Decision scheme generation method based on data driving

Abstract

The invention discloses a decision scheme generation method based on data driving, and relates to the technical field of decision generation, and the method comprises the following steps: S1, applying the decision scheme generation method based on data driving to active remanufacturing of in-service mechanical products, and designing three in-service mechanical product remanufacturing schemes for the in-service mechanical products meeting the remanufacturability, and obtaining failure characteristic data of the in-service mechanical product meeting the remanufacturability, carrying out quantitative processing on the failure characteristic data, obtaining pollution emission data in the remanufacturing process of the in-service mechanical product meeting the remanufacturability, and processing the pollution emission data. According to the decision-making scheme generation method based on data driving, the failure characteristic data and the pollution emission data of the in-service mechanical product meeting the remanufacturability are obtained and processed, data support is provided for the follow-up process, and the decision-making scheme is generated based on the failure characteristic data of the in-service mechanical product meeting the remanufacturability. And formulating a grading threshold matrix of each type of failure characteristics.

Description

Technical Field

[0001] The present invention relates to the technical field of decision making, and in particular to a method for generating a decision solution based on data-driven. Background Art

[0002] With the continuous advancement of science and technology, more and more problems continue to emerge, and decision analysis is required for different problems. The Chinese patent with application number 202210430690.9 discloses "a decision generation method and device, which relates to the field of computer technology, specifically to the field of big data and artificial intelligence technology. The specific implementation scheme is: first, multiple pre-trained decision models corresponding to multiple decision strategies are obtained, and the pre-trained decision models correspond to the decision strategies one by one. Then, the problem to be processed and the decision scenario corresponding to the problem to be processed are obtained, and based on the decision scenario corresponding to the problem to be processed, a target decision model is selected from the multiple pre-trained decision models. Finally, based on the problem to be processed and the target decision model, a target decision corresponding to the problem to be processed is generated. Multiple pre-trained decision models corresponding to the decision strategies are obtained in advance, and in the process of using the pre-trained decision models, the same pre-trained decision model can be used to make decisions on different problems to be processed, thereby realizing the decoupling between the decision model and the problem to be processed.";

[0003] This prior art only solves the problem that with the rise of machine learning in recent years, some solutions use machine learning to accelerate solutions, and are applied to precise methods, heuristic methods or direct end-to-end solutions. Corresponding decision models are trained for different problems so that the decision models can make decisions on the problems. It does not take into account that when applied to active remanufacturing of in-service mechanical products, relevant data of in-service mechanical products that meet the remanufacturability should be obtained and processed, and the quality of in-service mechanical products that meet the remanufacturability should be further graded, thereby reducing the design difficulty of active remanufacturing process solutions in different design solutions, and conducting a comprehensive benefit evaluation of the active remanufacturing of in-service mechanical products from multiple aspects to determine the optimal solution. Summary of the invention

[0004] The purpose of the present invention is to provide a data-driven decision-making solution generation method to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a data-driven decision-making solution generation method, comprising the following steps:

[0006] S1: The data-driven decision-making scheme generation method is applied to the active remanufacturing of in-service mechanical products. Three in-service mechanical product remanufacturing schemes are designed for in-service mechanical products that meet the remanufacturability. The failure characteristic data of in-service mechanical products that meet the remanufacturability are obtained and the failure characteristic data are quantified. The pollution emission data in the remanufacturing process of in-service mechanical products that meet the remanufacturability are obtained and processed.

[0007] S2: Based on the failure characteristic data of in-service mechanical products that meet the remanufacturability, a corresponding failure characteristic data set is established, and a classification threshold matrix of various failure characteristics is formulated based on the market demand and remanufacturing parameters of the in-service mechanical products to achieve accurate quality classification of in-service mechanical product parts;

[0008] S3: Based on the three designed remanufacturing schemes for in-service mechanical products and the quality level of in-service mechanical product parts, the in-service mechanical product parts required in different remanufacturing schemes are optimally allocated under the consideration of size constraints, so as to meet the market performance requirements of in-service mechanical products and achieve the coordinated optimization of active remanufacturing cost and quality of in-service mechanical products;

[0009] S4: Establish a decision matrix for active remanufacturing of in-service mechanical products from three aspects: economic benefit analysis, pollution emission analysis, and product quality analysis. Conduct a comprehensive benefit evaluation on the three designed remanufacturing plans for in-service mechanical products, and select the in-service mechanical product manufacturing plan with the best comprehensive benefit evaluation for implementation.

[0010] Preferably, step S1 also includes designing three remanufacturing schemes for in-service mechanical products that meet the requirements of remanufacturing, including a performance upgrade type active remanufacturing scheme, a performance repair type active remanufacturing scheme, and a performance degradation type active remanufacturing scheme. Failure characteristic data of in-service mechanical products that meet the remanufacturing requirements are obtained through modern intelligent detection technology, including three parameters: failure form, failure degree, and failure location. The failure degree parameters corresponding to each failure form of the in-service mechanical products that meet the remanufacturing requirements are interval quantized and normalized, and the failure degree data are converted into a value between [0, 1].

[0011] Preferably, step S1 further includes acquiring energy consumption data during the remanufacturing process of in-service mechanical products that meet the remanufacturability in the three designed schemes, and the consumed energy is divided into five types: raw coal, water, electricity, gasoline and diesel, and the energy consumption data of each type of energy is converted into carbon dioxide emission data after combustion of standard carbon through an energy consumption data conversion algorithm, and the specific calculation formula is as follows:

[0012]

[0013] In the formula, βi A represents the conversion factor of type i energy into standard coal, i Indicates the amount of Class I energy used in the remanufacturing process of in-service mechanical products.

[0014] Preferably, the step S2 further comprises establishing a failure characteristic data set of in-service mechanical products and their parts from three perspectives of failure location, failure form and failure degree based on the failure characteristic data of in-service mechanical products that meet remanufacturability. The specific expression is as follows:

[0015] P=[U 1 ,U 2 ,…,U n ]

[0016] In the formula, P represents the failure characteristic dataset of in-service mechanical product parts, U n The failure characteristic data set represents the nth failure form of the parts of in-service mechanical products. Taking the wear failure form as an example, the failure characteristic data set of the wear of the parts of in-service mechanical products is established. The specific expression is as follows:

[0017]

[0018] In the formula, m represents the mth in-service mechanical product component, k represents the wear position of the kth in-service mechanical product component, and w mk It represents the wear degree of the kth wear position of the mth in-service mechanical product component. The same method is used to establish the failure characteristic data set of other failure forms of in-service mechanical product components.

[0019] Preferably, step S2 further includes setting each column parameter in the failure characteristic data set of various failure forms of in-service mechanical product parts as a sub-failure vector of the corresponding failure form, and in the process of active remanufacturing of mechanical products, in order to avoid the situation where in-service mechanical product parts are under-repaired or over-repaired, thereby affecting the overall performance of the mechanical product, the active remanufacturing repair threshold is set according to the market demand and redesign parameters of the in-service mechanical products. Taking the wear failure form as an example, a wear classification threshold matrix is ​​established, and its specific expression is as follows:

[0020]

[0021] In the formula, δ x represents the wear classification threshold matrix, The grading threshold vector represents the kth wear position, and the sub-failure vector is divided into k+1 quality levels in combination with the upper and lower limits of 0 and 1, and each quality level is numbered with non-repeating uppercase English letters. The wear failure of in-service mechanical product parts is divided into corresponding quality levels based on the quality level of each sub-failure vector. The other failures of in-service mechanical product parts are divided into corresponding quality levels in the same way, so that the failure characteristics of in-service mechanical product parts after grading show higher concentration and lower complexity. Combined with the set active remanufacturing repair threshold, the design difficulty of the active remanufacturing process plan is reduced.

[0022] Preferably, the step S3 further includes taking into account the dimensional constraints, based on the three designed remanufacturing schemes for in-service mechanical products, and combining the quality levels of the in-service mechanical product parts, to perform the optimal allocation operation on the in-service mechanical product parts required in different remanufacturing schemes. The specific operation is to use the factory's remanufacturing capacity for in-service mechanical products and the market demand for in-service mechanical products as the upper and lower limits of the dimensional accuracy constraints, construct a tolerance dimensional constraint free range, and use the dimensional constraint accuracy loss as the target to construct a dimensional accuracy loss function for in-service mechanical product parts under different dimensional accuracies, and its specific expression is as follows:

[0023]

[0024] In the formula, A represents the number of alternative parts, a represents the ath alternative part, f(T ab ) represents the tolerance function of the ath candidate part with accuracy grade b, f(T a ) represents the design target tolerance function of the ath candidate part, and the dimensional accuracy loss functions of the in-service mechanical product parts under various dimensional accuracy are accumulated to obtain the final dimensional accuracy loss function of the in-service mechanical product parts.

[0025] Preferably, the step S3 further comprises constructing a cost function for selecting and matching parts of in-service mechanical products with the goal of minimizing the remanufacturing cost, and the specific expression thereof is as follows:

[0026]

[0027] In the formula, B represents the total number of dimensional accuracy levels of mechanical product parts in service, A ab represents the factory's remanufacturing capability for the ath candidate part at accuracy level b, B ab It indicates the factory's remanufacturing process control for the ath candidate part with accuracy level b. represents the process tolerance index of the ath candidate part with accuracy grade b, Y represents the total number of candidate parts with accuracy grade b, y represents the yth candidate part with accuracy grade b, C Lb represents the reuse cost of parts with accuracy level b, CNb The procurement cost of the Nth new part with accuracy grade b is represented by the jointly constructed final dimensional accuracy loss function of the in-service mechanical product parts. A collaborative optimization algorithm is used to perform global optimization search and solution to achieve the optimal allocation operation of the in-service mechanical product parts, while achieving the collaborative optimization of the active remanufacturing cost and quality of the in-service mechanical products.

[0028] Preferably, step S4 further includes respectively performing process scheme design and parts selection operations for the three designed remanufacturing schemes for in-service mechanical products, and respectively establishing a decision matrix for active remanufacturing schemes for in-service mechanical products from three aspects: economic benefit analysis of active remanufacturing of in-service mechanical products, pollution emission analysis, and product quality analysis. The specific operation of the economic benefit analysis is to obtain historical remanufacturing cost data and corresponding mechanical product failure feature data, calculate the similarity between the historical mechanical product failure feature data and the failure feature data of in-service mechanical products that meet the remanufacturability through the Euclidean algorithm, take the three groups of cost data with the highest failure feature similarity, and predict the cost of active remanufacturing mechanical products through the cost prediction algorithm. The specific calculation formula is as follows:

[0029]

[0030] Where D′ d It represents the remanufacturing cost of the failure characteristics of in-service mechanical products ranked by similarity d, and α represents the smoothing coefficient.

[0031] Preferably, step S4 also includes analyzing the pollution emission in the same way as the economic benefit analysis, obtaining the energy consumption in the remanufacturing process of the in-service mechanical products and converting it into the carbon dioxide emission data after the combustion of standard carbon, and using the horizontal comparison method, subtracting the carbon dioxide emission data in the active remanufacturing program of the in-service mechanical products from the carbon dioxide emission data in the historical mechanical product manufacturing process, and dividing the result with the carbon dioxide emission data in the historical mechanical product manufacturing process to obtain the pollution emission benefit evaluation value, wherein the product quality analysis specifically evaluates the performance reliability and social recognition of the in-service mechanical products, performs performance evaluation on the in-service mechanical products based on expert experience, obtains social recognition based on social surveys, and uses half of the cumulative result of the two as the product quality evaluation value, and constructs a decision matrix for the active remanufacturing program of in-service mechanical products, and its specific expression is as follows:

[0032]

[0033] Wherein, Xre1 represents the economic benefit evaluation value of the first design method, Xrp1 represents the pollution emission evaluation value of the first design method, Xrq1 represents the product quality evaluation value of the first design method, and ω1 represents the weight coefficient of the first evaluation index analyzed by the semi-supervised learning algorithm. A comprehensive benefit evaluation is conducted on the three designed remanufacturing schemes for in-service mechanical products, and the in-service mechanical product manufacturing scheme with the best comprehensive benefit evaluation is selected for execution.

[0034] Compared with the prior art, the beneficial effects of the present invention include at least the following: the present invention proposes a data-driven decision-making scheme generation method, which obtains and processes the failure characteristic data and pollution emission data of in-service mechanical products that meet the remanufacturability, provides data support for the follow-up, and formulates a grading threshold matrix of various failure characteristics based on the failure characteristic data of in-service mechanical products that meet the remanufacturability, so as to achieve accurate grading of the quality of in-service mechanical product parts and components, reduce the design difficulty of active remanufacturing process schemes, and further optimize the in-service mechanical product parts and components required in different remanufacturing schemes while considering size constraints and costs, so as to achieve coordinated optimization of the active remanufacturing cost and quality of in-service mechanical products, conduct multi-faceted analysis of the active remanufacturing schemes of in-service mechanical products and establish a decision matrix for the active remanufacturing schemes of in-service mechanical products, conduct a comprehensive benefit evaluation on the designed in-service mechanical product remanufacturing schemes, and determine the active manufacturing schemes of in-service mechanical products based on the comprehensive benefit evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic flow chart of a data-driven decision-making solution generation method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] See also Figure 1 The present invention provides a technical solution: a method for generating a decision solution based on data-driven, comprising the following steps:

[0038] S1: The data-driven decision-making scheme generation method is applied to the active remanufacturing of in-service mechanical products. Three in-service mechanical product remanufacturing schemes are designed for in-service mechanical products that meet the remanufacturability. The failure characteristic data of in-service mechanical products that meet the remanufacturability are obtained and the failure characteristic data are quantified. The pollution emission data in the remanufacturing process of in-service mechanical products that meet the remanufacturability are obtained and processed.

[0039] S2: Based on the failure characteristic data of in-service mechanical products that meet the remanufacturability, a corresponding failure characteristic data set is established, and a classification threshold matrix of various failure characteristics is formulated based on the market demand and remanufacturing parameters of the in-service mechanical products to achieve accurate quality classification of in-service mechanical product parts;

[0040] S3: Based on the three designed remanufacturing schemes for in-service mechanical products and the quality level of in-service mechanical product parts, the in-service mechanical product parts required in different remanufacturing schemes are optimally allocated under the consideration of size constraints, so as to meet the market performance requirements of in-service mechanical products and achieve the coordinated optimization of active remanufacturing cost and quality of in-service mechanical products;

[0041] S4: Establish a decision matrix for active remanufacturing of in-service mechanical products from three aspects: economic benefit analysis, pollution emission analysis, and product quality analysis. Conduct a comprehensive benefit evaluation on the three designed remanufacturing plans for in-service mechanical products, and select the in-service mechanical product manufacturing plan with the best comprehensive benefit evaluation for implementation.

[0042] Step S1 also includes designing three in-service mechanical product remanufacturing schemes for in-service mechanical products that meet the requirements of remanufacturing, including a performance upgrade type active remanufacturing scheme, a performance repair type active remanufacturing scheme, and a performance degradation type active remanufacturing scheme, obtaining failure characteristic data of in-service mechanical products that meet the requirements of remanufacturing through modern intelligent detection technology, including three parameters: failure form, failure degree, and failure position, performing interval quantization and normalization processing on the failure degree parameters corresponding to each failure form of the in-service mechanical products that meet the requirements of remanufacturing, and converting the failure degree data into a value between [0, 1];

[0043] Step S1 also includes obtaining energy consumption data during the remanufacturing process of in-service mechanical products that meet the remanufacturability in the three designed schemes, and the consumed energy is divided into five types: raw coal, water, electricity, gasoline and diesel, and the energy consumption data of each type of energy is converted into carbon dioxide emission data after combustion of standard carbon through an energy consumption data conversion algorithm. The specific calculation formula is as follows:

[0044]

[0045] In the formula, β iA represents the conversion factor of type i energy into standard coal, i It indicates the amount of Class I energy used in the remanufacturing process of in-service mechanical products;

[0046] Step S2 also includes establishing a failure characteristic data set of in-service mechanical products and their parts from three perspectives: failure location, failure form, and failure degree based on the failure characteristic data of in-service mechanical products that meet remanufacturability. The specific expression is as follows:

[0047]

[0048] In the formula, P represents the failure characteristic dataset of in-service mechanical product parts, U n The failure characteristic data set represents the nth failure form of the parts of in-service mechanical products. Taking the wear failure form as an example, the failure characteristic data set of the wear of the parts of in-service mechanical products is established. The specific expression is as follows:

[0049]

[0050] In the formula, m represents the mth in-service mechanical product component, k represents the wear position of the kth in-service mechanical product component, and w mk Indicates the wear degree of the kth wear position of the mth in-service mechanical product component, and uses the same method to establish a failure characteristic data set of other failure forms of in-service mechanical product components;

[0051] Step S2 also includes setting each column parameter in the failure characteristic data set of various failure forms of in-service mechanical product parts as a sub-failure vector of the corresponding failure form, and in the process of active remanufacturing of mechanical products, in order to avoid the situation where the in-service mechanical product parts are under-repaired or over-repaired, thereby affecting the overall performance of the mechanical product, the active remanufacturing repair threshold is set according to the market demand and redesign parameters of the in-service mechanical products. Taking the wear failure form as an example, a wear classification threshold matrix is ​​established, and its specific expression is as follows:

[0052]

[0053] In the formula, δ x represents the wear classification threshold matrix, The classification threshold vector representing the kth wear position is used, and the sub-failure vector is divided into k+1 quality levels in combination with the upper and lower limits of 0 and 1, and each quality level is numbered with non-repeating uppercase English letters. The wear failure of in-service mechanical product parts is divided into corresponding quality levels based on the quality level of each sub-failure vector. The other failures of in-service mechanical product parts are divided into corresponding quality levels in the same way, so that the failure characteristics of in-service mechanical product parts after classification show higher concentration and lower complexity. Combined with the set active remanufacturing repair threshold, the design difficulty of active remanufacturing process scheme is reduced;

[0054] Step S3 also includes taking into account the dimensional constraints, based on the three designed remanufacturing schemes for in-service mechanical products, combined with the quality level of the parts of the in-service mechanical products, to perform the optimal allocation operation for the in-service mechanical product parts required in different remanufacturing schemes. The specific operation is to use the factory's remanufacturing capacity for in-service mechanical products and the market demand for in-service mechanical products as the upper and lower limits of the dimensional accuracy constraints, construct the tolerance dimensional constraint free range, and use the dimensional constraint accuracy loss as the target to construct the dimensional accuracy loss function of the in-service mechanical product parts under different dimensional accuracies. The specific expression is as follows:

[0055]

[0056] In the formula, A represents the number of alternative parts, a represents the ath alternative part, f(T ab ) represents the tolerance function of the ath candidate part with accuracy grade b, f(T a ) represents the design target tolerance function of the ath candidate part, and the dimensional accuracy loss function of the in-service mechanical product parts under each dimensional accuracy is accumulated to obtain the final dimensional accuracy loss function of the in-service mechanical product parts;

[0057] Step S3 also includes constructing a cost function for selecting and matching parts of in-service mechanical products with the goal of minimizing the remanufacturing cost. The specific expression is as follows:

[0058]

[0059] In the formula, B represents the total number of dimensional accuracy levels of mechanical product parts in service, A ab represents the factory's remanufacturing capability for the ath candidate part at accuracy level b, B ab It indicates the factory's remanufacturing process control for the ath candidate part with accuracy level b. represents the process tolerance index of the ath candidate part with accuracy grade b, Y represents the total number of candidate parts with accuracy grade b, y represents the yth candidate part with accuracy grade b, C Lb represents the reuse cost of parts with accuracy level b, C NbThe procurement cost of the Nth new part with accuracy level b is represented, and the final dimensional accuracy loss function of the in-service mechanical product parts is jointly constructed. The global optimization is solved through the collaborative optimization algorithm to achieve the optimal allocation operation of the in-service mechanical product parts, and at the same time, the collaborative optimization of the active remanufacturing cost and quality of the in-service mechanical products is achieved;

[0060] Step S4 also includes process scheme design and parts selection operations for the three designed remanufacturing schemes for in-service mechanical products, and establishes a decision matrix for active remanufacturing schemes for in-service mechanical products from three aspects: economic benefit analysis, pollution emission analysis, and product quality analysis. The specific operation of economic benefit analysis is to obtain historical remanufacturing cost data and corresponding mechanical product failure feature data, calculate the similarity between the historical mechanical product failure feature data and the failure feature data of in-service mechanical products that meet the remanufacturability through the Euclidean algorithm, take the three groups of cost data with the highest failure feature similarity, and predict the cost of active remanufacturing mechanical products through the cost prediction algorithm. The specific calculation formula is as follows:

[0061]

[0062] Where D′ d represents the remanufacturing cost of the failure characteristics of in-service mechanical products ranked by similarity d, and α represents the smoothing coefficient;

[0063] Step S4 also includes analyzing the pollution emissions in the same way as the economic benefit analysis, obtaining the energy consumption in the remanufacturing process of the in-service mechanical products and converting it into the carbon dioxide emission data after the combustion of standard carbon, and using the horizontal comparison method to subtract the carbon dioxide emission data in the active remanufacturing program of the in-service mechanical products from the carbon dioxide emission data in the historical mechanical product manufacturing process, and dividing the result with the carbon dioxide emission data in the historical mechanical product manufacturing process to obtain the pollution emission benefit evaluation value, wherein the product quality analysis specifically evaluates the performance reliability and social recognition of the in-service mechanical products, performs performance evaluation on the in-service mechanical products based on expert experience, obtains social recognition based on social surveys, and uses half of the cumulative result of the two as the product quality evaluation value, and constructs a decision matrix for the active remanufacturing program of in-service mechanical products, and its specific expression is as follows:

[0064]

[0065] Wherein, Xre1 represents the economic benefit evaluation value of the first design method, Xrp1 represents the pollution emission evaluation value of the first design method, Xrq1 represents the product quality evaluation value of the first design method, and ω1 represents the weight coefficient of the first evaluation index analyzed by the semi-supervised learning algorithm. A comprehensive benefit evaluation is conducted on the three designed remanufacturing schemes for in-service mechanical products, and the in-service mechanical product manufacturing scheme with the best comprehensive benefit evaluation is selected for execution.

[0066] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0067] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A data-driven decision-making solution generation method, characterized by The following steps are involved: S1: The data-driven decision-making scheme generation method is applied to the active remanufacturing of in-service mechanical products. Three in-service mechanical product remanufacturing schemes are designed for in-service mechanical products that meet the remanufacturability. The failure characteristic data of in-service mechanical products that meet the remanufacturability are obtained and the failure characteristic data are quantified. The pollution emission data in the remanufacturing process of in-service mechanical products that meet the remanufacturability are obtained and processed. S2: Based on the failure characteristic data of in-service mechanical products that meet the remanufacturability, a corresponding failure characteristic data set is established, and a classification threshold matrix of various failure characteristics is formulated based on the market demand and remanufacturing parameters of the in-service mechanical products to achieve accurate quality classification of in-service mechanical product parts; S3: Based on the three designed remanufacturing schemes for in-service mechanical products and the quality level of in-service mechanical product parts, the in-service mechanical product parts required in different remanufacturing schemes are optimally allocated under the consideration of size constraints, so as to meet the market performance requirements of in-service mechanical products and achieve the coordinated optimization of active remanufacturing cost and quality of in-service mechanical products; S4: Establish a decision matrix for active remanufacturing of in-service mechanical products from three aspects: economic benefit analysis, pollution emission analysis, and product quality analysis. Conduct a comprehensive benefit evaluation on the three designed remanufacturing plans for in-service mechanical products, and select the in-service mechanical product manufacturing plan with the best comprehensive benefit evaluation for implementation.

2. The data-driven decision-making solution generation method according to claim 1 is characterized in that: The step S1 also includes designing three remanufacturing schemes for in-service mechanical products that meet the requirements of remanufacturing, including a performance upgrade type active remanufacturing scheme, a performance repair type active remanufacturing scheme, and a performance degradation type active remanufacturing scheme. The failure characteristic data of in-service mechanical products that meet the remanufacturing requirements are obtained through modern intelligent detection technology, including three parameters: failure form, failure degree, and failure location. The failure degree parameters corresponding to each failure form of the in-service mechanical products that meet the remanufacturing requirements are interval quantized and normalized, and the failure degree data are converted into a value between [0, 1].

3. The data-driven decision-making solution generation method according to claim 1, characterized in that: The step S1 also includes acquiring energy consumption data during the remanufacturing process of in-service mechanical products that meet the remanufacturability within the three designed schemes, and the consumed energy is divided into five types: raw coal, water, electricity, gasoline and diesel, and the energy consumption data of each type of energy is converted into carbon dioxide emission data after combustion of standard carbon through an energy consumption data conversion algorithm.

4. The data-driven decision-making solution generation method according to claim 1 is characterized in that: The step S2 also includes establishing a failure characteristic data set of in-service mechanical products and their parts from three perspectives of failure location, failure form and failure degree based on the failure characteristic data of in-service mechanical products that meet the remanufacturability, establishing a failure characteristic data set of in-service mechanical products and their parts, further establishing a failure characteristic data set of in-service mechanical product parts wear by taking the wear failure form as an example, and establishing a failure characteristic data set of other failure forms of in-service mechanical product parts in the same way.

5. The data-driven decision-making solution generation method according to claim 1 is characterized in that: The step S2 also includes setting each column parameter in the failure characteristic data set of various failure forms of in-service mechanical product parts as a sub-failure vector of the corresponding failure form, and in the process of active remanufacturing of mechanical products, in order to avoid insufficient or excessive repair of in-service mechanical product parts and thus affect the overall performance of the mechanical product, the active remanufacturing repair threshold is set according to the market demand and redesign parameters of the in-service mechanical products. Taking the wear failure form as an example, a wear grading threshold matrix is ​​established, and each quality level is numbered with non-repeating uppercase English letters. The wear failure of in-service mechanical product parts is divided into corresponding quality levels based on the quality level of each sub-failure vector. In the same way, other failures of in-service mechanical product parts are divided into corresponding quality levels, so that the failure characteristics of in-service mechanical product parts after grading show higher concentration and lower complexity. Combined with the set active remanufacturing repair threshold, the design difficulty of the active remanufacturing process scheme is reduced.

6. The data-driven decision-making solution generation method according to claim 1, characterized in that: The step S3 also includes taking into account the dimensional constraints, based on the three designed remanufacturing schemes for in-service mechanical products, combined with the quality grades of the in-service mechanical product parts and components, to perform the optimal allocation operation on the in-service mechanical product parts and components required in different remanufacturing schemes. The specific operation is to use the factory's remanufacturing capacity for in-service mechanical products and the market demand for in-service mechanical products as the upper and lower limits of the dimensional accuracy constraints, construct a tolerance dimensional constraint free range, and construct a dimensional accuracy loss function of in-service mechanical product parts and components under different dimensional accuracies with the dimensional constraint accuracy loss as the target, and accumulate the dimensional accuracy loss functions of in-service mechanical product parts and components under each dimensional accuracy to obtain the final dimensional accuracy loss function of in-service mechanical product parts and components.

7. The data-driven decision-making solution generation method according to claim 1 is characterized in that: The step S3 also includes constructing a cost function for selecting and matching parts of in-service mechanical products with the goal of minimizing remanufacturing costs, and jointly constructing a final in-service mechanical product parts dimensional accuracy loss function, and performing global optimization and solving through a collaborative optimization algorithm to achieve the optimal matching operation of in-service mechanical product parts, while achieving collaborative optimization of the active remanufacturing cost and quality of in-service mechanical products.

8. The data-driven decision-making solution generation method according to claim 1, characterized in that: The step S4 also includes respectively performing process scheme design and parts selection operations for the three designed remanufacturing schemes for in-service mechanical products, and respectively establishing a decision matrix for active remanufacturing schemes for in-service mechanical products from three aspects: economic benefit analysis of active remanufacturing of in-service mechanical products, pollution emission analysis, and product quality analysis. The specific operation of the economic benefit analysis is to obtain historical remanufacturing cost data and corresponding mechanical product failure characteristic data, calculate the similarity between the historical mechanical product failure characteristic data and the failure characteristic data of in-service mechanical products that meet the remanufacturability through the Euclidean algorithm, take the three groups of cost data with the highest failure characteristic similarity, and predict the cost of active remanufacturing mechanical products through the cost prediction algorithm.

9. The data-driven decision-making solution generation method according to claim 1, characterized in that: The step S4 also includes analyzing the pollution emissions in the same way as the economic benefit analysis, obtaining the energy consumption in the remanufacturing process of the in-service mechanical products and converting it into carbon dioxide emission data after the combustion of standard carbon, and using a horizontal comparison method to subtract the carbon dioxide emission data in the active remanufacturing plan of the in-service mechanical products from the carbon dioxide emission data in the historical mechanical product manufacturing process, and dividing the result with the carbon dioxide emission data in the historical mechanical product manufacturing process to obtain a pollution emission benefit assessment value, wherein the product quality analysis specifically evaluates the performance reliability and social recognition of the in-service mechanical products, performs a performance evaluation on the in-service mechanical products based on expert experience, obtains social recognition based on social surveys, and uses half of the cumulative result of the two as the product quality assessment value, and constructs a decision matrix for the active remanufacturing plan of the in-service mechanical products, conducts a comprehensive benefit evaluation on the three designed in-service mechanical product remanufacturing plans, and selects the in-service mechanical product manufacturing plan with the best comprehensive benefit evaluation for execution.

Images