Search

CN-122021885-A - Fault diagnosis system, method, computing device cluster, and computer-readable storage medium

CN122021885ACN 122021885 ACN122021885 ACN 122021885ACN-122021885-A

Abstract

The embodiment of the application discloses a fault diagnosis system, a fault diagnosis method, a computing device cluster and a computer readable storage medium, relating to the technical field of fault treatment; the system comprises a first interactive platform, a large model, a second interactive platform and a large model, wherein the first interactive platform is used for uploading a questioning text, the large model is used for inquiring an experience database according to input equipment data and the questioning text to obtain target experience and fault initial diagnosis information, the target experience and the fault initial diagnosis information are returned to the first interactive platform, dynamic analysis is carried out on the target experience, the equipment data and the questioning text to obtain a fault diagnosis result, the fault diagnosis result is returned to the first interactive platform, the second interactive platform is used for inputting the questioning text of the fault diagnosis result into the large model, the large model is also used for intelligently analyzing the questioning text to obtain a final diagnosis result, and the final diagnosis result is returned to the first interactive platform. Thus, the scheme can provide an interaction mechanism for the user so that the user can acquire detailed information of the fault.

Inventors

  • FENG DA

Assignees

  • 深圳TCL新技术有限公司

Dates

Publication Date
20260512
Application Date
20260114

Claims (10)

  1. 1. A fault diagnosis system, comprising: the first interaction platform is used for uploading the questioning text; the large model is used for inquiring an experience database according to input equipment data and the questioning text to obtain target experience and fault initial diagnosis information, returning the target experience and the fault initial diagnosis information to the first interactive platform, dynamically analyzing the target experience, the equipment data and the questioning text to obtain a fault diagnosis result, and returning the fault diagnosis result to the first interactive platform; the second interaction platform is used for inputting the inquiring text of the fault diagnosis result into the large model; and the large model is also used for intelligently analyzing the inquiry text to obtain a final diagnosis result and returning the final diagnosis result to the first interaction platform.
  2. 2. The system of claim 1, wherein the system further comprises a controller configured to control the controller, The large model is used for determining the uncertainty of the fault diagnosis result and automatically outputting a device information request to the second interaction platform when the uncertainty is larger than the uncertainty threshold; the second interaction platform is specifically used for requesting to input a query text of the fault diagnosis result to the large model based on the equipment information.
  3. 3. The system of claim 1, wherein the system further comprises: the database is used for storing session records; The second interaction platform inputs the additional text of the fault diagnosis result into the large model, and the method comprises the following steps: the second interactive platform inputs the challenge text after consulting the session record.
  4. 4. The system of claim 1, wherein the device data comprises a data sequence; The large model queries the experience database according to the input equipment data and the questioning text to obtain the target experience and the fault initial diagnosis information, and the method comprises the following steps: The large model performs trend analysis on the data sequence to obtain trend data, and queries the experience database based on the question text to obtain the target experience; And the large model analyzes the trend data and the equipment data according to the fault judging rule to determine the fault initial diagnosis information.
  5. 5. The system of claim 1, wherein the system further comprises: the device is used for determining the load type of the device, determining the data acquisition frequency according to the load type of the device, and acquiring the multi-mode device data according to the data acquisition frequency; The device is also used for carrying out data preprocessing on the multi-mode device data to obtain the device data, and uploading the device data to the large model.
  6. 6. The system of claim 1, wherein the first interactive platform uploading the question text comprises: the first interactive platform uploads an initial text to the large model, and uploads the questioning text with complete information according to the information supplement prompt when the large model returns the information supplement prompt; And the large model is also used for carrying out information identification on the initial text when receiving the initial text uploaded by the first interactive platform, and outputting the information supplement prompt to the first interactive platform when the information of the initial text is not complete.
  7. 7. The system of claim 1, wherein the system further comprises a controller configured to control the controller, The second interaction platform is further used for outputting feedback information of the final diagnosis result; And the large model is also used for carrying out experience summarization processing on the equipment data and the final diagnosis result based on the large model to obtain fault experience when the feedback information is characterized and recognized, and adding the fault experience into the experience database.
  8. 8. The fault diagnosis method is characterized by being applied to a fault diagnosis system, wherein the fault diagnosis system comprises a first interaction platform, a second interaction platform and a large model, and the method comprises the following steps: Acquiring equipment data and a question text uploaded by the first interactive platform; Inputting the equipment data and the questioning text into the large model to obtain target experience and fault initial diagnosis information obtained by the large model according to the equipment data and the questioning text query experience database, and returning the target experience and the fault initial diagnosis information to the first interactive platform; dynamically analyzing the target experience, the equipment data and the questioning text based on the large model to obtain a fault diagnosis result, and returning the fault diagnosis result to the first interaction platform; Acquiring a query text of the fault diagnosis result input by the second interaction platform; And carrying out intelligent analysis on the inquiry text based on the large model to obtain a final diagnosis result, and returning the final diagnosis result to the first interaction platform.
  9. 9. A cluster of computing devices, characterized in that, Including at least one computing device, each computing device including a processor and a memory; the processor is configured to execute instructions stored in the memory to cause the cluster of computing devices to perform the method of claim 8.
  10. 10. A computer-readable storage medium comprising, The computer-readable storage medium having instructions stored therein that, when executed on at least one computing device, cause the at least one computing device to perform the method of claim 8.

Description

Fault diagnosis system, method, computing device cluster, and computer-readable storage medium Technical Field The embodiment of the application relates to the technical field of fault processing, in particular to a fault diagnosis system, a fault diagnosis method, a computing device cluster and a computer readable storage medium. Background The field of equipment fault diagnosis depends on two modes of manual experience inspection and simple threshold judgment for a long time. The manual experience inspection is influenced by the professional level of operators, the misjudgment rate is high, and fault discovery is delayed due to long inspection period and manual inspection limitation. The simple threshold value judgment only depends on a single fixed value to trigger fault prompt, complex working conditions and dynamic changes of equipment operation cannot be adapted, potential hidden dangers are easily ignored, and the missing report rate is high. In the related art, the fault diagnosis of the equipment is performed by using Artificial Intelligence (AI), however, the AI usually directly outputs a fault diagnosis result aiming at the input information, so that a user is difficult to know key details such as diagnosis basis, fault logic and the like, and inconvenience is brought to subsequent fault investigation and equipment maintenance decision. Disclosure of Invention Embodiments of the present application provide a fault diagnosis system, method, computing device cluster, and computer readable storage medium, which may provide an interaction mechanism for a user to obtain detailed information of a fault. In a first aspect, an embodiment of the present application provides a fault diagnosis system, including: the first interaction platform is used for uploading the questioning text; the large model is used for inquiring an experience database according to input equipment data and the questioning text to obtain target experience and fault initial diagnosis information, returning the target experience and the fault initial diagnosis information to the first interactive platform, dynamically analyzing the target experience, the equipment data and the questioning text to obtain a fault diagnosis result, and returning the fault diagnosis result to the first interactive platform; the second interaction platform is used for inputting the inquiring text of the fault diagnosis result into the large model; and the large model is also used for intelligently analyzing the inquiry text to obtain a final diagnosis result and returning the final diagnosis result to the first interaction platform. In a second aspect, an embodiment of the present application provides a fault diagnosis method, which is applied to a fault diagnosis system, where the fault diagnosis system includes a first interaction platform, a second interaction platform, and a large model, and the method includes: Acquiring equipment data and a question text uploaded by the first interactive platform; Inputting the equipment data and the questioning text into the large model to obtain target experience and fault initial diagnosis information obtained by the large model according to the equipment data and the questioning text query experience database, and returning the target experience and the fault initial diagnosis information to the first interactive platform; dynamically analyzing the target experience, the equipment data and the questioning text based on the large model to obtain a fault diagnosis result, and returning the fault diagnosis result to the first interaction platform; Acquiring a query text of the fault diagnosis result input by the second interaction platform; And carrying out intelligent analysis on the inquiry text based on the large model to obtain a final diagnosis result, and returning the final diagnosis result to the first interaction platform. In a third aspect, an embodiment of the present application further provides a computing device cluster, including at least one computing device, each computing device including a processor and a memory, where the processor is configured to execute instructions stored in the memory, so that the computing device cluster performs the methods provided in the various alternative implementations of the embodiment of the present application. In a fourth aspect, embodiments of the present application also provide a computer-readable storage medium having instructions stored therein that, when executed on at least one computing device, cause the at least one computing device to perform the methods provided in the various alternative implementations of embodiments of the present application. In a fifth aspect, embodiments of the present application also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium an