A ship bearing fault processing method and system based on a knowledge graph

Abstract

The application relates to the technical field of fault diagnosis, in particular to a ship bearing fault processing method and system based on a knowledge graph, which comprises the following steps: acquiring bearing application information and component association information, constructing a three-dimensional model of a ship bearing system application according to bearing entity parameters and component entity parameters, and obtaining a bearing application model. Data trends of bearing operation data and component operation data are monitored, and the operation trend data is applied to the bearing application model for model evolution, so that a bearing evolution animation is obtained. Running images of the bearing evolution animation are intercepted, image feature information is summarized, the image feature information is input into a bearing knowledge graph for feature recognition, whether the image feature information has a fault abnormality is judged, if yes, fault detail information and a fault solution scheme are determined based on the recognition result of the bearing knowledge graph and the image feature information. The application improves the reliability and operation efficiency of the ship bearing.

Description

Technical Field

[0001] This application relates to the technical field of fault diagnosis, and in particular to a method and system for handling ship bearing faults based on knowledge graphs. Background Technology

[0002] As supporting components of core equipment such as propulsion systems and generator sets, the operating condition of ship bearings directly affects the safety and economy of ship navigation. Currently, the monitoring and maintenance of ship bearings mainly relies on periodic manual inspections and experience-based judgment. This method is not only inefficient but also fails to capture subtle changes in the bearing's operation in real time, especially early signs that could lead to serious failures. With the development of ships towards larger, higher-speed, and more automated models, traditional methods are no longer sufficient to meet the needs of modern ship bearing operation and maintenance. Summary of the Invention

[0003] To address at least one of the aforementioned technical problems, this application provides a knowledge graph-based method and system for handling ship bearing failures.

[0004] Firstly, this application provides a knowledge graph-based method for handling ship bearing faults, employing the following technical solution:

[0005] Obtain bearing application information for the ship bearings and component association information associated with the ship bearings;

[0006] Based on the bearing entity parameters in the bearing application information and the component entity parameters associated with the ship bearing in the component association information, a three-dimensional model of the ship bearing system application is constructed to obtain a bearing application model corresponding to the ship bearing system application.

[0007] The data flow of bearing operation data in the bearing application information and component operation data in the component association information is monitored, and the monitored operation flow data is applied to the bearing application model to perform model evolution, resulting in bearing evolution animation.

[0008] The image of the bearing evolution animation at different time points is captured at different positions in the ship bearing system, and the image feature information in the image is summarized.

[0009] The image feature information is input into the bearing knowledge graph for feature recognition. It is determined whether there is a fault or abnormality in the image feature information. If so, the target time node of the fault or abnormality is determined based on the image feature information, and it is determined whether the target time node conforms to a preset time period. If it does, the fault details and fault solution are determined based on the recognition results of the bearing knowledge graph and the image feature information.

[0010] By employing the aforementioned technical solution, bearing application information and component association information related to ship bearings are obtained. The bearing application information includes the key parameters of the ship bearing itself, while the component association information reveals the interaction between the bearing and other components. These interconnected pieces of information form the overall cognitive framework of the ship bearing system. This lays a solid foundation for accurate analysis of ship bearing system applications, avoids model biases caused by missing or inaccurate information, and thus better reflects the actual system conditions. Based on the bearing entity parameters in the bearing application information and the entity parameters of the components associated with the ship bearing in the component association information, a three-dimensional model of the ship bearing system application is constructed, resulting in a bearing application model. The bearing entity parameters determine the basic shape and performance characteristics of the bearing, while the component entity parameters affect the position and function of the associated components within the system. Combining these two to construct a three-dimensional model provides a visual representation of the spatial structure of the ship bearing system and the relative positional relationships between its components. Data flow monitoring is performed on the bearing operation data in the bearing application information and the component operation data in the component association information. The monitored operation flow data is then applied to the bearing application model to drive model evolution, resulting in a bearing evolution animation. Bearing operation data reflects the actual working status of the bearing during operation, while component operation data reflects the operation of related components. The process involves capturing operational images of different nodes in the marine bearing system at different time points from the bearing evolution animation, and summarizing the image feature information from these images. The bearing evolution animation records the dynamic changes of the system over time, and the operational images at different time points and locations reflect the system's operational status at different times and locations from multiple dimensions. Summarizing the image feature information allows for the integration and analysis of scattered image data. The image feature information is then input into the bearing knowledge graph for feature recognition to determine if any faults or anomalies exist. If so, the target time point of the fault or anomaly is determined based on the image feature information, and it is determined whether the target time point conforms to a preset time period. If it does, the fault details and solutions are determined based on the recognition results of the bearing knowledge graph and the image feature information. The bearing knowledge graph contains a wealth of knowledge and experience about marine bearing systems. Inputting image feature information into it allows for accurate identification using its powerful knowledge base. Determining the target time point of the fault and whether it conforms to a preset time period helps to accurately pinpoint the time range of the fault occurrence. The final determination of fault details and solutions can quickly and effectively resolve faults in the operation of ship bearing systems, reduce downtime, improve the reliability and operating efficiency of ship bearings, and ensure the normal navigation of ships.

[0011] In one possible implementation, the step of constructing a three-dimensional model of the ship bearing system application based on the bearing entity parameters in the bearing application information and the component entity parameters associated with the ship bearing in the component association information, to obtain a bearing application model corresponding to the ship bearing system application, includes:

[0012] The bearing feature points of the ship bearing and the component feature points of the associated components are determined based on the bearing entity parameters and the component entity parameters.

[0013] The component feature points and the bearing feature points are respectively converted into component grid objects corresponding to the component feature points and bearing grid object groups corresponding to the bearing feature points;

[0014] The component grid object is converted into component connection space data, and the grid function is used to obtain the source of the widest elevation value of all planar positions in the bearing grid object group;

[0015] The widest elevation value of all planar spatial locations in the bearing grid object group is recorded as the target grid in the form of integer grid data;

[0016] Based on the target grid, select the bearing object cell at the corresponding position in the bearing grid object group to obtain virtual bearing data composed of one or more bearing spatial elevation grids;

[0017] The virtual bearing data is converted into bearing duty data. Based on each bearing component object type in the bearing grid object group, the bearing space data of the bearing component is generated in the virtual bearing data, taking the component connection space data and the bearing duty data as the basis and the distribution of the bearing components corresponding to the bearing component object type in the target grid as the condition.

[0018] By summarizing bearing spatial data from different perspectives and dimensions, a three-dimensional bearing model is constructed to obtain a bearing application model corresponding to the application of the ship bearing system.

[0019] In one possible implementation, the monitoring of data flow for the bearing operation data in the bearing application information and the component operation data in the component association information includes:

[0020] Historical fault information of ship bearings within a historical period is collected, and features are extracted from the historical fault information to obtain time dimension features and corresponding ship bearing features and component operation features. The time dimension features include a first time period before the ship bearing failure event, a second time period during the event, and a third time period after the event.

[0021] The ship bearing characteristics and component operation characteristics during the first time period and the second time period are respectively arranged in a positive time sequence feature evolution arrangement to obtain a first feature set corresponding to the first time period and a second feature set corresponding to the second time period.

[0022] The ship bearing rating and component operation characteristics during the third time period are arranged in reverse chronological order to obtain a third feature set corresponding to the third time period.

[0023] The bearing operation data and the component operation data are subjected to feature extraction according to a preset time period to obtain real-time feature sets for different time periods. Each real-time feature set contains real-time bearing operation features and real-time component operation features.

[0024] The features in the real-time feature set are matched with the features in the second feature set to determine whether there is a match between the real-time bearing operation feature and the ship bearing feature and / or the real-time component operation feature and the component operation feature. If not, the features in the real-time feature set are matched with the features in the first feature set and the third feature set to determine whether there is a match between the features in the first feature set and the features in the real-time feature set and / or the features in the third feature set. Based on the feature consistency results, feature evolution extraction is performed from the features in the first feature set and / or the third feature set to obtain the ship bearing operation trajectory data.

[0025] In one possible implementation, determining whether the real-time bearing operation characteristics match the ship bearing characteristics and / or the real-time component operation characteristics match the component operation characteristics includes:

[0026] If there exists a real-time bearing operation characteristic that matches the ship bearing characteristic, but no real-time component operation characteristic matches the component operation characteristic, then the fault details and fault solutions of the ship bearing are determined based on the historical fault information, and the fault details and fault solutions are sent to the target terminal.

[0027] If there exists a real-time component operation feature that matches the component running feature and there is no real-time bearing operation feature that matches the ship bearing feature, then the abnormal time period and degree of mismatch between the real-time component operation feature and the component running feature are determined, and the abnormal time period and degree of mismatch are used as search conditions to search the historical fault information to obtain the component fault details and fault solutions, as well as the fault potential information and potential solutions of the ship bearing.

[0028] If there exists a real-time component operation characteristic that matches the component running characteristic, and a real-time bearing operation characteristic that matches the ship bearing characteristic, then based on the historical fault information, the bearing fault characteristic corresponding to the real-time component operation characteristic is determined, and it is determined whether the bearing fault characteristic is consistent with the real-time bearing operation characteristic. If so, the component running characteristic is taken as the root cause characteristic of the fault, and the fault solution corresponding to the root cause characteristic is determined based on the historical fault information. If the bearing fault characteristic is inconsistent with the real-time bearing operation characteristic, then the ship bearing characteristic is taken as the root cause characteristic of the fault, and the fault solution corresponding to the root cause characteristic is determined based on the historical fault information.

[0029] In one possible implementation, the step of extracting feature evolution data from the first feature set and / or the second feature set based on feature consistency results to obtain the operational trajectory data of the ship bearing includes:

[0030] When the feature consistency result is that the features in the first feature set are consistent with the features in the real-time feature set, the target feature position in the first feature set that is consistent with the features in the real-time feature set is determined, and the time-series features of the first feature set are selected based on the target feature position to obtain the operating direction data of the ship bearing;

[0031] When the feature consistency result is that the features in the third feature set are consistent with the features in the real-time feature set, the target feature position in the third feature set that is consistent with the features in the real-time feature set is determined, and the time-series features of the third feature set are selected based on the target feature position to obtain the operating direction data of the ship bearing.

[0032] In one possible implementation, the method further includes:

[0033] When the feature consistency result is that the features in the first feature set are consistent with the features in the real-time feature set and the features in the third feature set are consistent with the features in the real-time feature set, then the first target position in the first feature set that is consistent with the features in the real-time feature set and the second target position in the third feature set that is consistent with the features in the real-time feature set are determined respectively.

[0034] Based on the first target location and the first feature set, temporal features are selected to obtain the first directional data in the first feature set;

[0035] Based on the second target location and the third feature set, temporal features are selected to obtain the second direction data in the third feature set;

[0036] The real-time feature set is continuously monitored in real time, and subsequent feature sets are collected. The overlap rate of the subsequent feature sets with the first directional data and the second directional data is detected to obtain the overlap rate of the first directional data with different time nodes in the first directional data and the overlap rate of the second directional data with different time nodes in the second directional data.

[0037] The first direction data and the second direction data are spliced ​​together based on the first direction overlap rate and the second direction overlap rate to obtain the operating direction data of the ship bearing.

[0038] In one possible implementation, the step of inputting the image feature information into a bearing knowledge graph for feature recognition and determining whether the image feature information indicates a fault or abnormality further includes:

[0039] Acquire bearing fault images and corresponding fault details and troubleshooting steps;

[0040] A bearing knowledge graph is constructed based on the bearing fault images, fault details, and fault resolution steps.

[0041] Secondly, this application provides a knowledge graph-based ship bearing fault handling system, which adopts the following technical solution:

[0042] A knowledge graph-based ship bearing fault handling system includes:

[0043] The information acquisition module is used to acquire bearing application information of the ship bearing and component association information associated with the ship bearing;

[0044] The model building module is used to build a three-dimensional model of the ship bearing system application based on the bearing entity parameters in the bearing application information and the component entity parameters associated with the ship bearing in the component association information, so as to obtain a bearing application model corresponding to the ship bearing system application.

[0045] The model evolution module is used to monitor the data flow of bearing operation data in the bearing application information and component operation data in the component association information, and apply the monitored operation flow data to the bearing application model to perform model evolution, thereby obtaining a bearing evolution animation.

[0046] The image determination module is used to capture the running images of different position nodes in the ship bearing system at different time points in the bearing evolution animation, and summarize the image feature information in the running images;

[0047] The fault determination module is used to input the image feature information into the bearing knowledge graph for feature recognition, determine whether there is a fault or abnormality in the image feature information, and if so, determine the target time node of the fault or abnormality based on the image feature information, and determine whether the target time node conforms to a preset time period. If it does, determine the fault details and fault solution based on the recognition result of the bearing knowledge graph and the image feature information.

[0048] In one possible implementation, when the model building module constructs a three-dimensional model of the ship bearing system application based on the bearing entity parameters in the bearing application information and the component entity parameters associated with the ship bearing in the component association information, and obtains a bearing application model corresponding to the ship bearing system application, it is specifically used for:

[0049] The bearing feature points of the ship bearing and the component feature points of the associated components are determined based on the bearing entity parameters and the component entity parameters.

[0050] The component feature points and the bearing feature points are respectively converted into component grid objects corresponding to the component feature points and bearing grid object groups corresponding to the bearing feature points;

[0051] The component grid object is converted into component connection space data, and the grid function is used to obtain the source of the widest elevation value of all planar positions in the bearing grid object group;

[0052] The widest elevation value of all planar spatial locations in the bearing grid object group is recorded as the target grid in the form of integer grid data;

[0053] Based on the target grid, select the bearing object cell at the corresponding position in the bearing grid object group to obtain virtual bearing data composed of one or more bearing spatial elevation grids;

[0054] The virtual bearing data is converted into bearing duty data. Based on each bearing component object type in the bearing grid object group, the bearing space data of the bearing component is generated in the virtual bearing data, taking the component connection space data and the bearing duty data as the basis and the distribution of the bearing components corresponding to the bearing component object type in the target grid as the condition.

[0055] By summarizing bearing spatial data from different perspectives and dimensions, a three-dimensional bearing model is constructed to obtain a bearing application model corresponding to the application of the ship bearing system.

[0056] In another possible implementation, when the model evolution module monitors the data flow of bearing operation data in the bearing application information and component operation data in the component association information, it is specifically used for:

[0057] Historical fault information of ship bearings within a historical period is collected, and features are extracted from the historical fault information to obtain time dimension features and corresponding ship bearing features and component operation features. The time dimension features include a first time period before the ship bearing failure event, a second time period during the event, and a third time period after the event.

[0058] The ship bearing characteristics and component operation characteristics during the first time period and the second time period are respectively arranged in a positive time sequence feature evolution arrangement to obtain a first feature set corresponding to the first time period and a second feature set corresponding to the second time period.

[0059] The ship bearing rating and component operation characteristics during the third time period are arranged in reverse chronological order to obtain a third feature set corresponding to the third time period.

[0060] The bearing operation data and the component operation data are subjected to feature extraction according to a preset time period to obtain real-time feature sets for different time periods. Each real-time feature set contains real-time bearing operation features and real-time component operation features.

[0061] The features in the real-time feature set are matched with the features in the second feature set to determine whether there is a match between the real-time bearing operation feature and the ship bearing feature and / or the real-time component operation feature and the component operation feature. If not, the features in the real-time feature set are matched with the features in the first feature set and the third feature set to determine whether there is a match between the features in the first feature set and the features in the real-time feature set and / or the features in the third feature set. Based on the feature consistency results, feature evolution extraction is performed from the features in the first feature set and / or the third feature set to obtain the ship bearing operation trajectory data.

[0062] In another possible implementation, the model evolution module, when determining whether the real-time bearing operation characteristics match the ship bearing characteristics and / or whether the real-time component operation characteristics match the component operation characteristics, is specifically used for:

[0063] If there exists a real-time bearing operation characteristic that matches the ship bearing characteristic, but no real-time component operation characteristic matches the component operation characteristic, then the fault details and fault solutions of the ship bearing are determined based on the historical fault information, and the fault details and fault solutions are sent to the target terminal.

[0064] If there exists a real-time component operation feature that matches the component running feature and there is no real-time bearing operation feature that matches the ship bearing feature, then the abnormal time period and degree of mismatch between the real-time component operation feature and the component running feature are determined, and the abnormal time period and degree of mismatch are used as search conditions to search the historical fault information to obtain the component fault details and fault solutions, as well as the fault potential information and potential solutions of the ship bearing.

[0065] If there exists a real-time component operation characteristic that matches the component running characteristic, and a real-time bearing operation characteristic that matches the ship bearing characteristic, then based on the historical fault information, the bearing fault characteristic corresponding to the real-time component operation characteristic is determined, and it is determined whether the bearing fault characteristic is consistent with the real-time bearing operation characteristic. If so, the component running characteristic is taken as the root cause characteristic of the fault, and the fault solution corresponding to the root cause characteristic is determined based on the historical fault information. If the bearing fault characteristic is inconsistent with the real-time bearing operation characteristic, then the ship bearing characteristic is taken as the root cause characteristic of the fault, and the fault solution corresponding to the root cause characteristic is determined based on the historical fault information.

[0066] In another possible implementation, when the model evolution module extracts feature evolution data from the first feature set and / or the second feature set based on feature consistency results to obtain the operational trajectory data of the ship bearing, it is specifically used for:

[0067] When the feature consistency result is that the features in the first feature set are consistent with the features in the real-time feature set, the target feature position in the first feature set that is consistent with the features in the real-time feature set is determined, and the time-series features of the first feature set are selected based on the target feature position to obtain the operating direction data of the ship bearing;

[0068] When the feature consistency result is that the features in the third feature set are consistent with the features in the real-time feature set, the target feature position in the third feature set that is consistent with the features in the real-time feature set is determined, and the time-series features of the third feature set are selected based on the target feature position to obtain the operating direction data of the ship bearing.

[0069] In another possible implementation, the system further includes: a location determination module, a first selection module, a second selection module, an overlap rate detection module, and a data stitching module, wherein,

[0070] The location determination module is used to determine, when the feature consistency result is that the features in the first feature set are consistent with the features in the real-time feature set and the features in the third feature set are consistent with the features in the real-time feature set, respectively determine a first target location in the first feature set that is consistent with the features in the real-time feature set and a second target location in the third feature set that is consistent with the features in the real-time feature set.

[0071] The first selection module is used to select temporal features based on the first target location and the first feature set to obtain first directional data in the first feature set;

[0072] The second selection module is used to select temporal features based on the second target location and the third feature set to obtain second directional data in the third feature set;

[0073] The overlap rate detection module is used to continuously monitor the real-time feature set, collect subsequent feature sets, and perform overlap rate detection on the subsequent feature sets with the first directional data and the second directional data respectively, so as to obtain the first directional overlap rate with different time nodes in the first directional data and the second directional overlap rate with different time nodes in the second directional data.

[0074] The data stitching module is used to stitch the first direction data and the second direction data according to the first direction overlap rate and the second direction overlap rate to obtain the operating direction data of the ship bearing.

[0075] In another possible implementation, the system further includes: a fault acquisition module and a map construction module, wherein,

[0076] The fault acquisition module is used to acquire bearing fault images and corresponding fault details and fault resolution steps;

[0077] The knowledge graph construction module is used to build a bearing knowledge graph based on the bearing fault image, the fault details information, and the fault resolution steps.

[0078] Thirdly, this application provides an electronic device that adopts the following technical solution:

[0079] At least one processor;

[0080] Memory;

[0081] At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: execute a knowledge graph-based method for handling ship bearing failures as described in any of the first aspects.

[0082] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution:

[0083] A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform a knowledge graph-based method for handling ship bearing failures, as described in any of the first aspects.

[0084] In summary, this application includes at least one of the following beneficial technical effects:

[0085] By employing the aforementioned technical solution, bearing application information and component association information related to ship bearings are obtained. The bearing application information includes the key parameters of the ship bearing itself, while the component association information reveals the interaction between the bearing and other components. These interconnected pieces of information form the overall cognitive framework of the ship bearing system. This lays a solid foundation for accurate analysis of ship bearing system applications, avoids model biases caused by missing or inaccurate information, and thus better reflects the actual system conditions. Based on the bearing entity parameters in the bearing application information and the entity parameters of the components associated with the ship bearing in the component association information, a three-dimensional model of the ship bearing system application is constructed, resulting in a bearing application model. The bearing entity parameters determine the basic shape and performance characteristics of the bearing, while the component entity parameters affect the position and function of the associated components within the system. Combining these two to construct a three-dimensional model provides a visual representation of the spatial structure of the ship bearing system and the relative positional relationships between its components. Data flow monitoring is performed on the bearing operation data in the bearing application information and the component operation data in the component association information. The monitored operation flow data is then applied to the bearing application model to drive model evolution, resulting in a bearing evolution animation. Bearing operation data reflects the actual working status of the bearing during operation, while component operation data reflects the operation of related components. The process involves capturing operational images of different nodes in the marine bearing system at different time points from the bearing evolution animation, and summarizing the image feature information from these images. The bearing evolution animation records the dynamic changes of the system over time, and the operational images at different time points and locations reflect the system's operational status at different times and locations from multiple dimensions. Summarizing the image feature information allows for the integration and analysis of scattered image data. The image feature information is then input into the bearing knowledge graph for feature recognition to determine if any faults or anomalies exist. If so, the target time point of the fault or anomaly is determined based on the image feature information, and it is determined whether the target time point conforms to a preset time period. If it does, the fault details and solutions are determined based on the recognition results of the bearing knowledge graph and the image feature information. The bearing knowledge graph contains a wealth of knowledge and experience about marine bearing systems. Inputting image feature information into it allows for accurate identification using its powerful knowledge base. Determining the target time point of the fault and whether it conforms to a preset time period helps to accurately pinpoint the time range of the fault occurrence. The final determination of fault details and solutions can quickly and effectively resolve faults in the operation of ship bearing systems, reduce downtime, improve the reliability and operating efficiency of ship bearings, and ensure the normal navigation of ships. Attached Figure Description

[0086] Figure 1 This is a flowchart illustrating a knowledge graph-based method for handling ship bearing failures, as provided in an embodiment of this application.

[0087] Figure 2 This is a schematic diagram of a knowledge graph-based ship bearing fault handling system provided in an embodiment of this application.

[0088] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0089] The following is in conjunction with the appendix Figure 1-3 This application will be described in further detail.

[0090] This specific embodiment is merely an explanation of this application and is not intended to limit it. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they are within the scope of this application.

[0091] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0092] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0093] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0094] This application provides a knowledge graph-based method for handling ship bearing faults, executed by an electronic device. This electronic device can be a standalone physical electronic device, a cluster of multiple physical electronic devices, a distributed system, or a cloud electronic device providing cloud computing services. This application does not impose any limitations on this method. Figure 1 As shown, the method includes:

[0095] Step S10: Obtain the bearing application information of the ship bearing and the component association information associated with the ship bearing.

[0096] In the embodiments of this application, bearing application information refers to various relevant data and conditions used to represent the actual application scenarios of ship bearings, including bearing model specifications, installation position, working load, operating speed and other parameter information, reflecting the specific usage status of bearings during ship operation. Component association information refers to relevant data used to represent other ship components that have functional connections with and influence each other with the ship bearings. These components include shafts, gears, couplings and other components that cooperate with the bearings. Component association information covers the component model, size, connection position and their interaction relationship with the bearings.

[0097] Specifically, for the ship bearings themselves, it's necessary to collect basic information such as their model and specifications, as this determines the bearing's basic performance and applicable range. For example, different bearing models have different load capacities and speed limits. Simultaneously, the bearing's installation location information should be recorded, as the installation location affects the bearing's stress distribution and heat dissipation. Dynamic information on the bearing's working load and operating speed needs to be collected in real-time using sensors and other equipment installed on the ship to understand the bearing's actual operating status. Furthermore, obtaining information on components associated with the ship bearing is crucial. Components directly connected to the bearing or functionally interacting with it, such as shaft dimensions and materials affecting the bearing's stress distribution, and gear meshing affecting its vibration characteristics, are also essential. By collecting detailed information on these components' models, dimensions, connection methods, and their interactions with the bearing, a comprehensive understanding of the ship bearing system's operating environment and mutual influence mechanisms can be achieved.

[0098] Step S11: Based on the bearing entity parameters in the bearing application information and the component entity parameters associated with the ship bearing in the component association information, construct a three-dimensional model of the ship bearing system application to obtain the bearing application model corresponding to the ship bearing system application.

[0099] Specifically, bearing entity parameters refer to the specific values ​​or characteristics of the bearing itself that accurately describe its physical properties and performance indicators, such as the bearing's diameter, width, inner diameter, outer diameter, material, and precision grade. Component entity parameters refer to the specific values ​​or characteristics of components that functionally interact with the ship's bearings, describing their physical and performance characteristics, such as the diameter, length, and material of the shaft the bearing mates with, and the module, number of teeth, and tooth profile of gears. Three-dimensional model construction refers to the process of using computer technology to create a virtual model in three-dimensional space that accurately reflects the shape, structure, and spatial relationships of an object based on given parameters and data. A bearing application model refers to a virtual model obtained through three-dimensional model construction technology that completely and accurately presents the form, structure, positional relationships of various components, and operational characteristics of the ship's bearing system in actual applications.

[0100] In this application, the bearing feature points of the ship bearing and the component feature points of the associated components are determined based on the bearing entity parameters and component entity parameters. The component feature points and bearing feature points are respectively converted into component grid objects corresponding to the component feature points and bearing grid object groups corresponding to the bearing feature points. The component grid objects are converted into component connection space data, and the source of the widest elevation value of all planar positions in the bearing grid object group is obtained by using a grid function. The source of the widest elevation value of all planar spatial positions in the bearing grid object group is recorded as target grid in the form of integer grid data. Based on the target grid, bearing object pixels at corresponding positions in the bearing grid object group are selected to obtain virtual bearing data composed of one or more bearing spatial elevation grids. The virtual bearing data is converted into bearing occupancy data. Based on the bearing component object type in the bearing grid object group, the component connection spatial data and bearing occupancy data are used as a basis, and the distribution of bearing components corresponding to the bearing component object type in the target grid is used as a condition to generate bearing spatial data of bearing components in the virtual bearing data. The bearing spatial data from different perspective dimensions are summarized to construct a three-dimensional bearing model, resulting in a bearing application model corresponding to the application of the ship bearing system.

[0101] Step S12: Monitor the data flow of bearing operation data in bearing application information and component operation data in component association information, and apply the monitored operation flow data to the bearing application model to perform model evolution, thereby obtaining bearing evolution animation.

[0102] Specifically, various sensor devices are used to collect bearing operation data and component operation data in real time. These sensors are installed at key locations on the bearings and related components; for example, temperature sensors are installed near the bearings to measure temperature, and speed sensors are installed on the shafts to measure rotational speed. The collected data is transmitted to a data monitoring system via a network. The data monitoring system tracks the data flow in real time, recording the entire process from data generation by the sensors, through the transmission lines, to entering the data processing module, ensuring data integrity and accuracy. Then, the monitored operation data is analyzed and processed to extract key information affecting the bearing application model, such as how excessively high temperatures affect bearing material properties, and abnormal rotational speeds lead to accelerated bearing wear. Next, this key information is applied to the bearing application model, dynamically adjusting the model based on data changes. For example, if the temperature data increases, the bearing material properties are correspondingly changed in the model to simulate the bearing performance changes caused by the temperature increase; if the rotational speed data changes, the bearing rotation parameters in the model are adjusted to reflect the impact of rotational speed changes on bearing operation. Finally, using animation technology, the evolution of the model was transformed into a bearing evolution animation, which dynamically displays the state changes of the bearing system under the influence of different operating data, allowing staff to understand the system's operation more intuitively.

[0103] In this application, historical fault information of ship bearings within a historical period is collected, and features are extracted from the historical fault information to obtain time-dimensional features and corresponding ship bearing features and component operation features. The time-dimensional features include a first time period before the ship bearing fault event, a second time period during the event, and a third time period after the event. The ship bearing features and component operation features within the first and second time periods are arranged in a forward time sequence to obtain a first feature set corresponding to the first time period and a second feature set corresponding to the second time period. The ship bearing features and component operation features within the third time period are arranged in a reverse time sequence to obtain a third feature set corresponding to the third time period. Features are extracted from the bearing operation data and component operation data according to a preset time period to obtain real-time feature sets for different time periods. Each real-time feature set contains real-time bearing operation features and real-time component operation features. The features in the real-time feature set are matched with the features in the second feature set to determine whether there is a match between the real-time bearing operation features and the ship bearing features, and / or the real-time component operation features and the component operation features. If not, the features in the real-time feature set are matched with the features in the first feature set and the third feature set to determine whether there is a match between the features in the first feature set and the features in the real-time feature set, and / or whether there is a match between the features in the third feature set and the features in the real-time feature set. Based on the feature consistency results, feature evolution extraction is performed from the features in the first feature set and / or the third feature set to obtain the ship bearing operation trajectory data.

[0104] Specifically, if real-time bearing operation characteristics match the characteristics of the ship bearing, but real-time component operation characteristics do not match the characteristics of the component operation, then the fault details and solutions for the ship bearing are determined based on historical fault information, and these information and solutions are sent to the target terminal. If real-time component operation characteristics match the characteristics of the component operation, but real-time bearing operation characteristics do not match the characteristics of the ship bearing, then the abnormal time period and degree of mismatch between the real-time component operation characteristics and the component operation characteristics are determined, and the abnormal time period and degree of mismatch are used as search criteria to retrieve historical fault information, obtaining the fault details and solutions for the component, as well as the potential fault information and solutions for the ship bearing. If real-time component operation characteristics match component running characteristics, and real-time bearing operation characteristics match ship bearing characteristics, then the bearing fault characteristics corresponding to the real-time component operation characteristics are determined based on historical fault information. If the bearing fault characteristics are consistent with the real-time bearing operation characteristics, the component running characteristics are taken as the root cause characteristics of the fault, and the fault solution corresponding to the root cause characteristics is determined based on historical fault information. If the bearing fault characteristics are inconsistent with the real-time bearing operation characteristics, then the ship bearing characteristics are taken as the root cause characteristics of the fault, and the fault solution corresponding to the root cause characteristics is determined based on historical fault information.

[0105] Specifically, when the feature consistency result indicates that a feature in the first feature set matches a feature in the real-time feature set, the location of the target feature in the first feature set that matches the feature in the real-time feature set is determined. Then, based on the target feature location, time-series features are selected from the first feature set to obtain the operational trajectory data of the ship bearing. Similarly, when the feature consistency result indicates that a feature in the third feature set matches a feature in the real-time feature set, the location of the target feature in the third feature set that matches the feature in the real-time feature set is determined. Then, based on the target feature location, time-series features are selected from the third feature set to obtain the operational trajectory data of the ship bearing. When the feature consistency result is that the features in the first feature set are consistent with the features in the real-time feature set and the features in the third feature set are consistent with the features in the real-time feature set, then the first target position in the first feature set that is consistent with the features in the real-time feature set and the second target position in the third feature set that is consistent with the features in the real-time feature set are determined respectively. Based on the first target position and the first feature set, time-series features are selected to obtain the first direction data in the first feature set. Based on the second target position and the third feature set, time-series features are selected to obtain the second direction data in the third feature set. The real-time feature set is continuously monitored in real time, and subsequent feature sets are collected. The overlap rate of the subsequent feature sets with the first direction data and the second direction data is detected respectively to obtain the first direction overlap rate with the first direction data at different time points and the second direction overlap rate with the second direction data at different time points. Based on the first direction overlap rate and the second direction overlap rate, the first direction data and the second direction data are spliced ​​together to obtain the operating direction data of the ship bearing.

[0106] Step S13: Extract the running images of different nodes in the ship bearing system at different time points from the bearing evolution animation, and summarize the image feature information in the running images.

[0107] Specifically, the time and location nodes to be captured are determined based on the analysis requirements. Time nodes can be divided according to the key stages of the bearing system's operation, such as the startup stage, stable operation stage, and deceleration stage. Location nodes can be selected based on the structural and functional characteristics of the bearing system, such as the stress-bearing parts and easily worn parts of the bearing. Then, using animation playback software or a dedicated image capture tool, the selected time nodes are located in the bearing evolution animation, and the running images of each location node at that moment are captured. Next, the captured running images are preprocessed, such as adjusting the brightness and contrast of the images and removing noise, to improve image quality. Afterward, image processing techniques and algorithms are used to extract image feature information from the preprocessed running images. For example, color histogram algorithms are used to extract color features, texture analysis algorithms are used to extract texture features, edge detection algorithms are used to extract shape features, and motion tracking algorithms are combined to extract motion features. Finally, the extracted image feature information is summarized and organized to establish an image feature information database.

[0108] Step S14: Input the image feature information into the bearing knowledge graph for feature recognition, determine whether there is a fault or abnormality in the image feature information. If so, determine the target time node of the fault or abnormality based on the image feature information, and determine whether the target time node conforms to the preset time period. If it does, determine the fault details and fault solution based on the recognition results of the bearing knowledge graph and the image feature information.

[0109] Specifically, the aggregated image feature information is input into a pre-constructed bearing knowledge graph. The knowledge reasoning module in the knowledge graph performs pattern matching and logical reasoning on the input feature information to identify whether there are any cases matching known fault characteristics, thereby determining whether an abnormal fault situation exists. If an abnormal fault situation exists, the image feature information is further analyzed, combined with the time correlation information in the knowledge graph, to determine the target time node of the fault anomaly. Then, the target time node is compared with a preset time period to determine whether it conforms to the preset time range. If the target time node conforms to the preset time period, it indicates that the fault occurred within a time period that requires special attention and needs to be dealt with as soon as possible. Next, based on the recognition results of the bearing knowledge graph, that is, the correspondence between fault features and fault types in the knowledge graph, and the fault manifestation reflected by the image feature information, the fault details are determined, including fault type, location, severity, etc. Finally, based on the fault details, the corresponding fault solutions are queried in the bearing knowledge graph, and adjusted and optimized according to the actual situation to formulate a solution suitable for the current fault situation. The preset time period is a time range pre-set based on the operating characteristics of the bearing system, maintenance plan, and historical fault data. It is used to determine whether the time of the fault occurrence is within an acceptable range or requires special attention.

[0110] In this embodiment of the application, the following steps are used when constructing the bearing knowledge graph: obtaining bearing fault images and corresponding fault details and fault resolution steps, and constructing a bearing knowledge graph based on the bearing fault images, fault details and fault resolution steps.

[0111] This application provides a knowledge graph-based method for handling ship bearing faults, acquiring bearing application information and component association information related to the ship bearing. The bearing application information includes key parameters of the ship bearing itself, while the component association information reveals the interaction between the bearing and other components. These interconnected pieces of information form the overall cognitive framework of the ship bearing system. This lays a solid foundation for accurate analysis of the ship bearing system application, avoiding model bias caused by missing or inaccurate information, and thus better reflecting the actual system condition. Based on the bearing entity parameters in the bearing application information and the component entity parameters related to the ship bearing in the component association information, a three-dimensional model of the ship bearing system application is constructed, resulting in a bearing application model. The bearing entity parameters determine the basic shape and performance characteristics of the bearing, while the component entity parameters affect the position and function of the associated components in the system. Combining these two to construct a three-dimensional model can intuitively present the spatial structure of the ship bearing system and the relative positional relationships between its components. Data flow monitoring is performed on the bearing operation data in the bearing application information and the component operation data in the component association information, and the monitored operation flow data is applied to the bearing application model to evolve the model, resulting in a bearing evolution animation. Bearing operation data reflects the actual working status of the bearing during operation, while component operation data reflects the operation of related components. The process involves capturing operational images of different nodes in the marine bearing system at different time points from the bearing evolution animation, and summarizing the image feature information from these images. The bearing evolution animation records the dynamic changes of the system over time, and the operational images at different time points and locations reflect the system's operational status at different times and locations from multiple dimensions. Summarizing the image feature information allows for the integration and analysis of scattered image data. The image feature information is then input into the bearing knowledge graph for feature recognition to determine if any faults or anomalies exist. If so, the target time point of the fault or anomaly is determined based on the image feature information, and it is determined whether the target time point conforms to a preset time period. If it does, the fault details and solutions are determined based on the recognition results of the bearing knowledge graph and the image feature information. The bearing knowledge graph contains a wealth of knowledge and experience about marine bearing systems. Inputting image feature information into it allows for accurate identification using its powerful knowledge base. Determining the target time point of the fault and whether it conforms to a preset time period helps to accurately pinpoint the time range of the fault occurrence. The final determination of fault details and solutions can quickly and effectively resolve faults in the operation of ship bearing systems, reduce downtime, improve the reliability and operating efficiency of ship bearings, and ensure the normal navigation of ships.

[0112] The following describes a knowledge graph-based ship bearing fault handling system provided in an embodiment of this application. The knowledge graph-based ship bearing fault handling system described below can be referred to in conjunction with the knowledge graph-based ship bearing fault handling method described above. Figure 2 , Figure 2 This is a schematic diagram of the structure of a knowledge graph-based ship bearing fault handling system 20 provided in an embodiment of this application, including:

[0113] Information acquisition module 21 is used to acquire bearing application information of ship bearings and component association information associated with ship bearings;

[0114] The model building module 22 is used to build a three-dimensional model of the ship bearing system application based on the bearing entity parameters in the bearing application information and the component entity parameters associated with the ship bearing in the component association information, so as to obtain the bearing application model corresponding to the ship bearing system application.

[0115] The model evolution module 23 is used to monitor the data flow of bearing operation data in bearing application information and component operation data in component association information, and apply the monitored operation flow data to the bearing application model to perform model evolution, thereby obtaining bearing evolution animation.

[0116] The image determination module 24 is used to capture the running images of different positions in the ship bearing system at different time points in the bearing evolution animation, and summarize the image feature information in the running images;

[0117] The fault determination module 25 is used to input image feature information into the bearing knowledge graph for feature recognition, determine whether there is a fault or abnormality in the image feature information, and if so, determine the target time node of the fault or abnormality based on the image feature information, and determine whether the target time node conforms to the preset time period. If it does, determine the fault details and fault solution based on the recognition results of the bearing knowledge graph and the image feature information.

[0118] In one possible implementation of this application embodiment, when the model building module 22 constructs a three-dimensional model of the ship bearing system application based on the bearing entity parameters in the bearing application information and the component entity parameters associated with the ship bearing in the component association information, and obtains a bearing application model corresponding to the ship bearing system application, it is specifically used for:

[0119] The bearing feature points and component feature points associated with the ship bearing are determined based on the bearing entity parameters and component entity parameters.

[0120] The component feature points and bearing feature points are respectively converted into component grid objects corresponding to the component feature points and bearing grid object groups corresponding to the bearing feature points;

[0121] Convert the component grid object into component connection space data, and use grid functions to obtain the source of the widest elevation value for all planar positions in the bearing grid object group;

[0122] Record the source of the widest elevation value of all planar spatial locations in the bearing grid object group as the target grid in the form of integer grid data;

[0123] Based on the target grid, select the bearing object cell at the corresponding position in the bearing grid object group to obtain virtual bearing data composed of one or more bearing spatial elevation grids;

[0124] The virtual bearing data is converted into bearing duty data. Based on each bearing component object type in the bearing grid object group, the bearing space data of the bearing components in the virtual bearing data is generated, taking the component connection space data and bearing duty data as the basis and the distribution of the bearing components corresponding to the bearing component object type in the target grid as the condition.

[0125] By summarizing bearing spatial data from different perspectives and dimensions, a three-dimensional bearing model is constructed, resulting in a bearing application model corresponding to the application of ship bearing systems.

[0126] In another possible implementation of this application embodiment, when the model evolution module 23 monitors the data flow of bearing operation data in bearing application information and component operation data in component association information, it is specifically used for:

[0127] Historical failure information of ship bearings within a historical period is collected, and features are extracted from the historical failure information to obtain time dimension features and corresponding ship bearing features and component operation features. The time dimension features include the first time period before the ship bearing failure event, the second time period during the event, and the third time period after the event.

[0128] The ship bearing characteristics and component operation characteristics during the first time period and the second time period are respectively arranged in positive time sequence feature evolution to obtain the first feature set corresponding to the first time period and the second feature set corresponding to the second time period.

[0129] The ship bearing rating and component operation characteristics during the third time period are arranged in reverse time sequence to obtain the third feature set during the third time period;

[0130] Features are extracted from bearing operation data and component operation data according to preset time periods to obtain real-time feature sets for different time periods. Each real-time feature set contains real-time bearing operation features and real-time component operation features.

[0131] The features in the real-time feature set are matched with the features in the second feature set to determine whether there is a match between the real-time bearing operation features and the ship bearing features, and / or the real-time component operation features and the component operation features. If not, the features in the real-time feature set are matched with the features in the first feature set and the third feature set to determine whether there is a match between the features in the first feature set and the features in the real-time feature set, and / or whether there is a match between the features in the third feature set and the features in the real-time feature set. Based on the feature consistency results, feature evolution extraction is performed from the features in the first feature set and / or the third feature set to obtain the ship bearing operation trajectory data.

[0132] Another possible implementation in this application embodiment is that, when determining whether there is a match between real-time bearing operation characteristics and ship bearing characteristics and / or real-time component operation characteristics and component running characteristics, the model evolution module 23 is specifically used for:

[0133] If there is a real-time bearing operation characteristic that matches the ship bearing characteristic, but no real-time component operation characteristic that matches the component operation characteristic, then the ship bearing fault details and fault solutions are determined based on historical fault information, and the fault details and fault solutions are sent to the target terminal.

[0134] If there is a match between the real-time component operation characteristics and the component running characteristics, but there is no match between the real-time bearing operation characteristics and the ship bearing characteristics, then the abnormal time period and degree of mismatch between the real-time component operation characteristics and the component running characteristics are determined, and the abnormal time period and degree of mismatch are used as search conditions to search for historical fault information to obtain the fault details and fault solutions of the component, as well as the fault potential information and potential solutions of the ship bearing.

[0135] If real-time component operation characteristics match component running characteristics, and real-time bearing operation characteristics match ship bearing characteristics, then the bearing fault characteristics corresponding to the real-time component operation characteristics are determined based on historical fault information. If the bearing fault characteristics are consistent with the real-time bearing operation characteristics, the component running characteristics are taken as the root cause characteristics of the fault, and the fault solution corresponding to the root cause characteristics is determined based on historical fault information. If the bearing fault characteristics are inconsistent with the real-time bearing operation characteristics, then the ship bearing characteristics are taken as the root cause characteristics of the fault, and the fault solution corresponding to the root cause characteristics is determined based on historical fault information.

[0136] In another possible implementation of this application embodiment, when the model evolution module 23 extracts features from the first feature set and / or the second feature set based on the feature consistency result to obtain the ship bearing operation trajectory data, it is specifically used for:

[0137] When the feature consistency result is that the features in the first feature set are consistent with the features in the real-time feature set, the target feature position in the first feature set that is consistent with the features in the real-time feature set is determined, and the time-series features of the first feature set are selected based on the target feature position to obtain the operating direction data of the ship bearing;

[0138] When the feature consistency result is that the features in the third feature set are consistent with the features in the real-time feature set, the target feature position in the third feature set that is consistent with the features in the real-time feature set is determined, and the time-series features of the third feature set are selected based on the target feature position to obtain the operating direction data of the ship bearing.

[0139] In another possible implementation of this application embodiment, system 20 further includes: a position determination module, a first selection module, a second selection module, an overlap rate detection module, and a data stitching module, wherein,

[0140] The location determination module is used to determine the first target location in the first feature set that matches the features in the real-time feature set and the second target location in the third feature set that matches the features in the real-time feature set when the feature consistency result is that the features in the first feature set match the features in the real-time feature set and the features in the third feature set match the features in the real-time feature set.

[0141] The first selection module is used to select temporal features based on the first target location and the first feature set to obtain first orientation data in the first feature set.

[0142] The second selection module is used to select temporal features based on the second target location and the third feature set to obtain the second orientation data in the third feature set.

[0143] The overlap rate detection module is used to continuously monitor the real-time feature set, collect subsequent feature sets, and perform overlap rate detection on the subsequent feature sets with the first direction data and the second direction data respectively, so as to obtain the overlap rate of the first direction data at different time points and the overlap rate of the second direction data at different time points.

[0144] The data stitching module is used to stitch together the first direction data and the second direction data according to the first direction overlap rate and the second direction overlap rate to obtain the operating direction data of the ship bearing.

[0145] In another possible implementation of this application embodiment, system 20 further includes: a fault acquisition module and a map construction module, wherein,

[0146] The fault acquisition module is used to acquire bearing fault images and corresponding fault details and troubleshooting steps.

[0147] The knowledge graph building module is used to build a bearing knowledge graph based on bearing fault images, fault details, and fault resolution steps.

[0148] This application provides an electronic device, such as... Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3 The illustrated electronic device 300 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 300 does not constitute a limitation on the embodiments of this application.

[0149] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in connection with the embodiments of this application. Processor 301 may also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0150] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0151] The memory 303 may be a ROM (Read-Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or it may be an EEPROM (Electrically Erasable Programmable Read-Only Memory), a CD-ROM (Compact Disc Read-Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0152] The memory 303 is used to store application code that executes the scheme of the embodiments of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0153] Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0154] The following describes a computer-readable storage medium provided by an embodiment of this application. The computer-readable storage medium described below can be referred to in correspondence with the method described above.

[0155] This application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the steps of the knowledge graph-based ship bearing fault handling system described above.

[0156] Since the embodiments of the computer-readable storage medium portion correspond to the embodiments of the method portion, please refer to the description of the embodiments of the method portion for the embodiments of the computer-readable storage medium portion.

[0157] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0158] The above are only some embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for handling ship bearing faults based on knowledge graphs, characterized in that, include: Obtain bearing application information for the ship bearings and component association information associated with the ship bearings; Based on the bearing entity parameters in the bearing application information and the component entity parameters associated with the ship bearing in the component association information, a three-dimensional model of the ship bearing system application is constructed to obtain a bearing application model corresponding to the ship bearing system application. The data flow of bearing operation data in the bearing application information and component operation data in the component association information is monitored, and the monitored operation flow data is applied to the bearing application model to perform model evolution, resulting in bearing evolution animation. The image of the bearing evolution animation at different time points is captured at different positions in the ship bearing system, and the image feature information in the image is summarized. The image feature information is input into the bearing knowledge graph for feature recognition. It is determined whether there is a fault or abnormality in the image feature information. If so, the target time node of the fault or abnormality is determined based on the image feature information, and it is determined whether the target time node conforms to a preset time period. If it does, the fault details and fault solution are determined based on the recognition results of the bearing knowledge graph and the image feature information.

2. The method for handling ship bearing faults based on knowledge graphs according to claim 1, characterized in that, The step of constructing a three-dimensional model of the ship bearing system application based on the bearing entity parameters in the bearing application information and the component entity parameters associated with the ship bearing in the component association information, to obtain a bearing application model corresponding to the ship bearing system application, includes: The bearing feature points of the ship bearing and the component feature points of the associated components are determined based on the bearing entity parameters and the component entity parameters. The component feature points and the bearing feature points are respectively converted into component grid objects corresponding to the component feature points and bearing grid object groups corresponding to the bearing feature points; The component grid object is converted into component connection space data, and the grid function is used to obtain the source of the widest elevation value of all planar positions in the bearing grid object group; The widest elevation value of all planar spatial locations in the bearing grid object group is recorded as the target grid in the form of integer grid data; Based on the target grid, select the bearing object cell at the corresponding position in the bearing grid object group to obtain virtual bearing data composed of one or more bearing spatial elevation grids; The virtual bearing data is converted into bearing duty data. Based on each bearing component object type in the bearing grid object group, the bearing space data of the bearing component is generated in the virtual bearing data, taking the component connection space data and the bearing duty data as the basis and the distribution of the bearing components corresponding to the bearing component object type in the target grid as the condition. By summarizing bearing spatial data from different perspectives and dimensions, a three-dimensional bearing model is constructed to obtain a bearing application model corresponding to the application of the ship bearing system.

3. The method for handling ship bearing faults based on knowledge graphs according to claim 2, characterized in that, The monitoring of data flow for the bearing operation data in the bearing application information and the component operation data in the component association information includes: Historical fault information of ship bearings within a historical period is collected, and features are extracted from the historical fault information to obtain time dimension features and corresponding ship bearing features and component operation features. The time dimension features include a first time period before the ship bearing failure event, a second time period during the event, and a third time period after the event. The ship bearing characteristics and component operation characteristics during the first time period and the second time period are respectively arranged in a positive time sequence feature evolution arrangement to obtain a first feature set corresponding to the first time period and a second feature set corresponding to the second time period. The ship bearing rating and component operation characteristics during the third time period are arranged in reverse chronological order to obtain a third feature set corresponding to the third time period. The bearing operation data and the component operation data are subjected to feature extraction according to a preset time period to obtain real-time feature sets for different time periods. Each real-time feature set contains real-time bearing operation features and real-time component operation features. The features in the real-time feature set are matched with the features in the second feature set to determine whether there is a match between the real-time bearing operation feature and the ship bearing feature and / or the real-time component operation feature and the component operation feature. If not, the features in the real-time feature set are matched with the features in the first feature set and the third feature set to determine whether there is a match between the features in the first feature set and the features in the real-time feature set and / or the features in the third feature set. Based on the feature consistency results, feature evolution extraction is performed from the features in the first feature set and / or the third feature set to obtain the ship bearing operation trajectory data.

4. The method for handling ship bearing faults based on knowledge graphs according to claim 3, characterized in that, The determination of whether the real-time bearing operation characteristics match the ship bearing characteristics and / or the real-time component operation characteristics match the component operation characteristics includes: If there exists a real-time bearing operation characteristic that matches the ship bearing characteristic but no real-time component operation characteristic that matches the component operation characteristic, then the fault details and fault solutions of the ship bearing are determined based on the historical fault information, and the fault details and fault solutions are sent to the target terminal. If there exists a real-time component operation feature that matches the component running feature and there is no real-time bearing operation feature that matches the ship bearing feature, then the abnormal time period and degree of mismatch between the real-time component operation feature and the component running feature are determined, and the abnormal time period and degree of mismatch are used as search conditions to search the historical fault information to obtain the component fault details and fault solutions, as well as the fault potential information and potential solutions of the ship bearing. If there exists a real-time component operation characteristic that matches the component running characteristic, and a real-time bearing operation characteristic that matches the ship bearing characteristic, then based on the historical fault information, the bearing fault characteristic corresponding to the real-time component operation characteristic is determined, and it is determined whether the bearing fault characteristic is consistent with the real-time bearing operation characteristic. If so, the component running characteristic is taken as the root cause characteristic of the fault, and the fault solution corresponding to the root cause characteristic is determined based on the historical fault information. If the bearing fault characteristic is inconsistent with the real-time bearing operation characteristic, then the ship bearing characteristic is taken as the root cause characteristic of the fault, and the fault solution corresponding to the root cause characteristic is determined based on the historical fault information.

5. The method for handling ship bearing faults based on knowledge graphs according to claim 4, characterized in that, The step of extracting feature evolution data of ship bearings based on feature consistency results from the first feature set and / or the second feature set to obtain the operational trajectory data includes: When the feature consistency result is that the features in the first feature set are consistent with the features in the real-time feature set, the target feature position in the first feature set that is consistent with the features in the real-time feature set is determined, and the time-series features of the first feature set are selected based on the target feature position to obtain the operating direction data of the ship bearing; When the feature consistency result is that the features in the third feature set are consistent with the features in the real-time feature set, the target feature position in the third feature set that is consistent with the features in the real-time feature set is determined, and the time-series features of the third feature set are selected based on the target feature position to obtain the operating direction data of the ship bearing.

6. The method for handling ship bearing faults based on knowledge graphs according to claim 5, characterized in that, The method further includes: When the feature consistency result is that the features in the first feature set are consistent with the features in the real-time feature set and the features in the third feature set are consistent with the features in the real-time feature set, then the first target position in the first feature set that is consistent with the features in the real-time feature set and the second target position in the third feature set that is consistent with the features in the real-time feature set are determined respectively. Based on the first target location and the first feature set, temporal features are selected to obtain the first directional data in the first feature set; Based on the second target location and the third feature set, temporal features are selected to obtain the second direction data in the third feature set; The real-time feature set is continuously monitored in real time, and subsequent feature sets are collected. The overlap rate of the subsequent feature sets with the first directional data and the second directional data is detected to obtain the overlap rate of the first directional data with different time nodes in the first directional data and the overlap rate of the second directional data with different time nodes in the second directional data. The first direction data and the second direction data are spliced ​​together based on the first direction overlap rate and the second direction overlap rate to obtain the operating direction data of the ship bearing.

7. The method for handling ship bearing faults based on knowledge graphs according to claim 1, characterized in that, Before inputting the image feature information into the bearing knowledge graph for feature recognition and determining whether the image feature information indicates a fault or abnormality, the process also includes: Acquire bearing fault images and corresponding fault details and troubleshooting steps; A bearing knowledge graph is constructed based on the bearing fault images, fault details, and fault resolution steps.

8. A knowledge graph-based ship bearing fault handling system, characterized in that, include: The information acquisition module is used to acquire bearing application information of the ship bearing and component association information associated with the ship bearing; The model building module is used to build a three-dimensional model of the ship bearing system application based on the bearing entity parameters in the bearing application information and the component entity parameters associated with the ship bearing in the component association information, so as to obtain a bearing application model corresponding to the ship bearing system application. The model evolution module is used to monitor the data flow of bearing operation data in the bearing application information and component operation data in the component association information, and apply the monitored operation flow data to the bearing application model to perform model evolution, thereby obtaining a bearing evolution animation. The image determination module is used to capture the running images of different position nodes in the ship bearing system at different time points in the bearing evolution animation, and summarize the image feature information in the running images; The fault determination module is used to input the image feature information into the bearing knowledge graph for feature recognition, determine whether there is a fault or abnormality in the image feature information, and if so, determine the target time node of the fault or abnormality based on the image feature information, and determine whether the target time node conforms to a preset time period. If it does, determine the fault details and fault solution based on the recognition result of the bearing knowledge graph and the image feature information.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: perform a knowledge graph-based ship bearing fault handling method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, include: The computer program is stored and can be loaded by a processor and executed as described in any one of claims 1-7, which is a knowledge graph-based method for handling ship bearing failures.

Images