Steam turbine fault repair system, repair method and electronic equipment

Abstract

The present invention provides a steam turbine fault inspection and repair system, an inspection and repair method, and an electronic device. The steam turbine fault inspection and repair system includes: a mind map module for creating a mind map of a steam turbine fault decision tree; wherein the fault decision tree represents the relationship between the steam turbine fault phenomenon and the fault cause in the form of a decision tree; a template engine module for converting the exported data of the mind map into a rule flow that can be recognized by the rule engine; a data acquisition module for acquiring the operating data of the steam turbine; a rule engine module for inferring the fault occurring in the steam turbine based on the rule flow and the operating data; and a conclusion management module for displaying the fault and generating a corresponding fault inspection and repair plan accordingly. The present invention effectively realizes the separation of the steam turbine fault inspection and repair judgment method and the system rule code research and development. Business personnel can achieve the code development effect through a simple mind map, generate the judgment logic for steam turbine fault inspection and repair, and infer the possible faults and inspection and repair plans of the steam turbine.

Description

Technical Field

[0001] The present invention relates to the technical field of steam turbines, and in particular to a steam turbine fault repair system, a repair method and electronic equipment. Background Art

[0002] A steam turbine, also known as a steam turbine engine, is a rotary steam-powered device. High-temperature, high-pressure steam passes through a fixed nozzle, accelerating into an airflow and then spraying onto blades. This causes the rotor, equipped with rows of blades, to rotate, simultaneously producing work. Steam turbines are a staple of modern thermal power plants and are also used in the metallurgical and chemical industries, as well as in ship propulsion systems.

[0003] Currently, to automate turbine fault repair, turbine developers need to learn computer programming languages, develop rules for identifying turbine faults through computer programming, and then develop software products that use these rules and turbine operating data to deduce possible turbine faults. However, learning computer programming languages is time-consuming and difficult, and the software product development cycle is long, making it difficult to quickly apply to automated turbine fault repair scenarios. Summary of the Invention

[0004] In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide a steam turbine fault repair system, a repair method and an electronic device to solve the above-mentioned shortcomings in the prior art.

[0005] To achieve the above-mentioned purpose and other related purposes, the present invention provides a fault inspection and repair system for a steam turbine that can be graphically configured in the form of a mind map, comprising: a mind map module for creating a mind map of a steam turbine fault decision tree; wherein the fault decision tree represents the relationship between the steam turbine fault phenomenon and the fault cause in the form of a mind map; a template engine module for converting the exported data of the mind map into a rule flow that can be recognized by a rule engine; a data acquisition module for acquiring the operating data of the steam turbine; a rule engine module for inferring the fault occurring in the steam turbine based on the rule flow and the operating data; and a conclusion management module for displaying the fault and generating a corresponding fault inspection and repair plan.

[0006] In one embodiment of the present invention, the mind map module is also used to: provide an interactive interface, which is provided with an add node control, a save node control, a compile node control and a mind map display area for creating the mind map; wherein, when the compile node control is triggered, the template engine module converts the exported data of the mind map into a rule flow recognizable by the rule engine, and transmits it to the rule engine module.

[0007] In one embodiment of the present invention, the conversion method of the template engine module includes: extracting all conclusion nodes of the mind map and their corresponding paths from the exported data; for each of the paths, removing the first node, taking the last node as the conclusion node, and taking the remaining nodes as conditional nodes; and constructing each of the rule flows based on the set of the conclusion nodes and the conditional nodes of each path.

[0008] In one embodiment of the present invention, the data acquisition module specifically includes: a real-time data management module, which is used to obtain real-time operating data of each measuring point of the turbine; a maintenance order management module, which is used to determine a maintenance order based on the fault phenomenon of the turbine and import the operating data into the maintenance order to convert the real-time operating data into fact data that can be used by the rule engine.

[0009] In one embodiment of the present invention, the system further includes: a data management module for converting the exported data of the mind map into a specific format and storing it in a database, reading and displaying data from the database, and providing data modification and deletion functions.

[0010] In one embodiment of the present invention, the system further includes: a maintenance plan management module for providing maintenance file upload, download, management, import and export services.

[0011] In one embodiment of the present invention, the system further includes: a basic information management module for providing basic elements and management functions for making a mind map.

[0012] In one embodiment of the present invention, the mind map module includes: JSMIND mind map creation tool; the template engine module includes: Velocity template engine tool; the rule engine module includes: Drools rule engine tool.

[0013] To achieve the above-mentioned and other related purposes, the present invention provides a method for troubleshooting a steam turbine, comprising: creating a mind map of a steam turbine fault decision tree; wherein the fault decision tree represents the relationship between the steam turbine fault phenomenon and the fault cause in the form of a decision tree; converting the derived data of the mind map into a rule flow recognizable by a rule engine; obtaining the operating data of the steam turbine; inferring the fault occurring in the steam turbine based on the rule flow and the operating data; and displaying the fault to generate a corresponding fault troubleshooting plan.

[0014] To achieve the above-mentioned purpose and other related purposes, the present invention provides an electronic device, which is communicatively connected to a steam turbine, and includes: the steam turbine fault repair system.

[0015] As described above, the turbine fault inspection and repair system, inspection and repair method, and electronic equipment of the present invention effectively realize the separation of the turbine fault inspection and repair judgment method and the system rule code research and development. The components that are more in line with the characteristics of turbine fault inspection and repair make the rule configuration, rule display, rule sharing, and rule dynamic loading in actual business more efficient and intuitive. Business personnel can achieve the code development effect through a simple mind map, generate the judgment logic of turbine fault inspection and repair, and automatically infer the possible faults, fault causes, and inspection and repair plans of the turbine. In view of the characteristics of many turbine models, high degree of customization, and uneven levels of maintenance personnel, this application independently customizes fault inspection and repair rules, realizing the purpose of modularization and reusability of inspection and repair rules. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 Shown is a schematic diagram of the development process of the steam turbine fault repair system of the present invention.

[0017] Figure 2 Shown is a module schematic diagram of a steam turbine fault repair system in one embodiment of the present invention.

[0018] Figure 3 Shown is a diagram of the human-computer interaction interface of a steam turbine fault repair system in one embodiment of the present invention.

[0019] Figures 4a to 4d Show as click Figure 3 The human-computer interaction interface diagram displayed by several main operation controls.

[0020] Figure 5 Shown is a data structure in a table data format according to an embodiment of the present invention.

[0021] Figure 6 Shown is a schematic diagram of a fault decision tree in an example of the present invention.

[0022] Figure 7 Shown is a schematic diagram of a process in which a template engine converts a rule data model into a rule flow in one embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0024] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0025] See also Figure 1 To implement intelligent maintenance for steam turbine operations, our initial design involved displaying a questionnaire on the interface. The questionnaire contained several questions about turbine failures. Binary tree-based technology determined the turbine failure by obtaining the user's "Yes" or "No" response. Since the results of practical questions are often complex and diverse, rather than simply "Yes" or "No," we decided to use a decision tree to more effectively implement logical judgments.

[0026] The path to a leaf node in the decision tree is a rule. The leaf node is the conclusion, and the path from the root to the parent node of the leaf node is the condition. All nodes are considered measurement points on the turbine. Each measurement point contains a KKS number, an operator, threshold information, and a description. KKS is an industrial representation of the measurement point and component status. Operators refer to computer instructions used in computing languages to compare KKS status values. Currently, KKS logical operators include >, <, =, >=, <=, and <>. Thresholds refer to the critical value of a KKS status value, and description information refers to the meaning of the current KKS in this fault decision tree. Based on the conversion relationship between decision trees and rules, we decided to use a rule engine to implement the judgment logic.

[0027] The rule engine needs to use rule flow as a basis for judgment. In order to allow general business personnel to easily write rule flow, we choose to use mind mapping tools for visual rule development, and require that they can be written and used immediately. Therefore, this application preferably uses JSMind mind mapping as a visualization tool. JSMind mind mapping tool is a lightweight tool with data structures such as NodeArray. Custom development is relatively easy and can be easily embedded in other Web systems. This application can also use Xmind mind mapping and FreeMind mind mapping to achieve similar functions, but both require secondary development. In addition, the documentation for these two tools is relatively small, and it takes a certain amount of time to develop them. Although Xmind is open source and can be embedded in the Web, it has fewer development documents. Although FreeMind is open source, the rich client system cannot be connected to the Web system, and the distribution of the rule data model still needs to be processed.

[0028] In addition, this application preferably uses the Velocity template engine, which is a lightweight tool with mature technology and high usability. Of course, the technical solution of this application can also be implemented using other template engines on the market. This application preferably uses the Drools rule engine, which is mature technology and has low cost, wide use, and high performance as open source software.

[0029] The steam turbine fault inspection and repair system proposed in this application will be described in detail below with reference to the accompanying drawings.

[0030] like Figure 2 As shown, the turbine fault maintenance system of the present application mainly includes: a mind map module 21, a template engine module 22, a data acquisition module 23, a rule engine module 24, a conclusion management module 25, and further includes: a data management module 26, a maintenance plan management module 27, and a basic information management module 28.

[0031] The mind map module 21 is used to create a mind map of the steam turbine fault decision tree.

[0032] Specifically, the fault decision tree represents the relationship between the turbine fault phenomenon and the fault cause in the form of a decision tree. Such a tree can be used to find the fault cause through the fault phenomenon, referred to as a decision fault tree. The decision fault tree is determined by technical experts based on experience. Figure 3 The mind map module 21 provides an interactive interface, in which a row of operation controls for creating a mind map and a display area for displaying the created mind map are provided. Figures 4a to 4d Several key operating controls are explained.

[0033] ①Add controls for fault phenomenon nodes

[0034] like Figure 4a As shown, after the user clicks the control, the system pops up a fault phenomenon edit box, allowing the user to select a fault phenomenon in the phenomenon name drop-down box to add a fault phenomenon node. Preferably, this application stipulates that a fault decision tree corresponds to a fault phenomenon. After the user selects a fault, the system defaults to the fault phenomenon. The added fault phenomenon node is displayed in the display area of the interface, as shown in the following figure. Figure 3 The “AST oil pressure normal” node is shown.

[0035] ②Add controls for phenomenon nodes

[0036] like Figure 4bAs shown in the figure, after the user clicks the control, the system pops up the phenomenon node edit box, allowing the user to select a phenomenon in the phenomenon node drop-down box and enter the description of the phenomenon in the phenomenon node description. Click OK to complete the addition of the phenomenon node. After the user selects the phenomenon node, the phenomenon node is established by default. The added phenomenon node is displayed in the display area of the interface, as shown in the figure. Figure 3 As shown in the "Turbine Reset" node and "Turbine Tripped" node.

[0037] ③Add control for conditional node

[0038] like Figure 4c As shown, after the user clicks the control, the system pops up the condition node edit box, allowing the user to select a turbine measuring point in the measuring point drop-down box, enter the operator in the upper or lower operator, enter the connector in the connection symbol, and enter the corresponding value in the upper or lower limit value. In this way, the syntax of the condition node a≤measuring point≤b or a≥measuring point, measuring point≥b is realized. The added condition node is displayed in the display area of the interface, as shown Figure 3 The “2PT3615>=1.0” node and the “2PT3615<=0.188” node are shown.

[0039] ④Add the control of the conclusion node

[0040] like Figure 4d As shown, after the user clicks the control, the system pops up the conclusion node edit box. When the user selects the diagnosis conclusion in the action type drop-down box, the corresponding conclusion will be displayed in the conclusion description box. Optionally, the user can upload the maintenance plan required by the system in the upload function. The added conclusion node is displayed in the display area of the interface, as shown in the following figure. Figure 3 The "AST Success = Yes" node is shown.

[0041] ⑤Controls for saving nodes

[0042] When the user clicks this control, the system verifies that all data is complete, stores the fault decision tree in the database as a rule data model, and performs the following optimizations:

[0043] Because the ID attribute and ParentID (i.e., parent node, the upper node of the decision tree) attribute in the data model provided by JSMind are both text types. This type has poor performance when querying and comparing data, especially when the amount of data increases sharply. Therefore, when saving the rule data model, secondary development was carried out to convert these two values into numeric types to improve efficiency. In addition, since each node of the decision tree was regarded as a measurement point object at the beginning of the design, it has the attribute of value. For fault phenomena and phenomenon nodes, the values are character types "N" and "Y". This does not conform to the numeric value in the conditional node, so the two special values N and Y are digitized, such as N is defined as -999 and Y is defined as -998.

[0044] It should be noted that the rule data model of this application is a data structure that stores JSMind mind maps in JSON format. JSMind uses this data structure to display its data, and the system uses this data structure to transform and generate rule flows. JSMind itself provides three data structures, namely tree object format, table object format, and freemind format. The table object format refers to the parallel relationship between nodes, and uses ParentId to identify the superior and subordinate relationships. It is suitable for data interaction with relational databases and is more suitable for rule processing and conversion. Therefore, this application preferably uses the table data format provided by JSMind as the basis of the rule data model. This application has obtained the required rule data model through secondary development based on the JSMind table data structure. The table data format is similar to Figure 5 The data structure shown. The rule data model of this application is based on the table data structure of JSMind and adds new attributes on its basis. These data attributes mainly meet the characteristics of turbine operation and maintenance and help to convert and identify system rules, and help the system to convert the fault decision tree into a rule flow in the later stage. Some values such as parentIdValue and level_code_value are character types when first uploaded. Such types are not easy to use and are inefficient to query. Therefore, when corresponding to parentId and Level_code (Level_code is text type, but the original random text is converted into the current node's ID (PK in the database) plus "_" combined text), it becomes a numeric type. The following table contains specific descriptions and explanations of specific attributes.

[0045]

[0046] It should be noted that the protection scope of this application is not limited to storing the mind map data in the form of a regular data model. Technical means of using other data structures to achieve the same data storage effect should be regarded as the protection scope of this application.

[0047] ⑥Controls for compiling nodes

[0048] When the user clicks the control, the system starts compiling the current fault decision tree, and instructs the template engine module 22 to compile the mind map data, such as data stored in the rule data model, into a rule flow recognizable by the rule engine and dynamically load it into the rule engine module 23.

[0049] The template engine module 22 is used to convert the exported data of the mind map into a rule flow that can be recognized by the rule engine.

[0050] Specifically, taking the rule data model used for exporting mind map data as an example, the template engine module 22 mainly performs two tasks: the first part is to find the data required for each rule from the rule data model; the second part is to convert these rule data into rule flow through the conversion template.

[0051] The following will be combined Figure 6 and Figure 7 , which details the implementation process of the Velocity template engine converting the rule data model into a rule flow.

[0052] Figure 6 The display is a fault decision tree for a steam turbine. The leftmost node is the fault phenomenon, the rightmost column of nodes is the conclusion node RHS, the middle ones are all condition nodes LHS, ID is the identifier, and P is the node path. Figure 7 As shown, all conclusion nodes are taken from the rule data model, and the path to which each conclusion node belongs is taken. For each path, the first node is removed, the last node is used as the conclusion node, and the remaining nodes (set) are used as condition nodes. Each rule is constructed based on the set of conclusion nodes and condition nodes of each path. All RHS nodes of a fault detection decision tree are translated into a rule, and the rule is saved in the database, waiting for user compilation. For this example, since the entire JSON collection object is stored in the form of an array, and not all nodes can be converted into rules, only the conclusion node can be extracted as a rule. The reason is that the conclusion node stores a complete path from it to the root node, and only those that meet this condition can be converted into rules.

[0053] System developers develop conversion templates in the Velocity language in advance. During compilation, the Velocity template engine arranges all the rules under the fault detection decision tree in chronological order based on the conversion template to form a rule flow (i.e., a string representation of the rules). The rule flow is compiled by the rule engine to become business logic. For example, the conversion template is:

[0054]

[0055]

[0056] Figure 3 After compiling the fault rule tree shown, the system will automatically convert "Turbine reset - 2PT3615 >= 1.0 - AST success = Y" and "Turbine shielded - 2PT3615 <= 0.188 - AST success = Y" into rules that can be executed by the rule engine. The translation effect is:

[0057] IF the turbine has been reset = Y and 2PT3615> = 1.0 THEN AST is successful

[0058] IF TURBINE SHIELDED = Y and 2PT3615 < 0.188 THEN AST is successful.

[0059] It should be noted that those skilled in the art may use other methods to convert the exported data of the mind map into a rule flow, and the scope of protection of this application is not limited to the above example.

[0060] The data acquisition module 23 is used to obtain the operating data of the steam turbine.

[0061] Specifically, the data acquisition module 23 further includes submodules: a real-time data management module 231 and a maintenance order management module 232. The real-time data management module 231 is used to acquire real-time operating data from each measuring point of the steam turbine. This module primarily serves as the interface between the system and the steam turbine, and is used to import the real-time data from the steam turbine into a maintenance order. The maintenance order management module 232 is used to determine a maintenance order based on the turbine's fault symptoms and import the operating data into the maintenance order, thereby facilitating the conversion of the real-time operating data into factual data usable by the rule engine. It should be noted that the maintenance order is a storage medium for the real-time operating data of the steam turbine and preferably serves as a source of factual data for the rule engine. Factual data refers to a snapshot of the current values of each measuring point during turbine operation, taken after they are entered into the maintenance order. Those skilled in the art may employ other technical means to achieve the conversion of real-time operating data from the steam turbine into factual data, and the format of the maintenance order should not be construed as limiting the scope of protection of this application.

[0062] The rule engine module 24 is configured to infer the fault of the steam turbine based on the rule flow and the operation data.

[0063] Specifically, the Drools rule engine converts the legal rule flow into executable fault judgment logic, uses the real-time data of turbine operation as facts to perform rule reasoning, and returns the obtained reasoning process to the conclusion management module 25. It should be noted that the Drools rule engine is an open source rule engine, and the rule reasoning has been developed. In order to embed it into this system, we have done some secondary development work. Drools itself provides two ways to import rules: one is the Drools rule file; the other is the rule string. In order to realize dynamic loading of rules, we adopt the latter method, converting the rules into rule flow and importing them into Drools. Then Drools dynamically compiles all valid rules, so that the system logic changes dynamically, so that users feel that as long as they write the decision tree themselves, the system logic will automatically change, achieving the same effect as programming, and this process is transparent to users, as simple as saving a file.

[0064] The conclusion management module 25 is used to display the faults obtained by reasoning and generate corresponding fault repair plans based on them.

[0065] Specifically, this module is mainly used for parsing RHS nodes. After the rule operation, the rule engine module 24 infers which RHS node needs to be executed and returns the PK (i.e., primary key, representing the unique identifier of a node in the database) of the RHS node to the conclusion management module 25. When multiple results are obtained according to the same fault decision tree, the system will bring back all RHS nodes that meet the conditions and execute all RHS nodes in sequence. That is to say, when multiple conclusions are determined according to the same set of parameters, the system will bring back all conclusions together and execute each conclusion in the order of priority of the conclusion. The RHS node refers to the conclusion node. The maintenance plan refers to the method of repairing a certain fault of the turbine. If the conclusion contains a maintenance file, the maintenance file download list will be provided to the user through this module.

[0066] The data management module 26 is used to convert the exported data of the mind map into a specific format, such as a rule data model, store it in a database, read data from the database and display it, and provide data modification and deletion functions.

[0067] The maintenance plan management module 27 provides services for uploading, downloading, managing, importing, and exporting maintenance files. It also provides a link to the conclusion management module 25 for downloading maintenance plans. Similar to an FTP function, it supports maintenance plan file formats such as Word, Excel, PDF, and JPG. The maintenance plan management module 27 can utilize existing file upload controls to upload maintenance files to the server and store them in the file system as files, rather than in the database.

[0068] The basic information management module 28 is used to provide the basic elements for making a mind map, such as fault phenomenon management, measurement point management, and node management, and provides functions such as adding, querying, and modifying these data.

[0069] Those skilled in the art will appreciate that the division of the various modules in the above system embodiments is merely a division of logical functions, and in actual implementation, they may be fully or partially integrated into one or more physical entities. Furthermore, these modules may be implemented entirely in the form of software called by processing elements, entirely in the form of hardware, or partially in the form of software called by processing elements and partially in the form of hardware.

[0070] The turbine fault inspection and maintenance system of this application combines JSMind and Velocity for the first time and redefines a rule-making tool that conforms to the characteristics of turbine operation and maintenance in accordance with the characteristics of turbine operation and maintenance. By simply clicking the save and compile buttons with the mouse, business personnel can easily and in real time change business rules, making the rule engine transparent to business personnel, greatly reducing the cost of business personnel using the rule system.

[0071] Similar to the principle of the aforementioned system embodiment, the present application also provides a steam turbine fault troubleshooting method, which is applied to electronic equipment and includes the following steps:

[0072] Step 1: Create a mind map of the steam turbine fault decision tree; wherein the fault decision tree represents the relationship between the steam turbine fault phenomenon and the fault cause in the form of a mind map;

[0073] Step 2: Convert the exported data of the mind map into a rule flow that can be recognized by the rule engine;

[0074] Step 3: Obtain the operating data of the steam turbine;

[0075] Step 4: Inferring the fault of the steam turbine based on the rule flow and the operating data;

[0076] Step 5: Display the fault and generate a corresponding fault repair plan based on it.

[0077] Since the specific implementation of this embodiment is the same as that of the aforementioned system embodiment, a repeated description thereof will not be given here.

[0078] The present application also provides an electronic device, such as a desktop computer, a portable computer, a tablet computer, or a smart phone, which is communicatively connected to a steam turbine. In particular, the electronic device includes the steam turbine fault repair system described in any of the aforementioned system embodiments.

[0079] In summary, the steam turbine fault repair system, repair method, and electronic equipment of the present invention have the following beneficial technical effects, thereby overcoming various shortcomings of the prior art and having high industrial application value:

[0080] 1. Reduce the cost for business personnel to use the rule system

[0081] The rule system is a relatively complex software system, especially the writing of rule files. In the absence of the tools of this application, general business personnel must learn how to write rule files. This process requires not only learning a computer programming language but also learning the rule writing language. This time cost takes at least a year. Even if you learn these languages, you still have a considerable learning curve when you need to use dynamic loading rules. Now that a graphical configuration system has been developed, the learning cost of factory operation and maintenance personnel has been greatly reduced. Operation and maintenance personnel only need to focus on their original business, which is of great help in promoting the application of rule systems.

[0082] 2. Use customized mind mapping tools to develop business rule decision trees, which is more convenient than general tools.

[0083] Drools also provides a visualization tool similar to JSMind in this system for developing business rules, but this tool is far from suitable for the field of steam turbine operation and maintenance and cannot meet the requirements of steam turbine operation and maintenance. With this application tool, we can provide components that meet specific business requirements according to user requirements for easy user use.

[0084] 3. Business personnel can achieve the effect of dynamic programming of business logic by making a mind map of the fault decision tree

[0085] Transforming decision rules is a common problem in operations and maintenance. Dynamic rule loading, a feature of rule engines, was difficult to implement before the development of this system, significantly impacting the user experience. This system automatically converts fault decision trees into rule flows, instantly changing the business decision logic with a simple click of the mouse.

[0086] 4. Rich export data structure can better share turbine operation and maintenance management knowledge

[0087] In addition to the data structures mentioned above, this system can export corresponding data structure files such as snapshots of mind maps, thus providing a convenient display tool for data sharing and brainstorming within the organization.

[0088] 5. It can realize the condition maintenance of steam turbine

[0089] This system is connected to the steam turbine in real time and can obtain the real-time operation data of the steam turbine. Therefore, it can infer the possible faults of the steam turbine based on the current status of the steam turbine and the reasoning rules, which helps to implement condition-based maintenance in a timely manner.

[0090] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical principles disclosed herein are intended to be covered by the claims of the present invention.

Claims

1. A steam turbine fault repair system, characterized in that: include: A mind map module is used to create a mind map of a steam turbine fault decision tree; wherein the fault decision tree represents the relationship between the steam turbine fault phenomenon and the fault cause in the form of a mind map; A template engine module, used for converting the exported data of the mind map into a rule flow recognizable by a rule engine; Data acquisition module, used to obtain turbine operation data from a database outside the system; A rule engine module, configured to infer a fault occurring in the steam turbine based on the rule flow and the operating data; Conclusion management module, used to query the inferred faults and generate corresponding fault repair plans; The mind map provides an interactive interface, in which a row of operation controls for creating a mind map and a display area for displaying the created mind map are provided, including: a control for adding a fault phenomenon node. After the user clicks the control, the system pops up a fault phenomenon editing box, allowing the user to select a fault phenomenon in the phenomenon name drop-down box to implement the addition of a fault phenomenon node; a control for adding a phenomenon node. After the user clicks the control, the system pops up a phenomenon node editing box, allowing the user to select a phenomenon in the phenomenon node drop-down box and enter a description of the phenomenon in the phenomenon node description. After clicking OK, the phenomenon node is added. After the user selects a phenomenon node, the phenomenon node is assumed to be established. A control for adding a conditional node After the user clicks the control, the system pops up the condition node edit box, allowing the user to select a turbine measuring point in the measuring point drop-down box, enter the operator in the upper or lower operator, enter the connector in the connection symbol, and enter the corresponding value in the upper or lower limit value. In this way, the syntax of the condition node a≤measuring point≤b or a≥measuring point, measuring point≥b syntax is implemented. The control for adding the conclusion node is added. After the user clicks the control, the system pops up the conclusion node edit box. When the user selects the diagnostic conclusion in the action type drop-down box, the corresponding conclusion will be displayed in the conclusion description box. The control for saving the node is used. After the user clicks the control, the system verifies that all data is complete and stores the fault decision tree in the database in the form of a rule data model. The template engine includes finding the data required for each rule from the rule data model and converting this rule data into a rule flow through a conversion template. System developers pre-develop the conversion template using the Velocity language. During compilation, the Velocity template engine arranges all the rules under the fault detection decision tree in chronological order based on the conversion template to form a rule flow. The rule flow becomes business logic after being compiled by the rule engine.

2. The system according to claim 1, wherein: The mind map module is also used to: provide an interactive interface, which is equipped with an add node control, a save node control, a compile node control and a mind map display area for creating the mind map; wherein, when the compile node control is triggered, the template engine module converts the exported data of the mind map into a rule flow recognizable by the rule engine and transmits it to the rule engine module.

3. The system according to claim 1, wherein: The conversion methods of the template engine module include: Extracting all conclusion nodes of the mind map and their corresponding paths from the exported data; For each of the paths, remove the first node, use the last node as the conclusion node, and use the remaining nodes as condition nodes; The rule flow is constructed according to the set of the conclusion node and the condition node of each path.

4. The system according to claim 1, wherein: The data acquisition module specifically includes: Real-time data management module, used to obtain real-time operating data of each measuring point of the steam turbine; A maintenance order management module is used to determine a maintenance order according to the fault phenomenon of the steam turbine and import the operating data into the maintenance order to convert the real-time operating data into fact data that can be used by the rule engine.

5. The system according to claim 1, wherein: Also includes: The data management module is used to convert the exported data of the mind map into a specific format and store it in a database, read data from the database and display it, and provide data modification and deletion functions. The specific format is the rule data model.

6. The system according to claim 1, wherein: Also includes: The maintenance plan management module is used to provide maintenance file upload, download, management, import and export services.

7. The system according to claim 1, wherein: Also includes: The basic information management module is used to provide the basic elements and management functions for making mind maps.

8. The system according to claim 1, wherein: The mind map module includes: JSMIND mind map creation tool; the template engine module includes: Velocity template engine tool; the rule engine module includes: Drools rules engine tool.

9. A method for troubleshooting a steam turbine, characterized in that: include: Creating a mind map of a steam turbine fault decision tree; wherein the fault decision tree represents the relationship between the steam turbine fault phenomenon and the fault cause in the form of a decision tree; Converting the exported data of the mind map into a rule flow recognizable by a rule engine; Obtaining steam turbine operating data; Inferring a fault occurring in the steam turbine based on the rule flow and the operating data; Display the fault and generate a corresponding fault repair plan based on it; The mind map provides an interactive interface, in which a row of operation controls for creating a mind map and a display area for displaying the created mind map are provided, including: a control for adding a fault phenomenon node. After the user clicks the control, the system pops up a fault phenomenon editing box, allowing the user to select a fault phenomenon in the phenomenon name drop-down box to implement the addition of a fault phenomenon node; a control for adding a phenomenon node. After the user clicks the control, the system pops up a phenomenon node editing box, allowing the user to select a phenomenon in the phenomenon node drop-down box and enter a description of the phenomenon in the phenomenon node description. After clicking OK, the phenomenon node is added. After the user selects a phenomenon node, the phenomenon node is assumed to be established. A control for adding a conditional node After the user clicks the control, the system pops up the condition node edit box, allowing the user to select a turbine measuring point in the measuring point drop-down box, enter the operator in the upper or lower operator, enter the connector in the connection symbol, and enter the corresponding value in the upper or lower limit value. In this way, the syntax of the condition node a≤measuring point≤b or a≥measuring point, measuring point≥b syntax is implemented. The control for adding the conclusion node is added. After the user clicks the control, the system pops up the conclusion node edit box. When the user selects the diagnostic conclusion in the action type drop-down box, the corresponding conclusion will be displayed in the conclusion description box. The control for saving the node is used. After the user clicks the control, the system verifies that all data is complete and stores the fault decision tree in the database in the form of a rule data model. The template engine includes finding the data required for each rule from the rule data model and converting this rule data into a rule flow through a conversion template. System developers pre-develop the conversion template using the Velocity language. During compilation, the Velocity template engine arranges all the rules under the fault detection decision tree in chronological order based on the conversion template to form a rule flow. The rule flow becomes business logic after being compiled by the rule engine.

10. An electronic device, characterized in that: The system is communicatively connected to a steam turbine and comprises: a steam turbine fault repair system according to any one of claims 1 to 8.

Images