Intelligent monitoring method and system for offshore oil pollution

Abstract

The invention relates to an intelligent marine oil pollution monitoring method and system, and the method comprises the steps: obtaining marine environment data with a space-time identifier in a to-be-monitored marine region, carrying out the digital modeling of the marine environment data, obtaining a marine digital model, mapping the marine digital model to a physical space of a marine entity model, and obtaining a marine oil pollution model; the method is used for depicting marine environment change rules. Acquiring a fluorescence image of each detection node in the ocean area to be detected, determining the fluorescence intensity of the fluorescence image, and obtaining the petroleum pollutant concentration according to the corresponding relationship between the fluorescence intensity and the petroleum pollutant concentration in the water body in water; and the petroleum pollutant concentration of each node is endowed with a weight according to the pollutant grade, and is mapped to the ocean entity model for displaying the change rule of the petroleum pollutant concentration in the ocean. According to the method, powerful support is provided for formulating scientific and reasonable pollution treatment schemes and ecological restoration measures, and the effect and efficiency of pollution treatment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pollution detection, and in particular to an intelligent monitoring method and system for marine oil pollution. Background Art

[0002] With the rapid development of the marine economy, marine oil extraction, transportation and other activities are becoming increasingly frequent, and marine oil pollution incidents also occur from time to time, posing a threat to the marine ecological environment. Traditional marine oil pollution monitoring methods mainly rely on manual sampling and laboratory analysis, which have problems such as low monitoring efficiency, poor real-time performance, and limited coverage. It is difficult to meet the needs of rapid, accurate, and comprehensive monitoring of marine oil pollution. In addition, the marine environment is complex and changeable, and a single monitoring method is difficult to effectively reflect the diffusion pattern and changing trend of oil pollutants in the ocean, and cannot provide timely and accurate decision-making basis for pollution control and ecological restoration. Therefore, there is an urgent need for a method and system that can intelligently and efficiently monitor marine oil pollution to meet the challenges brought by marine oil pollution. Summary of the Invention

[0003] In order to solve the problems existing in the above-mentioned prior art, the purpose of the present invention is to provide an intelligent monitoring method and system for marine oil pollution, which can provide strong support for the formulation of scientific and reasonable pollution control plans and ecological restoration measures, and help improve the effectiveness and efficiency of pollution control.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] An intelligent monitoring method for marine oil pollution, comprising:

[0006] Acquire ocean environment data with time and space identification in the ocean area to be measured, perform digital modeling on the ocean environment data to obtain an ocean digital model, and map the ocean digital model to the physical space of the ocean physical model to depict the law of change of the ocean environment;

[0007] Acquire a fluorescence image of each detection node in the ocean area to be measured, determine the fluorescence intensity of the fluorescence image, and obtain the concentration of the petroleum pollutants according to the corresponding relationship between the fluorescence intensity and the concentration of the petroleum pollutants in the water body;

[0008] The oil pollutant concentration at each node is weighted according to the pollutant level and mapped to the ocean entity model to show the changing pattern of oil pollutant concentration in the ocean.

[0009] Optionally, obtaining the marine environment data includes: collecting and standardizing water temperature, salinity, sea level, wind speed and air pressure data in the ocean area to be measured to obtain the marine environment data.

[0010] Optionally, obtaining the ocean digital model includes:

[0011] Classifying and digitally encoding the ocean environment data according to water temperature field, salinity field, sea level height field, wind speed field and air pressure field to obtain an ocean data structure;

[0012] Performing time series and spatial distribution mapping on the physical quantities in the ocean data structure to obtain the spatiotemporal distribution characteristics of the ocean environment elements;

[0013] Based on the spatiotemporal distribution characteristics, coupling analysis and correlation calculation are performed on the interaction relationship between the marine environmental elements to obtain a marine element correlation matrix;

[0014] Inputting the ocean element correlation matrix into a dynamic evolution model to analyze the changing rules of the ocean environment state and obtain an environmental evolution sequence;

[0015] A mapping function between the physical ocean environment and the digital space is established based on the environmental evolution sequence to obtain a digital twin mapping relationship, and the digital twin mapping relationship is input into a feature extractor to extract key features of the ocean environment to obtain an ocean environment feature vector;

[0016] The ocean environment feature vector and the digital twin mapping relationship are model integrated to construct the ocean digital model.

[0017] Optionally, determining the fluorescence intensity of the fluorescence image includes:

[0018] Emitting laser light at each detection node position in the ocean area to be measured, obtaining the fluorescence image under the illumination of the excitation light with a fixed intensity, and obtaining the reference fluorescence emission power based on the mapping relationship between the fluorescence emission power and the fluorescence grayscale value of the fluorescence image;

[0019] The reference fluorescence emission power is calculated according to the fluorescence spectrum integral relationship to obtain a reference fluorescence emission intensity, and the fluorescence intensity of the fluorescence image is determined using the reference fluorescence emission intensity.

[0020] Optionally, determining the fluorescence intensity using the reference fluorescence emission intensity includes:

[0021] A1=A2×B×C

[0022] Among them, A1 is the fluorescence intensity of the fluorescence image, A2 is the baseline fluorescence emission intensity, B is the illumination light power change, and C is the fluorescence power change.

[0023] Optionally, assigning weights to the petroleum pollutant concentrations at each node according to the pollutant level includes:

[0024]

[0025] Among them, C i is the pollution concentration of the ith node, W1, W2, W3 represent different weights and C2 is the pollution level value preset, W(C i ) is the weight of node i.

[0026] To achieve the above objectives, the present invention also provides an intelligent marine oil pollution monitoring system, comprising:

[0027] A digital model building module is used to obtain marine environmental data with time and space identification in the ocean area to be measured, perform digital modeling on the marine environmental data, obtain a marine digital model, and map the marine digital model to the physical space of the marine physical model to depict the law of marine environmental change;

[0028] a pollution concentration detection module, configured to obtain a fluorescence image of each detection node in the ocean area to be detected, determine the fluorescence intensity of the fluorescence image, and obtain the concentration of the petroleum pollutants according to a corresponding relationship between the fluorescence intensity and the concentration of the petroleum pollutants in the water body;

[0029] The pollution concentration display module is used to assign weights to the oil pollutant concentrations at each node according to the pollutant level and map them to the ocean entity model to display the changing pattern of oil pollutant concentrations in the ocean.

[0030] Optionally, the digital model building module includes:

[0031] A digital model building unit is used to obtain ocean environment data with time and space identification in the ocean area to be measured; the ocean environment data includes: water temperature field, salinity field, sea level height field, wind speed field and air pressure field;

[0032] Classifying and digitally encoding the ocean environment data according to water temperature field, salinity field, sea level height field, wind speed field and air pressure field to obtain an ocean data structure;

[0033] Performing time series and spatial distribution mapping on the physical quantities in the ocean data structure to obtain spatiotemporal distribution characteristics of ocean environmental elements, performing coupling analysis and correlation calculation on the interaction relationships between ocean environmental elements based on the spatiotemporal distribution characteristics to obtain an ocean element correlation matrix, inputting the ocean element correlation matrix into a dynamic evolution model to analyze the law of change of ocean environmental state and obtain an environmental evolution sequence;

[0034] Based on the environmental evolution sequence, a mapping function between the physical ocean environment and the digital space is established to obtain a digital twin mapping relationship, and the digital twin mapping relationship is input into a feature extractor to extract key features of the ocean environment to obtain an ocean environment feature vector. The ocean environment feature vector and the digital twin mapping relationship are model integrated to construct the ocean digital model.

[0035] Optionally, the pollution concentration detection module includes:

[0036] a fluorescence intensity detection module configured to emit laser light at each detection node position in the ocean area to be measured, obtain the fluorescence image under illumination of fixed-intensity excitation light, obtain a reference fluorescence emission power based on a mapping relationship between fluorescence emission power and fluorescence grayscale value of the fluorescence image, calculate the reference fluorescence emission power based on a fluorescence spectrum integral relationship to obtain a reference fluorescence emission intensity, and determine the fluorescence intensity of the fluorescence image using the reference fluorescence emission intensity;

[0037] The pollution concentration detection unit is used to obtain the concentration of petroleum pollutants in the water according to the corresponding relationship between the fluorescence intensity and the concentration of petroleum pollutants in the water body.

[0038] The beneficial effects of the present invention are:

[0039] The present invention obtains marine environmental data with time and space labels in the marine area to be tested and performs real-time monitoring and analysis of fluorescent images, which can quickly and accurately obtain information on the concentration of petroleum pollutants, greatly improving the monitoring efficiency and real-time performance, and reducing the time cost of manual sampling and laboratory analysis.

[0040] The present invention maps the ocean digital model into the physical space of the ocean entity model, which can comprehensively depict the changing patterns of the ocean environment and the concentration of petroleum pollutants. It can not only obtain pollution data of local detection nodes, but also understand the pollution distribution and diffusion trend of the entire ocean area to be tested from a macro perspective, providing a more comprehensive basis for pollution control.

[0041] The present invention uses digital modeling, fluorescence image analysis and other technical means to realize the intelligent monitoring of marine oil pollution, automatically processes, analyzes and assigns weights to marine environmental data and fluorescence images, reduces interference from human factors, improves the accuracy and reliability of monitoring data, and also reduces the workload of monitoring personnel.

[0042] By assigning weights to the petroleum pollutant concentrations at each node according to the pollutant level and mapping them to an ocean entity model, the present invention can intuitively display the changing patterns of petroleum pollutant concentrations in the ocean, providing strong support for the formulation of scientific and reasonable pollution control plans and ecological restoration measures, and helping to improve the effectiveness and efficiency of pollution control. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] 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.

[0044] Figure 1 This is a flow chart of an intelligent method for monitoring marine oil pollution according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0046] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0047] like Figure 1 As shown, this embodiment discloses an intelligent monitoring method for marine oil pollution, including: obtaining marine environmental data with time and space identification in the marine area to be measured, digitally modeling the marine environmental data to obtain a marine digital model, and mapping the marine digital model to the physical space of a marine physical model to depict the law of marine environmental change; obtaining a fluorescence image of each detection node in the marine area to be measured, determining the fluorescence intensity of the fluorescence image, and obtaining the oil pollutant concentration according to the corresponding relationship between the fluorescence intensity and the oil pollutant concentration in the water body; assigning a weight to the oil pollutant concentration of each node according to the pollutant level, and mapping it to the marine physical model to display the law of change of the oil pollutant concentration in the ocean.

[0048] Furthermore, obtaining the ocean environment data includes: collecting and standardizing the water temperature, salinity, sea level, wind speed and air pressure data in the ocean area to be measured to obtain the ocean environment data.

[0049] Furthermore, obtaining the ocean digital model includes: classifying and digitally encoding the ocean environmental data according to the water temperature field, salinity field, sea level height field, wind speed field and air pressure field to obtain the ocean data structure; performing time series and spatial distribution mapping on the physical quantities in the ocean data structure to obtain the spatiotemporal distribution characteristics of the ocean environmental elements; performing coupling analysis and correlation calculation on the interaction relationship between the ocean environmental elements based on the spatiotemporal distribution characteristics to obtain the ocean element association matrix; inputting the ocean element association matrix into the dynamic evolution model to analyze the law of change of the ocean environmental state to obtain the environmental evolution sequence; establishing a mapping function between the physical ocean environment and the digital space based on the environmental evolution sequence to obtain a digital twin mapping relationship, and inputting the digital twin mapping relationship into the feature extractor to extract key features of the ocean environment to obtain an ocean environment feature vector; performing model integration on the ocean environment feature vector and the digital twin mapping relationship to construct an ocean digital model.

[0050] Specifically, data collection time slot division and prioritization: In an integrated sea-air-shore monitoring network, marine environmental monitoring equipment is distributed across various locations, collecting real-time marine environmental data. To efficiently manage and optimize the data collection process, the data collection time slots for these devices need to be periodically divided and prioritized based on the importance and urgency of the data. This creates a sampling schedule that ensures that critical data is collected and processed first.

[0051] Data credibility assessment and exception handling: Based on the sampling schedule, the raw data collected by monitoring equipment undergoes a series of processing steps. First, the collected data undergoes error calculation and threshold determination to assess its credibility. If the credibility indicator falls below the preset threshold, the data is considered an anomaly, marked, and removed. This process results in a valid data set that can be used for subsequent analysis and processing.

[0052] Dynamic adjustment and synchronization of data sampling cycles: Based on the temporal distribution of valid data sets, the data sampling cycle is dynamically adjusted. For example, if data in certain areas changes rapidly, the sampling frequency can be increased; if data changes slowly, the sampling frequency can be appropriately reduced. Furthermore, data collected by different monitoring devices is synchronized to ensure temporal consistency across all data. This process results in time-calibrated data.

[0053] Data preprocessing: Further processing of the time series calibration data involves data cleaning (removing noise and duplicate data), normalization (normalizing the data to a consistent dimension), and quantization (discretizing continuous data). These steps improve data quality and consistency, facilitating subsequent analysis and processing. After preprocessing, data in a standardized format is obtained.

[0054] Data spatiotemporal encoding and timeliness analysis: Standard format data is geocoded according to the spatial distribution of monitoring equipment and timestamped. This allows each piece of data to have a clear spatiotemporal identity. Based on this spatiotemporal correlation, the data change rate and transmission delay between adjacent sampling points are calculated to obtain data timeliness parameters. These parameters reflect the real-time nature and dynamic changes of the data.

[0055] Data encapsulation and transmission: Spatiotemporal correlation data and data timeliness parameters are encapsulated into data packets and encoded using a transmission protocol. This ensures that the data has a clear format and identifier during transmission, making it easier to receive and interpret. The result is marine environmental data with spatiotemporal identifiers.

[0056] Data classification and digital coding: Marine environmental data is categorized according to different physical quantities, such as water temperature, salinity, sea level height, wind speed, and air pressure. Each category of data is digitally encoded to enable efficient processing by computer systems. This process yields the ocean data structure.

[0057] Spatiotemporal distribution feature analysis: Physical quantities in the ocean data structure are mapped to their time series and spatial distribution to derive the spatiotemporal distribution features of marine environmental elements. For example, this includes analyzing how water temperature varies over time and space, and how salinity is distributed across different regions. These features can intuitively reflect the dynamics of the marine environment.

[0058] Marine Element Correlation Analysis: Based on temporal and spatial distribution characteristics, this approach conducts coupling analysis and correlation calculations on the interactions between marine environmental elements. For example, this approach analyzes the relationship between water temperature and salinity, and the impact of wind speed on sea level. These analyses generate a marine element correlation matrix, which quantifies the strength of interactions between different elements.

[0059] Analysis of marine environmental state changes: The marine element correlation matrix is ​​input into a dynamic evolution model to analyze the changing patterns of the marine environment. For example, the model can predict future trends in the marine environment and generate environmental evolution sequences. These sequences can provide a scientific basis for marine environmental prediction and management.

[0060] Establishing a digital twin mapping relationship: Based on the environmental evolution sequence, a mapping function is established between the physical ocean environment and the digital space. This mapping function maps the state of the physical ocean environment to the digital space, resulting in a digital twin mapping relationship. This approach enables digital simulation and analysis of the ocean environment.

[0061] Extracting key features of the marine environment: The digital twin mapping relationship is input into a feature extractor to extract key features of the marine environment. For example, key features of water temperature variations and main patterns in salinity distribution are extracted. These key features can be used for further analysis and decision support, resulting in a marine environment feature vector.

[0062] Finally, the ocean digital model is constructed by integrating the ocean environment feature vectors and the digital twin mapping relationship into a model. This model comprehensively reflects the physical characteristics, spatiotemporal distribution, and dynamic changes of the ocean environment, providing a powerful tool for ocean environmental monitoring, prediction, and management.

[0063] Through the above series of steps, efficient collection, processing and analysis of marine environmental monitoring data can be achieved, providing strong support for marine scientific research and marine resource management.

[0064] Furthermore, mapping the ocean digital model to the physical space of the ocean physical model involves defining the ocean space as consisting of three components: physical space, digital space, and the interactive relationship between the two spaces. Entity types exist in the physical space, while modeling models exist in the digital space. The physical space encompasses natural ocean elements, spatiotemporal patterns, and natural variations. The digital space is composed of ocean objects, functions, and relationships. The physical and digital spaces exhibit real-time, two-way interaction, enabling virtual-real interaction and symbiosis between the physical and digital spaces. The interactive relationship between the physical and digital spaces refers to the mapping relationship from physical to digital space, the optimization decision from digital to physical space, and the association between the physical and digital spaces.

[0065] Furthermore, determining the fluorescence intensity of the fluorescence image includes: emitting a laser at each detection node position in the ocean area to be measured, obtaining a fluorescence image under illumination of a fixed intensity of excitation light, obtaining a reference fluorescence emission power based on a mapping relationship between the fluorescence emission power and the fluorescence grayscale value of the fluorescence image; calculating the reference fluorescence emission power based on a fluorescence spectrum integral relationship to obtain a reference fluorescence emission intensity, and determining the fluorescence intensity of the fluorescence image using the reference fluorescence emission intensity.

[0066] Specifically, in the ocean area to be measured, lasers are emitted at various detection node locations. Under the irradiation of excitation light of a fixed intensity, a fluorescence camera is used to capture the fluorescence image produced by the fluorescent molecules, and a power meter is used to measure the power of the illumination light to obtain a baseline fluorescence emission power. At the same time, a spectrometer is used to record the wavelength of the illumination light and the wavelength of the fluorescence emission, thereby obtaining a fluorescence dataset that serves as a fluorescence benchmark. On this basis, the depth, scattering coefficient, and / or absorption coefficient of the fluorescent molecules are further expanded, and changes in illumination light and fluorescence are studied to enrich the fluorescence dataset. Finally, the baseline fluorescence emission intensity is multiplied by the changes in illumination light power and fluorescence power to calculate the final fluorescence emission intensity.

[0067] The process of obtaining a baseline fluorescence emission power involves using a simulated fluorescence light source and adjusting its intensity. Next, a fluorescence camera and power meter are used to detect and collect multiple sets of fluorescence emission power and fluorescence grayscale values, thereby establishing a mapping relationship between fluorescence emission power and fluorescence grayscale values. Next, the grayscale values ​​of the fluorescence image are read and, based on this established mapping relationship, the baseline fluorescence emission power is calculated.

[0068] Obtaining the baseline fluorescence emission intensity involves eliminating interference from excitation light to accurately measure fluorescence emission intensity. A filter is placed in front of the power meter to effectively filter out the excitation light, ensuring that the power meter's measurement results reflect only the power of the fluorescence. The power meter collects the fluorescence emission power and, combined with the integral relationship of the fluorescence spectrum, calculates the baseline fluorescence emission intensity. This process ensures that the fluorescence emission intensity measurement is free from interference from excitation light, thereby improving measurement accuracy and reliability.

[0069] Extended depth, scattering coefficients, and / or absorption coefficients of fluorescent molecules: To more fully investigate the behavior of fluorescent molecules under different conditions, it is necessary to extend the depth, scattering coefficients, and / or absorption coefficients of fluorescent molecules and calculate changes in illumination and fluorescence.

[0070] Set parameter ranges and calculate changes: Fluorescence Molecular Depth: Set the depth range for fluorescent molecules, for example, from 0 to 10 meters. Also, set the wavelength of the illumination light and calculate the changes after the illumination light propagates at different depths, recording this as the change in illumination light power. Similarly, set the fluorescence emission wavelength and calculate the changes after the fluorescence light propagates at different depths, recording this as the change in fluorescence power.

[0071] Scattering Coefficient and Absorption Coefficient: Set the range of the scattering coefficient and absorption coefficient, for example, from 0.1 to 1.0 for the scattering coefficient and from 0.01 to 0.1 for the absorption coefficient. Calculate the changes in illumination and fluorescence under these coefficients, and record them as the change in illumination power and fluorescence power, respectively.

[0072] Depth Range Extension and Calculation: Expand the depth range of fluorescent molecules to a specific interval, such as 0 to 10 meters. Set the depth sampling rate to one sample per meter, generating a series of depth values ​​with a resolution of 1 meter. For each depth value, calculate the change in illumination power and fluorescence power. This allows for detailed analysis of the changes in illumination and fluorescence at different depths.

[0073] Scattering and Absorption Coefficient Range Expansion and Calculation: The scattering coefficient range is expanded to 0.1 to 1.0, and the scattering sampling rate is set to sample every 0.1, resulting in a series of scattering values ​​with a resolution of 0.1. For each scattering value, the change in illumination power and fluorescence power is calculated. Similarly, the absorption coefficient range is expanded to 0.01 to 0.1, and the absorption sampling rate is set to sample every 0.01, resulting in a series of absorption values ​​with a resolution of 0.01. For each absorption value, the change in illumination power and fluorescence power is calculated.

[0074] By following these steps, we can systematically study the behavior of fluorescent molecules at different depths, scattering coefficients, and absorption coefficients, thereby gaining a more comprehensive understanding of the dynamics of fluorescence. This data can be used to further analyze the properties of fluorescent molecules and their performance under different environmental conditions.

[0075] Further, using the reference fluorescence emission intensity, determining the fluorescence intensity includes:

[0076] A1=A2×B×C

[0077] Among them, A1 is the fluorescence intensity of the fluorescence image, A2 is the baseline fluorescence emission intensity, B is the illumination light power change, and C is the fluorescence power change.

[0078] Furthermore, the concentration of oil pollutants at each node is weighted according to the pollutant level, including:

[0079]

[0080] Among them, C i is the pollution concentration of the ith node, W1, W2, W3 represent different weights and C2 is the pollution level value preset, W(C i ) is the weight of node i.

[0081] This embodiment also provides an intelligent monitoring system for marine oil pollution, including: a digital model construction module, used to obtain marine environmental data with time and space identification in the marine area to be tested, digitally model the marine environmental data, obtain a marine digital model, and map the marine digital model to the physical space of a marine physical model to depict the law of marine environmental change; a pollution concentration detection module, used to obtain fluorescent images of each detection node in the marine area to be tested, determine the fluorescence intensity of the fluorescent image, and obtain the oil pollutant concentration according to the corresponding relationship between the fluorescence intensity and the concentration of oil pollutants in the water body; a pollution concentration display module, used to assign weights to the oil pollutant concentrations of each node according to the pollutant level, and map them to the marine physical model to display the law of change of the oil pollutant concentration in the ocean.

[0082] Furthermore, the digital model construction module includes: a digital model construction unit, which is used to obtain marine environmental data with time and space identification in the marine area to be tested; the marine environmental data include: water temperature field, salinity field, sea level height field, wind speed field and air pressure field; the marine environmental data are classified and digitally encoded according to the water temperature field, salinity field, sea level height field, wind speed field and air pressure field to obtain the marine data structure; the physical quantities in the marine data structure are mapped in time series and spatial distribution to obtain the spatiotemporal distribution characteristics of the marine environmental elements, and the interaction relationship between the marine environmental elements is coupled analyzed and the correlation degree is calculated based on the spatiotemporal distribution characteristics to obtain the marine element association matrix, and the marine element association matrix is ​​input into the dynamic evolution model to analyze the law of change of the marine environmental state to obtain the environmental evolution sequence; based on the environmental evolution sequence, a mapping function between the physical marine environment and the digital space is established to obtain a digital twin mapping relationship, and the digital twin mapping relationship is input into the feature extractor to extract the key features of the marine environment to obtain the marine environment feature vector, and the marine environment feature vector and the digital twin mapping relationship are model integrated to construct an marine digital model.

[0083] Furthermore, the pollution concentration detection module includes: a fluorescence intensity detection module, which is used to emit laser at each detection node position in the ocean area to be measured, obtain a fluorescence image under the illumination of fixed intensity excitation light, obtain a reference fluorescence emission power based on the mapping relationship between the fluorescence emission power and the fluorescence grayscale value of the fluorescence image, calculate the reference fluorescence emission power according to the fluorescence spectrum integral relationship, obtain the reference fluorescence emission intensity, and use the reference fluorescence emission intensity to determine the fluorescence intensity of the fluorescence image; a pollution concentration detection unit, which is used to obtain the concentration of petroleum pollutants according to the corresponding relationship between the fluorescence intensity and the concentration of petroleum pollutants in the water body.

[0084] The embodiments described above are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by persons skilled in the art should fall within the scope of protection defined by the claims of the present invention.

Claims

1. A method for intelligent monitoring of marine oil pollution, characterized in that: include: Acquire ocean environment data with time and space identification in the ocean area to be measured, perform digital modeling on the ocean environment data to obtain an ocean digital model, and map the ocean digital model to the physical space of the ocean physical model to depict the law of change of the ocean environment; Acquire a fluorescence image of each detection node in the ocean area to be measured, determine the fluorescence intensity of the fluorescence image, and obtain the concentration of the petroleum pollutants according to the corresponding relationship between the fluorescence intensity and the concentration of the petroleum pollutants in the water body; The oil pollutant concentration at each node is weighted according to the pollutant level and mapped to the ocean entity model to show the changing pattern of oil pollutant concentration in the ocean.

2. The method for intelligent monitoring of marine oil pollution according to claim 1, characterized in that: Acquiring the marine environment data includes: collecting and standardizing the water temperature, salinity, sea level, wind speed and air pressure data in the ocean area to be measured to obtain the marine environment data.

3. The intelligent monitoring method for marine oil pollution according to claim 1, characterized in that: Acquiring the ocean digital model includes: Classifying and digitally encoding the ocean environment data according to water temperature field, salinity field, sea level height field, wind speed field and air pressure field to obtain an ocean data structure; Performing time series and spatial distribution mapping on the physical quantities in the ocean data structure to obtain the spatiotemporal distribution characteristics of the ocean environment elements; Based on the spatiotemporal distribution characteristics, coupling analysis and correlation calculation are performed on the interaction relationship between the marine environmental elements to obtain a marine element correlation matrix; Inputting the ocean element correlation matrix into a dynamic evolution model to analyze the changing rules of the ocean environment state and obtain an environmental evolution sequence; A mapping function between the physical ocean environment and the digital space is established based on the environmental evolution sequence to obtain a digital twin mapping relationship, and the digital twin mapping relationship is input into a feature extractor to extract key features of the ocean environment to obtain an ocean environment feature vector; The ocean environment feature vector and the digital twin mapping relationship are model integrated to construct the ocean digital model.

4. The method for intelligent monitoring of marine oil pollution according to claim 1, characterized in that: Determining the fluorescence intensity of the fluorescence image includes: Emitting laser light at each detection node position in the ocean area to be measured, obtaining the fluorescence image under the illumination of the excitation light with a fixed intensity, and obtaining the reference fluorescence emission power based on the mapping relationship between the fluorescence emission power and the fluorescence grayscale value of the fluorescence image; The reference fluorescence emission power is calculated according to the fluorescence spectrum integral relationship to obtain a reference fluorescence emission intensity, and the fluorescence intensity of the fluorescence image is determined using the reference fluorescence emission intensity.

5. The method for intelligent monitoring of marine oil pollution according to claim 4, characterized in that: Determining the fluorescence intensity using the reference fluorescence emission intensity includes: A1=A2×B×C Among them, A1 is the fluorescence intensity of the fluorescence image, A2 is the baseline fluorescence emission intensity, B is the illumination light power change, and C is the fluorescence power change.

6. The method for intelligent monitoring of marine oil pollution according to claim 1, characterized in that: The concentration of oil pollutants at each node is weighted according to the pollutant level, including: Among them, C i is the pollution concentration of the ith node, W1, W2, W3 represent different weights and C2 is the pollution level value preset, W(C i ) is the weight of node i.

7. An intelligent monitoring system for marine oil pollution, characterized in that: include: A digital model building module is used to obtain marine environmental data with time and space identification in the ocean area to be measured, perform digital modeling on the marine environmental data, obtain a marine digital model, and map the marine digital model to the physical space of the marine physical model to depict the law of marine environmental change; a pollution concentration detection module, configured to obtain a fluorescence image of each detection node in the ocean area to be detected, determine the fluorescence intensity of the fluorescence image, and obtain the concentration of the petroleum pollutants according to a corresponding relationship between the fluorescence intensity and the concentration of the petroleum pollutants in the water body; The pollution concentration display module is used to assign weights to the oil pollutant concentrations at each node according to the pollutant level and map them to the ocean entity model to display the changing pattern of oil pollutant concentrations in the ocean.

8. The intelligent marine oil pollution monitoring system according to claim 7 is characterized in that: The digital model building module includes: A digital model building unit is used to obtain ocean environment data with time and space identification in the ocean area to be measured; the ocean environment data includes: water temperature field, salinity field, sea level height field, wind speed field and air pressure field; Classifying and digitally encoding the ocean environment data according to water temperature field, salinity field, sea level height field, wind speed field and air pressure field to obtain an ocean data structure; Performing time series and spatial distribution mapping on the physical quantities in the ocean data structure to obtain spatiotemporal distribution characteristics of ocean environmental elements, performing coupling analysis and correlation calculation on the interaction relationships between ocean environmental elements based on the spatiotemporal distribution characteristics to obtain an ocean element correlation matrix, inputting the ocean element correlation matrix into a dynamic evolution model to analyze the law of change of ocean environmental state and obtain an environmental evolution sequence; Based on the environmental evolution sequence, a mapping function between the physical ocean environment and the digital space is established to obtain a digital twin mapping relationship, and the digital twin mapping relationship is input into a feature extractor to extract key features of the ocean environment to obtain an ocean environment feature vector. The ocean environment feature vector and the digital twin mapping relationship are model integrated to construct the ocean digital model.

9. The intelligent marine oil pollution monitoring system according to claim 7, characterized in that: The pollution concentration detection module includes: a fluorescence intensity detection module configured to emit laser light at each detection node position in the ocean area to be measured, obtain the fluorescence image under illumination of fixed-intensity excitation light, obtain a reference fluorescence emission power based on a mapping relationship between fluorescence emission power and fluorescence grayscale value of the fluorescence image, calculate the reference fluorescence emission power based on a fluorescence spectrum integral relationship to obtain a reference fluorescence emission intensity, and determine the fluorescence intensity of the fluorescence image using the reference fluorescence emission intensity; The pollution concentration detection unit is used to obtain the concentration of petroleum pollutants in the water according to the corresponding relationship between the fluorescence intensity and the concentration of petroleum pollutants in the water body.

Images