Data knowledge hybrid driven ship test and maintenance process autonomous evolution method

Abstract

The invention discloses a data knowledge hybrid driven ship test and maintenance process autonomous evolution method. The method comprises the following steps: acquiring real-time data information of operation conditions of various equipment of a ship; constructing a logical reasoning system based on an expert knowledge base and a deep reinforcement learning model used for maintaining a decision; according to the method, a ship test and maintenance process digital twin model is constructed, real parameter simulation is performed in a virtual scene according to acquired real-time data information and virtual environment parameters, so that virtual simulation of the ship test and maintenance process is performed, and the ship test and maintenance process is simulated in combination with a constructed logical reasoning system and a deep reinforcement learning model. Performing prediction and decision optimization on ship test and maintenance effects; by deploying a digital twinborn model, a logical reasoning system and a deep reinforcement learning model, the ship test and maintenance process is rehearsed and evaluated so as to optimize a ship test and maintenance scheme. According to the invention, data knowledge hybrid driven ship test and maintenance process autonomous evolution can be realized.

Description

Technical Field

[0001] This invention relates to the field of marine engineering, and in particular to an automated evolution method for ship testing and maintenance processes driven by a data-knowledge hybrid approach. Background Technology

[0002] With the development of technologies related to shipbuilding and energy, the size, weight, and other traditional physical parameters of modern ship equipment, as well as the complexity of their internal design and structure, are rapidly increasing. Coupled with the inherently long cycles, high costs, and significant uncertainties of traditional ship testing and maintenance work, this presents even greater challenges to ship performance testing and maintenance engineering, further increasing the risks involved in ship inspection and maintenance. Ship testing and maintenance technologies also require a comprehensive upgrade in both management methods and technical approaches.

[0003] Digital twin technology fully utilizes data from physical models, sensors, and operational history to integrate multi-disciplinary, multi-physical-quantity, multi-scale, and multi-probabilistic simulation processes, completing mapping in virtual space to reflect the entire lifecycle of the corresponding physical equipment. Proposed in the early 20th century, this technology remains under development due to limitations in computer science and big data algorithms, particularly in data collection and processing, and model building. However, in recent years, the development and continuous progress of technologies such as the Internet of Things, big data, cloud computing, and artificial intelligence have made it increasingly possible to utilize digital twin technology for virtual-real integration and scenario simulation in engineering. Summary of the Invention

[0004] In response to the urgent need in the shipbuilding industry for information-based management of modern ship testing and intelligent design of maintenance programs, this invention proposes an autonomous evolution method for ship testing and maintenance processes driven by data and knowledge hybrid approaches, aiming to solve problems related to the design of modern ship testing and maintenance programs.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: In a first aspect, the present invention provides an autonomous evolution method for ship testing and maintenance processes driven by data and knowledge hybrid approaches, the method comprising: S1. Collect real-time data on the operating status of various ship equipment; S2. Collect relevant literature and industry standards on ship testing and maintenance, establish an expert knowledge base, and construct a logical reasoning system based on the physical characteristics-ship status related knowledge and causal logic, as well as a deep reinforcement learning model for maintenance decision-making. S3. Scenario building is carried out through digital twin technology to construct a digital twin model of the ship testing and maintenance process. Based on the collected real-time data information and virtual environment parameters, the real parameters are simulated in the virtual scene to conduct virtual simulation of the ship testing and maintenance process. Combined with the constructed logical reasoning system and deep reinforcement learning model, the ship testing and maintenance effect is predicted and the decision is optimized. S4. By deploying digital twin models, logical reasoning systems, and deep reinforcement learning models, the ship testing and maintenance process is rehearsed and evaluated to optimize ship testing and maintenance plans.

[0006] In the above scheme, step S1 includes: Determine the information items to be collected, the collection accuracy, and the sampling frequency; Select the appropriate sensors for installation, and centralize the data at the data acquisition terminal for data aggregation and preprocessing.

[0007] In the above scheme, the real-time data information collected is the real-time status data and monitoring information generated during the ship testing and maintenance process, including at least temperature information, operating noise, vibration amplitude, main engine status, fuel consumption and emissions, and load and draft.

[0008] In the above scheme, step S2 includes: Collect relevant literature and industry standards on ship testing and maintenance. The literature entries should include at least the fault judgment threshold entries and logical relationships of commonly used equipment. Commonly used equipment should include at least ship power equipment, navigation equipment and communication equipment. The collected literature and industry standards related to ship testing and maintenance are organized and integrated, expert knowledge is merged and summarized, and an expert knowledge base and knowledge representation form are selected to systematically model and describe the acquired knowledge, and a logical reasoning system based on the expert knowledge base is constructed. The ship testing and maintenance environment is modeled as a reinforcement learning environment, and a deep reinforcement learning model is constructed for maintenance decision-making.

[0009] In the above scheme, the Web Ontology Language (OWL) is used as the modeling language to achieve a unified description of the expert knowledge base. By utilizing the functions and features of Protégé and OWL, the concept layer, category layer, attribute layer, and instance layer of the expert knowledge base architecture are designed.

[0010] In the above scheme, a parallel approach of physical modeling and statistical modeling is adopted to construct a digital twin model of the ship testing and maintenance process. This digital twin model includes: Physical model: Digital simulation of the actual environment for ship testing and maintenance using 3D modeling software; The statistical model combines virtual parameters from the physical model with actual transmission parameters from the sensors to perform statistical feature analysis, making relevant result predictions and plan optimizations; the statistical model is a deep learning model.

[0011] In the above scheme, the decision-making process is based on a logical reasoning system and a deep reinforcement learning model. This process is driven by a data-knowledge hybrid approach and is applied to ship testing and maintenance.

[0012] In the above scheme, the logical reasoning system completes the autonomous evolution of the knowledge level based on the completion status of the current task and the new literature published online. At the same time, the newly added multidimensional feature data collected by the ship when performing new tasks is added to the state space data of the deep reinforcement learning model, so that the data-driven autonomous evolution of the lower level can be successfully carried out.

[0013] In a second aspect, the present invention provides a computer device, comprising: a processor and a memory, the memory storing a program or instructions executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes as described in any one of the first aspects.

[0014] Thirdly, the present invention provides a computer-readable storage medium, characterized in that it stores a program or instructions thereon, which, when executed by a processor, implement the steps of the data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes as described in any one of the first aspects.

[0015] In summary, compared with the prior art, the above-described technical solutions conceived by this invention can achieve the following beneficial effects: The method proposed in this invention achieves dynamic simulation, intelligent prediction, and autonomous decision-making optimization throughout the entire process of ship testing and maintenance by constructing a data- and knowledge-driven digital twin system. This method not only integrates real-time equipment data and multi-dimensional environmental information to ensure the accuracy of model predictions and the reliability of solutions, but also leverages logical reasoning and deep reinforcement learning models to enable the system to continuously learn and autonomously evolve from historical data and interactions. Compared to traditional methods, this invention significantly improves resource utilization efficiency, the scientific nature of solutions, and execution flexibility in the testing and maintenance process. It effectively reduces operation and maintenance costs and uncertainties through digital and intelligent means, comprehensively enhancing the overall efficiency and adaptability of ship testing and maintenance work. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the overall process of an auto-evolutionary method for ship testing and maintenance driven by data and knowledge hybridization, provided in an embodiment of the present invention. Figure 2A block diagram of a data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of data flow provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of a digital twin model provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of autonomous evolution provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of model deployment provided in an embodiment of the present invention; Figure 7 This is a schematic diagram of the hardware structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments provided by this invention without inventive effort are within the scope of protection of this invention.

[0018] Obviously, the accompanying drawings described below are merely some examples or embodiments of the present invention. Those skilled in the art can apply the present invention to other similar scenarios based on these drawings without any inventive effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this invention, modifications to design, manufacturing, or production based on the technical content disclosed in this invention are merely conventional technical means and should not be construed as insufficient disclosure of the present invention.

[0019] In this invention, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this invention may be combined with other embodiments without conflict.

[0020] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "a," "an," "an," "the," and similar words used in this invention do not indicate quantity limitation and may indicate singular or plural. The terms "comprising," "including," "having," and any variations thereof used in this invention are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms "connected," "linked," "coupled," and similar words used in this invention are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "A plurality" used in this invention refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships may exist; for example, "A and / or B" can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects have an "or" relationship. The terms "first," "second," and "third" used in this invention are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0021] Given the challenges of long cycles, high costs, and highly dynamic nature in ship testing and maintenance, this invention proposes a data-knowledge hybrid-driven autonomous evolution method for the ship testing and maintenance process. This method constructs a digital twin system integrating real-time data and expert knowledge to achieve dynamic simulation, intelligent prediction, and autonomous optimization of the entire ship testing and maintenance process. Specifically, it includes: collecting real-time data on ship equipment operation; establishing an expert knowledge base and a logical reasoning system based on it; constructing a deep reinforcement learning model for maintenance decision-making; building a digital twin model of ship testing and maintenance, and integrating the above system and model for simulation and prediction in a virtual environment; and finally, through system deployment, achieving dynamic optimization and autonomous evolution of the testing and maintenance plan, thereby comprehensively improving the flexibility, reliability, and intelligence level of the ship testing and maintenance process.

[0022] like Figure 1 and Figure 2 As shown, the present invention provides an automated evolution method for ship testing and maintenance processes driven by data and knowledge hybrid principles. Step S1: Collect real-time data on the operating status of various ship equipment; Step S2: Collect relevant literature and industry standards on ship testing and maintenance, establish an expert knowledge base, and construct a logical reasoning system based on the expert knowledge base and a deep reinforcement learning model for maintenance decision-making based on the knowledge related to physical characteristics and ship status and causal logic. Step S3: Scenario building is carried out using digital twin technology to construct a digital twin model of the ship testing and maintenance process. Based on the collected real-time data and virtual environment parameters, the real parameters are simulated in the virtual scenario to conduct virtual simulation of the ship testing and maintenance process. Combined with the constructed logical reasoning system and deep reinforcement learning model, the ship testing and maintenance effect is predicted and the decision is optimized. Step S4: By deploying digital twin models, logical reasoning systems, and deep reinforcement learning models, the ship testing and maintenance process is rehearsed and evaluated, ultimately aiming to optimize the ship testing and maintenance plan.

[0023] In some embodiments, step S1 specifically includes: Real-time data on the operational status of various ship equipment is collected. Ship data acquisition is the starting point of the entire method, providing data support and factual evidence for its implementation. This step involves first determining the information items to be collected, the collection accuracy, and the sampling frequency based on specific conditions. Generally, the collected information focuses on ship engine equipment and other key equipment. For special-operation vessels, relevant improvements should be made to the data collection plan. After determining the sampling requirements, corresponding sensors are selected and installed. The data is then collected at the data acquisition terminal for data aggregation, cleaning, standardization, and other preprocessing work, preparing for the next step of inputting the dataset into the digital twin model. It is important to note that the stability of the sensors and data acquisition terminal used in this step directly affects the reliability of the final solution; therefore, it is crucial to ensure the stability and reliability of the data acquisition equipment.

[0024] The data required for this step includes real-time status data and monitoring information generated during ship testing and maintenance processes, such as generator sets and control equipment. The collected status data includes: hull physical information and equipment operating parameters, typically including temperature information, operating noise, vibration amplitude, main engine status, fuel consumption and emissions, load and draft, and other physical information of various equipment during ship operation.

[0025] In some embodiments, step S2 specifically includes: Collect relevant literature and industry standards on ship testing and maintenance to establish an expert knowledge base. The literature entries collected in this step should include threshold entries and logical relationships related to fault diagnosis of commonly used equipment. Commonly used equipment includes, but is not limited to, ship propulsion equipment represented by engines, navigation equipment represented by radar, and communication equipment represented by data cables. Organize and integrate the collected expert knowledge and experimental data, merging and summarizing the expert knowledge. Based on the summarized expert knowledge and the needs of the expert knowledge base, select appropriate knowledge bases and knowledge representation forms to systematically model and describe the acquired knowledge. Commonly used knowledge representation forms mainly include: rule representation, ontology representation, decision trees, causal graphs, etc., to model and represent expert knowledge based on the collected knowledge. Rule representation (IF-THEN rules) is a form based on conditional reasoning, usually expressed in the form of "if...then...", mainly used to describe behavior or conclusions under specific conditions. This method is easy to understand and implement, widely used in expert systems and machine learning, and can clearly capture simple causal relationships. Ontology representation is a form of knowledge description that defines classes, attributes, and their relationships.

[0026] Using OWL (Web Ontology Language) as the modeling language, a unified description of the expert knowledge base is achieved. Leveraging the features and functionalities of Protégé and OWL, the concept layer, category layer, attribute layer, and instance layer of the expert knowledge base architecture are designed. Using Protégé as the ontology editor, based on the composition structure of the ontology model, classes and properties are defined by adding classes and properties. Descriptions of equivalence classes, members, and subclasses are added to refine the specific definitions of classes. The property definition function adds descriptions of equivalence properties, members, subclasses, domains, and ranges to refine the specific definitions of properties. This effectively constructs and manages the knowledge base, improving knowledge storage, retrieval, and reasoning capabilities.

[0027] A logical reasoning system is built based on an expert knowledge base. This system predicts the effectiveness of ship testing and maintenance based on knowledge of fault determination thresholds and logical relationships for commonly used equipment. Furthermore, the ship testing and maintenance environment (including equipment status, prediction results, and environmental conditions) is modeled as a reinforcement learning environment. A deep reinforcement learning model is constructed for maintenance decision-making. The model (agent) learns how to formulate the optimal maintenance action based on the current state (analyzed by the deep learning model).

[0028] In some embodiments, step S3 specifically includes: Digital twin model construction. The main function of the digital twin model in this method is to predict and optimize the effectiveness of ship testing and maintenance based on the dataset and virtual environment parameters collected in step S1. In selecting modeling methods, this invention adopts a parallel approach of physical modeling and statistical modeling. On the one hand, 3D modeling software is used to digitally simulate the actual environment of ship testing and maintenance; on the other hand, multiple statistical models are established to combine the statistical correlation characteristics of various equipment operating parameters during ship testing and maintenance with virtual environment parameters to ultimately make optimization decisions.

[0029] Specifically, the digital twin model described in this step should include two parts: a physical model and a statistical model. The physical model needs to consider various environmental conditions during the actual operation of the ship, such as wave height, wind direction, wind speed, ambient temperature and humidity, etc. The statistical model should combine the virtual parameters in the physical model with the actual transmission parameter information of the sensors to perform statistical feature analysis, make relevant result predictions and plan optimizations. Through the digital twin model, combined with the logical reasoning system based on the expert knowledge base constructed in step S2, the test results of the ship in the actual target environment can be roughly predicted, thereby adjusting the ship's operation and maintenance plan in a timely manner. The statistical model can adopt a deep learning model, which is built using a DNN neural network as the basic framework.

[0030] The decision-making process is implemented based on a logical reasoning system and a deep reinforcement learning model. This process is driven by a data-knowledge hybrid approach and applies to ship testing and maintenance. The construction process of the logical reasoning system and the deep reinforcement learning model has been described in detail in step S2.

[0031] In some embodiments, step S4 specifically includes: Model Deployment. By correctly installing and deploying the model, a precise mathematical model of ship information is obtained from the digital twin model. This model, based on an expert knowledge base, employs a logical reasoning system and a deep reinforcement learning model for maintenance decisions. It can continuously iterate its parameters after being fed a large dataset, achieving autonomous evolution and improving operational capabilities. This results in higher efficiency, more rational resource allocation, and lower actual costs for ship testing and maintenance. Specifically, existing expert knowledge bases typically do not contain decision-making items for new environments and tasks. The digital twin model performs knowledge-level autonomous evolution based on the current task completion status and newly published online literature to adapt to maintenance recommendations in the new era and multiple scenarios. Simultaneously, newly collected multidimensional feature data from when the ship performs new tasks is added to the state space data of the deep reinforcement learning model, enabling successful data-driven autonomous evolution at the lower level.

[0032] Specifically, based on the prediction results output by the digital twin model of the ship testing and maintenance process in step S3, the direction of the ship operation and maintenance plan can be basically determined by the deep reinforcement learning model. The model also follows up synchronously, that is, it continuously acquires relevant equipment information parameters during the operation and maintenance process, thereby achieving the effect of dynamically adjusting the test and maintenance plan throughout the entire ship testing and maintenance process. After following the test and maintenance plan for a long time, the model can autonomously evolve based on previous simulation experience, improving the observability, controllability and flexibility of the ship testing and maintenance process.

[0033] In addition, the output of the digital twin system needs to be designed with a user interface that facilitates human-computer interaction and an excellent parameter visualization interface so that users can combine the system to optimize human-computer collaborative decisions. At the same time, the software system should be updated and upgraded accordingly as the target ship changes.

[0034] Specifically, the data-knowledge hybrid-driven autonomous evolution method for digital twin models of ship testing and maintenance processes in this embodiment of the invention, such as... Figure 1 As shown, this method can be roughly divided into three parts: data acquisition, building a digital twin model, and model deployment. The data acquisition phase can be broadly categorized into two types: ship hull physical information and equipment operating parameters. The former mainly refers to the inherent physical properties of the ship itself, such as hull shape, load capacity, and draft. The latter mainly includes parameters related to the ship's operating status, such as engine operating temperature and full-load speed. When collecting information, it is essential to first clarify the type of data to be collected, the collection frequency, and the collection accuracy. The parameters to be collected are often directly related to user needs and ship type, while the sampling frequency and accuracy are influenced by the application scenario. Generally speaking, general types of ships do not have special requirements for sampling accuracy and frequency because the manufacturing process of high-precision, high-frequency sensors is complex and costly. Of course, for vessels engaged in special operations, high-precision, high-frequency sensors should still be used to ensure the reliability and real-time nature of the information obtained. The construction of a digital twin model comprises two parts: physical model building and statistical model building. Physical model building involves simulating the actual environment of ship testing and maintenance with the help of 3D modeling software (such as Unity). The statistical model, through intelligent algorithms such as machine learning, constructs a mathematical model to predict the operational status of the system. Combined with the constructed logical reasoning system and deep reinforcement learning model, it predicts and optimizes the effectiveness of ship testing and maintenance. After deployment, with continuous data input, the model can autonomously evolve by constantly updating its parameters in real time, enabling it to function normally even under drastic changes in environmental parameters. The autonomous evolution capability of the digital twin model enhances the method's ability to cope with extreme weather conditions such as cold waves and typhoons.

[0035] Figure 3This diagram illustrates the data flow. The data sources for the method described in this invention mainly include two parts: real-world parameters collected by sensors and virtual environment parameters generated by a digital twin model. This information is ultimately collected by a data acquisition card and used to create a dataset, which is then input into the data processing terminal. In addition to simple data organization, the data processing terminal performs preprocessing such as dimensionality reduction on the dataset to ensure that the final dataset sent to the statistical model is directly usable.

[0036] Figure 4 This is a schematic diagram of a digital twin model. The digital twin model achieves a mapping between real and virtual spaces. As shown in the diagram, through 3D modeling technology and data acquisition, a ship testing and maintenance scenario is constructed in the virtual space. Through program computation, process parameters are fed back, providing a reference for optimizing ship testing and maintenance plans in the real space. Furthermore, the digital twin model integrates a logical reasoning system based on an expert knowledge base and a deep reinforcement learning model oriented towards maintenance decision-making, forming a data- and knowledge-driven intelligent kernel. This kernel enables the model not only to perform simulations but also to autonomously analyze and make decisions based on real-time data and domain knowledge. It evaluates the long-term effects of different maintenance strategies in the simulation environment and outputs optimized action recommendations, thereby driving the entire system to achieve self-improvement and autonomous evolution through continuous interaction.

[0037] Figure 5 This diagram illustrates the autonomous evolution process of the data-knowledge hybrid driven module. As ship environmental requirements evolve and related technologies advance, knowledge items and data samples related to ship testing and maintenance can be automatically imported into the module. This alters the inference rules of the expert system and the weighting coefficients of machine learning tools, achieving a dual-dimensional update of knowledge and data. The updated model is then imported into a digital twin interface for user interaction and real-time observation of ship dynamics.

[0038] Figure 6 The diagram shows the model deployment. The deployment of this model mainly includes three parts: the ship-side, the user-side, and the autonomous evolution module. The ship-side mainly includes the deployment of sensors; the user-side includes the deployment of the digital twin model and the human-computer interaction module; and the autonomous evolution module mainly includes the deployment of the data feedback module to facilitate system updates and iterations. During the deployment of these modules, the deployment method needs to be appropriately adjusted according to the characteristics of the ship type, such as specifying the sensor installation locations for different ship types and updating the corresponding 3D models for specific ship types.

[0039] In summary, this invention relates to a data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes. Addressing the challenges of dynamic complexity and difficulty in real-time observation and control during ship testing and maintenance, this method constructs a digital twin model of ship testing and maintenance, deploys sensors in key components such as generator sets and control equipment to collect equipment status data and operational information in real time, and further constructs a time-sensitive network to ensure real-time and reliable data transmission throughout the entire ship testing and maintenance process. Based on the collected real-time data and virtual environment parameters, the digital twin model is driven to perform high-fidelity virtual simulation of the actual ship testing and maintenance process, achieving a bidirectional dynamic mapping between the physical entity and the digital model. Through this mapping, the system can perceive the state changes of the physical system during ship testing and maintenance in real time, and predict and evaluate the health status and operational trends of equipment through a logical reasoning system based on an expert knowledge base. This is then combined with a deep reinforcement learning model for maintenance decision-making to quickly respond and output optimization strategies, driving the model to continuously evolve autonomously through interaction. This invention achieves accurate modeling, real-time data fusion, and dynamic autonomous optimization of the ship testing and maintenance process, significantly improving the observability, controllability, and execution flexibility of the process.

[0040] It should be noted that the steps shown in the above process or in the flowchart of the accompanying figures can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0041] Combination Figure 1 The data-knowledge hybrid-driven automated evolution method for ship testing and maintenance processes described in this embodiment of the invention can be implemented by a computer device. Figure 7 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Figure 7 As shown, the device may include a processor 301 and a memory 302 storing computer program instructions.

[0042] Specifically, the processor 301 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of the present invention.

[0043] Memory 302 may include a large-capacity memory for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 302 may include removable or non-removable (or fixed) media. Where appropriate, memory 302 may be internal or external to a data processing device. In a particular embodiment, memory 302 is non-volatile memory. In a particular embodiment, memory 302 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random Access Memory (FPMDRAM), Extended Data Out Dynamic Random Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0044] The memory 302 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible computer program instructions executed by the processor 301.

[0045] The processor 301 reads and executes computer program instructions stored in the memory 302 to implement any of the data-knowledge hybrid-driven automated evolution methods for ship testing and maintenance processes in the above embodiments.

[0046] In some embodiments, the computer device may further include a communication interface 303 and a bus 300. For example, Figure 7 As shown, the processor 301, memory 302, and communication interface 303 are connected through bus 300 and complete communication with each other.

[0047] The communication interface 303 is used to enable communication between the various modules, devices, units, and / or equipment in the embodiments of the present invention. The communication interface 303 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0048] Bus 300 includes hardware, software, or both, that couples components of a computer device together. Bus 300 includes, but is not limited to, at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. For example, and not as a limitation, bus 300 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 300 may include one or more buses. Although specific buses are described and illustrated in the embodiments of the present invention, the present invention is contemplated by any suitable bus or interconnect.

[0049] This computer device can execute the data-knowledge hybrid-driven automated evolution method for ship testing and maintenance processes as described in this embodiment of the invention, thereby achieving a combination of... Figure 1 The described data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes.

[0050] Furthermore, in conjunction with the data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes described in the above embodiments, this invention can be implemented using a computer-readable storage medium. This computer-readable storage medium stores computer program instructions; when executed by a processor, these computer program instructions implement any of the data-knowledge hybrid-driven autonomous evolution methods for ship testing and maintenance processes described in the above embodiments.

[0051] It should be noted that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification. In addition, depending on the implementation needs, the various steps / components described in this invention can be broken down into more steps / components, or two or more steps / components or parts of steps / components can be combined into new steps / components to achieve the purpose of this invention.

[0052] It will be readily understood by those skilled in the art that the above-described embodiments merely illustrate several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A data-knowledge hybrid-driven, autonomous evolution method for ship testing and maintenance processes, characterized in that, The method includes: S1. Collect real-time data on the operating status of various ship equipment; S2. Collect relevant literature and industry standards on ship testing and maintenance, establish an expert knowledge base, and construct a logical reasoning system based on the physical characteristics-ship status related knowledge and causal logic, as well as a deep reinforcement learning model for maintenance decision-making. S3. Scenario building is carried out through digital twin technology to construct a digital twin model of the ship testing and maintenance process. Based on the collected real-time data and virtual environment parameters, the real parameters are simulated in the virtual scene to conduct virtual simulation of the ship testing and maintenance process. Combined with the constructed logical reasoning system and deep reinforcement learning model, the ship testing and maintenance effect is predicted and the decision is optimized. S4. By deploying digital twin models, logical reasoning systems, and deep reinforcement learning models, the ship testing and maintenance process is rehearsed and evaluated to optimize ship testing and maintenance plans.

2. The data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes according to claim 1, characterized in that, Step S1 includes: Determine the information items to be collected, the collection accuracy, and the sampling frequency; Select the appropriate sensors for installation, and centralize the data at the data acquisition terminal for data aggregation and preprocessing.

3. The data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes according to claim 1, characterized in that, The collected real-time data information includes real-time status data and monitoring information generated during ship testing and maintenance, including at least temperature information, operating noise, vibration amplitude, main engine status, fuel consumption and emissions, and load and draft.

4. The data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes according to claim 1, characterized in that, Step S2 includes: Collect relevant literature and industry standards on ship testing and maintenance. The literature entries should include at least the fault judgment threshold entries and logical relationships of commonly used equipment. Commonly used equipment should include at least ship power equipment, navigation equipment and communication equipment. The collected literature and industry standards related to ship testing and maintenance are organized and integrated, expert knowledge is merged and summarized, and an expert knowledge base and knowledge representation form are selected to systematically model and describe the acquired knowledge, and a logical reasoning system based on the expert knowledge base is constructed. The ship testing and maintenance environment is modeled as a reinforcement learning environment, and a deep reinforcement learning model is constructed for maintenance decision-making.

5. The data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes according to claim 4, characterized in that, Using the web ontology language OWL as the modeling language, a unified description of the expert knowledge base is achieved. By leveraging the functions and features of Protégé and OWL, the concept layer, category layer, attribute layer, and instance layer of the expert knowledge base architecture are designed.

6. The data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes according to claim 1, characterized in that, A digital twin model of the ship testing and maintenance process is constructed using a parallel approach of physical modeling and statistical modeling. This digital twin model includes: Physical model: Digital simulation of the actual environment for ship testing and maintenance using 3D modeling software; The statistical model combines virtual parameters from the physical model with actual transmission parameters from the sensors to perform statistical feature analysis, making relevant result predictions and plan optimizations; the statistical model is a deep learning model.

7. The data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes according to claim 1, characterized in that, The decision-making process is based on a logical reasoning system and a deep reinforcement learning model. This process is driven by a data-knowledge hybrid approach and is applied to ship testing and maintenance.

8. The data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes according to claim 7, characterized in that, The logical reasoning system performs autonomous evolution at the knowledge level based on the completion status of the current task and newly published online literature. At the same time, it adds the newly added multidimensional feature data collected by the ship when performing new tasks to the state space data of the deep reinforcement learning model, so that the data-driven autonomous evolution at the lower level can be successfully carried out.

9. A computer device, characterized in that, include: A processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions which, when executed by the processor, implement the steps of the data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, It stores programs or instructions that, when executed by a processor, implement the steps of the data-knowledge hybrid-driven autonomous evolution method for ship testing and maintenance processes as described in any one of claims 1 to 8.

Images