Uncertainty evaluation method and device for microwave detection of PE pipe and equipment thereof

Abstract

The application discloses a PE pipe microwave detection uncertainty evaluation method and device and equipment thereof, and relates to the technical field of nondestructive testing.The method comprises the following steps: obtaining detection data of uncertainty factors in a PE pipe microwave detection process, wherein the uncertainty factors are labeled with data property identifiers; converting the detection data into membership vectors based on the data property identifiers and corresponding preset conversion rules, wherein the preset conversion rules comprise membership function conversion based on a combination of trapezoidal distribution and triangular distribution, and weight vector direct quantization conversion based on expert scoring and engineering experience adjustment; and performing fuzzy comprehensive evaluation on the uncertainty factors based on the membership vectors and preset weights to obtain a comprehensive evaluation result.Under the premise of not relying on repeated measurements or physical tracing required for uncertainty evaluation, the method realizes structured, operable and engineering interpretable comprehensive evaluation of the uncertainty factors in the PE pipe microwave detection process.

Description

Technical Field

[0001] This application relates to the field of nondestructive testing technology, and in particular to uncertainty evaluation methods, apparatus and equipment for microwave testing of PE pipes. Background Technology

[0002] Microwave nondestructive testing technology has received widespread attention in recent years for the inspection of composite materials and plastic welded structures due to its sensitivity to changes in the dielectric properties of polymer materials and its good penetration ability to non-metallic materials.

[0003] Microwave testing often involves multiple stages, including electromagnetic excitation, material response, and signal processing. This results in microwave testing results exhibiting response characteristics under the combined influence of multiple factors, leading to significant uncertainties in the testing process. Currently, there is a lack of unified calibration and metrological traceability conditions for uncertainty assessment in microwave nondestructive testing, making it difficult to evaluate the microwave testing process using existing uncertainty assessment methods.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, and equipment for evaluating the uncertainty of microwave testing of PE (Polyethylene) pipes, aiming to solve the technical problem that it is difficult to evaluate the microwave testing process using existing uncertainty assessment methods.

[0006] To achieve the above objectives, this application proposes an uncertainty evaluation method for microwave testing of PE pipes, the method comprising: Data on uncertainties during microwave testing of PE pipes are obtained, and the uncertainties are marked with data property identifiers. Based on the data property identifier and the corresponding preset conversion rules, the detection data is converted into a membership vector. The preset conversion rules include membership function conversion based on a combination of trapezoidal and triangular distributions, and direct quantization conversion of weight vectors adjusted based on expert scoring and engineering experience. Based on the membership vector and preset weights, a fuzzy comprehensive evaluation is performed on the uncertain factors to obtain a comprehensive evaluation result.

[0007] In one embodiment, the data property identifier includes a quantitative identifier and a qualitative identifier. The step of converting the detection data into a membership vector based on the data property identifier and the corresponding preset conversion rule includes: If the data property identifier is a quantitative identifier, then based on the membership function of the combination of trapezoidal distribution and triangular distribution, the quantitative data in the detection data marked with the quantitative identifier is transformed into a membership vector; If the data property identifier is a qualitative identifier, then based on the weight vector adjusted by expert scoring and engineering experience, the qualitative data in the detection data marked with the qualitative identifier is converted into a membership vector.

[0008] In one embodiment, before the step of converting the qualitative data labeled with the qualitative identifier in the detection data into a membership vector based on a weight vector adjusted by expert scoring and engineering experience if the data property identifier is a qualitative identifier, the method further includes: Obtain the judgment matrix obtained by experts based on their professional knowledge and engineering experience, after comparing the uncertain factors pairwise. Perform a consistency check on the judgment matrix to obtain the consistency ratio of the judgment matrix; If the consistency ratio is not less than the preset consistency threshold, then the judgment matrix is ​​adjusted and the consistency check is performed again until the consistency ratio is less than the preset consistency threshold. If the consistency ratio is less than the preset consistency threshold, then a normalized weight vector is determined based on the judgment matrix.

[0009] In one embodiment, the uncertainty factors are divided into primary factors and secondary factors according to a preset hierarchical structure; The primary factors include at least one of the following: instrument performance, environmental conditions, sample characteristics, and operation and data processing. Each of the secondary factors belongs to the corresponding primary factor. Each of the secondary factors is marked with a data property identifier and a traceability status identifier. The traceability status identifier includes at least one of traceable, partially traceable, or untraceable.

[0010] In one embodiment, after the step of performing a fuzzy comprehensive evaluation on the uncertainty factors based on the membership vector and preset weights to obtain a comprehensive evaluation result, the method further includes: Based on the traceability status identifier, target secondary factors that are either untraceable or partially traceable are selected from the secondary factors; Obtain the evaluation value corresponding to the target secondary factor in the comprehensive evaluation result; Based on the weights of the target secondary factors and the evaluation values, the source-free adaptability index of the target secondary factors is determined; The non-traceability adaptability index is compared with a preset reliability threshold, and the reliability level of the comprehensive evaluation result under non-metric traceability conditions is determined based on the comparison results.

[0011] In one embodiment, after the step of performing a fuzzy comprehensive evaluation on the uncertainty factors based on the membership vector and preset weights to obtain a comprehensive evaluation result, the method further includes: Based on instrument technical specifications, engineering experience, and data dispersion characteristics, the secondary factors are randomly sampled to obtain multiple sample sets. The simulation uncertainty assessment is performed on each of the aforementioned sample sets to obtain the simulation evaluation results; Based on the simulation evaluation results, error analysis is performed on the comprehensive evaluation results to obtain the statistical distribution characteristics of the comprehensive evaluation results.

[0012] In one embodiment, the preset weights include secondary weight vectors corresponding to each of the secondary factors and primary weight vectors corresponding to each of the primary factors. The step of performing fuzzy comprehensive evaluation on the uncertainty factors based on the membership vectors and the preset weights to obtain a comprehensive evaluation result further includes: Based on the membership vectors and corresponding weight vectors of the secondary factors in the primary factors, a secondary fuzzy comprehensive evaluation is performed on the primary factors to obtain the comprehensive evaluation value of the primary factors. Based on the comprehensive evaluation value of each primary factor and its corresponding primary weight vector, a primary fuzzy comprehensive evaluation is performed on the primary factors to obtain the comprehensive evaluation result.

[0013] Furthermore, to achieve the above objectives, this application also proposes an uncertainty evaluation device for microwave testing of PE pipes, the uncertainty evaluation device for microwave testing of PE pipes comprising: The acquisition module is used to acquire detection data of uncertain factors during the microwave testing of PE tubes, wherein the uncertain factors are marked with data property identifiers; The conversion module is used to convert the detection data into a membership vector based on the data property identifier and the corresponding preset conversion rules. The preset conversion rules include membership function conversion based on a combination of trapezoidal distribution and triangular distribution, and direct quantization conversion of weight vectors adjusted based on expert scoring and engineering experience. The evaluation module is used to perform fuzzy comprehensive evaluation on the uncertainty factors based on the membership vector and preset weights, and obtain a comprehensive evaluation result.

[0014] Furthermore, to achieve the above objectives, this application also proposes an uncertainty evaluation device for microwave testing of PE tubes, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the uncertainty evaluation method for microwave testing of PE tubes as described above.

[0015] One or more technical solutions proposed in this application have at least the following technical effects: In the uncertainty evaluation of microwave testing of PE pipes, detection data of uncertainty factors during the microwave testing process are obtained. This detection data is labeled with data property identifiers, and based on these identifiers and corresponding preset transformation rules, the detection data is converted into membership vectors. These preset transformation rules include membership function transformations based on a combination of trapezoidal and triangular distributions, and direct quantification transformations using fuzzy linguistic variables based on expert scoring and engineering experience. By introducing data property identifiers and preset transformation rules, detection data from different sources can be matched with corresponding transformation methods according to their identifiers, generating a unified membership vector. The trapezoidal and triangular distributions are used in this process. The system employs two mechanisms: membership function transformation and fuzzy linguistic variable quantification transformation based on expert scoring and engineering experience. These mechanisms enhance the adaptability to different types of detection data. Furthermore, based on the membership vector and preset weights, a fuzzy comprehensive evaluation of the uncertainty factors is performed to obtain a comprehensive evaluation result. This fuzzy comprehensive evaluation, combined with preset weights, avoids reliance on repeated measurements or probability statistics, enabling the comprehensive evaluation result to systematically reflect the superimposed impact of multiple sources of uncertainty factors. Ultimately, without relying on repeated measurements or physical tracing required for uncertainty assessment, a structured, operable, and engineering-interpretable comprehensive evaluation of uncertainty factors during PE tube microwave testing is achieved. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating the uncertainty evaluation method for microwave testing of PE tubes provided in the first embodiment of this application; Figure 2 A flowchart illustrating the second embodiment of the uncertainty evaluation method for microwave testing of PE tubes in this application; Figure 3 A flowchart illustrating the third embodiment of the uncertainty evaluation method for microwave testing of PE tubes in this application; Figure 4 This is a schematic diagram of the module structure of the uncertainty evaluation device for microwave testing of PE tubes according to an embodiment of this application; Figure 5This is a schematic diagram of the hardware operating environment involved in the uncertainty evaluation method for microwave detection of PE tubes in this application embodiment.

[0019] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0021] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0022] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or microwave testing platform capable of performing the above functions. The following description uses a microwave testing platform as an example to illustrate this embodiment and the subsequent embodiments.

[0023] Based on this, embodiments of this application provide an uncertainty evaluation method for microwave testing of PE tubes, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the uncertainty evaluation method for microwave testing of PE pipes in this application.

[0024] In this embodiment, the uncertainty evaluation method for microwave testing of PE tubes includes steps S10~S30: Step S10: Obtain detection data of uncertainties during the microwave testing of PE tubes, wherein the uncertainties are marked with data property identifiers; It should be noted that PE pipes are pipes made of polyethylene material. Uncertainties refer to various variables or conditions that may affect the accuracy, repeatability, or reliability of test results during the microwave testing of PE pipes. These include, but are not limited to, instrument performance, environmental conditions, sample characteristics, operation, and data processing. Data property identifiers are metadata tags used to mark the type of test data attribute corresponding to a certain uncertainty factor, including quantitative and qualitative identifiers. Quantitative identifiers indicate that the corresponding number can be obtained directly through numerical measurement (e.g., temperature value, signal-to-noise ratio). Qualitative identifiers indicate that the corresponding data needs to be expressed through subjective judgment or verbal description (e.g., high operator proficiency, severe environmental interference).

[0025] Understandably, in practical applications of microwave testing for PE pipes, there is often a lack of unified calibration standards and a complete metrological traceability system. By labeling each uncertainty factor with a data nature identifier (such as a quantitative or qualitative identifier) ​​while acquiring the test data, the microwave testing platform can identify which factors have a traceable basis and which factors are essentially non-metrological information. This metadata labeling method can provide a structured basis for distinguishing between traceable and non-traceable information in subsequent processing, avoiding evaluation bias caused by data type confusion in subsequent processing.

[0026] Step S20: Based on the data property identifier and the corresponding preset conversion rules, the detection data is converted into a membership vector. The preset conversion rules include membership function conversion based on a combination of trapezoidal and triangular distributions, and direct quantization conversion of weight vectors adjusted based on expert scoring and engineering experience. It should be noted that the preset transformation rules pre-define the mapping logic from data to membership vectors for different data properties; these include: analytical transformation rules based on trapezoidal-trigonometric combination membership functions for quantitative data, and linguistic variable quantification rules based on expert scoring and engineering experience for qualitative data. The membership vector is a vector composed of the degree of membership corresponding to the original detection data of a certain uncertainty factor after fuzzification processing, on a preset comment set. The preset comment set can be divided into five uncertainty levels: very low, relatively low, medium, relatively high, and very high. The membership function is a composite fuzzy membership function constructed by concatenating or weighting trapezoidal and trigonometric functions, used to map continuous quantitative data to membership degrees under multi-level comments.

[0027] Understandably, using a membership function combining trapezoidal and triangular distributions to transform quantitative data can accurately characterize the nonlinear features of uncertainties in engineering practice. For example, instrument performance indicators often remain stable within the allowable error range (suitable for trapezoidal distribution), while the influence of environmental temperature exhibits a unimodal sensitivity (suitable for triangular distribution). Furthermore, by introducing expert scoring and engineering experience adjustment mechanisms to process qualitative data, soft factors such as operator proficiency and the degree of on-site interference can be scientifically incorporated into the evaluation system. Therefore, this path transformation not only maintains the mathematical rigor of quantitative data but also integrates the practical experience of domain experts, enabling uncertainties of different natures to be expressed in a standardized manner within a unified fuzzy mathematical framework.

[0028] Understandably, for qualitative factors that cannot be directly quantified, introducing a weight vector-based quantification rule that adjusts for weights based on expert scoring and long-term engineering experience can transform subjective descriptions into structured membership vectors, effectively integrating domain knowledge, avoiding semantic information loss, and thus providing accurate evaluation data for subsequent comprehensive evaluation.

[0029] Step S30: Based on the membership vector and preset weights, perform fuzzy comprehensive evaluation on the uncertainty factors to obtain a comprehensive evaluation result.

[0030] It should be noted that the preset weights are numerical coefficients reflecting the degree of influence of each uncertainty factor on the final evaluation result. Fuzzy comprehensive evaluation is a process of synthesizing the membership vectors of each factor with their corresponding weights to output a comprehensive membership vector or a single evaluation value that represents the overall uncertainty. Specifically, fuzzy comprehensive evaluation is a two-level fuzzy comprehensive evaluation.

[0031] Understandably, the two-level fuzzy comprehensive evaluation mechanism not only preserves the integrity of intermediate evaluation information but also achieves dimensionality reduction analysis of complex systems, thereby avoiding information overload. Furthermore, by introducing a scientific weighting system based on the AHP (Analytic Hierarchy Process) method, the differences in the degree of influence of various uncertainty factors on the detection results can be accurately reflected.

[0032] Understandably, fuzzy comprehensive evaluation can integrate discrete uncertainty factors into continuous quantitative results, thereby intuitively understanding the overall level of uncertainty and making hierarchical decisions accordingly, thus improving the decision-making efficiency and safety of PE pipe testing projects.

[0033] Understandably, by performing fuzzy synthesis operations on the membership vectors of each uncertainty factor and their corresponding preset weights, the overall uncertainty level under the coupling effect of multiple factors can be comprehensively reflected, thereby more comprehensively and objectively assessing the credibility of the detection results.

[0034] Among them, the preset weights can be determined based on the analytic hierarchy process combined with expert consensus test to ensure that the weight allocation reflects both technical importance and logical consistency; the fuzzy comprehensive evaluation based on this can improve the scientific nature and decision support value of the evaluation results.

[0035] Optionally, to further improve the adaptive capability, a dynamic weight adjustment mechanism can be introduced: when there is a significant deviation between the historical detection results and the subsequent excavation verification (such as a prediction of "low uncertainty" but the actual discovery of serious defects), the microwave detection platform automatically triggers the backpropagation algorithm to fine-tune the weight coefficients of relevant factors and update them in the next evaluation process, thereby achieving online learning and continuous optimization.

[0036] Optionally, to accommodate the evaluation granularity requirements of different engineering scenarios, multi-granularity evaluation set configuration can be supported. Fuzzy interpolation or semantic alignment modules can also be configured on the microwave detection platform. Through fuzzy interpolation or semantic alignment modules, membership vectors of different granularities can be uniformly mapped to a common evaluation space, thereby ensuring the consistency and comparability of evaluation results.

[0037] Optionally, the uncertainty factors are divided into primary factors and secondary factors according to a preset hierarchical structure; The primary factors include at least one of the following: instrument performance, environmental conditions, sample characteristics, and operation and data processing. Each of the secondary factors belongs to the corresponding primary factor. Each of the secondary factors is marked with a data property identifier and a traceability status identifier. The traceability status identifier includes at least one of traceable, partially traceable, or untraceable.

[0038] It should be noted that the hierarchical structure pre-organizes uncertainties into a tree-like structure according to their logical attribution and influence level. The top level consists of primary factors, and the lower levels consist of secondary factors belonging to each primary factor. Primary factors summarize a class of common influencing sources, including at least one of the following: instrument performance, environmental conditions, sample characteristics, and operation and data processing. Secondary factors are specific, identifiable uncertainties belonging to a primary factor, used to refine the description of measurable or assessable variables in actual testing. For example, instrument performance can be divided into secondary factors such as frequency accuracy, acquisition bandwidth, and antenna dispersion; environmental conditions can be divided into secondary factors such as ambient temperature and electromagnetic interference; sample characteristics can be divided into secondary factors such as material homogeneity, surface roughness, and geometric dimensional deviations; and operation and data processing can be divided into secondary factors such as operator experience and data processing methods.

[0039] Among these, instrument performance refers to the technical condition and output characteristics of the microwave testing equipment itself. Environmental conditions refer to the external physical or meteorological environment during the testing process. Sample characteristics refer to the physical or chemical properties of the PE pipe being tested. Operation and data processing refer to the operational actions performed by the testing personnel and the subsequent data analysis process.

[0040] It should be noted that the traceability status identifier is a metadata tag used to characterize whether a certain secondary factor has metrological traceability capability. It includes at least three statuses: traceable, partially traceable, or non-traceable. Among them, traceable means that the factor can be calibrated through national or industry standard devices and a complete traceability chain can be established; partially traceable means that only some parameters or ranges are traceable; and non-traceable means that it relies entirely on experience judgment or there are no standard calibration methods.

[0041] It should be noted that by dividing the uncertainty factors into primary and secondary factors through a pre-defined hierarchical structure, the logical and modular organization of the influencing factors can be achieved, avoiding chaotic factor listing and subjective and arbitrary weight allocation.

[0042] Understandably, the primary factors cover four dimensions: instrument, environment, sample, and operation, comprehensively anchoring the key links in the entire testing chain, which can ensure that there are no major omissions in the evaluation system; the specification of the secondary factors makes each influencing point measurable and traceable, which can provide a structured basis for accurately locating the root cause of the problem.

[0043] Understandably, by simultaneously labeling each secondary factor with both data nature and traceability status identifiers, it is possible to distinguish which information has a metrological basis and which relies on engineering experience. This allows for differentiated processing strategies in subsequent evaluations, avoiding both blindly rejecting untraceable factors and over-relying on their accuracy. Consequently, when comprehensively evaluating uncertainties in the microwave testing process of PE pipes, uncertainties can be rationally integrated and risks can be controlled.

[0044] It is understandable that by using hierarchical modeling and dual-identification management, we can avoid circumventing or ignoring the lack of traceability, and then explicitly incorporate the lack of traceability into the evaluation framework, thereby achieving a comprehensive evaluation result that is structurally reasonable, has reliable weights, and is usable even under weak traceability conditions.

[0045] This embodiment provides an uncertainty evaluation method for microwave testing of PE pipes. In the uncertainty evaluation of microwave testing of PE pipes, detection data of uncertainty factors during the microwave testing process are acquired. The detection data is labeled with data property identifiers, and based on the data property identifiers and corresponding preset transformation rules, the detection data is converted into membership vectors. The preset transformation rules include membership function transformation based on a combination of trapezoidal and triangular distributions, and direct quantification transformation using fuzzy linguistic variables based on expert scoring and engineering experience. By introducing data property identifiers and preset transformation rules, detection data from different sources can be matched with corresponding transformation methods according to their identifiers, generating a unified membership vector. Among these mechanisms, the membership function transformation combining trapezoidal and triangular distributions, and the fuzzy linguistic variable quantification transformation based on expert scoring and engineering experience, enhance the adaptability to different types of detection data. Then, based on the membership vector and preset weights, a fuzzy comprehensive evaluation of the uncertainty factors is performed to obtain a comprehensive evaluation result. This, combined with preset weights, achieves fuzzy comprehensive evaluation, avoiding reliance on repeated measurements or probability statistics, and enabling the comprehensive evaluation result to systematically reflect the superimposed impact of multiple sources of uncertainty factors. Finally, without relying on repeated measurements or physical tracing required for uncertainty assessment, a structured, operable, and engineering-interpretable comprehensive evaluation of the uncertainty factors in the microwave testing process of PE tubes is achieved.

[0046] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2Step S20 also includes steps S01~S02: Step S01: If the data property identifier is a quantitative identifier, then based on the membership function of the combination of trapezoidal distribution and triangular distribution, the quantitative data in the detection data marked with the quantitative identifier is converted into a membership vector. Step S02: If the data property identifier is a qualitative identifier, then based on the weight vector adjusted by expert scoring and engineering experience, the qualitative data in the detection data marked with the qualitative identifier is converted into a membership vector.

[0047] It should be noted that quantitative data refers to detection parameters with precise values ​​and units, directly collected by measuring instruments or sensors. Qualitative data, on the other hand, is information obtained through direct quantification by instruments, relying on human experience or on-site description. The weight vector also includes the secondary weight vectors corresponding to each of the secondary factors and the primary weight vectors corresponding to each of the primary factors.

[0048] It is understandable that using a combination of trapezoidal and triangular distributions to transform quantitative data through membership functions can better align with the cognitive models of tolerance intervals and critical transition zones in engineering practice. This reduces the reliance on high-precision metrological traceability, thus ensuring that membership mapping still has physical meaning and engineering rationality even in scenarios with no or weak traceability.

[0049] Understandably, the engineering experience adjustment process can also be forced to associate verifiable evidence (such as standard clause numbers and database statistical conclusions) to enhance the credibility and persuasiveness of the conversion results, and to provide a complete decision support chain for the evaluation conclusions, thereby meeting the compliance requirements of engineering auditing, quality traceability, and responsibility definition.

[0050] Optionally, prior to step S02, the uncertainty evaluation method for the microwave testing of the PE tube further includes: Obtain the judgment matrix obtained by experts based on their professional knowledge and engineering experience, after comparing the uncertain factors pairwise. Perform a consistency check on the judgment matrix to obtain the consistency ratio of the judgment matrix; If the consistency ratio is not less than the preset consistency threshold, then the judgment matrix is ​​adjusted and the consistency check is performed again until the consistency ratio is less than the preset consistency threshold. If the consistency ratio is less than the preset consistency threshold, then a normalized weight vector is determined based on the judgment matrix.

[0051] It should be noted that pairwise comparison involves evaluating the relative importance of several uncertain factors at the same level, assigning values ​​according to a preset scale (such as a 1-9 Saaty scale), and forming the comparison results. Consistency testing is a mathematical verification of the judgment matrix to determine whether there are logical contradictions or excessive subjective biases in the experts' pairwise comparison results. The consistency ratio is the ratio of the consistency index of the judgment matrix to the average random consistency index of the same order. The preset consistency threshold is a pre-set upper limit for determining whether the consistency ratio of the judgment matrix is ​​acceptable.

[0052] It is understandable that, in microwave testing of PE tubes, the degree of influence of different uncertainty factors on the results varies significantly. If the weight allocation is arbitrary or lacks a basis, it will lead to a distorted comprehensive evaluation. By introducing pairwise comparisons by experts to construct a judgment matrix and forcing consistency checks, it can be ensured that the weight assignment reflects both professional consensus and logical consistency.

[0053] Understandably, since traditional expert scoring often suffers from inconsistent standards such as cyclical bias or scale confusion, closed-loop verification of consistency ratio and preset consistency threshold can effectively identify and correct irrational judgments, thereby improving the scientificity and credibility of subjective weighting.

[0054] In practical implementation, in multi-factor comprehensive evaluation studies in the field of engineering testing, a number of experts between 3 and 10 is sufficient to obtain relatively stable judgment results. In this embodiment, five experts with extensive experience in PE pipeline testing, microwave testing technology, and related uncertainty analysis are invited to independently score the results. Based on their professional knowledge and practical experience, and referring to Saaty's 1-9 scale method, the experts independently complete the judgment matrix. Subsequently, the scoring results are geometrically averaged to obtain the final judgment matrix A. If all results pass the consistency test (CR < 0.1), it indicates that the weighting results have good logical consistency and engineering rationality. The eigenvector w is then normalized to obtain the weight vector. The preset consistency threshold is 0.1. Optionally, when CR≥0.1, the historical qualified matrix knowledge graph is invoked, and a graph neural network is used to identify contradictory patterns (such as "when the ambient humidity is >80%, experts often overestimate the weight of operational factors"), dynamically generate correction suggestions, and visualize the adjustment path.

[0055] Based on the first and second embodiments of this application, the same or similar content as the above embodiments in the third embodiment of this application can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Step S30 also includes steps S1 to S2: Step S1: Based on the membership vector and corresponding weight vector of the secondary factors in the primary factors, perform secondary fuzzy comprehensive evaluation on the primary factors to obtain the comprehensive evaluation value of the primary factors; Step S2: Based on the comprehensive evaluation value of each primary factor and the corresponding primary weight vector, perform a primary fuzzy comprehensive evaluation on the primary factors to obtain the comprehensive evaluation result.

[0056] It should be noted that the secondary weight vector is a normalized set of weights reflecting the relative importance of each secondary factor under the same primary factor. Secondary fuzzy comprehensive evaluation is the process of using fuzzy synthesis operators to perform aggregation operations within the same primary factor, based on the membership vectors of its subordinate secondary factors and their corresponding secondary weight vectors, to output the overall uncertainty evaluation value of that primary factor. The primary weight vector is a normalized set of weights reflecting the degree of influence of each primary factor on the overall detection uncertainty. Primary fuzzy comprehensive evaluation is the process of performing fuzzy synthesis operations again based on the comprehensive evaluation value of each primary factor and its corresponding primary weight vector, ultimately obtaining a global comprehensive evaluation result characterizing the uncertainty of the entire PE tube microwave detection process.

[0057] It is understandable that, since microwave testing of PE pipes involves multiple sources and multiple levels of uncertainties, if a single-level direct weighting evaluation is used, it will be difficult to reflect the logical attribution and influence coupling relationship between factors. However, by constructing a two-level fuzzy comprehensive evaluation architecture from level two to level one, a systematic and hierarchical integration from micro factors to macro conclusions is achieved.

[0058] Understandably, in the second-level fuzzy comprehensive evaluation, factors of the same type are locally aggregated to avoid cross-category interference; in the first-level evaluation, the four major categories of factors are weighted and integrated according to their global importance, which not only preserves the details of the internal structure but also achieves overall coordination, thereby improving the structure and scientific nature of the evaluation.

[0059] In practice, different synthesis operators can be used for the second-level and first-level fuzzy comprehensive evaluations. For example, the second-level evaluation uses a weighted average to preserve details, while the first-level evaluation uses a maximum-minimum operator to highlight the weakest link, so as to achieve the dual goals of refined modeling and risk focus.

[0060] In practical implementation, when the number of secondary factors under a certain primary factor is small (e.g., only 1), the secondary evaluation can be automatically skipped, and the membership vector of the secondary factor can be directly used as the comprehensive evaluation value of the primary factor, thereby improving calculation efficiency.

[0061] Optionally, after step S30, the uncertainty evaluation method for the microwave testing of the PE tube further includes: Based on the traceability status identifier, target secondary factors that are either untraceable or partially traceable are selected from the secondary factors; Obtain the evaluation value corresponding to the target secondary factor in the comprehensive evaluation result; Based on the weights of the target secondary factors and the evaluation values, the source-free adaptability index of the target secondary factors is determined; The non-traceability adaptability index is compared with a preset reliability threshold, and the reliability level of the comprehensive evaluation result under non-metric traceability conditions is determined based on the comparison results.

[0062] It should be noted that the target secondary factors are the set of secondary factors whose traceability status is marked as untraceable or partially traceable. The evaluation value is the quantitative contribution of the target secondary factors to the comprehensive evaluation result. The non-traceability adaptability index characterizes the comprehensive influence intensity of untraceable / partially traceable factors on the comprehensive evaluation result.

[0063] It is understandable that in the actual application of microwave testing of PE pipes, a large number of field factors (such as operating experience and visual condition) naturally lack metrological traceability conditions. Simply excluding these factors will lead to a lack of evaluation information; if they are included indiscriminately, uncontrollable deviations may be introduced. However, by introducing a non-traceability adaptability index, the quantitative assessment and controllable management of the impact of non-traceability factors can be achieved.

[0064] Understandably, by comparing the non-traceability adaptability index with a preset confidence threshold, the reliability level of the comprehensive evaluation results in a weak traceability environment can be objectively determined, providing testing personnel with a clear basis for decision-making.

[0065] Optionally, after step S30, the uncertainty evaluation method for the microwave testing of the PE tube further includes: Based on instrument technical specifications, engineering experience, and data dispersion characteristics, the secondary factors are randomly sampled to obtain multiple sample sets. The simulation uncertainty assessment is performed on each of the aforementioned sample sets to obtain the simulation evaluation results; Based on the simulation evaluation results, error analysis is performed on the comprehensive evaluation results to obtain the statistical distribution characteristics of the comprehensive evaluation results.

[0066] It should be noted that the instrument's technical specifications refer to the performance parameter range specified in the microwave testing equipment's manufacturer's or calibration documentation. Engineering experience refers to the qualitative or semi-quantitative understanding of factor fluctuation patterns accumulated during PE pipe microwave testing practice. Data dispersion characteristics refer to the statistical variability exhibited by a specific secondary factor in historical testing data. Error analysis is based on multiple simulated evaluation results, calculating the statistical deviations (such as mean square error and confidence intervals) between these results and the original comprehensive evaluation results to assess the robustness of the original results. Statistical distribution characteristics are the probability distribution features of the comprehensive evaluation results under simulated perturbations.

[0067] Understandably, multi-source fusion random sampling based on instrument technical specifications, engineering experience, and the discreteness of data ensures that the sample set generation process combines equipment physical constraints, historical data regularity, and statistical rigor. This effectively avoids the shortcomings of purely theoretical sampling being divorced from engineering practice or purely empirical sampling lacking mathematical foundation, thereby improving the representativeness and credibility of simulation evaluation.

[0068] Understandably, by performing a full-process simulation uncertainty assessment on multiple sample sets, a single static evaluation is extended into a dynamic probability analysis framework, which upgrades the comprehensive evaluation results from isolated numerical values ​​to a probability distribution description, intuitively revealing the possible range and risk boundaries of the results under real operating conditions, thereby improving the accuracy of uncertainty assessment for microwave testing of PE tubes.

[0069] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the uncertainty evaluation method of microwave testing of PE tubes in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0070] This application also provides an uncertainty evaluation device for microwave testing of PE pipes; please refer to [reference needed]. Figure 4 The uncertainty evaluation device for microwave testing of PE pipes includes: The acquisition module 10 is used to acquire detection data of uncertain factors during the microwave testing of PE tubes. The uncertain factors are marked with data property identifiers, which include quantitative and qualitative identifiers. The conversion module 20 is used to convert the detection data into a membership vector based on the data property identifier and the corresponding preset conversion rules. The preset conversion rules include membership function conversion based on a combination of trapezoidal distribution and triangular distribution, and direct quantization conversion of weight vectors adjusted based on expert scoring and engineering experience. Evaluation module 30 is used to perform fuzzy comprehensive evaluation on the uncertainty factors based on the membership vector and preset weights to obtain a comprehensive evaluation result. The preset weights include the secondary weight vectors corresponding to each secondary factor and the primary weight vectors corresponding to each primary factor.

[0071] Optionally, the conversion module 20 is further configured to, if the data property identifier is a quantitative identifier, convert the quantitative data in the test data marked with the quantitative identifier into a membership vector based on a membership function combining trapezoidal and triangular distributions; and if the data property identifier is a qualitative identifier, convert the qualitative data in the test data marked with the qualitative identifier into a membership vector based on a weight vector adjusted by expert scoring and engineering experience.

[0072] Optionally, the conversion module 20 is further configured to obtain a judgment matrix obtained by experts through pairwise comparisons of the uncertainty factors based on their professional knowledge and engineering experience; perform a consistency check on the judgment matrix to obtain the consistency ratio of the judgment matrix; if the consistency ratio is not less than a preset consistency threshold, adjust the judgment matrix and perform the consistency check again until the consistency ratio is less than the preset consistency threshold; if the consistency ratio is less than the preset consistency threshold, determine a normalized weight vector based on the judgment matrix.

[0073] Optionally, the uncertainty factors are divided into primary factors and secondary factors according to a preset hierarchical structure; the primary factors include at least one of instrument performance, environmental conditions, sample characteristics, and operation and data processing; each secondary factor belongs to the corresponding primary factor, wherein each secondary factor is marked with the data property identifier and traceability status identifier, and the traceability status identifier includes at least one of traceable, partially traceable, or non-traceable.

[0074] Optionally, the evaluation module 30 is further configured to: filter out untraceable or partially traceable target secondary factors from the secondary factors based on the traceability status identifier; obtain the evaluation value corresponding to the target secondary factor in the comprehensive evaluation result; determine the non-traceability adaptability index of the target secondary factor based on the weight of the target secondary factor and the evaluation value; compare the non-traceability adaptability index with a preset reliability threshold, and determine the reliability level of the comprehensive evaluation result under non-metric traceability conditions based on the comparison result.

[0075] Optionally, the evaluation module 30 is further configured to randomly sample the secondary factors based on instrument technical indicators, engineering experience, and data dispersion characteristics to obtain multiple sample sets; to perform simulation uncertainty assessment on each sample set to obtain simulation evaluation results; and to perform error analysis on the comprehensive evaluation results based on the simulation evaluation results to obtain the statistical distribution characteristics of the comprehensive evaluation results.

[0076] Optionally, the evaluation module 30 is further configured to perform a second-level fuzzy comprehensive evaluation on the first-level factor based on the membership degree vector and the corresponding second-level weight vector of the second-level factor in the first-level factor, to obtain the comprehensive evaluation value of the first-level factor; and to perform a first-level fuzzy comprehensive evaluation on the first-level factor based on the comprehensive evaluation value and the corresponding first-level weight vector of each of the first-level factors, to obtain the comprehensive evaluation result.

[0077] The uncertainty evaluation device for microwave testing of PE pipes provided in this application, employing the uncertainty evaluation method for microwave testing of PE pipes in the above embodiments, can solve the technical problem of difficulty in evaluating the microwave testing process using existing uncertainty assessment methods. Compared with the prior art, the beneficial effects of the uncertainty evaluation device for microwave testing of PE pipes provided in this application are the same as those of the uncertainty evaluation method for microwave testing of PE pipes provided in the above embodiments, and other technical features in the uncertainty evaluation device for microwave testing of PE pipes are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0078] This application provides an uncertainty evaluation device for microwave testing of PE pipes. The uncertainty evaluation device for microwave testing of PE pipes includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the uncertainty evaluation method for microwave testing of PE pipes in the above embodiment 1.

[0079] The following is for reference. Figure 5 This document illustrates a schematic diagram of a structurally suitable uncertainty evaluation device for implementing microwave testing of PE tubes according to embodiments of this application. The uncertainty evaluation device for microwave testing of PE tubes in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The uncertainty evaluation device for microwave testing of PE tubes shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0080] like Figure 5As shown, the uncertainty evaluation device for microwave testing of PE tubes may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the uncertainty evaluation device for microwave testing of PE tubes. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the uncertainty evaluation equipment for PE tube microwave testing to communicate wirelessly or wiredly with other devices to exchange data. Although the uncertainty evaluation equipment for PE tube microwave testing with various systems is shown in the figure, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0081] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0082] The uncertainty evaluation device for microwave testing of PE pipes provided in this application, employing the uncertainty evaluation method for microwave testing of PE pipes in the above embodiments, can solve the technical problem that it is difficult to evaluate the microwave testing process using existing uncertainty assessment methods. Compared with the prior art, the beneficial effects of the uncertainty evaluation device for microwave testing of PE pipes provided in this application are the same as those of the uncertainty evaluation method for microwave testing of PE pipes provided in the above embodiments, and other technical features in this uncertainty evaluation device for microwave testing of PE pipes are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0083] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0084] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0085] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to perform the uncertainty evaluation method for microwave testing of PE tubes in the above embodiments.

[0086] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0087] The aforementioned computer-readable storage medium may be included in the uncertainty evaluation device for microwave testing of PE tubes; or it may exist independently and not be assembled into the uncertainty evaluation device for microwave testing of PE tubes.

[0088] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the uncertainty evaluation device for microwave testing of PE tubes, the uncertainty evaluation device for microwave testing of PE tubes causes the device to: acquire detection data of uncertainty factors during the microwave testing of PE tubes, wherein the uncertainty factors are labeled with data property identifiers; convert the detection data into membership vectors based on the data property identifiers and corresponding preset conversion rules, wherein the preset conversion rules include membership function conversion based on a combination of trapezoidal and triangular distributions, and direct quantization conversion of weight vectors adjusted based on expert scoring and engineering experience; and perform fuzzy comprehensive evaluation on the uncertainty factors based on the membership vectors and preset weights to obtain a comprehensive evaluation result.

[0089] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0090] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0091] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0092] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the uncertainty evaluation method for microwave testing of PE tubes described above. This solves the technical problem of difficulty in evaluating the microwave testing process using existing uncertainty assessment methods. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the uncertainty evaluation method for microwave testing of PE tubes provided in the above embodiments, and will not be repeated here.

[0093] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the uncertainty evaluation method for microwave testing of PE tubes as described above.

[0094] The computer program product provided in this application can solve the technical problem that it is difficult to evaluate the microwave detection process using existing uncertainty assessment methods. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the uncertainty assessment method for PE tube microwave detection provided in the above embodiments, and will not be repeated here.

[0095] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A method for evaluating the uncertainty of microwave testing of PE pipes, characterized in that, The method includes: Data on uncertainties during microwave testing of PE pipes are obtained, and the uncertainties are marked with data property identifiers. Based on the data property identifier and the corresponding preset conversion rules, the detection data is converted into a membership vector. The preset conversion rules include membership function conversion based on a combination of trapezoidal and triangular distributions, and direct quantization conversion of weight vectors adjusted based on expert scoring and engineering experience. Based on the membership vector and preset weights, a fuzzy comprehensive evaluation is performed on the uncertain factors to obtain a comprehensive evaluation result.

2. The method as described in claim 1, characterized in that, The data property identifier includes quantitative and qualitative identifiers. The step of converting the detection data into a membership vector based on the data property identifier and the corresponding preset conversion rule includes: If the data property identifier is a quantitative identifier, then based on the membership function of the combination of trapezoidal distribution and triangular distribution, the quantitative data in the detection data marked with the quantitative identifier is transformed into a membership vector; If the data property identifier is a qualitative identifier, then based on the weight vector adjusted by expert scoring and engineering experience, the qualitative data in the detection data marked with the qualitative identifier is converted into a membership vector.

3. The method as described in claim 2, characterized in that, Before the step of converting the qualitative data labeled with the qualitative identifier in the detection data into a membership vector based on a weight vector adjusted by expert scoring and engineering experience, if the data property identifier is a qualitative identifier, the method further includes: Obtain the judgment matrix obtained by experts based on their professional knowledge and engineering experience, after comparing the uncertain factors pairwise. Perform a consistency check on the judgment matrix to obtain the consistency ratio of the judgment matrix; If the consistency ratio is not less than the preset consistency threshold, then the judgment matrix is ​​adjusted and the consistency check is performed again until the consistency ratio is less than the preset consistency threshold. If the consistency ratio is less than the preset consistency threshold, then a normalized weight vector is determined based on the judgment matrix.

4. The method as described in claim 1, characterized in that, The uncertainties are divided into primary factors and secondary factors according to a preset hierarchical structure; The primary factors include at least one of the following: instrument performance, environmental conditions, sample characteristics, and operation and data processing. Each of the secondary factors belongs to the corresponding primary factor. Each of the secondary factors is marked with a data property identifier and a traceability status identifier. The traceability status identifier includes at least one of traceable, partially traceable, or untraceable.

5. The method as described in claim 4, characterized in that, After the step of performing a fuzzy comprehensive evaluation of the uncertainty factors based on the membership vector and preset weights to obtain the comprehensive evaluation result, the method further includes: Based on the traceability status identifier, target secondary factors that are either untraceable or partially traceable are selected from the secondary factors; Obtain the evaluation value corresponding to the target secondary factor in the comprehensive evaluation result; Based on the weights of the target secondary factors and the evaluation values, the source-free adaptability index of the target secondary factors is determined; The non-traceability adaptability index is compared with a preset reliability threshold, and the reliability level of the comprehensive evaluation result under non-metric traceability conditions is determined based on the comparison results.

6. The method as described in claim 4, characterized in that, After the step of performing a fuzzy comprehensive evaluation of the uncertainty factors based on the membership vector and preset weights to obtain the comprehensive evaluation result, the method further includes: Based on instrument technical specifications, engineering experience, and data dispersion characteristics, the secondary factors are randomly sampled to obtain multiple sample sets. The simulation uncertainty assessment is performed on each of the aforementioned sample sets to obtain the simulation evaluation results; Based on the simulation evaluation results, error analysis is performed on the comprehensive evaluation results to obtain the statistical distribution characteristics of the comprehensive evaluation results.

7. The method as described in claim 4, characterized in that, The preset weights include the secondary weight vectors corresponding to each of the secondary factors and the primary weight vectors corresponding to each of the primary factors. The step of performing fuzzy comprehensive evaluation on the uncertain factors based on the membership vectors and the preset weights to obtain the comprehensive evaluation result further includes: Based on the membership vectors and corresponding weight vectors of the secondary factors in the primary factors, a secondary fuzzy comprehensive evaluation is performed on the primary factors to obtain the comprehensive evaluation value of the primary factors. Based on the comprehensive evaluation value of each primary factor and its corresponding primary weight vector, a primary fuzzy comprehensive evaluation is performed on the primary factors to obtain the comprehensive evaluation result.

8. An uncertainty evaluation device for microwave testing of PE pipes, characterized in that, The device includes: The acquisition module is used to acquire detection data of uncertain factors during the microwave testing of PE tubes, wherein the uncertain factors are marked with data property identifiers; The conversion module is used to convert the detection data into a membership vector based on the data property identifier and the corresponding preset conversion rules. The preset conversion rules include membership function conversion based on a combination of trapezoidal distribution and triangular distribution, and direct quantization conversion of weight vectors adjusted based on expert scoring and engineering experience. The evaluation module is used to perform fuzzy comprehensive evaluation on the uncertainty factors based on the membership vector and preset weights, and obtain a comprehensive evaluation result.

9. The apparatus as claimed in claim 8, characterized in that, The conversion module is further configured to, if the data property identifier is a quantitative identifier, convert the quantitative data in the detection data marked with the quantitative identifier into a membership vector based on a membership function combining trapezoidal and triangular distributions; and if the data property identifier is a qualitative identifier, convert the qualitative data in the detection data marked with the qualitative identifier into a membership vector based on a weight vector adjusted by expert scoring and engineering experience.

10. An uncertainty evaluation device for microwave testing of PE pipes, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the uncertainty evaluation method for microwave testing of PE tubes as described in any one of claims 1 to 7.

Images