Hull structure health monitoring method based on digital twinning

Abstract

The invention belongs to the technical field of ship body structure health monitoring, and provides a ship body structure health monitoring method based on digital twinning, which comprises the following steps: S1, acquiring multi-dimensional data such as stress, strain, vibration and temperature of a ship body structure in real time by using various sensors arranged on the ship body structure; s2, on the basis of the collected historical data, combining a physical model, material attributes and manufacturing process information of the ship body structure, constructing a digital twin body of the ship body structure; s3, performing feature extraction on the data acquired in real time; according to the invention, the multi-dimensional data of the hull structure is collected in real time and the digital twinborn body is constructed, so that comprehensive and real-time monitoring and accurate evaluation of the hull structure are realized; according to the method, abnormal data in the ship body structure can be found in time, the future health state of the ship body structure can be predicted, powerful support is provided for maintenance and reinforcement decisions, early warning can be conducted in time when the health state is abnormal, the safety and reliability of the ship are effectively improved, and the maintenance cost is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of hull structure health monitoring, and specifically relates to a hull structure health monitoring method based on digital twin. Background Art

[0002] With the development of the shipbuilding industry, the health monitoring of hull structures is of great significance for ensuring the safe navigation of ships. Traditional hull structure health monitoring methods mainly rely on manual inspections and regular detections, which have problems such as low detection efficiency, high cost, and poor real-time performance. At the same time, due to the complex hull structure and harsh working environment, traditional monitoring methods are difficult to accurately and comprehensively reflect the health status of the hull structure.

[0003] In recent years, digital twin technology, as a new technical means, has been widely applied in fields such as aerospace and intelligent manufacturing. Digital twin technology realizes real-time interaction and mapping between the physical world and the digital world by constructing a virtual model of a physical entity, providing a new solution for the health monitoring of hull structures.

[0004] However, the current research on applying digital twin technology to hull structure health monitoring is still in its infancy, with problems such as inaccurate construction of digital twins and imperfect health status assessment methods.

[0005] Therefore, those skilled in the art have proposed a hull structure health monitoring method based on digital twin to solve the problems raised in the background art. Summary of the Invention

[0006] In order to solve the above technical problems, the present invention provides a hull structure health monitoring method based on digital twin to solve the problems that the current research on applying digital twin technology to hull structure health monitoring is still in its infancy, with problems such as inaccurate construction of digital twins and imperfect health status assessment methods.

[0007] A hull structure health monitoring method based on digital twin includes:

[0008] S1. Using a variety of sensors arranged on the hull structure to collect multi-dimensional data such as stress, strain, vibration, and temperature of the hull structure in real time;

[0009] S2. Based on the collected historical data, combining with the physical model, material properties, and manufacturing process information of the hull structure, constructing a digital twin of the hull structure;

[0010] S3. Extracting features from the real-time collected data, and comparing them with the digital twin in real time, and detecting whether there is abnormal data in the hull structure through machine learning algorithms;

[0011] S4. Based on the results of anomaly detection and combined with the fatigue life prediction model of the hull structure, comprehensively evaluate the health status of the hull structure;

[0012] S5. When the health status of the hull structure is abnormal, send warning messages to the crew or management in a timely manner and provide decision support for maintenance or reinforcement.

[0013] Preferably, in step S2, a deep learning algorithm is used to extract features and perform pattern recognition on the collected historical data to improve the accuracy and robustness of the digital twin.

[0014] Preferably, in the process of constructing the digital twin, a multi-objective optimization algorithm is introduced to optimize the construction process of the digital twin. This algorithm can find the optimal digital twin construction parameters, such as model accuracy, computational efficiency, etc., on the premise of meeting multiple constraints.

[0015] Preferably, in step S3, the formula of the machine learning algorithm includes:

[0016]

[0017] where x is the data point to be classified, x i is the support vector, α i is the Lagrange multiplier, y i is the class label of the support vector, K(x, x i ) is the kernel function, and b is the bias term.

[0018] Preferably, in the health status assessment step, combining the real-time monitoring data and historical maintenance records of the hull structure, a health status prediction model based on a Bayesian network is used to predict the future health status of the hull structure.

[0019] Preferably, in the health status assessment, a health status assessment algorithm based on fuzzy logic is introduced. This algorithm can comprehensively evaluate the health status of the hull structure according to the fuzzy membership functions of multiple monitoring indicators.

[0020] Preferably, in the warning and decision support step, according to the health status assessment results of the hull structure, a maintenance plan or reinforcement plan is automatically generated and displayed to the crew or management through a visual interface.

[0021] A hull structure health monitoring system based on digital twin, using the above-mentioned hull structure health monitoring method based on digital twin, includes:

[0022] A data acquisition module, which is used to use a variety of sensors arranged on the hull structure to collect multi-dimensional data such as stress, strain, vibration, and temperature of the hull structure in real time;

[0023] A digital twin construction module constructs a digital twin of the hull structure based on the historical data collected by the data acquisition module, in combination with the physical model, material properties, and manufacturing process information of the hull structure. During the construction process, deep learning algorithms are used to extract features and identify patterns from the collected historical data to improve the accuracy and robustness of the digital twin;

[0024] A real-time monitoring and comparison module extracts features from the data collected in real time by the data acquisition module and compares them in real time with the digital twin in the digital twin module. Machine learning algorithms are used to detect whether there is abnormal data in the hull structure;

[0025] A health status evaluation module comprehensively evaluates the health status of the hull structure based on the results of anomaly detection in the real-time monitoring and comparison module, in combination with the fatigue life prediction model of the hull structure, and using a health status prediction model based on a Bayesian network. During the health status evaluation, a health status evaluation algorithm based on fuzzy logic is introduced, which can comprehensively evaluate the health status of the hull structure according to the fuzzy membership functions of multiple monitoring indicators;

[0026] An early warning and decision support module, when the health status evaluation module evaluates that the health status of the hull structure is abnormal, timely sends warning information to the crew or management personnel and provides decision support for repair or reinforcement. According to the health status evaluation results of the hull structure, a repair plan or reinforcement plan is automatically generated and displayed to the crew or management personnel through a visual interface.

[0027] A processor is configured to execute the digital twin-based hull structure health monitoring method according to the above.

[0028] A computer-readable storage medium stores a computer program thereon. When the computer program is executed by a processor, it implements the digital twin-based hull structure health monitoring method according to the above.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] 1. The present invention realizes comprehensive and real-time monitoring of the hull structure by using a variety of sensors arranged on the hull structure to collect multi-dimensional data such as stress, strain, vibration, and temperature of the hull structure in real time, and constructing a digital twin of the hull structure based on these data; this method overcomes the problems of low detection efficiency, high cost, and poor real-time performance in traditional monitoring methods, and improves the accuracy and efficiency of monitoring.

[0031] 2. In the process of constructing the digital twin, the present invention uses deep learning algorithms to extract features and recognize patterns from the collected historical data, improving the accuracy and robustness of the digital twin. At the same time, a multi-objective optimization algorithm is introduced to optimize the construction process of the digital twin, ensuring that the optimal digital twin construction parameters, such as model accuracy and computational efficiency, are obtained under the premise of meeting multiple constraints.

[0032] 3. The present invention extracts features from the real-time collected data through machine learning algorithms and compares them with the digital twin in real time, enabling the timely discovery of abnormal data in the hull structure, thus realizing the accurate assessment of the health status of the hull structure. In addition, by combining the fatigue life prediction model of the hull structure and the health status prediction model based on the Bayesian network, the present invention can predict the future health status of the hull structure, providing strong support for maintenance and reinforcement decisions.

[0033] 4. When evaluating the health status, the present invention introduces a health status evaluation algorithm based on fuzzy logic, which can comprehensively evaluate the health status of the hull structure according to the fuzzy membership functions of multiple monitoring indicators, improving the accuracy and comprehensiveness of the evaluation.

[0034] 5. When the health status of the hull structure is abnormal, the present invention can timely send warning information to the crew or management personnel and provide decision support for maintenance or reinforcement. At the same time, according to the health status evaluation results of the hull structure, a maintenance plan or reinforcement plan is automatically generated and displayed to the crew or management personnel through a visual interface, facilitating their quick response and handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is a flowchart of the method for monitoring the health of a hull structure based on digital twin according to the present invention;

[0036] Figure 2 is a framework diagram of the system for monitoring the health of a hull structure based on digital twin according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0037] The following further describes in detail the embodiments of the present invention with reference to the drawings and examples. The following examples are used to illustrate the present invention, but cannot be used to limit the scope of the present invention.

[0038] Example: The present invention provides a method for monitoring the health of a hull structure based on digital twin, as Figure 1 shown, including:

[0039] S1. Using a variety of sensors arranged on the hull structure to collect multi-dimensional data such as stress, strain, vibration, and temperature of the hull structure in real time;

[0040] S2. Based on the collected historical data, combined with the physical model of the hull structure, material properties, and manufacturing process information, construct a digital twin of the hull structure;

[0041] S3. Extract features from the real-time collected data and compare them with the digital twin in real time. Detect whether there is abnormal data in the hull structure through machine learning algorithms;

[0042] S4. According to the results of the anomaly detection, combined with the fatigue life prediction model of the hull structure, comprehensively evaluate the health status of the hull structure;

[0043] S5. When the health status of the hull structure is abnormal, send early warning information to the crew or management in a timely manner and provide decision support for repair or reinforcement.

[0044] As can be seen from the above, this digital twin-based hull structure health monitoring method realizes comprehensive and real-time monitoring and accurate evaluation of the hull structure by collecting multi-dimensional data of the hull structure in real time and constructing a digital twin. This method can timely detect abnormal data in the hull structure, predict the future health status of the hull structure, provide strong support for repair and reinforcement decisions, and can give early warnings in a timely manner when the health status is abnormal, effectively improving the safety and reliability of the ship and reducing the maintenance cost.

[0045] Further, in step S2, a deep learning algorithm is used to extract features and perform pattern recognition on the collected historical data to improve the accuracy and robustness of the digital twin. The deep learning algorithm includes:

[0046]

[0047] Among them, represents the output of the k-th convolution kernel at the position (i, j) of the input image, represents the weight of the convolution kernel, represents the pixel value of the input image, b k represents the bias term, and f represents the activation function.

[0048] As can be seen from the above, the present invention uses a deep learning algorithm to extract features and perform pattern recognition on the collected historical data, which can significantly improve the accuracy and robustness of the digital twin. Through the comprehensive action of elements such as convolution kernels, weights, pixel values of input images, bias terms, and activation functions in the deep learning algorithm, precise processing and analysis of historical data are realized, thereby constructing a digital twin that is closer to the real hull structure and providing a more reliable basis for subsequent health monitoring and evaluation.

[0049] Furthermore, in the process of constructing the digital twin, a multi-objective optimization algorithm is introduced to optimize the construction process of the digital twin. This algorithm can find the optimal digital twin construction parameters, such as model accuracy, computational efficiency, etc., on the premise of meeting multiple constraint conditions. The formula of the multi-objective optimization algorithm includes:

[0050] minf(x)=f[f1(x),f2(x),...,f m (x)];

[0051] s.t.g i (x)≤0,i=1,2,...,n;

[0052] h j (x)=0j=1,2,...,n;

[0053] Among them, f(x) is the objective function vector, and g i (x) and h j (x) are the inequality and equality constraint conditions respectively.

[0054] As can be seen from the above, in the process of constructing the digital twin, introducing a multi-objective optimization algorithm can further optimize the construction process of the digital twin. On the premise of meeting multiple constraint conditions, this algorithm can automatically search for and determine the optimal digital twin construction parameters, such as model accuracy, computational efficiency, etc., so as to ensure that the constructed digital twin has both high accuracy and can operate efficiently. This helps to improve the accuracy and real-time performance of hull structure health monitoring and provides a more solid guarantee for the safe navigation of ships.

[0055] Furthermore, in step S3, the formula of the machine learning algorithm includes:

[0056]

[0057] Among them, x is the data point to be classified, x i is the support vector, α i is the Lagrange multiplier, y i is the class label of the support vector, K(x,x i ) is the kernel function, and b is the bias term.

[0058] As can be seen from the above, by comparing and calculating the data point to be classified with the support vector, and combining key elements such as the Lagrange multiplier, the class label of the support vector, the kernel function, and the bias term, accurate classification and anomaly detection of real-time collected data can be achieved. The application of this algorithm significantly improves the accuracy and sensitivity of hull structure health monitoring, enabling even minor anomalies in the hull structure to be detected and processed in a timely manner, thus effectively ensuring the safe operation of the ship.

[0059] Furthermore, in the health status assessment step, by combining the real-time monitoring data of the hull structure and the historical maintenance records, a health status prediction model based on Bayesian network is adopted to predict the future health status of the hull structure. The health status prediction model based on Bayesian network is an advanced method that uses Bayes' theorem and probability graph theory to evaluate the future health status of the hull structure. It constructs a Bayesian network structure containing multiple nodes and dependencies by analyzing the historical monitoring data and domain knowledge of the hull structure, and makes inferences based on the real-time monitoring data and the conditional probability table in the network, so as to achieve accurate prediction and risk assessment of the health status of the hull structure.

[0060] As can be seen from the above, in the health status assessment step, by combining the real-time monitoring data of the hull structure and the historical maintenance records, and adopting a health status prediction model based on Bayesian network, the historical data and real-time monitoring information can be fully utilized to accurately predict the future health status of the hull structure. Through the powerful reasoning ability of the Bayesian network, this model comprehensively considers various influencing factors and complex relationships of the hull structure, effectively improving the accuracy and reliability of the prediction. This not only helps to detect potential structural problems in advance, but also provides a scientific basis and decision-making support for the safe operation of the ship, thus reducing the maintenance cost and extending the service life of the ship.

[0061] Furthermore, when conducting the health status assessment, a health status assessment algorithm based on fuzzy logic is introduced. This algorithm can comprehensively evaluate the health status of the hull structure according to the fuzzy membership functions of multiple monitoring indicators. The formula of the health status assessment algorithm is as follows:

[0062]

[0063] where H is the health status assessment result, w i is the weight of the i-th monitoring indicator, μ i (X i ) is the fuzzy membership function of the i-th monitoring indicator, and X i is the real-time acquisition data of the i-th monitoring indicator.

[0064] As can be seen from the above, when conducting the health status assessment, introducing a health status assessment algorithm based on fuzzy logic can comprehensively consider the fuzziness and uncertainty of multiple monitoring indicators, and comprehensively evaluate the health status of the hull structure through the fuzzy membership function. This algorithm combines the weights of each monitoring indicator and the real-time acquisition data, and calculates the health status assessment result through a specific formula, making the assessment process more scientific and accurate. This assessment method can more truly reflect the actual health condition of the hull structure, provide a more reliable basis for subsequent maintenance and reinforcement decisions, and help improve the safety and operation efficiency of the ship.

[0065] Further, in the warning and decision-making support step, according to the evaluation result of the health status of the hull structure, a maintenance plan or reinforcement plan is automatically generated and displayed to the crew or management personnel through a visual interface.

[0066] As can be seen from the above, in the warning and decision-making support step, a maintenance plan or reinforcement plan is automatically generated according to the evaluation result of the health status of the hull structure and displayed to the crew or management personnel through a visual interface, greatly improving the efficiency and accuracy of decision-making. This method not only enables the crew and management personnel to intuitively and quickly understand the health status of the hull structure, but also enables them to take corresponding measures promptly according to the generated maintenance plan or reinforcement plan, effectively preventing potential safety hazards and ensuring the safe operation of the ship. At the same time, the visual display method is also convenient for information sharing and communication, enhancing the teamwork ability and further improving the overall level of ship maintenance management.

[0067] Furthermore, the effect of the digital twin-based hull structure health monitoring method of the embodiment is compared with the current traditional hull structure health monitoring method (comparative example), and the following table is obtained:

[0068]

[0069]

[0070] As can be seen from the above table, the digital twin-based hull structure health monitoring method has significant advantages compared with the traditional method, including higher accuracy, real-time performance, comprehensiveness and prediction ability, as well as stronger decision-making support and cost-effectiveness. These methods not only improve the safety and reliability of the ship, but also reduce the maintenance cost and extend the service life of the ship, which is an important development direction in the future field of hull structure health monitoring.

[0071] A digital twin-based hull structure health monitoring system, as Figure 2 shown, uses the above-mentioned digital twin-based hull structure health monitoring method, including:

[0072] A data acquisition module, which is used to use a variety of sensors arranged on the hull structure to collect multi-dimensional data such as stress, strain, vibration, and temperature of the hull structure in real time;

[0073] A digital twin body construction module, based on the historical data collected by the data acquisition module, combined with the physical model, material properties and manufacturing process information of the hull structure, constructs a digital twin body of the hull structure. During the construction process, deep learning algorithms are used to extract features and identify patterns from the collected historical data to improve the accuracy and robustness of the digital twin body;

[0074] A real-time monitoring and comparison module extracts features from the data collected in real time by the data collection module and compares them with the digital twin in the digital twin module in real time, and uses machine learning algorithms to detect whether there is abnormal data in the hull structure;

[0075] A health status evaluation module comprehensively evaluates the health status of the hull structure according to the results of abnormal detection in the real-time monitoring and comparison module, combines the fatigue life prediction model of the hull structure, and uses a health status prediction model based on a Bayesian network. When evaluating the health status, a health status evaluation algorithm based on fuzzy logic is introduced, and this algorithm can comprehensively evaluate the health status of the hull structure according to the fuzzy membership functions of multiple monitoring indicators;

[0076] An early warning and decision support module, when the health status evaluation module evaluates that the health status of the hull structure is abnormal, sends early warning information to the crew or management personnel in a timely manner and provides decision support for repair or reinforcement. Among them, according to the health status evaluation result of the hull structure, a repair plan or reinforcement plan is automatically generated and displayed to the crew or management personnel through a visual interface.

[0077] An embodiment of the present application provides an electronic device, which is applicable to the above-mentioned digital twin-based hull structure health monitoring method, including:

[0078] A memory for storing computer programs and data;

[0079] A processor for running system programs.

[0080] An embodiment of the present application provides a computer storage medium, which is applicable to the above-mentioned digital twin-based hull structure health monitoring method, and performs hierarchical confidentiality management on the above system and data according to the requirements of confidentiality management.

[0081] Those skilled in the art should understand that the embodiments of the present application can be provided as a system or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0082] This application is described with reference to the flowcharts and / or block diagrams of devices (systems) and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, as well as the combination of flows and / or blocks in the flowchart and / or block diagram. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0083] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0084] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0085] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0086] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.

[0087] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media, and can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information accessible by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0088] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, article or device comprising the element.

[0089] The embodiments of the present invention are given for purposes of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A hull structure health monitoring method based on digital twin, characterized in that: include: S1. Use a variety of sensors arranged on the hull structure to collect multi-dimensional data such as stress, strain, vibration, temperature, etc. of the hull structure in real time; S2. Based on the collected historical data, combined with the physical model, material properties and manufacturing process information of the hull structure, a digital twin of the hull structure is constructed; S3, extract features from the real-time collected data and compare it with the digital twin in real time, and use machine learning algorithms to detect whether there are abnormal data in the hull structure; S4. Based on the results of abnormality detection and combined with the fatigue life prediction model of the hull structure, a comprehensive assessment of the health status of the hull structure is conducted; S5. When the health status of the hull structure is abnormal, timely send warning information to the crew or management personnel, and provide decision support for maintenance or reinforcement.

2. A hull structure health monitoring method based on digital twins as claimed in claim 1, characterized in that: In step S2, a deep learning algorithm is used to perform feature extraction and pattern recognition on the collected historical data.

3. A hull structure health monitoring method based on digital twins as claimed in claim 1, characterized in that: In the process of building digital twins, a multi-objective optimization algorithm is introduced to optimize the construction process of digital twins. This algorithm can find the optimal digital twin construction parameters while satisfying multiple constraints.

4. A hull structure health monitoring method based on digital twins as claimed in claim 1, characterized in that: In step S3, the formula of the machine learning algorithm includes: Among them, x is the data point to be classified, x i is the support vector, α i is the Lagrange multiplier, y i is the class label of the support vector, K(x,x i ) is the kernel function and b is the bias term.

5. A hull structure health monitoring method based on digital twins as claimed in claim 1, characterized in that: In the health status assessment step, the future health status of the hull structure is predicted by using a health status prediction model based on a Bayesian network in combination with the real-time monitoring data and historical maintenance records of the hull structure.

6. A hull structure health monitoring method based on digital twins as claimed in claim 5, characterized in that: In health status assessment, a health status assessment algorithm based on fuzzy logic is introduced. This algorithm can comprehensively assess the health status of the hull structure according to the fuzzy membership functions of multiple monitoring indicators.

7. A hull structure health monitoring method based on digital twins as claimed in claim 1, characterized in that: In the early warning and decision support step, a maintenance plan or reinforcement plan is automatically generated according to the health status assessment result of the hull structure, and is presented to the crew or management personnel through a visual interface.

8. A hull structure health monitoring system based on digital twins, characterized by: A hull structure health monitoring method based on digital twins according to any one of claims 1 to 7, comprising: The data acquisition module is used to collect multi-dimensional data such as stress, strain, vibration, temperature, etc. of the hull structure in real time using a variety of sensors arranged on the hull structure; A digital twin construction module, which constructs a digital twin of the hull structure based on the historical data collected by the data collection module and in combination with the physical model, material properties and manufacturing process information of the hull structure, wherein a deep learning algorithm is used in the construction process to perform feature extraction and pattern recognition on the collected historical data to improve the accuracy and robustness of the digital twin; A real-time monitoring and comparison module extracts features from the data collected in real time by the data acquisition module, and compares the data with the digital twin in the digital twin module in real time, and detects whether there is abnormal data in the hull structure through a machine learning algorithm; A health status assessment module, which comprehensively assesses the health status of the hull structure according to the results of abnormality detection in the real-time monitoring and comparison module, combined with the fatigue life prediction model of the hull structure, and adopts a health status prediction model based on a Bayesian network, wherein a health status assessment algorithm based on fuzzy logic is introduced during the health status assessment, and the algorithm can comprehensively assess the health status of the hull structure according to the fuzzy membership functions of multiple monitoring indicators; The early warning and decision support module sends early warning information to the crew or management personnel in a timely manner when the health status assessment module assesses that the health status of the hull structure is abnormal, and provides decision support for maintenance or reinforcement. According to the health status assessment results of the hull structure, a maintenance plan or reinforcement plan is automatically generated and displayed to the crew or management personnel through a visual interface.

9. A processor, characterized in that: The method is configured to execute the hull structure health monitoring method based on digital twin according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the hull structure health monitoring method based on digital twins as described in any one of claims 1 to 7 is implemented.

Images