A Quantitative Diagnosis Method and System for Shaft Faults Based on Least Confidence Rule Reasoning

By constructing a fault rule base and calculating the comprehensive credibility through the minimum credibility rule reasoning method, the problems of multi-rule conflict and uncertainty in shaft fault diagnosis are solved, and quantitative diagnosis and reliable fault assessment are realized, thereby improving the robustness and interpretability of the diagnosis.

CN123115864APending Publication Date: 2026-11-17HUANENG CHONGQING LUOWEN POWER CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611324723.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-28
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing shaft system fault diagnosis methods have limited capabilities in handling multiple rule conflicts and uncertainties, making it difficult to provide quantitative reliability. Furthermore, traditional rule-based reasoning methods do not perform well in diagnosing complex operating conditions.

Method used

The minimum confidence rule reasoning method is adopted. By constructing a rule base containing fault rules and their confidence factors, the confidence of each successfully matched rule is calculated using the minimum confidence fusion strategy. The minimum value is used as the comprehensive confidence of the fault type, and quantitative diagnostic results are output in combination with the preset diagnostic threshold.

Benefits of technology

It enables quantitative diagnosis of shaft system faults, improves the robustness and interpretability of diagnostic results, effectively handles multi-rule conflicts and measurement noise, provides clear numerical reliability, and facilitates maintenance personnel in arranging maintenance sequences.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123115864A_ABST
    Figure CN123115864A_ABST
Patent Text Reader

Abstract

This invention belongs to the field of fault diagnosis technology and relates to a quantitative diagnosis method and system for shaft system faults based on minimum confidence rule reasoning. It includes: acquiring monitoring data from key measuring points of the shaft system; constructing a fault rule library containing multiple fault rules and their corresponding confidence factors; matching the monitoring data with the fault rules in the fault rule library based on a minimum confidence reasoning mechanism, and calculating the confidence of each successfully matched rule; for each fault type, taking the minimum confidence value among all successfully matched rules that conclude as the fault type as the comprehensive confidence of that fault type; and outputting fault types and their quantitative diagnosis results for which the comprehensive confidence exceeds a preset diagnostic threshold, based on this threshold. This invention effectively solves the problems of multiple rule conflicts, inability to provide quantitative output, and weak uncertainty handling capabilities in traditional rule reasoning by introducing a minimum confidence fusion strategy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention belongs to the field of fault diagnosis technology and relates to a quantitative diagnosis method and system for shaft system faults based on minimum confidence rule reasoning. Background Technology

[0002] Shaft systems (such as steam turbine generator sets, ship propulsion shaft systems, and large compressor rotor systems) are core components of rotating machinery, and their operating status directly affects the safety and production efficiency of the entire equipment. When shaft systems experience faults such as imbalance, misalignment, rubbing, loosening, or cracks, failure to diagnose them promptly and accurately may lead to catastrophic accidents and huge economic losses.

[0003] Currently, shaft system fault diagnosis mainly relies on two methods: First, intelligent diagnostic methods based on signal processing and machine learning, such as support vector machines, neural networks, or deep learning models. While these methods offer high diagnostic accuracy, they typically require a large number of labeled fault samples for training, and the models suffer from poor interpretability, making the diagnostic process a "black box" and difficult to gain the trust of on-site maintenance personnel. Second, rule-based reasoning methods based on expert systems summarize the experience of domain experts into "IF-THEN" rules, offering advantages such as clear logic and strong interpretability. However, traditional rule-based reasoning methods have limited capabilities in handling uncertainties (such as measurement noise and conflicts between rules), typically only outputting qualitative "yes / no" conclusions, failing to provide quantitative credibility of fault occurrence and struggling to meet the needs of refined diagnosis under complex operating conditions. In particular, when multiple rules simultaneously point to different or even contradictory fault conclusions, there is a lack of effective conflict resolution and comprehensive evaluation mechanisms. Summary of the Invention

[0004] To address the problems in the existing technology, this invention provides a quantitative diagnosis method and system for shaft system faults based on minimum confidence rule reasoning. By introducing a minimum confidence fusion strategy, it effectively solves the problems of multiple rule conflicts, inability to provide quantitative output, and weak uncertainty handling capabilities in traditional rule reasoning.

[0005] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, the present invention provides a quantitative diagnosis method for shaft system faults based on minimum confidence rule reasoning, comprising the following steps: Acquire monitoring data from key measuring points in the shaft system; Construct a fault rule library containing multiple fault rules and their corresponding credibility factors; Based on the minimum confidence reasoning mechanism, the monitoring data is matched with the fault rules in the fault rule base, and the confidence of each successfully matched rule is calculated. For each fault type, the minimum confidence level among all rules that successfully match and conclude that fault type is taken as the overall confidence level for that fault type. Based on a preset diagnostic threshold, the system outputs the fault types and their quantitative diagnostic results for those with a comprehensive reliability exceeding the threshold.

[0006] Preferably, the key measuring points include shaft vibration displacement measuring points, bearing temperature measuring points, lubricating oil property measuring points, and shaft torque measuring points; the monitoring data include vibration amplitude, phase, temperature value, oil particle count, and torque fluctuation coefficient.

[0007] Preferably, each fault rule in the fault rule base includes a set of preconditions, a conclusion fault type, and a corresponding confidence factor; the set of preconditions includes one or more monitoring data feature criteria, and the monitoring data feature criteria are logically ANDed; the confidence factor is a real number in the range [0, 1], used to characterize the degree of certainty that the conclusion fault type is valid when all criteria in the set of preconditions are satisfied.

[0008] Preferably, matching the monitoring data with fault rules in the fault rule base includes: For each fault rule, the matching degree of each monitoring data feature criterion in its precondition set is calculated based on the monitoring data; If the matching degree of any monitoring data feature criterion is lower than the preset rule trigger threshold, the rule is determined to be a failure to match. If the matching degree of all monitoring data feature criteria is not lower than the rule trigger threshold, the rule is determined to be a successful match, and the minimum value of the matching degree of all monitoring data feature criteria is taken as the activation matching degree of the rule.

[0009] Preferably, the formula for calculating the credibility of each successfully matched rule is as follows:

[0010] In the formula, For the first The credibility of a successfully matched rule. For the first The activation matching degree of the rule, For the first The credibility factor of each rule.

[0011] Preferably, for each fault type, the minimum credibility among all rules that successfully match and conclude as fault type is used as the overall credibility of that fault type, including: For the same fault type If there is The following rules were successfully matched, and their credibility levels are as follows: Then the fault type Overall credibility for:

[0012] If no matching rule exists, then 0 .

[0013] Preferably, when the overall confidence level of different fault types all exceeds the diagnostic threshold, the fault type with the highest overall confidence level is output as the primary diagnostic conclusion, and the other fault types and their overall confidence levels are output at the same time.

[0014] Secondly, the present invention provides a quantitative diagnosis system for shaft system faults based on minimum confidence rule reasoning, comprising: Data acquisition module: used to acquire monitoring data of key measuring points in the shaft system; Rule building module: Used to build a fault rule library containing multiple fault rules and their corresponding credibility factors; Credibility calculation module: used to match the monitoring data with the fault rules in the fault rule base based on the minimum credibility reasoning mechanism, and calculate the credibility of each successfully matched rule; Matching module: For each fault type, the minimum confidence level of all rules that match successfully and conclude that fault type is used as the overall confidence level of that fault type. Diagnostic output module: Used to output the fault type and its quantitative diagnostic result when the overall confidence level exceeds the preset diagnostic threshold.

[0015] Thirdly, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of a method for quantitative diagnosis of shaft system faults based on least confidence rule reasoning.

[0016] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of a method for quantitative diagnosis of shaft system faults based on least confidence rule reasoning.

[0017] Compared with the prior art, the present invention has the following beneficial effects: By acquiring monitoring data from key measurement points in the shaft system, comprehensive and real-time raw information can be provided for subsequent reasoning, ensuring the authenticity and sufficiency of the diagnostic basis. By constructing a fault rule base containing multiple fault rules and their corresponding confidence factors, domain expert experience is solidified into the system in a structured and quantitative manner. This retains the good interpretability of traditional rule-based reasoning while assigning a clear uncertainty measure to each rule, facilitating flexible maintenance and expansion of the knowledge base. By matching monitoring data with the rule base based on a minimum confidence reasoning mechanism and calculating the confidence of each successfully matched rule, a quantitative conversion from continuous monitoring values ​​to discrete rule conclusions is achieved, effectively handling measurement noise and... The problem of ambiguity in the criteria boundary is addressed by using the minimum credibility of all successfully matched rules that lead to that type as the overall credibility of the fault type for each fault type. This minimum value strategy embodies the principle of prudent and conservative reasoning, automatically resolving conflicts between multiple rules and preventing over-evaluation of fault types due to inflated credibility of individual rules. Finally, based on a preset diagnostic threshold, fault types with overall credibility exceeding the threshold and their quantitative diagnostic results are output. This ensures that the diagnostic conclusion is no longer a simple "yes / no" qualitative judgment, but a quantitative output with clear numerical credibility, facilitating maintenance personnel to distinguish between primary and secondary faults based on credibility levels and to rationally arrange the maintenance sequence. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0020] 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 in this application can be combined with each other.

[0021] The following detailed description is exemplary and intended to provide 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 to which this application pertains. The terminology used in this invention is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.

[0022] The first objective of this invention is to provide a quantitative diagnosis method for shaft system faults based on minimum confidence rule reasoning, such as... Figure 1As shown, it includes the following steps: Obtain monitoring data from key measuring points in the shaft system.

[0023] Construct a fault rule library containing multiple fault rules and their corresponding credibility factors.

[0024] Based on the minimum confidence reasoning mechanism, the monitoring data is matched with the fault rules in the fault rule base, and the confidence of each successfully matched rule is calculated.

[0025] For each fault type, the minimum credibility of all rules that successfully match and conclude that fault type is taken as the overall credibility of that fault type.

[0026] Based on a preset diagnostic threshold, the system outputs the fault types and their quantitative diagnostic results for those with a comprehensive reliability exceeding the threshold.

[0027] This method acquires real-time monitoring data using sensors installed at key locations in the shaft system. It then constructs a rule base containing several fault rules and their corresponding confidence factors. Each rule consists of a set of preconditions and a conclusion about the fault type. The confidence factor is pre-set in the [0,1] range by domain experts based on experience or historical statistical data to characterize the certainty of the rule's conclusion. Based on this, using a minimum confidence reasoning mechanism, the current monitoring data is matched one by one with the rules in the rule base. For each successfully matched rule, the activation matching degree is calculated based on the degree to which each criterion in its preconditions is satisfied, and multiplied by the rule's confidence factor. The reliability factor yields the reliability of the rule. Next, for the same fault type, the minimum reliability among all rules that point to and match that type is taken as the overall reliability of the fault type. This method of taking the minimum value reflects a prudent diagnostic logic, that is, a higher overall evaluation is given only when all evidence supporting the fault reaches a sufficiently reliable level. Finally, the overall reliability of each fault type is compared with a preset diagnostic threshold, and all fault types that exceed the threshold and their specific reliability values ​​are output. When multiple faults exceed the threshold at the same time, the one with the highest overall reliability is output as the primary diagnostic conclusion, along with the remaining possible faults.

[0028] The above method makes full use of the expert knowledge and experience rules accumulated in the field of shaft system fault diagnosis over a long period of time. By introducing the minimum confidence fusion strategy, it can effectively handle multi-rule conflicts and measurement uncertainties, and avoid the problem of conclusion deviation caused by mismatch of individual rules in traditional rule reasoning, thereby significantly improving the robustness and engineering credibility of the diagnostic results.

[0029] The key measuring points include shaft vibration displacement measuring points, bearing temperature measuring points, lubricating oil property measuring points, and shaft torque measuring points. The monitoring data includes vibration amplitude, phase, temperature value, oil particle count, and torque fluctuation coefficient. Specifically, eddy current displacement sensors are installed at each bearing housing across the shaft to obtain vibration displacement signals, thereby extracting vibration amplitude and phase information. Platinum resistance temperature sensors are arranged on the bearing pads and return oil lines of each bearing set to continuously monitor bearing temperature. Samples are taken from the main return oil line of the lubrication system, and an online particle counter is used to analyze oil properties, obtaining oil particle count data including wear particle count and particle size distribution. At the same time, a torque meter is installed at the input or output end of the shaft to measure instantaneous torque fluctuation, and then the torque fluctuation coefficient is calculated.

[0030] For example, each fault rule in the fault rule base includes a set of preconditions, a conclusion fault type, and a corresponding confidence factor. The set of preconditions includes one or more monitoring data feature criteria, and the monitoring data feature criteria are logically ANDed. That is, in actual engineering, the occurrence of a specific fault often requires multiple feature parameters to meet abnormal conditions simultaneously to confirm it. For example, imbalance faults usually require the vibration amplitude to exceed the limit and the phase to be stable, while a large vibration amplitude alone is not enough to determine imbalance. Therefore, the logical AND relationship ensures the necessary and sufficient conditions for rule triggering. The confidence factor is a real number in the range [0, 1], which is pre-assigned by domain experts based on empirical statistics or historical fault sample analysis. It is used to quantitatively characterize the degree of confidence that the conclusion fault type is valid when all criteria in the current precondition set are strictly met. 0 represents no confidence, 1 represents absolute confidence, and the intermediate value reflects the confidence difference of different rule conclusions.

[0031] For example, matching the monitoring data with fault rules in the fault rule base includes: For each fault rule, the matching degree of each monitoring data feature criterion in its precondition set is calculated based on the monitoring data. The matching degree reflects the degree to which the actual measured value meets the abnormal range defined by the criterion. For example, the matching degree is 1 when the vibration amplitude exceeds the set threshold and 0 when it is completely normal. Intermediate states can be interpolated by linear or fuzzy membership functions. This is because the measured values ​​in shaft fault diagnosis often contain noise and fluctuations. If the matching degree of any monitoring data feature criterion is lower than the preset rule trigger threshold (usually a small positive number, such as 0.3 or 0.5, is used to filter out accidental fluctuations caused by measurement disturbances), the rule is judged to have failed to match. This means that at least one key feature in the preconditions has failed to reach the minimum confidence level sufficient to trigger the rule. According to the nature of logical AND relations, the conditions of the entire rule are not met. Conversely, if the matching degree of all monitoring data feature criteria is not lower than the rule trigger threshold, the rule is determined to be a successful match, and the minimum value of the matching degree of all monitoring data feature criteria is taken as the activation matching degree of the rule.

[0032] The above matching strategy avoids the mis-triggering of rules due to slight overshooting or transient disturbances of a single criterion, thus improving the system's anti-interference capability. On the other hand, using the minimum value as the activation matching degree provides a conservative and robust basis for the subsequent calculation of rule credibility, effectively suppressing the unreasonable increase in overall credibility due to excessively high matching of individual criteria. This makes the final output of quantitative fault diagnosis results closer to engineering practice, with good robustness and practical engineering value.

[0033] For example, the formula for calculating the credibility of each successfully matched rule is as follows:

[0034] In the formula, For the first The credibility of a successfully matched rule; For the first The activation matching degree of a rule represents the overall degree to which the current monitoring data satisfies the set of preconditions for that rule; For the first The credibility factor of a rule represents the degree of confidence in the conclusion of the rule based on expert experience.

[0035] For example, for each fault type, the minimum credibility among all rules that successfully match and conclude that fault type is used as the overall credibility of that fault type, including: For the same fault type If there is The following rules were successfully matched, and their credibility levels are as follows: Then the fault type Overall credibility for:

[0036] If no matching rule exists, then 0 .

[0037] In practical engineering, the same fault type can often be described by multiple different rules from different feature perspectives. For example, an imbalance fault may be supported by multiple rules such as "vibration amplitude exceeds the standard and phase is stable" and "vibration is sensitive to changes in rotational speed." The credibility of each rule represents the degree of certainty about the fault from its respective feature dimension. Only when all independent evidence pointing to the fault reaches a sufficiently credible level can the fault conclusion be considered reliable. If the credibility of any rule is low, it indicates that the fault has not been fully confirmed in a certain key feature. According to the weakest link principle in logical reasoning, the overall credibility should not be higher than the weakest piece of evidence. Using the minimum value as the comprehensive credibility can effectively suppress the phenomenon of inflated credibility caused by the accidental fulfillment of the preconditions of individual rules or noise interference, and avoid the system making an overly optimistic erroneous judgment about a certain fault type. At the same time, this strategy naturally has the ability to resolve conflicts. When different rules point to the same fault but have large differences in credibility, the minimum value directly reflects the weak link in the evidence chain, prompting maintenance personnel to further verify the reliability of the corresponding measurement points or rules.

[0038] For example, when the overall confidence level of different fault types all exceeds the diagnostic threshold, the fault type with the highest overall confidence level is output as the primary diagnostic conclusion, while the remaining fault types and their overall confidence levels are also output. In complex actual operating conditions, rotating machinery shaft systems may experience multiple concurrent faults, such as imbalance and bearing loosening occurring simultaneously, or a dominant fault triggering other secondary faults. In such cases, outputting only the single conclusion with the highest confidence level could easily lead maintenance personnel to overlook potential or accompanying faults, resulting in incomplete diagnostic information or even misjudgments. By simultaneously outputting all fault types exceeding the diagnostic threshold and their confidence levels, and clearly distinguishing the primary conclusion from other possible faults, this method highlights the most likely faults to guide priority handling while retaining other auxiliary information for comprehensive judgment.

[0039] A second objective of this invention is to provide a quantitative diagnostic system for shaft system faults based on minimum confidence rule reasoning, comprising: Data acquisition module: used to acquire monitoring data of key measuring points in the shaft system; Rule building module: Used to build a fault rule library containing multiple fault rules and their corresponding credibility factors; Credibility calculation module: used to match the monitoring data with the fault rules in the fault rule base based on the minimum credibility reasoning mechanism, and calculate the credibility of each successfully matched rule; Matching module: For each fault type, the minimum confidence level of all rules that match successfully and conclude that fault type is used as the overall confidence level of that fault type. Diagnostic output module: Used to output the fault type and its quantitative diagnostic result when the overall confidence level exceeds the preset diagnostic threshold.

[0040] The system acquires key measurement data such as shaft vibration, temperature, oil, and torque in real time through the data acquisition module, ensuring the comprehensiveness and timeliness of the input information. The rule construction module transforms the experience of domain experts into a structured rule base with credibility factors, giving the system good interpretability and knowledge scalability. The credibility calculation module is based on the minimum credibility reasoning mechanism. By calculating the product of the activation matching degree and credibility factor of each successfully matched rule, it effectively integrates the fuzziness of the monitoring data and the uncertainty of the rules themselves. The matching module takes the minimum credibility of all successfully matched rules for the same fault type as the comprehensive credibility, strictly following the conservative reasoning principle of "the weakest link determines the overall credibility" in the field of fault diagnosis, which significantly improves the robustness and anti-interference ability of the diagnostic results. The diagnostic output module filters and outputs all fault types that exceed the threshold and their quantitative credibility according to the preset threshold. It prioritizes the primary conclusion with the highest credibility and presents other possible faults at the same time, avoiding the drawbacks of traditional systems with single conclusions or information truncation.

[0041] In one embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions from the computer storage medium to achieve a corresponding method flow or function. The processor described in this embodiment of the present invention can be used for the operation of a quantitative diagnosis method for shaft system faults based on least confidence rule reasoning.

[0042] This invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the shaft fault quantitative diagnosis method based on minimum confidence rule reasoning in the above embodiments.

[0043] 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.

[0044] 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 device that provides the functions specified in one or more boxes.

[0045] 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 instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0046] 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.

[0047] 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 quantitative diagnosis method for shaft system faults based on minimum confidence rule reasoning, characterized in that, Includes the following steps: Acquire monitoring data from key measuring points in the shaft system; Construct a fault rule library containing multiple fault rules and their corresponding credibility factors; Based on the minimum confidence reasoning mechanism, the monitoring data is matched with the fault rules in the fault rule base, and the confidence of each successfully matched rule is calculated. For each fault type, the minimum confidence level among all rules that successfully match and conclude that fault type is taken as the overall confidence level for that fault type. Based on a preset diagnostic threshold, the system outputs the fault types and their quantitative diagnostic results for those with a comprehensive reliability exceeding the threshold.

2. The quantitative diagnosis method for shaft system faults based on minimum confidence rule reasoning according to claim 1, characterized in that, The key measuring points include shaft vibration displacement measuring points, bearing temperature measuring points, lubricating oil property measuring points, and shaft torque measuring points; the monitoring data include vibration amplitude, phase, temperature value, oil particle count, and torque fluctuation coefficient.

3. The quantitative diagnosis method for shaft system faults based on minimum confidence rule reasoning according to claim 1, characterized in that, Each fault rule in the fault rule base includes a set of preconditions, a conclusion fault type, and a corresponding confidence factor. The set of preconditions includes one or more monitoring data feature criteria, and the monitoring data feature criteria are logically ANDed with each other. The confidence factor is a real number in the range [0, 1], used to characterize the degree of certainty that the conclusion fault type is valid when all criteria in the set of preconditions are satisfied.

4. The quantitative diagnosis method for shaft system faults based on minimum confidence rule reasoning according to claim 3, characterized in that, The step of matching the monitoring data with the fault rules in the fault rule base includes: For each fault rule, the matching degree of each monitoring data feature criterion in its precondition set is calculated based on the monitoring data; If the matching degree of any monitoring data feature criterion is lower than the preset rule trigger threshold, the rule is determined to be a failure to match. If the matching degree of all monitoring data feature criteria is not lower than the rule trigger threshold, the rule is determined to be a successful match, and the minimum value of the matching degree of all monitoring data feature criteria is taken as the activation matching degree of the rule.

5. The quantitative diagnosis method for shaft system faults based on minimum confidence rule reasoning according to claim 4, characterized in that, The formula for calculating the credibility of each successfully matched rule is as follows: In the formula, For the first The credibility of a successfully matched rule. For the first The activation matching degree of the rule, For the first The credibility factor of each rule.

6. The quantitative diagnosis method for shaft system faults based on minimum confidence rule reasoning according to claim 5, characterized in that, For each fault type, the minimum credibility among all rules that successfully match and conclude that fault type is used as the overall credibility for that fault type, including: For the same fault type If there is The following rules were successfully matched, and their credibility levels are as follows: Then the fault type Overall credibility for: If no matching rule exists, then 0 .

7. The quantitative diagnosis method for shaft system faults based on minimum confidence rule reasoning according to claim 6, characterized in that, When the overall confidence level of different fault types exceeds the diagnostic threshold, the fault type with the highest overall confidence level is output as the primary diagnostic conclusion, and the other fault types and their overall confidence levels are output at the same time.

8. A quantitative diagnosis system for shaft system faults based on minimum confidence rule reasoning, characterized in that, include: Data acquisition module: used to acquire monitoring data of key measuring points in the shaft system; Rule building module: Used to build a fault rule library containing multiple fault rules and their corresponding credibility factors; Credibility calculation module: used to match the monitoring data with the fault rules in the fault rule base based on the minimum credibility reasoning mechanism, and calculate the credibility of each successfully matched rule; Matching module: For each fault type, the minimum confidence level of all rules that match successfully and conclude that fault type is used as the overall confidence level of that fault type. Diagnostic output module: Used to output the fault types and their quantitative diagnostic results that have a comprehensive confidence level exceeding the preset diagnostic threshold.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-7.