Product recovery scheme prediction method and system for product design

Abstract

The invention provides a product design-oriented product recovery scheme prediction method and system. The method comprises the steps of defining evaluation influence factors of a product recovery scheme; evaluating the relative importance of each factor by using a comprehensive decision-making tool combining an analytic hierarchy process and a decision-making test and evaluation laboratory method, and calculating to obtain a comprehensive weight; the invention discloses recovery scheme probability prediction based on fuzzy comprehensive evaluation. The method comprises the following steps: establishing a factor set consisting of elements of factors influencing an evaluation object; establishing an evaluation set composed of different recovery schemes possibly made for the evaluation object; constructing a fuzzy evaluation matrix based on the factor set and the evaluation set; constructing a weight set fuzzy set of each influence factor based on the comprehensive weight; and obtaining a comprehensive evaluation model based on the weight set fuzzy set and the fuzzy evaluation matrix, obtaining the probability that a certain product part executes a set recovery scheme based on the comprehensive evaluation model, and obtaining a predicted product recovery scheme based on the obtained probability.

Description

Technical Field

[0001] This invention belongs to the field of recyclable product design technology, and particularly relates to a product recycling scheme prediction method and system for product design. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Design for recyclability aims to improve the consistency between the "product design" and "end-of-life recycling" stages, that is, to design products with recycling in mind. Product design-oriented recycling scenario prediction is an important research area of ​​design for recyclability. It refers to considering end-of-life recycling options during the design phase, thereby enabling targeted product design to reduce the difficulty of end-of-life recycling and increase recycling value. The goal is to reduce resource waste and environmental pollution after product obsolescence from the design stage.

[0004] The core objective of recycling is to achieve a closed-loop cycle of materials and components after use. Based on the "complexity" of the recycling process, end-of-life product recycling can be categorized into: product-level recycling, component-level recycling, material recycling, and energy recycling. Furthermore, the actual end-of-life product recycling process is typically influenced by a combination of factors, including the product's end-of-life condition, recycling time, recycling location, and recycling technology. Therefore, accurately predicting the recycling plan after a product's end-of-life during the design phase is a time-consuming and complex task.

[0005] Design-oriented product recycling prediction should be as simple and easy to use as possible. However, current technology has not yet been able to quickly and accurately predict recycling options after a product's end-of-life during the design phase, thus impacting the efficiency and quality of recyclable design. Summary of the Invention

[0006] To overcome the shortcomings of the existing technology, this invention provides a product recycling plan prediction method oriented towards product design. By integrating the Analytic Hierarchy Process (AHP), the Decision-Making Trial and Evaluation Laboratory (DEMATEL) method (AHP-DEMATEL), and the Fuzzy Comprehensive Evaluation Method, this method reduces the impact of recycling uncertainties, thereby improving the accuracy of product end-of-life recycling plan prediction during the design phase.

[0007] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions: Firstly, a product recycling plan prediction method oriented towards product design is disclosed, including: Define the factors influencing the evaluation of product recycling programs; The relative importance of each factor was assessed using a comprehensive decision-making tool that combines the analytic hierarchy process (AHP) and decision experiment and evaluation laboratory methods, and the comprehensive weights were calculated. Probability prediction of recovery schemes based on fuzzy comprehensive evaluation includes: Establish a factor set composed of various factors affecting the evaluation object; Establish an evaluation set consisting of different possible recycling schemes for the evaluated object; Construct a fuzzy evaluation matrix based on the factor set and evaluation set; A fuzzy set of weights for each influencing factor is constructed based on the comprehensive weights. A comprehensive evaluation model is obtained based on the weight set fuzzy set and fuzzy evaluation matrix. Based on this comprehensive evaluation model, the probability of a certain product part implementing a set recycling plan is obtained. Based on the obtained probability, a predicted product recycling plan is obtained.

[0008] As a further technical solution, the evaluation factors for product recycling programs are defined, including: material characteristics, ease of separation, component durability, market demand, recycling level, and policy support.

[0009] As a further technical solution, a comprehensive decision-making tool combining the analytic hierarchy process (AHP) and decision experimentation and evaluation laboratory methods is used to assess the relative importance of each factor, specifically including: The initial weights of each factor are calculated based on the analytic hierarchy process (AHP). The initial weights of each factor are corrected based on the decision experiment and evaluation laboratory method; The overall weight is calculated based on the corrected weights.

[0010] Secondly, a product recycling plan prediction system oriented towards product design is disclosed, including: The module for defining influencing factors is configured to: define the influencing factors for evaluating product recycling programs; The comprehensive weight calculation module is configured to: use a comprehensive decision-making tool that combines the analytic hierarchy process and decision experiment and evaluation laboratory methods to assess the relative importance of each factor and calculate the comprehensive weight; The recycling scheme probability prediction module is configured as follows: recycling scheme probability prediction based on fuzzy comprehensive evaluation, including: Establish a factor set composed of various factors affecting the evaluation object; Establish an evaluation set consisting of different possible recycling schemes for the evaluated object; Construct a fuzzy evaluation matrix based on the factor set and evaluation set; A fuzzy set of weights for each influencing factor is constructed based on the comprehensive weights. A comprehensive evaluation model is obtained based on the weight set fuzzy set and fuzzy evaluation matrix. Based on this comprehensive evaluation model, the probability of a certain product part implementing a set recycling plan is obtained. Based on the obtained probability, a predicted product recycling plan is obtained.

[0011] The above one or more technical solutions have the following beneficial effects: This invention simplifies complex real-world recycling scenarios by predefining recycling schemes and general recycling processes, while ensuring comprehensive consideration of various recycling strategies for scrapped parts. Secondly, addressing the issue of poor evaluation accuracy caused by recycling uncertainties, it combines AHP-DEMATEL and fuzzy comprehensive evaluation methods to reduce design evaluation errors through probabilistic prediction of recycling schemes.

[0012] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0013] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0014] Figure 1 A general flowchart for the recycling process of end-of-life products; Figure 2 This is a schematic diagram of the triangular membership function selected in this invention; Figure 3 This is an exploded view of the product of this invention; Figure 4 This is a flowchart of the overall method of the present invention. Detailed Implementation

[0015] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0016] It should be noted that the terminology used herein is for the purpose of describing particular implementations only and is not intended to limit the exemplary implementations of the present invention.

[0017] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0018] Example 1 See appendix Figure 4As shown, this embodiment discloses a product recycling plan prediction method for product design, including: Step 1: Define the factors influencing the evaluation of product recycling programs; Step 2: Use a comprehensive decision-making tool that combines the analytic hierarchy process (AHP) and decision experimentation and evaluation laboratory methods to assess the relative importance of each factor and calculate the comprehensive weight. Step 3: Probability prediction of recovery schemes based on fuzzy comprehensive evaluation, including: Establish a factor set composed of various factors affecting the evaluation object; Establish an evaluation set consisting of different possible recycling schemes for the evaluated object; Construct a fuzzy evaluation matrix based on the factor set and evaluation set; A fuzzy set of weights for each influencing factor is constructed based on the comprehensive weights. A comprehensive evaluation model is obtained based on the weight set fuzzy set and fuzzy evaluation matrix. Based on this comprehensive evaluation model, the probability of a certain product part implementing a set recycling plan is obtained. Based on the obtained probability, a predicted product recycling plan is obtained.

[0019] This method reduces assessment errors caused by uncertainties in recycling by predicting the probability of different recycling schemes for each part after the product is scrapped. Simultaneously, by combining the recycling value assessment of each part with the overall disassembly cost estimation, a comprehensive recyclability assessment index is constructed to achieve rapid product recyclability assessment during the design phase.

[0020] In one implementation example, before defining the factors influencing the evaluation of the product recycling program in step one, the recycling program is first defined. Specifically, a general recycling process for end-of-life products is defined, and four main recycling programs are identified, such as... Figure 1 As shown, it includes: (1) Reuse and remanufacturing (U): This refers to the direct reuse or downgrading of parts with residual value after the scrapped products are dismantled, and cleaning, repair or refurbishment is required when necessary. (2) Material recycling (R): This refers to the recovery of valuable materials from scrapped products or parts after crushing and separation operations for reuse in original or other products. (3) Landfill (L): This refers to the direct dumping of scrapped products and parts with no recycling value into designated landfills. This paper regards the landfilling of solid waste as a complex and unprofitable process. (4) Incineration (I): This refers to the incineration of scrapped products and parts to recover energy.

[0021] Furthermore, while it's difficult to accurately predict the recycling scheme for end-of-life products or parts during the design phase, the probability of implementing each recycling scheme for a particular end-of-life product or part can be predicted by analyzing the factors influencing the choice of recycling scheme. This study employs AHP-DEMATEL and fuzzy comprehensive evaluation to predict the probability of recycling schemes for each part of an end-of-life product. The method first defines six factors influencing the selection of recycling schemes for end-of-life products (parts), then calculates the weights of each influencing factor based on AHP-DEMATEL, and finally uses fuzzy comprehensive evaluation to estimate the probability of each recycling scheme for the end-of-life part.

[0022] Defining the influencing factors for recycling scheme evaluation: Analyzing the factors affecting the selection of recycling schemes after product obsolescence during the design phase requires considering not only the design factors that have a significant and easily measurable impact on the choice of recycling scheme, but also the potential future recycling environment. Therefore, this analysis examines the influencing factors for recycling scheme evaluation from two aspects: "product design" and "recycling environment."

[0023] Among these factors, "material selection" and "structural design" in product design directly influence the choice of recycling schemes. In recyclability assessments, this is mainly reflected in the impact of "material selection" and "ease of disassembly" on product recyclability. The recycling environment involves broader external conditions, with complex and diverse influences on the choice of product recycling schemes. "Recycling technology level," "market demand," and "regulations and policies" are the most significant external factors. Therefore, based on the above analysis, this implementation example proposes the following six factors influencing the selection of recycling schemes for products or parts during the end-of-life stage, based on the company's (similar parts) historical database and the designer's experience. These factors are explained to facilitate expert understanding and evaluation.

[0024] In step one, the six factors mentioned above that influence the selection of recycling schemes for products or parts during the end-of-life stage specifically include: Material characteristics (N1): Assessing the material's value, purity, toxicity, heat capacity, and technical performance (such as strength, wear resistance, environmental adaptability, etc., which affect the processing and use of parts) to determine possible end-of-life recycling schemes for the product (part). Ease of separation (N2): Analyzing the ease of disassembly and separation characteristics of the product or part, combined with disassembly cost estimation, to determine whether it has value for reuse, remanufacturing, or material recycling. Durability of parts (N3): Measuring durability by comparing the design life of the part with the design life of the entire machine. Generally, the longer the life of a part, the higher its feasibility for reuse and remanufacturing. Market demand (N4): Market demand for recycled parts or materials affects its economic feasibility and priority. Generally, materials and parts with higher demand usually have higher market prices, and their potential for material recycling or reuse and remanufacturing is also higher. Recycling level (N5): Including the maturity of recycling technology and the organizational efficiency of the recycling supply chain. Recycling technology encompasses disassembly, sorting, cleaning, and reprocessing capabilities, while supply chain organization efficiency involves the distribution of recycling facilities, transportation networks, and processing capacity. Higher recycling levels mean that end-of-life parts can be recycled and processed more efficiently at lower costs. Policy support (N6): The level of government support for the recycling industry, including subsidies, tax breaks, and other incentives. Higher levels of government support for the recycling industry, i.e., more subsidies provided, will encourage end-of-life parts manufacturers to choose more environmentally friendly recycling methods.

[0025] In one implementation example, in step two, based on the AHP-DEMATEL influencing factor weight calculation, the degree of influence of influencing factors on the selection of recycling schemes varies for different types of products and recycling scenarios, and there are usually complex interactions between these factors. Especially in electromechanical products with complex structures and diverse materials, multiple influencing factors often exhibit significant coupling relationships. Changes in a single factor may affect other decision variables, thereby affecting the overall evaluation results. Therefore, using the traditional analytic hierarchy process (AHP) to estimate the weights of influencing factors is difficult to reflect the interaction effects between factors, leading to biased evaluation results and reducing the scientific rigor and accuracy of recycling scheme selection.

[0026] To overcome the aforementioned limitations, the AHP-DEMATEL method is introduced to calculate the weights of influencing factors in the evaluation of recycling schemes for various parts of electromechanical products. AHP-DEMATEL not only assesses the relative importance of each factor but also quantifies the interactions between them by introducing DEMATEL, correcting subjective biases caused by neglecting factor coupling and thus more closely reflecting the actual decision-making mechanism under the recycling logic of electromechanical products.

[0027] Compared to traditional AHP methods, AHP-DEMATEL is more suitable for the early stages of product design when information is incomplete and influencing factors are complex and closely interrelated. By systematically identifying and modeling the causal relationships between various factors, this method effectively improves the interpretability of the evaluation model and provides more reliable decision support for the selection of subsequent recycling schemes.

[0028] Specifically, this includes: 2-1) Initial weight calculation based on AHP: AHP decomposes complex decision problems into multiple levels by constructing a hierarchical structure and quantifies the importance of each influencing factor using a pairwise comparison method. Its key steps include constructing a judgment matrix, calculating eigenvalues ​​to obtain weights, and ensuring the rationality of the decision logic through consistency checks. During the implementation of AHP, experts first use a 1-9 scale to compare the importance of factors based on corporate objectives (this paper mainly considers the company's preferences for economic and environmental objectives) to construct a judgment matrix of influencing factors for the recovery plan. A As shown in formula (1): (1) in, Indicating influencing factors i Relative factors j The degree of importance, and satisfying , , ; n This indicates the number of influencing factors, as shown in this implementation example. n= 6.

[0029] Then, the eigenvalue method is used to calculate the weights of each factor, and a consistency check is performed to ensure the logical correctness of the evaluation process. Maximum eigenvalue. The calculation is shown in formula (2): (2) in, For feature vectors W The i Each component.

[0030] 2-2) Weight Correction Based on DEMATEL: The AHP method assumes that the influencing factors are independent of each other. DEMATEL is introduced to construct a direct influence matrix to help designers understand the relationship between the six recycling influencing factors defined in this paper.

[0031] The first step in applying the DEMATEL method is for experts to construct a direct influence matrix. M As shown in formula (3), it is used to quantify the degree of influence between various factors.

[0032] A five-level scale (0-4) is used to measure the strength of interactions among influencing factors. Subsequently, the direct influence matrix is ​​normalized to obtain the normalized influence matrix. N As shown in formula (4). Finally, the comprehensive influence matrix is ​​calculated by multiplying the normalized influence matrix by itself. T As shown in formula (5), this comprehensively reflects the interaction between various factors.

[0033] (3) (4) (5) in, Indicator Factors i Factors j The degree of direct impact, I It is the identity matrix. for The inverse matrix.

[0034] Based on the values ​​in the comprehensive influence matrix T The influence of each element can be further calculated. Degree of influence and centrality The calculation formula is as follows: (6) (7) (8) 2-3) Comprehensive Weight Calculation Based on AHP-DEMATEL: Constructing an AHP-DEMATEL model can overcome the subjectivity of experts to some extent, making the weight estimation results more scientific and accurate. Currently, there are various methods using the DEMATEL method to correct the initial AHP weights to obtain the comprehensive weights, among which the centrality-based calculation method is more common. Centrality comprehensively considers the influence and affectedness of each factor, reflecting the overall importance of the factor in the system. Therefore, the centrality-based method is used to calculate the comprehensive weights, and the calculation formula is as follows: (9) in, These are the initial weights obtained based on the AHP method.

[0035] In one implementation example, regarding step three, the probability prediction of the recovery scheme based on fuzzy comprehensive evaluation: Fuzzy comprehensive evaluation is an evaluation tool based on fuzzy mathematics. It uses membership theory to transform qualitative evaluation into quantitative evaluation, effectively addressing evaluation objects with high uncertainty and difficulty in quantification.

[0036] The selection of recycling schemes for end-of-life products (parts) involves a variety of fuzzy and difficult-to-quantify influencing factors. Fuzzy comprehensive evaluation method can effectively handle these uncertainties, making the weight estimation of recycling schemes more reasonable and scientific. The specific calculation steps are as follows.

[0037] (3-1) Establishing a factor set: A factor set is a general set composed of each factor that affects the evaluation object as an element, as shown in formula (10).

[0038] (10) in, Indicates the first impact assessment object i One factor.

[0039] This paper evaluates the selection of recycling schemes, focusing on six factors that influence the assessment of recycling schemes. Therefore, n =6 and .

[0040] (3-2) Establish the evaluation set: The evaluation set is a collection of various possible results that the evaluator may make for the evaluation object, as shown in formula (11).

[0041] (11) in, Indicates the first j Evaluation results.

[0042] In this implementation example, the evaluator may make four different evaluation results for the evaluated object, which are the four different recycling schemes. m =4 and .

[0043] (3-3) Constructing the fuzzy evaluation matrix: Membership functions are used to represent the degree of adaptation of each influencing factor to different recovery schemes. Assumptions Indicating factors affecting recycling Recycling scheme If the membership degree is given, then the fuzzy set of the single-factor evaluation can be represented as: (12) Depend on n A fuzzy matrix composed of single-factor evaluation sets It can be represented as: (13) This paper combines expert evaluation and fuzzy linguistic variables to construct a membership function, and defines five levels of linguistic variables as fuzzy variables for fuzzy evaluation, as shown in Table 1.

[0044] Table 1. Definitions of Fuzzy Variables and Fuzzy Sets

[0045] In addition, choose such Figure 2 The triangular membership function shown models the fuzzy sets in Table 1 to evaluate their uncertainty. The triangular membership function consists of three parameters. a, b, c Confirmed, among which a and c These represent the left and right endpoints where the membership degree is 0, respectively. b This represents the peak point with a membership degree of 1. This function is simple in form, computationally efficient, and suitable for fuzzy representations of expert scores, facilitating subsequent fuzzy computation and defuzzification. Secondly, several field experts were invited to assess the membership of influencing factors under the four recycling schemes based on the characteristic values ​​of the evaluated products or parts. During the expert evaluation process, a question-and-answer format could be used to obtain the experts' evaluation results, such as, "Based on the material characteristics of this part, what do you think is the likelihood of its reuse and remanufacturing at the end-of-life stage?"

[0046] In the process of fuzzy comprehensive evaluation, since the expert evaluation results in fuzzy membership degrees, further fuzzy set operations are required to obtain the comprehensive evaluation results. To this end, this paper first uses the Alpha cut set method to perform fuzzy operations (the operation rules are shown in formulas (14)-(17)), and then uses the centroid method (as shown in formula (18)) to defuzzify the fuzzy set in order to obtain clear weight values.

[0047] (14) (15) (16) (17) (18) in, , For triangular fuzzy numbers, express Level of collection; Fuzzy numbers under cut set For interval . The membership function representing the composite fuzzy number. Deblur the result.

[0048] (3-4) Constructing a fuzzy comprehensive evaluation model: Calculating the comprehensive influence degree based on the AHP-DEMATEL method. Construct a fuzzy set of weights for each influencing factor. Z and fuzzy evaluation matrix RA comprehensive evaluation model can be obtained. B As shown in formula (19): (19) in, This indicates that a certain product (part) performs the following procedure: j The probability of each recycling scheme.

[0049] Instance verification Taking the probabilistic prediction of a scrapping and recycling scheme for an automotive alternator as an example, this paper verifies the feasibility and effectiveness of the proposed design-oriented product recycling scheme prediction. All data in this example are from the internet and references, and have passed the data rationality verification. (The following is a continuation of the previous sentence.) Figure 3 An exploded view of an example of an automotive alternator design, such as... Figure 3 As shown, this article only considers 10 core components, and the specific data are shown in Table 2 below.

[0050] Table 2 Core Components of a Certain Automotive Alternator

[0051] Assuming the company's design preference for this alternator is "70% economic objective and 30% environmental objective," based on the influencing factor weighting method, the weights of the six influencing factors affecting the selection of the recycling scheme for this alternator are calculated as follows: .

[0052] Based on the proposed fuzzy comprehensive evaluation method, fuzzy evaluation matrices for recycling schemes of each part are constructed, and the probabilities of executing different recycling schemes are calculated, as shown in Table 3. Table 3 shows that the predicted recycling scheme for each part in this case is "material recycling," thus obtaining the predicted recycling schemes for each part of the case product.

[0053] It should be noted that since most of the parts in this case are metal, the fuzzy evaluation process has certain similarities, so the predicted probability values ​​are highly similar, but the overall method is still effective.

[0054] Table 3. Predicted probability of each component implementing each recycling plan

[0055] Example 2 The purpose of this embodiment is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the above-described method.

[0056] Example 3 The purpose of this embodiment is to provide a computer-readable storage medium.

[0057] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps of the above method.

[0058] Example 4 The purpose of this embodiment is to provide a product recycling plan prediction system oriented towards product design, including: The module for defining influencing factors is configured to: define the influencing factors for evaluating product recycling programs; The comprehensive weight calculation module is configured to: use a comprehensive decision-making tool that combines the analytic hierarchy process and decision experiment and evaluation laboratory methods to assess the relative importance of each factor and calculate the comprehensive weight; The recycling scheme probability prediction module is configured as follows: recycling scheme probability prediction based on fuzzy comprehensive evaluation, including: Establish a factor set composed of various factors affecting the evaluation object; Establish an evaluation set consisting of different possible recycling schemes for the evaluated object; Construct a fuzzy evaluation matrix based on the factor set and evaluation set; A fuzzy set of weights for each influencing factor is constructed based on the comprehensive weights. A comprehensive evaluation model is obtained based on the weight set fuzzy set and fuzzy evaluation matrix. Based on this comprehensive evaluation model, the probability of a certain product part implementing a set recycling plan is obtained. Based on the obtained probability, a predicted product recycling plan is obtained.

[0059] Example 5 The purpose of this embodiment is to provide a computer program product containing instructions that, when run on a computer, cause the computer to perform the methods and functions involved in any of the above embodiments. The steps and methods involved in the apparatus of the above embodiments correspond to those in Embodiment 1. For specific implementation details, please refer to the relevant description section of Embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood as including any medium capable of storing, encoding, or carrying an instruction set for execution by a processor and enabling the processor to perform any of the methods in this invention.

[0060] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computer devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computer device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. The present invention is not limited to any particular combination of hardware and software.

[0061] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A product recycling plan prediction method oriented towards product design, characterized by comprising: Define the factors influencing the evaluation of product recycling programs; The relative importance of each factor was assessed using a comprehensive decision-making tool that combines the analytic hierarchy process (AHP) and decision experiment and evaluation laboratory methods, and the comprehensive weights were calculated. Probability prediction of recovery schemes based on fuzzy comprehensive evaluation includes: Establish a factor set composed of various factors affecting the evaluation object; Establish an evaluation set consisting of different possible recycling schemes for the evaluated object; Construct a fuzzy evaluation matrix based on the factor set and evaluation set; A fuzzy set of weights for each influencing factor is constructed based on the comprehensive weights. A comprehensive evaluation model is obtained based on the weight set fuzzy set and fuzzy evaluation matrix. Based on this comprehensive evaluation model, the probability of a certain product part implementing a set recycling plan is obtained. Based on the obtained probability, a predicted product recycling plan is obtained.

2. The product recycling scheme prediction method based on product design as described in claim 1, characterized in that, Define the factors influencing the evaluation of product recycling programs, including: material characteristics, ease of separation, component durability, market demand, recycling levels, and policy support.

3. The product recycling scheme prediction method based on product design as described in claim 1, characterized in that, A comprehensive decision-making tool combining the analytic hierarchy process (AHP) and decision experimentation and evaluation laboratory methods is used to assess the relative importance of each factor, specifically including: The initial weights of each factor are calculated based on the analytic hierarchy process (AHP). The initial weights of each factor are corrected based on the decision experiment and evaluation laboratory method; The overall weight is calculated based on the corrected weights.

4. The product recycling scheme prediction method based on product design as described in claim 1, Its characteristics include material properties: measuring the value, purity, toxicity, heat capacity, and technical performance of materials to determine possible disposal and recycling options for products or parts; Ease of disassembly: Analyze the ease of disassembly and separation characteristics of a product or part, and combine this with disassembly cost estimates to determine whether it has value for reuse, remanufacturing, or material recycling. Part durability: The durability of a part is measured by comparing its design life with that of the whole machine. Market demand: Market demand for recycled parts or materials will affect their economic viability and priority; Recycling level: This includes the maturity of recycling technologies and the organizational efficiency of the recycling supply chain; Policy support: The level of government support for the recycling industry, including subsidies, tax breaks, and other incentives.

5. The product recycling scheme prediction method based on product design as described in claim 1, characterized in that, The initial weights of each factor are calculated based on the analytic hierarchy process (AHP), specifically including: AHP breaks down complex decision problems into multiple levels by constructing a hierarchical structure and uses a pairwise comparison method to quantify the importance of each influencing factor. Its key steps include constructing a judgment matrix, calculating eigenvalues ​​to obtain weights, and ensuring the rationality of the decision logic through consistency checks. During the implementation of AHP, experts first use the 1-9 scale to compare the importance of factors based on corporate objectives, construct a matrix of factors affecting the recovery plan, and then use the eigenvalue method to calculate the weight of each factor and conduct a consistency check to ensure the correctness of the logic in the evaluation process.

6. The product recycling scheme prediction method based on product design as described in claim 1, characterized in that, The initial weights of each factor are corrected based on the decision experiment and evaluation laboratory method, specifically including: Construct a direct impact matrix to quantify the degree of influence between various factors; A five-point scale of 0-4 is used to measure the strength of the interaction between influencing factors; Subsequently, the direct influence matrix was normalized to obtain the normalized influence matrix. ， Finally, the comprehensive influence matrix is ​​calculated by multiplying the normalized influence matrix by itself. ， Based on the values ​​in the comprehensive influence matrix, the influence degree, the degree of being influenced, and the centrality of each element are further calculated.

7. A product recycling plan prediction system oriented towards product design, characterized in that, include: The module for defining influencing factors is configured to: define the influencing factors for evaluating product recycling programs; The comprehensive weight calculation module is configured to: use a comprehensive decision-making tool that combines the analytic hierarchy process and decision experiment and evaluation laboratory methods to assess the relative importance of each factor and calculate the comprehensive weight; The recycling scheme probability prediction module is configured as follows: recycling scheme probability prediction based on fuzzy comprehensive evaluation, including: Establish a factor set composed of various factors affecting the evaluation object; Establish an evaluation set consisting of different possible recycling schemes for the evaluated object; Construct a fuzzy evaluation matrix based on the factor set and evaluation set; A fuzzy set of weights for each influencing factor is constructed based on the comprehensive weights. A comprehensive evaluation model is obtained based on the weight set fuzzy set and fuzzy evaluation matrix. Based on this comprehensive evaluation model, the probability of a certain product part implementing a set recycling plan is obtained. Based on the obtained probability, a predicted product recycling plan is obtained.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method described in any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it performs the steps of the method described in any one of claims 1-6.

Images