Life-life digital health management system applied to container ship

Abstract

The invention provides a lifelong digital health management system applied to a container ship, and the system comprises a data collection module which is used for collecting health parameter data of in-situ measurement of the container ship; the data transmission module is connected with the data acquisition module and is used for storing and transmitting the health parameter data; the data analysis module is connected with the data transmission module and used for analyzing the health parameter data to obtain the corresponding ship body residual strength; the ship body diagnosis module is respectively connected with the data transmission module and the data analysis module and is used for analyzing the health parameter data and the ship body residual strength to obtain a corresponding ship body safety assessment result; and the visualization module is respectively connected with the data analysis module and the ship body diagnosis module and is used for visually displaying the ship body residual strength and the ship body safety evaluation result. The method has the beneficial effects that the analysis accuracy of the hull residual strength can be improved, and the safety of the hull structure can be accurately diagnosed.

Description

Technical Field

[0001] This invention relates to the technical field of health management for marine vessels, and more specifically, to a lifelong digital health management system for container ships. Background Technology

[0002] Communication and digital technologies are developing rapidly. For example, 6G has a speed of 1 terabits per second, which is 50 times faster than 5G, and a latency of 100 microseconds, which is 10 times shorter than 5G. Now is the perfect time to leverage these technological advantages to solve challenges in many fields. In harsh marine environments, ships and offshore structures operating in remote waters may malfunction, leading to catastrophic consequences such as casualties, property damage, and marine pollution. For ships and offshore structures, digitizing basic health information in real time will be an effective way to prevent such disasters.

[0003] In existing technologies, Digital Health Engineering (DHE) systems used for lifelong health management of container ships require the corresponding digital twin to perform data analysis and visualization in order to develop the DHE system and maintain real-time data processing. Computational fluid dynamics (CFD) and finite element analysis (FEA) of large ship hull structures require high computing power and time. Calculations usually take longer than real-time display and cannot guarantee accuracy. Unlike the field of structural design, there are currently no standardized guidelines for real-time digitalization of safety assessment and management of ship hull structures, and it is not possible to perform real-time health status diagnosis of a large number of suspicious areas in the ship hull structure. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to improve the accuracy of the analysis of the remaining strength of the hull and to achieve accurate diagnosis of the safety of the hull structure. In order to overcome the defects of the prior art (or related technology) mentioned above, the present invention provides a lifelong digital health management system for container ships.

[0005] This invention provides a lifelong digital health management system for container ships, comprising: A data acquisition module is used to collect health parameter data measured in situ on container ships; A data transmission module, connected to the data acquisition module, is used to store and transmit the health parameter data; A data analysis module, connected to the data transmission module, is used to analyze the health parameter data to obtain the corresponding remaining hull strength; A hull diagnostic module is connected to the data transmission module and the data analysis module respectively, and is used to analyze the health parameter data and the remaining strength of the hull to obtain the corresponding hull safety assessment results; A visualization module is connected to the data analysis module and the hull diagnosis module respectively, and is used to visualize the remaining strength of the hull and the safety assessment results of the hull.

[0006] Compared with existing technologies, the lifelong digital health management system for container ships proposed in this application has the following advantages: This application uses in-situ measured health parameter data of container ships as basic data. The data transmission module ensures the accurate transmission and real-time nature of the health parameter data. The data analysis module analyzes the transmitted health parameter data to quantify the health parameters. The remaining strength of the hull is calculated using computational fluid dynamics and finite element analysis models and visualized, thereby improving the accuracy of the analysis of the remaining strength of the hull. The hull diagnosis module can assess the health status of the hull structure using the structural safety index method, analyze the hull safety assessment results, and achieve accurate diagnosis of the safety of the hull structure.

[0007] In one possible implementation, the data analysis module includes: A first analysis unit is used to extract the hull structure data from the health parameter data, create a hull geometric model based on the hull structure data, and establish a finite element analysis model for mechanical analysis. A second analysis unit, connected to the first analysis unit, is used to identify the ship's geometric model to obtain ship damage data, and to integrate the ship damage data into the finite element analysis model; A third analysis unit, connected to the first analysis unit and the second analysis unit respectively, is used to calculate the stress and deformation distribution data of the hull geometry model under multiple pre-set load conditions using the finite element analysis model; A fourth analysis unit, connected to the second and third analysis units respectively, is used to perform nonlinear finite element analysis on the hull damage data and the stress and deformation distribution data to obtain the corresponding hull residual strength.

[0008] In one possible implementation, the hull diagnostic module includes: A fifth analysis unit is used to extract the applied load from the health parameter data; A sixth analysis unit, connected to the fifth analysis unit, is used to calculate the current safety factor based on the applied load and the remaining strength of the hull; A seventh analysis unit, connected to the sixth analysis unit, is used to compare the current safety factor with a pre-set critical safety factor, and obtain the hull safety assessment result characterizing safety when the current safety factor is greater than the critical safety factor; or The hull safety assessment result, which characterizes insecurity, is obtained when the current safety factor is not greater than the critical safety factor.

[0009] In one possible implementation, the sixth analysis unit obtains the current security factor using the following formula: ; in, This indicates the current safety factor; This indicates the remaining strength of the hull; This indicates the applied load.

[0010] In one possible implementation, a health prediction module is further included, which is connected to the data transmission module and the data analysis model respectively, and is used to predict the future structural health status of the hull geometry model based on the health parameter data and the pre-acquired historical hull data.

[0011] Compared with existing technologies, the above-mentioned technical solution can use health parameter data and historical hull data to predict the future health status of the hull geometry model, providing ship operators with a time window to prevent disasters or problems, and enabling preventive measures to be taken in advance by predicting the future structural health status.

[0012] In one possible implementation, the health prediction module includes: A data acquisition unit is used to collect the historical hull data, including in-service damage data, operating condition data, maintenance and repair data; A data monitoring unit is used to extract sensor data and environmental monitoring data from the health parameter data; A preprocessing unit, connected to the data acquisition unit and the data monitoring unit respectively, is used to preprocess the historical hull data, the sensor data and the environmental monitoring data to obtain preprocessed data; An eighth analysis unit, connected to the preprocessing unit, is used to analyze and predict the future structural health status of the hull geometry model by using computational fluid dynamics and the finite element analysis model to obtain the preprocessed data.

[0013] In one possible implementation, the in-service damage data includes the type, location, size, and time of damage during the container ship's service life; the operating condition data includes wave height, wind speed, and sailing speed; and the maintenance and repair records include repair time, repair method, and post-repair structural condition.

[0014] In one possible implementation, the preprocessing unit obtains the preprocessed data by means of preprocessing methods including data cleaning, data transformation, and feature extraction. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the structure of the present invention; Explanation of reference numerals in the attached diagram: 1. Data acquisition module; 2. Data transmission module; 3. Data analysis module; 31. First analysis unit; 32. Second analysis unit; 33. Third analysis unit; 34. Fourth analysis unit; 4. Hull diagnostic module; 41. Fifth analysis unit; 42. Sixth analysis unit; 43. Seventh analysis unit; 5. Visualization module; 6. Health prediction module; 61. Data acquisition unit; 62. Data monitoring unit; 63. Preprocessing unit; 64. Eighth analysis unit. Detailed Implementation

[0016] First, those skilled in the art should understand that these embodiments are merely used to explain the technical principles of the embodiments of this application and are not intended to limit the scope of protection of the embodiments of this application. Those skilled in the art can make adjustments as needed to adapt to specific application scenarios.

[0017] The present application will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0018] See Figure 1 This application discloses a lifelong digital health management system for container ships. From the perspective of lifelong health management, both the human body and engineering structures share many similarities. Just as the human body requires regular and appropriate health care to maintain lifespan and prevent disease, engineering structures must also undergo health management through continuous health monitoring, diagnosis, remedial measures, and prediction of future health conditions to ensure structural safety and prevent accidents that could lead to catastrophic consequences. Based on this viewpoint, this application designs a lifelong digital health management system for container ships, which mainly consists of five parts: Measurement of health parameter data In order to assess the health status of the hull structure, this application requires the collection of health parameter data such as in-situ measured marine environmental conditions, in-service damage and operating conditions. The data acquisition module 1 for collecting health parameter data requires that suitable and reliable measuring instruments be selected for each health parameter, such as using X-band radar technology to measure sea waves and wind speed, using non-destructive testing tools to measure in-service damage, and using accelerometers to measure engine vibration, etc. Real-time data transmission The data transmission module 2 is one of the key modules of the lifelong digital health management system proposed in this application. It can be implemented through modern technology. In specific operation, health parameter data can be recorded in the shipborne data recorder. Subsequently, the recorded data can be transmitted to the land-based (ground-based, shore-based) data analysis center using various communication technologies. WiFi can be used for data transmission on the ship, while near-Earth orbit satellites such as Beidou can be used for data transmission between the ship and the land-based data analysis center. Data Analysis and Visualization Data analysis module 3 analyzes the transmitted health parameter data, quantifying health parameters such as wave height, wave period, and wave duration to assess marine environmental conditions. It also analyzes health parameters such as the type, shape, size, and location of in-service damage. By analyzing these health parameters, marine environmental loads and the remaining strength of the hull structure can be calculated. Load and load effects are calculated using predefined models through computer simulation. Computational Fluid Dynamics (CFD, hereinafter referred to as an abbreviation) can be used to calculate marine environmental loads considering operating conditions. The remaining strength of the hull structure can be calculated by combining nonlinear finite element analysis (NLEA, hereinafter referred to as an abbreviation) obtained from the CFD load analysis results. Visualization module 5 visualizes the remaining strength of the hull, facilitating the study of time-varying changes in health parameters and their impact on the hull structure. Diagnosis and remedial measures Because yielding or plasticity, buckling and fracture lead to a decrease in structural stiffness and strength, certain structural components or hull beams may experience progressive collapse. To prevent catastrophic failures of the hull structure, it is necessary to perform accurate diagnosis based on specific safety standards and using artificial intelligence (AI) technology. The health status of the hull structure will be diagnosed based on the results of numerical simulation. Quantitative risk assessment can also be applied to this system. This application combines artificial intelligence with deep learning, and analyzes the health parameter data and the remaining strength of the hull through the hull diagnosis module 4 to obtain the corresponding hull safety assessment results, and proposes remedial measures based on the hull safety assessment results. (5) Predicting future structural health Predicting potential future health conditions is crucial for ensuring safe operation and structural lifespan. Historical hull data on in-service damage measured using physical models can help predict potential future health conditions.

[0019] See also Figure 1The calculation process of residual strength of hull: The residual strength of a hull structure refers to the maximum load capacity that the hull structure can withstand after experiencing factors such as damage, corrosion, or fatigue. Calculating the residual strength of a hull structure usually relies on complex engineering analysis and simulation methods, rather than simple formulas. For complex hull structures, advanced simulation tools and methods, such as nonlinear finite element analysis, are usually required to obtain more accurate results. These methods can better capture the complex impact of damage on structural strength, thereby providing reliable data support for hull safety and maintenance decisions.

[0020] See also Figure 1 The specific calculation steps for the residual strength of the hull include: 1. Collect data and build models: Collect detailed data on the hull structure, including geometry, material properties, and structural layout; Use a computer to create a geometric model of the ship's hull; A finite element model (FEM) is established for subsequent mechanical analysis; 2. Identify and assess the injury: Identify any damage on the hull geometry model, such as cracks, corrosion, or fatigue damage; Assess the nature, location, and extent of the damage and integrate it into the finite element analysis model; 3. Calculate the load distribution after damage: The stress and deformation distribution of the damaged hull geometry model under various load conditions was calculated using finite element analysis (FEA). 4. Residual strength analysis: Based on damage assessment and load distribution calculation, nonlinear finite element analysis (NLFEA) is performed to evaluate the residual strength of the hull geometry model under damage conditions. This process typically involves considering the nonlinear behavior of materials (such as plasticity) and geometric nonlinearity (such as large deformation); 5. Calculate the safety factor and residual strength: The maximum load-bearing capacity of the hull geometric model after damage, i.e., the remaining strength of the hull, is calculated using nonlinear analysis results. By comparing the ultimate strength before and after the damage, i.e. the remaining strength of the hull, and calculating the current safety factor, the safety of the hull is assessed.

[0021] See also Figure 1 The health status of the ship's hull structure will be primarily assessed using the structural safety index method, as shown in the following formula: ; This represents the maximum load-bearing capacity (i.e., the remaining strength of the hull). Represents the application of load. Represents the current safety factor. This represents the critical safety factor, with a recommended value of 1.5, used as an example in a safety study. It should always be greater than To ensure the safety of the ship's structure.

[0022] See also Figure 1 The steps for predicting the future structural health of a ship's hull are as follows: 1. Data collection and organization a. Historical hull data collection: In-service damage data: Collect damage records of the hull structure during its service life, including damage type, location, size and time of occurrence; Operating condition data: Collect environmental data of the hull structure under different operating conditions, such as wave height, wind speed and sailing speed; Maintenance and repair data: Records all maintenance and repair activities, including repair time, method, and post-repair structural condition; b. Real-time monitoring data: Sensor data: Sensors installed on the ship's hull structure can monitor key parameters such as stress, strain, vibration, and temperature in real time; Environmental monitoring: Using environmental monitoring equipment to collect real-time marine environmental data, such as tides, wind speed, and wave conditions; 2. Data Analysis and Preprocessing a. Data cleaning: Clean the raw data, handle missing values, outliers and noise to ensure the accuracy and integrity of the data; b. Data transformation: Standardize data from different sources and formats, and transform it into a form suitable for analysis; c. Feature extraction: Key features affecting structural health, such as stress concentration zones, frequency of fatigue damage, and the impact of environmental changes, are extracted from the raw data. 3. Establish a mathematical model a. Time-varying mathematical model: Use time-varying mathematical models (such as stochastic process models) to describe the trend of structural health over time; b. Machine learning and artificial intelligence: Prediction is made using machine learning algorithms and artificial intelligence technologies; Regression analysis is used to predict changes in continuous health indicators, such as residual intensity. Classification algorithms are used to identify and classify injury types and severity. Deep learning models, such as neural networks, are able to handle complex time-varying and multidimensional data; 4. Prediction and Simulation a. Load and environment simulation: Computational fluid dynamics (CFD) and finite element analysis (FEA) are used to simulate the effects of future loads and environmental conditions on the structure; b. Health status simulation: Based on historical hull data and real-time monitoring data, the above models and methods are used to predict future structural health status. 5. Verification and Update a. Verification of prediction results: The accuracy of the prediction model was verified using actual operational data, and necessary adjustments were made. b. Model update: Regularly update the model and parameters to reflect the latest operating conditions and damage status.

[0023] See also Figure 1 Despite various efforts, marine accidents still occur frequently, resulting in serious consequences such as casualties, property damage, and marine pollution. Researchers in many industries and academia have studied nonlinear structural mechanisms to accurately predict structural behavior under real-world conditions based on historical data. However, health parameters (marine environmental conditions, operating conditions, and in-service damage) exhibit high instability, uncertainty, complexity, and ambiguity in prediction. Furthermore, the accuracy of predictions based on historical hull data has declined due to various factors such as climate change. In addition, the shipbuilding industry typically conducts hull structure health monitoring annually or biennially, which may pose potential risks to health assessments between inspection periods. To address these issues, this application aims to develop a lifelong digital health management system (DHE). Real-time health assessment and management through the DHE system will allow ship operators to efficiently manage their assets, providing them with accurate ship health information and sufficient time to prevent disasters.

[0024] In the description of this application, the references to terms such as "an embodiment," "some embodiments," "in this embodiment," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0025] 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 technical scope 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.

Claims

1. A lifelong digital health management system for container ships, characterized in that, include: A data acquisition module (1) is used to collect health parameter data of container ships measured in situ; A data transmission module (2) is connected to the data acquisition module (1) and is used to store and transmit the health parameter data; A data analysis module (3) is connected to the data transmission module (2) and is used to analyze the health parameter data to obtain the corresponding hull remaining strength. A hull diagnostic module (4) is connected to the data transmission module (2) and the data analysis module (3) respectively, and is used to analyze the health parameter data and the remaining strength of the hull to obtain the corresponding hull safety assessment results; A visualization module (5) is connected to the data analysis module (3) and the hull diagnosis module (4) respectively, and is used to visualize the remaining strength of the hull and the safety assessment results of the hull.

2. The lifelong digital health management system according to claim 1, characterized in that, The data analysis module (3) includes: A first analysis unit (31) is used to extract the hull structure data in the health parameter data, and to create a hull geometric model based on the hull structure data, and to establish a finite element analysis model for mechanical analysis; A second analysis unit (32) is connected to the first analysis unit (31) and is used to identify the ship's geometric model to obtain ship damage data and integrate the ship damage data into the finite element analysis model. A third analysis unit (33) is connected to the first analysis unit (31) and the second analysis unit (32) respectively, and is used to calculate the stress and deformation distribution data of the ship hull geometric model under multiple pre-set load conditions using the finite element analysis model; A fourth analysis unit (34) is connected to the second analysis unit (32) and the third analysis unit (33) respectively, and is used to perform nonlinear finite element analysis on the hull damage data and the stress and deformation distribution data to obtain the corresponding hull residual strength.

3. The lifelong digital health management system according to claim 1, characterized in that, The hull diagnostic module (4) includes: A fifth analysis unit (41) is used to extract the applied load from the health parameter data; A sixth analysis unit (42), connected to the fifth analysis unit (41), is used to calculate the current safety factor based on the applied load and the remaining strength of the hull; A seventh analysis unit (43), connected to the sixth analysis unit (42), is used to compare the current safety factor with a preset critical safety factor, and obtain the hull safety assessment result characterizing safety when the current safety factor is greater than the critical safety factor; or The hull safety assessment result, which characterizes insecurity, is obtained when the current safety factor is not greater than the critical safety factor.

4. The lifelong digital health management system according to claim 3, characterized in that, The sixth analysis unit (42) obtains the current security factor using the following formula: ； in, This indicates the current safety factor; This indicates the remaining strength of the hull; This indicates the applied load.

5. The lifelong digital health management system according to claim 2, characterized in that, It also includes a health prediction module (6), which is connected to the data transmission module (2) and the data analysis model (3) respectively, and is used to predict the future structural health status of the hull geometry model based on the health parameter data and the historical hull data obtained in advance.

6. The lifelong digital health management system according to claim 5, characterized in that, The health prediction module (6) includes: A data acquisition unit (61) is used to acquire the historical hull data, including in-service damage data, operating condition data, maintenance and repair data; A data monitoring unit (62) is used to extract sensor data and environmental monitoring data from the health parameter data; A preprocessing unit (63) is connected to the data acquisition unit (61) and the data monitoring unit (62) respectively, and is used to preprocess the historical hull data, the sensor data and the environmental monitoring data to obtain preprocessed data; An eighth analysis unit (64) is connected to the preprocessing unit (63) and is used to analyze and predict the future structural health status of the hull geometry model by computational fluid dynamics and the finite element analysis model.

7. The lifelong digital health management system according to claim 6, characterized in that, The in-service damage data includes the type, location, size, and time of damage during the container ship's service life; the operating condition data includes wave height, wind speed, and sailing speed; and the maintenance and repair records include repair time, repair method, and post-repair structural condition.

8. The lifelong digital health management system according to claim 6, characterized in that, The preprocessing unit (63) uses data cleaning, data transformation and feature extraction to obtain the preprocessed data.

Images