Method, system and device for multi-dimensional evaluation of properties of a reconstituted metal material, and storage medium

Abstract

The application relates to the technical field of material performance evaluation, and discloses a remanufactured metal material performance multidimensional evaluation method, system, device and storage medium. The evaluation method comprises the following steps: establishing an evaluation index system and setting secondary indexes; determining the weights of each primary criterion and each secondary index and performing consistency test; obtaining measured original data; performing synthetic operation on the standardized evaluation value and the weight to obtain a comprehensive performance score; and determining the performance grade of the material to be evaluated. The application constructs a four-dimensional comprehensive evaluation system, scientifically assigns weights by using the analytic hierarchy process to eliminate subjective bias, matches corresponding membership functions according to index attributes to perform data standardization, and finally performs fuzzy evaluation fusion calculation, so that objective and accurate quantitative grading is realized.

Description

Technical Field

[0001] This application relates to the field of material performance evaluation technology, and in particular to a method, system, computer equipment, and computer storage medium for multidimensional evaluation of the performance of reconstituted metallic materials. Background Technology

[0002] Reconstituted metal materials are key basic materials in high-end manufacturing fields such as aerospace, electronic device packaging, and precision instrument manufacturing. With the gradual depletion of primary resources, extracting and recycling various metal materials from secondary resources has become an important way to ensure the supply of related materials. To ensure the reliability and applicability of these reconstituted metal materials in specific application scenarios, a scientific and objective comprehensive evaluation of their various performance indicators is necessary.

[0003] Currently, performance evaluation of reconstituted metal materials typically focuses on assessing single-dimensional technical indicators, such as using conventional component analysis to detect impurity content or conducting single physical property tests. Some existing evaluation methods and standards primarily remain at the level of verifying the technical compliance of the final product. When making comprehensive judgments, they usually rely on expert experience for qualitative assessments or use simple linear scoring methods for summarization.

[0004] However, existing technologies for evaluating reconstituted metal materials have significant shortcomings. First, the evaluation dimensions are too simplistic, failing to incorporate factors such as technological level, economic input, environmental impact, and resource consumption into a unified evaluation system, thus failing to comprehensively reflect the material's overall utilization efficiency. Second, the various test indicators of reconstituted metal materials have different attributes and dimensions, and existing technologies lack standardized processing methods for different quantitative physical parameters, making it impossible to accurately map their actual physical meaning. Furthermore, existing weight allocations often rely excessively on subjective judgment, lacking rigorous weight calculation models and scientific consistency verification mechanisms, resulting in overly subjective evaluation models that cannot output stable and reliable quantitative results.

[0005] In summary, existing material performance evaluation methods are unable to overcome the shortcomings of single evaluation dimensions, strong subjectivity of evaluation results, and lack of standardized processing of multi-source quantitative parameters. They lack a scientific, systematic, and objective multi-dimensional quantitative evaluation method, making it difficult to objectively quantify the superiority and inferiority of reconstituted metal materials under different batches or different process routes, and failing to meet the accurate evaluation needs of reconstituted metal materials for harsh application scenarios. Summary of the Invention

[0006] In a first aspect, the present invention provides a multi-dimensional evaluation method for the properties of reconstituted metallic materials, comprising: Establish an evaluation index system that includes four primary criteria: technological level, economic benefits, environmental impact, and resource and energy consumption, and set secondary indicators under each primary criterion; The weights of each primary criterion and each secondary indicator in the evaluation index system were determined using the analytic hierarchy process (AHP), and a consistency test was performed. Obtain the measured raw data of the material to be evaluated under each of the secondary indicators; match the corresponding membership function according to the attributes of the secondary indicators, and process the measured raw data into dimensionless standardized evaluation values ​​through the membership function; The fuzzy comprehensive evaluation method is used to synthesize the standardized evaluation values ​​and the corresponding weights to obtain the comprehensive performance score of the material to be evaluated. The performance level of the material to be evaluated is determined based on the comprehensive performance score.

[0007] In an optional implementation, the step of using the analytic hierarchy process (AHP) to determine the weights of each primary criterion and each secondary indicator in the evaluation index system, and performing a consistency check, specifically includes: constructing a judgment matrix of the relative importance of each indicator at the same level using the Delphi method; wherein the elements of the judgment matrix are quantified using the 1-9 scale; calculating the maximum eigenvalue and eigenvector of the judgment matrix using the square root method or the sum-product method, and using the normalized eigenvector as the weight of the corresponding indicator; calculating the consistency ratio, and determining the weights to be valid when the consistency ratio is less than 0.10; and / or, The secondary indicators at the aforementioned technical level include at least one of the following: melting point, hardness, wetting angle, sealing leakage rate, impurity content, technological advancement, technological stability, technological maturity, and product qualification rate; and / or, The secondary indicators under the economic benefits mentioned include at least one of the following: equipment input per unit product, operating input per unit product, and annual direct revenue per unit product; and / or, The secondary indicators under the environmental impact assessment include at least one of the following: wastewater discharge per unit product, waste residue generation per unit product, exhaust gas emissions per unit product, and environmental risk prevention and control level; and / or, The secondary indicators under resource energy consumption include at least one of the following: comprehensive energy consumption per unit product, metal recovery rate, and water resource recycling rate.

[0008] In an optional implementation, the step of matching the corresponding membership function based on the attributes of the secondary index includes: For secondary indicators with benefit-related attributes, an upper limit linear membership function is used; For secondary indicators with cost as their attribute, a lower limit linear membership function is used. For secondary indices with critical mutation effect attributes, the S-shaped logistic membership function is adopted; For secondary indicators with an optimal interval range attribute, a parabolic membership function is adopted; For secondary indicators with decay properties over time, an exponential decay membership function is used.

[0009] In an optional implementation, the formula for the S-type logistic membership function is: ; Where x is the measured raw data, x0 is the set threshold midpoint, and k is the steepness coefficient; and / or, The formula for the parabolic membership function is: when hour, For the optimal value, d is the tolerance half-width; and / or, The formula for the exponentially decaying membership function is: ; Where λ is the attenuation coefficient.

[0010] In an optional implementation, before the processing into dimensionless standardized evaluation values, a data preprocessing and veto step is further included, specifically including: Consistency verification is performed on the measured raw data of the logically related secondary indicators. If there is a logical contradiction among the measured raw data, the subsequent comprehensive evaluation calculation is rejected. Multi-point sampling measured data of the same batch of materials to be evaluated are obtained, and the standard deviation and coefficient of variation of the multi-point sampling measured data are calculated. When each of the secondary indicators includes a technical stability indicator and the coefficient of variation exceeds a preset variation threshold, the standardized evaluation value of the technical stability indicator is reduced proportionally. The measured raw data of each of the secondary indicators are compared with a preset absolute rejection threshold. If any measured raw data exceeds the absolute rejection threshold, the material to be evaluated is determined to be unqualified, and the comprehensive performance score is forcibly set to zero, and the comprehensive evaluation calculation is no longer performed. And / or, Before determining the weights of each primary criterion and each secondary indicator in the evaluation index system using the analytic hierarchy process (AHP), the process also includes: Multiple downstream application scenarios and corresponding weight vectors for each scenario are preset. A scenario selection instruction is received from the user. Based on the scenario selection instruction, the corresponding weight vectors are called to update the weights of each primary criterion and each secondary indicator before a comprehensive evaluation is performed; and / or, The multidimensional evaluation method for the properties of reconstituted metallic materials also includes a long-term service performance prediction step, specifically including: Obtain key performance data of the material to be evaluated before and after accelerated aging tests, and calculate the performance degradation rate D; evaluate long-term service stability using an exponential stability membership function, the calculation formula of which is: ; Where k is a preset attenuation sensitivity coefficient; According to the obtained S stab The expected lifespan level of the material to be evaluated is output based on the preset range of the value.

[0011] In an optional embodiment, the multidimensional performance evaluation method for reconstituted metal materials further includes a process reverse diagnostic step: Construct and store an indicator-process correlation mapping library; the indicator-process correlation mapping library records the quantitative correlation between each secondary indicator and the preceding process, controllable process parameters, and the direction of influence; When the standardized evaluation value of any secondary indicator is lower than the preset evaluation value threshold, the indicator-process association mapping library is queried, and controllable process parameter adjustment suggestions are generated and output according to the corresponding influence direction.

[0012] In an optional implementation, the multidimensional evaluation method for the properties of reconstituted metallic materials further includes a feedback learning step, specifically comprising: Record the changes in the indicators of the evaluated material before and after generating the controllable process parameter adjustment suggestions; If the same controllable process parameter adjustment suggestion is used multiple times and the corresponding indicator improvement meets the preset conditions, the recommendation confidence of the controllable process parameter adjustment suggestion in the indicator-process association mapping library will be automatically increased.

[0013] Secondly, the present invention provides a multi-dimensional evaluation system for the properties of reconstituted metallic materials, comprising: The system construction module is used to establish an evaluation index system that includes four primary criteria: technical level, economic benefits, environmental impact, and resource and energy consumption, and to set secondary indicators under each primary criterion. The weight calculation module is used to determine the weights of each primary criterion and each secondary indicator in the evaluation index system using the analytic hierarchy process (AHP), and to perform consistency checks. The data input module is used to acquire the measured raw data of the material to be evaluated under each of the secondary indicators; match the corresponding membership function according to the attributes of the secondary indicators, and process the measured raw data into dimensionless standardized evaluation values ​​through the membership function; The fuzzy evaluation module is used to perform a fuzzy comprehensive evaluation method to synthesize the standardized evaluation values ​​and the corresponding weights to obtain the comprehensive performance score of the material to be evaluated. The results output module is used to determine the performance level of the material to be evaluated based on the comprehensive performance score.

[0014] Thirdly, the present invention provides a computer device, the computer device including a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the multi-dimensional evaluation method for the performance of reconstituted metallic materials as described in any of the foregoing embodiments.

[0015] Fourthly, the present invention provides a computer storage medium storing a computer program, which, when executed on a processor, implements the multi-dimensional evaluation method for the performance of reconstituted metal materials according to any one of the foregoing embodiments.

[0016] The method provided in this application constructs a comprehensive evaluation index system encompassing four dimensions: technological level, economic benefits, environmental impact, and resource and energy consumption. This breaks away from the limitations of previous methods that focused solely on component purity or single physical performance testing, enabling a comprehensive assessment of the material's overall performance throughout its entire lifecycle. By employing the analytic hierarchy process (AHP) to determine the weights of each level of indicators and combining this with a rigorous consistency verification mechanism, the method effectively reduces the subjective bias arising from excessive reliance on personal experience in traditional qualitative assessments, ensuring the objectivity and logical rigor of the weight allocation.

[0017] To address the challenges of varying dimensions and physical properties in different measured data, this application precisely matches the corresponding membership functions to the inherent properties of each test indicator for dimensionless processing. This scientifically transforms discrete quantitative parameters into standard evaluation values, accurately mapping the true physical meaning of the material. Finally, fuzzy comprehensive evaluation is used for information synthesis, deeply integrating qualitative analysis with quantitative calculation. This provides a scientific, stable, and quantifiable accurate evaluation method, effectively meeting the objective ranking requirements for demanding application scenarios. Attached Figure Description

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

[0019] Figure 1 This is a schematic diagram of the hardware operating environment involved in an embodiment of the multi-dimensional evaluation method for the properties of reconstituted metallic materials of the present invention; Figure 2 This is a flowchart illustrating Example 1 of the multidimensional evaluation method for the properties of reconstituted metallic materials according to the present invention. Figure 3A flowchart illustrating the multidimensional evaluation method provided in the embodiments of this application; Figure 4 A schematic diagram of the hierarchical structure of the evaluation index system provided in the embodiments of this application; Figure 5 A schematic diagram of the analytic hierarchy process for determining weights provided in an embodiment of this application; Figure 6 This is a detailed flowchart of step S200 in Example 2 of the multi-dimensional evaluation method for the properties of reconstituted metallic materials of the present invention; Figure 7 This is a detailed flowchart of step S500 in Example 4 of the multi-dimensional evaluation method for the properties of reconstituted metallic materials of the present invention. Figure 8 This is a detailed flowchart of step S800 in Example 4 of the multidimensional evaluation method for the properties of reconstituted metallic materials of the present invention. Figure 9 This is a detailed flowchart of step S900 in Example 4 of the multidimensional evaluation method for the properties of reconstituted metallic materials of the present invention. Figure 10 This is a schematic diagram of the module connections of the multi-dimensional performance evaluation device for reconstructed metallic materials according to the present invention; Figure 11 This is a schematic diagram of the module composition of the evaluation system provided in the embodiments of this application. Detailed Implementation

[0020] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0021] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] In the following, the terms “comprising,” “having,” and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as excluding, firstly, the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations thereof.

[0023] Furthermore, the terms "first," "second," and "third" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0024] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be construed as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.

[0025] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0026] like Figure 1 The diagram shown is a structural schematic of the hardware operating environment of the terminal involved in an embodiment of the present invention.

[0027] The multi-dimensional evaluation system for the performance of reconstituted metal materials according to embodiments of the present invention can be a PC, or a mobile terminal device such as a smartphone, tablet computer, or portable computer. This multi-dimensional evaluation system for the performance of reconstituted metal materials may include: a processor 1001, such as a CPU; a network interface 1004; a user interface 1003; a memory 1005; and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen, an input unit such as a keyboard, or a remote control; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed RAM memory or a stable memory, such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001. Optionally, the multi-dimensional evaluation system for the performance of reconstituted metal materials may also include RF (Radio Frequency) circuitry, audio circuitry, a Wi-Fi module, etc. In addition, the multi-dimensional evaluation system for the performance of reconstituted metal materials can also be equipped with other sensors such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, which will not be elaborated here.

[0028] Those skilled in the art will understand that Figure 1 The multidimensional evaluation system for the properties of reconstituted metal materials shown is not intended to limit it and may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. Figure 1As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a data interface control program, a network connection program, and a multi-dimensional evaluation program for the performance of reconstituted metallic materials.

[0029] Example 1 refer to Figure 2 Embodiment 1 of this application provides a multi-dimensional evaluation method for the performance of reconstituted metal materials. This method objectively evaluates the comprehensive utilization efficiency of reconstituted metal materials by establishing a scientific hierarchical model and mathematical quantitative analysis (for example, it can refer to...). Figure 3 This is one implementation method for a multidimensional evaluation of the properties of reconstituted metallic materials, specifically including the following steps: Step S100: Establish an evaluation index system that includes four primary criteria: technical level, economic benefits, environmental impact and resource and energy consumption, and set secondary indicators under each primary criterion.

[0030] Specifically, in order to overcome the one-sidedness of a single-dimensional evaluation, this embodiment is based on the concept of life cycle assessment, combined with... Figure 4 The hierarchical structure shown constructs a three-tiered evaluation framework: 'Target Layer - Criterion Layer - Indicator Layer'. The target layer provides a comprehensive performance evaluation of remanufactured metallic materials; the criterion layer comprises the four independent yet mutually constraining primary criteria. The technical level criterion characterizes the reliability of the process and physical products; the economic benefit criterion measures the economic feasibility of input and output; the environmental impact criterion examines the ecological burden of the material remanufacturing process; and the resource and energy consumption criterion reflects the energy efficiency and material sustainability of the process. Under each primary criterion, several concrete and measurable secondary indicators are refined based on the actual physicochemical properties of the evaluated materials and industrial application requirements, thus forming an indicator network that comprehensively covers the material's characteristics.

[0031] Step S200: The weights of each primary criterion and each secondary indicator in the evaluation index system are determined using the analytic hierarchy process (AHP), and a consistency check is performed.

[0032] In determining the weights, since the influence of each level of indicator on the final evaluation target differs, it is necessary to assign them quantitative weights. To reduce the influence of subjective judgment, this embodiment can be based on... Figure 5 The illustrated process incorporates the Analytic Hierarchy Process (AHP). In this step, because the influence of each level of indicators on the final evaluation objective differs, they need to be assigned quantitative weights. To reduce the influence of subjective judgment, this embodiment introduces the AHP. For indicators within the same level, a judgment matrix reflecting the relative importance among the indicators is constructed. Subsequently, the eigenvalues ​​and eigenvectors of this judgment matrix are calculated, and the obtained eigenvectors are normalized. The result is the weight of the corresponding indicator.

[0033] To ensure the logical rigor and rationality of the weight allocation results and avoid logical fallacies that contradict each other in the judgment of relative importance, a consistency check must be performed on the judgment matrix simultaneously. The consistency ratio of the judgment matrix is ​​calculated. Only when this ratio meets a set threshold condition can the calculated weights be deemed valid and adopted; otherwise, the logical relationships of the judgment matrix must be revised.

[0034] It should be noted that consistency testing refers to the process of verifying the consistency of the judgment matrix using mathematical indicators when constructing a judgment matrix using the analytic hierarchy process (AHP). This is done to prevent logical contradictions in the evaluator's judgment thinking, such as "A is more important than B, B is more important than C, but C is more important than A." It is a core constraint to ensure the scientific nature of the weights.

[0035] Step S300: Obtain the measured raw data of the material to be evaluated under each of the secondary indicators; match the corresponding membership function according to the attributes of the secondary indicators, and process the measured raw data into dimensionless standardized evaluation values ​​through the membership function.

[0036] During the evaluation process, the first step is to acquire the raw measured data of the evaluated object. Because these objective data contain different physical units (e.g., temperature, concentration, energy consumption), have different dimensions, and exhibit significant differences in data ranges, they cannot be directly used for comprehensive calculations. Therefore, this embodiment uses fuzzy mathematics principles for data standardization.

[0037] Different secondary indicators have different physical meanings and requirements (i.e., different indicator attributes). For example, for some indicators, higher values ​​are better, while for others, lower values ​​are better. Some indicators require strict control within a specific range, and some have obvious performance mutation thresholds. The core of this step is to strictly match the corresponding membership function mathematical model to each secondary indicator based on its inherent physical and economic attributes. The measured raw data with units is substituted into the corresponding membership function as input variables. Through function mapping, it is converted into dimensionless values ​​within a unified range (usually [0,1]), i.e., the standardized evaluation values. This process not only eliminates dimensional barriers but also more accurately characterizes the unique nonlinear evolution laws of different material parameters.

[0038] Step S400: Using the fuzzy comprehensive evaluation method, the standardized evaluation value and the corresponding weight are combined to obtain the comprehensive performance score of the material to be evaluated.

[0039] After data standardization and weight allocation, fuzzy comprehensive evaluation is used for information synthesis. The standardized evaluation values ​​of each level of indicators extracted in step S300 are constructed into a fuzzy relation matrix. Then, using a suitable fuzzy synthesis operator, this fuzzy relation matrix is ​​combined with the corresponding level weight vectors obtained in step S2. This process deeply integrates local, discrete single-indicator state data with the overall dimensional importance preferences, ultimately converging upwards layer by layer to calculate and output a quantitative comprehensive performance score, achieving a scientific transformation from multidimensional complex data to a single evaluation scalar.

[0040] The specific synthesis operation process is as follows: First, establish the evaluation factor set U and the comment set V. Construct a fuzzy relation matrix R based on the standardized evaluation values ​​of each individual indicator. Using the fuzzy synthesis operator, synthesize the weight vector W with the fuzzy relation matrix R to obtain the fuzzy evaluation result vector B: B = W * R. Subsequently, the evaluation result vector B is clarified to obtain the final comprehensive performance score S, calculated as: S = (Σb j f j ) / Σb j Among them, b j f represents the membership degree of the evaluation object to the j-th rating level. j This is the preset score value corresponding to the j-th evaluation level (e.g., 95 for excellent, 85 for good, etc.).

[0041] Step S500: Determine the performance level of the material to be evaluated based on the comprehensive performance score.

[0042] Finally, the system maps the comprehensive performance score calculated in step S4 to the corresponding evaluation level according to the pre-set score division interval, and intuitively outputs the final performance level definition result of the batch of reconstituted metal materials, thus completing the comprehensive evaluation process in all dimensions.

[0043] In summary, this application embodiment constructs an evaluation index system covering four dimensions: technology, economy, environment, and resources, achieving a comprehensive assessment of material performance and overcoming the limitations of single-dimensional evaluation. It utilizes the analytic hierarchy process (AHP) and consistency checks to scientifically allocate weights, eliminating subjective interference from human experience. For multi-source heterogeneous measured data, it standardizes the data by accurately matching membership functions based on index attributes, eliminating dimensional differences and accurately restoring physical properties. Finally, it synthesizes quantitative results through fuzzy comprehensive evaluation, forming a scientific, objective, and stable precise evaluation mechanism.

[0044] Example 2 This application provides a multi-dimensional evaluation method for the performance of reconstituted metal materials in Embodiment 1. When determining the weight of each level of indicators in the evaluation system, this embodiment adopts an integrated weighting mechanism that combines the Delphi method and the Analytic Hierarchy Process (AHP) to balance the depth of professional experience with the rigor of the mathematical model.

[0045] refer to Figure 6 Step S200 involves using the analytic hierarchy process (AHP) to determine the weights of each primary criterion and each secondary indicator in the evaluation index system, and performing a consistency check. Specifically, this includes: Step S210: The Delphi method is used to construct a judgment matrix of the relative importance of each indicator at the same level; wherein the elements of the judgment matrix are quantified using the 1-9 scale method.

[0046] First, a judgment matrix was constructed using the Delphi method. Several industry experts in relevant fields were invited to compare the relative importance of each indicator at the same level pairwise. A 1-9 scale was used for quantitative assignment during the comparison. Specifically, a scale of "1" indicates that the two indicators are equally important, "3" indicates that the former is slightly more important than the latter, "5" indicates that the former is significantly more important than the latter, "7" indicates that the former is strongly more important than the latter, and "9" indicates that the former is extremely more important than the latter. "2, 4, 6, 8" represent the median of the above adjacent judgments; for inverse comparisons, the reciprocal is used. Based on the experts' scores, an inverse judgment matrix reflecting the relative importance between indicators was constructed.

[0047] Table 1. AHP1-9 Scale and Its Meaning

[0048] The 1-9 scale mentioned above is a standard psychological measurement tool in the Analytic Hierarchy Process (AHP), used to transform decision-makers' vague perception of the relative importance of complex issues into a precise numerical matrix that can be calculated by computers or mathematical models.

[0049] Step S220: Calculate the maximum eigenvalue and eigenvector of the judgment matrix using the square root method or the sum-product method, and use the normalized eigenvector as the weight of the corresponding index.

[0050] Secondly, the weight vector is extracted. This embodiment uses the square root method to calculate the maximum eigenvalue and eigenvector of the judgment matrix. The calculation process may include, for example: The first step is to calculate the geometric mean M of each row of the judgment matrix. i The formula (Formula 1) is: ; Where n is the matrix order, a ij For matrix elements; The second step is to normalize the obtained geometric mean to obtain the weight W of the i-th indicator. i Formula (Formula 2) is: Thus, the comprehensive weight vector of each indicator is obtained.

[0051] The third step is to calculate the largest eigenvalue λ of the judgment matrix. max Formula (Formula 3) is: ; Where A is the judgment matrix and W is the weight vector.

[0052] Step S230: Calculate the consistency ratio. When the consistency ratio is less than 0.10, the weight is determined to be valid.

[0053] To ensure that experts do not encounter logical conflicts when performing pairwise comparisons of multiple indicators, a consistency check must be performed. The system uses formula (Formula 4): CI = (λ) max n) / (n-1); Calculate the consistency index CI, and introduce the average random consistency index RI of the corresponding order, and then obtain the consistency ratio CR = CI / RI.

[0054] Table 2. Standard values ​​of the consistency index RI

[0055] When the calculated CR < 0.10, the system determines that the judgment matrix has satisfactory consistency, and the extracted weight data is true and valid and adopted; if CR ≥ 0.10, it prompts that the judgment matrix needs to be readjusted until it passes the test.

[0056] Furthermore, regarding the indicator framework of the evaluation system, this embodiment, targeting the high-end application needs of remanufactured metal materials, has refined the four primary criteria in depth, specifically including: The secondary indicators at the aforementioned technical level include at least one of the following: melting point, hardness, wetting angle, sealing leakage rate, impurity content, technological advancement, technological stability, technological maturity, and product qualification rate. These indicators characterize the reliability of the material from both physical properties and engineering manufacturing dimensions.

[0057] Furthermore, the secondary indicators under the economic benefits include at least one of the following: equipment input per unit product, operating input per unit product, and annual direct revenue per unit product. These are used to quantify the cost-effectiveness of the regeneration process.

[0058] Furthermore, the secondary indicators under the environmental impact include at least one of the following: wastewater discharge per unit product, waste residue generation per unit product, exhaust gas emission per unit product, and environmental risk prevention and control level. This aims to examine the environmental impact of the process.

[0059] Furthermore, the secondary indicators under resource energy consumption include at least one of the following: comprehensive energy consumption per unit product, metal recovery rate, and water resource recycling rate. These are used to evaluate the energy and material recycling efficiency of the production process. Through the synergy of the above multi-dimensional indicators, a comprehensive and three-dimensional quantitative deconstruction of material performance is achieved.

[0060] In some implementations, after constructing the evaluation index system and obtaining the measured raw data, the data needs to be standardized. Since different secondary indicators have different physical units (e.g., temperature °C, content ppm, angle °, etc.) and their numerical magnitudes differ significantly, direct mathematical synthesis is not possible. Therefore, this embodiment, based on fuzzy mathematics theory and the inherent physical properties of each secondary indicator, precisely matches its corresponding membership function, thereby mapping the dimensional measured raw data to dimensionless standardized evaluation values ​​within the interval [0,1]. The specific matching rules and implementation methods are as follows: For secondary indicators with benefit-related attributes, an upper limit linear membership function is used.

[0061] Benefit-oriented indicators refer to those indicators where, under specific constraints, a higher value represents better performance or benefit (e.g., metal recovery rate, product qualification rate, etc.). The system presets a lower threshold (i.e., the lowest acceptable technical benchmark) and an upper threshold (i.e., the industry-leading ideal optimal value) for these indicators. When the measured raw data is less than or equal to the lower threshold, the standardized evaluation value is 0; when the measured raw data is greater than or equal to the upper threshold, the standardized evaluation value is 1; when it falls between the two, a linear interpolation method is used to calculate its standardized evaluation value, thus objectively reflecting the benefit level of the linear growth of the indicator.

[0062] Specifically, the formula for calculating the upper limit linear membership function is: when x ≥ x max When x = 1, S = 1; when x = 1, S = 1. min <x<x max When, S=(xx) min ) / (x max -x min When x ≤ x min When S=0.

[0063] Where x is the original measured data of this indicator, x max x represents the upper limit (ideal value) of this indicator. min This is the lower limit threshold (the lowest acceptable value) for this indicator.

[0064] For secondary indicators with cost attributes, a lower limit linear membership function is used.

[0065] Cost-based indicators refer to those where smaller values ​​represent better performance or lower costs (e.g., comprehensive energy consumption per unit of product, wastewater discharge per unit of product). In contrast to benefit-based indicators, the system uses a reverse linear mapping for these indicators. When the measured raw data is less than or equal to the ideal lower threshold, the standardized evaluation value is 1; when the measured raw data exceeds the allowable upper threshold, the evaluation value is directly set to 0; data in the intermediate range show a linear decrease in evaluation value as the value increases.

[0066] Specifically, the formula for calculating the lower bound linear membership function is as follows: When x≤x min At that time, S=1; When x min <x<x max At that time, S=(x max -x) / (x max -x min ); When x ≥ xmax, S = 0.

[0067] For secondary indices with critical mutation effect attributes, the S-type logistic membership function is used.

[0068] In the field of remanufactured metallic materials, the impact of certain technical indicators (especially the content of trace harmful impurities) on overall performance is not a uniform linear gradient, but rather exhibits a significant "critical abrupt change effect." For example, when a trace impurity in a material moves within a low concentration range, it has little effect on the wettability or conductivity of the alloy; however, once its concentration crosses a certain critical threshold midpoint, the macroscopic properties of the material will deteriorate precipitously. For such indicators, traditional linear normalization cannot truly reflect their physical laws. This embodiment introduces an S-shaped logistic curve for nonlinear mapping. By setting a specific threshold midpoint and steepness coefficient, the function exhibits a very steep slope near the critical abrupt change point. The effect is that near the critical point, even an extremely small increase in impurity content can lead to a drastic decay in the standardized evaluation value, thereby enabling the evaluation system to have a very high sensitivity to identify potential abrupt failure risks.

[0069] For secondary indicators that have an optimal range attribute, a parabolic membership function is used.

[0070] Some mechanical and physical properties (such as the hardness of alloy materials or specific heat treatment temperatures) exhibit a clear "optimal middle ground" characteristic. This means that excessively low values ​​lead to insufficient strength, while excessively high values ​​cause adverse effects such as increased brittleness and a sharp drop in plasticity. For these indicators where data must fall within the "optimal range," this embodiment uses a parabolic membership function. The optimal design parameter value of the material is used as the vertex of the parabola (where the standardized evaluation value is 1), and a tolerance half-width is set based on the allowable tolerance range of the process. When the measured data deviates from the optimal value, the evaluation value smoothly decays symmetrically or asymmetrically in the form of a quadratic parabola until it exceeds the tolerance boundary, at which point the evaluation value returns to zero. This perfectly aligns with the engineering control logic of pursuing a balanced middle ground for such parameters.

[0071] For secondary indicators with decay properties over time, an exponential decay membership function is used.

[0072] The membership function mentioned above is a core concept in fuzzy mathematics, used to characterize the degree to which an element belongs to a certain fuzzy set. In this scheme, it serves as a mathematical transformation tool, accurately translating complex physical quantities into absolute scores between 0 and 1 that the system can recognize.

[0073] For performance parameters of materials that are prone to aging degradation during long-term service (such as the sealing leakage rate and surface wear rate of precision packaging materials), even a small deterioration in these parameters often foreshadows a significant reduction in service life. Therefore, the system employs an exponentially decaying membership function, utilizing the negative exponential property of the natural base e, to ensure that when the measured value of an indicator shows an increasing trend (i.e., degradation), its standardized evaluation value declines rapidly in an exponential manner. This nonlinear processing mechanism effectively amplifies the degradation weight of aging-sensitive parameters, providing a rigorous mathematical constraint for material reliability assessment.

[0074] To further overcome the technical shortcomings of traditional evaluation systems where simple linear scoring cannot accurately reflect the complex physical evolution of materials, this embodiment provides a precise-matching underlying nonlinear mathematical operation model for the secondary indicators of specific attributes. The specific standardized calculation process and formula are as follows: For secondary indicators exhibiting critical mutation effects, a S-shaped logistic membership function is used for mathematical mapping. In high-end applications of reconstituted metallic materials, the influence of certain key indicators (such as the impurity content of specific harmful trace elements) on overall performance is not linear, but rather exhibits a clear triggering critical point. The formula for the S-shaped logistic membership function (Formula 5) is as follows: ; Where x is the original measured data of the index, x0 is the midpoint of the threshold set in advance based on the material physics experiment, which represents the critical data point where the material properties undergo a sudden reversal; k is the steepness coefficient, which is used to control the sensitivity of the S-curve near the critical point.

[0075] Taking harmful lead impurities in reconstituted indium-based alloy materials as an example, if preliminary physical experiments show that the wettability changes gradually when the impurity content is below 50 ppm, but increases sharply beyond 80 ppm leading to failure, the wetting angle can be set to a specific value between these two values, along with a specific steepness coefficient k. This formula ensures that when the measured data x fluctuates around the critical point x0, the output membership evaluation value S decays rapidly, thus perfectly simulating the objective physical phenomenon of abrupt material failure at the mathematical evaluation level, significantly improving the sensitivity of the evaluation.

[0076] In some implementations, parabolic membership functions are used for mathematical mapping of secondary indices with an optimal range attribute. Parameters such as material hardness and specific heat treatment temperatures are not sought to be infinitely large or small, but rather are required to fall strictly within an optimal central range. The formula for the parabolic membership function (Formula 6) is: when hour, Otherwise, that is, when At that time, S=0; In the above formula, x is also the original measured data; x opt d represents the optimal target value pursued by the material (i.e., the location of the vertex of the parabola); d represents the maximum allowable half-width in engineering (i.e., the single-sided tolerance limit).

[0077] For example, evaluating the hardness of a certain aerospace-grade remanufactured nickel-based superalloy used in turbine disk manufacturing. Assume the optimal hardness requirement for this component is 385 HV; a deviation too high will lead to decreased plasticity, while a deviation too low will result in insufficient strength, and the maximum allowable fluctuation range in engineering is ±70 HV. In this case, the system assigns x... opt =385. d=70. When the measured hardness is exactly equal to 385HV, the dimensionless score S is a full score of 1; when the measured value drifts to both sides, the score decreases smoothly at a quadratic rate; once the absolute value of the deviation exceeds the tolerance limit of 70HV, the formula directly outputs 0 points, realizing strict punishment for exceeding the process "sweet spot" parameters.

[0078] In some implementations, an exponentially decaying membership function is used for mathematical mapping of secondary indicators that have decay properties over time.

[0079] For applications such as aerospace sealing components, where long-term reliability requirements are extremely high, parameters such as sealing leakage rate and wear rate often exhibit non-linear degradation characteristics. Even a small increase in these values ​​represents a very high risk of failure. For these indicators, this embodiment uses the following formula for calculation: The formula (Formula 7) for the exponentially decaying membership function is as follows: ; Wherein, λ is the degradation coefficient. This value is determined by the degradation sensitivity of the material itself. This formula utilizes the negative exponential degradation characteristic of the natural base e. Its implementation mechanism is that when the index data x with time decay characteristics shows a slight increase in degradation, the formula can mathematically amplify this risk in an exponential form, causing the standardized evaluation value S to drop sharply, thus providing a more rigorous mathematical model for assessing the long-term service reliability of materials.

[0080] Example 3 Embodiment 1 of this application provides a multi-dimensional evaluation method for the performance of reconstituted metallic materials. To further adapt to the complex data environment of industrial sites, meet the stringent requirements of different downstream industrial chains, and achieve a comprehensive assessment of the material's entire lifecycle, this embodiment expands upon the basic evaluation model by incorporating data preprocessing, scenario adaptation, and service performance prediction mechanisms. Specific implementation details are as follows: refer to Figure 7 In some implementations, before step S300, which processes the data into dimensionless standardized evaluation values, a step S500 is included: data preprocessing and a veto step. That is, considering the industrial characteristics of large fluctuations in the composition of reconstituted metal materials and the susceptibility of multi-source data to errors, a multi-dimensional data verification and interception mechanism is introduced before performing the mapping process from the measured raw data to dimensionless standardized evaluation values. Specifically, this includes: Step S510: Perform consistency verification on the measured raw data of the secondary indicators that are logically related. If there is a logical contradiction among the measured raw data, refuse to execute the subsequent comprehensive evaluation calculation.

[0081] The system performs consistency checks on the measured raw data of the logically related secondary indicators. For example, the system automatically compares the input "overall material purity" with the "trace impurity content" data. If a logical contradiction is found (e.g., the nominal purity is 99.999%, but the measured input of the single impurity Pb ​​content is as high as 200ppm), the system immediately generates a logical conflict warning and refuses to execute subsequent comprehensive evaluation calculations, thereby cutting off the input source of erroneous data.

[0082] Step S520: Obtain multi-point sampling and measurement data of the same batch of materials to be evaluated, and calculate the standard deviation and coefficient of variation of the multi-point sampling and measurement data.

[0083] Step S530: When each of the secondary indicators includes a technical stability indicator and the coefficient of variation exceeds a preset variation threshold, the standardized evaluation value of the technical stability indicator is reduced proportionally. Step S540: Compare the measured raw data of each of the secondary indicators with the preset absolute veto threshold. If any of the measured raw data exceeds the absolute veto threshold, the material to be evaluated is determined to be unqualified, and the comprehensive performance score is forcibly set to zero and no further comprehensive evaluation calculation is performed.

[0084] Perform batch-level volatility evaluation. The system acquires multi-point sampling measurement data of the same batch of materials to be evaluated, and uses statistical algorithms to calculate the standard deviation σ and coefficient of variation CV (CV=σ / μ) of the data set. When each of the secondary indicators includes a technical stability indicator, and the calculated coefficient of variation exceeds a preset variation threshold (e.g., 5%), the system automatically reduces the standardized evaluation value of the technical stability indicator by a specific ratio (e.g., multiplied by 1-CV), thereby objectively penalizing materials with poor batch consistency.

[0085] Finally, a veto logic is implemented. The system compares the measured raw data of each of the secondary indicators with the preset absolute veto thresholds (safety or technical red lines) in the database one by one. If any of the measured raw data exceeds the absolute veto threshold, the system determines that the material to be evaluated is unqualified, forcibly sets the final comprehensive performance score to zero, and immediately terminates the subsequent fuzzy comprehensive evaluation calculation, strictly adhering to the technical bottom line of high-end applications.

[0086] In some implementations, before step S200, which uses the analytic hierarchy process (AHP) to determine the weights of each primary criterion and each secondary indicator in the evaluation index system, the method further includes: Step S600: Preset multiple downstream application scenarios and corresponding weight vectors for each scenario; receive scenario selection instructions input by the user; update the weights of each primary criterion and each secondary indicator by calling the corresponding weight vectors according to the scenario selection instructions, and then perform a comprehensive evaluation.

[0087] Different downstream application scenarios have significantly different performance focuses for remanufactured metal materials. This embodiment pre-defines multiple downstream application scenarios (such as aerospace-grade, high-end electronic packaging, cost-priority, etc.) in the system database and configures weight vectors for each scenario corresponding to its specific demand tendencies at the criterion and indicator levels. Before using the analytic hierarchy process (AHP) to determine the weight matrix for comprehensive calculation, the system provides a human-computer interaction interface to receive user-input scenario selection commands. After receiving the command, the system dynamically calls the weight vector matching the scenario, updates the basic weights covering each primary criterion and each secondary indicator, and then performs fuzzy synthesis calculations. This mechanism enables the same algorithm architecture to automatically adapt to the differentiated evaluation needs of multiple industry dimensions.

[0088] Specifically, the downstream application scenarios and their corresponding criterion layer weight vectors preset in this embodiment are shown in Table 3 below: Table 3. Scene Adaptive Weight Vector Mapping Table

[0089] Referring to Table 4, when a user selects the "Aerospace Grade" scenario through the human-computer interaction interface, the system automatically increases the weight of technical level to 0.55 to reflect the extreme requirements for reliability and advancement in this field; while when the "Cost Priority" scenario is selected, the system dynamically adjusts the weight of economic benefits to 0.60. This scenario-driven dynamic weight update mechanism ensures that the evaluation results accurately match the actual application preferences of different industries.

[0090] Taking the reconstituted In93Ag7 alloy solder in Experiment Example 1 as an example: under the weighting of the 'Aerospace Grade' scenario (technical level weight 0.1837, economic benefit 0.4413, environmental impact 0.2952, resource and energy consumption 0.0798), its final calculated score is 78.5 points. If the application scenario is switched to 'Civilian Electronic Packaging Grade', the system calls the corresponding weight vector (0.30, 0.50, 0.10, 0.10) to recalculate, and its comprehensive performance score becomes: S'=0.30×0.8137+0.50×0.75+0.10×0.82+0.10×0.78≈77.9 points. The dynamic adjustment of the score intuitively demonstrates the difference in applicability evaluation of the same material under different industrial orientations.

[0091] In some embodiments, the multidimensional evaluation method for the properties of reconstituted metallic materials further includes step S700, a long-term service performance prediction step, specifically including: Step S710: Obtain key performance index data of the material to be evaluated before and after the accelerated aging test, and calculate the performance degradation rate D; To overcome the limitations of static evaluation, this embodiment introduces accelerated aging test data for lifetime prediction. Specifically, the system acquires key performance index data (such as initial shear strength and post-aging shear strength) of the material under evaluation before and after accelerated aging tests (e.g., high-temperature thermal storage tests), and calculates the performance degradation rate D. For benefit-related indicators, the specific formula for the degradation rate is typically as follows: D=1-P aged / P initial .

[0092] Step S720: The long-term service stability is evaluated using an exponential stability membership function, calculated using the formula (Formula 8): ; Where k is a preset attenuation sensitivity coefficient.

[0093] After obtaining the attenuation rate, the long-term service stability of the material is evaluated using an exponential stability membership function, and its mathematical calculation formula is Equation 7 above.

[0094] In the above formula, k is a preset attenuation sensitivity coefficient, the value of which is determined by the physical properties of the material itself and the specific aging conditions (for example, for brazing filler metals used in aerospace sealing, the system sets a larger k value to amplify the aging risk). This exponential formula ensures that when the attenuation rate shows a deteriorating trend, the stability score can decline exponentially and rapidly.

[0095] Step S730, based on the obtained S stab The expected lifespan level of the material to be evaluated is output based on the preset range of the value.

[0096] Finally, the system uses the calculated S stab The value is compared with the preset stability grading range, and the expected lifespan level of the material to be evaluated is output (e.g., outputting different levels such as lifespan greater than 10 years, 5 to 10 years, etc.), providing a reliable and forward-looking decision-making basis for high-end long-life application scenarios.

[0097] The coefficient of variation mentioned above is a normalized measure of the dispersion of a probability distribution, defined as the ratio of the standard deviation to the mean. In this scheme, it is used to measure the degree of performance fluctuation of a material over spatial sampling or time batches.

[0098] Example 4 Embodiment 1 of this application provides a multi-dimensional evaluation method for the performance of reconstituted metallic materials. To overcome the technical shortcomings of traditional material performance evaluation, which often remains at the static score level and cannot directly guide upstream production and manufacturing, this embodiment, based on the obtained evaluation scores, further introduces a process reverse diagnosis mechanism, realizing an industrial closed loop of "evaluation-diagnosis-optimization." Specific implementation details are as follows: refer to Figure 8 The multidimensional evaluation method for the properties of reconstituted metal materials further includes step S800, a process reverse diagnosis step: Step S810: Construct and store the indicator-process correlation mapping library; the indicator-process correlation mapping library records the quantitative correlation between each secondary indicator and the preceding process, controllable process parameters, and the direction of influence.

[0099] During system initialization or early deployment, a structured "index-process correlation mapping library" is constructed based on materials science mechanisms, historical production data, and industry expert experience, and persistently stored in the system's database. This mapping library aims to establish a quantitative or semi-quantitative mapping relationship between backend performance and frontend manufacturing processes.

[0100] Specifically, the mapping library accurately records the correlation between each secondary indicator and the preceding process steps, controllable process parameters, and the direction of influence.

[0101] The term "preceding process" refers to one or more physical / chemical processing steps that determine the performance of a particular indicator, such as vacuum melting, rolling, or heat treatment. "Controllable process parameters" refer to specific physical quantities that can be adjusted manually in this process, such as refining temperature, annealing time, and cold working deformation. "Direction of influence" refers to whether the increase or decrease of the controllable parameter has a positive promoting effect or a negative inhibiting effect on the corresponding performance indicator.

[0102] For example, for reconstituted indium-based alloy materials, a rule recorded in the mapping library may be: the associated process of the secondary index "wetting angle" is "vacuum melting", and the corresponding controllable process parameters are "refining temperature" and "holding time", and the "direction of influence" is negatively correlated (that is, the higher the temperature and the longer the time, the smaller the wetting angle is usually, and the better the wetting performance).

[0103] Table 4. Example of Index-Process Association Mapping Library

[0104] Step S820: When the standardized evaluation value of any secondary indicator is lower than the preset evaluation value threshold, query the indicator-process association mapping library, generate controllable process parameter adjustment suggestions according to the corresponding influence direction, and output them.

[0105] During the evaluation process, the system monitors the dimensionless "standardized evaluation value" obtained after processing each secondary indicator using a membership function in real time. The system pre-sets an evaluation value threshold (this threshold typically represents the tolerable performance baseline in engineering, for example, set to 0.6). When the system detects that the standardized evaluation value of any one or more secondary indicators is lower than the preset threshold, the system immediately marks the indicator as a "bottleneck indicator" and automatically triggers a reverse diagnostic procedure. After triggering, the system uses the name identifier of the bottleneck indicator as the retrieval basis to search the indicator-process association mapping library, quickly identifying the associated upstream process steps that cause the performance bottleneck and their corresponding controllable process parameters.

[0106] After extracting the relevant process parameters and their influencing directions, the system's built-in diagnostic logic reasoning engine automatically generates specific engineering adjustment instructions based on the "influence direction." Specifically, the generation logic is as follows: if a controllable process parameter is found to be negatively correlated with the optimization direction of the bottleneck indicator, the system generates a suggestion to "appropriately increase" that parameter; if it is positively correlated, it generates a suggestion to "appropriately decrease" that parameter.

[0107] Subsequently, the system formats and assembles the "shortcoming indicator name + related process steps + suggested controllable process parameters and their direction" to generate intuitive suggestions for adjusting controllable process parameters (e.g., output: "Diagnosis revealed a shortcoming indicator: poor wetting angle performance; suggested improvement direction: appropriately increase the refining temperature in the vacuum melting process and extend the holding time"), and outputs it to production technicians along with the final comprehensive evaluation report. This mechanism breaks down the information barriers between evaluation and production, enabling each evaluation to be transformed into a concrete action guide to drive process optimization.

[0108] In some implementations, to ensure that the system's process optimization suggestions better align with the complex actual conditions of industrial sites and avoid the incompatibility of static rules across different production lines, this embodiment further introduces a data-driven feedback learning step on top of process reverse diagnosis. This enables the system to possess the ability for self-iteration and positive reinforcement of its knowledge base. Specific implementation details are as follows: refer to Figure 9 The multidimensional evaluation method for the properties of reconstituted metallic materials further includes step S900, a feedback learning step, specifically including: Step S910: Record the changes in the indicators of the evaluated material before and after generating the controllable process parameter adjustment suggestions.

[0109] After the system outputs controllable process parameter adjustment suggestions for specific bottleneck indicators, the system initiates a tracking and verification mechanism to continuously record the indicator changes of the evaluated material before and after the generation of the suggestions. Specifically, the system extracts the measured performance data of the initial batch of material that triggered the diagnostic suggestion and compares it with the re-inspection data of the new batch of material produced after the adoption of the process adjustment suggestion to accurately calculate the specific indicator improvement (i.e., the increment or percentage change in performance data) brought about by the adjustment. This process binds the abstract diagnostic suggestion with the objective physical improvement results, forming a closed-loop empirical sample.

[0110] Step S920: If the same controllable process parameter adjustment suggestion is used multiple times and the corresponding index improvement magnitude meets the preset conditions, the recommendation confidence of the controllable process parameter adjustment suggestion in the index-process correlation mapping library is automatically increased.

[0111] Based on this, the system's built-in feedback learning engine monitors and statistically analyzes the execution effect of each diagnostic suggestion in real time. If the same controllable process parameter adjustment suggestion is adopted multiple times in actual production (i.e., the adoption frequency reaches a preset statistical base), and the improvement magnitude of the corresponding indicator calculated based on the aforementioned comparison meets preset conditions (e.g., the average improvement magnitude of the dimensionless evaluation value of the indicator exceeds a set threshold, or the indicator is successfully changed from unqualified to qualified), then the system determines that the suggestion has high effectiveness and universality in the current production environment. Subsequently, the system automatically triggers an update algorithm to improve the recommendation confidence of the controllable process parameter adjustment suggestion in the underlying indicator-process association mapping library. As the confidence value is continuously accumulated and dynamically updated, when encountering the same performance shortcomings in the future, the system will prioritize outputting process adjustment schemes with higher confidence, thereby realizing the adaptive closed-loop evolution of the process diagnostic knowledge base.

[0112] The aforementioned recommendation confidence level refers to the quantitative weight value that characterizes the reliability of a specific reasoning rule or suggested strategy in an expert system or recommendation algorithm model. In this scheme, a process adjustment suggestion with a higher confidence level indicates that it has undergone more thorough practical verification in historical actual production, and the probability that it will be prioritized by the system and ultimately resolve material performance defects is also greater.

[0113] To further verify the practical application effect of the multidimensional evaluation method described in this application, specific experimental examples are provided below. However, it should be understood that these experimental examples are only for more detailed explanation and should not be construed as limiting the present invention in any way.

[0114] Experimental Example 1: Suitability Evaluation of Reconstituted In93Ag7 Alloy Brazing Filler for Aerospace Sealing This experimental example aims to examine the complete evaluation and optimization process of the multidimensional evaluation method of the present invention in specific industrial materials (reconstituted In93Ag7 alloy brazing filler metal) and specific high-end application scenarios (aerospace sealing).

[0115] 1. Construction of the experimental method indicator system: referring to Figure 4 The hierarchical structure shown illustrates the evaluation index system for indium-based solders. Under the primary criterion "Technical Level A1", secondary indicators such as "melting point", "hardness", "wetting angle", "sealing leakage rate" and "impurity content" are set.

[0116] Weighting determination: Ten domain experts were invited to determine the weighting based on... Figure 5 Perform AHP analysis using the procedure shown. Construct a judgment matrix for the indicators under "Technical Level A1" (see Table 5 below).

[0117] Data standardization: Obtain the original measured data of the materials to be evaluated. Perform standardization by matching the corresponding membership function according to the indicator attributes.

[0118] Comprehensive evaluation: Information synthesis is performed using the fuzzy comprehensive evaluation method.

[0119] Reverse diagnostics: For the identified weak indicators, optimization suggestions are generated by querying the "indicator-process" correlation mapping library.

[0120] 2. Experimental Results and Analysis: Weight calculation results: The expert judgment matrix is ​​shown in Table 5.

[0121] Table 5. Technical Level A1 Level Indicator Judgment Matrix

[0122] After calculation and consistency verification, the weight vector W is obtained. A1 =(0.118,0.062,0.189,0.428,0.204).

[0123] Standardization results: The measured data and standardized scores are shown in Table 6.

[0124] Table 6. Results of Standardization Processing of Indicator Data

[0125] Comprehensive evaluation and analysis: The composite calculation yields a score of 0.8137 for the technology level dimension. Combining the scores of other dimensions (economy 0.75, environment 0.82, resources 0.78) and the weights of the criteria layer, the final comprehensive performance score is S=78.5, corresponding to a performance level of "medium".

[0126] The results indicate that the material meets general industrial sealing requirements, but improvements in leakage rate and wetting angle are needed for aerospace applications.

[0127] Process optimization suggestions: The optimization suggestions generated by the system are shown in Table 7.

[0128] Table 7. Recommendations for Process Reverse Diagnosis and Optimization

[0129] Experiment Example 2: Data Fluctuation Processing and Veto Experiment in Reconstructing Nickel-Based Superalloys This experimental example aims to examine the decision-making logic of this evaluation method in dealing with component fluctuations and fatal defects in industrial production.

[0130] 1. Experimental Method: Multi-point sampling and testing were performed on a batch of remanufactured nickel-based superalloys to obtain hardness distribution data and the content of key impurities (sulfur). The system executed a data reliability preprocessing procedure.

[0131] 2. Experimental Results and Analysis: Fluctuation handling: The obtained hardness multi-point sampling measured data are: 380, 420, 390, 410, 350 HV. The calculated mean μ = 390, and the coefficient of variation CV = 6.3%. Since CV > 5%, the system determines that the data fluctuation is large, automatically corrects the membership degree of the "Technical Stability" index from 0.80 to 0.80 × (1 - 0.063) = 0.75, and issues a re-inspection prompt.

[0132] One-vote veto execution: If the sulfur content of the harmful element is found to be 0.05% during testing, exceeding the preset absolute veto threshold of 0.02%, the system will directly determine the batch of materials as "unqualified" based on the "one-vote veto" logic, forcibly set the comprehensive performance score to 0, and output the reason: "Sulfur content exceeds the standard, does not meet the requirements for use in high-temperature alloys".

[0133] Experimental Example 3: Accelerated Aging Test and Expected Life Prediction of Reconstituted Gold-Based Solder This experimental example aims to examine the predictive effectiveness of this method in assessing the long-term service reliability of materials.

[0134] 1. Experimental Method: Obtain shear strength data for a batch of reconstituted gold-based brazing filler metal before and after an accelerated aging test (heat storage at 200℃ for 500 hours). Evaluate the stability using an exponential stability membership function.

[0135] 2. Experimental Results and Data Recording: The initial shear strength was 85 MPa, which decreased to 75 MPa after aging.

[0136] Calculation and Prediction: The system calculates a performance degradation rate D = 0.1176. Setting the degradation sensitivity coefficient k = 3, the stability score S is calculated using an exponential function.stab =0.702.

[0137] Predicted conclusion: Based on the rating mapping, the expected service life of this material is "Good" (5-10 years). Its actual service life in environments below 200℃ is estimated to be approximately 8 years.

[0138] Comparative Example 1: Traditional Single Linear Evaluation Method This comparative example aims to verify, by comparing it with Experimental Example 1, the significant advantages of the multidimensional nonlinear membership model used in this application in identifying high-end defect materials.

[0139] Experimental methods: The original data of the reconstituted In93Ag7 alloy solder, identical to those in Experimental Example 1, were used (Pb impurities 45 ppm, sealing leakage rate 1.3 × 10⁻⁶). -10 Pa·m 3 / s).

[0140] The difference lies in the fact that Comparative Example 1 only examines technical indicators, and all indicators use a simple direct linear scoring method without introducing S-shaped mutation functions and parabolic functions for correction penalties. Experimental results and analysis: Under the traditional linear scoring mode, since the Pb impurity (45ppm) has not yet reached the absolute exceedance threshold, its linear score is extremely high (approximately 90 points or more), and the material is ultimately rated as "excellent".

[0141] In Experiment 1 of this application, the Pb index score was corrected and weighted by the sigmoid membership function to capture mutation risk. Combined with multi-dimensional indicators such as economy and environment, the final score was only 78.5 points (medium), which was accurately intercepted and required process optimization.

[0142] This comparison demonstrates that the method of this application can effectively identify potential risks in high-end applications that are easily missed by traditional evaluation systems, and has higher evaluation accuracy and engineering practical value.

[0143] Experiment Example 4: Evolution of Feedback Learning in the Reverse Diagnostic Mapping Library This experimental example aims to verify the system's ability to self-optimize and learn from process recommendations.

[0144] Experimental Method: For the "wetting angle" shortcoming observed in 10 consecutive production batches, the system recommended increasing the vacuum refining temperature to 250℃. The system continuously recorded the performance changes of new batches of material after this recommendation was adopted.

[0145] Experimental Results and Analysis: Statistics showed that in the eight batches that adopted the recommendation, the wetting angle performance improved by an average of 25%, meeting the preset "significant improvement" threshold. The system automatically executed a confidence update algorithm, increasing the recommendation confidence of this process rule in the mapping library from the initial 0.60 to 0.92. In subsequent evaluations, if a weakness in the wetting angle reappears, the system will prioritize pushing this high-confidence optimization solution. This confirms that the system possesses the ability for dynamic knowledge evolution.

[0146] refer to Figure 10 This application also provides a multi-dimensional evaluation system for the properties of reconstituted metal materials (see schematic diagram of the module composition of the evaluation system). Figure 11 ),include: System construction module 10 is used to establish an evaluation index system that includes four primary criteria: technical level, economic benefits, environmental impact and resource and energy consumption, and to set secondary indicators under each primary criterion; The weight calculation module 20 is used to determine the weights of each primary criterion and each secondary indicator in the evaluation index system using the analytic hierarchy process (AHP), and to perform consistency checks. The data input module 30 is used to acquire the measured raw data of the material to be evaluated under each of the secondary indicators; match the corresponding membership function according to the attributes of the secondary indicators, and process the measured raw data into dimensionless standardized evaluation values ​​through the membership function; The fuzzy evaluation module 40 is used to perform a fuzzy comprehensive evaluation method to synthesize the standardized evaluation value with the corresponding weight to obtain the comprehensive performance score of the material to be evaluated. The result output module 50 is used to determine the performance level of the material to be evaluated based on the comprehensive performance score.

[0147] It is understood that the apparatus in this embodiment corresponds to the multi-dimensional evaluation method for the performance of reconstituted metal materials in the above embodiments, and the options in the above embodiments are also applicable to this embodiment, so they will not be described again here.

[0148] This application also provides a computer device, which includes a processor and a memory. The memory stores a computer program, and the processor executes the computer program to implement the multi-dimensional evaluation method for the performance of reconstituted metal materials as described in any of the foregoing embodiments.

[0149] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0150] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory is used to store computer programs, and the processor can execute the computer programs accordingly after receiving execution instructions.

[0151] This application also provides a computer storage medium storing a computer program, which, when executed on a processor, implements the multi-dimensional evaluation method for the performance of reconstituted metal materials according to any one of the foregoing embodiments.

[0152] The computer storage medium can be a readable storage medium, a non-volatile storage medium, or a volatile storage medium. For example, the computer storage medium may include, but is not limited to, 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.

[0153] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, 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 alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive 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 diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0154] In addition, the functional modules or units in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0155] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a 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 smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0156] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes 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.

Claims

1. A multi-dimensional evaluation method for the properties of reconstituted metallic materials, characterized in that, include: Establish an evaluation index system that includes four primary criteria: technological level, economic benefits, environmental impact, and resource and energy consumption, and set secondary indicators under each primary criterion; The weights of each primary criterion and each secondary indicator in the evaluation index system were determined using the analytic hierarchy process (AHP), and a consistency test was performed. Obtain the measured raw data of the material to be evaluated under each of the secondary indicators; match the corresponding membership function according to the attributes of the secondary indicators, and process the measured raw data into dimensionless standardized evaluation values ​​through the membership function; The fuzzy comprehensive evaluation method is used to synthesize the standardized evaluation values ​​and the corresponding weights to obtain the comprehensive performance score of the material to be evaluated. The performance level of the material to be evaluated is determined based on the comprehensive performance score.

2. The multi-dimensional evaluation method for the properties of reconstituted metallic materials as described in claim 1, characterized in that, The step of determining the weights of each primary criterion and secondary indicator in the evaluation index system using the analytic hierarchy process (AHP) and performing a consistency check includes: constructing a judgment matrix of the relative importance of each indicator at the same level using the Delphi method; quantifying the elements of the judgment matrix using a 1-9 scale; calculating the maximum eigenvalue and eigenvector of the judgment matrix using the square root method or the sum-product method, and using the normalized eigenvector as the weight of the corresponding indicator; calculating the consistency ratio, and determining the validity of the weights when the consistency ratio is less than 0.10; and / or... The secondary indicators at the aforementioned technical level include at least one of the following: melting point, hardness, wetting angle, sealing leakage rate, impurity content, technological advancement, technological stability, technological maturity, and product qualification rate; and / or, The secondary indicators under the economic benefits mentioned include at least one of the following: equipment input per unit product, operating input per unit product, and annual direct revenue per unit product; and / or, The secondary indicators under the environmental impact assessment include at least one of the following: wastewater discharge per unit product, waste residue generation per unit product, exhaust gas emissions per unit product, and environmental risk prevention and control level; and / or, The secondary indicators under resource energy consumption include at least one of the following: comprehensive energy consumption per unit product, metal recovery rate, and water resource recycling rate.

3. The multi-dimensional evaluation method for the properties of reconstituted metallic materials as described in claim 1, characterized in that, The step of matching the membership function corresponding to the attributes of the secondary indicator includes: For secondary indicators with benefit-related attributes, an upper limit linear membership function is used; For secondary indicators with cost as their attribute, a lower limit linear membership function is used. For secondary indices with critical mutation effect attributes, the S-shaped logistic membership function is adopted; For secondary indicators with an optimal interval range attribute, a parabolic membership function is adopted; For secondary indicators with decay properties over time, an exponential decay membership function is used.

4. The multi-dimensional evaluation method for the properties of reconstituted metal materials as described in claim 3, characterized in that, The formula for the S-type logistic membership function is: ； Where x is the measured raw data, x0 is the set threshold midpoint, and k is the steepness coefficient; and / or, The formula for the parabolic membership function is: when hour, Otherwise S=0; where x opt For the optimal value, d is the tolerance half-width; and / or, The formula for the exponentially decaying membership function is: ； Where λ is the attenuation coefficient.

5. The multi-dimensional evaluation method for the properties of reconstituted metallic materials as described in claim 1, characterized in that, Before the processing into dimensionless standardized evaluation values, the process also includes data preprocessing and a veto step, specifically including: Consistency verification is performed on the measured raw data of the logically related secondary indicators. If there is a logical contradiction among the measured raw data, the subsequent comprehensive evaluation calculation is rejected. Multi-point sampling measured data of the same batch of materials to be evaluated are obtained, and the standard deviation and coefficient of variation of the multi-point sampling measured data are calculated. When each of the secondary indicators includes a technical stability indicator and the coefficient of variation exceeds a preset variation threshold, the standardized evaluation value of the technical stability indicator is reduced proportionally. The measured raw data of each of the secondary indicators are compared with a preset absolute rejection threshold. If any measured raw data exceeds the absolute rejection threshold, the material to be evaluated is determined to be unqualified, and the comprehensive performance score is forcibly set to zero, and the comprehensive evaluation calculation is no longer performed. And / or, Before determining the weights of each primary criterion and each secondary indicator in the evaluation index system using the analytic hierarchy process (AHP), the process also includes: Multiple downstream application scenarios and corresponding weight vectors for each scenario are preset. A scenario selection instruction is received from the user. Based on the scenario selection instruction, the corresponding weight vectors are called to update the weights of each primary criterion and each secondary indicator before a comprehensive evaluation is performed; and / or, The multidimensional evaluation method for the properties of reconstituted metallic materials also includes a long-term service performance prediction step, specifically including: Obtain key performance data of the material to be evaluated before and after accelerated aging tests, and calculate the performance degradation rate D; evaluate long-term service stability using an exponential stability membership function, the calculation formula of which is: ； Where k is a preset attenuation sensitivity coefficient; According to the obtained S stab The expected lifespan level of the material to be evaluated is output based on the preset range of the value.

6. The multi-dimensional evaluation method for the properties of reconstituted metallic materials as described in claim 1, characterized in that, The multidimensional performance evaluation method for reconstituted metallic materials also includes a process reverse diagnosis step: Construct and store an indicator-process correlation mapping library; the indicator-process correlation mapping library records the quantitative correlation between each secondary indicator and the preceding process, controllable process parameters, and the direction of influence; When the standardized evaluation value of any secondary indicator is lower than the preset evaluation value threshold, the indicator-process association mapping library is queried, and controllable process parameter adjustment suggestions are generated and output according to the corresponding influence direction.

7. The multi-dimensional evaluation method for the properties of reconstituted metallic materials as described in claim 6, characterized in that, The multidimensional evaluation method for the properties of reconstituted metallic materials also includes a feedback learning step, specifically: Record the changes in the indicators of the evaluated material before and after generating the controllable process parameter adjustment suggestions; If the same controllable process parameter adjustment suggestion is used multiple times and the corresponding indicator improvement meets the preset conditions, the recommendation confidence of the controllable process parameter adjustment suggestion in the indicator-process association mapping library will be automatically increased.

8. A multi-dimensional evaluation system for the properties of reconstituted metallic materials, characterized in that, include: The system construction module is used to establish an evaluation index system that includes four primary criteria: technical level, economic benefits, environmental impact, and resource and energy consumption, and to set secondary indicators under each primary criterion. The weight calculation module is used to determine the weights of each primary criterion and each secondary indicator in the evaluation index system using the analytic hierarchy process (AHP), and to perform consistency checks. The data input module is used to acquire the measured raw data of the material to be evaluated under each of the secondary indicators; The membership function is matched to the attribute of the secondary indicator, and the measured raw data is processed into dimensionless standardized evaluation values ​​through the membership function. The fuzzy evaluation module is used to perform a fuzzy comprehensive evaluation method to synthesize the standardized evaluation values ​​and the corresponding weights to obtain the comprehensive performance score of the material to be evaluated. The results output module is used to determine the performance level of the material to be evaluated based on the comprehensive performance score.

9. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the multidimensional evaluation method for the properties of reconstituted metallic materials as described in any one of claims 1-7.

10. A computer storage medium, characterized in that, It stores a computer program, which, when executed on a processor, implements the multidimensional evaluation method for the properties of reconstituted metallic materials according to any one of claims 1-7.

Images