A belt scale measurement result credibility intelligent diagnosis and interpretation system

Abstract

This invention relates to the field of belt scale metering and discloses an intelligent diagnostic and interpretation system for the reliability of belt scale metering results, used for diagnostic and analysis scenarios after belt scale metering results are generated. The system includes, after the metering results are generated, acquiring a multi-source evidence set through an evidence aggregation module, comprising current and historical metering results, operating condition information, unit status, verification status, and abnormal events, conducting a comprehensive evaluation, and having a factor interpretation module identify the main factors affecting reliability, forming structured interpretation information, generating a graded diagnostic conclusion, and outputting a complete report including reliability level, risk source, result referenceability, and usage recommendations. This invention solves the problems of existing technologies having single judgment criteria, lack of interpretive capabilities, and insufficient accuracy in assessments under complex operating conditions, significantly improving the understandability, referenceability, and practical application value of belt scale metering results in industrial production.

Description

Technical Field

[0001] This invention relates to the field of belt scale measurement, and in particular to an intelligent diagnostic and interpretation system for the reliability of belt scale measurement results. Background Technology

[0002] In existing technologies, the processing of belt scale measurement results mainly includes technologies for result display and alarm, technologies for measurement result error analysis and result evaluation, technologies for industrial intelligent diagnosis and result assessment, and technologies for result usage suggestions and decision support. In current operating scenarios, the measurement results continuously generated by the system are typically used for production statistics, operation monitoring, and other similar purposes.

[0003] However, considering the problem that this invention aims to solve, the existing technology has the following main shortcomings: The basis for judging the credibility of the results is singular and lacks comprehensiveness: existing solutions usually focus more on the result value itself or simple statistical characteristics, and lack a mechanism to comprehensively incorporate operating condition information, unit status information, historical result information, verification-related information and abnormal event information into the credibility judgment.

[0004] Lack of interpretable output capability for the credibility of results: Even if existing technologies can provide anomaly alerts, they usually lack the ability to interpret the main factors affecting credibility, sources of risk, and diagnostic criteria, making the results difficult to understand and trust.

[0005] Lack of intelligent evaluation capabilities in multi-factor coupled scenarios: In complex working conditions, single threshold judgment or simple rule judgment is difficult to accurately reflect the true degree of credibility, which can easily lead to misjudgment, omission, or insufficient interpretation.

[0006] There is a lack of a complete chain from result judgment to result usage recommendations: Existing technologies often remain at the level of normal / abnormal judgment, lacking the ability to further develop a complete output that includes the degree of reference of the result, result usage recommendations, and risk warnings.

[0007] Lack of ability to record and trace the evolution of result credibility: Existing solutions lack a mechanism to continuously record the evolution of result credibility and influencing factors, making it difficult to support subsequent review and analysis.

[0008] Therefore, we propose an intelligent diagnostic and interpretation system for the reliability of belt scale measurement results to solve the above problems. Summary of the Invention

[0009] This invention provides an intelligent diagnostic and interpretation system for the reliability of belt scale measurement results, which is used for diagnostic and analysis scenarios after the belt scale measurement results are generated.

[0010] The first aspect of this invention provides an intelligent diagnostic and interpretation system for the reliability of belt scale measurement results. The system includes: a result input and evidence aggregation module, used to acquire the current measurement result and multi-source evidence information related to the current measurement result after the belt scale measurement result is formed; the multi-source evidence information includes at least operating condition information, unit status information, historical result information, verification-related information, and abnormal event information; a result diagnosis input set is formed by aggregating the current measurement result and the multi-source evidence information; a reliability intelligent evaluation module, connected to the result input and evidence aggregation module, used to receive the original input source output by the result input and evidence aggregation module, i.e., the result diagnosis input set; a comprehensive evaluation of the reliability of the current measurement result based on the result diagnosis input set; and a reliability evaluation result is formed after the evaluation; and an influencing factor interpretation module, connected to the reliability intelligent evaluation module, used to receive the reliability evaluation result output by the reliability intelligent evaluation module and acquire the original input source, i.e., the result diagnosis input set; and an identification of factors affecting the current measurement result based on the reliability evaluation result and the multi-source evidence information in the result diagnosis input set. The system comprises the following modules: a main factor for measuring the reliability of the measurement result; identification and interpretation of influencing factors; a result classification and diagnosis module connected to the influencing factor interpretation module; receiving the reliability assessment result output by the reliability intelligent assessment module and the influencing factor interpretation result output by the influencing factor interpretation module; diagnosing and judging the current measurement result based on the aforementioned reliability assessment result and influencing factor interpretation result; forming a reliability level or diagnostic level conclusion after judgment; a result interpretation and suggestion output module connected to the reliability intelligent assessment module, the influencing factor interpretation module, and the result classification and diagnosis module; receiving the reliability assessment result, the influencing factor interpretation result, and the reliability level or diagnostic level conclusion; combining the received results and conclusions, outputting at least one of the following information corresponding to the current measurement result: a reliability conclusion, an explanation of influencing factors, a degree of reference for the result, and a suggestion for the use of the result; and a history record and traceability module connected to the result interpretation and suggestion output module; acquiring and recording the process of reliability change, influencing factor change, and diagnostic conclusion change of the current measurement result formed during the execution of the above modules; forming a traceable record after recording.

[0011] Optionally, in a first implementation of the first aspect of the present invention, the credibility intelligent assessment module is specifically used to: use at least one of rule assessment, statistical assessment, pattern recognition assessment or model assessment, combined with the numerical value, fluctuation characteristics and continuity of the current measurement result, to judge the credibility of the current measurement result; the credibility assessment result includes at least one of credibility assessment value, credibility level or credibility category.

[0012] Optionally, in a second implementation of the first aspect of the present invention, the main factors affecting the reliability of the current measurement result identified by the influencing factor interpretation module include at least one of the following: operating condition fluctuation factors, unit state abnormality factors, historical result deviation factors, verification state related factors, and communication or state instability factors; the influencing factor interpretation result includes at least one of the following: main influencing factor category, influence direction, influence degree, and risk source description.

[0013] Optionally, in a third implementation of the first aspect of the present invention, the confidence level or diagnostic level conclusion formed by the result grading and diagnosis module includes: highly reliable, referable, requires attention, low reliable, or not recommended for direct use.

[0014] Optionally, in the fourth implementation of the first aspect of the present invention, the result usage suggestions output by the result interpretation and suggestion output module include at least one of the following: can be directly referenced, suggested in combination with historical results, suggested for manual review, not suggested as a direct control basis, or suggested to pay attention to relevant risk factors.

[0015] Optionally, in the fifth implementation of the first aspect of the present invention, there is a linkage analysis relationship between the modules in the system. Specifically, when the result classification diagnosis module forms a diagnosis level conclusion that needs attention or is of low confidence, the influencing factor interpretation module is triggered to further identify the main factors that lead to the decrease in confidence. The result interpretation and suggestion output module synchronously outputs suggestions for manual review or recommendations not to use the main factors as a basis for direct control.

[0016] A second aspect of this invention provides an intelligent diagnostic and interpretation method for the reliability of belt scale measurement results, comprising the following steps: after the belt scale measurement result is formed, acquiring the current measurement result and multi-source evidence information related to the current measurement result; converging the current measurement result and the multi-source evidence information to form a result diagnostic input set, wherein the multi-source evidence information includes at least operating condition information, unit status information, historical result information, verification-related information, and abnormal event information; based on the result diagnostic input set, comprehensively evaluating the reliability of the current measurement result to form a reliability evaluation result; and based on the reliability evaluation result and the multi-source evidence information in the result diagnostic input set... Evidence information is used to identify the main factors affecting the credibility of the current measurement result and form an explanation of the influencing factors; based on the credibility assessment result and the explanation of the influencing factors, the current measurement result is diagnosed and judged to form a credibility level or diagnostic level conclusion; combining the credibility assessment result, the explanation of the influencing factors, and the credibility level or diagnostic level conclusion, at least one of the following information corresponding to the current measurement result is output: credibility conclusion, explanation of influencing factors, degree of reference of the result, and suggestions for use of the result; and the process of change in the credibility of the current measurement result, the process of change in influencing factors, and the process of change in the diagnostic conclusion are recorded to form a traceable record.

[0017] Optionally, in the first implementation of the second aspect of the present invention, a comprehensive evaluation of the reliability of the current measurement result is performed, specifically including: using at least one of rule evaluation, statistical evaluation, pattern recognition evaluation, or model evaluation, and combining the numerical value, fluctuation characteristics, and continuity of the current measurement result for judgment; identifying the main factors affecting the reliability of the current measurement result, specifically including: identifying at least one of the following: operating condition fluctuation factors, unit state abnormality factors, historical result deviation factors, verification state related factors, and communication or state instability factors.

[0018] Optionally, in a second implementation of the second aspect of the present invention, when outputting information corresponding to the current measurement result: when the formed confidence level or diagnostic level conclusion is of concern or low confidence, the output description of influencing factors includes specific risk sources that lead to a decrease in confidence, and the output results usage suggestions include suggestions to combine with historical results for reference, suggestions to manually review, or not to use as a direct control basis.

[0019] A third aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the above-described intelligent diagnosis and interpretation system for the reliability of belt scale measurement results.

[0020] The mechanism of this invention is as follows: Instead of making a single-point judgment based solely on the result value itself, an intelligent analysis mechanism oriented towards multi-source evidence is introduced into the result diagnosis framework, enabling the system to comprehensively diagnose the reliability of the result based on the current measurement result, historical result information, operating condition information, unit status information, verification-related information, and abnormal event information, and generate an interpretable output. Beneficial effects: A framework for intelligent diagnosis and interpretation of the reliability of belt scale measurement results has been established. This invention no longer simply displays or scores the measurement results, but forms an integrated diagnostic system after the results are generated through multi-source evidence fusion, reliability assessment, interpretation of influencing factors, hierarchical diagnosis, and suggestion output.

[0021] By introducing a multi-source evidence comprehensive analysis mechanism, and combining information such as working conditions and status for a comprehensive judgment, the misjudgment and omission caused by single-rule judgment are reduced.

[0022] It not only outputs the credibility conclusions of the results, but also identifies and outputs the main factors that affect the credibility of the current results, enabling users to understand the reasons behind the results and enhance their confidence in using the product.

[0023] Based on the diagnostic conclusions and influencing factors, it can further output the reference value of the results and usage suggestions, providing practical support for subsequent manual judgment, business use and decision-making reference.

[0024] The system can continuously record the changes in the reliability of results, influencing factors, and diagnostic conclusions, which facilitates subsequent review analysis, anomaly analysis, and strategy optimization.

[0025] By introducing artificial intelligence or intelligent analysis mechanisms, the system can better adapt to complex working conditions, dynamic disturbances, and scenarios involving multiple coupled factors, thereby improving the stability and practicality of the diagnostic results. Attached Figure Description

[0026] Figure 1 This is a block diagram of the overall structure of the intelligent diagnosis and interpretation system for the reliability of belt scale measurement results of the present invention.

[0027] Figure 2 This is a flowchart for the reliability diagnosis and interpretation of the measurement results of the belt scale of the present invention.

[0028] Figure 3 This is a schematic diagram illustrating the intelligent analysis relationship of the credibility of metrological results based on multi-source evidence in this invention.

[0029] Figure 4 This is a schematic diagram of the interpretation chain for the reliability of the measurement results of this invention. Detailed Implementation

[0030] This invention provides an intelligent diagnostic and interpretation system for the reliability of belt scale measurement results, used in diagnostic and analysis scenarios after belt scale measurement results are generated. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0031] This invention provides an intelligent diagnostic and interpretation system for the reliability of belt scale measurement results. It is applied to the diagnosis and analysis of belt scale measurement results after they are generated. It is used to comprehensively evaluate the reliability of the current measurement results and identify and interpret the factors that affect the reliability of the results, thereby generating a reliability diagnosis conclusion, interpretation information, and results usage suggestions.

[0032] In one specific implementation, the system includes at least: a result input and evidence aggregation module, a credibility intelligent assessment module, an influencing factor interpretation module, a result grading and diagnosis module, a result interpretation and suggestion output module, and a history record and traceability module. These modules can be deployed in the same controller, host computer, or industrial computing unit, or they can be distributed across multiple functional units for collaborative implementation.

[0033] The results input and evidence aggregation module is used to obtain the current measurement results and multi-source evidence information related to the measurement results, and form a set of results diagnosis inputs.

[0034] In one implementation, multi-source evidence information may include, but is not limited to: current measurement result information; historical measurement result information; operating condition related information; unit status related information; verification related information; abnormal event related information; and other auxiliary information related to the reliability of the results.

[0035] In this invention, the focus of the result input and evidence aggregation module is not on regenerating the measurement results, but on aggregating the relevant evidence information after the results are formed, so that subsequent credibility diagnosis and interpretation are based on multi-source evidence, rather than relying solely on a single result value.

[0036] It should be noted that the No. 1 coal feeder main belt scale at a thermal power plant has just completed a time slice measurement, generating the current instantaneous flow rate and cumulative results. At this time, the result input and evidence aggregation module is automatically triggered, pulling relevant evidence data from various interfaces to form the following multi-source evidence information table: Although the current instantaneous flow rate (825.5 t / h) seems like a perfectly reasonable and within-range value, the result input and evidence aggregation module did not simply record this number. It extracted all dimensions from the table—including the slight deviation of sensor #2, the low belt tension, the objective fact that the physical calibration cycle was approaching, and the transient anomaly alarm from 8 minutes ago.

[0037] These aligned and structured multi-source data together form the result diagnostic input set for this study, and are fully pushed to the downstream intelligent credibility assessment module, thereby ensuring that the subsequent diagnosis is not a blind single-point threshold alarm, but a three-dimensional assessment based on comprehensive on-site evidence.

[0038] The credibility intelligent assessment module is used to comprehensively assess the credibility of the current measurement results based on the result diagnosis input set, and form a credibility assessment result.

[0039] In one implementation, the reliability intelligent assessment module can combine the current result value, result fluctuation characteristics, result continuity, operating condition, unit status, historical result trends, verification-related information, and abnormal event information to form a comprehensive reliability judgment on the current measurement result.

[0040] Credibility assessment results may include, but are not limited to: credibility assessment value; credibility level; credibility category; and credibility trend.

[0041] In this invention, the credibility intelligent assessment module is not limited to fixed threshold judgment or a single scoring method. Instead, it enables the system to more comprehensively judge the credibility of the current measurement results by comprehensively analyzing multi-source evidence.

[0042] In a preferred embodiment, the credibility intelligent assessment can be implemented by rule assessment, statistical assessment, pattern recognition assessment, model assessment, or a combination thereof, but the present invention is not limited to a specific implementation method.

[0043] It should be noted that during the data aggregation phase, the module received the current diagnostic input set from the No. 1 coal feeder main belt scale of a thermal power plant. The current instantaneous flow rate is displayed as 825.5 tons / hour. The system sets the initial basic reliability score for this diagnosis to a maximum of 100 points and begins multi-source linkage assessment. The intelligent reliability assessment process table is as follows: In this assessment, although the measurement result of 825.5 tons / hour itself is not abnormal, after multi-dimensional linkage verification by the assessment module, the system determined that the reliability of this measurement result has hidden risks due to the coupling effect of sensor deviation, insufficient tension, and the near-term calibration and recent fluctuations.

[0044] Based on the above logic, the system performs overall calculations and arrives at a final credibility score of 75 points (100-12-5-8) for this measurement period. Subsequently, the module officially outputs the **credibility assessment result**, which includes a quantitative assessment value (75 points), a mapped credibility level (credibility judgment: requires attention), and a trend label indicating that the credibility is in a downward decay trend. The system then prepares to transfer the complete assessment product to downstream modules for further interpretation.

[0045] The influencing factors explanation module is used to identify the main factors affecting the credibility of the current measurement results based on the credibility assessment results and multi-source evidence information, and to generate corresponding explanatory information.

[0046] In one implementation, the influencing factor explanation module can identify at least one of the following factors: Factors related to operating condition fluctuations; factors related to abnormal unit status; factors related to deviations in historical results; factors related to verification status; factors related to abnormal events; factors related to communication or unstable status; and other factors related to changes in the reliability of results.

[0047] Explanatory information may include, but is not limited to: categories of major influencing factors; direction of influence; degree of influence; explanation of the source of risk; and explanatory warning information.

[0048] In this invention, the focus of the influencing factor explanation module is not to simply explain the abnormality of the result, but to form a structured explanation of the reasons for the change in the credibility of the result, so that the system can answer why the result is judged as highly credible, referable, or low credible.

[0049] It should be noted that, regarding the current metering result of 825.5 tons / hour for the main conveyor belt scale of coal feed into furnace No. 1, the upstream reliability intelligent assessment module has already concluded 75 points (assessment level: requiring attention). At this point, the influencing factor explanation module is activated, extracting the underlying evidence that led to this 25-point deduction and transforming it into structured explanatory information. Structured Explanation Table of Influencing Factors: In this embodiment, the module does not output obscure sensor millivolt voltage differences or underlying system alarm codes to the user. Instead, it summarizes and refines the sensor's deviation and insufficient tension as abnormal factors of the unit state, and clearly points out the physical consequences that they may bring about nonlinear errors; it interprets the objective fact of 55 days without calibration as the risk of accumulated zero-point drift.

[0050] Through this step, the module successfully transforms multi-dimensional, scattered data into white-box interpretable results with clear categories, directions, degrees, and descriptions. Finally, the module packages the structured information within this table and passes it to the downstream result interpretation and suggestion output module. This enables the system, when finally presenting diagnostic reports to operators, not only to highlight areas requiring attention but also to clearly explain why the system issued the warning, thus truly achieving interpretable results.

[0051] The results grading and diagnostic module is used to form a confidence level or diagnostic level conclusion for the current measurement results based on the confidence assessment results and the interpretation results of influencing factors.

[0052] In one implementation, the diagnostic level may include, but is not limited to: high confidence; referable; require attention; low confidence; not recommended for direct use.

[0053] In this invention, the result grading and diagnosis module aims to move beyond simple trust / untrustworthiness judgments in result diagnosis, and instead generate grading and diagnosis conclusions that are more suitable for engineering use and management decisions.

[0054] It should be noted that the operating scenario of the No. 1 coal feeder main belt scale continues. At this time, the result grading and diagnosis module simultaneously receives two core inputs from upstream: first, the comprehensive evaluation score is 75 points; second, the interpretation module identifies three specific risk factors (including one unit state anomaly - significant impact). The module immediately retrieves the built-in grading decision matrix for comprehensive grading, resulting in the measurement result grading and diagnosis decision table: In the system execution of this embodiment, if only the conventional absolute value of 75 points is used for a one-size-fits-all approach, the result may be classified by the system as a barely passing, ordinary state. However, the intelligence of this graded diagnosis module lies in its integration of a conditional degradation mechanism based on risk factors.

[0055] During rule verification, the module discovered that the upstream input explanation clearly included a negative factor classified as significant (i.e., the output deviation between the two sets of sensors reached 5% and the tension was too low). According to the composite judgment rules in the decision table, even though the base score was still 75 points, because the red line condition of abnormal equipment status was triggered, the module would directly lock the diagnostic level of this measurement result as **needs attention**.

[0056] Subsequently, the module formally establishes the diagnostic level conclusion based on this standard and transmits it to the downstream result interpretation and recommendation output module. This grading method, which integrates quantitative scoring with qualitative risk, ensures that the diagnostic conclusion is rigorous and reliable, effectively avoiding the omission of high-risk hidden dangers caused by relying solely on scores.

[0057] The results interpretation and recommendation output module is used to output at least one of the following: reliability diagnosis conclusion, interpretation information, reference level, and results usage recommendations corresponding to the current measurement results.

[0058] In one implementation, the output may include, but is not limited to: the current result's credibility level; the main influencing factors of the current result; the risk source category; the degree of reference value of the result; suggestions for using the result; and prompts for manual review.

[0059] In one implementation, the recommendations for using the results may include, but are not limited to: direct reference; reference in conjunction with historical results; manual review; not recommended as a direct control basis; and attention to relevant risk factors.

[0060] In this invention, the key point of the result interpretation and suggestion output module is to explain why the result is credible or unreliable while outputting the credibility conclusion, and to provide corresponding usage suggestions, thereby improving the comprehensibility and practical value of the result.

[0061] It should be noted that this continues the operational diagnostic scenario of the No. 1 coal feeder main belt scale. At this point, the upstream result classification diagnostic module has already provided clear conclusions requiring attention, and the influencing factor explanation module has also delivered qualitative analysis regarding sensor deviation, insufficient tension, and near-term calibration. Upon receiving this packaged information, this module immediately triggers the corresponding output template, generating an intelligent diagnostic report of the current measurement results on the operator workstation (or the MES system push terminal). The intelligent diagnostic and suggestion output report table for belt scale measurement results is as follows: In a traditional system, the screen would only display a cold, impersonal 825.5 t / h or flash a generic yellow alarm light, discouraging operators from taking action. This module, however, translates complex internal logic into intuitive business language, recognizing the hardware risk of sensor deviation. Therefore, its usage recommendations precisely state the safety limitations of not using it as a direct feedforward signal to the DCS, while also providing alternative solutions based on historical average data and maintenance suggestions focusing on the tensioning device. This transforms monotonous metering figures into a highly interpretable and valuable decision-making aid.

[0062] The history and traceability module is used to record the process of changes in the reliability of results, changes in influencing factors, and changes in diagnostic conclusions, in order to form a traceable record.

[0063] In one implementation, the recorded content may include, but is not limited to: the process of changes in credibility level; the process of changes in influencing factors; the process of changes in risk sources; the process of changes in diagnostic conclusions; the process of changes in recommendations for the use of results; and time series information on the diagnosis of results.

[0064] In this invention, the focus of the historical record and traceability module is not simply to leave traces, but to provide a continuous basis for subsequent review analysis, manual verification, strategy optimization and system iteration.

[0065] It should be noted that after the upstream result interpretation and suggestion output module generates a diagnostic report requiring attention and issues maintenance suggestions on the central control room workstation, the history and traceability module is silently awakened in the background. It standardizes and encapsulates the complete analysis chain data for this (and several adjacent diagnostic cycles) and writes it to the factory's history traceability database. The belt scale diagnostic history traceability log table (time series snapshot) is as follows: The specific business value lies in post-event traceability and strategy iteration: Suppose that at 3:00 PM that day, the boiler unit experienced abnormal fluctuations in combustion efficiency. When reviewing the cause of the accident, the thermal control engineer can directly retrieve the traceability table of this module to clearly verify that at 2:30 PM, although the belt scale displayed 825.5 t / h, which seemed normal, the system had accurately recorded that the reliability score had dropped to 75 points, and retained conclusive evidence of sensor deviation and insufficient tension. Engineers can thus quickly pinpoint the source of the problem, avoiding a situation where there is no way to verify the facts. At the same time, these traceability records, accumulated over a long period according to time sequences, also provide industrial sample data for subsequent adjustments or optimizations to the deduction weight ratio within the intelligent reliability assessment module.

[0066] In one specific embodiment, the result reliability diagnosis and interpretation process of the present invention may include the following steps: Step S1: Obtain the current measurement results and related evidence information; obtain the current measurement results, and gather the operating condition information, unit status information, historical result information, verification-related information, abnormal event information and other auxiliary information related to the measurement results to form a result diagnosis input set.

[0067] Step S2: Conduct a comprehensive reliability assessment of the current measurement results; based on the result diagnostic input set, conduct a comprehensive analysis of the reliability of the current measurement results to form a reliability assessment result.

[0068] Step S3: Identify the main factors affecting the credibility of the results; based on the credibility assessment results and the result diagnosis input set, identify the main factors affecting the credibility of the current metrological results and form corresponding explanatory information.

[0069] Step S4: Form a confidence level diagnosis conclusion for the results; Based on the confidence assessment results and interpretation information, form a confidence level or diagnosis level conclusion for the current measurement results.

[0070] Step S5: Output result interpretation information and usage recommendations; Based on the confidence level or diagnostic level conclusion and interpretation information, output at least one of the following information: the confidence level conclusion of the current measurement result, the main influencing factors, the reference level of the result, and the usage recommendations of the result.

[0071] Step S6: Record the diagnostic process and the evolution of results; record the changes in the reliability of the current measurement results, the changes in influencing factors, and the changes in the diagnostic conclusions to form traceable information.

[0072] Through the above steps, the present invention realizes intelligent diagnosis and interpretation of the reliability of belt scale measurement results.

[0073] One of the key technical features of this invention is that the modules are not independent of each other, but rather have a dependency and linkage relationship.

[0074] In one implementation method, the linkage relationship can be expressed as follows: The set of diagnostic inputs formed by the result input and the evidence aggregation module affects the credibility intelligent assessment results; The identification direction and key points of the explanation of factors influencing the credibility assessment results; The explanation of influencing factors affects the graded diagnostic conclusions; The credibility assessment results and the explanation results of influencing factors jointly affect the interpretation of results and the output of recommendations. The combined results from multiple modules jointly determine the final credibility interpretation output and the recommendations for using the results.

[0075] For example: When the credibility intelligent assessment module determines that the current result is in a low credibility state, the influencing factor explanation module can further identify the main factors that lead to the decrease in credibility and output the corresponding explanation information. When the influencing factor interpretation module identifies that the current decline in credibility is mainly due to fluctuations in operating conditions and abnormal unit status, the result classification diagnosis module can form a diagnosis conclusion of "needs attention" or "low credibility". When the result grading and diagnosis module reaches a low confidence conclusion, the result interpretation and suggestion output module can further output usage suggestions such as "not recommended as a direct control basis" or "recommend manual review".

[0076] Through the above-mentioned linkage analysis, the present invention enables the diagnosis of results to no longer rely on a single conclusion, but to be based on the joint output of multi-source evidence fusion, credibility assessment, factor interpretation and result recommendations.

[0077] The invention will now be described in conjunction with a specific scenario.

[0078] In a certain belt scale operation scenario, after the system generates the current measurement result, the result input and evidence aggregation module synchronously obtains the historical result information, current operating condition information, unit status information, recent verification related information and abnormal event information corresponding to the result, and forms a result diagnosis input set.

[0079] Subsequently, the credibility intelligent assessment module conducts a comprehensive analysis of the current measurement results and finds that although the current results themselves do not significantly exceed the limits, the credibility level decreases due to the fluctuation of the current operating conditions and the abnormal state of the unit, resulting in an assessment result of "low reference value" or "needs attention".

[0080] Based on this, the influencing factor explanation module identifies the main factors affecting the credibility of the current results, including: large fluctuations in the current operating conditions; abnormalities in the status of individual units; and deviations in the trend of historical results.

[0081] Based on the above assessment and interpretation results, the result grading and diagnostic module further generates a "needs attention" diagnostic conclusion.

[0082] The results interpretation and suggestion output module outputs one or more of the following information: the current result credibility level is "needs attention"; the main influencing factors are operating condition fluctuations, abnormal unit status, and historical deviations; it is recommended to refer to historical results in conjunction with the current results; it is recommended to manually review the results before using them as an important basis.

[0083] At the same time, the history and traceability module records the changes in the credibility of the current results, the changes in influencing factors, and the changes in diagnostic conclusions, so as to facilitate subsequent review and analysis.

[0084] As can be seen from this embodiment, the present invention does not change the original measurement results themselves, but improves the interpretability, reference value and usability of the results through intelligent diagnosis and interpretation mechanisms after the results are formed.

[0085] Without departing from the overall concept of this invention, each module in this invention can be implemented in different ways.

[0086] For example, the credibility intelligent assessment module can be implemented using rule-based assessment, statistical assessment, pattern recognition assessment, model assessment, or a combination thereof. The influencing factor explanation module can be implemented by factor identification, evidence summarization, risk source extraction, explanation rule output, or a combination thereof; The result classification diagnosis module can be implemented using classification rule diagnosis, comprehensive judgment diagnosis, or a combination thereof. The results interpretation and suggestion output module can be implemented using structured output, level prompt output, suggestion output, or a combination thereof; The history and traceability module can be implemented using event logging, time-series archiving, diagnostic process logging, or a combination thereof.

[0087] After the belt scale measurement results are generated, the reliability of the results is intelligently evaluated based on multi-source evidence, and the main factors affecting the reliability are explained and output, thus forming an integrated diagnostic and interpretation framework that includes reliability diagnosis conclusions and results usage recommendations.

[0088] Reference Figure 1 The diagram illustrates the overall structure of the intelligent diagnostic and interpretation system for the reliability of belt scale measurement results according to the present invention. Figure 1 As shown, the system of the present invention includes a result input and evidence aggregation module, a credibility intelligent assessment module, an influencing factor interpretation module, a result grading and diagnosis module, a result interpretation and suggestion output module, and a history record and traceability module.

[0089] The system comprises the following modules: Result Input and Evidence Aggregation Module, which acquires the current measurement result and related multi-source evidence; Credibility Intelligent Assessment Module, which comprehensively assesses the credibility of the current measurement result; Influencing Factor Explanation Module, which identifies the main factors affecting the credibility of the current result and generates explanatory information; Result Grading and Diagnosis Module, which generates a credibility level or diagnostic level conclusion based on the credibility assessment results and explanatory information; Result Explanation and Recommendation Output Module, which outputs at least one of the following: credibility conclusion, explanation of influencing factors, reference level of the result, and recommendations for the use of the result; and History Recording and Traceability Module, which records the process of changes in the credibility of the result, the process of changes in influencing factors, and the process of changes in the diagnostic conclusion.

[0090] Figure 1 This invention is not intended to simply display or score measurement results, but rather to form an integrated intelligent reliability diagnosis and interpretation system after the results are generated, through reliability assessment, factor interpretation, hierarchical diagnosis, and suggestion output.

[0091] Reference Figure 2 The flowchart illustrating the reliability diagnosis and interpretation of the belt scale measurement results of the present invention is shown. Figure 2 As shown, the result reliability diagnosis and interpretation process of the present invention may include the following steps: S1, obtain the current measurement results and related evidence information; S2, Perform a comprehensive credibility assessment; S3, Identify the main factors affecting the reliability of the results; S4, forming a credible grading diagnostic conclusion; Then, determine whether explanations and suggestions need to be output; if explanations and suggestions are needed, execute the result explanation information and use suggestions to output; if explanations and suggestions are not needed, output the confidence conclusion; finally, record the diagnostic process and result evolution information.

[0092] Figure 2 This invention is mainly used to illustrate that it does not simply judge the credibility based on the result value itself, but rather forms a complete diagnostic process oriented towards the credibility and interpretability of the result after the result is formed, through evidence aggregation, credibility assessment, factor interpretation, hierarchical diagnosis, and output of interpretation and suggestions.

[0093] Reference Figure 3 This illustrates the intelligent analysis relationship of the credibility of metrological results based on multi-source evidence, as presented in this invention. Figure 3 As shown, current measurement result information, historical measurement result information, operating condition related information, unit status related information, verification related information, and abnormal event related information are all input into the result credibility intelligent analysis module. The result credibility intelligent analysis module comprehensively analyzes multi-source evidence information to form credibility assessment results, influencing factor explanation results, and graded diagnostic conclusions, and further forms result recommendation basis.

[0094] The system comprises several key components: current measurement results reflect the core object being diagnosed; historical measurement results provide trends and historical context; operating condition information characterizes the operating conditions; unit status information provides unit-level evidence related to result reliability; verification information reflects the relationship between results and verification status; and abnormal event information provides the context of events that cause changes in result reliability. Based on this, the system uses an intelligent result reliability analysis module to fuse and analyze multi-source evidence, generating results such as reliability assessment, factor interpretation, and tiered diagnosis, and further forming the basis for subsequent recommendations.

[0095] Figure 3 This invention is primarily intended to illustrate that the artificial intelligence or intelligent analysis capabilities in this invention are not additional to the system but are embedded within key analytical processes such as result credibility assessment, interpretation of influencing factors, and tiered diagnosis, thereby supporting the improvement of the credibility and interpretability of metrological results.

[0096] Reference Figure 4 This illustrates the interpretation chain for the reliability of the measurement results of the present invention. For example... Figure 4 As shown, the current measurement results are evaluated for reliability, which in turn leads to a graded diagnostic conclusion. Based on this, the system further generates an explanation of influencing factors and determines the degree of reference of the results, ultimately forming a recommendation for the use of the results.

[0097] Among them, the credibility assessment result is used to characterize the credibility of the current measurement result; the graded diagnostic conclusion is used to characterize the credibility level or diagnostic level to which the current result belongs; the influencing factor explanation result is used to explain the main factors affecting the credibility of the current result; the result reference level is used to characterize the reference level of the current result in subsequent applications; and the result usage recommendation is used to provide corresponding reference, review or restriction recommendations for the current result.

[0098] Figure 4 This invention is primarily intended to illustrate that the output of this invention does not stop at the credibility level itself, but rather unfolds along an interpretive chain of "credibility assessment - graded diagnosis - factor interpretation - reference level - usage recommendations," thereby enabling the measurement results not only to be judged, but also to be interpreted and used appropriately.

[0099] The present invention also provides an intelligent diagnostic and interpretation device for the reliability of belt scale measurement results. The intelligent diagnostic and interpretation device for the reliability of belt scale measurement results includes a memory and a processor. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor performs the steps of the intelligent diagnostic and interpretation system for the reliability of belt scale measurement results in the above embodiments.

[0100] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when the instructions are executed on a computer, cause the computer to perform the steps of the intelligent diagnosis and interpretation system for the reliability of the belt scale measurement results.

[0101] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0102] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0103] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A smart diagnostic and interpretation system for the reliability of belt scale measurement results, characterized in that, include: The result input and evidence aggregation module is used to obtain the current measurement result and multi-source evidence information related to the current measurement result after the belt scale measurement result is formed, and to aggregate the current measurement result and the multi-source evidence information to form a result diagnosis input set. The credibility intelligent assessment module is connected to the result input and evidence aggregation module; Based on the aforementioned result diagnostic input set, a comprehensive evaluation of the reliability of the current measurement result is conducted to form a reliability evaluation result; The influencing factor interpretation module is connected to the credibility intelligent assessment module; based on the credibility assessment results and multi-source evidence information in the result diagnosis input set, it identifies the main factors affecting the credibility of the current measurement result and obtains the influencing factor interpretation results; The result grading and diagnosis module is connected to the influencing factor interpretation module; based on the credibility assessment results and the influencing factor interpretation results transmitted above, the current measurement result is diagnosed and judged, and a credibility level or diagnosis level conclusion is formed after the judgment; The results interpretation and suggestion output module is connected to the credibility intelligent assessment module, the influencing factor interpretation module, and the results grading diagnosis module, respectively. Based on the credibility assessment results, the influencing factor interpretation results, and the credibility level or diagnosis level conclusion, it outputs at least one of the following information corresponding to the current measurement result: credibility conclusion, influencing factor description, result reference level, and result usage suggestion. The historical record and traceability module is connected to the result interpretation and suggestion output module; This is used to acquire and record the changes in the reliability of the current measurement results, the changes in influencing factors, and the changes in the diagnostic conclusions formed during the execution of the above modules, and the records are traceable.

2. The intelligent diagnosis and interpretation system for the reliability of belt scale measurement results according to claim 1, characterized in that, The credibility intelligent assessment module is specifically used to: judge the credibility of the current measurement result by using at least one of rule assessment, statistical assessment, pattern recognition assessment or model assessment, combined with the numerical value, fluctuation characteristics and continuity of the current measurement result; The credibility assessment result includes at least one of credibility assessment value, credibility level, or credibility category.

3. The intelligent diagnosis and interpretation system for the reliability of belt scale measurement results according to claim 1, characterized in that, The influencing factor interpretation module identifies the main factors affecting the reliability of the current measurement results, including: At least one of the following: operating condition fluctuation factors, unit status abnormal factors, historical result deviation factors, verification status related factors, and communication or status instability factors; The explanation of the influencing factors includes at least one of the following: the category of the main influencing factors, the direction of influence, the degree of influence, and the source of risk.

4. The intelligent diagnosis and interpretation system for the reliability of belt scale measurement results according to claim 1, characterized in that, The confidence level or diagnostic level conclusions generated by the result grading and diagnostic module include: highly reliable, referable, require attention, low reliability, or not recommended for direct use.

5. The intelligent diagnosis and interpretation system for the reliability of belt scale measurement results according to claim 4, characterized in that, The results usage suggestions output by the results interpretation and suggestion output module include at least one of the following: can be directly referenced, it is recommended to refer to historical results, it is recommended to manually review, it is not recommended to use as a direct control basis, or it is recommended to pay attention to relevant risk factors.

6. The intelligent diagnosis and interpretation system for the reliability of belt scale measurement results according to claim 5, characterized in that, There are interconnected analytical relationships between the modules within the system, specifically: When the result classification and diagnosis module reaches a diagnosis level conclusion of "needs attention" or "low confidence", it triggers the influencing factor interpretation module to further identify the main factors that lead to the decrease in confidence. The result interpretation and suggestion output module then simultaneously outputs suggestions for manual review or recommendations not to use the main factors as a basis for direct control.

7. A method for intelligent diagnosis and interpretation of the reliability of belt scale measurement results, characterized in that, Includes the following steps: After the belt scale measurement result is generated, the current measurement result and multi-source evidence information related to the current measurement result are obtained, and the current measurement result and the multi-source evidence information are aggregated to form a result diagnosis input set; Based on the set of diagnostic results, the reliability of the current measurement results is comprehensively evaluated to form a reliability evaluation result; Based on the credibility assessment results and the multi-source evidence information in the result diagnosis input set, the main factors affecting the credibility of the current measurement results are identified, and an explanation result of the influencing factors is formed. Based on the credibility assessment results and the explanation results of the influencing factors, the current measurement results are diagnosed and determined to form a credibility level or diagnostic level conclusion. Based on the credibility assessment results, the explanation results of the influencing factors, and the credibility level or diagnostic level conclusion, output at least one of the following information corresponding to the current measurement result: credibility conclusion, explanation of influencing factors, degree of reference of the result, and suggestions for use of the result; as well as Record the changes in the reliability of the current measurement results, the changes in influencing factors, and the changes in diagnostic conclusions to form a traceable record.

8. The intelligent diagnosis and interpretation method for the reliability of belt scale measurement results according to claim 7, characterized in that, The reliability of the current measurement results is comprehensively evaluated, specifically including: using at least one of rule-based evaluation, statistical evaluation, pattern recognition evaluation, or model evaluation, and making a judgment based on the numerical value, fluctuation characteristics, and continuity of the current measurement results; Identify the main factors affecting the reliability of the current measurement results, specifically including: identifying at least one of the following: operating condition fluctuation factors, unit status anomaly factors, historical result deviation factors, verification status related factors, and communication or status instability factors.

9. The intelligent diagnosis and interpretation method for the reliability of belt scale measurement results according to claim 7, characterized in that, When outputting information corresponding to the current measurement result: when the resulting confidence level or diagnostic level conclusion is of concern or low confidence, the output influencing factor description includes the specific risk sources that lead to the decrease in confidence, and the output results usage suggestions include suggestions to combine with historical results for reference, suggestions for manual review, or not to use as a direct control basis.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 7 to 9.

Images