Intelligent boiler system fault diagnosis method

Abstract

The invention relates to the technical field of fault diagnosis, and provides a boiler system fault intelligent diagnosis method which comprises the following steps: S1, collecting an equipment specification, a design document and a historical debugging document of a boiler system as original data; s2, cleaning, labeling and preprocessing the original data to generate a data set, and storing the data set in a database; s3, selecting an LLM model, and training the LLM model by using the data set; s4, a data interface is developed, the data interface receives and analyzes the parameters of all the sensors in real time, and abnormal parameters are recognized; s5, inputting the abnormal parameters into the trained LLM model, and generating corresponding fault description by the LLM model according to the information in the database; s6, the LLM model combines the fault description and the fault logic in the database to generate a corresponding fault cause list; and S7, the fault description and the fault reason list are displayed to a worker, and corresponding inspection steps and maintenance methods are provided at the same time.

Description

Technical Field

[0001] The invention relates to the technical field of fault diagnosis, and in particular to an intelligent fault diagnosis method for a boiler system. Background Art

[0002] In the daily operation of the boiler system, sensors of the boiler and its auxiliary equipment such as fans and water pumps monitor various key parameters such as temperature, pressure, flow, etc. to ensure stable operation of the system.

[0003] However, when the parameters reported by the sensor are abnormal (generally exceeding the set fixed limit), professionals are usually required to interpret the abnormal data and determine the possible cause of the fault, and then guide the on-site staff to conduct inspections and repairs. This process is not only time-consuming and laborious, but may also delay fault handling due to human misjudgment. Summary of the invention

[0004] In view of the defects in the prior art, the purpose of the present invention is to provide an intelligent diagnosis method for boiler system faults, which can automatically convert the abnormal parameters into an easy-to-understand fault description when the sensor parameters of the boiler system are abnormal, and further analyze the cause of the fault, thereby reminding on-site staff to conduct timely inspection and processing.

[0005] In order to achieve the above object, the present invention is implemented by the following technical solution: a boiler system fault intelligent diagnosis method, comprising the following steps:

[0006] S1. Collect equipment manuals, design documents and historical commissioning documents of the boiler system as raw data;

[0007] S2. Clean, annotate and preprocess the raw data to generate a data set, which is stored in a database;

[0008] S3, selecting an LLM model, and using the data set to train the LLM model, so that the LLM model can understand the professional terms, parameter meanings and fault logic of the boiler system;

[0009] S4. Develop a data interface that receives and analyzes the parameters of all sensors in real time and identifies abnormal parameters;

[0010] S5, inputting the abnormal parameters into the trained LLM model, and the LLM model generates a corresponding fault description according to the information in the database;

[0011] S6, the LLM model combines the fault description and the fault logic in the database to generate a corresponding fault cause list;

[0012] S7. Show the fault description and the fault cause list to the staff, and provide corresponding inspection steps and maintenance methods.

[0013] Furthermore, in step S2, after the cleaning, labeling and preprocessing of the raw data are completed, key information is extracted to generate a data set;

[0014] The key information includes equipment model, parameter range, fault description and corresponding inspection steps and maintenance methods.

[0015] Further, in step S2, the database includes a graphic database, a document database and a cloud database.

[0016] Further, in step S3, low-rank trainable weights are added to the LLM model.

[0017] Furthermore, in step S3, the retriever and the external knowledge base are integrated into the LLM model.

[0018] Furthermore, the method further comprises the following steps:

[0019] S8. Build application services based on the LLM model, wherein the application services include intelligent customer service, document generation, and code assistance.

[0020] Furthermore, the method further comprises the following steps:

[0021] S9. Develop a user-friendly interface, which includes a web interface, a mobile application, and a command line tool.

[0022] Furthermore, the method further comprises the following steps:

[0023] S10. Establish a user feedback mechanism to collect users' evaluation and suggestions on the output of the LLM model for optimizing the performance of the LLM model.

[0024] Furthermore, the method further comprises the following steps:

[0025] S11. After the LLM model training is completed, adjust the instructions of the LLM model according to business needs to make it more suitable for specific scenarios.

[0026] Beneficial effects of the present invention: The present invention provides an intelligent fault diagnosis method for a boiler system, which utilizes the equipment manual, design documents and historical debugging documents of the boiler system, combined with the LLM model, to construct a set of intelligent fault diagnosis methods. When the sensor parameters of the boiler system are abnormal, the method can automatically convert the abnormal parameters into an easy-to-understand fault description, and further analyze and generate possible causes of the fault, thereby reminding the staff to conduct inspection and processing in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic diagram of the process structure of the present invention. DETAILED DESCRIPTION

[0028] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0029] In this application, unless otherwise clearly specified and limited, the terms "connection" and "fixation" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] In the description of the present application, it should be understood that the terms "longitudinal", "lateral", "horizontal", "top", "bottom", "up", "down", "inside" and "outside" etc. indicating orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0031] In addition, the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. In the description of the present invention, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0032] like Figure 1 As shown, the present invention provides a boiler system fault intelligent diagnosis method, comprising the following steps:

[0033] S1. Collect the equipment manual, design documents and historical commissioning documents of the boiler system as the original data. The equipment manual is provided by the boiler manufacturer, which contains the cause of the failure and the corresponding inspection steps and maintenance methods. The design document is provided by the boiler design institute. The historical commissioning document is provided by the commissioning unit.

[0034] S2. Clean, label and preprocess the original data to generate a data set suitable for training large language models, which is stored in the database. The data set includes professional terms, parameter meanings and fault logic.

[0035] S3. According to the requirements, a large language model suitable for processing natural language text is selected. The present invention selects the LLM model. The LLM model is trained using the data set so that the LLM model can understand the professional terms, parameter meanings and fault logic of the boiler system.

[0036] S4. Develop an API data interface, which receives and analyzes all sensor parameters in real time and identifies abnormal parameters, allowing the boiler company's internal system or external application to interact with the LLM model through HTTP requests.

[0037] S5. The abnormal parameters are input into the trained LLM model, and the LLM model generates a corresponding fault description according to the information in the database.

[0038] S6. The LLM model combines the fault description and the fault logic in the database to generate a corresponding list of possible fault causes.

[0039] S7. Show the fault description and fault cause list to the staff, and provide corresponding inspection steps and repair methods.

[0040] The present invention utilizes the equipment manual, design documents and historical debugging documents of the boiler system, combined with the LLM model, to construct a set of intelligent fault diagnosis methods. When the sensor parameters of the boiler system are abnormal, the method can automatically convert the abnormal parameters into an easy-to-understand fault description, and further analyze and generate possible fault causes, thereby reminding the staff to conduct inspection and processing in time.

[0041] In one embodiment, in step S2, after the original data is cleaned, labeled and preprocessed, key information is extracted to generate a data set.

[0042] Key information includes equipment model, parameter range, fault description and corresponding inspection steps and repair methods, so as to improve the query efficiency and accuracy of LLM model.

[0043] In one embodiment, in step S2, the database includes a graph database, a document database, a cloud database, etc., to ensure the security and accessibility of the data.

[0044] In one embodiment, in step S3, LLM technology is used for fine-tuning to enhance or adjust the function of the LLM model by adding low-rank trainable weights to the LLM model without retraining the entire LLM model.

[0045] In one embodiment, in step S3, the retriever and the external knowledge base are integrated into the LLM model to improve the accuracy and relevance of the answers of the LLM model.

[0046] In one embodiment, the following steps are also included:

[0047] S8. Build application services based on the LLM model, including intelligent customer service, document generation and code assistance.

[0048] In one embodiment, the following steps are also included:

[0049] S9. Develop user-friendly interfaces, including web interfaces, mobile applications, and command-line tools, to facilitate user interaction with the LLM model.

[0050] In one embodiment, the following steps are also included:

[0051] S10. Establish a user feedback mechanism to collect users’ evaluation and suggestions on the output of the LLM model, so as to continuously optimize the performance and accuracy of the LLM model.

[0052] In one embodiment, the following steps are also included:

[0053] S11. After the LLM model training is completed, adjust the instructions of the LLM model according to business needs to make it more suitable for specific scenarios.

[0054] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention.

[0055] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A boiler system fault intelligent diagnosis method, characterized in that: The following steps are involved: S1. Collect equipment manuals, design documents and historical commissioning documents of the boiler system as raw data; S2. Clean, annotate and preprocess the raw data to generate a data set, which is stored in a database; S3, selecting an LLM model, and using the data set to train the LLM model, so that the LLM model can understand the professional terms, parameter meanings and fault logic of the boiler system; S4. Develop a data interface that receives and analyzes the parameters of all sensors in real time and identifies abnormal parameters; S5, inputting the abnormal parameters into the trained LLM model, and the LLM model generates a corresponding fault description according to the information in the database; S6, the LLM model combines the fault description and the fault logic in the database to generate a corresponding fault cause list; S7. Show the fault description and the fault cause list to the staff, and provide corresponding inspection steps and maintenance methods.

2. A boiler system fault intelligent diagnosis method according to claim 1, characterized in that: In step S2, after the raw data is cleaned, labeled and preprocessed, key information is extracted to generate a data set; The key information includes equipment model, parameter range, fault description and corresponding inspection steps and maintenance methods.

3. A boiler system fault intelligent diagnosis method according to claim 2, characterized in that: In step S2, the database includes a graphic database, a document database and a cloud database.

4. A boiler system fault intelligent diagnosis method according to claim 2, characterized in that: In step S3, low-rank trainable weights are added to the LLM model.

5. The intelligent diagnosis method for boiler system fault according to claim 1, characterized in that: In step S3, the retriever and the external knowledge base are integrated into the LLM model.

6. The intelligent diagnosis method for boiler system fault according to claim 1, characterized in that: The following steps are also included: S8. Build application services based on the LLM model, wherein the application services include intelligent customer service, document generation, and code assistance.

7. The intelligent diagnosis method for boiler system fault according to claim 1, characterized in that: The following steps are also included: S9. Develop a user-friendly interface, which includes a web interface, a mobile application, and a command line tool.

8. The intelligent diagnosis method for boiler system fault according to claim 1, characterized in that: The following steps are also included: S10. Establish a user feedback mechanism to collect users' evaluation and suggestions on the output of the LLM model for optimizing the performance of the LLM model.

9. The intelligent diagnosis method for boiler system fault according to claim 1, characterized in that: The following steps are also included: S11. After the LLM model training is completed, adjust the instructions of the LLM model according to business needs to make it more suitable for specific scenarios.

Images