Acoustic method-based hydrothermal liquid nozzle material mass calculation grading method and system

Abstract

The invention discloses a hydrothermal nozzle matter mass calculation grading method and system based on an acoustic method, and relates to the technical field of ocean exploration, and the method comprises the steps: synchronously collecting hydrothermal nozzle data through employing a deployed acoustic device and a multi-environment parameter sensor, and carrying out the preprocessing and calibration; and acoustic features and environmental features are extracted based on acoustic data and environmental parameter data included in the hydrothermal nozzle data. According to the invention, the acoustic characteristic data and the environmental characteristic data of the hydrothermal nozzle are collected and processed in real time, the substance quantity trend index is output through the substance quantity trend calculation model, dynamic monitoring of the substance quantity of the hydrothermal nozzle is realized, the change trend of the substance quantity can be found in time, and according to the calculation result obtained by the substance quantity trend calculation model, the dynamic monitoring of the substance quantity of the hydrothermal nozzle is realized. According to the method, the material quantity of the hydrothermal nozzle is divided into different grades by combining the preset grading standard and the actual demand, so that the resource potential of the hydrothermal nozzle can be evaluated, and guidance is provided for reasonable development and utilization of deep sea mineral resources.

Description

Technical Field

[0001] The present invention relates to the field of ocean exploration technology, and in particular to a method and system for estimating and grading the mass of hydrothermal vent materials based on acoustic methods. Background Art

[0002] The seafloor hydrothermal vent area is rich in scientific value. It is a key window for studying the balance, circulation and heat budget of geochemical substances, and a natural laboratory for exploring the origin of early life on Earth. Hydrothermal vents often contain large amounts of mineral resources such as metal sulfides. Understanding the environmental parameters of the hydrothermal vent area is a basic condition for the future development and utilization of seafloor resources. Accurately estimating the quality of hydrothermal vent materials can provide an important basis for evaluating the potential reserves of hydrothermal sulfide resources, thereby providing scientific guidance for the exploration and development of deep-sea mineral resources.

[0003] In the existing technology, the environmental conditions of deep-sea hydrothermal vents are complex and changeable. The simultaneous changes of multiple environmental parameters will interfere with acoustic measurements, thereby affecting the accuracy of mass estimation. Therefore, how to couple the acoustic measurement data with multiple environmental parameters for analysis, conduct trend analysis on the mass of hydrothermal vents, and establish a unified hydrothermal vent mass classification standard to ensure the accuracy of hydrothermal vent mass estimation and classification is the problem to be solved by the present invention. To this end, a hydrothermal vent mass estimation and classification method and system based on acoustic methods are proposed. Summary of the Invention

[0004] The present invention aims to provide a method and system for estimating and grading the mass of hydrothermal vent materials based on acoustic methods, so as to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: In the first aspect, a method for estimating and classifying hydrothermal vent material mass based on acoustic methods comprises the following steps: S1. Use deployed acoustic equipment and multi-environmental parameter sensors to synchronously collect hydrothermal vent data, and perform preprocessing and calibration to ensure data quality; S2. Extracting acoustic and environmental characteristics based on the acoustic data and environmental parameter data contained in the hydrothermal vent data, and integrating them with preset characteristic benchmark values ​​to obtain a comprehensive characteristic sequence table; S3. Combine the comprehensive feature sequence table to conduct coupling analysis on acoustic features and environmental features, and analyze the correlation between acoustic features and environmental features to eliminate the influence of environmental interference on the estimation of material mass; S4. Based on the results of the coupling analysis, a mass trend estimation model is constructed to estimate the mass trend of hydrothermal vent materials by integrating acoustic and environmental characteristics. S5. Based on the results of the mass trend estimation model, combined with the preset classification standards and actual needs, different mass grades are classified and the mass grade of the hydrothermal vents is determined; S6. Verify the accuracy of the mass trend estimation model and classification standards through actual offshore test data, and iteratively optimize the mass trend estimation model and classification standards based on the verification results to improve the reliability of mass estimation and classification.

[0006] A further improvement of the technical solution of the present invention is that: S1 specifically includes: According to the requirements of hydrothermal vent detection, multi-beam imaging sonar is selected as the acoustic equipment, and the configuration includes temperature, pressure, turbidity, pH value, and and develop a detailed equipment deployment plan to carry acoustic equipment and multi-environmental parameter sensors on manned submersibles; After the manned submersible dives to the hydrothermal vent area to be investigated, the acoustic equipment and multi-environmental parameter sensors are started to synchronously collect hydrothermal vent data including acoustic data and environmental parameter data, and the collected hydrothermal vent data are transmitted to the control center of the manned submersible in real time through the data transmission system. The acoustic data includes target intensity and scattering intensity, which are used to analyze the eruption state and material quality of the hydrothermal vent, and the environmental parameter data include temperature, pressure, turbidity, pH value, and concentrations, used to assess the physicochemical characteristics of hydrothermal vents; The collected raw hydrothermal vent data are preprocessed, including filtering, denoising and smoothing operations to eliminate noise and interference in the data. At the same time, the data are format converted and standardized, and the preprocessed hydrothermal vent data are calibrated using known field calibration data.

[0007] A further improvement of the technical solution of the present invention is that: S2 specifically includes: Signal processing techniques are used to analyze the target intensity and scattering intensity in the acoustic data, extracting acoustic features, including the peak value of the target intensity and the changing trend of the scattering intensity, to reflect the acoustic characteristics of the hydrothermal vents. The acoustic features extracted from the acoustic data are then organized and recorded to form a preliminary set of acoustic features. Temperature, pressure, turbidity, pH value, and The concentration is statistically analyzed and feature extracted to obtain environmental characteristics, including the mean and variance of temperature and pressure, the rate of change of turbidity, pH value, and The critical threshold of concentration is used to characterize the physical and chemical environmental characteristics of hydrothermal vents, and then the extracted environmental characteristics are classified and summarized to construct the environmental characteristic subset; Based on the need for hydrothermal vent material mass estimation and historical survey data in the hydrothermal vent area, the baseline values ​​of acoustic and environmental characteristics are determined based on the average values ​​of each characteristic in the historical survey data; The extracted acoustic feature set, environmental feature subset and the determined baseline value of each feature are integrated and arranged in chronological order to form a comprehensive feature sequence table.

[0008] A further improvement of the technical solution of the present invention is that: S3 specifically includes: Based on the comprehensive feature sequence table, the Pearson correlation coefficient is calculated using the correlation analysis method to analyze the correlation between acoustic features and environmental features. A correlation threshold is set and feature pairs with an absolute value of the correlation coefficient greater than the correlation threshold are screened out. These feature pairs are considered to have an impact on the mass estimation. Based on the results of the correlation analysis, a multiple linear regression model was used as the basic framework to construct a coupling model of acoustic and environmental characteristics. The multiple environmental characteristics that screened out that influenced each other were used as independent variables, and the corresponding acoustic characteristics were used as dependent variables to establish a quantitative relationship between environmental and acoustic characteristics. An independent data set is used to verify the constructed coupling model of acoustic features and environmental features, and the accuracy and reliability of the model are evaluated. The cross-validation method is used to divide the data set into a training set and a test set. The training set is used to build the model, and the test set is used to verify the performance of the model. The error index between the model prediction value and the actual value is calculated to quantify the accuracy of the model. Then, based on the results of the model verification, the coupling model of acoustic features and environmental features is optimized and adjusted. The model verification and optimization process is repeated until the final coupling model of acoustic features and environmental features is obtained.

[0009] A further improvement of the technical solution of the present invention is that the screening process of the feature pairs that influence each other in the estimation of the amount of substance is as follows: Obtain a comprehensive feature sequence table, extract acoustic features and environmental features from the comprehensive feature sequence table, ensure that the data points of each feature are arranged in consistent chronological order, and organize the acoustic features and environmental features into numerical data matrices, with each row representing an observation point and each column representing a feature; Determine the combination of acoustic and environmental features to be analyzed, calculate the Pearson correlation coefficient between each pair of features, and record the correlation coefficient for each pair of features, as well as the corresponding p-value used to determine whether the correlation is significant; According to the requirements of hydrothermal vent observation, the correlation threshold is set, and the absolute value of the correlation coefficient is greater than 0.5. At the same time, the significance level p<0.05 is set, and the feature pairs with the absolute value of the correlation coefficient greater than the correlation threshold and the p value less than the significance level are screened out from the calculation results. Then, the screened feature pairs and their correlation coefficients and p values ​​are sorted into a table to form a list of key feature pairs for subsequent coupling analysis, that is, to obtain the feature pairs that affect each other in the mass estimation, including target intensity and temperature, scattering intensity and turbidity, target intensity and concentration, scattered intensity vs. pH, and target intensity vs. pressure.

[0010] A further improvement of the technical solution of the present invention is that: S4 specifically includes: According to the coupling analysis results of acoustic characteristics and environmental characteristics, the neural network model is selected as the basic architecture, and the number of neurons in the input layer, hidden layer and output layer is determined. The number of neurons in the input layer is consistent with the number of selected acoustic characteristics and environmental characteristics, including target intensity, temperature, scattering intensity, turbidity, Concentration, pH value and pressure, extract the baseline value of each feature, the number of neurons in the output layer is 1, which is used to output the predicted value of the mass trend of the hydrothermal vent material, so as to build a mass trend estimation model, and use the selected acoustic characteristics and environmental characteristics as independent variables, and the mass trend of the hydrothermal vent material as the dependent variable; Integrate a large amount of pre-collected historical survey data for hydrothermal vent areas, including acoustic and environmental characteristics, and divide it into training and test sets. Label the baseline values ​​of the acoustic and environmental characteristics. Use the training set in conjunction with the neural network model for training. Adjust the model parameters through the back-propagation algorithm. Use the test set to verify the initially constructed mass trend estimation model. Calculate the error index between the model prediction value and the actual mass. Repeat the model verification and optimization process until the model's prediction accuracy meets the expected requirements, thus obtaining the final mass trend estimation model. The constructed mass trend inference model is deployed and constructed, and the acoustic characteristics and environmental characteristics selected from the comprehensive feature sequence table are input. The mass trend inference model then outputs the mass trend index to analyze the changing trend of the hydrothermal vent state.

[0011] A further improvement of the technical solution of the present invention is that the calculation process of the mass trend index is: Collect the currently measured acoustic and environmental characteristic values, determine the baseline value of each characteristic based on the average value of historical survey data, and set the adjustment coefficient according to the model sensitivity requirements; For each feature, calculate the ratio of its current value to the baseline value, and calculate the square of each ratio. Then add the square values ​​of all features to get the total, and take the square root of the total to get the value of the numerator. For each feature, calculate the deviation between the current value and the baseline value, add up the deviations of all features to get the total deviation, multiply the total deviation by the adjustment coefficient, and calculate the exponential function with e as the base of the natural logarithm. Then add 1 to the exponential term to get the value of the denominator; The calculated value of the numerator is divided by the value of the denominator to obtain the final mass trend index. When all characteristics are equal to the benchmark value, the numerator and denominator both take the middle value, indicating that the mass tends to be stable. When most characteristics are significantly higher than the benchmark value, the numerator increases and the denominator decreases, indicating that the mass tends to increase. When most characteristics are significantly lower than the benchmark value, the numerator decreases and the denominator increases, indicating that the mass tends to decrease. If the mass trend index continues to rise, it indicates that the mass output of the hydrothermal vent has increased and the eruption activity has strengthened. If the mass trend index continues to decline, it indicates that the mass output has decreased and the eruption activity has weakened. If the mass trend index fluctuates slightly and is close to the median value, it indicates that the eruption state is relatively stable.

[0012] A further improvement of the technical solution of the present invention is that: S5 specifically includes: Based on the monitoring objectives and actual needs of hydrothermal vents, and combined with historical survey data in the hydrothermal vent area, the mass grade standard is defined. The mass grade is divided into three levels: low mass grade, medium mass grade, and high mass grade. The corresponding classification threshold is assigned to each mass grade in combination with the mass trend index. According to the mass trend index output by the mass trend calculation model and combined with the preset mass grade standard, the mass of each data point is divided into the corresponding grade, and the mass grade of each data point is recorded to form a mass grade time series.

[0013] A further improvement of the technical solution of the present invention is that: S6 specifically includes: Organize and conduct offshore trials, using onboard acoustic equipment and environmental sensors to synchronously collect acoustic and environmental characteristic data from hydrothermal vents. Preprocess the collected data, including filtering, denoising, and format conversion, to ensure data quality. Simultaneously, record the mass trend index for each data point, and obtain actual mass measurements from hydrothermal samples collected on-site as benchmark data for validating models and classification standards. Compare the mass trend index output by the mass trend estimation model with the field verification data, calculate the error index between the model prediction value and the actual mass, classify the mass trend index value output by the model into the corresponding mass grade according to the preset mass grade standard, and compare it with the mass grade of the field verification data to evaluate the accuracy of the classification standard, statistically analyze the deviation between the model prediction value and the actual value, analyze the performance of the model at different mass grades, and identify potential problems with the model and classification standard; Based on the verification results, the parameters of the mass trend estimation model are adjusted, the model structure is optimized, and the prediction accuracy of the model is improved. Based on the output results of the adjusted model, the thresholds for the mass grade division are re-evaluated and adjusted to ensure the rationality and accuracy of the classification standards. The new model and classification standards are used to re-verify the offshore test data, and the verification process is repeated until the model prediction accuracy and classification accuracy meet the expected requirements.

[0014] In a second aspect, a hydrothermal vent material mass estimation and classification system based on acoustic methods is used to implement the above-mentioned hydrothermal vent material mass estimation and classification method based on acoustic methods, including: The data acquisition module is used to use acoustic equipment and environmental sensors carried on the manned submersible to synchronously collect acoustic characteristic data and environmental characteristic data of the hydrothermal vents, and preprocess and calibrate the data; The feature extraction and integration module is used to use signal processing technology to perform feature analysis on the target intensity and scattering intensity in the acoustic data, extract acoustic features, perform statistical analysis and feature extraction on the environmental parameter data, obtain environmental features, and integrate them into a comprehensive feature sequence table based on preset feature baseline values ​​to comprehensively and accurately reflect the acoustic and environmental characteristics of the hydrothermal vents; The feature coupling analysis module is used to analyze the correlation between acoustic features and environmental features in combination with the comprehensive feature sequence table, screen out feature pairs that influence each other in the mass estimation, and construct a coupling model of acoustic features and environmental features to describe the dependence of acoustic features on environmental features, thereby eliminating the influence of environmental interference on the mass estimation; The mass trend analysis module is used to construct a mass trend estimation model based on the coupled analysis results of acoustic characteristics and environmental characteristics, input the screened acoustic characteristics and environmental characteristics, output a mass trend index, and evaluate the mass change trend of the hydrothermal vent; The mass grade classification module is used to classify different mass grades based on the estimated results obtained by the mass trend estimation model, combined with the preset classification standards and actual needs, and record the mass grade of each data point to form a mass grade time series, which intuitively displays the change of the mass grade of the hydrothermal vent over time; The verification and optimization module is used to verify the accuracy of the mass trend estimation model and classification standards through actual offshore test data, and iteratively optimize the mass trend estimation model and classification standards based on the verification results to improve the reliability of the mass estimation and classification, and ensure the accuracy and reliability of the mass estimation and classification results.

[0015] Due to the adoption of the above technical solution, the present invention has the following technical advancements compared to the prior art: The present invention provides a hydrothermal vent mass estimation and classification method and system based on acoustic methods. By real-time collection and processing of acoustic characteristic data and environmental characteristic data of hydrothermal vents, a mass trend index is output through a mass trend estimation model, thereby realizing dynamic monitoring of the mass of hydrothermal vents. This helps to timely discover the changing trend of mass. According to the estimation results obtained by the mass trend estimation model, combined with preset classification standards and actual needs, the mass of hydrothermal vents is divided into different grades, which helps to evaluate the resource potential of hydrothermal vents and provide guidance for the rational development and utilization of deep-sea mineral resources.

[0016] The present invention provides a hydrothermal vent mass estimation and classification method and system based on acoustic methods. By synchronously collecting acoustic data and environmental parameter data and applying signal processing technology and coupling analysis models, the influence of environmental interference on mass estimation is effectively eliminated, the accuracy of mass estimation is significantly improved, and more accurate data support is provided for the exploration and development of deep-sea mineral resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application 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 described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a schematic diagram of the workflow of the present invention; Figure 2 Schematic diagram of the method of the present invention. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0020] Example 1, as Figure 1 、 Figure 2 As shown, the present invention provides a method for estimating and classifying the mass of hydrothermal vent materials based on an acoustic method, comprising the following steps: S1. Use the deployed acoustic equipment and multi-environmental parameter sensors to synchronously collect hydrothermal vent data, and perform preprocessing and calibration to ensure data quality. According to the requirements of hydrothermal vent detection, select multi-beam imaging sonar as the acoustic equipment, and configure temperature, pressure, turbidity, pH value, and Multi-environmental parameter sensors are used to ensure that all equipment has high precision, high stability and resistance to deep-sea high pressure and high temperature. A detailed equipment deployment plan is formulated to carry acoustic equipment and multi-environmental parameter sensors on manned submersibles. Among them, the multi-beam imaging sonar is installed at a suitable position on the submersible to ensure that its acoustic signal coverage can cover the entire detection area. The environmental parameter sensor is installed near the acoustic equipment to collect acoustic data and environmental parameter data at the same time, ensuring that all equipment is seamlessly connected to the data transmission system of the manned submersible. After the manned submersible dives to the hydrothermal vent area to be investigated, the acoustic equipment and multi-environmental parameter sensors are started to synchronously collect hydrothermal vent data including acoustic data and environmental parameter data, and the collected hydrothermal vent data are transmitted to the control center of the manned submersible in real time through the data transmission system. Among them, the acoustic data include target intensity and scattering intensity, which are used to analyze the eruption state and material mass of the hydrothermal vent. The environmental parameter data include temperature, pressure, turbidity, pH value, and Concentration is used to evaluate the physical and chemical characteristics of hydrothermal vents. The collected raw hydrothermal vent data is preprocessed, including filtering, denoising, and smoothing operations to eliminate noise and interference in the data. At the same time, the data is format converted and standardized, and the preprocessed hydrothermal vent data is calibrated using known field calibration data. By comparing the field calibration data with the collected data, the equipment parameters are adjusted to eliminate deviations caused by equipment errors or environmental changes, ensuring the accuracy and reliability of the data; S2. Based on the acoustic data and environmental parameter data contained in the hydrothermal vent data, the acoustic features and environmental features are extracted, and combined with the preset characteristic benchmark values, a comprehensive feature sequence table is obtained. The target intensity and scattering intensity in the acoustic data are analyzed using signal processing technology to extract acoustic features, including the peak value of the target intensity and the changing trend of the scattering intensity, to reflect the acoustic characteristics of the hydrothermal vent. The acoustic features extracted from the acoustic data are sorted and recorded to form a preliminary acoustic feature set. The temperature, pressure, turbidity, pH value, and The concentration is statistically analyzed and feature extracted to obtain environmental characteristics, including the mean and variance of temperature and pressure, the rate of change of turbidity, pH value, and The key threshold of concentration is used to characterize the physical and chemical environmental characteristics of hydrothermal vents, and then the extracted environmental characteristics are classified and summarized to construct an environmental characteristic subset. Combined with the needs of hydrothermal vent mass estimation and historical survey data of the hydrothermal vent area, the baseline values ​​of acoustic characteristics and environmental characteristics are determined based on the average value of each characteristic in the historical survey data. The extracted acoustic characteristic set, environmental characteristic subset and the determined baseline value of each characteristic are integrated and arranged in chronological order to ensure that each comprehensive characteristic data point can reflect acoustic and environmental information at the same time, thereby forming a comprehensive characteristic sequence table. The value range of the baseline value is determined based on the historical survey data of the hydrothermal vent area and the long-term monitoring data of the environmental parameters and acoustic characteristics of the area. By statistically analyzing the data obtained from multiple surveys in the hydrothermal vent area in the past, including acoustic data and environmental parameter data, the typical value range of each characteristic under normal conditions and different eruption intensity conditions is determined, thereby providing a reference basis for the determination of the baseline value, and then according to the average value of each characteristic, Determine the baseline value. In addition, for the analysis of acoustic data characteristics: During the target intensity characteristic analysis, the collected target intensity data is first filtered, denoised and smoothed to remove outliers and noise interference in the data. The peak detection algorithm in the signal processing technology is used to identify the peak points in the target intensity data. The peak points correspond to the concentrated areas of energy of hydrothermal vent eruption materials, reflecting the intensity changes of the eruption materials. The target intensity is an important indicator reflecting the energy of hydrothermal vent eruption materials in acoustic measurement. A higher target intensity is related to the concentration and energy of hydrothermal vent eruption materials. During the scattering intensity characteristic analysis, the scattering intensity data is also filtered, denoised and smoothed to ensure data quality. By calculating the derivative of the scattering intensity data, the trend of scattering intensity changes over time is analyzed. The scattering intensity is an indicator of the scattering ability of small particles of hydrothermal vent eruption materials to sound waves in acoustic measurement. Its changing trend can reflect the distribution and concentration changes of small particles in the eruption materials, thereby providing a basis for estimating the mass of the materials. For the feature extraction of environmental parameter data: In the process of temperature feature extraction, the temperature data is first filtered, denoised and smoothed to eliminate random fluctuations and outliers in the data. The average value of the temperature data within a fixed time interval is calculated to reflect the average temperature level of the hydrothermal vent area during the time period. The variance of the temperature data is calculated to measure the degree of temperature fluctuation within the time interval. A larger variance means that the temperature change caused by the hydrothermal vent eruption activity is more drastic. Temperature is a key environmental parameter in the hydrothermal vent area. The high-temperature fluid erupted from the hydrothermal vent directly affects the temperature change of the surrounding seawater. The mean and variance of the temperature can be used to understand the impact of the eruption activity on the surrounding environment. The degree of influence of ambient temperature; in the process of pressure feature extraction, the pressure data is filtered, denoised and smoothed, the average value of the pressure data is calculated to reflect the average pressure level in the hydrothermal vent area, the variance of the pressure data is calculated, and the pressure fluctuation is understood. The pressure fluctuation is related to the impact and flow of the erupting material. Pressure is an important physical parameter during the eruption of the hydrothermal vent. The pressure change generated by the erupting material in the vent will affect the propagation and intensity of the acoustic signal, and can also reflect the intensity and stability of the eruption; in the process of turbidity feature extraction, the turbidity data is filtered, denoised and smoothed as above, and the change rate of the turbidity data is calculated, that is, the adjacent data points The ratio of the difference in turbidity between the two times to the time interval. Turbidity is another environmental parameter in the hydrothermal vent area that reflects the concentration of suspended particles in the eruption material. The rate of change of turbidity can reflect the diffusion and precipitation of the eruption material in the seawater. In the process of pH value feature extraction, the pH value data also needs to be filtered, denoised and smoothed. According to the chemical properties and historical data of the hydrothermal vent eruption material, the key threshold of the pH value is determined. For example, when the pH value is lower than a certain value, it indicates that the eruption material is highly acidic and has a significant chemical impact on the surrounding environment. The pH value is an important chemical parameter in the hydrothermal vent eruption material. The material erupted from the hydrothermal vent has A lower pH value indicates acidity. By monitoring changes in pH and its key threshold, we can understand the chemical properties of the erupting materials and their impact on the chemical environment of the surrounding seawater. In the process of extracting concentration features, the concentration data is filtered, denoised, and smoothed. Based on the chemical composition and historical data of hydrothermal vent eruption materials, the key concentration threshold is determined. For example, when the concentration is higher than a certain value, it means that the content of a certain important component in the erupting material is high. Concentration is an important chemical component in hydrothermal vent eruption materials. Its content in hydrothermal vent eruption materials is closely related to the mass of the erupted materials. By monitoring the concentration and its key threshold, the mass of the erupted materials can be inferred. S3. Combined with the comprehensive feature sequence table, the acoustic features and environmental features are coupled and analyzed to analyze the correlation between the acoustic features and environmental features to eliminate the impact of environmental interference on the mass estimation. Based on the comprehensive feature sequence table, the Pearson correlation coefficient is calculated using the correlation analysis method to analyze the correlation between the acoustic features and environmental features. The correlation threshold is set to screen out feature pairs with an absolute value of the correlation coefficient greater than the correlation threshold, which are the feature pairs that influence each other in the mass estimation. According to the results of the correlation analysis, the multivariate linear regression model is used as the basic framework to construct a coupling model of acoustic features and environmental features. The multiple environmental features that influence each other are selected as independent variables, and the corresponding acoustic features are used as dependent variables to establish a quantitative relationship between environmental features and acoustic features. The model parameters are estimated by the least squares method to construct a preliminary coupling model. A coupling model is constructed to describe the dependence of acoustic features on environmental features. An independent data set is used to verify the constructed coupling model of acoustic features and environmental features, and the accuracy and reliability of the model are evaluated. A cross-validation method is used to divide the data set into a training set and a test set. The training set is used to build the model, and the test set is used to verify the performance of the model. The error index between the model prediction value and the actual value is calculated to quantify the accuracy of the model. Based on the results of the model verification, the coupling model of acoustic features and environmental features is optimized and adjusted, and the model parameters are adjusted to improve the performance of the model. At the same time, the residual of the model is analyzed to find the source of the existing systematic error, and the model is improved in a targeted manner. The model verification and optimization process is repeated until the final coupling model of acoustic features and environmental features is obtained to ensure that the model can effectively eliminate the impact of environmental interference on the mass estimation; In addition, the screening process of the characteristic pairs that influence each other in the estimation of the amount of substance is as follows: Obtain a comprehensive feature sequence table, extract acoustic features and environmental features from the comprehensive feature sequence table, ensure that the data points of each feature are arranged in chronological order, and organize the acoustic features and environmental features into numerical data matrices, where each row represents an observation point and each column represents a feature. Determine the combination of acoustic features and environmental features to be analyzed, calculate the Pearson correlation coefficient between each pair of features, record the correlation coefficient of each pair of features, and the corresponding p-value used to determine whether the correlation is significant. Set the correlation threshold according to the hydrothermal vent observation requirements, and the absolute value of the correlation coefficient is greater than 0.5. At the same time, set the significance level p<0.05. Filter out feature pairs with an absolute value of the correlation coefficient greater than the correlation threshold and a p-value less than the significance level from the calculation results. Then organize the filtered feature pairs and their correlation coefficients and p-values ​​into a table to form a list of key feature pairs for subsequent coupling analysis, that is, obtain feature pairs that influence each other in the mass estimation, including target intensity and temperature, scattering intensity and turbidity, target intensity and Concentration, scattering intensity and pH value, as well as target intensity and pressure. Among them, for target intensity and temperature, target intensity is an important indicator reflecting the energy of hydrothermal vent eruption materials in acoustic measurement. Higher target intensity is related to the concentration and energy of hydrothermal vent eruption materials. Temperature is a key environmental parameter in the hydrothermal vent area. The high-temperature fluid erupted from the hydrothermal vent directly affects the temperature change of the surrounding seawater. There is a positive correlation between target intensity and temperature. When the amount of material erupted from the hydrothermal vent is large, the target intensity is large. At the same time, the erupted high-temperature material will increase the temperature of the surrounding seawater. Therefore, the change in the mass of hydrothermal vent eruption materials can be inferred by the synchronous change of target intensity and temperature. Higher target intensity and temperature values ​​indicate that the mass of the eruption materials is large. For scattering intensity and turbidity, scattering intensity is Acoustic measurement is an indicator of the ability of tiny particles of hydrothermal vent eruption materials to scatter sound waves. The materials erupted from hydrothermal vents usually contain a large number of tiny particles. The particles will produce scattering signals under the action of sound waves. Turbidity is another environmental parameter in the hydrothermal vent area that reflects the concentration of suspended particles in the eruption materials. The increase in turbidity means that the concentration of suspended particles of the eruption materials in the seawater increases. There is a negative correlation between scattering intensity and turbidity. As the scattering intensity increases, the turbidity decreases. When the number of particles with smaller particle size increases, the scattering intensity increases, but these particles may be more likely to diffuse into the seawater, resulting in a decrease in local turbidity. The negative correlation is related to the physical and chemical properties of the eruption materials. By monitoring the changes in scattering intensity and turbidity, the mass of the hydrothermal vent materials can be accurately calculated, which is very important for the target intensity and turbidity. Concentration, target intensity reflects the total energy and concentration of the material ejected from the hydrothermal vent, Concentration is an important chemical component in hydrothermal vent eruption materials. The content of the material in the hydrothermal vent is closely related to the amount of material erupted, and the target intensity is closely related to the There is a positive correlation between the concentrations, and the changes in the mass of the erupted material are related to The concentration changes synchronously. When the mass of the hydrothermal vent is large, the target intensity is large. concentration will also increase, and vice versa, by monitoring the target intensity and Concentration can be used to infer the mass of the eruption material, which can help identify the changes in the sulfide content in the eruption material and its contribution to the quality of the eruption material. As for the scattering intensity and pH value, the scattering intensity reflects the scattering effect of tiny particles in the hydrothermal vent eruption material on sound waves. The pH value is an important chemical parameter in the hydrothermal vent eruption material. The material erupted from the hydrothermal vent has a low pH value (acidic). There is a negative correlation between the scattering intensity and the pH value. When the scattering intensity increases, the pH value decreases. The acidic components in the eruption material react with seawater during the eruption process, resulting in a decrease in the pH value of the local seawater. At the same time, the presence of acidic components also changes the surface properties of the particles in the eruption material, thereby affecting The scattering effect of particles on sound waves can be used to infer the mass of hydrothermal vent materials by monitoring changes in scattering intensity and pH value. As for target intensity and pressure, the target intensity is related to the water pressure near the hydrothermal vent. When a hydrothermal vent erupts, the high pressure will push the erupted material to a greater distance, affecting the propagation and intensity of the acoustic signal. The pressure value measured by the pressure sensor reflects the instantaneous pressure of the erupted material at the vent. The target intensity is positively correlated with the pressure. The density and eruption intensity of the erupted material are closely related to the pressure of the vent. A higher target intensity is accompanied by a higher pressure value, which means that the mass of the erupted material is greater. By monitoring the target intensity and pressure, the mass of the erupted material can be inferred. The calculation formula of Pearson correlation coefficient is: ; Where, is the Pearson correlation coefficient, and are the i-th observation values ​​of the two features, and are the mean of the observed values ​​of the two features respectively; S4. Based on the results of the coupling analysis, a mass trend estimation model is constructed to estimate the mass trend of hydrothermal vent materials by integrating acoustic and environmental characteristics. S5. Based on the results of the mass trend estimation model, combined with the preset classification standards and actual needs, different mass grades are classified and the mass grade of the hydrothermal vents is determined; S6. Verify the accuracy of the mass trend estimation model and classification standards through actual offshore test data, and iteratively optimize the mass trend estimation model and classification standards based on the verification results to improve the reliability of mass estimation and classification.

[0021] Example 2, as Figure 1 、 Figure 2 As shown, based on Example 1, the present invention provides a technical solution: preferably, S4 specifically includes: According to the coupling analysis results of acoustic characteristics and environmental characteristics, the neural network model is selected as the basic architecture, and the number of neurons in the input layer, hidden layer and output layer is determined. The number of neurons in the input layer is consistent with the number of selected acoustic characteristics and environmental characteristics, including target intensity, temperature, scattering intensity, turbidity, Concentration, pH value and pressure, extract the baseline value of each feature, the number of neurons in the output layer is 1, which is used to output the predicted value of the mass trend of the hydrothermal vent, in order to build a mass trend estimation model, and use the screened acoustic characteristics and environmental characteristics as independent variables, and the mass trend of the hydrothermal vent as the dependent variable, integrate a large amount of historical survey data of the hydrothermal vent area containing acoustic characteristics and environmental characteristics collected in advance, divide it into training set and test set, mark the baseline values ​​of acoustic characteristics and environmental characteristics, use the training set in combination with the neural network model for training, adjust the model parameters through the back propagation algorithm, make the model output as close to the actual mass as possible, calculate the error between the predicted value and the actual mass value, adjust the bias parameter of the network according to the error, and monitor the loss function value and training error of the model in real time during the training process Indicators, according to the error change trend, adjust the learning rate or the number of training iterations to avoid overfitting or underfitting, use the test set to verify the initially constructed mass trend inference model, calculate the error indicators between the model prediction value and the actual mass, including relative error, root mean square error, etc., to evaluate the accuracy and reliability of the model. If the verification result is not ideal, analyze the source of the error, optimize the model according to the error source, adjust the model parameters, repeat the model verification and optimization process until the model's prediction accuracy meets the expected requirements, obtain the final mass trend inference model, deploy the constructed mass trend inference model, input the acoustic characteristics and environmental characteristics selected from the comprehensive feature sequence table, and then output the mass trend index through the mass trend inference model to analyze the changing trend of the hydrothermal vent state; In addition, the calculation process of the mass trend index is: Collect the currently measured acoustic characteristic values ​​and environmental characteristic values, and determine the baseline value of each characteristic based on the average value of historical survey data, set the adjustment coefficient according to the model sensitivity requirement, calculate the ratio of the current value to the baseline value for each characteristic, and calculate the square of each ratio, and then add the square values ​​of all characteristics to get the total, take the square root of the total, and get the value of the numerator. For each characteristic, calculate the deviation of the current value from the baseline value, add the deviation values ​​of all characteristics to get the total deviation value, multiply the total deviation value by the adjustment coefficient, and calculate the exponential function with e as the base of the natural logarithm, and then add 1 to the exponential term to get the value of the denominator, and multiply the calculated denominator by the adjustment coefficient. The value of the sub-part is divided by the value of the denominator to obtain the final mass trend index. When all characteristics are equal to the baseline value, the numerator and denominator are both taken to the middle value, indicating that the mass tends to be stable. When most characteristics are significantly higher than the baseline value, the numerator increases and the denominator decreases, indicating that the mass tends to increase. When most characteristics are significantly lower than the baseline value, the numerator decreases and the denominator increases, indicating that the mass tends to decrease. If the mass trend index continues to rise, it indicates that the mass output of the hydrothermal vent is increasing and the eruption activity is intensifying. If the mass trend index continues to decline, it indicates that the mass output is decreasing and the eruption activity is weakening. If the mass trend index fluctuates slightly and is close to the median value, it indicates that the eruption state is relatively stable. The calculation expression of the mass trend index is: ; Where QI is the mass trend index, which is used to evaluate the mass change trend of hydrothermal vents. is the current measurement value of the j-th feature, is the benchmark value of the jth feature, determined based on the average value of each feature in the historical survey data, is the adjustment coefficient, which is used to adjust the sensitivity of the model. Its value is 0.1. The value range of QI is between 0 and 1. equal When the QI value is close to 0, it means that the amount of matter tends to be stable. Significant deviation When , the value of QI is close to 1, indicating that the amount of matter tends to change significantly; S5 specifically includes: According to the monitoring objectives and actual needs of hydrothermal vents, the material quality grade standard is defined in combination with the historical survey data of the hydrothermal vent area, and the material quality grade is divided into three grades, namely low material quality grade, medium material quality grade and high material quality grade. The corresponding division threshold is assigned to each material quality grade in combination with the material quality trend index. According to the material quality trend index output by the material quality trend calculation model, combined with the preset material quality grade standard, the material quality of each data point is divided into the corresponding grade, and the material quality grade of each data point is recorded to form a material quality grade time series. It should be noted that the preset grading standard is the material quality grade division. The grading standard is mainly based on the historical survey data of the hydrothermal vent area. By analyzing the distribution of the material quality trend index in the historical data, the division threshold is determined to reflect the characteristics of different material quality grades; the actual needs include the potential of hydrothermal vent resources. The assessment of the force and the trend of mass changes in the hydrothermal vent area are used to provide guidance for the rational development and utilization of deep-sea mineral resources. In addition, for marine environmental protection and scientific research, understanding the mass grade of hydrothermal vents is helpful to evaluate their impact on the surrounding marine environment. By analyzing the historical survey data of the hydrothermal vent area, the performance and characteristics of different mass grades in actual observations are understood, providing data support for the setting of classification standards. Furthermore, the basis for the division threshold is the historical survey data of the hydrothermal vent area and the mass trend index. The benchmark values ​​of acoustic characteristics and environmental characteristics are determined according to the average value of each feature in the historical survey data of the hydrothermal vent area, thereby providing a reference basis for the mass grade division. By constructing a mass trend calculation model and outputting the mass trend index, the mass of the hydrothermal vents is divided into different mass grades in combination with the preset classification standards and actual needs. Multiple material quality levels correspond to multiple classification thresholds one by one, and the corresponding relationship is as follows: The threshold for low substance level classification is: , indicating that the vent material quality is low and the activity is weak; The thresholds for the quality grade of the substances are: , indicating that the vent material quality is moderate and the activity is normal; The threshold for high material content is: , indicating that the vent material is of higher quality and the activity is stronger; Among them, QI is the mass trend index, is the upper threshold of the low mass level and the lower threshold of the medium mass level, is the upper threshold of the medium mass level and the lower threshold of the high mass level, =0.33, =0.67; S6 specifically includes: Organize and carry out offshore tests, use the onboard acoustic equipment and environmental sensors to synchronously collect acoustic and environmental characteristic data of hydrothermal vents, and pre-process the collected data, including filtering, denoising, format conversion, etc., to ensure data quality. At the same time, record the mass trend index of each data point, and obtain the actual measurement value of the mass from the hydrothermal samples collected on site as the benchmark data for verifying the model and grading standards. Compare the value of the mass trend index output by the mass trend inference model with the field verification data, calculate the error index between the model prediction value and the actual mass, and divide the mass trend index value output by the model into To the corresponding mass level, and compare it with the mass level of the field verification data, evaluate the accuracy of the classification standard, statistically analyze the deviation between the model prediction value and the actual value, analyze the performance of the model under different mass levels, identify potential problems of the model and classification standards, and adjust the parameters of the mass trend estimation model according to the verification results, optimize the model structure, and improve the prediction accuracy of the model. According to the output results after the model adjustment, re-evaluate and adjust the mass level division threshold to ensure the rationality and accuracy of the classification standard, use the new model and classification standard to re-verify the offshore test data, and repeat the verification process until the model prediction accuracy and classification accuracy meet the expected requirements.

[0022] Example 3, as Figure 1 、 Figure 2 As shown, based on Examples 1-2, the present invention further provides a hydrothermal vent material mass estimation and classification system based on acoustic methods, which is used to implement the above-mentioned hydrothermal vent material mass estimation and classification method based on acoustic methods, including: A data acquisition module is used to synchronously collect acoustic and environmental characteristic data of hydrothermal vents using acoustic equipment and environmental sensors carried on a manned submersible, and to preprocess and calibrate the data; The feature extraction and integration module is used to use signal processing technology to perform feature analysis on the target intensity and scattering intensity in the acoustic data, extract acoustic features, perform statistical analysis and feature extraction on the environmental parameter data, obtain environmental features, and integrate them with the preset feature baseline values ​​to obtain a comprehensive feature sequence table, which comprehensively and accurately reflects the acoustic and environmental characteristics of the hydrothermal vents. The feature coupling analysis module is used to combine the comprehensive feature sequence table to analyze the correlation between acoustic features and environmental features, screen out feature pairs that influence each other in the mass estimation, and construct a coupling model of acoustic features and environmental features to describe the dependence of acoustic features on environmental features and eliminate the influence of environmental interference on the mass estimation; The mass trend analysis module is used to build a mass trend estimation model based on the coupled analysis results of acoustic and environmental characteristics. It inputs the selected acoustic and environmental characteristics and outputs a mass trend index to evaluate the mass change trend of hydrothermal vents. The mass grade classification module is used to classify different mass grades based on the results obtained from the mass trend estimation model, combined with the preset classification standards and actual needs, and record the mass grade of each data point to form a mass grade time series, which can intuitively display the changes in the mass grade of hydrothermal vents over time; The verification and optimization module is used to verify the accuracy of the mass trend estimation model and classification standards through actual offshore test data, and iteratively optimize the mass trend estimation model and classification standards based on the verification results to improve the reliability of mass estimation and classification, and ensure the accuracy and reliability of mass estimation and classification results.

[0023] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for estimating and classifying hydrothermal vent material mass based on acoustic methods, characterized in that: The following steps are involved: S1. Use the deployed acoustic equipment and multi-environmental parameter sensors to synchronously collect hydrothermal vent data, and perform preprocessing and calibration; S2. Extracting acoustic and environmental characteristics based on the acoustic data and environmental parameter data contained in the hydrothermal vent data, and integrating them with preset characteristic benchmark values ​​to obtain a comprehensive characteristic sequence table; S3. Combine the comprehensive feature sequence table to conduct coupling analysis on acoustic features and environmental features, and analyze the correlation between acoustic features and environmental features; S4. Based on the results of the coupling analysis, a mass trend estimation model is constructed to estimate the mass trend of hydrothermal vent materials by integrating acoustic and environmental characteristics. S5. Based on the results of the mass trend estimation model, combined with the preset classification standards and actual needs, different mass grades are classified and the mass grade of the hydrothermal vents is determined; S6. Verify the accuracy of the mass trend estimation model and classification standards through actual offshore test data, and iteratively optimize the mass trend estimation model and classification standards based on the verification results.

2. The method for estimating and classifying hydrothermal vent material mass based on acoustic methods according to claim 1, characterized in that: Said S1 specifically includes: According to the requirements of hydrothermal vent detection, multi-beam imaging sonar is selected as the acoustic equipment, and the configuration includes temperature, pressure, turbidity, pH value, and and develop a plan for equipment deployment to place acoustic equipment and multi-environmental parameter sensors on manned submersibles; After the manned submersible dives to the hydrothermal vent area to be investigated, the acoustic equipment and multi-environmental parameter sensors are started to synchronously collect hydrothermal vent data including acoustic data and environmental parameter data, and the collected hydrothermal vent data are transmitted to the control center of the manned submersible in real time through the data transmission system. The acoustic data includes target intensity and scattering intensity, and the environmental parameter data includes temperature, pressure, turbidity, pH value, and concentration; The collected raw hydrothermal vent data are preprocessed, including filtering, denoising and smoothing operations. At the same time, the data are format converted and standardized, and the preprocessed hydrothermal vent data are calibrated using known field calibration data.

3. The method for estimating and classifying hydrothermal vent material mass based on acoustic methods according to claim 1, characterized in that: The S2 specifically includes: Signal processing technology is used to perform feature analysis on the target intensity and scattering intensity in the acoustic data, extracting acoustic features, including the peak value of the target intensity and the changing trend of the scattering intensity. The acoustic features extracted from the acoustic data are then sorted and recorded to form a preliminary acoustic feature set. Temperature, pressure, turbidity, pH value, and The concentration is statistically analyzed and feature extracted to obtain environmental characteristics, including the mean and variance of temperature and pressure, the rate of change of turbidity, pH value, and The key threshold of concentration is determined, and then the extracted environmental features are classified and summarized to construct an environmental feature subset; Based on the need for hydrothermal vent material mass estimation and historical survey data in the hydrothermal vent area, the baseline values ​​of acoustic and environmental characteristics are determined based on the average values ​​of each characteristic in the historical survey data; The extracted acoustic feature set, environmental feature subset and the determined baseline value of each feature are integrated and arranged in chronological order to form a comprehensive feature sequence table.

4. The method for estimating and classifying hydrothermal vent material mass based on acoustic methods according to claim 2, characterized in that: The S3 specifically includes: Based on the comprehensive feature sequence table, the Pearson correlation coefficient is calculated using the correlation analysis method to analyze the correlation between acoustic features and environmental features. A correlation threshold is set and feature pairs with an absolute value of the correlation coefficient greater than the correlation threshold are screened out. These feature pairs are considered to have an impact on the mass estimation. Based on the results of the correlation analysis, a multiple linear regression model was used as the basic framework to construct a coupling model of acoustic and environmental characteristics. The multiple environmental characteristics that screened out that influenced each other were used as independent variables, and the corresponding acoustic characteristics were used as dependent variables to establish a quantitative relationship between environmental and acoustic characteristics. An independent data set is used to verify the constructed coupling model of acoustic features and environmental features. The cross-validation method is used to divide the data set into a training set and a test set. The training set is used to build the model, and the test set is used to verify the performance of the model. The error index between the model prediction value and the actual value is calculated. Then, based on the results of the model verification, the coupling model of acoustic features and environmental features is optimized and adjusted. The model verification and optimization process is repeated until the final coupling model of acoustic features and environmental features is obtained.

5. The method for estimating and classifying hydrothermal vent material mass based on acoustic methods according to claim 4, characterized in that: The screening process of the feature pairs that influence each other in the estimation of the amount of substance is as follows: Obtain a comprehensive feature sequence table, extract acoustic features and environmental features from the comprehensive feature sequence table, ensure that the data points of each feature are arranged in consistent chronological order, and organize the acoustic features and environmental features into numerical data matrices, with each row representing an observation point and each column representing a feature; Determine the combination of acoustic and environmental features to be analyzed, calculate the Pearson correlation coefficient between each pair of features, and record the correlation coefficient for each pair of features, as well as the corresponding p-value used to determine whether the correlation is significant; According to the requirements of hydrothermal vent observation, the correlation threshold is set, and the absolute value of the correlation coefficient is greater than 0.

5. At the same time, the significance level p<0.05 is set, and the feature pairs with the absolute value of the correlation coefficient greater than the correlation threshold and the p value less than the significance level are screened out from the calculation results. Then, the screened feature pairs and their correlation coefficients and p values ​​are sorted into a table to form a list of key feature pairs for subsequent coupling analysis, that is, to obtain the feature pairs that affect each other in the mass estimation, including target intensity and temperature, scattering intensity and turbidity, target intensity and concentration, scattered intensity vs. pH, and target intensity vs. pressure.

6. The method for estimating and classifying hydrothermal vent material mass based on acoustic methods according to claim 1, characterized in that: The S4 specifically includes: According to the coupling analysis results of acoustic characteristics and environmental characteristics, the neural network model is selected as the basic architecture to determine the number of neurons in the input layer, hidden layer and output layer, including target intensity, temperature, scattering intensity, turbidity, concentration, pH value and pressure, extract the baseline value of each feature to build a mass trend estimation model, and use the selected acoustic and environmental characteristics as independent variables and the mass trend of hydrothermal vents as the dependent variable; Integrate a large amount of pre-collected historical survey data on hydrothermal vent areas, including acoustic and environmental characteristics, and divide it into training and test sets. Label the baseline values ​​of the acoustic and environmental characteristics. Use the training set in conjunction with the neural network model for training. Adjust the model parameters through the back-propagation algorithm. Use the test set to verify the initially constructed mass trend estimation model. Calculate the error index between the model prediction value and the actual mass. Repeat the model verification and optimization process to obtain the final mass trend estimation model. The constructed mass trend inference model is deployed and constructed, and the acoustic characteristics and environmental characteristics selected from the comprehensive feature sequence table are input. The mass trend inference model then outputs the mass trend index to analyze the changing trend of the hydrothermal vent state.

7. The method for estimating and classifying hydrothermal vent material mass based on acoustic methods according to claim 6, characterized in that: The calculation process of the mass trend index is as follows: Collect the currently measured acoustic and environmental characteristic values, determine the baseline value of each characteristic based on the average value of historical survey data, and set the adjustment coefficient according to the model sensitivity requirements; For each feature, calculate the ratio of its current value to the baseline value, and calculate the square of each ratio. Then add the square values ​​of all features to get the total, and take the square root of the total to get the value of the numerator. For each feature, calculate the deviation between the current value and the baseline value, add up the deviations of all features to get the total deviation, multiply the total deviation by the adjustment coefficient, and calculate the exponential function with e as the base of the natural logarithm. Then add 1 to the exponential term to get the value of the denominator; Divide the calculated value of the numerator by the value of the denominator to obtain the final mass trend index.

8. The method for estimating and classifying hydrothermal vent material mass based on acoustic methods according to claim 7, characterized in that: The S5 specifically includes: Based on the monitoring objectives and actual needs of hydrothermal vents, and combined with historical survey data in the hydrothermal vent area, the mass grade standard is defined. The mass grade is divided into three levels: low mass grade, medium mass grade, and high mass grade. The corresponding classification threshold is assigned to each mass grade in combination with the mass trend index. According to the mass trend index output by the mass trend calculation model and combined with the preset mass grade standard, the mass of each data point is divided into the corresponding grade, and the mass grade of each data point is recorded to form a mass grade time series.

9. The method for estimating and classifying hydrothermal vent material mass based on acoustic methods according to claim 1, characterized in that: The S6 specifically includes: Organize and conduct offshore trials, using onboard acoustic equipment and environmental sensors to simultaneously collect acoustic and environmental characteristic data from hydrothermal vents. Preprocess the collected data, record the mass trend index for each data point, and obtain actual mass measurements from hydrothermal samples collected on site. Compare the mass trend index output by the mass trend estimation model with the field verification data, calculate the error index between the model prediction value and the actual mass, classify the mass trend index value output by the model into the corresponding mass grade according to the preset mass grade standard, and compare it with the mass grade of the field verification data to evaluate the accuracy of the classification standard, statistically analyze the deviation between the model prediction value and the actual value, analyze the performance of the model at different mass grades, and identify potential problems with the model and classification standard; Based on the verification results, the parameters of the mass trend estimation model are adjusted, the model structure is optimized, and based on the output results of the adjusted model, the mass grade classification thresholds are re-evaluated and adjusted. The new model and classification standards are used to re-verify the offshore test data, and the verification process is repeated until the model prediction accuracy and classification accuracy meet the expected requirements.

10. A hydrothermal vent material mass estimation and classification system based on acoustic methods, used to implement the hydrothermal vent material mass estimation and classification method based on acoustic methods as described in any one of claims 1 to 9, characterized in that: include: The data acquisition module is used to use acoustic equipment and environmental sensors carried on the manned submersible to synchronously collect acoustic characteristic data and environmental characteristic data of the hydrothermal vents, and preprocess and calibrate the data; The feature extraction and integration module is used to use signal processing technology to perform feature analysis on the target intensity and scattering intensity in the acoustic data, extract acoustic features, perform statistical analysis and feature extraction on the environmental parameter data, obtain environmental features, and integrate them into a comprehensive feature sequence table based on the preset feature reference values; The feature coupling analysis module is used to analyze the correlation between acoustic features and environmental features in combination with the comprehensive feature sequence table, screen out feature pairs that influence each other in the mass estimation, and construct a coupling model of acoustic features and environmental features to describe the dependence of acoustic features on environmental features; The mass trend analysis module is used to construct a mass trend estimation model based on the coupled analysis results of acoustic characteristics and environmental characteristics, input the screened acoustic characteristics and environmental characteristics, output a mass trend index, and evaluate the mass change trend of the hydrothermal vent; The substance mass grade classification module is used to classify different substance mass grades based on the estimated results obtained by the substance mass trend estimation model, combined with preset classification standards and actual needs, and record the substance mass grade of each data point to form a substance mass grade time series; The verification and optimization module is used to verify the accuracy of the material mass trend estimation model and classification standards through actual offshore test data, and iteratively optimize the material mass trend estimation model and classification standards based on the verification results.

Images