Fault analysis and fault-tolerant control method, device and equipment for ship

Abstract

The invention provides a ship fault analysis and fault-tolerant control method, device and equipment, and relates to the technical field of ship fault control, and the method comprises the steps: obtaining the real-time operation data of a target ship; inputting the real-time operation data into a pre-constructed digital twin model of the target ship for ship fault simulation analysis to obtain a fault analysis result; the digital twin model is fused with the target ship on the spatial scale and the time scale to synchronously reflect the mechanical health state of the target ship at the current moment, and fault virtual simulation analysis is carried out under real-time operation data to obtain a fault analysis result; matching a target fault-tolerant control scheme corresponding to the fault type and the fault level from a configured ship fault and fault-tolerant control knowledge graph database; and generating ship control parameters according to the target fault-tolerant control scheme. According to the invention, comprehensive and accurate ship fault analysis can be carried out, and a fault-tolerant control scheme with fast response and low safety risk is output.

Description

Technical Field

[0001] This application relates to the technical field of ship fault control. Specifically, it relates to a method, device, and equipment for fault analysis and fault tolerance control of ships. Background Art

[0002] Currently, ship fault diagnosis and fault tolerance control technologies mainly include the following two categories: The first category is the static diagnosis method based on an expert system. By relying on a predefined fault rule base (such as IF-THEN logic), it matches sensor data with known fault modes and triggers preset fault tolerance actions (such as switching redundant devices); for example, patent CN20XX123456A proposes a fault handling solution for a ship power system based on a rule engine. The second category is the simulation diagnosis method based on digital twins. By using a digital twin model to simulate the state of ship equipment and combining historical data to train machine learning models (such as SVM, random forest) for fault classification; for example, in "Digital Twin Modeling and Fault Prediction of Ship Power Systems", the health assessment of battery packs is realized through the twin model.

[0003] However, the above methods have the following problems: First, the fault scenarios are not covered comprehensively. Traditional simulations rely on manually preset faults and cannot dynamically generate complex coupled faults (such as multi-device chain faults triggered by sudden environmental changes), resulting in poor generalization ability of AI models. Second, the fault tolerance strategies are rigid. The static rule base is difficult to handle unknown fault modes and lacks multi-objective optimization (such as the balance of safety, energy consumption, and timeliness), and the fault tolerance decisions are single. Third, the knowledge update is lagging. The expert system relies on manual input of experience and cannot automatically mine new fault modes and solutions from real-time data, with a slow response speed (usually > 2 seconds). Finally, the virtual and real data are fragmented. Existing digital twin systems do not achieve real-time fusion of virtual fault signals and real sensor data, resulting in a large deviation between simulation test results and actual working conditions. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide a method, device, and equipment for fault analysis and fault tolerance control of ships, which solves the above problems existing in the prior art, can perform comprehensive and accurate ship fault analysis, and output a fault tolerance control solution with fast response, low safety risk, and low energy consumption.

[0005] In a first aspect, the present invention provides a method for fault analysis and fault tolerance control of a ship, the method including:

[0006] Obtain the real-time operation data of the target ship;

[0007] Input the real-time operation data into the digital twin model of the target ship pre-constructed for ship fault simulation analysis to obtain a fault analysis result; wherein, the fault analysis result includes: a fault type and a fault level; the digital twin model is fused with the target ship in terms of spatial scale and time scale to synchronously reflect the mechanical health state of the target ship at the current moment, and perform fault virtual simulation analysis under the real-time operation data to obtain a fault analysis result;

[0008] Match the target fault tolerance control scheme corresponding to the fault type and the fault level from the configured ship fault and fault tolerance control knowledge graph database;

[0009] Generate ship control parameters according to the target fault tolerance control scheme;

[0010] Based on the ship control parameters, control the target ship to continue sailing.

[0011] In an alternative embodiment, the construction method of the digital twin model of the target ship includes:

[0012] Obtain the three-dimensional geometric model and dynamic behavior model of the target ship, as well as all historical operation data covering the entire life cycle of the target ship; wherein, all historical operation data includes: fault operation data and corresponding fault types, and normal operation data;

[0013] The dynamic behavior model is used to characterize the physical characteristics and operation rules of all subsystems of the target ship;

[0014] Construct the initial digital twin model of the target ship according to the three-dimensional geometric model and dynamic behavior model;

[0015] Analyze all the historical operation data to obtain multiple target performance indicators, the first correlation relationship between the target performance indicators, the second correlation relationship between each target performance indicator and the first safety score, energy consumption and response time of the target ship, and the historical operation data associated with each target performance indicator; wherein, each target performance indicator is a performance indicator related to the first safety score, energy consumption and response time of the target ship;

[0016] Integrate multiple target performance indicators, the corresponding first and second correlation relationships, and the historical operation data associated with the corresponding target performance indicators into the initial digital twin model to obtain a processed initial digital twin model;

[0017] Train the processed initial digital twin model using all the historical operation data to obtain the digital twin model of the target ship.

[0018] In an alternative embodiment, integrating a plurality of target performance metrics, corresponding first and second association relationships, and historical operation data associated with the corresponding target performance metrics into the initial digital twin model to obtain a processed initial digital twin model, including:

[0019] Obtain the risk coefficients, safety thresholds, and fault determination rules corresponding to each configured target performance metric; wherein, the fault determination rule includes: a target difference and a fault level corresponding to the target difference; wherein, the target difference is the difference between the parameter value of the historical operation data associated with any target performance metric under the corresponding target performance metric and the corresponding safety threshold;

[0020] Integrate the respective target performance metrics and the corresponding risk coefficients, safety thresholds, fault determination rules, first association relationship, second association relationship, and historical operation data associated with the corresponding target performance metrics into the initial digital twin model to obtain a processed initial digital twin model.

[0021] In an alternative embodiment, the fault analysis result further includes: a first safety score for the target ship to continue operating under the real-time operation data;

[0022] The first safety score is obtained by summing the target differences corresponding to each target performance metric and the risk coefficients of the corresponding target performance metrics.

[0023] In an alternative embodiment, matching the target fault tolerance control scheme corresponding to the fault type and the fault level from the configured ship fault and fault tolerance control knowledge graph library, including:

[0024] Match a plurality of initial fault tolerance control schemes corresponding to the fault type and the fault level from the configured ship fault and fault tolerance control knowledge graph library; wherein, any initial fault tolerance control scheme includes: at least one fault tolerance control measure and the execution time and energy consumption required to execute the corresponding fault tolerance control measure;

[0025] For any initial fault tolerance control scheme, calculate the total response time and total energy consumption of the target ship to execute the initial fault tolerance control scheme;

[0026] Based on the fault type, the fault level, and the first safety score, predict the second safety score of the target ship under the total response time and the total energy consumption;

[0027] Input each initial fault tolerance control scheme, the corresponding total response time, total energy consumption, and second safety score into a pre-constructed multi-objective optimization model to obtain an optimal fault tolerance control scheme;

[0028] Use the optimal fault tolerance control scheme as the target fault tolerance control scheme.

[0029] In an alternative embodiment, the target performance metrics include: the overload risk of the ship recommender and the safe sailing speed.

[0030] In a second aspect, the present invention provides a fault analysis and fault tolerance control device for a ship, the device comprising:

[0031] An acquisition unit for acquiring real-time operation data and navigation environment data of a target ship;

[0032] An analysis unit for inputting the real-time operation data into a digital twin model of the target ship pre-constructed for ship fault simulation analysis to obtain a fault analysis result; wherein, the fault analysis result includes: the fault type and the fault level; the digital twin model is used to fuse with the target ship in terms of spatial scale and time scale to synchronously reflect the mechanical health state of the target ship at the current moment, and perform fault virtual simulation analysis under the real-time operation data to obtain a fault analysis result;

[0033] A matching unit for matching a target fault tolerance control scheme corresponding to the fault type and the fault level from a configured ship fault and fault tolerance control knowledge graph library;

[0034] A generation unit for generating ship control parameters according to the target fault tolerance control scheme;

[0035] A control unit for controlling the target ship to sail under the navigation environment data based on the ship control parameters.

[0036] In a third aspect, the present invention provides an electronic device, the electronic device comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0037] The memory is used for storing a computer program;

[0038] The processor is used for implementing the method according to any one of the foregoing embodiments when executing the program stored on the memory.

[0039] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and the computer program realizes the method according to any one of the foregoing embodiments when executed by a processor.

[0040] This application establishes a digital twin model of the target ship by combining the coupling relationship between environmental parameters and equipment status. The digital twin model aligns virtual fault signals and real data in space and time; incorporates the risk of thruster overload and safe speed into the target performance indicators to participate in the evaluation of the ship's safety score; determines the fault-tolerant control scheme based on a dynamic reasoning framework of graph embedding and multi-objective optimization, combined with a fault-tolerant decision tree of a knowledge graph; not only effectively improves the accuracy of fault analysis, increases the response speed, and reduces the operation and maintenance costs, but also can adapt to fault analysis and processing under various operation data and various environments.

[0041] The fault identification accuracy rate of this application is ≥95% (the traditional method is ≤80%), and especially the detection rate of compound faults is increased by 40%. The full-link delay from the occurrence of a fault to the execution of a fault-tolerant action in this application is ≤500 ms (the traditional system is ≥2 seconds). This application reduces unnecessary shutdowns caused by misjudgment, and it is expected that the maintenance cost will be reduced by 25%. This application supports the automatic processing of more than 200 fault modes (the traditional system is ≤50). Brief Description of the Drawings

[0042] In order to more clearly illustrate the technical solutions of the embodiments of this application, the following will briefly introduce the drawings required to be used in the embodiments of this application. It should be understood that the following drawings only show some embodiments of this application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other relevant drawings can also be obtained based on these drawings.

[0043] Figure 1 It is a flowchart of a method for fault analysis and fault-tolerant control of a ship provided by an embodiment of this application;

[0044] Figure 2 It is a schematic structural diagram of a device for fault analysis and fault-tolerant control of a ship provided by an embodiment of this application;

[0045] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of this application. Detailed Embodiments

[0046] The following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of this application.

[0047] The fault analysis and fault tolerance control method for ships provided by the embodiments of the present application can be applied to a server or a terminal with strong computing power. The server can be a physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms. The terminal can be a user equipment (UE) such as a mobile phone, a smart phone, a laptop computer, a digital broadcast receiver, a personal digital assistant (PDA), a tablet computer (PAD), a handheld device, a vehicle-mounted device, a wearable device, a computing device or other processing devices connected to a wireless modem, a mobile station (MS), a mobile terminal, etc. The terminal and the server can be directly or indirectly connected through wired or wireless communication methods, which are not limited in this application.

[0048] The preferred embodiments of the present application will be described below with reference to the accompanying drawings of the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. And without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0049] Figure 1 It is a schematic flowchart of a fault analysis and fault tolerance control method for a ship provided by an embodiment of the present application. As Figure 1 shown, the method may include:

[0050] Step S110: Obtain the real-time operation data of the target ship, input the real-time operation data into the digital twin model of the target ship constructed in advance for ship fault simulation analysis, and obtain a fault analysis result.

[0051] In the embodiments of the present application, the real-time operation data includes: the structural data of the target ship, the real-time position, the course, the speed, the route, and the positions of rescue points on the route, the operation parameters of each device on the ship, the fuel consumption, the output power and status of the generator set, the performance indicators of the ship propulsion state, the ship weight, the types, weights, and distribution conditions of the goods loaded on the ship, and other special matters (such as whether it is a hazardous chemical), the liquid level monitoring results of each cabin of the ship, the stress analysis results, and the status of safety equipment; the water density, water flow speed, wind speed, wind direction, air temperature, air pressure, humidity, sea current direction and speed, wave height and period of the water area at the real-time position and on the route.

[0052] In the embodiments of the present application, the structural data of the ship includes: blade area, battery type, battery storage capacity, ship area, and so on.

[0053] In the embodiments of the present application, the fault analysis result includes: fault type, fault level, and the first safety score for the target ship to continue operating under real-time operation data; the first safety score is obtained by summing the target differences corresponding to each target performance index and the corresponding target performance index risk coefficients.

[0054] In the embodiments of the present application, the digital twin model is integrated with the target ship in terms of spatial scale and time scale to synchronously reflect the mechanical health state of the target ship at the current moment, and perform fault virtual simulation analysis under real-time operation data to obtain the fault analysis result; wherein, the mechanical health state is the health state of all components on the target ship.

[0055] In the embodiments of the present application, the method for constructing the digital twin model of the target ship includes:

[0056] Obtain the three-dimensional geometric model and dynamic behavior model of the target ship, as well as all historical operation data covering the entire life cycle of the target ship; according to the three-dimensional geometric model and dynamic behavior model, construct the initial digital twin model of the target ship; analyze all historical operation data to obtain multiple target performance indicators, the first correlation relationship between the target performance indicators, the first safety score of each target performance indicator and the target ship, the second correlation relationship between energy consumption and response time, and the historical operation data associated with each target performance indicator;

[0057] Integrate multiple target performance indicators, the corresponding first correlation relationship and second correlation relationship, and the historical operation data associated with the corresponding target performance indicators into the initial digital twin model to obtain the processed initial digital twin model; use all historical operation data to train the processed initial digital twin model to obtain the digital twin model of the target ship.

[0058] In another embodiment of the present application, the method for constructing the digital twin model of the target ship further includes:

[0059] Obtain the wear model of the target ship, the maintenance records covering the entire life cycle of the target ship, and all components of the target ship; wherein, the maintenance records include maintenance date, fault date, fault location, environmental data at the fault location (including water density and water flow velocity, etc.), maintenance parts, fault causes, wear status, and maintenance measures;

[0060] For any component, extract the wear status, fault cause, maintenance measure, and environmental data at the fault location corresponding to the component from the maintenance records, and match the corresponding historical operation data according to the fault date;

[0061] Perform a correlation analysis on the wear state, failure causes, maintenance measures, environmental data at the failure location, and corresponding historical operation data of the component to determine the correlation between the historical operation data of the ship, the environmental data at the failure location, the component failure causes, and the wear state;

[0062] Utilize the correlation between the historical operation data of the ship, the environmental data at the failure location, the component failure causes, and the wear state to train a wear model for the target ship and obtain a trained wear model;

[0063] Integrate the trained wear model into the digital twin model of the target ship, and add the correlation between the historical operation data of the ship, the environmental data at the failure location, the component failure causes, and the wear state as an operation constraint of the digital twin model of the target ship to the digital twin model to obtain the final digital twin model.

[0064] In the embodiment of the present application, integrating the wear model into the digital twin model means associating and integrating the wear model with the digital twin model. The digital twin model of the target ship is data-mapped with each data acquisition device (such as temperature sensors and speed detectors, etc.) on the target ship, enabling the digital twin model to receive and process real-time operation data from the target ship in real time, and simulating the navigation of the target ship with the actual navigation state and wear state of the target ship, so that the digital twin model can reflect the spatio-temporal change characteristics of the target ship at the spatial and temporal scales and the mechanical health state at the current moment in real time.

[0065] In the embodiment of the present application, the target performance indicators include: the overload risk and safe speed of the ship recommender.

[0066] In the embodiment of the present application, all historical operation data includes: fault operation data and corresponding fault types, as well as normal operation data; the dynamic behavior model is used to characterize the physical characteristics and operation rules of all subsystems of the target ship; each target performance indicator is a performance indicator related to the first safety score, energy consumption, and response time of the target ship.

[0067] In the embodiment of the present application, integrating multiple target performance indicators, corresponding first and second correlation relationships, and historical operation data associated with the corresponding target performance indicators into the initial digital twin model to obtain a processed initial digital twin model, including:

[0068] Obtain the risk coefficient, safety threshold, and fault determination rule corresponding to each configured target performance indicator; wherein, the fault determination rule includes: the target difference and the fault level corresponding to the target difference; wherein, the target difference is the difference between the parameter value of the historical operation data associated with any target performance indicator under the corresponding target performance indicator and the corresponding safety threshold;

[0069] Integrate each target performance index, the corresponding risk coefficient, safety threshold, fault determination rule, first association relationship, second association relationship, and historical operation data associated with the corresponding target performance index into the initial digital twin model to obtain the processed initial digital twin model.

[0070] Step S120: Match the target fault tolerance control scheme corresponding to the fault type and fault level from the configured ship fault and fault tolerance control knowledge graph database.

[0071] In the embodiment of the present application, matching the target fault tolerance control scheme corresponding to the fault type and fault level from the configured ship fault and fault tolerance control knowledge graph database includes:

[0072] Match multiple initial fault tolerance control schemes corresponding to the fault type and fault level from the configured ship fault and fault tolerance control knowledge graph database; for any initial fault tolerance control scheme, calculate the total response time and total energy consumption of the target ship for executing the initial fault tolerance control scheme; based on the fault type, fault level, and first safety score, predict the second safety score of the target ship under the total response time and total energy consumption; input each initial fault tolerance control scheme, the corresponding total response time, total energy consumption, and second safety score into the pre-constructed multi-objective optimization model to obtain the optimal fault tolerance control scheme; use the optimal fault tolerance control scheme as the target fault tolerance control scheme.

[0073] In the embodiment of the present application, any initial fault tolerance control scheme includes: at least one fault tolerance control measure and the execution time and energy consumption required for executing the corresponding fault tolerance control measure.

[0074] In the embodiment of the present application, the construction method of the ship fault and fault tolerance control knowledge graph database includes:

[0075] Obtain the basic data of the target ship, historical operation data (including the same data items as the real-time operation data), the ship type and ship model of the target ship, the fault case database corresponding to the corresponding ship type and ship model, and the ship expert database; among them, the data in the fault case database includes: fault phenomenon, fault cause analysis, fault tolerance measures taken, and the final solution result; it not only covers the solved conventional faults, but also particularly focuses on those unknown fault mode cases that are difficult to handle or have special characteristics; the ship expert database includes: academic literature, research reports, industry standards, and discussion contents on professional forums in the ship engineering field, the latest fault research results, new fault tolerance control technologies, and the best practice experiences in the industry; the basic data includes: information such as ship structure, system composition, normal operation parameter range, and preset fault response strategies, etc.

[0076] Identify entities, numerical entities, and relationships from the data obtained above.

[0077] Perform clustering analysis on the historical fault case data in the fault case library, classify similar fault cases into one category, and discover potential fault mode clusters; by analyzing the common features of the fault cases within each fault mode cluster, extract new ship faults; use the association rule mining algorithm to analyze the association relationships among fault phenomena, fault causes, adopted fault tolerance control schemes, and final results;

[0078] Construct an initial ship fault and fault tolerance control knowledge graph library based on the identified entities, numerical entities, relationships, and corresponding ship faults and fault tolerance control schemes;

[0079] For any fault tolerance control scheme in the initial ship fault and fault tolerance control knowledge graph library, calculate the total response time, total energy consumption, and second safety score of the fault tolerance control scheme according to the pre-constructed multi-objective function; obtain the configured multi-objective optimized fault tolerance inference rules and the total response time, total energy consumption, and second safety score of each fault tolerance control scheme, and update the ship fault and fault tolerance control knowledge graph library.

[0080] In the embodiments of the present application, identifying entities, numerical entities, and relationships includes:

[0081] Named entity recognition based on deep learning: Adopt advanced deep learning models, such as BERT, GPT, etc. combined with the Transformer architecture, train the collected text data, and identify entities related to ship faults and fault tolerance control, including ship equipment names (such as main engines, steering gears, generators, etc.), fault types (such as mechanical faults, electrical faults, communication faults, etc.), fault locations (such as engine pistons, propeller blades, etc.), fault tolerance control methods (such as redundant control, adaptive control, fault reconstruction control, etc.), and related performance indicators (such as safety level, energy consumption value, maintenance time, etc.);

[0082] Numerical entity extraction: For numerical entities in historical operation data, such as pressure values, temperature values, rotational speeds, etc., extract them through data parsing and pattern matching methods, and associate them with corresponding equipment and operating states;

[0083] Use semantic analysis tools in natural language processing technology, such as dependency syntax analysis, semantic role annotation, etc., to deeply understand the semantic relationships between entities in the obtained data, and obtain the relationships between entities; for example, determine the causal relationship between "fault cause" and "fault type", the coping relationship between "fault tolerance control method" and "fault type", and the influence relationship between "performance indicator" and "fault tolerance control method".

[0084] In the embodiments of the present application, for homonymous or synonymous entities extracted from different data sources, entity alignment is performed by comparing multi-dimensional information such as the attribute information of the entities (such as device models, fault feature descriptions, etc.), context information, and semantic similarity; a knowledge conflict detection and resolution mechanism is established, and the conflicting knowledge is evaluated and corrected through manual review, reference to authoritative materials, or the experience of domain experts to ensure the consistency and accuracy of the knowledge graph.

[0085] In the embodiments of the present application, the multi-objective optimization fault-tolerant inference rules are determined based on domain knowledge and expert experience, including that if the current ship is in a high-risk navigation area and a certain type of fault that may affect safety occurs, a fault-tolerant control method with a high safety level is preferentially selected; if the fuel reserve of the ship is low and the fault has little impact on navigation, a fault-tolerant control strategy with low energy consumption is preferentially considered. Through these inference rules, an optimal fault-tolerant decision-making scheme is automatically inferred according to different ship operating states and fault conditions to balance multi-objective requirements.

[0086] In the embodiments of the present application, the ship fault and fault-tolerant control knowledge graph library adopts a knowledge update rule based on incremental learning. When new ship operation data, fault cases, or research results appear, the new data can be automatically incorporated into the existing knowledge graph. For example, an online learning neural network model is used to fine-tune the model when new data arrives, and the entity, relationship, and attribute information in the knowledge graph are updated.

[0087] In the embodiments of the present application, each initial fault-tolerant control scheme, the corresponding total response time, total energy consumption, and second safety score are input into a pre-constructed multi-objective optimization model to obtain an optimal fault-tolerant control scheme, including:

[0088] An optimal fault-tolerant control scheme is determined by adopting a graph optimization scheme; the initial fault-tolerant control scheme is regarded as nodes and edges in the graph, and safety, energy consumption, and response time are converted into weights of the graph. By calculating the optimal path or maximum flow in the graph, an optimal fault-tolerant control scheme that meets multi-objective balance is found.

[0089] Step S130: Generate ship control parameters according to the target fault-tolerant control scheme, and based on the ship control parameters, control the target ship to continue sailing.

[0090] In the embodiments of the present application, when the ship operator adjusts the ship control parameters to optimize ship control, the adjusted ship control parameters of the ship operator are used to generate a new fault-tolerant control scheme, which is updated in the configured ship fault and fault-tolerant control knowledge graph library.

[0091] In an embodiment of the present application, the ship fault analysis and fault-tolerant control method includes:

[0092] Step 1: Construct the dynamic fault simulation framework of ship digital twin

[0093] Thruster overload risk formula in dynamic fault injection

[0094] Formula: P ovorload = k·v 2 ·ρ;

[0095] Where, P overload : Thruster overload risk index (dimensionless), the larger the value, the higher the overload risk; k: Thruster load coefficient (determined by thruster design parameters, unit: m -1 ), and the calculation formula is Where C thrust is the thrust coefficient, A is the thruster blade area (m 2 ); v: Real-time water flow velocity (unit: m / s), measured by on-board flow velocity sensor; ρ: Water density (unit: kg / m 3 ), and the fresh water density of 1000 kg / m 3 is taken by default (can be adjusted according to the actual salinity of the water area).

[0096] Basis for formula derivation:

[0097] Based on the thruster thrust formula F thrust = 0.5·C thrust ·A·ρ·v 2 in hydrodynamics, the overload risk index P overload is simplified to the ratio of thrust to rated load, and the dimension is eliminated through normalization, and finally expressed as k·v 2 ·ρ.

[0098] Step 2: Generation of fault-tolerant decision-making based on knowledge graph

[0099] Safe navigation speed calculation formula

[0100] Formula:

[0101] Where, v safc : Safe navigation speed threshold (unit: m / s), exceeding this speed may cause equipment overload; F thrust : Real-time thrust of thruster (unit: N), calculated from motor power and speed; C d : Hull resistance coefficient (dimensionless), calibrated through ship model test or CFD simulation; A: Hull cross-sectional area (unit: m 2 ); ρ: Water density (unit: kg / m 3 ).

[0102] Basis for formula derivation: According to the ship resistance balance principle, the thruster thrust needs to be equal to the hull resistance: Solve for v by transforming the above formula safe , and the expression for the safe sailing speed can be obtained.

[0103] Step 3: Multi-objective optimization objective function

[0104] Formula:

[0105]

[0106] Parameter definition and quantification method:

[0107] Risk coefficient: The severity score of the fault consequence (0 - 1), which is the first safety score, predefined according to the fault type (e.g., battery thermal runaway = 0.9, sensor drift = 0.3);

[0108] Energy consumption: The power consumption of the fault-tolerant action (unit: kWh), for example, the energy consumption of starting the standby motor = 5 kWh;

[0109] Response time: The total delay from the occurrence of the fault to the execution of the fault-tolerant action (unit: s);

[0110] Safety threshold, which is the second safety score: Ship stability parameters (such as GM value ≥ 0.3 m), determined by the ship design specifications.

[0111] Taking the fault handling process of battery thermal runaway as an example:

[0112] 1. Fault injection and detection:

[0113] The digital twin model injects the signal of "abnormal increase in battery temperature" (parameter: temperature rise rate ≥ 5℃ / s);

[0114] The anomaly is detected through the AI model, triggering a knowledge graph query.

[0115] 2. Knowledge graph reasoning:

[0116] Match the historical node "precursor of thermal runaway" and associate the solution:

[0117] Primary fault tolerance: Start the liquid cooling system (energy consumption = 2 kWh, risk coefficient = 0.2);

[0118] Intermediate fault tolerance: Isolate the faulty battery module (energy consumption = 1 kWh, risk coefficient = 0.4);

[0119] Select the optimal solution (balancing energy consumption and risk) through the NSGA-II algorithm.

[0120] 3. Fault-tolerant execution:

[0121] The edge computing node issues the instruction to "start the liquid cooling system" (response time = 300 ms);

[0122] Monitor that the temperature drops back to the safe range (<60°C) and update the knowledge graph.

[0123] Corresponding to the above method, an embodiment of the present application further provides a fault analysis and fault tolerance control device for a ship, as Figure 2 shown. The fault analysis and fault tolerance control device for the ship includes:

[0124] An acquisition unit 210, configured to acquire real-time operation data and navigation environment data of a target ship;

[0125] An analysis unit 220, configured to input the real-time operation data into a digital twin model of the target ship pre-constructed for ship fault simulation analysis to obtain a fault analysis result; wherein, the fault analysis result includes: a fault type and a fault level; the digital twin model is used to fuse with the target ship in terms of spatial scale and time scale to synchronously reflect the mechanical health state of the target ship at the current moment, and perform fault virtual simulation analysis under the real-time operation data to obtain a fault analysis result;

[0126] A matching unit 230, configured to match a target fault tolerance control scheme corresponding to the fault type and the fault level from a configured ship fault and fault tolerance control knowledge graph library;

[0127] A generating unit 240, configured to generate ship control parameters according to the target fault tolerance control scheme;

[0128] A control unit 250, configured to control the target ship to navigate under the navigation environment data based on the ship control parameters.

[0129] The functions of the functional units of the fault analysis and fault tolerance control device for the ship provided in the above embodiments of the present application can be implemented by the above method steps. Therefore, the specific working processes and beneficial effects of each unit in the fault analysis and fault tolerance control device for the ship provided in the embodiments of the present application will not be repeated here.

[0130] An embodiment of the present application further provides an electronic device, as Figure 3 shown, including a processor 310, a communication interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communication interface 320, and the memory 330 complete mutual communication through the communication bus 340.

[0131] The memory 330 is used to store a computer program;

[0132] When the processor 310 is configured to execute the program stored on the memory 330, the following steps are implemented:

[0133] Acquire real-time operation data of the target ship;

[0134] Input the real-time operation data into the pre-constructed digital twin model of the target ship for ship fault simulation analysis to obtain the fault analysis results; among them, the fault analysis results include: fault type and fault level; the digital twin model is fused with the target ship in terms of spatial scale and time scale to synchronously reflect the mechanical health state of the target ship at the current moment, and conduct fault virtual simulation analysis under the real-time operation data to obtain the fault analysis results;

[0135] Match the target fault tolerance control scheme corresponding to the fault type and fault level from the configured ship fault and fault tolerance control knowledge graph library;

[0136] Generate ship control parameters according to the target fault tolerance control scheme;

[0137] Based on the ship control parameters, control the target ship to continue sailing.

[0138] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0139] The communication interface is used for communication between the above-mentioned electronic device and other devices.

[0140] The memory can include a Random Access Memory (RAM), and can also include a Non-Volatile Memory (NVM), such as at least one disk memory. Optionally, the memory can also be at least one storage device located far from the aforementioned processor.

[0141] The above-mentioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processing (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0142] Since the implementation manners and beneficial effects of the components of the electronic device in the above embodiments for solving problems can be implemented by referring to the steps in the embodiments shown in Figure 1 Therefore, the specific working process and beneficial effects of the electronic device provided in the embodiments of the present application will not be repeated here.

[0143] In another embodiment provided by the present application, a computer-readable storage medium is further provided. Instructions are stored in the computer-readable storage medium. When it runs on a computer, it causes the computer to execute the fault analysis and fault tolerance control method of the ship described in any one of the above embodiments.

[0144] In another embodiment provided by the present application, a computer program product including instructions is further provided. When it runs on a computer, it causes the computer to execute the fault analysis and fault tolerance control method of the ship described in any one of the above embodiments.

[0145] Those skilled in the art should understand that the embodiments in the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the embodiments in the embodiments of 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 embodiments in the embodiments of 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.

[0146] The embodiments in the embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments in the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. 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, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0147] 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, so that the instructions stored in the computer-readable memory generate a manufactured product including an instruction device, and the instruction device implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0148] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, causing a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one process or multiple processes and / or one block or multiple blocks. Figure 1 one process or multiple processes and / or Figure 1 steps for implementing the functions specified in one block or multiple blocks.

[0149] Although the preferred embodiments in the embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the embodiments of the present application.

[0150] Obviously, those skilled in the art can make various changes and modifications to the embodiments in the embodiments of the present application without departing from the spirit and scope of the embodiments in the embodiments of the present application. Thus, if these modifications and variations of the embodiments in the embodiments of the present application fall within the scope of the claims of the embodiments of the present application and their equivalent technologies, the embodiments in the embodiments of the present application are also intended to include these changes and modifications.

Claims

1. A fault analysis and fault tolerance control method for a ship, characterized in that, The method includes: Obtaining the real-time operation data of the target ship; Inputting the real-time operation data into the digital twin model of the target ship pre-constructed for ship fault simulation analysis to obtain a fault analysis result; wherein, the fault analysis result includes: fault type and fault level; the digital twin model is fused with the target ship in terms of spatial scale and time scale to synchronously reflect the mechanical health state of the target ship at the current moment, and perform fault virtual simulation analysis under the real-time operation data to obtain a fault analysis result; Matching the target fault tolerance control scheme corresponding to the fault type and the fault level from the configured ship fault and fault tolerance control knowledge graph database; Generating ship control parameters according to the target fault tolerance control scheme; Based on the ship control parameters, controlling the target ship to continue sailing.

2. The method according to claim 1, characterized in that The construction method of the digital twin model of the target ship includes: Obtaining the three-dimensional geometric model and dynamic behavior model of the target ship, and all historical operation data covering the entire life cycle of the target ship; wherein, all historical operation data includes: fault operation data and corresponding fault types, as well as normal operation data; The dynamic behavior model is used to characterize the physical characteristics and operation rules of all subsystems of the target ship; Constructing the initial digital twin model of the target ship according to the three-dimensional geometric model and dynamic behavior model; Analyzing all the historical operation data to obtain multiple target performance indicators, the first association relationship between the target performance indicators, the first safety score of the target ship related to each target performance indicator, the second association relationship between energy consumption and response time, and the historical operation data associated with each target performance indicator; wherein, each target performance indicator is a performance indicator related to the first safety score, energy consumption and response time of the target ship; Integrating multiple target performance indicators, the corresponding first association relationship and second association relationship, and the historical operation data associated with the corresponding target performance indicators into the initial digital twin model to obtain a processed initial digital twin model; Training the processed initial digital twin model with all the historical operation data to obtain the digital twin model of the target ship.

3. The method according to claim 2, characterized in that Integrating multiple target performance indicators, the corresponding first association relationship and second association relationship, and the historical operation data associated with the corresponding target performance indicators into the initial digital twin model to obtain a processed initial digital twin model, including: Obtaining the risk coefficient, safety threshold and fault determination rule corresponding to each target performance indicator configured; wherein, the fault determination rule includes: target difference and the fault level corresponding to the target difference; wherein, the target difference is the difference between the parameter value of the historical operation data associated with any target performance indicator under the corresponding target performance indicator and the corresponding safety threshold; Integrate the respective target performance indicators, corresponding risk coefficients, safety thresholds, fault determination rules, first association relationships, second association relationships, and historical operation data associated with the respective target performance indicators into the initial digital twin model to obtain a processed initial digital twin model.

4. The method according to claim 3, wherein The fault analysis result further includes: a first safety score for the target ship to continue operating under the real-time operation data; The first safety score is obtained by summing the target differences corresponding to the respective target performance indicators and the corresponding target performance indicator risk coefficients.

5. The method according to claim 4, characterized in that, From the configured ship fault and fault tolerance control knowledge graph library, match the target fault tolerance control scheme corresponding to the fault type and the fault level, including: From the configured ship fault and fault tolerance control knowledge graph library, match multiple initial fault tolerance control schemes corresponding to the fault type and the fault level; wherein, any one of the initial fault tolerance control schemes includes: at least one fault tolerance control measure and the execution time and energy consumption required to execute the corresponding fault tolerance control measure; For any one of the initial fault tolerance control schemes, calculate the total response time and total energy consumption of the target ship to execute the initial fault tolerance control scheme; Based on the fault type, the fault level, and the first safety score, predict the second safety score of the target ship under the total response time and the total energy consumption; Input each initial fault tolerance control scheme, the corresponding total response time, total energy consumption, and second safety score into a pre-constructed multi-objective optimization model to obtain an optimal fault tolerance control scheme; Use the optimal fault tolerance control scheme as the target fault tolerance control scheme.

6. The method according to claim 3, wherein The target performance indicators include: the overload risk of the ship recommender and the safe sailing speed.

7. A fault analysis and fault tolerance control device for a ship, characterized in that, The device includes: An acquisition unit, configured to acquire real-time operation data and navigation environment data of a target ship; An analysis unit, configured to input the real-time operation data into a pre-constructed digital twin model of the target ship for ship fault simulation analysis to obtain a fault analysis result; wherein, the fault analysis result includes: a fault type and a fault level; the digital twin model is used to fuse with the target ship on a spatial scale and a time scale to synchronously reflect the mechanical health state of the target ship at the current moment, and perform fault virtual simulation analysis under the real-time operation data to obtain a fault analysis result; A matching unit, configured to match the target fault tolerance control scheme corresponding to the fault type and the fault level from the configured ship fault and fault tolerance control knowledge graph library; A generation unit, configured to generate ship control parameters according to the target fault tolerance control scheme; A control unit, configured to control the target ship to sail under the navigation environment data based on the ship control parameters.

8. An electronic device, characterized in that, The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; The memory is used to store a computer program; The processor, when executing the program stored on the memory, implements the method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1-6 is implemented.

Images