Thermal power generating unit and alarm analysis method, device, equipment and medium thereof

Abstract

The application provides a thermal power unit and an alarm analysis method, device and equipment thereof and a medium. The method comprises the following steps: acquiring an alarm signal of the thermal power unit; determining at least one initial cause entity corresponding to a target alarm entity from a knowledge graph; determining a device detection point corresponding to each initial cause entity according to a pre-established mapping relationship, so as to obtain real-time detection data corresponding to each initial cause entity from the device detection point; and determining a target cause entity from the at least one initial cause entity based on the real-time detection data, so that alarm diagnosis is changed from manual troubleshooting depending on artificial experience to cause positioning based on data verification, and the scientificity and objectivity of alarm analysis are improved. Meanwhile, through automatic comparison of the knowledge graph, a time-consuming artificial troubleshooting process is compressed to automatic diagnosis within seconds, key time is saved for rapid isolation of faults and recovery of stable operation of the unit, and the probability of unplanned shutdown is effectively reduced.

Description

Technical Field

[0001] This invention relates to the field of thermal power generation technology, and in particular to a thermal power unit and its alarm analysis method, device, equipment and medium. Background Technology

[0002] As a complex coupled system comprising numerous devices such as boilers, turbines, and generators, thermal power units involve intricate physicochemical reactions and energy conversions during operation, with variable operating conditions and close interrelationships. One of the core challenges to the safe and stable operation of these units lies in the rapid and accurate root cause analysis and diagnosis of the massive amounts of alarm information generated within the system.

[0003] Currently, the alarm handling methods commonly used in the industry rely heavily on the experience and manual troubleshooting of operators. When the distributed control system (DCS) of a thermal power unit triggers an alarm, operators need to rely on their personal knowledge or search through a large number of paper and electronic operating procedures to manually identify the possible causes listed in the documents. This diagnostic method is highly dependent on the experience level of the operators, and differences in personnel skills may lead to uncertainty in the handling effect, introducing human operation risks. Summary of the Invention

[0004] This invention addresses the operational risks associated with relying on manual identification of alarm signals in existing technologies by proposing a thermal power unit and its alarm analysis method, device, equipment, and medium.

[0005] This invention provides an alarm analysis method for thermal power units, the method comprising: Acquire the alarm signal of the thermal power unit; the alarm signal includes at least a target alarm entity; Determine at least one initial cause entity corresponding to the target alarm entity from the knowledge graph; the knowledge graph includes at least one alarm entity and at least one cause entity corresponding to each alarm entity; Based on the pre-established mapping relationship, determine the device detection point corresponding to each initial cause entity, so as to obtain the real-time detection data corresponding to each initial cause entity from the device detection point; Based on the real-time detection data, a target cause entity is determined from at least one of the initial cause entities; the target cause entity is the initial cause entity whose real-time detection data has been verified by the fault among the at least one initial cause entity.

[0006] In one embodiment, the knowledge graph also includes a measure entity corresponding to each cause entity; The step of determining the target cause entity from at least one initial cause entity based on the real-time detection data includes: The target measure entity corresponding to the target alarm entity is determined from the knowledge graph; The thermal power unit is adjusted based on the target measures entity.

[0007] In one embodiment, the knowledge graph also includes a device entity corresponding to each of the cause entities; The adjustment of the thermal power unit based on the target measure entity also includes: The target device entity corresponding to the target cause entity is determined from the knowledge graph; Based on the target measure entity, the target equipment entity in the thermal power unit is adjusted.

[0008] In one embodiment, the method further includes: Obtain the knowledge base of the thermal power unit; the knowledge base includes one or more of the following: operating procedures, system diagrams, and historical fault reports; Based on the language model, the alarm entity, the cause entity, the device entity, and the measure entity, as well as the semantic relationships between the entities, are determined from the knowledge base. A knowledge graph is established by using the alarm entity, the cause entity, the device entity, and the measure entity as nodes and the semantic relationships between the entities as edges.

[0009] In one embodiment, the method further includes: Determine the device detection point corresponding to each cause entity, and establish a mapping relationship based on each cause entity and its corresponding device detection point; the device detection point includes KKS code and device tag number.

[0010] In one embodiment, determining the target cause entity from at least one of the initial cause entities based on the real-time detection data includes: Determine the fault determination criteria for each of the initial cause entities; If the real-time detection data meets the fault determination conditions, the corresponding initial cause entity is determined as the target cause entity.

[0011] This invention provides an alarm analysis device for thermal power units, the device comprising: The first acquisition module is used to acquire the alarm signal of the thermal power unit; the alarm signal includes at least a target alarm entity; The first cause determination module is used to determine at least one initial cause entity corresponding to the target alarm entity from the knowledge graph; the knowledge graph includes at least one alarm entity and at least one cause entity corresponding to each alarm entity; The real-time detection module is used to determine the device detection point corresponding to each initial cause entity according to the pre-established mapping relationship, so as to obtain the real-time detection data corresponding to each initial cause entity from the device detection point; The second cause determination module is used to determine a target cause entity from at least one initial cause entity based on the real-time detection data; the target cause entity is the initial cause entity whose real-time detection data has been verified by fault among the at least one initial cause entity.

[0012] This invention provides a thermal power unit that performs alarm analysis based on the alarm analysis method for thermal power units as described in any of the above embodiments.

[0013] This invention provides an electronic device, which includes a processor and a memory. The memory stores at least one instruction, at least one program, a code set, or an instruction set. The processor loads and executes the at least one instruction, at least one program, a code set, or an instruction set to implement the alarm analysis method for thermal power units as described in any of the above embodiments.

[0014] This invention provides a computer-readable storage medium storing at least one instruction or at least one program, which is loaded and executed by a processor to implement the alarm analysis method for thermal power units as described in any of the above embodiments.

[0015] The present invention provides a thermal power unit and its alarm analysis method, device, equipment and medium, which have the following technical effects: Alarm diagnosis has shifted from manual troubleshooting relying on human experience to cause localization based on data verification, improving the scientific rigor and objectivity of alarm analysis. Simultaneously, through automatic comparison using knowledge graphs, the time-consuming manual troubleshooting process is compressed into second-level automated diagnosis, gaining critical time for quickly isolating faults and restoring stable unit operation, effectively reducing the probability of unplanned outages. By objectively verifying the initial cause entity using real-time detection data, misjudgments caused by differences in human experience or subjective negligence are effectively avoided, improving the overall security of the system. Furthermore, the application of knowledge graphs promotes the standardization, digitization, and large-scale application of expert knowledge, accelerating the intelligent transformation process of thermal power plants.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0017] The accompanying drawings, which form part of this specification, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 A first flowchart of an alarm analysis method for thermal power units provided as an exemplary embodiment of the present invention; Figure 2 A first structural diagram of a knowledge graph is provided as an exemplary embodiment of the present invention; Figure 3 A second structural diagram of a knowledge graph is provided as an exemplary embodiment of the present invention; Figure 4 A second flowchart of an alarm analysis method for thermal power units provided as an exemplary embodiment of the present invention; Figure 5 A structural diagram of an alarm analysis device for a thermal power unit provided as an exemplary embodiment of the present invention; Figure 6 This is a structural diagram of an electronic device provided as an exemplary embodiment of the present invention. Detailed Implementation

[0018] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0019] The following detailed descriptions are exemplary and intended to provide a further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this invention is for describing specific embodiments only and is not intended to limit the scope of the exemplary embodiments according to the invention. The terms "first," "second," "third," etc., used in this invention are merely examples and are not intended to limit the specific content of the invention.

[0020] An exemplary embodiment of the present invention provides an alarm analysis method for thermal power units, see below. Figure 1 The methods include: S101, Obtain alarm signals from thermal power units.

[0021] The alarm signal includes at least a target alarm entity. For example, the alarm signal is usually generated by the distributed control system or monitoring system of the thermal power unit. The target alarm entity may include an alarm name, such as "boiler fire extinguishing", or a corresponding alarm number. This embodiment does not limit this and the configuration is based on the actual use scenario.

[0022] S102. Determine at least one initial cause entity corresponding to the target alarm entity from the knowledge graph.

[0023] The knowledge graph includes at least one alarm entity and at least one cause entity corresponding to each alarm entity. An alarm entity may contain an alarm name or an alarm number, and a cause entity may contain a cause name, such as... Figure 2 The knowledge graph shown in the figure has blue parts representing alarm entities and red parts representing cause entities. An alarm entity usually corresponds to at least one cause entity. Based on the target alarm entity, the initial cause entity that matches it can be obtained from the knowledge graph.

[0024] Specifically, alarm entities and cause entities are connected through semantic relationships such as "HAS_CAUSE". Starting from the target alarm entity, a graph traversal query is performed in the knowledge graph to retrieve all initial cause entities connected through the "HAS_CAUSE" relationship.

[0025] S103. Based on the pre-established mapping relationship, determine the device detection point corresponding to each initial cause entity, so as to obtain the real-time detection data corresponding to each initial cause entity from the device detection point.

[0026] In thermal power units, alarm signals are usually generated by equipment failures. After tracing the target alarm entity back to the initial cause entity, each cause entity has equipment that caused its failure. By determining the equipment detection point corresponding to each initial cause entity, real-time detection data of the corresponding equipment can be obtained for alarm analysis.

[0027] In one embodiment, the method for constructing the mapping relationship between device detection points and cause entities further includes: Identify the device detection point corresponding to each cause entity, and establish a mapping relationship based on each cause entity and its corresponding device detection point.

[0028] The equipment testing points include the KKS code and the equipment tag number.

[0029] Specifically, for each "causal entity" in the knowledge graph, a mapping relationship is predefined between it and the corresponding equipment detection point (using KKS code or equipment tag number as an example) in the underlying real-time database. This mapping relationship forms a data bridge connecting abstract knowledge logic and concrete physical measurement points. Different equipment detection points can determine their corresponding KKS codes for subsequent real-time detection data queries. For example, the KKS code for the causal entity "two induced draft fans tripped" is KKS002KKS102; the KKS code for the causal entity "two forced draft fans tripped" is KKS003KKS103; the KKS code for the causal entity "two primary air fans tripped" is UKK5004 / KK5104; the KKS code for the causal entity "no flame detected" is KKS005; the KKS code for the causal entity "feedwater flow rate is lower than 645t / h" is KK5006; and the KKS code for the causal entity "furnace pressure is lower than -1.8kPa" is... The corresponding KKS codes are: KK5007, cause entity "furnace pressure higher than 1.5 kPa"; KK5007, cause entity "water-cooled wall metal temperature higher than 20 degrees Celsius"; KK5008, cause entity "flame detector cooling air pressure lower than 3.23 kPa"; KK5010, cause entity "total airflow less than 30%"; KKS011, cause entity "separator outlet temperature higher than 20 degrees Celsius"; KKS012, cause entity "all fuel loss"; KKS013, KKS113, KKS213, cause entity "desulfurization system trip"; KKS014, cause entity "all feedwater pumps trip"; and KKS015 / KKS115 / KKS215. KK5315KKS415, the cause entity "Unit lateral interlock protection action" has the corresponding KKS code KKS016, and the cause entity "Turbine trip" has the corresponding KKS code KKSO17.

[0030] S104. Based on real-time detection data, determine the target cause entity from at least one initial cause entity.

[0031] The target cause entity is the initial cause entity whose real-time detection data has passed the fault verification in at least one initial cause entity. If the detection data passes the fault verification, it can be considered that the device corresponding to the device detection point has indeed failed. This initial cause entity is one of the reasons for triggering the alarm signal, so it can be used as the target cause entity.

[0032] In one embodiment, step S104 specifically includes: Determine the fault determination conditions for each initial cause entity. If the real-time detection data meets the fault determination conditions, identify the corresponding initial cause entity as the target cause entity. Logically match and verify the real-time detection data with the corresponding fault determination conditions, automatically verify the fault, and select initial cause entities whose data states meet the fault determination conditions as target cause entities. At the same time, filter out initial cause entities that do not meet the fault determination conditions.

[0033] In one embodiment, the knowledge graph also includes a measure entity corresponding to each cause entity. After step S104, the following steps are also included: The target alarm entity is identified from the knowledge graph, and the target measure entity is adjusted based on the target measure entity.

[0034] Among them, such as Figure 2 The knowledge graph shown in the diagram represents alert entities (blue), cause entities (red), and measure entities (brown). Target measure entities can be represented by their names. Alert entities typically correspond to at least one measure entity. Based on a target alert entity, a matching target measure entity can be retrieved from the knowledge graph. Alert entities and measure entities are connected through semantic relationships such as "HAS_SOLUTION". Starting with the target alert entity, the corresponding target measure entity is retrieved from the knowledge graph based on "HAS_SOLUTION".

[0035] In this embodiment, by retrieving the target measure entity, the measures that should be taken in response to the current alarm signal can be determined, which helps to prompt operators to take what measures to eliminate the impact of the alarm signal.

[0036] In an optional implementation, the knowledge graph also includes a device entity corresponding to each cause entity, and after step S104, it further includes: The target equipment entity corresponding to the target cause entity is identified from the knowledge graph, and the target equipment entity in the thermal power unit is adjusted based on the target measure entity.

[0037] The target device entity can be represented by its device name, such as... Figure 3The knowledge graph shown in the diagram represents alarm entities in blue, cause entities in red, and device entities in green. A cause entity typically corresponds to at least one device entity. Based on the target cause entity, the matching target device entity can be retrieved from the knowledge graph. Cause entities and device entities are connected through semantic relationships such as "AFFECTS" and "RELATED_TO". Starting with the target cause entity, the target device entity corresponding to the target cause entity is retrieved from the knowledge graph based on "AFFECTS".

[0038] In this embodiment, by retrieving the target device entity, it is possible to determine which specific device should be addressed in response to the current alarm signal, thus prompting operators to eliminate the impact of the alarm signal.

[0039] In one embodiment, see Figure 4 The methods also include: S401. Obtain the knowledge base of thermal power units.

[0040] The knowledge base includes one or more of the following: operating procedures, system diagrams, and historical fault reports.

[0041] S402. Based on the language model, determine the alarm entity, cause entity, device entity, and measure entity from the knowledge base, as well as the semantic relationships between each entity.

[0042] Specifically, the preferred language model is the LLM model. Based on the language model, the operating procedures, system diagrams and historical fault reports of thermal power units are automatically parsed to accurately extract keywords such as "alarm phenomenon", "root cause of fault", "handling measures" and related "equipment entities". The semantic relationships between these keywords, such as causality, correlation and resolution, are analyzed to form alarm entities, cause entities, equipment entities and measure entities that are interconnected.

[0043] S403. Establish a knowledge graph by using alarm entities, cause entities, device entities, and measure entities as nodes and semantic relationships between entities as edges.

[0044] Specifically, interconnected alarm entities, cause entities, device entities, and measure entities are stored in a graph database (such as Neo4j) to construct a knowledge graph. In the knowledge graph, alarm entities, cause entities, device entities, and measure entities are treated as nodes, and the semantic relationships between entities are defined as edges. For example, an alarm entity is associated with a cause entity through the "HAS_CAUSE" relationship, a cause entity is associated with a measure entity through the "HAS_SOLUTION" relationship, and a cause entity is associated with an affected device entity through the "AFFECTS" or "RELATED_TO" relationship. Figure 2 ,3 As shown, you can see the cause entity, the action entity associated with the alarm entity, and the device entity associated with each cause entity.

[0045] In one embodiment, the method further includes: A diagnostic report is generated based on the target alarm entity and its corresponding target cause entity, target equipment entity, and target measure entity to provide decision support for operators.

[0046] In this embodiment, alarm diagnosis shifts from manual troubleshooting relying on human experience to cause localization based on data verification, improving the scientific rigor and objectivity of alarm analysis. Simultaneously, through automatic comparison using knowledge graphs, the time-consuming manual troubleshooting process is compressed into second-level automatic diagnosis, gaining crucial time for quickly isolating faults and restoring stable unit operation, effectively reducing the probability of unplanned outages. By objectively verifying the initial cause entity using real-time detection data, misjudgments caused by differences in human experience or subjective negligence are effectively avoided, improving the overall system security. Furthermore, the application of knowledge graphs promotes the standardization, digitization, and large-scale application of expert knowledge, accelerating the intelligent transformation process of thermal power enterprises.

[0047] An exemplary embodiment of the present invention provides an alarm analysis device for thermal power units, see below. Figure 5 The device includes: The first acquisition module 51 is used to acquire alarm signals from thermal power units; the alarm signals include at least a target alarm entity. The first cause determination module 52 is used to determine at least one initial cause entity corresponding to the target alarm entity from the knowledge graph; the knowledge graph includes at least one alarm entity and at least one cause entity corresponding to each alarm entity; The real-time detection module 53 is used to determine the device detection point corresponding to each initial cause entity according to the pre-established mapping relationship, so as to obtain the real-time detection data corresponding to each initial cause entity from the device detection point; The second cause determination module 54 is used to determine a target cause entity from at least one initial cause entity based on real-time detection data; the target cause entity is the initial cause entity whose real-time detection data has been verified by the fault among the at least one initial cause entity.

[0048] In one embodiment, the knowledge graph also includes a measure entity corresponding to each cause entity, and the second cause determination module 54 is further configured to: Identify the target measure entity corresponding to the target alarm entity from the knowledge graph; Adjustments are made to thermal power units based on the target measures entity.

[0049] In one embodiment, the knowledge graph also includes a device entity corresponding to each cause entity, and the second cause determination module 54 is further configured to: Identify the target device entity corresponding to the target cause entity from the knowledge graph; Based on the target measures entity, the target equipment entity in the thermal power unit is adjusted.

[0050] In one embodiment, the apparatus further includes: The second acquisition module is used to acquire the knowledge base of the thermal power unit; the knowledge base includes one or more of the operating procedures, system diagrams and historical fault reports. The first semantic determination module is used to determine alarm entities, cause entities, device entities, and measure entities, as well as the semantic relationships between each entity, from the knowledge base based on the language model. A module is established to create a knowledge graph by using alarm entities, cause entities, device entities, and measure entities as nodes and the semantic relationships between these entities as edges.

[0051] In one embodiment, the apparatus further includes: The detection point determination module is used to determine the device detection point corresponding to each cause entity and establish a mapping relationship based on each cause entity and its corresponding device detection point; the device detection point includes KKS code and device tag number.

[0052] In one embodiment, the second cause determination module 54 is further configured to: Determine the failure criteria for each initial cause entity; If the real-time detection data meets the fault determination conditions, the corresponding initial cause entity is determined as the target cause entity.

[0053] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The system embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this disclosure according to actual needs.

[0054] One embodiment of the present invention provides a thermal power unit that performs alarm analysis based on the alarm analysis method of the thermal power unit as described in the above embodiment.

[0055] An exemplary embodiment of the present invention also provides an electronic device, see below. Figure 6The electronic device 600 can vary significantly due to differences in configuration or performance, and may include one or more central processing units (CPUs) 610 (CPUs 610 may include, but are not limited to, microprocessors (MCUs) or programmable logic devices (FPGAs), a memory 630 for storing data, and one or more storage media 620 (e.g., one or more mass storage devices) for storing application programs 623 or data 622. The memory 630 and storage media 620 may be temporary or persistent storage. The storage media 620 stores at least one instruction, at least one program, code set, or instruction set, which is loaded and executed by the processor to implement the aforementioned method.

[0056] Furthermore, the central processing unit 610 can be configured to communicate with the storage medium 620 and execute a series of instructions stored in the storage medium 620 on the electronic device 600. The electronic device 600 may also include one or more power supplies 630, one or more wired or wireless network interfaces 650, one or more input / output interfaces 640, and / or one or more operating systems 621, such as Windows Server™, MacOSX™, Unix™, Linux™, FreeBSD™, etc.

[0057] The input / output interface 640 can be used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the electronic device 600. In one example, the input / output interface 640 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 input / output interface 640 may be a radio frequency (RF) module used for wireless communication with the Internet.

[0058] Those skilled in the art will understand that Figure 6 The structure shown is for illustrative purposes only and does not limit the structure of the electronic system described above. For example, electronic device 600 may also include... Figure 6 The more or fewer components shown, or having the same Figure 6 The different configurations shown.

[0059] Embodiments of the present invention also provide a computer-readable storage medium, which may be disposed in a server to store at least one instruction, at least one program, code set, or instruction set related to implementing a method in the method embodiments, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the above method.

[0060] Optionally, in this embodiment, the storage medium may be located at at least one of the multiple network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0061] Embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0062] The program code for executing the computer program product of the present invention can be written in any combination of one or more programming languages. The program code can be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0063] As is known from common technical knowledge, this invention can be implemented through other embodiments that do not depart from its spirit or essential characteristics. Therefore, the disclosed embodiments described above are merely illustrative in all respects and are not the only ones. All modifications within the scope of this invention or its equivalents are included in this invention.

[0064] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0065] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.

[0066] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction set implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0067] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0068] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for analyzing alarms in thermal power units, characterized in that, The method includes: Acquire the alarm signal of the thermal power unit; the alarm signal includes at least a target alarm entity; Determine at least one initial cause entity corresponding to the target alarm entity from the knowledge graph; the knowledge graph includes at least one alarm entity and at least one cause entity corresponding to each alarm entity; Based on the pre-established mapping relationship, determine the device detection point corresponding to each initial cause entity, so as to obtain the real-time detection data corresponding to each initial cause entity from the device detection point; Based on the real-time detection data, a target cause entity is determined from at least one of the initial cause entities; the target cause entity is the initial cause entity whose real-time detection data has been verified by the fault among the at least one initial cause entity.

2. The alarm analysis method as described in claim 1, characterized in that, The knowledge graph also includes a measure entity corresponding to each of the cause entities; The step of determining the target cause entity from at least one initial cause entity based on the real-time detection data includes: The target measure entity corresponding to the target alarm entity is determined from the knowledge graph; The thermal power unit is adjusted based on the target measures entity.

3. The alarm analysis method as described in claim 2, characterized in that, The knowledge graph also includes the device entity corresponding to each of the cause entities; The adjustment of the thermal power unit based on the target measure entity also includes: The target device entity corresponding to the target cause entity is determined from the knowledge graph; Based on the target measure entity, the target equipment entity in the thermal power unit is adjusted.

4. The alarm analysis method according to any one of claims 1-3, characterized in that, The method further includes: Obtain the knowledge base of the thermal power unit; the knowledge base includes one or more of the following: operating procedures, system diagrams, and historical fault reports; Based on the language model, the alarm entity, the cause entity, the device entity, and the measure entity, as well as the semantic relationships between the entities, are determined from the knowledge base. A knowledge graph is established by using the alarm entity, the cause entity, the device entity, and the measure entity as nodes and the semantic relationships between the entities as edges.

5. The alarm analysis method as described in claim 4, characterized in that, The method further includes: Determine the device detection point corresponding to each cause entity, and establish a mapping relationship based on each cause entity and its corresponding device detection point; the device detection point includes KKS code and device tag number.

6. The alarm analysis method as described in claim 1, characterized in that, The step of determining the target cause entity from at least one initial cause entity based on the real-time detection data includes: Determine the fault determination criteria for each of the initial cause entities; If the real-time detection data meets the fault determination conditions, the corresponding initial cause entity is determined as the target cause entity.

7. An alarm analysis device for thermal power units, characterized in that, The device includes: The first acquisition module is used to acquire the alarm signal of the thermal power unit; the alarm signal includes at least a target alarm entity; The first cause determination module is used to determine at least one initial cause entity corresponding to the target alarm entity from the knowledge graph; the knowledge graph includes at least one alarm entity and at least one cause entity corresponding to each alarm entity; The real-time detection module is used to determine the device detection point corresponding to each initial cause entity according to the pre-established mapping relationship, so as to obtain the real-time detection data corresponding to each initial cause entity from the device detection point; The second cause determination module is used to determine a target cause entity from at least one initial cause entity based on the real-time detection data; the target cause entity is the initial cause entity whose real-time detection data has been verified by fault among the at least one initial cause entity.

8. A thermal power unit, characterized in that, The thermal power unit performs alarm analysis based on the alarm analysis method for thermal power units as described in any one of claims 1-6.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set, or instruction set, and the processor loads and executes the at least one instruction, at least one program, code set, or instruction set to implement the alarm analysis method for thermal power units as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction or at least one program, which is loaded and executed by a processor to implement the alarm analysis method for thermal power units as described in any one of claims 1-6.

Images