A big data visualization system for marine equipment

Abstract

This invention discloses a big data visualization system for marine equipment, specifically relating to the field of visualization technology. It involves collecting underwater environmental monitoring data, equipment operating status data, and location information data from marine equipment; analyzing the abnormal change characteristics of the underwater environmental monitoring data and the spatial distribution characteristics of the location information data to generate environmental anomaly characteristic data and location spatial characteristic data; analyzing the operating trend characteristics and historical fault mode characteristics of the equipment operating status data to obtain equipment status trend data and historical fault characteristic data; outputting a marine environment visualization layer through spatial coupling analysis; outputting an equipment operation prediction visualization layer through equipment status prediction analysis; and merging the marine environment visualization layer and the equipment operation prediction visualization layer to form a unified multi-dimensional visualization interface; thus achieving a comprehensive and intuitive display of marine equipment operating data and environmental data.

Description

Technical Field

[0001] This invention relates to the field of visualization technology, and more specifically, to a big data visualization system for marine equipment. Background Technology

[0002] With the deepening of marine development and exploration, a large number of marine equipment are being widely used in marine environmental monitoring and resource development. In actual operation, this marine equipment generates a large amount of complex, multi-dimensional data.

[0003] Traditional data processing and visualization methods typically perform isolated analysis on single data types, making it difficult to effectively reveal the complex correlation between marine equipment data and environmental data. This results in incomplete risk assessment of equipment operation and difficulty in timely and accurate identification of abnormal environmental events, thereby increasing the safety risks of equipment operation and the uncertainty of marine operation decisions. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a big data visualization method and system for marine equipment to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: A big data visualization system for marine equipment, comprising: Data acquisition module: Acquires equipment operation status data and environmental perception data of marine equipment, performs data time-series synchronization and standardized preprocessing, and generates a multi-source data set of marine equipment in a unified format; Feature Analysis Module: Based on multi-source data sets of marine equipment, it generates equipment operation status feature data for real-time analysis of equipment operation status and environmental situation awareness feature data for real-time analysis of environmental situation. Status Analysis Module: Analyzes abnormal trends in equipment operation status based on equipment operation status characteristic data, and outputs equipment failure risk prediction data; Spatial Modeling Module: Identifies high-risk areas in complex marine environments based on environmental situational awareness feature data, and outputs environmental risk area identification data; Status prediction module: Based on equipment failure risk prediction data and environmental risk area identification data, establish a risk linkage assessment model and output comprehensive risk assessment data for marine equipment operation; Layer fusion module: Based on the comprehensive risk assessment data of marine equipment operation, spatial mapping and dynamic rendering are performed to generate a real-time big data visualization interface that integrates the risk status of marine equipment with the environmental situation.

[0006] In a preferred embodiment, equipment operation status data and environmental perception data of marine equipment are acquired, and data time-series synchronization and standardization preprocessing are performed to generate a unified format multi-source data set of marine equipment, specifically: Collect underwater environmental monitoring data, equipment operating status data, and location information data output by sensors on marine equipment; Underwater environmental monitoring data, equipment operation status data, and location information data are uniformly timestamped and time-series synchronized. Denoising was performed on the underwater environment monitoring data, equipment operation status data, and location information data after time-synchronized processing. The underwater environmental monitoring data, equipment operation status data, and location information data after denoising are processed to unify the data format, forming a standardized comprehensive dataset for marine equipment.

[0007] In a preferred embodiment, based on a multi-source data set of marine equipment, equipment operating status characteristic data for real-time analysis of equipment operating status and environmental situation awareness characteristic data for real-time analysis of environmental situation are generated, specifically as follows: Based on a standardized comprehensive dataset of marine equipment, time-series comparisons are made of various monitoring indicators in underwater environmental monitoring data to extract abnormal change characteristics of underwater environmental monitoring data in the time dimension and generate environmental anomaly characteristic data. Based on a standardized comprehensive dataset of marine equipment, spatial clustering analysis is used to process the location information data, identify the spatial clustering areas of marine equipment, determine the spatial distribution patterns of the spatial clustering areas in different time periods, and generate location spatial feature data.

[0008] In a preferred embodiment, based on a comprehensive marine equipment dataset, the operational trend characteristics and historical failure mode characteristics of the equipment operating status data are analyzed to generate equipment status trend data and historical failure characteristic data, specifically: Based on a standardized comprehensive dataset of marine equipment, trend feature analysis is performed on equipment operation status data in a continuous time sequence to generate equipment status trend data. Based on a standardized comprehensive dataset of marine equipment, historical fault data is used to extract pattern features of fault events from equipment operating status data, thereby generating historical fault feature data.

[0009] In a preferred embodiment, spatial coupling analysis is performed based on environmental anomaly feature data and location spatial feature data to establish a spatial visualization model of the marine environmental anomaly area, and a marine environmental visualization layer is output, specifically: Spatial interpolation methods are used to perform spatial continuity analysis on the abnormal change features in environmental anomaly feature data to obtain the spatial continuity distribution results of the abnormal change features; Spatial statistical methods were used to perform spatial density analysis on spatial clustering locations in spatial feature data at different time periods to obtain the density distribution results of spatial location clustering locations. Spatial coupling analysis is performed on the spatial continuity distribution results and spatial density distribution results to determine the spatial coupling relationship between anomalous change characteristics and spatial location clustering areas; Based on spatial coupling relationships, a spatial visualization model of abnormal marine environmental areas is established, and a marine environmental visualization layer is output.

[0010] In a preferred embodiment, equipment status prediction analysis is performed based on equipment status trend data and historical fault characteristic data to establish a marine equipment operation status prediction visualization model, and outputs an equipment operation prediction visualization layer, specifically as follows: Time series forecast analysis is performed on equipment status trend data to obtain the predicted operating trend of marine equipment; Statistical analysis methods were used to analyze historical failure characteristic data to obtain the types of failure events that occurred in marine equipment and the corresponding predicted probability distribution results. The prediction results of the operation trend of marine equipment are correlated and matched with the failure event types and corresponding prediction probability distribution results to determine the prediction relationship between the operation trend of marine equipment and failure events. Based on the predictive relationships, a visualization model for predicting the operational status of marine equipment is established, and a visualization layer for predicting equipment operation is output.

[0011] In a preferred embodiment, the marine environment visualization layer and the equipment operation prediction visualization layer are integrated to generate a unified multi-dimensional visualization interface, specifically: Synchronize the marine environment visualization layer and the equipment operation prediction visualization layer on the time axis and align their spatial coordinates. Overlay synchronized and aligned layers to create a multi-dimensional visual layout that includes a spatial view, a time-series view, and an interactive control area. Set interactive control methods for layer switching and data filtering in a multi-dimensional visualization layout; Real-time graphics rendering is performed on the layers after interactive control to generate a unified multi-dimensional visualization interface.

[0012] The technical effects and advantages of the big data visualization system for marine equipment proposed in this invention are as follows: Underwater environmental monitoring data, equipment operating status data, and location information data are synchronized in time and filtered for noise to form a comprehensive dataset for marine equipment, improving data integrity and accuracy. By analyzing the characteristics of abnormal changes and spatial distribution, the correlation between abnormal environmental areas and equipment activity trajectories can be intuitively revealed, providing a dynamic early warning basis for marine environmental monitoring. Analysis of operational trend characteristics and historical failure mode characteristics generates equipment status trend data and historical failure characteristic data, providing a reliable reference for equipment health assessment. Through spatial coupling analysis of environmental anomaly characteristic data and location spatial characteristic data, a spatial visualization model of abnormal marine environmental areas is established, realizing an intuitive presentation of marine environmental risk areas in three-dimensional space. Through predictive analysis of equipment status trend data and historical failure characteristic data, a predictive visualization model of marine equipment operating status is established, enabling the early detection of potential fault hazards. By merging the marine environmental visualization layer and the equipment operation prediction visualization layer, a multi-dimensional visualization interface is generated, achieving synchronous display of the marine environment and equipment status, significantly improving the operational safety of marine equipment and the efficiency of environmental monitoring. Attached Figure Description

[0013] Figure 1 This is a schematic diagram of the structure of a big data visualization system for marine equipment according to the present invention. Detailed Implementation

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention. Example 1

[0015] Figure 1 The present invention discloses a big data visualization system for marine equipment, comprising: Data acquisition module: Acquires equipment operation status data and environmental perception data of marine equipment, performs data time-series synchronization and standardized preprocessing, and generates a multi-source data set of marine equipment in a unified format; Feature Analysis Module: Based on multi-source data sets of marine equipment, it generates equipment operation status feature data for real-time analysis of equipment operation status and environmental situation awareness feature data for real-time analysis of environmental situation. Status Analysis Module: Analyzes abnormal trends in equipment operation status based on equipment operation status characteristic data, and outputs equipment failure risk prediction data; Spatial Modeling Module: Identifies high-risk areas in complex marine environments based on environmental situational awareness feature data, and outputs environmental risk area identification data; Status prediction module: Based on equipment failure risk prediction data and environmental risk area identification data, establish a risk linkage assessment model and output comprehensive risk assessment data for marine equipment operation; Layer fusion module: Based on the comprehensive risk assessment data of marine equipment operation, spatial mapping and dynamic rendering are performed to generate a real-time big data visualization interface that integrates the risk status of marine equipment with the environmental situation.

[0016] Acquire equipment operation status data and environmental perception data of marine equipment, perform time-series synchronization and standardized preprocessing, and generate a unified format multi-source data set for marine equipment, including: Collect underwater environmental monitoring data, equipment operating status data, and location information data output by sensors on marine equipment; Marine equipment refers to marine monitoring devices that are deployed in the marine environment for long or short periods and are capable of autonomous or remote control, such as underwater vehicles, underwater robots, deep-sea exploration equipment, and underwater sensor network nodes. An example of an underwater vehicle will be used for illustration.

[0017] Underwater environmental monitoring data includes physical and chemical parameters of the marine environment such as temperature, salinity, water flow velocity, underwater pressure, and dissolved oxygen. These data are collected by specialized sensors installed on underwater vehicles. For example, temperature sensors collect real-time temperature data, salinity sensors collect real-time salinity data, current meters collect real-time water flow velocity data, pressure sensors collect real-time underwater pressure data, and oxygen sensors collect real-time dissolved oxygen data.

[0018] The equipment's operational status data includes the underwater vehicle's own battery voltage data, battery charge data, thruster operating current data, thruster speed data, internal temperature data, internal humidity data, and operational status indicator data of the control system. These data are collected in real time by status monitoring sensors installed in the underwater vehicle's battery module, thruster module, and avionics compartment. For example, voltage sensors collect battery voltage data in real time, current sensors collect thruster operating current data in real time, speed sensors collect thruster speed data in real time, temperature and humidity sensors collect internal temperature and humidity data of the underwater vehicle in real time, and the controller outputs operational status indicator data of the control system.

[0019] Location information data includes the underwater vehicle's real-time spatial location in the ocean, such as longitude, latitude, depth, and navigation trajectory data, which is acquired in real time through the underwater vehicle's onboard inertial navigation system or underwater acoustic positioning system. For example, the inertial navigation system outputs the underwater vehicle's position coordinates and navigation path data in real time, or it receives position correction data sent by a surface base station through an underwater acoustic communication unit.

[0020] Underwater environmental monitoring data, equipment operation status data, and location information data are uniformly timestamped and time-series synchronized. All sensor output data is processed with a unified timestamp. For example, each temperature, salinity, voltage, and location coordinate data is automatically appended with a unified timestamp, such as year, month, day, hour, minute, and second, during generation. Based on the unified timestamp, all different types of data streams are arranged and aligned according to a unified time sequence, thus forming multiple data streams with a completely consistent timeline.

[0021] Denoising was performed on the underwater environment monitoring data, equipment operation status data, and location information data after time-synchronized processing. Appropriate filtering algorithms are selected for denoising different types of data. For example, moving average filtering algorithms are used to process potential random interference and data noise in temperature, salinity, and pressure data; low-pass filtering algorithms are used to denoise potential high-frequency noise components in voltage, current, and speed data in equipment operation status data; and Kalman filtering algorithms are used to process longitude, latitude, and depth coordinate data to remove potential positioning jumps or errors in location information data. These methods effectively remove noise components from various types of data, thereby improving data accuracy.

[0022] The underwater environmental monitoring data, equipment operation status data, and location information data after denoising are processed to unify the data format and form a standardized comprehensive dataset of marine equipment. To address the differences in data output formats from various sensors, a standardized format conversion process is implemented. For example, data from different sensors is uniformly converted into a structured numerical data format, with each data point containing a standardized timestamp field, data type field, sensor identifier field, and numerical field, and stored and processed with uniform numerical precision. Simultaneously, different types of data are saved according to a unified data storage standard, such as a relational database or time-series database format.

[0023] Based on multi-source data sets of marine equipment, equipment operating status characteristic data for real-time analysis of equipment operating status and environmental situation awareness characteristic data for real-time analysis of environmental situation are generated, including: Based on a standardized comprehensive dataset of marine equipment, time-series comparisons are made of various monitoring indicators in underwater environmental monitoring data to extract abnormal change characteristics of underwater environmental monitoring data in the time dimension and generate environmental anomaly characteristic data. Taking water temperature data as an example, the temperature data collected by the underwater vehicle over a continuous period of time is arranged chronologically. The numerical differences between different time points are calculated, and temperature changes exceeding the normal fluctuation range are identified as abnormal fluctuations, manifested as rapid increases or decreases in temperature. For example, a sudden increase in water temperature from 5 degrees Celsius to 8 degrees Celsius within a short period is an abnormal fluctuation; a slow temperature change over a longer period is considered normal. After identifying abnormal fluctuations, the start and end times of the abnormal fluctuations are determined, defining the duration of the abnormal fluctuation, i.e., the temporal interval of the abnormal fluctuation. The intensity of the abnormal fluctuation is determined by calculating the absolute value of the difference between the start and end times of the abnormal fluctuation; for example, the intensity of the temperature change is 3 degrees Celsius. Simultaneously, the total number of occurrences and average frequency of this type of abnormal fluctuation are statistically analyzed throughout the entire analysis period. For example, if this type of abnormal temperature fluctuation occurs 5 times in 24 hours, the frequency is an average of once every 4.8 hours. Similarly, the data on salinity, water flow velocity, underwater pressure, and dissolved oxygen concentration in the water are analyzed in turn to generate environmental anomaly characteristic data, including the time interval of the abnormal fluctuations, the intensity of the abnormal fluctuations, and the frequency of the abnormal fluctuations.

[0024] Based on a standardized comprehensive dataset of marine equipment, spatial clustering analysis is used to process the location information data, identify the spatial clustering locations of marine equipment, determine the spatial distribution patterns of these locations over different time periods, and generate location spatial feature data. Location information data refers to the spatial information data, such as the longitude, latitude, depth coordinates, and navigation trajectory, recorded in real time by the underwater vehicle. This data is also an important component of the standardized marine equipment comprehensive dataset in step S1. Spatial clustering analysis is used to process the location information data. Based on the density of the spatial coordinate data, the location of the marine equipment is divided, with higher-density coordinate points grouped into the same cluster, and lower-density coordinate points grouped into other clusters or identified as discrete regions. For example, if the underwater vehicle repeatedly located within the spatial range of 120.5°E to 121°E longitude, 22°N to 22.5°N latitude, and 300 meters to 500 meters depth during monitoring, this area is identified as a spatially clustered location region.

[0025] After identifying the spatial clustering locations, clustering pattern analysis is performed on different time periods to determine the spatial distribution pattern of marine equipment location information data within those time periods. For example, a certain area may only have a dense concentration of marine equipment locations during specific time periods (such as 2 PM to 4 PM daily), constituting a specific spatial distribution pattern within that time period. Analysis can be conducted by dividing the day into different time periods, for example, using each 4-hour interval as a time interval, and statistically analyzing the number and density of equipment locations within each time interval to derive the spatial distribution characteristics of the spatial clustering locations within different time periods. The coordinates of the spatial clustering locations, the spatial clustering intensity (location density) of each area at different time periods, and the repetitive patterns of spatial location clustering within each time period are then formatted into a unified numerical data format to generate spatial feature data.

[0026] Based on a comprehensive dataset of marine equipment, the operational trend characteristics and historical failure mode characteristics of equipment operating status data are analyzed to generate equipment status trend data and historical failure characteristic data, including: Based on a standardized comprehensive dataset of marine equipment, trend feature analysis is performed on equipment operation status data in a continuous time sequence to generate equipment status trend data. Taking battery voltage data from equipment operating status data as an example, the continuously collected battery voltage data is arranged in chronological order. For instance, during the monitoring period, the battery voltage is recorded once per minute for 24 hours, resulting in a total of 1440 data points, forming a continuous battery voltage data sequence. Trend characteristic analysis is then performed on the battery voltage data sequence. Trend characteristic analysis refers to using mathematical statistical analysis to determine the direction, intensity, and duration of battery voltage changes over time. For example, by calculating the difference in battery voltage data between adjacent time points, it can be determined whether the voltage is gradually increasing or decreasing. For instance, if the battery voltage gradually decreases from 48 volts at the beginning to 44 volts at the end of the monitoring, it indicates an overall downward trend, which is the trend direction. Based on the trend direction, the trend intensity is determined, which refers to the magnitude of battery voltage change per unit time. For example, an average voltage decrease of 0.17 volts per hour reflects the trend intensity. The trend duration refers to the length of time the battery voltage continues to decrease, which is 24 hours. Using a similar method, trend characteristic analysis was performed on battery power, thruster operating current, thruster speed, and internal temperature and humidity data. For example, if the thruster operating current gradually increased from 2 amps to 5 amps over a certain period, the trend direction would be current increase, the trend strength would be 0.05 amps per minute, and the trend duration would be 60 minutes. Based on the above analysis, equipment status trend data was generated, including trend direction, trend strength, and trend duration.

[0027] Based on a standardized comprehensive dataset of marine equipment, historical fault data is used to extract pattern features of fault events from equipment operating status data to generate historical fault feature data. Historical fault event data records the status information of various fault events that occurred during the historical operation of marine equipment, such as abnormal battery voltage drops, abnormal thruster shutdowns, abnormal internal temperature increases, and control system restarts. Taking abnormal thruster shutdown as an example, this refers to a situation where the thruster stops rotating during normal operation. During feature extraction, the timing of all abnormal thruster shutdown events is identified. For example, if three abnormal thruster shutdown events occur at 10:05 AM, 1:20 PM, and 4:40 PM respectively, the timing pattern of these fault events indicates a relatively concentrated occurrence within specific time periods.

[0028] After determining the event type and timing pattern, the changes in equipment status before and after each failure are analyzed. Taking a thruster abnormal shutdown event as an example, within 10 minutes before the event, an abnormal increase in the thruster operating current may be observed, for example, from the normal 3 amps to 4.5 amps. Within a few minutes after the event, the current drops to 0 amps. The equipment voltage data accompanying the thruster abnormal shutdown event may also decrease before the failure, such as from the normal 48 volts to 45 volts. Through analysis of multiple similar thruster abnormal shutdown events in historical data, typical status change patterns before and after the event are summarized, including trends in parameters such as current, voltage, and temperature.

[0029] The frequency of equipment failures was statistically analyzed. For example, during a continuous 7-day monitoring period, the thruster abnormal shutdown event occurred a total of 10 times, meaning the frequency of failure events was approximately 1.43 times per day on average; abnormal internal temperature rise events occurred 5 times per week, with a frequency of approximately 0.71 times per day; and control system restart events occurred 3 times per month, with a frequency of 0.1 times per day. Through the above analysis and statistics, the event types of equipment failures, the temporal patterns of equipment failures, the changes in the state of equipment before and after failures, and the frequency of equipment failures were summarized to generate historical failure characteristic data.

[0030] Spatial coupling analysis is performed based on environmental anomaly characteristic data and location spatial characteristic data to establish a spatial visualization model of marine environmental anomaly areas, and output marine environmental visualization layers, including: Spatial interpolation methods are used to perform spatial continuity analysis on the abnormal change features in environmental anomaly feature data to obtain the spatial continuity distribution results of the abnormal change features; Environmental anomaly characteristic data includes the abnormal fluctuation characteristics of multiple environmental monitoring parameters, such as water temperature, salinity, water flow velocity, underwater pressure, and dissolved oxygen concentration, within a specific time dimension, including the time interval of the abnormal fluctuation, the intensity of the abnormal fluctuation, and the frequency of the abnormal fluctuation.

[0031] Environmental anomaly data is generated only at the discrete spatial location of the sensor acquisition points, but in actual monitoring, marine environmental anomalies usually exhibit spatial continuity. Therefore, spatial interpolation methods are used to convert discrete data into continuous spatial data. Spatial interpolation methods include inverse distance weighted interpolation, kriging interpolation, and natural neighborhood interpolation, etc., with kriging interpolation as an example for explanation.

[0032] For example, when an underwater vehicle records anomaly data in water temperature at multiple locations at different latitudes, longitudes, and depths during monitoring in a marine area, such as 120.2°E, 22.1°N, 400 meters deep; 120.3°E, 22.15°N, 450 meters deep; and 120.4°E, 22.2°N, 480 meters deep, the anomaly characteristics at each location are the magnitude, duration, and frequency of the temperature rise. Using the Kriging interpolation method, these discrete data points are used as the original data points for interpolation. First, a spatial variogram is established based on the known anomaly characteristic values ​​to describe the spatial correlation and variation patterns of the anomaly characteristic data across different spatial locations. Then, interpolation is performed at locations not actually measured using the spatial variogram to obtain the anomaly characteristic values ​​for these unmeasured locations. For example, by using measured data points and spatial interpolation, abnormal temperature change characteristic values ​​of unmeasured points such as longitude 120.25°E, latitude 22.125°N, and depth 420 meters can be calculated. The interpolated calculation points and the actual measurement points form a spatially continuous data distribution, thereby obtaining a complete spatially continuous distribution result of abnormal change characteristics.

[0033] Spatial statistical methods were used to perform spatial density analysis on spatial clustering locations in spatial feature data at different time periods to obtain the density distribution results of spatial location clustering locations. Locational spatial characteristic data includes the coordinate ranges of areas where marine equipment appears frequently during continuous monitoring, such as longitude 120.5°E to 121°E, latitude 22°N to 22.5°N, and depth 300 meters to 500 meters, as well as the spatial clustering intensity and location density of each area at different time periods. Spatial statistical methods include kernel density estimation, spatial hotspot analysis, and spatial autocorrelation analysis. Kernel density estimation will be used as an example for explanation.

[0034] For example, during a continuous 7-day monitoring period, the latitude, longitude, and depth information recorded by underwater vehicles from multiple locations showed spatial clustering, particularly during specific time periods each day, such as 2 PM to 4 PM. Marine equipment was most frequently observed within the range of 120.6°E to 120.8°E longitude, 22.2°N to 22.3°N latitude, and 350 to 400 meters depth. Kernel density estimation was used to calculate the spatial density of all recorded points within this area. This method uses each spatial recording location as the center and assigns different weights based on distance within a certain spatial range to calculate the density value of locations in the vicinity of each location. Higher density values ​​indicate a higher density of equipment presence, while lower density values ​​indicate a relatively sparse distribution. Using this method, a spatial density distribution map of the entire monitoring area was obtained. Different colored areas in the spatial density distribution map represent different density values, thus showing the density distribution of spatially clustered areas over different time periods—this is the density distribution result of the spatially clustered areas.

[0035] Spatial coupling analysis is performed on the spatial continuity distribution results and spatial density distribution results to determine the spatial coupling relationship between anomalous change characteristics and spatial location clustering areas; Spatial coupling analysis refers to the comparison of the continuous spatial distribution of environmental anomaly characteristics with the density distribution of spatially clustered areas using spatial overlay or cross-analysis methods to determine whether a spatial correlation exists. For example, when overlaying a continuous spatial distribution map of anomaly water temperature characteristics with a density distribution map of equipment locations, if the anomaly in water temperature overlaps with or is adjacent to areas with high location density, it indicates a spatial coupling relationship between the anomaly and the locations where marine equipment is densely located. If the anomaly does not overlap or is not adjacent to the areas with dense equipment locations, it indicates no spatial coupling relationship. Through this analysis, the spatial correlation or non-correlation between the anomaly data and the spatial location data is determined, and the spatial coupling relationship between the anomaly and the clustered locations is recorded.

[0036] A spatial visualization model of the marine environment anomaly area is established based on the spatial coupling relationship, and a marine environment visualization layer is output. Spatial visualization models refer to representing spatial coupling relationships in a visual graphical or image-based manner. For example, using a geographic information system platform, a three-dimensional visualization environment can be constructed using latitude and longitude coordinates and depth information. Anomalies in the environment within the spatial coupling relationship can be represented by color or spatial outlines. For instance, areas with obvious spatial coupling can be marked as red areas, while areas with less obvious spatial coupling can be marked as green areas, and the result can be output as a marine environment visualization layer.

[0037] Based on equipment status trend data and historical fault characteristic data, equipment status prediction analysis is performed to establish a visualization model for predicting the operating status of marine equipment, and outputting equipment operation prediction visualization layers, including: Time series forecast analysis is performed on equipment status trend data to obtain the predicted operating trend of marine equipment; Equipment status trend data includes the direction, intensity, and duration of the trend in equipment operating status data over time. Equipment operating status data includes battery voltage data, battery charge data, thruster operating current data, thruster speed data, internal temperature data, internal humidity data, and control system operating status indicators, etc. Time series predictive analysis refers to using equipment status trend data and mathematical statistical methods to analyze the possible future evolution trends and characteristics of equipment status. Battery voltage data will be used as an example for illustration.

[0038] The battery voltage trend data is processed. For example, over the past 24 hours, the average battery voltage decreased by 0.17 volts per hour, and the trend was downward. Time series forecasting analysis is used, based on historical voltage trend data, with exponential smoothing as an example. Exponential smoothing assigns different weights to data points at different times based on historical data, with more recent data points having higher weights and earlier data points having lower weights. This yields the possible trend of battery voltage changes over a certain period. For example, predicting the battery voltage over the next 6 hours, it is still possible that the average voltage decrease will be 0.17 volts per hour. Therefore, it can be inferred that the voltage in the first hour may decrease from 44 volts to 43.83 volts, and in the second hour it may continue to decrease to 43.66 volts, and so on, ultimately forming the predicted battery voltage trend for the next 6 hours. The same method was used to predict and analyze battery power data, thruster operating current data, thruster speed data, and internal temperature and humidity data. For example, if the thruster operating current has increased by an average of 0.05 amps per minute over a period of time, based on the trend data, it is predicted that the thruster operating current may continue to rise in the next 30 minutes, from the current 5 amps to 6.5 amps, thus forming the thruster operating current prediction result. All the predicted data were then organized into a unified format to form the marine equipment operation trend prediction result.

[0039] Statistical analysis methods were used to analyze historical failure characteristic data to obtain the types of failure events that occurred in marine equipment and the corresponding predicted probability distribution results. Historical fault characteristic data includes the types of fault events that have occurred in the equipment's history, the temporal patterns of these fault events, the changes in the equipment's state before and after the fault, and the frequency of the fault. The following example illustrates this: An abnormal stoppage fault event in a thruster. Historical fault characteristic data records the number of times thruster abnormal shutdown events occur, for example, 10 thruster abnormal shutdown failures occurring within 7 consecutive days. Statistical analysis methods, such as the Poisson distribution model or Bayesian statistical methods, are used. Taking the Poisson distribution model as an example, the calculation process of the predicted probability distribution of thruster abnormal shutdown events is explained. The Poisson distribution model uses the frequency of historical events as the basis for calculation. For example, if thruster abnormal shutdown events occur 10 times within 7 days, that is, an average of approximately 1.43 times per day, the predicted probability of different numbers of thruster abnormal shutdown events occurring in the next day is calculated. For example, the probability of 0 thruster abnormal shutdowns in the next day is 0.24, the probability of 1 occurrence is 0.35, the probability of 2 occurrences is 0.25, and the probability of 3 or more occurrences is 0.16. These are the predicted probability distribution results for thruster abnormal shutdown events. Similarly, the same statistical analysis method was used for fault events such as abnormal battery voltage drop, abnormal internal temperature rise, and control system restart to calculate the predicted probability distribution of each fault event. For example, the control system restart event occurs an average of 3 times in a month, or about 0.1 times per day. Using the Poisson distribution model, the probability of 0 restarts in the next day is calculated to be 0.9, the probability of 1 restart is 0.09, and the probability of 2 restarts is 0.01, thus forming a complete set of fault event types and their corresponding predicted probability distributions.

[0040] The prediction results of the operation trend of marine equipment are correlated and matched with the failure event types and corresponding prediction probability distribution results to determine the prediction relationship between the operation trend of marine equipment and failure events. Association matching refers to establishing the potential intrinsic relationship between equipment operation trend prediction results and fault event prediction probability distributions through data matching and analysis methods. This will be illustrated using the propeller operating current prediction results and the predicted probability of propeller abnormal shutdown events as an example: For example, time series predictive analysis revealed that the thruster operating current might rise to 6.5 amps in the next 30 minutes. This upward trend was correlated with historical fault characteristic data showing thruster abnormal shutdown events. Historical data indicated that when the thruster operating current exceeded a specific threshold, such as 6 amps, the probability of an abnormal thruster shutdown increased. Based on historical data, when the predicted thruster operating current reached 6.5 amps in the future, correlation matching was performed with data showing a probability of 0.35 for one occurrence and 0.25 for two occurrences of an abnormal thruster shutdown event. This revealed a significant increase in the probability of future abnormal thruster shutdown events. Therefore, it was determined that the upward trend of the thruster operating current and the abnormal thruster shutdown event have a predictive correlation. Similarly, correlation matching analysis was performed between the continuous decrease in battery voltage and abnormal battery voltage decrease events, and between the continuous increase in internal temperature and abnormal internal temperature increase events, respectively, establishing predictive relationships between various equipment operating trends and fault events.

[0041] Based on the predictive relationships, a visualization model for predicting the operational status of marine equipment is established, and a visualization layer for predicting equipment operation is output. A predictive visualization model for operational status refers to the use of computer graphics visualization technology to intuitively and graphically present the predictive relationship between equipment operational trend prediction results and fault event prediction probability distribution results. The following example illustrates this using a timeline graph in a computer graphics system: The predicted results of equipment operation trends and the predicted probabilities of fault events are displayed on a computer graphical interface in the form of a time axis. For example, in the graphical interface, the horizontal axis represents future time, the upper part of the vertical axis represents the equipment operation trend parameters, such as the change trends of voltage, current, temperature, and humidity; the lower part of the vertical axis represents the fault event types and their corresponding predicted probabilities, such as thruster abnormal stop faults, control system restart events, and their corresponding occurrence probabilities. Different trend prediction data and fault prediction probabilities are presented through different colors, line types, and marker methods, and the prediction relationship is reflected through time correspondence and interactive functions in the graph. For example, when moving to a specific time point on the thruster current prediction trend line, a prompt message is displayed indicating that the predicted probability of the thruster abnormal stop event has increased at that moment, thus intuitively showing the correlation between trend prediction and fault probability, forming a visual layer for equipment operation prediction.

[0042] By integrating marine environment visualization layers and equipment operation prediction visualization layers, a unified multi-dimensional visualization interface is generated, including: Synchronize the marine environment visualization layer and the equipment operation prediction visualization layer on the time axis and align their spatial coordinates. Time axis synchronization refers to unifying the time dimension of the marine environment visualization layer and the equipment operation prediction visualization layer. For example, the abnormal environmental parameters displayed in the environmental visualization layer and the predicted equipment operation trend data in the equipment operation prediction visualization layer are both displayed based on the same future time period, such as data for the next 24 hours. This ensures the consistency of the time series between the marine environment visualization layer and the equipment operation prediction visualization layer, forming data representation on the same time axis. Spatial coordinate alignment refers to processing the marine environment visualization layer and the equipment operation prediction visualization layer using a unified spatial reference system. For example, the spatial visualization layer for anomaly areas and the equipment operation prediction visualization layer are both based on a unified spatial coordinate system, such as using the WGS-84 coordinate system or the latitude-longitude-depth coordinate system, ensuring accurate matching of the spatial coordinates between the marine environment visualization layer and the equipment operation prediction visualization layer. For example, if the data for anomaly areas is located between longitude 120.5°E and 121°E, latitude 22°N and 22.5°N, and depth 300 meters to 500 meters, the spatial coordinates of the equipment operation status prediction data also correspond to the same area, ensuring data alignment accuracy during overlay analysis and avoiding data misalignment or coordinate drift.

[0043] Overlay synchronized and aligned layers to create a multi-dimensional visual layout that includes a spatial view, a time-series view, and an interactive control area. Layer overlay refers to simultaneously displaying a marine environment visualization layer (synchronized with the timeline and aligned with spatial coordinates) and an equipment operation prediction visualization layer within a computer graphics visualization system, and then combining them to form a unified layer display. For example, using a GIS (Geographic Information System) platform, abnormal environmental parameter data and predicted equipment operation status data for areas with the same spatial coordinates can be overlaid. Abnormal environmental parameter data can be represented by color gradients or blocks of varying transparency, while predicted equipment operation status data can be overlaid with symbols or markers within the same area. For instance, in areas with dense marine equipment locations, an area predicted to experience an abnormal rise in water temperature over the next 6 hours and a continuous decline in equipment battery voltage can be overlaid to visually demonstrate the correlation between simultaneous environmental anomalies and equipment operation risks within a spatial area. Multi-dimensional visualization layouts include spatial views, time-series views, and interactive control areas. Spatial views are geographic information layer views, such as displaying spatial anomalies and equipment status in the area where marine equipment is located in three dimensions; time series views show the predicted changes in environmental parameters and equipment status over a future period, such as the horizontal axis representing time and the vertical axis representing changes in environmental parameters and equipment status values ​​in a time series graph; interactive control areas refer to the functional areas used by users to control layer display, switching, and data filtering, such as interface elements like buttons, sliders, checkboxes, and drop-down menus, which are laid out in specific areas of the layer display interface, such as the right or bottom area of ​​the interface, where users can operate and control the display method of layer data.

[0044] Set interactive control methods for layer switching and data filtering in a multi-dimensional visualization layout; Layer switching allows users to freely switch between spatial and time-series views using buttons or menus in the interactive control area. For example, by setting a layer switching button, users can switch between an environmental anomaly layer, a device operation trend layer, and an environment-device association layer in 3D space. Data filtering allows users to filter data according to their needs. For example, users can use sliders or checkboxes in the interactive control area to filter the numerical range of specific environmental parameters (such as water temperature and salinity) or specific device status parameters (such as voltage and current). For example, users can use the slider to set a threshold for displaying water temperature anomalies, showing only data areas where the water temperature change intensity is greater than 2 degrees Celsius, or only showing data where the predicted battery voltage drop exceeds 1 volt. Through these interactive control methods, users can intuitively obtain customized, multi-dimensional visualized data displays.

[0045] Real-time graphical rendering of the layers after interactive control generates a unified multi-dimensional visualization interface; Real-time graphics rendering refers to the computer graphics visualization system immediately processing and updating the visualization layer display in real time based on user operations in the interactive control area, such as layer switching or data filtering. For example, when a user sets the threshold for abnormal water temperature to 3 degrees Celsius using a slider, the computer graphics visualization system immediately calculates and updates the corresponding data area, highlighting the abnormal water temperature area in the spatial view in real time, and simultaneously updating the abnormal water temperature curve data for the corresponding time period in the time series view. If the user selects to display the predicted trend of the thruster operating current data in the interactive control area, the computer graphics visualization system calculates and updates the equipment operating status trend markers in the corresponding area of ​​the spatial view in real time. Through this real-time update mechanism, environmental parameters and equipment status data can be updated interactively in real time, forming a multi-dimensional visualization interface that can dynamically respond to user needs. The multi-dimensional visualization interface includes a spatial view of environmental anomalies, a time-series view of equipment operating status trends, and an interactive control area. The various areas of the interface are interconnected. For example, when a user selects a specific area in the spatial view, the time-series view immediately displays the trend data of environmental parameters and equipment status within that area. When a user selects a specific time point in the time-series view, the spatial view immediately highlights the spatial distribution of equipment status and environmental anomalies at that moment, forming a real-time linkage between time and spatial data.

[0046] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0047] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0048] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0049] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0050] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0051] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0052] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0053] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0054] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0055] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A big data visualization system for marine equipment, characterized in that, include: Data acquisition module: Acquires equipment operation status data and environmental perception data of marine equipment, performs data time-series synchronization and standardized preprocessing, and generates a multi-source data set of marine equipment in a unified format; Feature Analysis Module: Based on multi-source data sets of marine equipment, it generates equipment operation status feature data for real-time analysis of equipment operation status and environmental situation awareness feature data for real-time analysis of environmental situation. Status Analysis Module: Analyzes abnormal trends in equipment operation status based on equipment operation status characteristic data, and outputs equipment failure risk prediction data; Spatial Modeling Module: Identifies high-risk areas in complex marine environments based on environmental situational awareness feature data, and outputs environmental risk area identification data; Status prediction module: Based on equipment failure risk prediction data and environmental risk area identification data, establish a risk linkage assessment model and output comprehensive risk assessment data for marine equipment operation; Layer fusion module: Based on the comprehensive risk assessment data of marine equipment operation, spatial mapping and dynamic rendering are performed to generate a real-time big data visualization interface that integrates the risk status of marine equipment with the environmental situation.

2. The big data visualization system for marine equipment according to claim 1, characterized in that, Acquire equipment operation status data and environmental perception data of marine equipment, perform time-series synchronization and standardized preprocessing, and generate a unified format multi-source data set for marine equipment, specifically: Collect underwater environmental monitoring data, equipment operating status data, and location information data output by sensors on marine equipment; Underwater environmental monitoring data, equipment operation status data, and location information data are uniformly timestamped and time-series synchronized. Denoising was performed on the underwater environment monitoring data, equipment operation status data, and location information data after time-synchronized processing. The underwater environmental monitoring data, equipment operation status data, and location information data after denoising are processed to unify the data format, forming a standardized comprehensive dataset for marine equipment.

3. The big data visualization system for marine equipment according to claim 2, characterized in that, Based on multi-source data sets of marine equipment, equipment operating status characteristic data for real-time analysis of equipment operating status and environmental situation awareness characteristic data for real-time analysis of environmental situation are generated, specifically: Based on a standardized comprehensive dataset of marine equipment, time-series comparisons are made of various monitoring indicators in underwater environmental monitoring data to extract abnormal change characteristics of underwater environmental monitoring data in the time dimension and generate environmental anomaly characteristic data. Based on a standardized comprehensive dataset of marine equipment, spatial clustering analysis is used to process the location information data, identify the spatial clustering areas of marine equipment, determine the spatial distribution patterns of the spatial clustering areas in different time periods, and generate location spatial feature data.

4. The big data visualization system for marine equipment according to claim 3, characterized in that, Based on a comprehensive dataset of marine equipment, the operational trend characteristics and historical failure mode characteristics of equipment operating status data are analyzed to generate equipment status trend data and historical failure characteristic data, specifically: Based on a standardized comprehensive dataset of marine equipment, trend feature analysis is performed on equipment operation status data in a continuous time sequence to generate equipment status trend data. Based on a standardized comprehensive dataset of marine equipment, historical fault data is used to extract pattern features of fault events from equipment operating status data, thereby generating historical fault feature data.

5. A big data visualization system for marine equipment according to claim 4, characterized in that, Spatial coupling analysis is performed based on environmental anomaly feature data and location spatial feature data to establish a spatial visualization model of marine environmental anomaly areas, and output a marine environmental visualization layer, specifically: Spatial interpolation methods are used to perform spatial continuity analysis on the abnormal change features in environmental anomaly feature data to obtain the spatial continuity distribution results of the abnormal change features; Spatial statistical methods were used to perform spatial density analysis on spatial clustering locations in spatial feature data at different time periods to obtain the density distribution results of spatial location clustering locations. Spatial coupling analysis is performed on the spatial continuity distribution results and spatial density distribution results to determine the spatial coupling relationship between anomalous change characteristics and spatial location clustering areas; Based on spatial coupling relationships, a spatial visualization model of abnormal marine environmental areas is established, and a marine environmental visualization layer is output.

6. A big data visualization system for marine equipment according to claim 5, characterized in that, Based on equipment status trend data and historical fault characteristic data, equipment status prediction analysis is performed to establish a visualization model for predicting the operating status of marine equipment, and outputs a visualization layer for equipment operation prediction, specifically: Time series forecast analysis is performed on equipment status trend data to obtain the predicted operating trend of marine equipment; Statistical analysis methods were used to analyze historical failure characteristic data to obtain the types of failure events that occurred in marine equipment and the corresponding predicted probability distribution results. The prediction results of the operation trend of marine equipment are correlated and matched with the failure event types and corresponding prediction probability distribution results to determine the prediction relationship between the operation trend of marine equipment and failure events. Based on the predictive relationships, a visualization model for predicting the operational status of marine equipment is established, and a visualization layer for predicting equipment operation is output.

7. A big data visualization system for marine equipment according to claim 6, characterized in that, By integrating marine environment visualization layers and equipment operation prediction visualization layers, a unified multi-dimensional visualization interface is generated, specifically as follows: Synchronize the marine environment visualization layer and the equipment operation prediction visualization layer on the time axis and align their spatial coordinates. Overlay synchronized and aligned layers to create a multi-dimensional visual layout that includes a spatial view, a time-series view, and an interactive control area. Set interactive control methods for layer switching and data filtering in a multi-dimensional visualization layout; Real-time graphics rendering is performed on the layers after interactive control to generate a unified multi-dimensional visualization interface.

Images