A power plant equipment monitoring method, system, device and medium

Abstract

A power plant equipment monitoring method comprises: identifying key information in power plant information based on a large language model, and extracting context information therefrom; the large language model analyzes real-time sensing data based on the context information of the to-be-monitored power plant equipment, obtains a device state of the to-be-monitored power plant equipment, and obtains detailed description content for explaining the device state; image information including the to-be-monitored power plant equipment is obtained, and the real-time sensing data, the context information, and the corresponding natural language description are respectively superimposed into the image information to generate an augmented reality display interface. Since the augmented reality display interface can facilitate a user to directly obtain a state in which the to-be-monitored power plant equipment is located and quickly obtain an explanation and description of the state in which the to-be-monitored power plant equipment is located, the user can intuitively and quickly and comprehensively understand the state of the power plant equipment. The application further provides a power plant equipment monitoring system, equipment and medium.

Description

Technical Field

[0001] This application relates to the field of power plant monitoring technology, specifically to a power plant equipment monitoring method, system, equipment, and medium. Background Technology

[0002] In the field of power engineering, monitoring and anomaly detection of power plant equipment are crucial to ensuring the continuity of power production, the reliability of equipment, and the safety of personnel. Current technical solutions primarily rely on discrete sensor data for power plant equipment monitoring. This data provides basic operational information such as temperature, pressure, and current.

[0003] However, power plant equipment typically generates a large amount of sensor data, which users often find difficult to directly obtain regarding the operational status of the equipment based on. Some solutions analyze this vast amount of sensor data through data processing, but these still rely on user experience and expertise to determine the equipment's operational status, making it challenging for users to accurately assess the equipment's condition. Furthermore, relying solely on sensor data analysis does not provide users with a comprehensive understanding of the power plant's overall status. Therefore, new technological solutions are needed for monitoring power plant equipment. Summary of the Invention

[0004] The main technical problem this application addresses is that users cannot fully understand the status of power plant equipment.

[0005] According to a first aspect, one embodiment provides a power plant equipment monitoring method, comprising:

[0006] The system obtains power plant information of the power plant to which the power plant equipment to be monitored belongs, identifies key information in the power plant information based on a large language model, and extracts context information associated with the power plant equipment to be monitored from the power plant information based on the key information associated with the power plant equipment to be monitored. The context information includes at least one of the historical operation information, maintenance information and equipment information of the power plant equipment to be monitored.

[0007] The real-time sensor data of the power plant equipment to be monitored is acquired so that the large language model can analyze the real-time sensor data based on the context information of the power plant equipment to be monitored, obtain the equipment status of the power plant equipment to be monitored, and obtain a detailed description of the equipment status, and generate natural language descriptions corresponding to the equipment status and the detailed description respectively.

[0008] Image information including the power plant equipment to be monitored is acquired, and real-time sensor data, context information, and natural language descriptions corresponding to the equipment status and detailed description content of the power plant equipment to be monitored are superimposed onto the image information to generate an augmented reality display interface for the power plant equipment to be monitored. User input information is also acquired so that the large language model can interact on the augmented reality display interface based on the input information.

[0009] In some embodiments, the historical operating information includes operating parameters and performance evaluations of the power plant equipment under monitoring during normal operation, as well as operating parameters and performance evaluations during abnormal operation.

[0010] And / or, the maintenance information includes maintenance records and / or upkeep records of the power plant equipment under monitoring during normal operation, as well as the abnormal state of the power plant equipment under monitoring during abnormal operation and the handling method for resolving the abnormal state;

[0011] And / or, the equipment information includes at least one of the following: maintenance method information, equipment design information, equipment specification information, and operating procedure information of the power plant equipment to be monitored.

[0012] In some embodiments, analyzing the real-time sensing data to obtain the equipment status of the power plant equipment to be monitored includes:

[0013] The large language model analyzes the changes and / or trends of the real-time sensing data based on the real-time sensing data, and obtains the performance evaluation of the power plant equipment to be monitored.

[0014] The large language model analyzes whether the real-time sensor data meets the threshold.

[0015] If the threshold is met, the power plant equipment under monitoring is determined to be in normal operating condition.

[0016] If the threshold is not met, then based on real-time sensing data over a period of time, it is determined whether the data conforms to the operating parameters of the power plant equipment under monitoring during normal operation. If it does, the power plant equipment under monitoring is determined to be in normal operating condition; if it does not, the power plant equipment under monitoring is determined to be in abnormal operating condition.

[0017] The performance evaluation and operating status of the power plant equipment to be monitored, as well as the changes and / or trends of the real-time sensor data, are taken as the equipment status.

[0018] In some embodiments, the detailed description of obtaining the interpretation of the device state includes:

[0019] When the power plant equipment under monitoring is in an abnormal operating state, the large language model analyzes the possible causes and / or potential problems of the abnormal operating state of the power plant equipment under monitoring based on context information.

[0020] When the power plant equipment under monitoring is in normal operation, the large language model analyzes the expected time when the power plant equipment under monitoring needs maintenance and / or upkeep based on contextual information.

[0021] The large language model analyzes the correlation between changes and / or trends in the real-time sensor data and time based on contextual information, and obtains the correlation results.

[0022] The possible causes and / or potential problems, along with the expected timing and relevant results, are included in the detailed description.

[0023] In some embodiments, when the power plant equipment under monitoring is in an abnormal operating state, the following is achieved:

[0024] The large language model obtains historical abnormal states that are similar to or the same as the abnormal operating state from the maintenance information, as well as maintenance methods for repairing the historical abnormal states;

[0025] The large language model generates operation suggestions for the abnormal operating state and operation guidance based on the operation suggestions, based on the maintenance method, the historical operation information and the equipment information.

[0026] The large language model generates natural language descriptions of the operation suggestions and the operation instructions;

[0027] Obtain natural language descriptions of the operation suggestions and instructions, and overlay them onto the image information.

[0028] In some embodiments, the operational recommendations include components in the power plant equipment to be monitored that need to be inspected, and / or maintenance procedures for the power plant equipment to be monitored that need to be maintained;

[0029] The operation instructions include at least one of the following: operation steps, operation tools, and operation precautions required based on the operation recommendations.

[0030] In some embodiments, the power plant equipment monitoring method further includes:

[0031] The system continuously acquires real-time sensor data and context information of the power plant equipment under monitoring, and updates the context information, equipment status, and detailed description of the power plant equipment under monitoring on the augmented reality display interface in real time.

[0032] When an abnormality or potential problem is determined in the monitored power plant equipment based on the equipment status and detailed description, an alarm shall be issued and / or relevant personnel shall be notified.

[0033] According to a second aspect, one embodiment provides a power plant equipment monitoring system, comprising:

[0034] The sensing unit is used to acquire the physical parameters of the power plant equipment to be monitored, so as to serve as the real-time sensor data of the power plant equipment to be monitored.

[0035] The camera unit is used to acquire image information of the power plant equipment to be monitored;

[0036] Storage unit, used to store data;

[0037] A processing unit is used to implement the power plant equipment monitoring method as described in the first aspect.

[0038] According to a third aspect, one embodiment provides a power plant equipment monitoring device, comprising:

[0039] Storage unit, used to store data;

[0040] The human-computer interaction unit is used to display visual information and obtain user input;

[0041] A processing unit is used to implement the power plant equipment monitoring method as described in the first aspect.

[0042] According to a fourth aspect, one embodiment provides a computer-readable storage medium storing a program that can be executed by a processor to implement the method as described in the first aspect.

[0043] According to the power plant equipment monitoring method of the above embodiments, contextual information associated with the monitored power plant equipment can be obtained from power plant information based on a large language model. The large language model then analyzes real-time sensor data based on the contextual information of the monitored power plant equipment to obtain the equipment status and a detailed description explaining the equipment status. Simultaneously, natural language descriptions corresponding to the equipment status and the detailed description are generated. The real-time sensor data, contextual information, and the natural language descriptions corresponding to the equipment status and detailed description are then overlaid onto image information to generate an augmented reality display interface. Since the equipment status allows users to directly obtain the status of the monitored power plant equipment, the detailed description allows users to quickly obtain an explanation of the monitored equipment's status, and the contextual information allows users to understand the historical operating information, maintenance information, and equipment information of the monitored power plant equipment, the augmented reality display interface allows users to intuitively, quickly, and comprehensively understand the status of the power plant equipment. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of a power plant equipment monitoring system according to one embodiment;

[0045] Figure 2 This is a schematic diagram of an enhanced display interface according to one embodiment;

[0046] Figure 3 This is a flowchart illustrating one embodiment of a power plant equipment monitoring method;

[0047] Figure 4 This is a schematic diagram of a power plant equipment monitoring device according to one embodiment. Detailed Implementation

[0048] The present application will now be described in further detail with reference to the accompanying drawings and specific embodiments. Similar elements in different embodiments are referred to by related similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of the present application. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to the present application are not shown or described in the specification. This is to avoid obscuring the core parts of the present application with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0049] Furthermore, the features, operations, or characteristics described in the specification can be combined in any suitable manner to form various embodiments. At the same time, the steps or actions in the method description can be rearranged or adjusted in a manner obvious to those skilled in the art. Therefore, the various orders in the specification and drawings are only for the clear description of a particular embodiment and do not imply a necessary order, unless otherwise stated that a particular order must be followed.

[0050] The serial numbers assigned to components in this document, such as "first" and "second," are used only to distinguish the described objects and have no sequential or technical meaning. The terms "connection" and "linkage" used in this application, unless otherwise specified, include both direct and indirect connections (linkages).

[0051] Current technical solutions primarily rely on sensor data analysis to obtain results. However, the large volume of sensor data in complex equipment environments makes it difficult for users to accurately determine equipment status and anomalies based on these results. Furthermore, users cannot quickly understand the state of power plant equipment or obtain relevant status information based solely on these analysis results. Moreover, the lack of in-depth understanding and contextual information regarding equipment status, based on sensor data analysis, hinders users' comprehensive understanding of the power plant equipment's condition.

[0052] In some embodiments of this application, a large language model can be used to obtain contextual information associated with the power plant equipment under monitoring from power plant information. The large language model then analyzes real-time sensor data based on this contextual information to obtain the equipment status of the power plant equipment under monitoring, as well as a detailed description explaining the equipment status. Natural language descriptions corresponding to the equipment status and the detailed description are generated separately. The equipment status allows users to directly access the current state of the power plant equipment under monitoring, while the detailed description provides a quick explanation of the status, enabling a deeper understanding of the equipment status. The contextual information allows users to understand the historical operation, maintenance, and equipment information of the power plant equipment under monitoring. Then, image information of the power plant equipment under monitoring is acquired, and the real-time sensor data, contextual information, and the natural language descriptions corresponding to the equipment status and detailed description are overlaid onto the image information to generate an augmented reality display interface. This augmented reality display interface allows users to quickly and comprehensively understand the status of the power plant equipment.

[0053] Some embodiments provide a power plant equipment monitoring system that can monitor power plant equipment and directly display the monitored equipment and its related status through an augmented reality display interface, providing natural language descriptions of the related statuses, allowing users to intuitively and comprehensively understand the status of the monitored power plant equipment. Please refer to [reference needed]. Figure 1 The power plant equipment monitoring system includes a sensing unit 10, a camera unit 20, a storage unit 30, and a processing unit 40, which are described in detail below.

[0054] The sensing unit 10 is used to acquire physical parameters of the power plant equipment to be monitored. In some embodiments, the sensing unit 10 may include one or more sensors distributed on or near the power plant equipment to acquire physical parameters such as temperature, pressure, current, and humidity. For example, temperature sensors may be distributed on the power plant equipment to acquire the temperature of the target object, and humidity sensors may be distributed near the power plant equipment to acquire the humidity of the environment in which the equipment is located. In some embodiments, the sensing unit 10 may include multiple sensors that measure different physical parameters, and there may be one or more sensors that measure the same physical parameter. In some embodiments, each sensor can acquire the measured physical parameters in real time, thereby generating real-time sensing data of the power plant equipment to be monitored for use in the status analysis of the power plant equipment. In some embodiments, the sensing unit 10 may also include a monitoring system, in which each sensor can transmit its sensing data to the monitoring system, and then output the data after processing by the monitoring system to ensure a continuous data stream. In some embodiments, the sensing unit 10 may be implemented based on Internet of Things (IoT) technology to ensure timely data transmission and storage.

[0055] The camera unit 20 is used to acquire image information of the power plant equipment to be monitored. In some embodiments, the camera unit 20 may include one or more cameras, so that an actual image of the power plant equipment to be monitored can be captured by one camera, or an actual image of the power plant equipment to be monitored from different angles can be captured by multiple cameras, and then the actual images of the power plant equipment from each angle can be obtained based on image fusion. In some embodiments, the image information of the power plant equipment to be monitored can be an image display method or a video display method.

[0056] The processing unit 40 is used to acquire power plant information of the power plant to which the monitored power plant equipment belongs, and then identify key information in the power plant information based on a large language model. Based on the key information associated with the monitored power plant equipment, it extracts contextual information related to the monitored power plant equipment from the power plant information. In some embodiments, since the relevant information of each power plant equipment is stored in a data center used for power plant management, the processing unit 40 needs to first acquire the power plant information and then identify key information in the power plant information based on a large language model. The large language model is a deep learning model trained using a large amount of text data. It can generate natural language text or understand the meaning of language text; for example, GPT-3.5 and Wenxin Yiyan large language models can be used. Based on the large language model, natural language processing techniques, such as word segmentation, named entity recognition, and part-of-speech tagging, can be used to analyze the text data in the power plant information, thereby identifying key information in the power plant information, such as equipment name, model, key parameters, date, and event description. Then, based on key information associated with the equipment in the power plant to be monitored, such as the model and name of the equipment, contextual information associated with the equipment is extracted from the power plant information. In some embodiments, before identifying key information, the text data in the power plant information can be cleaned and preprocessed, including removing special characters, punctuation marks, stop words, etc., to ensure data quality and consistency.

[0057] In some embodiments, the context information includes at least one of the following: historical operating information, maintenance information, and equipment information of the power plant equipment to be monitored. Historical operating information includes operating parameters and performance evaluations of the power plant equipment during normal operation, as well as operating parameters and performance evaluations during abnormal operation. For example, operating parameters can be changes, variances, average values, trends, etc., of equipment parameters during normal or abnormal operation, including parameters such as current, voltage, and temperature. Performance evaluation can be an evaluation of individual equipment parameters or an overall evaluation of the power plant equipment to be monitored. When the power plant equipment is operating normally, its operating parameters typically do not fluctuate significantly, and each equipment parameter usually meets certain threshold ranges. However, during abnormal operation, its operating parameters may fluctuate significantly, and some equipment parameters may exceed certain threshold ranges. Therefore, there is a significant difference between the operating parameters during normal operation and abnormal operation, which can be used to distinguish between normal and abnormal operation of the power plant equipment to be monitored.

[0058] The maintenance information includes maintenance records and upkeep records of the power plant equipment under monitoring during normal operation. For example, maintenance records may include performance assessments of the equipment during maintenance, the date of maintenance, and the specific maintenance items. Similarly, upkeep records may include performance assessments of the equipment during maintenance, the date of maintenance, and the specific maintenance items. The maintenance information also includes the abnormal state of the equipment under monitoring during abnormal operation and the handling methods for resolving this abnormal state. For example, the abnormal state may include specific abnormal events or the operating parameters of the equipment under monitoring when it malfunctions. The handling methods for resolving the abnormal state include the specific handling items performed and the corresponding handling steps. In some embodiments, the maintenance information can be obtained based on the maintenance work order information of the power plant equipment under monitoring.

[0059] The equipment information includes at least one of the following: maintenance method information, equipment design information, equipment specification information, and operating procedure information for the power plant equipment to be monitored. Maintenance method information can be obtained from the maintenance manual of the power plant equipment, while equipment design information, equipment specification information, and operating procedure information can be obtained from the manufacturer's documentation for the power plant equipment. In some embodiments, maintenance method information may include various maintenance items for the power plant equipment and the handling methods for each maintenance item. Equipment design information and equipment specification information may include equipment parameter design, performance design, and usage parameters. Operating procedure information may include various operating items for the power plant equipment and the handling methods for each operating item. In some embodiments, the acquired context information can be stored in a context knowledge base for subsequent querying and analysis; the context knowledge base may take the form of a database, graph database, or knowledge graph.

[0060] As can be seen from the above, the context information of the power plant equipment to be monitored includes a large amount of equipment data and historical data. Based on the context information, users can not only quickly understand the power plant equipment to be monitored, but also, when analyzing the status of the power plant equipment to be monitored, the analysis results can reflect the status of the power plant equipment to be monitored in depth, which is conducive to better analysis of the power plant equipment to be monitored in complex equipment environments.

[0061] The processing unit 40 is also used to acquire real-time sensing data of the power plant equipment to be monitored from the sensing unit 10, so that the large language model can analyze the real-time sensing data based on the context information of the power plant equipment to be monitored, obtain the equipment status of the power plant equipment to be monitored, and obtain a detailed description of the equipment status, and generate natural language descriptions corresponding to the equipment status and the detailed description respectively.

[0062] In some embodiments, the large language model can perform in-depth analysis of real-time sensor data, including analyzing changes and / or trends in the real-time sensor data. For example, it can analyze changes in current sensor data compared to previous sensor data over a period of time, such as changes in the mean, maximum, and minimum values ​​of the sensor data. It can also analyze the overall trend of the sensor data, such as whether the trend remains stable, shows a slight increase, or fluctuates significantly. In some embodiments, the large language model can also obtain performance evaluations of the monitored power plant equipment based on real-time sensor data. For example, for a specific sensor data point, its performance can be evaluated based on its threshold range, such as by assigning a specific score or a rating like excellent, good, or pass. Alternatively, it can perform an overall performance evaluation of the monitored power plant equipment based on individual sensor data points.

[0063] In some embodiments, the large language model also analyzes whether the real-time sensor data meets a threshold. If the threshold is met, the monitored power plant equipment is determined to be in normal operation. If the threshold is not met, the real-time sensor data over a period of time is used to determine whether it conforms to the operating parameters of the monitored power plant equipment during normal operation. If it does, the monitored power plant equipment is determined to be operating normally; otherwise, it is determined to be in an abnormal operating state. In this embodiment, when the real-time sensor data does not meet the threshold, it may be due to fluctuations caused by interference. This can be addressed by using the operating parameters of the monitored power plant equipment during normal operation from historical operating information. If the real-time sensor data over a period of time conforms to the operating parameters during normal operation—for example, if the trend and values ​​of the real-time sensor data over that period are basically consistent with the operating parameters during normal operation—then the monitored power plant equipment is determined to be in normal operation, thus avoiding interference from data affecting the judgment. Conversely, if the real-time sensor data does not conform to the threshold, the monitored power plant equipment is determined to be in an abnormal operating state. In this embodiment, the performance evaluation and operating status of the monitored power plant equipment, as well as the changes and / or trends of the real-time sensor data, are used as the equipment status of the monitored power plant equipment. In some embodiments, the large language model also generates natural language descriptions corresponding to the device status, so that users can quickly obtain relevant information, such as natural language descriptions of "boiler temperature rises above the normal range" or "turbine pressure drops slightly".

[0064] In some embodiments, the large language model also obtains a detailed description of the equipment status based on the contextual information of the power plant equipment being monitored. For example, when the power plant equipment under monitoring is in an abnormal operating state, the large language model analyzes the possible causes and / or potential problems of the abnormal operating state based on the contextual information. Historical operating information provides historical monitoring data and historical performance assessments of the power plant equipment under monitoring; maintenance information provides historical abnormal states, maintenance, and upkeep records of the power plant equipment under monitoring; and equipment information provides performance parameters of the power plant equipment under monitoring. Furthermore, based on multi-faceted information within the contextual information, the large language model can analyze the causes and / or potential problems of the abnormal operating state of the power plant equipment under monitoring separately, thus providing users with various possible causes and / or potential problems for reference. Simultaneously, based on historical data, it can enable a more accurate analysis of the equipment status of the power plant equipment under monitoring.

[0065] In some embodiments, when the monitored power plant equipment is in normal operation, the large language model analyzes the expected time for maintenance and / or upkeep based on contextual information. This upkeep information includes historical performance assessments of the monitored equipment during past maintenance and upkeep, as well as the date intervals between these historical maintenance and upkeep events. Therefore, based on the current performance assessment and the current date, the expected time for maintenance and / or upkeep can be analyzed. In some embodiments, the large language model can also analyze the correlation between changes and / or trends in real-time sensor data and time, obtaining correlation results. For example, if real-time sensor data consistently shows an upward trend in the first time period of a day and a fluctuating upward trend in the second time period, then the upward trend in the first time period and the fluctuating upward trend in the second time period can be used as a correlation result to help users understand the development trend of the real-time sensor data.

[0066] The large language model incorporates the aforementioned possible causes and / or potential problems, along with expected timing and relevance, into a detailed description of the equipment status. Simultaneously, the large language model generates a natural language description corresponding to this detailed description, enabling users to quickly obtain relevant information. As can be seen from the above, based on this detailed description, users can quickly gain a deep understanding of the current status and anomalies of the monitored power plant equipment without needing further analysis of its condition, thus reducing the professional knowledge and experience required from the user.

[0067] In some embodiments, when the power plant equipment under monitoring is in an abnormal operating state, the large language model also acquires historical abnormal states similar to or identical to the abnormal operating state from the maintenance information, as well as maintenance methods for repairing those historical abnormal states. For example, when the power plant equipment under monitoring is in an abnormal operating state, it can acquire historically occurring abnormal boiler temperature states from the maintenance information based on the specific state at this time, such as an abnormal boiler temperature state, or it can acquire similar or identical historical operating parameters from the maintenance information based on real-time sensor data corresponding to the abnormal boiler temperature state. Then, it acquires the maintenance method corresponding to the abnormal boiler temperature state, where the maintenance method can include maintenance items and maintenance steps. Next, based on the above maintenance method, historical operating information, and equipment information, the large language model generates operation suggestions for the above abnormal operating state and operation guidance based on the operation suggestions. Among them, based on the above maintenance method, the processing methods of similar abnormal states in historical data can be referenced to improve the accuracy of operation suggestions and operation guidance, while based on historical operating information and equipment information, operation suggestions and operation guidance applicable to the current power plant equipment under monitoring can be given.

[0068] In some embodiments, operational recommendations include components of the power plant equipment to be monitored that require inspection, and maintenance procedures for maintaining the power plant equipment. Operational instructions include at least one of the operational steps, tools, and precautions required based on the operational recommendations. In some embodiments, when there are multiple historical anomalies, operational recommendations and instructions are generated based on the best practices among them.

[0069] The large language model also generates natural language descriptions of operational suggestions and instructions, enabling users to quickly obtain relevant information. As shown above, the large language model can provide operational suggestions and instructions for abnormal states, guiding users to take appropriate actions. This helps reduce user subjectivity and improves the accuracy and consistency of decision-making.

[0070] In some embodiments, the processing unit 40 acquires image information from the camera unit 20, including the power plant equipment to be monitored, and overlays the real-time sensor data, context information, and natural language descriptions corresponding to the equipment status and detailed descriptions of the power plant equipment to the image information to generate an augmented reality display interface for the power plant equipment to be monitored. Please refer to... Figure 2The augmented reality (AR) interface allows users to intuitively view the power plant equipment under monitoring, understand its status and status analysis, thus gaining a more comprehensive understanding of the equipment and increasing the intelligence and comprehensiveness of the power plant equipment monitoring system. For example, users can quickly understand various historical data, specifications, and performance of the monitored power plant equipment based on contextual information, enabling them to quickly understand the equipment. For instance, when the monitored power plant equipment is in an abnormal state, users can see the specific abnormal state and the corresponding real-time sensor data through the AR interface, and directly obtain possible causes and / or potential problems of the abnormal state, thus providing users with more analytical directions, as well as corresponding operational suggestions and guidance. This avoids subjective judgment and potential human error, providing users with more support and guidance to help them take appropriate actions more quickly.

[0071] In some embodiments, the processing unit 40 can also acquire user input information so that the large language model can interact with the augmented reality display interface based on the input information. For example, the input information may be a user asking further questions about the analysis results or a user requesting further contextual information, and the large language model responds to the input information based on natural language processing technology to achieve interaction with the user.

[0072] In some embodiments, the processing unit 40 continuously acquires real-time sensor data and context information of the power plant equipment under monitoring, and updates the context information, equipment status, and detailed description of the equipment on the augmented reality display interface. Furthermore, when anomalies or potential problems are detected in the monitored power plant equipment based on its status and detailed description, alarms and / or notifications are issued to relevant personnel. For example, alarms and notifications may be implemented through sound, visual prompts, or message notifications. The processing unit 40 ensures timely monitoring by continuously analyzing and updating data. This helps to more quickly detect and respond to potential anomalies, improving the availability and reliability of the equipment.

[0073] Storage unit 30 is used to store various types of data.

[0074] The above is an explanation of the power plant equipment monitoring system.

[0075] Some embodiments provide a power plant equipment monitoring method, which can be applied to the aforementioned power plant equipment monitoring system. Please refer to... Figure 3 The power plant equipment monitoring method includes the following steps:

[0076] Step 100: Obtain context information of the power plant equipment to be monitored. Obtain the power plant information of the power plant to which the power plant equipment to be monitored belongs. Identify key information in the power plant information based on a large language model. Based on the key information associated with the power plant equipment to be monitored, extract context information associated with the power plant equipment to be monitored from the power plant information. The context information includes at least one of the historical operation information, maintenance information, and equipment information of the power plant equipment to be monitored.

[0077] Step 200: The large language model analyzes the real-time sensor data based on contextual information. Real-time sensor data of the power plant equipment to be monitored is acquired, enabling the large language model to analyze the real-time sensor data based on the contextual information of the power plant equipment to be monitored, obtain the equipment status of the power plant equipment to be monitored, and obtain a detailed description explaining the equipment status, and generate natural language descriptions corresponding to the equipment status and the detailed description content, respectively.

[0078] Step 300: Generate the augmented reality display interface for the power plant equipment to be monitored. Acquire image information including the power plant equipment to be monitored, and overlay the real-time sensor data, context information, and natural language descriptions corresponding to the equipment status and detailed description content of the power plant equipment to the image information to generate the augmented reality display interface for the power plant equipment to be monitored. Acquire user input information so that the large language model can interact with the augmented reality display interface based on the input information.

[0079] In some embodiments, the step of analyzing the real-time sensing data to obtain the equipment status of the power plant equipment to be monitored includes: the large language model analyzing the changes and / or trends of the real-time sensing data based on the real-time sensing data, and obtaining a performance evaluation of the power plant equipment to be monitored; the large language model analyzing whether the real-time sensing data meets a threshold; if the threshold is met, it is determined that the power plant equipment to be monitored is in normal operation; if the threshold is not met, based on the real-time sensing data over a period of time, it is determined whether it conforms to the operating parameters of the power plant equipment to be monitored during normal operation; if it conforms, it is determined that the power plant equipment to be monitored is in normal operation; if it does not conform, it is determined that the power plant equipment to be monitored is in abnormal operation; the performance evaluation and operating status of the power plant equipment to be monitored, as well as the changes and / or trends of the real-time sensing data, are used as the equipment status.

[0080] In some embodiments, obtaining a detailed description of the device status includes: when the monitored power plant equipment is in an abnormal operating state, the large language model analyzes the possible causes and / or potential problems of the abnormal operating state based on context information; when the monitored power plant equipment is in a normal operating state, the large language model analyzes the expected time for maintenance and / or upkeep of the monitored power plant equipment based on context information; the large language model analyzes the correlation between the changes and / or trends of the real-time sensor data and time based on context information, and obtains the correlation results; the possible causes and / or potential problems, as well as the expected time and the correlation results, are used as the detailed description.

[0081] In some embodiments, when the power plant equipment to be monitored is in an abnormal operating state, the following steps are taken: the large language model acquires historical abnormal states similar to or identical to the abnormal operating state from the maintenance information, as well as maintenance methods for repairing the historical abnormal states; the large language model generates operation suggestions for the abnormal operating state and operation guidance based on the maintenance methods, the historical operating information, and the equipment information; the large language model generates natural language descriptions of the operation suggestions and the operation guidance; the natural language descriptions of the operation suggestions and the operation guidance are acquired and superimposed on the image information.

[0082] Please refer to Figure 4 Some embodiments provide a power plant monitoring device, which includes a storage unit 50, a human-machine interaction unit 60, and a processing unit 70.

[0083] Storage unit 40 is used to store various types of data.

[0084] The human-computer interaction unit 60 is used to display visual information and obtain user input. For example, the human-computer interaction unit 60 may include a display, and information input devices such as a mouse, keyboard, and keypad. For example, the human-computer interaction unit 60 may include a touch screen for displaying visual information and obtaining user input.

[0085] The processing unit 70 is used to implement the above-mentioned power plant equipment monitoring method.

[0086] Some embodiments provide a computer-readable storage medium storing a program that can be executed by a processor to implement the power plant equipment monitoring method described above.

[0087] Those skilled in the art will understand that all or part of the functions of the various methods in the above embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, which may include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to achieve the above functions. For example, the program can be stored in the memory of a device, and when the program in the memory is executed by the processor, all or part of the above functions can be achieved. In addition, when all or part of the functions in the above embodiments are implemented by computer programs, the program can also be stored in a server, another computer, disk, optical disk, flash drive, or external hard drive, etc., and can be downloaded or copied to the memory of a local device, or the system of the local device can be updated. When the program in the memory is executed by the processor, all or part of the functions in the above embodiments can be achieved.

[0088] The above examples illustrate this application only to aid understanding and are not intended to limit its scope. Those skilled in the art to which this application pertains can make various simple deductions, modifications, or substitutions based on the ideas presented.

Claims

1. A method for monitoring power plant equipment, characterized in that, include: The system obtains power plant information of the power plant to which the power plant equipment to be monitored belongs, identifies key information in the power plant information based on a large language model, and extracts context information associated with the power plant equipment to be monitored from the power plant information based on the key information associated with the power plant equipment to be monitored. The context information includes at least one of the historical operation information, maintenance information and equipment information of the power plant equipment to be monitored. The real-time sensor data of the power plant equipment to be monitored is acquired so that the large language model can analyze the real-time sensor data based on the context information of the power plant equipment to be monitored, obtain the equipment status of the power plant equipment to be monitored, and obtain a detailed description of the equipment status, and generate natural language descriptions corresponding to the equipment status and the detailed description respectively. Image information including the power plant equipment to be monitored is acquired, and real-time sensor data, context information, and natural language descriptions corresponding to the equipment status and detailed description content of the power plant equipment to be monitored are superimposed onto the image information to generate an augmented reality display interface for the power plant equipment to be monitored. User input information is also acquired so that the large language model can interact on the augmented reality display interface based on the input information.

2. The power plant equipment monitoring method as described in claim 1, characterized in that, The historical operating information includes the operating parameters and performance evaluations of the power plant equipment under monitoring during normal operation, as well as the operating parameters and performance evaluations during abnormal operation. And / or, the maintenance information includes maintenance records and / or upkeep records of the power plant equipment under monitoring during normal operation, as well as the abnormal state of the power plant equipment under monitoring during abnormal operation and the handling method for resolving the abnormal state; And / or, the equipment information includes at least one of the following: maintenance method information, equipment design information, equipment specification information, and operating procedure information of the power plant equipment to be monitored.

3. The power plant equipment monitoring method as described in claim 2, characterized in that, The step of analyzing the real-time sensing data to obtain the equipment status of the power plant equipment to be monitored includes: The large language model analyzes the changes and / or trends of the real-time sensing data based on the real-time sensing data, and obtains the performance evaluation of the power plant equipment to be monitored. The large language model analyzes whether the real-time sensor data meets the threshold. If the threshold is met, the power plant equipment under monitoring is determined to be in normal operating condition. If the threshold is not met, then based on real-time sensing data over a period of time, it is determined whether the data conforms to the operating parameters of the power plant equipment under monitoring during normal operation. If it does, the power plant equipment under monitoring is determined to be in normal operating condition; if it does not, the power plant equipment under monitoring is determined to be in abnormal operating condition. The performance evaluation and operating status of the power plant equipment to be monitored, as well as the changes and / or trends of the real-time sensor data, are taken as the equipment status.

4. The power plant equipment monitoring method as described in claim 3, characterized in that, The detailed description of the interpretation of the device state includes: When the power plant equipment under monitoring is in an abnormal operating state, the large language model analyzes the possible causes and / or potential problems of the abnormal operating state of the power plant equipment under monitoring based on context information. When the power plant equipment under monitoring is in normal operation, the large language model analyzes the expected time when the power plant equipment under monitoring needs maintenance and / or upkeep based on contextual information. The large language model analyzes the correlation between changes and / or trends in the real-time sensor data and time based on contextual information, and obtains the correlation results. The possible causes and / or potential problems, along with the expected timing and relevant results, are included in the detailed description.

5. The power plant equipment monitoring method as described in claim 3, characterized in that, When the power plant equipment under monitoring is in an abnormal operating state, so that: The large language model obtains historical abnormal states that are similar to or the same as the abnormal operating state from the maintenance information, as well as maintenance methods for repairing the historical abnormal states; The large language model generates operation suggestions for the abnormal operating state and operation guidance based on the operation suggestions, based on the maintenance method, the historical operation information and the equipment information. The large language model generates natural language descriptions of the operation suggestions and the operation instructions; Obtain natural language descriptions of the operation suggestions and instructions, and overlay them onto the image information.

6. The power plant equipment monitoring method as described in claim 5, characterized in that, The operational recommendations include the components in the power plant equipment to be monitored that need to be inspected, and / or the maintenance procedures for the power plant equipment to be monitored that need to be maintained. The operation instructions include at least one of the following: operation steps, operation tools, and operation precautions required based on the operation recommendations.

7. The power plant equipment monitoring method according to any one of claims 1-6, characterized in that, Also includes: The system continuously acquires real-time sensor data and context information of the power plant equipment under monitoring, and updates the context information, equipment status, and detailed description of the power plant equipment under monitoring on the augmented reality display interface in real time. When an abnormality or potential problem is determined in the monitored power plant equipment based on the equipment status and detailed description, an alarm shall be issued and / or relevant personnel shall be notified.

8. A power plant equipment monitoring system, characterized in that, include: The sensing unit is used to acquire the physical parameters of the power plant equipment to be monitored, so as to serve as the real-time sensor data of the power plant equipment to be monitored. The camera unit is used to acquire image information of the power plant equipment to be monitored; Storage unit, used to store data; A processing unit is used to implement the power plant equipment monitoring method as described in any one of claims 1-7.

9. A power plant equipment monitoring device, characterized in that, include: Storage unit, used to store data; The human-computer interaction unit is used to display visual information and obtain user input; A processing unit is used to implement the power plant equipment monitoring method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The medium stores a program that can be executed by a processor to implement the method as described in any one of claims 1-7.

Images