Operation and maintenance method, device and equipment for ship electric propulsion system and storage medium

Abstract

The invention relates to an operation and maintenance method, device and equipment for a ship electric propulsion system and a storage medium, and belongs to the technical field of ship operation and maintaining.The operation and maintenance method for the ship electric propulsion system comprises the steps that multi-modal operation data of the ship electric propulsion system are obtained, a multi-modal data sensing large model is adopted to conduct feature extraction on the multi-modal operation data, and a multi-modal data sensing model is adopted to conduct feature extraction on the multi-modal operation data; obtaining multi-modal characteristic data of the multi-modal operation data; carrying out feature fusion on the multi-modal feature data by adopting a cross-modal cognitive large model to obtain semantic information of the multi-modal operation data; and determining an operation state of the ship electric propulsion system based on the semantic information, and determining an operation and maintenance strategy of the ship electric propulsion system based on the operation state. According to the method, mass multi-modal heterogeneous data of the ship electric propulsion system can be rapidly processed, and the operation and maintenance efficiency of the ship electric propulsion system is improved.

Description

Technical Field

[0001] The present invention relates to the field of ship operation and maintenance technology, and in particular to a ship electric propulsion system operation and maintenance method, device, equipment and storage medium. Background Art

[0002] All kinds of modern ships need to operate and maintain the equipment and loads of the electric propulsion system. The operation and maintenance of the electric propulsion system refers to the operation and maintenance personnel completing equipment status prediction, fault repair, resource organization and other equipment operation and maintenance work by monitoring the operating status, fault conditions, resource utilization and other data information of each power equipment.

[0003] In the prior art, the operation and maintenance of ship electric propulsion systems are all carried out by manually detecting the system status information or fault information. When the system alarms, the system fault status is manually determined, and a maintenance strategy is given based on experience. When the system works normally, the system is manually inspected. Due to the large number and variety of equipment in the ship's electric propulsion system, the data related to the equipment is multi-source, heterogeneous and massive. The operation and maintenance personnel are unable to accurately check such a large amount of complex data, resulting in delays or inaccuracies in the monitoring of the system equipment status, the identification and processing of faults, and poor operation and maintenance effects on the ship's electric propulsion system.

[0004] It can be seen that the existing technology has the problem of poor operation and maintenance effect when operating and maintaining the ship's electric propulsion system. Summary of the invention

[0005] In view of this, it is necessary to provide a ship electric propulsion system operation and maintenance method, device, equipment and storage medium to solve the problem of poor operation and maintenance effect when operating and maintaining the ship electric propulsion system in the prior art.

[0006] In order to solve the above problems, the present invention provides a ship electric propulsion system operation and maintenance method, comprising: Acquire the multimodal operation data of the ship's electric propulsion system, use the multimodal data perception large model to extract features from the multimodal operation data, and obtain multimodal feature data of the multimodal operation data; A cross-modal cognitive big model is used to fuse multimodal feature data to obtain semantic information of multimodal operation data; The operating status of the ship's electric propulsion system is determined based on the semantic information, and the operation and maintenance strategy of the ship's electric propulsion system is determined based on the operating status.

[0007] In a possible implementation, the multimodal operation data includes equipment operation status data, equipment resource utilization data, and historical fault data of the ship's electric propulsion system.

[0008] In a possible implementation, a multimodal data perception large model is used to extract features from multimodal operation data to obtain multimodal feature data of the multimodal operation data, including: The multimodal data perception big model is used to analyze the multimodal operation data based on multi-source heterogeneous data perception technology and multi-source heterogeneous data analysis technology to obtain the candidate data features of each mode of operation data; The target data features among the candidate data features are determined based on the operation and maintenance requirements of the ship electric propulsion system, and the feature vectors of each modal operation data are determined based on the target data features of each modal operation data.

[0009] In a possible implementation, a cross-modal cognitive macro model is used to perform feature fusion on multi-modal feature data to obtain semantic information of multi-modal operation data, including: The cross-modal cognitive big model is used to concatenate the feature vectors based on a variety of reasoning and decision-making techniques to obtain the target feature vector of the multi-modal operation data. Perform semantic recognition on the target feature vector to obtain the semantic information of multimodal operation data.

[0010] In a possible implementation, determining the operating state of the ship electric propulsion system based on the semantic information, and determining the operation and maintenance strategy of the ship electric propulsion system based on the operating state includes: When it is determined based on semantic information that a fault occurs in the ship's electric propulsion system, a maintenance strategy for the fault is determined based on historical maintenance strategies corresponding to the fault type.

[0011] In a possible implementation, determining the operating state of the ship electric propulsion system based on the semantic information, and determining the operation and maintenance strategy of the ship electric propulsion system based on the operating state includes: When it is determined based on the semantic information that the ship electric propulsion system operates normally, an operation monitoring strategy of the ship electric propulsion system is determined based on the operation status of the ship electric propulsion system.

[0012] In a possible implementation, when it is determined based on the semantic information that the ship electric propulsion system is operating normally, the method further includes: The state of the ship's electric propulsion system is predicted based on its operating status and semantic information, and the operation and maintenance strategy of the ship's electric propulsion system is determined based on the state prediction results.

[0013] The present invention also provides a ship electric propulsion system operation and maintenance device, comprising: A feature acquisition module is used to acquire multimodal operation data of a ship electric propulsion system, and extract features of the multimodal operation data using a multimodal data perception large model to obtain multimodal feature data of the multimodal operation data; The feature fusion module is used to fuse the multimodal feature data using a cross-modal cognitive model to obtain the semantic information of the multimodal operation data; The strategy determination module is used to determine the operating status of the ship's electric propulsion system based on semantic information, and to determine the operation and maintenance strategy of the ship's electric propulsion system based on the operating status.

[0014] The present invention also provides an electronic device, comprising a memory and a processor, wherein: Memory, used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the ship electric propulsion system operation and maintenance method of any of the above embodiments.

[0015] The present invention also provides a computer-readable storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the ship electric propulsion system operation and maintenance method of any of the above-mentioned embodiments.

[0016] The beneficial effects of the present invention are as follows: the ship electric propulsion system operation and maintenance method provided by the present invention extracts features from the multimodal operation data of the ship electric propulsion system through a multimodal data perception big model, and uses a cross-modal cognitive big model to perform feature fusion on the extracted feature data, thereby obtaining the semantic information of the multimodal operation data of the ship electric propulsion system, and determining the operation state of the ship electric propulsion system based on the semantic information, and determining the operation and maintenance strategy of the ship electric propulsion system based on the operation state. Through the multimodal perception big model and the cross-modal cognitive big model, the massive multimodal heterogeneous data of the ship electric propulsion system can be quickly processed, and the operation state of the ship electric propulsion system can be accurately identified. If a fault occurs in the ship electric propulsion system, a fault handling solution can be given in time, greatly improving the operation and maintenance efficiency of the ship electric propulsion system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic diagram of a process flow of a ship electric propulsion system operation and maintenance method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a flow chart of a feature vector extraction method provided by an embodiment of the present invention; Figure 3 A schematic diagram of a flow chart of a feature fusion method provided in an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a ship electric propulsion system operation and maintenance device provided by an embodiment of the present invention; Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of the present invention and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0020] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] A specific embodiment of the present invention, as Figure 1 As shown, a ship electric propulsion system operation and maintenance method is disclosed, comprising: S101, acquiring multimodal operation data of a ship electric propulsion system, and extracting features of the multimodal operation data using a multimodal data perception large model to obtain multimodal feature data of the multimodal operation data; S102, using a cross-modal cognitive large model to perform feature fusion on multi-modal feature data to obtain semantic information of the multi-modal operation data; S103, determining the operating status of the ship electric propulsion system based on the semantic information, and determining an operation and maintenance strategy of the ship electric propulsion system based on the operating status.

[0022] In an embodiment of the present invention, a ship electric propulsion system is a power combination mode for ships. By using a gas turbine or a diesel generator to generate three-phase alternating current to drive the motor to rotate the propeller or water jet propulsion, the ship electric propulsion system involves much more equipment than the traditional fuel propulsion system, and the operation data of each device in the ship electric propulsion system is multi-source, massive, and heterogeneous. Therefore, the operation and maintenance of the operation status of the equipment of the ship electric propulsion system is very complicated and cannot be simply achieved through manual monitoring. Multimodal operation data is the operation data of each device in the ship electric propulsion system, which contains complex types and huge quantities, and can reflect whether the ship electric propulsion system is operating normally. The multimodal data perception big model is a neural network model that can perceive and analyze multimodal data, such as a convolutional neural network model, a recurrent neural network model, a deep learning neural network model, etc. The multimodal data perception big model can extract features from the multimodal operation data of the ship electric propulsion system, and then obtain multimodal feature data of the multimodal operation data of the ship electric propulsion system.

[0023] Furthermore, a cross-modal cognitive big model is used to perform feature fusion on multimodal feature data to obtain semantic information of multimodal operation data. The cross-modal cognitive big model is also a neural network model, which is similar to the multimodal data perception big model, except that the function of the cross-modal cognitive big model is to perform feature fusion on multimodal feature data and analyze the semantic information of the multimodal operation data after feature fusion. The semantic information is used to represent the operating status of the ship's electric propulsion system, including the operating status of each device. By analyzing the operating status of the ship's electric propulsion system, it can be determined whether each device has a fault and provide a reasonable operation and maintenance method.

[0024] The ship electric propulsion system operation and maintenance method provided by the present invention extracts features from the multimodal operation data of the ship electric propulsion system through a multimodal data perception big model, and uses a cross-modal cognitive big model to perform feature fusion on the extracted feature data, thereby obtaining the semantic information of the multimodal operation data of the ship electric propulsion system, and determining the operation state of the ship electric propulsion system based on the semantic information, and determining the operation and maintenance strategy of the ship electric propulsion system based on the operation state. Through the multimodal perception big model and the cross-modal cognitive big model, the massive multimodal heterogeneous data of the ship electric propulsion system can be quickly processed, and the operation state of the ship electric propulsion system can be accurately identified. If the ship electric propulsion system fails, a fault handling solution can be given in time, greatly improving the operation and maintenance efficiency of the ship electric propulsion system.

[0025] As a possible implementation manner of the present invention, in this implementation manner, the multimodal operation data includes equipment operation status data, equipment resource utilization data, and historical fault data of the ship electric propulsion system.

[0026] In an embodiment of the present invention, the multimodal operation data of a ship's electric propulsion system includes operation status data of each device of the ship's electric propulsion system, device resource utilization data, and historical fault data, wherein the operation status data of each device includes but is not limited to the device's operation parameter information, fault code information, alarm information, etc., the device resource utilization data includes but is not limited to the resource occupancy of a single device, the usage of spare equipment, etc., the historical fault data includes but is not limited to the fault types, fault causes, fault handling solutions, etc. that have occurred in the ship's electric propulsion system, wherein the multimodal operation data includes but is not limited to audio data, image data, text data, sensor data, etc.

[0027] As a possible implementation mode of the present invention, in this implementation mode, Figure 2 As shown, a multimodal data perception large model is used to extract features from the multimodal operation data to obtain multimodal feature data of the multimodal operation data, including: S201, using a multimodal data perception large model to analyze the multimodal operation data based on multi-source heterogeneous data perception technology and multi-source heterogeneous data analysis technology to obtain candidate data features of each modal operation data; S202, determining target data features among candidate data features based on operation and maintenance requirements of the ship electric propulsion system, and determining feature vectors of each modal operation data based on the target data features of each modal operation data.

[0028] In an embodiment of the present invention, the multimodal data perception big model is constructed based on multi-source heterogeneous data perception technology and multi-source heterogeneous data analysis technology. The multimodal data perception big model can be trained by obtaining historical fault data, historical fault business processing data, equipment historical status data, equipment use, damage, remaining status and other data of the ship electric propulsion system as the training input of the multimodal data perception big model. The trained multimodal data perception big model can perform preliminary independent analysis and processing on each modal operation data of the ship electric propulsion system, and extract the key features of each modality. Specifically, the multimodal data perception big model is used to analyze the multimodal operation data based on the multi-source heterogeneous data perception technology and the multi-source heterogeneous data analysis technology, and extract the candidate data features of each modal operation data. The candidate data features are all the features of the modal operation data. Since the multimodal operation data is massive data, its candidate data features are also massive, and the candidate data features need to be screened. Specifically, the candidate data features can be screened according to the preset operation and maintenance requirements of the ship electric propulsion system to obtain the target data features. Specifically, the operation and maintenance requirements of the ship's electric propulsion system can be determined based on actual conditions, such as the operating power of the equipment in the ship, the resource usage of each device, the urgency of each device's fault handling, the importance of each device's status monitoring, etc. The candidate data features are screened through pre-set operation and maintenance requirements to obtain target data features that can meet the preset operation and maintenance requirements.

[0029] The embodiment of the present invention screens the data features of the multimodal operation data according to the preset operation and maintenance requirements of the ship electric propulsion system, ensures the accuracy of the target data features, and identifies the model, and provides an operation and maintenance strategy that meets the operation and maintenance requirements.

[0030] As a possible implementation mode of the present invention, in this implementation mode, Figure 3 As shown in the figure, a cross-modal cognitive model is used to fuse multimodal feature data to obtain semantic information of multimodal operation data, including: S301, using a cross-modal cognitive big model to perform vector concatenation on each feature vector based on multiple reasoning and decision-making technologies to obtain a target feature vector of the multi-modal operation data; S302, performing semantic recognition on the target feature vector to obtain semantic information of the multimodal operation data.

[0031] In an embodiment of the present invention, a cross-modal cognitive big model is constructed based on a variety of reasoning and decision-making technologies, such as logical reasoning, uncertainty reasoning, and intelligent decision-making reasoning technologies. The cross-modal cognitive big model can achieve comprehensive integration of all modal information in a unified semantic space, and conduct all-round understanding, reasoning and decision-making, and semantic generation of the operation information of each modality. Specifically, a cross-modal cognitive big model is used to splice the feature vectors obtained in the above-mentioned embodiments based on a variety of reasoning and decision-making technologies to obtain the target feature vector of the multi-modal operation data. The specific vector splicing method can be a simple feature-level fusion, or a decision-level fusion, a hybrid-level fusion, a model-level fusion, etc. After the feature fusion of the multi-modal operation data is realized, the target feature vector is semantically identified to obtain the semantic information of the multi-modal operation data.

[0032] The embodiment of the present invention obtains reliable semantic information by fusing and identifying multimodal feature vectors of multimodal operation data, which facilitates the determination of subsequent operation and maintenance strategies.

[0033] As a possible implementation of the present invention, in this implementation, the operation state of the ship electric propulsion system is determined based on the semantic information, and the operation and maintenance strategy of the ship electric propulsion system is determined based on the operation state, including: When it is determined based on semantic information that a fault occurs in the ship's electric propulsion system, a maintenance strategy for the fault is determined based on historical maintenance strategies corresponding to the fault type.

[0034] In an embodiment of the present invention, when it is determined based on semantic information that a fault occurs in the ship's electric propulsion system, the historical fault data of the ship's electric propulsion system is queried based on the fault type of the fault that occurs, the fault cause and fault handling method of similar types of faults are determined, and a reasonable fault repair strategy is given.

[0035] Further, when it is determined based on the semantic information that the ship's electric propulsion system is operating normally, an operation monitoring strategy for the ship's electric propulsion system is determined based on the operating state of the ship's electric propulsion system.

[0036] In an embodiment of the present invention, when it is determined based on semantic information that the ship's electric propulsion system is operating normally, it is necessary to monitor the operation of the ship's electric propulsion system in real time. Specifically, a reasonable operation monitoring strategy can be given according to the current operating status of the ship's electric propulsion system. For example, the monitoring importance of each device can be determined according to the operating status of each device in the ship's electric propulsion system.

[0037] Further, when it is determined based on the semantic information that the ship electric propulsion system operates normally, the ship electric propulsion system operation and maintenance method further includes: The state of the ship's electric propulsion system is predicted based on its operating status and semantic information, and the operation and maintenance strategy of the ship's electric propulsion system is determined based on the state prediction results.

[0038] In an embodiment of the present invention, when it is determined based on semantic information that the ship's electric propulsion system is operating normally, in order to maintain the operation and maintenance of the ship's electric propulsion system, it is necessary to predict the state of the ship's electric propulsion system in combination with the current operating state and semantic information of the ship's electric propulsion system, and give an operation and maintenance strategy based on the prediction result. For example, when it is predicted that a certain device in the ship's electric system may have a certain fault, the operation and maintenance personnel can be arranged to conduct an on-site inspection. Or if it is predicted that a certain part of a certain device in the ship's electric propulsion system may need to be replaced, the equipment warehouse can be dispatched to prepare spare parts in time to improve the efficiency of operation and maintenance.

[0039] In order to better implement the ship electric propulsion system operation and maintenance method in the embodiment of the present invention, based on the ship electric propulsion system operation and maintenance method, correspondingly, Figure 4 As shown, the embodiment of the present invention further provides a ship electric propulsion system operation and maintenance device, the ship electric propulsion system operation and maintenance device 400 includes: The feature acquisition module 401 is used to acquire the multimodal operation data of the ship electric propulsion system, and extract the features of the multimodal operation data using a multimodal data perception large model to obtain multimodal feature data of the multimodal operation data; A feature fusion module 402 is used to perform feature fusion on multimodal feature data using a cross-modal cognitive macro model to obtain semantic information of multimodal operation data; The strategy determination module 403 is used to determine the operating status of the ship's electric propulsion system based on the semantic information, and determine the operation and maintenance strategy of the ship's electric propulsion system based on the operating status.

[0040] The ship electric propulsion system operation and maintenance device 400 provided in the above embodiment can implement the technical solution described in the above ship electric propulsion system operation and maintenance method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above ship electric propulsion system operation and maintenance method embodiment, which will not be repeated here.

[0041] The ship electric propulsion system operation and maintenance device provided by the present invention extracts features from the multimodal operation data of the ship electric propulsion system through a multimodal data perception big model, and uses a cross-modal cognitive big model to perform feature fusion on the extracted feature data, thereby obtaining the semantic information of the multimodal operation data of the ship electric propulsion system, and determines the operation state of the ship electric propulsion system based on the semantic information, and determines the operation and maintenance strategy of the ship electric propulsion system based on the operation state. Through the multimodal perception big model and the cross-modal cognitive big model, the massive multimodal heterogeneous data of the ship electric propulsion system can be quickly processed, and the operation state of the ship electric propulsion system can be accurately identified. If the ship electric propulsion system fails, a fault handling solution can be given in time, greatly improving the operation and maintenance efficiency of the ship electric propulsion system.

[0042] like Figure 5 As shown, the present invention also provides an electronic device 500. The electronic device 500 includes a processor 501, a memory 502 and a display 503. Figure 5 Only some components of the electronic device 500 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0043] In some embodiments, the processor 501 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 502, such as the ship electric propulsion system operation and maintenance method of the present invention.

[0044] In some embodiments, the processor 501 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 501 may be local or remote. In some embodiments, the processor 501 may be implemented in a cloud platform. In some embodiments, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0045] In some embodiments, the memory 502 may be an internal storage unit of the electronic device 500, such as a hard disk or memory of the electronic device 500. In other embodiments, the memory 502 may also be an external storage device of the electronic device 500, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 500.

[0046] Furthermore, the memory 502 may include both an internal storage unit of the electronic device 500 and an external storage device. The memory 502 is used to store application software installed in the electronic device 500 and various data.

[0047] In some embodiments, the display 503 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 503 is used to display information of the electronic device 500 and to display a visual user interface. The components 501-503 of the electronic device 500 communicate with each other through a system bus.

[0048] In some embodiments, when the processor 501 executes the ship electric propulsion system operation and maintenance program in the memory 502, the following steps may be implemented: Acquire the multimodal operation data of the ship's electric propulsion system, use the multimodal data perception large model to extract features from the multimodal operation data, and obtain multimodal feature data of the multimodal operation data; A cross-modal cognitive big model is used to fuse multimodal feature data to obtain semantic information of multimodal operation data; The operating status of the ship's electric propulsion system is determined based on the semantic information, and the operation and maintenance strategy of the ship's electric propulsion system is determined based on the operating status.

[0049] It should be understood that: when the processor 501 executes the ship electric propulsion system operation and maintenance program in the memory 502, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0050] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 500 mentioned, and the electronic device 500 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 500 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0051] Correspondingly, an embodiment of the present invention also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, it can implement the steps or functions in the ship electric propulsion system operation and maintenance method provided by the above-mentioned method embodiments.

[0052] Those skilled in the art can understand that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0053] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A ship electric propulsion system operation and maintenance method, characterized in that: include: Acquire multimodal operation data of the ship electric propulsion system, and use a multimodal data perception large model to perform feature extraction on the multimodal operation data to obtain multimodal feature data of the multimodal operation data; Using a cross-modal cognitive large model to perform feature fusion on the multimodal feature data to obtain semantic information of the multimodal operation data; An operating state of the ship electric propulsion system is determined based on the semantic information, and an operation and maintenance strategy of the ship electric propulsion system is determined based on the operating state.

2. The ship electric propulsion system operation and maintenance method according to claim 1, characterized in that: The multimodal operation data includes equipment operation status data, equipment resource utilization data, and historical fault data of the ship electric propulsion system.

3. The ship electric propulsion system operation and maintenance method according to claim 1, characterized in that: The adopting of the multimodal data perception large model to extract features from the multimodal operation data to obtain multimodal feature data of the multimodal operation data includes: The multimodal data perception big model is used to analyze the multimodal operation data based on multi-source heterogeneous data perception technology and multi-source heterogeneous data analysis technology to obtain candidate data features of each modal operation data; The target data features among the candidate data features are determined based on the operation and maintenance requirements of the ship electric propulsion system, and the feature vectors of each modal operation data are determined based on the target data features of each modal operation data.

4. The ship electric propulsion system operation and maintenance method according to claim 3, characterized in that: The adopting of the cross-modal cognitive macro model to perform feature fusion on the multi-modal feature data to obtain semantic information of the multi-modal operation data includes: Using a cross-modal cognitive big model to perform vector concatenation on each of the feature vectors based on a variety of reasoning and decision-making techniques to obtain a target feature vector of the multimodal operation data; Perform semantic recognition on the target feature vector to obtain semantic information of the multimodal operation data.

5. The ship electric propulsion system operation and maintenance method according to claim 4, characterized in that: The determining the operating state of the ship electric propulsion system based on the semantic information, and determining the operation and maintenance strategy of the ship electric propulsion system based on the operating state, includes: When it is determined based on the semantic information that a fault occurs in the ship electric propulsion system, a maintenance strategy for the fault is determined based on a historical maintenance strategy corresponding to the fault type.

6. The ship electric propulsion system operation and maintenance method according to claim 5, characterized in that: The determining the operating state of the ship electric propulsion system based on the semantic information, and determining the operation and maintenance strategy of the ship electric propulsion system based on the operating state, includes: When it is determined based on the semantic information that the ship electric propulsion system operates normally, an operation monitoring strategy of the ship electric propulsion system is determined based on the operation status of the ship electric propulsion system.

7. The ship electric propulsion system operation and maintenance method according to claim 1, characterized in that: When it is determined based on the semantic information that the ship electric propulsion system operates normally, the method further includes: The state of the ship electric propulsion system is predicted based on the operating state of the ship electric propulsion system and the semantic information, and the operation and maintenance strategy of the ship electric propulsion system is determined based on the state prediction result.

8. A ship electric propulsion system operation and maintenance device, characterized in that: include: A feature acquisition module is used to acquire multimodal operation data of a ship electric propulsion system, and extract features from the multimodal operation data using a multimodal data perception large model to obtain multimodal feature data of the multimodal operation data; A feature fusion module, used to perform feature fusion on the multimodal feature data using a cross-modal cognitive macro model to obtain semantic information of the multimodal operation data; A strategy determination module is used to determine the operating status of the ship's electric propulsion system based on the semantic information, and determine the operation and maintenance strategy of the ship's electric propulsion system based on the operating status.

9. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the ship electric propulsion system operation and maintenance method described in any one of claims 1 to 7 above.

10. A computer-readable storage medium, characterized in that: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the ship electric propulsion system operation and maintenance method described in any one of claims 1 to 7 above.

Images