Satellite communication operation and maintenance monitoring method, cloud platform and electronic device

Abstract

The application relates to a satellite communication operation and maintenance monitoring method, a cloud platform and an electronic device, wherein the satellite communication operation and maintenance monitoring method comprises the following steps: acquiring multiple-source operation and maintenance parameters in real time; the multiple-source operation and maintenance parameters comprise link quality parameters of a satellite end and position and attitude parameters of a very small aperture terminal; based on an artificial intelligence model, the multiple-source operation and maintenance parameters are analyzed in real time according to an alarm rule related to multiple dimensions; in the case that the artificial intelligence model determines that there is an operation and maintenance fault based on the fault analysis, the artificial intelligence model is used to generate an operation and maintenance work order and a fault processing strategy according to the type of the operation and maintenance fault, the fault reason and operation and maintenance parameters related to the operation and maintenance fault; and the generated operation and maintenance work order and fault processing strategy are assigned to an operation and maintenance party. The application can realize intelligent, standardized and closed-loop active operation and maintenance for VSAT satellite communication operation and maintenance, thereby improving the response speed and processing timeliness of operation and maintenance.

Description

Technical Field

[0001] This application relates to the field of satellite communication operation and maintenance, and in particular to satellite communication operation and maintenance monitoring methods, cloud platforms and electronic devices. Background Technology

[0002] Satellite communication systems, especially satellite communication networks that include Very Small Aperture Terminals (VSATs), have been widely used in remote area communication, shipborne and airborne communication, and emergency communication scenarios. A typical satellite communication network usually consists of a satellite platform, gateway stations, a core network, and several VSATs. Due to the wide distribution and complex deployment environment of VSATs, their communication links are susceptible to factors such as rain attenuation, obstruction, interference, and equipment aging, thus requiring operation and maintenance support for the satellite communication system.

[0003] Currently, the traditional satellite communication operation and maintenance system commonly used in related technologies often involves users proactively reporting fault information to the operation and maintenance platform or customer service when they perceive network interruptions, speed degradation, lag, or inability to connect. After receiving user feedback, operation and maintenance personnel manually query data such as satellite link status, VSAT terminal status, signal level, bit error rate, and online status through the network management system. Then, relying on their experience, they diagnose, locate, and analyze the fault to determine its cause. Finally, a maintenance work order is manually created, and operation and maintenance personnel are assigned to remote processing or on-site repair. This approach relies on user-side fault reporting and human experience, making it a reactive operation and maintenance method, and the experience gained is difficult to reuse. Therefore, it suffers from passive response and delayed processing.

[0004] There is currently no effective solution to the problems of passive response and delayed processing in the operation and maintenance of related technologies. Summary of the Invention

[0005] This embodiment provides a satellite communication operation and maintenance monitoring method, cloud platform, and electronic device to solve the problems of passive response and delayed processing in related technologies.

[0006] Firstly, this embodiment provides a satellite communication operation and maintenance monitoring method for a cloud platform, wherein the cloud platform deploys an artificial intelligence model; the method includes:

[0007] Real-time acquisition of multi-source operation and maintenance parameters; the multi-source operation and maintenance parameters include the link quality parameters of the satellite end and the position and attitude parameters of the very small aperture terminal;

[0008] Based on the aforementioned artificial intelligence model, real-time fault analysis is performed on the multi-source operation and maintenance parameters according to the alarm rules associated with multi-dimensional parameters; the artificial intelligence model is trained based on an associated fault case library; the fault case library includes fault cases for satellite communication;

[0009] When the artificial intelligence model determines that there is an operation and maintenance failure based on the failure analysis, it uses the artificial intelligence model to generate operation and maintenance work orders and failure handling strategies according to the type and cause of the operation and maintenance failure and the operation and maintenance parameters associated with the operation and maintenance failure.

[0010] The generated maintenance work orders and fault handling strategies are assigned to the maintenance team.

[0011] In some embodiments, based on the artificial intelligence model, real-time fault analysis is performed on the multi-source operation and maintenance parameters according to alarm rules associated with multi-dimensional parameters, including:

[0012] Based on the aforementioned artificial intelligence model, and according to the alarm rules of the associated multi-dimensional parameters, the multi-source operation and maintenance parameters are analyzed for SMART terminal obstruction faults, transmit power faults, SMART terminal faults, and insufficient pitch angles.

[0013] In some embodiments, the very small caliber terminal is a shipborne very small caliber terminal;

[0014] The obstruction fault analysis includes: determining the existence of the obstruction fault when, among the multi-source operation and maintenance parameters, the signal-to-noise ratio (SNR) of the satellite end is less than or equal to a preset SNR threshold, and the carrier-to-noise ratio (CNR) of the satellite end is less than or equal to a preset CNR threshold, and a change in ship heading is detected; the SNR threshold represents the critical state of interruption of the satellite communication link; the CNR threshold represents the carrier lockout threshold of the satellite communication.

[0015] The transmit power fault analysis includes: determining that a transmit power fault exists when the signal-to-noise ratio is greater than the signal-to-noise ratio threshold and the carrier-to-noise ratio is less than or equal to the carrier-to-noise ratio threshold;

[0016] The fault analysis of the very small aperture terminal includes: when the signal-to-noise ratio and the carrier-to-noise ratio decrease by a preset value within a preset time period and the ship speed increases, it is determined that there is a very small aperture fault.

[0017] The pitch angle deficiency analysis includes: determining that there is a pitch angle deficiency fault when the signal-to-noise ratio is less than or equal to the signal-to-noise ratio threshold, the carrier-to-noise ratio is less than or equal to the carrier-to-noise ratio threshold, and the pitch angle of the very small aperture terminal is less than or equal to a preset pitch angle threshold; the pitch angle threshold represents the geometric pitch angle boundary value that satisfies the satellite communication quality.

[0018] In some embodiments, the fault case library includes historical maintenance cases and historical maintenance work orders; the training process of the artificial intelligence model includes:

[0019] The fault case library is divided into knowledge fragments and stored in a vector database;

[0020] The artificial intelligence model is trained to retrieve knowledge fragments corresponding to questions from the vector database in the form of questions, and the retrieved knowledge fragments are combined into answer text.

[0021] Perform accuracy verification on the answer text;

[0022] Repeat the training of the question format and the accuracy verification of the answer text until the accuracy of the answer text reaches the preset accuracy condition.

[0023] In some of these embodiments, the fault handling strategy is generated, including:

[0024] Based on the fault type of the operation and maintenance fault, the artificial intelligence model generates a fault handling strategy corresponding to the fault type.

[0025] In some embodiments, the method further includes:

[0026] Receive the processing data input into the maintenance work order by the maintenance party after completing the fault handling;

[0027] Based on the processed data, the artificial intelligence model performs self-learning on new cases, and the fault case library is updated based on the processed data.

[0028] In some of these embodiments, multi-source operation and maintenance parameters are acquired in real time, including:

[0029] The multi-source operation and maintenance parameters within a preset time range are associated and stored in time-segmented manner, with the carrier of the very small aperture terminal as the dimension.

[0030] In some embodiments, the method further includes:

[0031] The multi-source operation and maintenance parameters are subjected to trend analysis, and the changing trends of the multi-source operation and maintenance parameters are displayed in real time based on the trend analysis results.

[0032] Secondly, this embodiment provides a cloud platform for performing the satellite communication operation and maintenance monitoring method described in the first aspect above.

[0033] Thirdly, this embodiment provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the satellite communication operation and maintenance monitoring method described in the first aspect above.

[0034] Compared with related technologies, this embodiment provides a satellite communication operation and maintenance monitoring method, cloud platform, and electronic devices. The satellite communication operation and maintenance monitoring method acquires multi-source operation and maintenance parameters in real time. These parameters include link quality parameters at the satellite end and position and attitude parameters of the very small aperture terminal (VSAT). Based on an artificial intelligence model, real-time fault analysis is performed on these parameters according to alarm rules associated with the multi-dimensional parameters. The artificial intelligence model is trained based on an associated fault case library, which includes fault cases specific to satellite communication. When the artificial intelligence model determines that an operation and maintenance fault exists based on fault analysis, it generates operation and maintenance work orders and fault handling strategies according to the type and cause of the fault, combined with the associated operation and maintenance parameters. These work orders and strategies are then distributed to the operation and maintenance team. This enables intelligent and standardized proactive operation and maintenance for VSAT satellite communication, thereby improving response speed and timeliness.

[0035] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0036] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0037] Figure 1 This is a hardware structure block diagram of the terminal of the satellite communication operation and maintenance monitoring method according to an embodiment of this application;

[0038] Figure 2 This is a flowchart of a satellite communication operation and maintenance monitoring method according to an embodiment of this application;

[0039] Figure 3 This is a closed-loop architecture diagram of an embodiment of this application;

[0040] Figure 4 This is a flowchart of a satellite communication operation and maintenance monitoring method according to some embodiments of this application. Detailed Implementation

[0041] To better understand the purpose, technical solution, and advantages of this application, the application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0042] Unless otherwise defined, the technical or scientific terms used in this application shall have the general meaning understood by one of ordinary skill in the art to which this application pertains. Words such as “a,” “an,” “an,” “the,” “the,” and “these” used in this application do not indicate quantitative limitation and may be singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include steps or modules (units) not listed, or may include other steps or modules (units) inherent to these processes, methods, products, or devices. Words such as “connected,” “linked,” and “coupled” used in this application are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. Normally, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," "third," etc., used in this application are merely to distinguish similar objects and do not represent a specific order of objects.

[0043] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. For example, it can run on a terminal. Figure 1 This is a hardware structure block diagram of the terminal for the satellite communication operation and maintenance monitoring method in this embodiment. (See diagram for example.) Figure 1 As shown, a terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 and a memory 104 for storing data are also included. The processor 102 may be, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA). The terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that… Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown are illustrated.

[0044] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the satellite communication operation and maintenance monitoring method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0045] The transmission device 106 is used to receive or send data via a network. This network includes a wireless network provided by the terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 can be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0046] This embodiment provides a satellite communication operation and maintenance monitoring method for a cloud platform, where an artificial intelligence model is deployed. Figure 2 This is a flowchart of the satellite communication operation and maintenance monitoring method in this embodiment, as follows: Figure 2 As shown, the process includes the following steps:

[0047] Step S210: Obtain multi-source operation and maintenance parameters in real time; multi-source operation and maintenance parameters include link quality parameters of the satellite end and position and attitude parameters of the very small aperture terminal.

[0048] The satellite communication operation and maintenance monitoring method in this embodiment is applicable to shipborne VSAT satellite communication scenarios, or scenarios similar to shipborne VSAT satellite communication scenarios where the VSAT carrier is in a complex environment such as movement and swaying, making the satellite link susceptible to factors such as obstruction, weather, antenna attitude, radio frequency devices, and power anomalies.

[0049] In this embodiment, firstly, regarding data access, unified uploading of multi-source heterogeneous data to the cloud is achieved to realize full data collection and centralized, standardized management. The collected data mainly includes two categories: satellite-side link quality parameters and VSAT position and attitude parameters. Specifically, the satellite-side link quality parameters are several parameters characterizing the communication link quality at the satellite end, including but not limited to: signal-to-noise ratio (SNR), carrier-to-noise ratio (C / N0), packet loss rate, link latency, transmit power, receive power, and latency jitter. Specifically, this data can be uploaded to the cloud platform in real time via the VSAT / modem network management interface, IP-based data acquisition gateway, or protocols such as MQTT, HTTP, or TCP, and stored in a pre-built time-series database.

[0050] In shipborne VSAT scenarios, the position and attitude parameters of the very small aperture terminal (also known as VSAT terminal position and attitude parameters) can include, but are not limited to, satellite longitude, ship heading, speed, antenna elevation angle, and antenna azimuth angle. This data can originate from shipborne GPS / BeiDou, compass, and antenna control unit (ACU). This data is then uniformly accessed and stored in a cloud platform for spatiotemporal synchronization and correlation. After collecting these multi-source operation and maintenance parameters, real-time visualization can be provided, generating and displaying corresponding trend curves and historical backtracking data.

[0051] By uploading the link quality parameters from the satellite end and the position and attitude parameters from the VSAT end to the cloud in a unified manner through standardized acquisition interfaces (such as MQTT / HTTP / TCP protocols), the spatiotemporal synchronization and associated storage of multi-source operation and maintenance parameters are realized, thereby solving the problem of data silos and lack of linkage in related technologies.

[0052] Step S220: Based on the artificial intelligence model, real-time fault analysis is performed on multi-source operation and maintenance parameters according to the alarm rules of associated multi-dimensional parameters; the artificial intelligence model is trained based on the associated fault case library; the fault case library includes fault cases for satellite communication.

[0053] This alarm rule can be a logical judgment rule for alarming maintenance faults, associated with multiple dimensions of maintenance parameters from multiple sources. That is, the alarm rule involves a combined logical judgment of maintenance parameters from multiple dimensions. For example, for the fault judgment of VSAT obstruction, the signal-to-noise ratio, carrier-to-noise ratio, and the heading of the vessel carrying the VSAT can be combined. Only when these three dimensions of parameters meet certain threshold conditions is the VSAT obstruction fault determined to exist. In this way, the correlation judgment of multiple source maintenance parameters is achieved, thereby realizing accurate fault judgment based on the combination of multiple parameters. Understandably, the above alarm rule can support flexible configuration; for example, the various thresholds involved in the alarm rule can be flexibly configured to adapt to VSATs of different frequency bands, different satellites, and different ship types.

[0054] This artificial intelligence (AI) model can be implemented using a large language model (LLM) based on retrieval-enhanced generation (RAG), including but not limited to GPT-4o, Claude 3.5 Sonnet, Qwen2.5-72B, DeepSeek-V2.5, and Llama 3.1-70B. The fault case library can be a knowledge base represented in structured data format, covering several typical historical fault cases (e.g., VSAT obstruction historical fault cases, power anomaly historical fault cases, antenna historical fault cases, pitch anomaly historical fault cases, etc.) and work order data. During training, the data in the fault case library can be segmented into several knowledge fragments, such as case summary fragments, solution fragments, and root cause analysis fragments, and then vectorized and stored in a vector database (e.g., Milvus, Qdrant). The AI ​​model is input with questions containing various operational parameters to be analyzed. The AI ​​model retrieves the top K (Top-K) most similar knowledge fragments from a vector database based on the query. It then analyzes these fragments to determine the existence and type of fault, and organizes the results into an output answer. Human review is then used to assess the accuracy of the answer. In Prompt Engineering, the context—combining various operational parameters, recalled historical cases, multi-parameter judgment logic, and fault type—can be input into the LLM (Local Level Management Library). Specifically, to better align the trained AI model with operational standards in the satellite communication field, Low-Rank Adaptation (LoRA) can be used for fine-tuning, making its output more compatible with satellite communication operational practices. When new fault cases require updates, only the vector library needs to be added or removed; model retraining is unnecessary. This enables the AI ​​model to perform real-time fault analysis on multi-source operational parameters.

[0055] Alternatively, AI models for satellite communication operations and maintenance can be trained based on Time Series Large Model (TimeGPT, TimesFM) or traditional Long Short-Term Memory (LSTM) networks. These models can be trained using combined labels of normal and fault states from a fault case library, enabling them to predict trends in various operational parameters and perform fault analysis based on alarm rules.

[0056] The AI ​​model can receive multi-source operation and maintenance parameters in real time, perform threshold judgment, trend judgment and multi-parameter correlation shutdown, match them to the corresponding fault judgment logic / model, and output a high-confidence fault conclusion (e.g., what type of fault exists).

[0057] Furthermore, this embodiment sets alarm rules that are associated with multiple dimensions, enabling the AI ​​model to perform multi-parameter linkage reasoning and judgment when performing fault analysis. This replaces the single threshold alarm in related technologies, enabling accurate fault location and reducing the false alarm rate and false negative rate of fault analysis.

[0058] Step S230: If the artificial intelligence model determines that there is an operation and maintenance fault based on fault analysis, the artificial intelligence model is used to generate operation and maintenance work orders and fault handling strategies according to the type and cause of the operation and maintenance fault, combined with the operation and maintenance parameters associated with the operation and maintenance fault.

[0059] Upon confirming an operational fault, a work order can be automatically generated, along with a fault handling strategy to provide solutions for operations and maintenance personnel. This involves calling a work order generation interface to create the work order. During the generation process, the type and cause of the operational fault, along with associated operational parameters, analyzed by an AI model, are populated into the work order. The generated work order is then intelligently assigned and pushed to the relevant operations and maintenance personnel (e.g., operations engineers) based on their area of ​​responsibility, reminding them to handle the fault. For example, the information populated into the work order can include vessel information, location, time, fault type, alarm cause, and key parameters that triggered the alarm (such as SNR, C / N0, pitch angle, heading, and speed).

[0060] When generating fault handling strategies, the AI ​​model generates corresponding fault handling strategies based on the fault handling logic and steps contained in the work orders corresponding to the current fault type in the fault case library, and pushes them to the operation and maintenance party, thereby providing the operation and maintenance party with intelligent solutions.

[0061] By mapping fault types to fault handling strategies, an automated maintenance system is formed, enabling fault identification and automatic work order dispatch. This reduces reliance on engineers' manual experience and improves the stability and accuracy of maintenance. Compared to related technologies where fault alarms require manual monitoring, manual work order generation, and verbal instructions on troubleshooting, resulting in a time-consuming process, delayed response, and potential for fault escalation, this embodiment, based on an AI model, shortens the time from fault discovery to engineers receiving tasks and clarifying troubleshooting directions. Therefore, it also improves maintenance response efficiency, enables rapid initiation of fault handling, prevents fault escalation, and reduces losses such as communication interruptions.

[0062] Step S240: Distribute the generated maintenance work order and fault handling strategy to the maintenance party.

[0063] After assigning maintenance work orders and fault handling strategies to the maintenance team, a problem-solving and knowledge iteration mechanism can be established for the AI ​​model to achieve closed-loop optimization. Specifically, an input interface for fault handling feedback is set up in the interaction interface with the maintenance team. After the maintenance engineer completes the fault handling based on the work order and AI suggestions, it enters the closed-loop iteration stage. The process, method, results, and verification data of fault handling are filled in on the interaction interface, and the summary document is automatically uploaded to the cloud platform and synchronized to the fault case library of the AI ​​model. The AI ​​model performs self-learning, feature extraction, and rule optimization based on the updated fault case library, continuously improving the diagnostic accuracy. The more cases formed, the more accurate the AI ​​model's reasoning will be, thus enabling more efficient positive iteration in maintenance.

[0064] The AI ​​model can reason and analyze problems in new work orders and new fault cases, extracting and summarizing the handling steps and logical thinking for specific fault types, and storing them in a fault case library. When similar fault types are identified subsequently, solutions can be output based on the corresponding handling steps and logical thinking, continuously optimizing and improving the accuracy and problem-solving capabilities of the AI ​​model.

[0065] For example, if a ship cannot connect to the network, after the AI ​​detects that the relevant operation and maintenance parameters have reached the threshold, it determines that there is a fault of insufficient transmission power. Simultaneously, it outputs a corresponding fault-solving strategy for insufficient transmission power: "Retest the 1dB compression point (P1dB); if P1dB does not change, check the RF cable or up-converter power amplifier (BUC); if the physical link is normal, replace the BUC." Then, the work order and fault-solving strategy are automatically assigned to an engineer for processing. During the process, the engineer discovers that the problem is caused by deformation of the antenna surface. After completing the work order, the engineer writes this fault-solving result into a case study and uploads it to the fault case library. The AI ​​model automatically captures this work order and summarizes the generated fault causes and new fault-solving approaches into the fault case library for learning. The next time the same problem is identified, the AI ​​model will update the fault-solving strategy to: "Retest P1dB; if P1dB does not change, check the RF cable or BUC; if the physical link is normal, replace the BUC; check if the antenna surface is deformed."

[0066] The operation and maintenance monitoring method in this embodiment can be summarized as follows: First, the link quality parameters from the satellite and the position and attitude parameters from the VSAT are collected in real time and connected to the cloud platform to achieve data upload to the cloud. Then, the cloud platform visualizes and monitors the above-mentioned multi-source operation and maintenance parameters in a trend-based manner. The AI ​​model deployed on the cloud platform, based on the real-time analysis of the multi-source operation and maintenance parameters, analyzes whether there is a fault when performing multi-parameter linkage judgment by matching alarm rules of related multi-dimensional parameters. If so, the corresponding fault type is determined. Then, a work order is automatically triggered to generate, and the AI ​​generates a fault handling strategy corresponding to the fault type. The work order and fault handling strategy are pushed to the operation and maintenance team simultaneously. After the operation and maintenance team completes the fault handling according to the work order and fault handling strategy, it uploads the handling feedback. Based on the handling feedback completed by the operation and maintenance team, the AI ​​model learns new cases to optimize the AI ​​model and improve the accuracy of subsequent judgments. Ultimately, it can realize a closed-loop operation and maintenance driven by data visualization, real-time fault identification and timely problem repair, and an evolvable AI model. The operation and maintenance monitoring method in this embodiment is applicable to satellite communication operation and maintenance in mobile scenarios, and is particularly effective for fault operation and maintenance of changes in ship heading, speed and pitch, thus achieving professional operation and maintenance for maritime VSAT.

[0067] Through steps S210 to S240 above, multi-source operation and maintenance parameters are acquired in real time. These parameters include link quality parameters from the satellite and position and attitude parameters of the VSAT terminal. Based on an artificial intelligence model, real-time fault analysis is performed on these parameters according to alarm rules associated with the multi-dimensional parameters. The artificial intelligence model is trained based on an associated fault case library, which includes fault cases specific to satellite communication. When the artificial intelligence model determines that an operation and maintenance fault exists based on the fault analysis, it generates operation and maintenance work orders and fault handling strategies based on the type and cause of the fault, combined with the associated operation and maintenance parameters. These work orders and strategies are then assigned to the operation and maintenance team. This enables intelligent, standardized, and closed-loop proactive operation and maintenance for VSAT satellite communication, thereby improving response speed and timeliness.

[0068] In one embodiment, based on an artificial intelligence model and according to alarm rules for associated multi-dimensional parameters, real-time fault analysis of multi-source operation and maintenance parameters is performed, which may specifically include:

[0069] Based on the artificial intelligence model, and according to the alarm rules of the associated multi-dimensional parameters, the system performs analysis on the blockage faults, transmission power faults, and inadequate pitch angles of the VMS terminal for the multi-source operation and maintenance parameters.

[0070] This embodiment enables satellite communication operation and maintenance adapted to maritime VSAT systems for ship mobility scenarios. Specifically, it designs four types of multi-parameter linked fault alarm rules, including VSAT obstruction fault analysis, transmit power fault analysis, VSAT fault analysis, and VSAT insufficient pitch angle analysis. These four types of alarm rules can all be determined by a combination of satellite-side and VSAT-side operation and maintenance parameters, replacing single-parameter threshold alarms in related technologies.

[0071] When a ship is in a complex scenario of movement and swaying, a single parameter anomaly may be caused by multiple non-fault factors. For example, a momentary drop in SNR may be caused by temporary signal interference rather than equipment failure. Therefore, related technologies rely on a single parameter for fault diagnosis, which can lead to false alarms. Moreover, even when a single parameter is normal while multiple parameters are linked to anomalies, a fault still exists, but traditional single-parameter diagnosis will miss such faults. To address this, this embodiment sets up targeted linkage alarm rules for ship dynamic scenarios (changes in heading and speed) and link quality parameters (SNR, C / N0). This enables precise matching with fault scenarios, eliminates interference from single-parameter anomalies, and thus improves the accuracy of fault alarms, reduces false alarms and missed alarms, avoids ineffective maintenance costs, and enhances the targeting of maintenance.

[0072] More specifically, in one embodiment, the very small aperture terminal is a shipborne very small aperture terminal; the obstruction fault analysis includes: when, among the multi-source operation and maintenance parameters, the signal-to-noise ratio (SNR) at the satellite end is less than or equal to a preset SNR threshold, and the carrier-to-noise ratio (CNR) at the satellite end is less than or equal to a preset CNR threshold, and a change in the ship's heading is detected, an obstruction fault is determined to exist; the SNR threshold represents the critical state of interruption of the satellite communication link; the CNR threshold represents the carrier lock-out threshold of the satellite communication; the transmit power fault analysis includes: when the SNR is greater than the SNR threshold and the CNR is less than or equal to a preset CNR threshold, and a change in the ship's heading is detected, an obstruction fault is determined to exist; the SNR threshold represents the critical state of interruption of the satellite communication link; the CNR threshold represents the carrier lock-out threshold of the satellite communication; the transmit power fault analysis includes: when the SNR is greater than the SNR threshold and the CNR is less than or equal to a preset CNR threshold, the transmit power fault analysis includes: when the SNR is greater than the SNR threshold and the CNR is less than or equal to a preset CNR threshold, the transmit power fault analysis includes: when the transmit power is less than the transmit power ... When the signal-to-noise ratio (SNR) is equal to or greater than the carrier-to-noise ratio (CNR) threshold, a transmit power fault is identified. Fault analysis for very small aperture (VSA) terminals includes: when the SNR and CNR decrease by a preset value within a preset time period, and the ship's speed increases, a VSA fault is identified. Insufficient pitch angle analysis includes: when the SNR is less than or equal to the SNR threshold, and the CNR is less than or equal to the CNR threshold, and the VSA's pitch angle is less than or equal to a preset pitch angle threshold, an insufficient pitch angle fault is identified. The pitch angle threshold represents the geometric pitch angle boundary value that satisfies satellite communication quality.

[0073] Specifically, the VSAT obstruction determination can be as follows: if SNR≤7 and C / N0≤60 and the ship's course changes, VSAT obstruction is confirmed. Thus, based on the correlation judgment of three parameters—SNR, C / N0, and ship's course—VSAT obstruction fault analysis is achieved.

[0074] The determination of insufficient transmission power can be as follows: when SNR > 7 and C / N0 ≤ 60, it is determined that there is a fault of insufficient transmission power.

[0075] For VSAT antenna failure or tracking anomaly determination, the following can be made: if the SNR and C / N0 decrease by 4 dB within a preset short period of time (e.g., within 5 minutes) and the air speed increases, then a VSAT failure is determined to exist.

[0076] The determination of insufficient VSAT pitch angle can be as follows: when SNR≤7, C / N0≤60, and VSAT pitch angle≤15°, it is determined that there is a fault of insufficient VSAT pitch angle.

[0077] This embodiment focuses on the unique operational and maintenance (O&M) characteristics of ship movement scenarios, particularly considering changes in ship heading and speed (e.g., changes in heading triggering VSAT obstruction alarms, and increased speed causing VSAT tracking failures), and VSAT pitch angle adjustments. Furthermore, data acquisition and synchronization are adapted to environments with ship rolling and unstable signals. Compared to related technologies, VSAT O&M solutions are mostly applicable to fixed, stationary scenarios, failing to adequately consider attitude changes and signal fluctuations caused by ship movement. This results in poor adaptability and ineffective fault handling in maritime scenarios. This embodiment, through scenario-based rule design and optimized data acquisition, accurately matches the O&M needs of ship movement scenarios, thereby adapting to the VSAT O&M requirements of mobile vessels such as ocean-going ships and government vessels. This enables professional and targeted VSAT O&M in maritime settings, filling the gap in intelligent O&M in mobile scenarios.

[0078] Additionally, in one embodiment, the fault case library includes historical operation and maintenance cases and historical operation and maintenance work orders; the training process of the artificial intelligence model includes:

[0079] The fault case library is divided into knowledge fragments and stored in a vector database; the artificial intelligence model is trained in the form of questions to retrieve the knowledge fragments corresponding to the questions from the vector database, and the retrieved knowledge fragments are combined into answer text; the accuracy of the answer text is verified; the training in the form of questions and the accuracy verification of the answer text are repeated until the accuracy of the answer text reaches the preset accuracy condition.

[0080] Specifically, pre-written fault cases, product manuals, and other documents (not limited to PDF format) can be uploaded to the fault case library. Simultaneously, the logical thought process for troubleshooting can be documented and entered into the AI. The fault cases include examples compiled by engineers during their daily troubleshooting process, outlining the logic and steps involved. During the creation of these fault cases, experts can review them after completion before uploading them to the fault case library.

[0081] Then, the fault case library is divided into several small knowledge fragments and stored in a vector database. By asking questions, the AI ​​model can be guided to retrieve relevant knowledge fragments from the vector database as temporary output text based on the operational parameters carried in the question. These temporary output texts are then organized into the answer text.

[0082] The AI ​​model is trained using a fault case database and daily conversational questions. Engineers can initially verify the fault type judgments and suggested solutions output by the AI. Problematic content is fed back to the AI ​​model for adjustments, and the cases are updated for further training. After multiple rounds of verification of the AI ​​model's output, and once the accuracy of the output meets certain accuracy criteria (which can be set according to the actual application scenario), the AI ​​training is considered complete and it can be deployed in real-world fault analysis scenarios. This ensures the accuracy of the AI ​​model's output.

[0083] In addition, in one embodiment, generating a fault handling strategy may include: generating a fault handling strategy corresponding to the fault type based on the fault type of the operation and maintenance fault through an artificial intelligence model.

[0084] Different fault types require different solutions. In this embodiment, the AI ​​model can generate targeted fault handling strategies for the currently detected fault type based on historical fault cases and work orders. For example, for the VSAT obstruction fault, the corresponding fault handling strategy is: switch satellites; for the insufficient transmit power fault, the corresponding fault handling strategy is: retest P1dB; if P1dB does not change, check the RF cable or BUC; if the physical link is normal, replace the BUC; for the VSAT fault (degraded tracking performance), the corresponding fault handling strategy is: check the VSAT antenna tracking performance; for the insufficient VSAT pitch fault, the corresponding fault handling strategy is: check the VSAT pitch structure and control anomalies.

[0085] This embodiment can output standardized solutions that match the fault type based on AI models, thereby reducing reliance on manual operation and maintenance experience and improving the stability and accuracy of operation and maintenance.

[0086] In one embodiment, the above-mentioned operation and maintenance monitoring method may further include: receiving processing data input by the operation and maintenance party in the operation and maintenance work order after completing fault handling; performing new case self-learning on the artificial intelligence model based on the processing data; and updating the fault case library based on the processing data.

[0087] Specifically, after completing fault handling based on work orders and fault handling strategies, the operations and maintenance (O&M) party (such as O&M engineers) can send the fault handling process, methods, results, and verification data to the platform, generating a processing summary document which is then uploaded to the cloud platform and synchronized to the AI ​​model. The AI ​​model uses newly added cases from the processing data provided by the O&M party for self-learning, feature extraction, and rule optimization, thereby continuously improving the accuracy of fault diagnosis. By constructing a complete closed-loop process, the summary document uploaded by the O&M party after handling a fault is automatically synchronized to the AI ​​model. This distinguishes it from traditional non-closed-loop O&M models, enabling the AI ​​model to self-learn and optimize diagnostic rules, thus achieving positive iteration of case accumulation, model upgrades, and improved O&M efficiency.

[0088] In another embodiment, real-time acquisition of multi-source operation and maintenance parameters may specifically include: storing multi-source operation and maintenance parameters within a preset time range in a time-segmented manner, with the carrier of the Very Small Aperture Terminal (VSAT) as the dimension. Specifically, the attitude and position parameters of the VSAT and the link quality parameters of the satellite end within the preset time range (e.g., collecting data from the most recent few minutes at several-second intervals) may be stored at different times, with the carrier of the VSAT, such as a ship, as the dimension. This achieves spatiotemporal correlated storage of data from different dimensions, enabling the cloud-based and standardized unified management of multi-source heterogeneous data, solving the data silo problem in traditional operation and maintenance, and achieving the fusion of multi-source heterogeneous data to provide comprehensive and interconnected data support for subsequent fault diagnosis.

[0089] In one embodiment, the above-mentioned satellite communication operation and maintenance monitoring method may further include: performing trend analysis on multi-source operation and maintenance parameters, and displaying the changing trends of multi-source operation and maintenance parameters in real time based on the trend analysis results.

[0090] Time-series data dashboards or visualization components can be used to present various collected operation and maintenance parameters in real time, thereby dynamically and intuitively showing operation and maintenance personnel the trend of data changes.

[0091] Figure 3 This is a closed-loop architecture diagram of this embodiment, such as... Figure 3 As shown, in the scenario of satellite communication operation and maintenance for shipborne VSAT, the AI-driven closed-loop operation and maintenance system includes: a data acquisition layer that uses link quality parameters from the satellite end and position and attitude parameters from the VSAT end as multi-source operation and maintenance parameters; a cloud platform layer with deployed AI models; an AI intelligent diagnosis layer that supports threshold configuration, trigger thresholds, and automatic alarms based on multi-parameter correlation alarm rules; an automated operation and maintenance layer that generates and dispatches work orders and fault handling strategies; and a knowledge iteration layer that enables AI knowledge iteration.

[0092] Therefore, this embodiment unifies the uploading of multi-source data to the cloud, combines AI-powered intelligent fault identification and automatic work order generation and dispatch, and optimizes the AI ​​model through closed-loop feedback, thereby constructing a standardized, intelligent, and iterative VSAT operation and maintenance system. This system can solve the problems of difficult satellite communication operation and maintenance, slow positioning, and cumbersome troubleshooting in mobile scenarios.

[0093] Figure 4 These are flowcharts of satellite communication operation and maintenance monitoring methods in some embodiments, such as... Figure 4 As shown, the process includes the following steps:

[0094] Step S401: Real-time acquisition of link quality parameters and VSAT position and attitude parameters from the satellite end, and access to the cloud platform; wherein, the cloud platform performs spatiotemporal correlation and synchronization management of these multi-source operation and maintenance parameters.

[0095] In step S402, the cloud platform visualizes and monitors the parameters collected in step S401.

[0096] In step S403, the AI ​​model deployed on the cloud platform performs multi-parameter linkage judgment on the collected parameters, matches the alarm rules corresponding to the fault type, and outputs the fault type; wherein, the AI ​​model is pre-trained based on the fault case library to learn operation and maintenance knowledge and fault identification capabilities for satellite communication.

[0097] Step S404: Generate a work order and push it to the operations engineer, simultaneously providing the AI-generated fault handling strategy.

[0098] Step S405: Obtain the fault handling data uploaded by the maintenance engineer after the fault handling is completed.

[0099] Step S406: The AI ​​model learns new cases based on the uploaded fault handling data.

[0100] Steps S401 to S406 above, through real-time collection, analysis, and fault identification of multi-source operation and maintenance parameters from the satellite data terminal and VSAT terminal, enable early detection of faults and potential hazards, improving the timeliness of fault detection and response speed; relying on the core logic algorithm of AI to achieve fault identification, and combining historical data with real-time data to complete the accurate prediction of potential faults, can avoid sudden faults, thereby improving the operational stability of the satellite communication network; by using AI technology to achieve automatic anomaly triggering, automatic work order generation, and intelligent work order dispatch, manual intervention can be reduced, and the degree of operation and maintenance automation and the efficiency and accuracy of work order handling can be improved; by building an AI operation and maintenance knowledge base, fault solutions can be standardized, automatically matched, and output, standardizing fault handling processes, shortening handling cycles, and enabling efficient reuse of operation and maintenance experience; by building an AI-driven closed-loop operation and maintenance system, fault handling experience can be fed back into AI algorithms and knowledge bases to continuously optimize operation and maintenance capabilities. Therefore, this embodiment can transform the traditional passive response satellite communication operation and maintenance into an AI-driven proactive operation and maintenance mode, solving the problems of low operation and maintenance efficiency, delayed fault detection, lack of predictive ability, inability to reuse experience, and lack of closed-loop system in the existing technology, and ultimately comprehensively improving the operation and maintenance quality and operational stability of the satellite communication network.

[0101] This embodiment also provides a cloud platform for implementing the satellite communication operation and maintenance monitoring method described in the above embodiment, which will not be repeated hereafter.

[0102] This embodiment also provides an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0103] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0104] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0105] S1, real-time acquisition of multi-source operation and maintenance parameters; multi-source operation and maintenance parameters include link quality parameters of the satellite end and position and attitude parameters of the very small aperture terminal;

[0106] S2, based on an artificial intelligence model, performs real-time fault analysis on multi-source operation and maintenance parameters according to alarm rules associated with multi-dimensional parameters; the artificial intelligence model is trained based on an associated fault case library; the fault case library includes fault cases for satellite communication;

[0107] S3, when the artificial intelligence model determines that there is an operation and maintenance fault based on fault analysis, it uses the artificial intelligence model to generate operation and maintenance work orders and fault handling strategies according to the type and cause of the operation and maintenance fault, combined with the operation and maintenance parameters associated with the operation and maintenance fault.

[0108] S4 distributes the generated maintenance work orders and fault handling strategies to the maintenance team.

[0109] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.

[0110] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0111] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0112] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.

[0113] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0114] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims

1. A method for operation and maintenance monitoring of satellite communications, characterized in that, For use in a cloud platform, wherein an artificial intelligence model is deployed; the method includes: Real-time acquisition of multi-source operation and maintenance parameters; the multi-source operation and maintenance parameters include the link quality parameters of the satellite end and the position and attitude parameters of the very small aperture terminal; Based on the aforementioned artificial intelligence model, and according to the alarm rules of the associated multi-dimensional parameters, real-time fault analysis is performed on the multi-source operation and maintenance parameters; including: based on the aforementioned artificial intelligence model, and according to the alarm rules of the associated multi-dimensional parameters, performing separate analysis on the multi-source operation and maintenance parameters for very small aperture terminal (VSA) obstruction faults, transmit power faults, antenna faults, and pitch angle deficiencies; the VSA is a shipborne VSA. The obstruction fault analysis includes: determining the existence of the obstruction fault when, among the multi-source operation and maintenance parameters, the signal-to-noise ratio (SNR) of the satellite end is less than or equal to a preset SNR threshold, and the carrier-to-noise ratio (CNR) of the satellite end is less than or equal to a preset CNR threshold, and a change in ship heading is detected; the SNR threshold represents the critical state of interruption of the satellite communication link; the CNR threshold represents the carrier lockout threshold of the satellite communication. The transmit power fault analysis includes: determining that a transmit power fault exists when the signal-to-noise ratio is greater than the signal-to-noise ratio threshold and the carrier-to-noise ratio is less than or equal to the carrier-to-noise ratio threshold; The antenna fault analysis of the very small aperture terminal includes: when the signal-to-noise ratio and the carrier-to-noise ratio decrease by a preset value within a preset time period and the ship speed increases, it is determined that there is an antenna fault in the very small aperture terminal. The pitch angle deficiency analysis includes: determining that there is a pitch angle deficiency fault when the signal-to-noise ratio is less than or equal to the signal-to-noise ratio threshold, the carrier-to-noise ratio is less than or equal to the carrier-to-noise ratio threshold, and the pitch angle of the very small aperture terminal is less than or equal to a preset pitch angle threshold; the pitch angle threshold represents the geometric pitch angle boundary value that satisfies the satellite communication quality. The artificial intelligence model is trained based on an associated fault case library; the fault case library includes fault cases related to satellite communication. When the artificial intelligence model determines that there is an operation and maintenance failure based on the failure analysis, it uses the artificial intelligence model to generate operation and maintenance work orders and failure handling strategies according to the type and cause of the operation and maintenance failure and the operation and maintenance parameters associated with the operation and maintenance failure. The generated maintenance work orders and fault handling strategies are assigned to the maintenance team.

2. The satellite communication operation and maintenance monitoring method according to claim 1, characterized in that, The fault case library includes historical operation and maintenance cases and historical operation and maintenance work orders; the training process of the artificial intelligence model includes: The fault case library is divided into knowledge fragments and stored in a vector database; The artificial intelligence model is trained to retrieve knowledge fragments corresponding to questions from the vector database in the form of questions, and the retrieved knowledge fragments are combined into answer text. Perform accuracy verification on the answer text; Repeat the training of the question format and the accuracy verification of the answer text until the accuracy of the answer text reaches the preset accuracy condition.

3. The satellite communication operation and maintenance monitoring method according to claim 1, characterized in that, Generating the fault handling strategy includes: Based on the fault type of the operation and maintenance fault, the artificial intelligence model generates a fault handling strategy corresponding to the fault type.

4. The satellite communication operation and maintenance monitoring method according to claim 1, characterized in that, The method further includes: Receive the processing data input into the maintenance work order by the maintenance party after completing the fault handling; Based on the processed data, the artificial intelligence model performs self-learning on new cases, and the fault case library is updated based on the processed data.

5. The satellite communication operation and maintenance monitoring method according to claim 1, characterized in that, Real-time acquisition of multi-source operation and maintenance parameters, including: The multi-source operation and maintenance parameters within a preset time range are associated and stored in time-segmented manner, with the carrier of the very small aperture terminal as the dimension.

6. The satellite communication operation and maintenance monitoring method according to any one of claims 1 to 5, characterized in that, The method further includes: The multi-source operation and maintenance parameters are subjected to trend analysis, and the changing trends of the multi-source operation and maintenance parameters are displayed in real time based on the trend analysis results.

7. A cloud platform, characterized in that, The cloud platform is used to execute the operation and maintenance monitoring method for satellite communication as described in any one of claims 1 to 6.

8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the satellite communication operation and maintenance monitoring method according to any one of claims 1 to 6.

Images