitive complement sequence; based on the repetitive complement sequence, a performance prediction model is constructed three times to implement the three predictions, output the coating barrier performance three evaluation results, and judge the prediction accuracy of the coating barrier performance three evaluation results. The updating process is repeated based on the prediction accuracy until the accuracy of the performance prediction model meets the target requirements; based on the coating barrier performance prediction results, the damage points generated on the surface of the nanocoating during the contact between the nanocoating and seawater are analyzed, and the corrosion behavior of the nanocoating in various ocean regions is judged.

[0087] Specifically, after numbering each ocean area according to the corrosion behavior, a convex subdivision process is performed and an ocean topology map is constructed. The ocean topology map is processed to output location points whose corrosion behavior meets the target requirements as target installation location points of underwater pipelines, including: dividing the ocean area by setting a corrosion grade based on the corrosion behavior of the nanocoating, assigning a unique number to each ocean area, and spatially displaying the area numbers through a visual graph to form a regional classification map; performing a convex subdivision process on the regional classification map and establishing an ocean topology map, generating initial location points whose corrosion behavior meets the target requirements using a search inspiration algorithm based on the ocean topology map; optimizing the initial location points using an elastic band algorithm to obtain local target location points, constructing an initial tree based on the ocean topology map, and constructing a dynamic sampling domain by combining the subdivision line constraints and the informed constraint set; optimizing the initial tree based on the dynamic sampling domain, adjusting the local target location points, generating target location points whose corrosion behavior meets the target requirements, and using the target location points as target installation location points of the underwater pipeline.

[0088] Among them, the expression of the informed constraint set is:

[0089]

[0090] Where, Denotes the subconvex subdivision process and the process parameter d proc The set of location points that meet the heuristic optimization criteria is: a represents the sampling point of the ocean topology map, A area represents the free space in the ocean topology, a start represents the initial position point, a end represents the local target location point, f(c / b) represents the ratio of the c-th branch point to the total branch points b in the initial tree structure, and f(c-1 / b) represents the ratio of the c-1-th branch point to the total branch points b in the initial tree structure.

[0091] It should be explained that in the process of determining the target installation location, complex impedance data (such as Z' and Z" values ​​on the Nyquist plot) are obtained from the electrochemical impedance spectroscopy (EIS) experiment, and key parameters (including polarization resistance R p , charge transfer resistance R ct , double layer capacitance C dl ), with R p For example, assuming that the initial impedance spectrum data sequence is: R p =(1000, 1050, 1100, 1150, 1200)Ω·cm 2 , the grey prediction model is used for the initial prediction, and the coating barrier performance evaluation results are calculated (such as the prediction of the next moment R p =1250Ω·cm 2 ), remove the first item, add the predicted value, and update the sequence R pnew=(1050, 1100, 1150, 1200, 1250), based on the updated sequence, the grey prediction model is used again for secondary prediction (e.g., prediction R p =1300Ω·cm 2 ), repeat the process and make three predictions (such as R p =1350Ω·cm 2 ), and calculate the prediction accuracy (such as mean square error MSE). If the accuracy does not meet the requirements (such as MSE>5%), continue to update iteratively until the prediction error converges (such as MSE<2%), and finally obtain the prediction trend of the coating barrier performance (such as R p Time-varying curve), analyze the corrosion behavior of nano-coating in seawater, assuming R p Continue to decrease (such as from 1000Ω·cm 2 Down to 800Ω·cm 2 ), indicating that the protective performance of the coating is reduced and local damage points (such as microcracks and increased porosity) may occur.

[0092] According to the predicted R p Value, set the corrosion level (such as: low risk R p >1000Ω·cm 2 , medium risk 500~1000Ω·cm 2 , high risk R p <500Ω·cm 2 ), and number the ocean areas, assuming - Area A: R p =1200Ω·cm 2 → Low risk (No. 1); Region B: R p =800Ω·cm 2 → Medium risk (No. 2); Region C: R p =400Ω·cm 2 → High risk (number 3), the numbered area is convexly divided to form a spatial topological structure, for example, the low-risk area is adjacent to the medium-risk area, and the high-risk area is located at the edge.

[0093] Based on the ocean topology map, a search heuristic algorithm is used to find the path with the lowest corrosion risk. For example, from the starting point to the end point, the low-risk area (No. 1) is preferentially selected as the path point, and the initial path is smoothly optimized to avoid passing through the high-risk area. It is assumed that the initial path may pass through the medium-risk area (No. 2). After optimization, it bypasses the low-risk area (No. 1). At the same time, the segmentation line constraints (such as avoiding crossing the high-risk area) and the informed constraint set (such as only sampling the low-risk area) are combined to optimize the path and finally output the target installation location point.

[0094] Therefore, the data is dynamically updated through the equal-dimensional gray number supplementation technology to make the coating performance prediction more accurate. In combination with the corrosion level and topology map, it is ensured that the pipeline is installed in the low-corrosion risk area and avoids the high-risk area, thus extending the service life of the pipeline, scientifically guiding the installation location selection of the underwater pipeline, and maximizing the corrosion resistance.

[0095] like Figure 2 According to another embodiment of the present invention, a system for detecting and analyzing ocean pH values ​​is provided. The system includes:

[0096] The seawater pH detection module 1 is used to divide the ocean into regions, obtain seawater samples from each region, react the seawater samples with a sensitive indicator, and use photometry to measure the absorbance ratio to detect the pH value of seawater in each region of the ocean;

[0097] pH trend prediction module 2 is used to predict the oxygen production capacity of seaweed based on the seaweed data in various ocean regions, and analyze the pH trend of seawater in various ocean regions during a set period of time based on the prediction results and changes in light intensity;

[0098] Corrosion behavior analysis module 3 is used to build an electrochemical impedance spectroscopy test model, using the pH value change trend of seawater as the test condition to analyze the corrosion behavior of the nanocoating in various areas of the ocean and determine the target installation arrangement path of the underwater pipeline.

[0099] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for detecting and analyzing ocean pH, characterized in that: The analytical method includes: Divide the ocean into regions, obtain seawater samples from each region, react the seawater samples with sensitive indicators, use photometry to measure the absorbance ratio, and detect the pH value of seawater in each region of the ocean; Based on the seaweed data in various ocean regions, the oxygen production capacity of seaweed is predicted. The pH value trend of seawater in various ocean regions during a set period is analyzed based on the predicted results and changes in light intensity. An electrochemical impedance spectroscopy (EIS) test model was constructed, and the pH trend of seawater was used as the test condition to analyze the corrosion behavior of the nanocoating in various areas of the ocean, and to determine the target installation and arrangement path of the underwater pipeline.

2. A method for detecting and analyzing ocean pH value according to claim 1, characterized in that: The method of dividing the ocean into regions, obtaining seawater samples from each region of the ocean, reacting the seawater samples with a sensitive indicator, and measuring the absorbance ratio by photometry to detect the pH value of seawater in each region of the ocean includes: Divide the ocean test area into several square grids, map the sea level height and ocean depth data into the grids, and calculate the average ocean depth and height of each grid in the initial test area; Grids with average depth and height less than the target values ​​are eliminated to obtain the final ocean state distribution map. The clustering algorithm is used to determine the target number of clusters and the ocean test area is divided according to height and depth characteristics. Collect seawater samples from various areas of the ocean, select sensitive indicators and mix them into the seawater samples for reaction, and use a photometer to analyze the absorbance of the seawater samples at a specific wavelength; The absorbance ratio of marine samples is calculated based on the absorbance, and the absorbance ratio is mapped to the standard pH curve to determine the pH value of seawater in various areas of the ocean.

3. A method for detecting and analyzing ocean pH value according to claim 1, characterized in that: The method of predicting the oxygen production capacity of seaweed based on seaweed data in various ocean regions and analyzing the pH value change trend of seawater in various ocean regions during a set period of time based on the prediction results and changes in light intensity includes: Based on the mean clustering technology, historical operation correlation data is classified and the sample space is output. Then, based on the optimization algorithm and the sample space, the optimal weight solution is selected and a wavelet neural network prediction model is constructed. The wavelet neural network prediction model was used to establish the mapping relationship between algae quantity and organic matter production, and the linear relationship between algae quantity and organic matter conversion rate was analyzed based on the mapping relationship. Based on the linear relationship results, the oxygen production capacity is analyzed. At the same time, the seaweed distribution and biomass data of each area of ​​the ocean are extracted and input into the wavelet neural network prediction model to predict the oxygen production capacity of the seaweed. The changes in light intensity in various ocean regions within a set time period are obtained and combined with the predicted results of oxygen production capacity to analyze the formation trend of carbonic acid in various ocean regions. The trend of seawater pH changes is determined based on the analysis results.

4. A method for detecting and analyzing ocean pH value according to claim 3, characterized in that: The method of classifying historical operation correlation data based on mean clustering technology, outputting sample space, and screening the optimal weight solution based on the optimization algorithm and sample space to construct a wavelet neural network prediction model includes: Extract seaweed chlorophyll concentration and seaweed biomass as sample data based on historical operation correlation data, and define the number of cluster groups to analyze the Euclidean distance between sample data and cluster centers; Classify the sample data based on the Euclidean distance to obtain the sample space, and use the sample space to measure the clustering effect. Repeat the classification of the sample data according to the measurement results until the target sample space is obtained; The structural parameters of the wavelet neural network are set to train the wavelet neural network. Based on the training results, the optimization algorithm and the target sample space are used to screen the optimal solution of the wavelet neural network to construct a seaweed organic matter relationship prediction model.

5. A method for detecting and analyzing ocean pH value according to claim 4, characterized in that: The method of obtaining the change in light intensity in each ocean region within a set period of time, combining it with the oxygen production capacity prediction result, analyzing the formation trend of carbonic acid in each ocean region, and judging the change trend of seawater pH based on the analysis result includes: The light intensity change value within a set period is obtained and combined with the oxygen production capacity prediction result to generate sensitive characteristic parameters as the input of the integrated learning model, and the photosynthesis intensity inversion model is established using historical data; The carbon dioxide fixation capacity sequence of the seaweed is used as the output to obtain the mapping relationship between the light intensity change value and the oxygen production capacity, and the carbon dioxide fixation capacity of the seaweed, and output the real-time fixation capacity sequence; Modal decomposition technology is used to decompose the real-time fixed capacity sequence into modal components. Based on the modal components, a trend prediction model is constructed using the attention memory network mechanism to analyze the reaction trend between carbon dioxide and seawater calcium ions. The prediction results of each modal component are superimposed to deduce the formation rate and concentration change of carbonic acid, determine the formation trend of carbonic acid in various ocean regions, and judge the decreasing trend of carbon dioxide concentration based on the formation trend, and analyze the change trend of seawater pH.

6. A method for detecting and analyzing ocean pH value according to claim 1, characterized in that: The electrochemical impedance spectroscopy (EIS) test model was constructed, and the pH trend of seawater was used as a test condition to analyze the corrosion behavior of the nanocoating in various areas of the ocean. The target installation arrangement path of the underwater pipeline was determined, including: The temperature and salinity of different sea areas are obtained through marine environmental monitoring data, combined with the pH change trend as test input conditions, and the test input conditions are standardized; An experimental system was designed based on electrochemical impedance spectroscopy (EIS) technology. The test input conditions were used as variables, and impedance testing was performed on nano-coating materials for underwater pipelines to obtain impedance spectrum data on the changing trends of the nano-coating under seawater pH. Combining impedance spectroscopy data with the equal-dimensional gray number recursive filling technique, a coating barrier performance prediction model was constructed. Based on the coating barrier performance prediction results, the corrosion behavior of nano-coatings in various marine areas was analyzed. After numbering each ocean area according to its corrosion behavior, it performs convex segmentation and constructs an ocean topology map. The ocean topology map is processed and the locations where the corrosion behavior meets the target requirements are output as the target installation locations of the underwater pipeline.

7. A method for detecting and analyzing ocean pH value according to claim 6, characterized in that: The above-mentioned method combines the impedance spectrum data with the equal-dimensional gray number iteration technique to construct a coating barrier performance prediction model, and analyzes the corrosion behavior of the nanocoating in various marine areas based on the coating barrier performance prediction results, including: Based on the impedance spectrum data, a grey prediction model is constructed to implement the initial prediction, output the coating barrier performance evaluation results, remove the first item in the impedance spectrum data, and add the coating barrier performance evaluation results to the last item of the impedance spectrum data to update the impedance spectrum data and obtain the initial sequence; A supplementary prediction model is constructed based on the primary sequence to implement secondary prediction, output the secondary evaluation results of the coating barrier performance, remove the first item in the primary sequence, and add the secondary evaluation results of the coating barrier performance to the last item of the primary sequence to update the primary sequence to obtain the supplementary sequence; The performance prediction model is constructed three times according to the complement sequence to implement three predictions, and the three evaluation results of the coating barrier performance are output. The prediction accuracy of the three evaluation results of the coating barrier performance is determined, and the update process is repeated based on the prediction accuracy until the accuracy of the performance prediction model meets the target requirements; Based on the prediction results of the coating barrier performance, the damage points generated on the surface of the nanocoating during the contact between the nanocoating and seawater are analyzed, and the corrosion behavior of the nanocoating in various areas of the ocean is judged.

8. A method for detecting and analyzing ocean pH value according to claim 7, characterized in that: The method comprises: numbering each ocean area according to the corrosion behavior, performing convex segmentation processing, constructing an ocean topology map, processing the ocean topology map, and outputting location points where the corrosion behavior meets the target requirements as target installation location points of the underwater pipeline. Based on the corrosion behavior of nano-coatings, the marine areas are divided into corrosion levels, each marine area is assigned a unique number, and the regional numbers are spatially displayed through a visual graph to form a regional classification map; Convex subdivision is performed on the regional classification map to establish an ocean topology map. Based on the ocean topology map, a search heuristic algorithm is used to generate initial location points whose corrosion behavior meets the target requirements. The elastic band algorithm is used to optimize the initial position points to obtain the local target position points, and the initial tree is constructed based on the ocean topology map. The dynamic sampling domain is constructed by combining the segmentation line constraint and the informed constraint set. Based on the dynamic sampling domain optimization of the initial tree, the local target location points are adjusted to generate target location points whose corrosion behavior meets the target requirements. The target location points are used as the target installation location points of the underwater pipeline.

9. A method for detecting and analyzing ocean pH value according to claim 8, characterized in that: The expression of the informed constraint set is: Where, Denotes the subconvex subdivision process and the process parameter d proc The set of location points that meet the heuristic optimization criteria is: a represents the sampling point of the ocean topology map, A area represents the free space in the ocean topology, a start represents the initial position point, a end represents the local target location point, f(c / b) represents the ratio of the c-th branch point to the total branch points b in the initial tree structure, and f(c-1 / b) represents the ratio of the c-1-th branch point to the total branch points b in the initial tree structure.

10. A system for detecting and analyzing ocean pH values, for implementing the method for detecting and analyzing ocean pH values ​​according to any one of claims 1 to 9, characterized in that: The analysis system includes: The seawater pH detection module is used to divide the ocean into regions, obtain seawater samples from each region, react the seawater samples with a sensitive indicator, and use photometry to measure the absorbance ratio to detect the pH value of seawater in each region of the ocean; The pH trend prediction module is used to predict the oxygen production capacity of seaweed based on the seaweed data in various ocean areas, and analyze the pH trend of seawater in various ocean areas during a set period of time based on the prediction results and changes in light intensity; The corrosion behavior analysis module is used to build an electrochemical impedance spectroscopy (EIS) test model, using the pH trend of seawater as a test condition to analyze the corrosion behavior of nanocoatings in various ocean regions and determine the target installation and arrangement paths for underwater pipelines.

Images