Wire and cable raw material screening method and system combined with data analysis

Abstract

The invention provides a wire and cable raw material screening method and system combined with data analysis, and relates to the technical field of wires and cables, and the method comprises the steps: receiving a raw material screening instruction sent by a wire and cable production end to a wire and cable raw material library; on the basis of wire and cable production requirements, according to the conductor fitness evaluation model, carrying out fitness analysis on the conductor raw material library; based on wire and cable production requirements, according to the extrusion production accident event set, carrying out extrusion production risk analysis on the insulation sheath raw material library; performing performance risk analysis on the shielding filling raw material library according to the wire and cable production requirements; integrating the conductor raw material evaluation grid, the insulating sheath raw material evaluation grid and the shielding filling raw material evaluation grid to generate a multi-dimensional raw material evaluation grid; and according to the multi-dimensional raw material evaluation grid, carrying out automatic grading screening on the wire and cable raw material library. The technical problem that in the prior art, the electric wire and cable classification screening efficiency is low can be solved, and the technical effect of improving the classification screening efficiency is achieved.

Description

Technical Field

[0001] This application relates to the field of wire and cable technology, and in particular to a method and system for screening wire and cable raw materials by combining data analysis. Background Technology

[0002] With the rapid development of the wire and cable industry and the increasing demand for high-performance cables, the quality and performance of raw materials play a crucial role in the cable production process. High-performance cables not only require conductors to have excellent electrical conductivity and mechanical strength, but also require insulation sheaths to have excellent temperature resistance, abrasion resistance, and flame retardancy. At the same time, the shielding filling material needs to ensure good signal shielding effect and structural stability.

[0003] Currently, existing methods for managing raw materials for wires and cables mainly rely on manual screening and experience-based judgment, lacking a systematic and scientific evaluation and grading mechanism. This leads to unstable raw material quality and low screening efficiency. Furthermore, traditional methods often manage conductor, insulation sheath, and shielding filler materials separately, lacking multi-dimensional comprehensive analysis. This fails to fully reflect the compatibility and potential risks between raw materials, easily resulting in mismatched material combinations during production, leading to cable performance degradation or production accidents. For example, if the insulation sheath has insufficient temperature resistance when the conductor heats up, it may cause localized melting or short circuit risks; conversely, a low flame retardant rating in the shielding filler material may also pose safety hazards in fire or high-temperature environments.

[0004] In summary, the existing technology suffers from a lack of a comprehensive raw material management system based on multi-dimensional evaluation and risk prediction. This results in the inability to scientifically screen and optimize the combination of conductor, insulation sheath, and shielding filler materials in terms of performance matching, scrap risk, and production adaptability. Consequently, this technology further affects the reliability of wire and cable production, product performance stability, production safety, and economic benefits. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for screening raw materials for wires and cables that combines data analysis, in order to solve the technical problems in the prior art where the lack of a comprehensive raw material management system based on multi-dimensional evaluation and risk prediction leads to the inability to scientifically screen and optimize the combination of conductor, insulation sheath and shielding filler raw materials in terms of performance matching, scrap risk and production adaptability, which further affects the reliability of wire and cable production, product performance stability, production safety and economic benefits.

[0006] In view of the above problems, this application provides a method and system for screening wire and cable raw materials by combining data analysis.

[0007] Firstly, this application provides a method for screening raw materials for wires and cables that combines data analysis. This method is implemented through a system for screening raw materials for wires and cables that combines data analysis. The method includes: receiving a raw material screening instruction sent from the wire and cable production end to a raw material library, whereby the raw material library includes a conductor raw material library, an insulation sheath raw material library, and a shielding filler raw material library; the raw material screening instruction includes wire and cable production requirements; based on the wire and cable production requirements, performing a compatibility analysis on the conductor raw material library according to a conductor compatibility evaluation model to construct a conductor raw material evaluation grid; based on the wire and cable production requirements, performing an extrusion production risk analysis on the insulation sheath raw material library according to an extrusion production accident event set to construct an insulation sheath raw material evaluation grid; performing a performance risk analysis on the shielding filler raw material library according to the wire and cable production requirements to establish a shielding filler raw material evaluation grid; integrating the conductor raw material evaluation grid, the insulation sheath raw material evaluation grid, and the shielding filler raw material evaluation grid to generate a multi-dimensional raw material evaluation grid; and automatically classifying and screening the wire and cable raw material library according to the multi-dimensional raw material evaluation grid.

[0008] Preferably, the wire and cable raw material screening method combined with data analysis further includes: collecting storage characteristic information of the conductor raw material library and constructing a conductor raw material storage grid; performing multi-dimensional performance testing on each conductor raw material in the conductor raw material library to obtain a test sequence for each conductor raw material; evaluating the conductor raw material compatibility based on the conductor raw material test sequences, according to the wire and cable production requirements and the conductor compatibility evaluation model, to obtain multiple conductor compatibility evaluation sequences; predicting the scrap risk of each conductor raw material based on the conductor raw material test sequences to obtain a conductor scrap risk distribution; and dynamically mapping the conductor raw material storage grid according to the multiple conductor compatibility evaluation sequences and the conductor scrap risk distribution to generate the conductor raw material evaluation grid.

[0009] Preferably, the wire and cable raw material screening method combined with data analysis further includes: traversing the detection sequences of each conductor raw material and extracting a first conductor raw material detection sequence; constructing a first conductor feature vector set based on the first conductor raw material detection sequence; activating the conductor fit evaluation model, which includes multiple conductor fit evaluation indicators, including electrical feature fit, mechanical feature fit, and structural feature fit; inputting the wire and cable production requirements and the first conductor feature vector set into the conductor fit evaluation model to obtain a first fit evaluation result; performing a weighted calculation on the first fit evaluation result according to the fit weight conditions of the multiple conductor fit evaluation indicators to obtain a first comprehensive conductor fit; and encapsulating the first fit evaluation result and the first comprehensive conductor fit into a first conductor fit evaluation sequence.

[0010] Preferably, the wire and cable raw material screening method combined with data analysis further includes: retrieving scrap events based on a first conductor raw material detection sequence to obtain a conductor scrap event set; performing raw material performance twin evaluation on the conductor scrap event set based on the first conductor raw material detection sequence to obtain a raw material performance twin evaluation set; allocating attention to each scrap risk sample in the conductor scrap event set based on the raw material performance twin evaluation set to obtain a scrap risk attention map; performing fusion calculation on each scrap risk sample based on the scrap risk attention map to generate a first conductor scrap risk coefficient, and adding the first conductor scrap risk coefficient to the conductor scrap risk distribution.

[0011] Preferably, the wire and cable raw material screening method combined with data analysis further includes: collecting storage characteristic data of the insulation sheath raw material warehouse to construct an insulation sheath raw material storage grid; performing multi-degree-of-freedom performance testing on each insulation sheath raw material in the insulation sheath raw material warehouse to obtain multiple insulation sheath raw material data; performing extrusion production risk prediction on the multiple insulation sheath raw material data based on the extrusion production accident event set to obtain an extrusion production risk distribution; performing scrap risk prediction on the multiple insulation sheath raw material data to obtain an insulation sheath scrap risk distribution; and dynamically mapping the insulation sheath raw material storage grid based on the extrusion production risk distribution and the insulation sheath scrap risk distribution to generate the insulation sheath raw material evaluation grid.

[0012] Preferably, the wire and cable raw material screening method combined with data analysis further includes: identifying accident types based on the extrusion production accident event set to obtain an extrusion accident type set; tracing the accident paths of the extrusion accident type set based on the extrusion production accident event set to obtain an extrusion production accident path set; training an accident tree based on the extrusion production accident path set to obtain an extrusion production risk prediction model; subjecting the extrusion production accident path set to random perturbation to obtain an extrusion accident perturbation path set; reinforcing the extrusion production risk prediction model based on the extrusion accident perturbation path set to generate an extrusion production risk prediction channel; and inputting the multiple insulation sheath raw material data into the extrusion production risk prediction channel to obtain the extrusion production risk distribution.

[0013] Preferably, the wire and cable raw material screening method combined with data analysis further includes: constructing a shielding filler raw material storage grid based on the storage dataset of the shielding filler raw material library; predicting the expected performance of the shielding filler raw materials based on the production needs of the wire and cable, and constructing a raw material performance expectation space; performing performance testing based on the shielding filler raw material library to obtain data for each shielding filler raw material; evaluating the deviation risk of each shielding filler raw material data based on the raw material performance expectation space to obtain a raw material performance risk distribution; predicting the scrap risk based on each shielding filler raw material data to obtain a shielding filler raw material scrap risk distribution; and dynamically mapping the shielding filler raw material storage grid based on the raw material performance risk distribution and the shielding filler raw material scrap risk distribution to generate the shielding filler raw material evaluation grid.

[0014] Preferably, the wire and cable raw material screening method combined with data analysis further includes: the first conductor feature vector set includes a first conductor electrical feature vector, a first conductor mechanical feature vector, and a first conductor structural feature vector.

[0015] Preferably, the wire and cable raw material screening method combined with data analysis further includes: the fit weight conditions include electrical characteristic fit weight, mechanical characteristic fit weight and structural characteristic fit weight.

[0016] Secondly, this application also provides a wire and cable raw material screening system combining data analysis, used to execute the wire and cable raw material screening method combining data analysis as described in the first aspect, comprising: an instruction sending module, used to receive raw material screening instructions sent from the wire and cable production end to the wire and cable raw material library, the wire and cable raw material library including a conductor raw material library, an insulation sheath raw material library, and a shielding filling raw material library, the raw material screening instructions including wire and cable production requirements; a conductor raw material evaluation grid construction module, used to perform fit analysis on the conductor raw material library based on the wire and cable production requirements and according to a conductor fit evaluation model, and construct a conductor raw material evaluation grid; and an insulation sheath raw material evaluation grid construction module. The system comprises the following modules: a module for analyzing the extrusion production risks of the insulation sheath raw material library based on the wire and cable production requirements and an extrusion production accident event set, and constructing an evaluation grid for insulation sheath raw materials; a module for establishing an evaluation grid for shielding filler raw materials, which analyzes the performance risks of the shielding filler raw material library based on the wire and cable production requirements, and constructs an evaluation grid for shielding filler raw materials; a module for generating a multi-dimensional raw material evaluation grid, which integrates the evaluation grids for conductor raw materials, insulation sheath raw materials, and shielding filler raw materials, and generates a multi-dimensional raw material evaluation grid; and an automatic grading and screening module, which automatically grades and screens the wire and cable raw material library based on the multi-dimensional raw material evaluation grid.

[0017] The technical solution provided in this application has at least the following technical effects or advantages: by achieving the technical goal of multi-dimensional, dynamic and intelligent comprehensive evaluation and automatic grading and screening of wire and cable raw materials, it achieves the technical effects of improving raw material utilization efficiency, reducing scrap risk, optimizing material matching relationship, ensuring production safety and improving the overall performance and economic benefits of cable products.

[0018] The above description is merely an overview of the technical solution of this application. To enable a clearer understanding of the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the wire and cable raw material screening method based on data analysis proposed in this application.

[0021] Figure 2 This is a schematic diagram of the wire and cable raw material screening system based on data analysis, as described in this application.

[0022] Figure labeling: 1. Command sending module; 2. Conductor material evaluation grid construction module; 3. Insulation sheath material evaluation grid construction module; 4. Shielding filling material evaluation grid establishment module; 5. Multidimensional material evaluation grid generation module; 6. Automatic grading and screening module. Detailed Implementation

[0023] This application provides a data-driven method and system for screening raw materials for wires and cables. It addresses the technical problem in existing technologies where the lack of a comprehensive raw material management system based on multi-dimensional evaluation and risk prediction prevents the scientific screening and optimized combination of conductor, insulation sheath, and shielding filler materials in terms of performance matching, scrap risk, and production adaptability. This, in turn, negatively impacts the reliability, product performance stability, production safety, and economic efficiency of wire and cable production. The application achieves the technical goal of multi-dimensional, dynamic, and intelligent comprehensive evaluation and automatic grading screening of wire and cable raw materials, thereby improving raw material utilization efficiency, reducing scrap risk, optimizing material matching relationships, ensuring production safety, and enhancing the overall performance and economic efficiency of cable products.

[0024] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0025] Example 1, please refer to the appendix. Figure 1 This application provides a method for screening wire and cable raw materials based on data analysis, which is applied to a wire and cable raw material screening system based on data analysis, and specifically includes the following steps: S1: Receive raw material screening instructions sent from the wire and cable production end to the wire and cable raw material library. The wire and cable raw material library includes conductor raw material library, insulation sheath raw material library and shielding filling raw material library. The raw material screening instructions include wire and cable production requirements.

[0026] Specifically, receiving raw material screening instructions from the wire and cable production end to the wire and cable raw material warehouse indicates that during the wire and cable production process, the production equipment or management system will issue an instruction to the wire and cable raw material storage system based on the upcoming production task. This instruction tells the storage system to select and screen existing wire and cable raw materials. The wire and cable production end can be a control system on the production line or a scheduling system, capable of converting the information required for production into instruction signals and sending them out.

[0027] The wire and cable raw material warehouse includes conductor raw material warehouse, insulation sheath raw material warehouse, and shielding filler raw material warehouse, storing different types of raw materials respectively. The conductor raw material warehouse stores materials capable of conducting current, such as copper wire and aluminum wire; the insulation sheath raw material warehouse stores polymer insulation materials used to wrap the conductor, such as polyvinyl chloride or cross-linked polyethylene; the shielding filler raw material warehouse stores materials used to enhance the cable's anti-interference performance or maintain structural stability, such as metal braided mesh or flame-retardant fillers. Raw material selection instructions include wire and cable production requirements, such as the required cable specifications, conductor diameter, insulation thickness, withstand voltage rating, tensile strength, and operating environment conditions.

[0028] S2: Based on the production requirements of the wires and cables, the conductor material library is analyzed for compatibility according to the conductor compatibility evaluation model, and a conductor material evaluation grid is constructed.

[0029] Specifically, before screening conductor raw materials, the specific production task requirements must be clearly defined, such as whether high-voltage cables or low-voltage signal lines need to be produced. This determines the different requirements for the electrical, mechanical, and structural properties of the conductors. The conductor raw material library is analyzed for compatibility using a conductor compatibility evaluation model to calculate the degree of matching between the library and production needs. The conductor compatibility evaluation model includes multiple indicators, such as electrical characteristic compatibility, mechanical characteristic compatibility, and structural characteristic compatibility, quantifying the overall performance of each raw material. The compatibility results of all raw materials are then placed into a visualized coordinate or matrix system to display the superiority or inferiority relationships of the raw materials in a multi-dimensional way, constructing a conductor raw material evaluation grid.

[0030] S3: Based on the production needs of the wires and cables, perform extrusion production risk analysis on the insulation sheath raw material library according to the extrusion production accident event set, and construct an evaluation grid for insulation sheath raw materials.

[0031] Specifically, based on the production needs of wires and cables, an extrusion production risk analysis is conducted on the insulation sheath raw material warehouse using extrusion production accident event sets. This involves taking the specific requirements of wire and cable production as a premise, and using accumulated accident data from past extrusion production processes as a reference to analyze the potential risks of different batches of raw materials in the insulation sheath raw material warehouse. Wire and cable production needs refer to the performance requirements for manufacturing a certain type of product, such as insulation resistance greater than 20 megohms per kilometer, temperature resistance reaching 90 degrees Celsius, and tensile strength not less than 20 MPa. The extrusion production accident event set consists of anomalies and accident cases recorded in production practice, such as uneven insulation layer thickness, material decomposition producing bubbles, or cracking due to temperature instability. The extrusion production risk analysis calculates the probability that the raw material may trigger an accident during extrusion production by comparing raw material testing data with accident event characteristics. The results of the risk analysis are then integrated with raw material storage information and performance testing data into a structured evaluation system, constructing an insulation sheath raw material evaluation grid to classify the risk levels of the raw materials.

[0032] S4: Based on the production requirements of the wires and cables, perform performance risk analysis on the shielding filler material library and establish an evaluation grid for shielding filler materials.

[0033] Specifically, a performance risk analysis is conducted on the shielding and filling material warehouse based on the production needs of wires and cables. This involves analyzing the actual performance of shielding and filling materials against the specific requirements of the production end, and assessing potential risks. The production needs of wires and cables refer to the target performance requirements for the finished cables. For example, signal cables require a shielding attenuation of more than 60 dB, power cables require fillers with a temperature resistance higher than 90 degrees Celsius, and flame-retardant cables require fillers with an oxygen index of not less than 28%. The shielding and filling material warehouse is a centralized storage collection of raw materials used for shielding and filling in cables, including copper wire braided mesh, aluminum foil shielding tape, mica tape, and flame-retardant fillers. The performance risk analysis involves testing the conductivity, mechanical strength, thermal stability, and flame retardancy of the raw materials and comparing them with the thresholds set for production needs to determine whether there is any risk. For example, if a batch of aluminum foil shielding tape has insufficient thickness, resulting in a decrease in shielding performance, it is considered a high-risk raw material. By combining the results of performance risk analysis with raw material storage information, a multi-dimensional evaluation system is constructed, and a shielded raw material evaluation grid is established. This system can intuitively display the position of different batches of raw materials in terms of performance satisfaction, risk level, and usage priority in two-dimensional or three-dimensional space.

[0034] S5: Integrate the conductor material evaluation grid, the insulation sheath material evaluation grid, and the shielding fill material evaluation grid to generate a multi-dimensional material evaluation grid.

[0035] Specifically, the integrated evaluation grids for conductor materials, insulation sheath materials, and shielding filler materials unify the evaluation results of these three different types of materials into a larger data system. The conductor material evaluation grid is a structured result of adaptability and risk assessment of metallic conductor materials in cables, covering information such as conductivity, mechanical strength, and scrap risk. The insulation sheath material evaluation grid is the performance and risk analysis result of the cable's outer protective material, involving electrical insulation, mechanical abrasion resistance, and accident risks during production. The shielding filler material evaluation grid is an evaluation system for materials used inside cables to shield against signal interference or fill space, including shielding effectiveness, flame retardant performance, and aging scrap risk. These three evaluation grids are integrated into a unified data structure through data alignment and multi-dimensional merging, generating a multi-dimensional material evaluation grid. This multi-dimensional material evaluation grid not only displays the performance and risks of each type of material but also shows their inter-dimensional correlations, thus reflecting the combined effects between materials. For example, the conductor material needs to be matched with the insulation sheath material. If the conductor has high thermal performance, the sheath must have stronger temperature resistance. If the shielding filler material has a low flame retardant rating, it will also affect the overall safety of the cable.

[0036] S6: Automatically classify and screen the wire and cable raw material library according to the multi-dimensional raw material evaluation grid.

[0037] Specifically, the system automatically grades and screens the wire and cable raw material library based on a multi-dimensional raw material evaluation grid. This means that all conductor materials, insulation sheath materials, and shielding filler materials in the library are intelligently classified and screened using this grid. The multi-dimensional raw material evaluation grid is a multi-dimensional analysis model that integrates performance indicators, risk assessments, and compatibility results, simultaneously displaying information such as the electrical and mechanical properties, structural stability, production risks, and scrap risks of different materials. The wire and cable raw material library is a centralized collection of raw materials, containing a large number of batches from diverse sources. Automatic grading and screening uses algorithms and models to automatically allocate raw materials to different grades, such as priority use, optional, and obsolete grades. Automated grading improves screening efficiency and reduces human error. Previously, manually screening 100 batches of raw materials might require manual inspection and judgment, taking an average of 10 minutes per batch, totaling 1000 minutes. Automatic grading and screening, however, only requires rapid system calculation and can be completed within 5 minutes, thus increasing efficiency by 200 times. The classification is usually based on a combination of performance and risk. For example, a batch of conductor raw materials with high electrical conductivity, meeting mechanical strength standards, and low scrap risk is classified as a priority use grade; a batch of insulating sheath materials with good insulation but high extrusion risk is classified as an optional grade; and a batch of shielding materials that is clearly unqualified in flame retardant testing and has a high scrap risk is directly classified as an elimination grade.

[0038] Furthermore, this application also includes: collecting storage characteristic information of the conductor raw material warehouse and constructing a conductor raw material storage grid; performing multi-dimensional performance testing on each conductor raw material in the conductor raw material warehouse to obtain a testing sequence for each conductor raw material; based on the testing sequences of each conductor raw material, evaluating the compatibility of the conductor raw materials according to the wire and cable production requirements and the conductor compatibility evaluation model to obtain multiple conductor compatibility evaluation sequences; predicting the scrap risk of each conductor raw material based on the testing sequences of each conductor raw material to obtain a conductor scrap risk distribution; and dynamically mapping the conductor raw material storage grid according to the multiple conductor compatibility evaluation sequences and the conductor scrap risk distribution to generate the conductor raw material evaluation grid.

[0039] Specifically, collecting storage characteristic information of conductor raw material warehouses and constructing conductor raw material storage grids means collecting various storage-related data from warehouses storing conductor materials, including the storage location of raw materials, entry time, batch number, ambient temperature, humidity, and inventory quantity, etc., to reflect the storage status of raw materials in the warehouse. The conductor raw material storage grid is a way to map storage characteristic information into a gridded data structure. Each grid node corresponds to a batch or a specific conductor raw material, which facilitates subsequent marking and tracking of its status.

[0040] Next, each conductor material in the conductor material library undergoes multi-dimensional performance testing, including electrical, mechanical, and structural properties. Electrical properties refer to the material's characteristics when conducting current, such as resistivity, current carrying capacity, conductivity, and heat generation; the results reflect the material's efficiency in transmitting electrical energy. Mechanical properties test the material's performance under external forces, including tensile strength, elongation, and bending radius. Structural properties refer to the material's internal microstructure and appearance characteristics, including crystallinity, surface smoothness, and defect distribution, which contribute to improving long-term stability.

[0041] The results of electrical performance tests, mechanical performance tests, and structural performance tests are combined to form multidimensional performance data. This multidimensional performance data is then organized into a continuous dataset according to time or batch to obtain the test sequence for each conductor material.

[0042] Then, based on the detection sequences of each conductor material, the conductor material compatibility is evaluated according to the production requirements of wires and cables and the conductor compatibility evaluation model, resulting in multiple conductor compatibility evaluation sequences. This involves comparing the detected performance data with production requirements and calculating using a pre-established compatibility evaluation model. Each conductor compatibility evaluation sequence represents the compatibility of the same batch of materials under different demand scenarios. For example, the compatibility of a batch of copper wire might be 0.85 under low-voltage cable requirements, but 0.6 under high-voltage cable requirements. These compatibility results under different requirements constitute multiple compatibility evaluation sequences.

[0043] Furthermore, based on the testing sequences of each conductor material, a scrap risk prediction is performed for each conductor material to obtain a conductor scrap risk distribution. This indicates that not only is the current applicability of the material analyzed, but also potential future problems are predicted. The scrap risk prediction utilizes testing data, combined with historical usage cases of the material, to infer the likelihood of the material failing during subsequent use or storage. For example, if the testing sequence shows that the corrosion resistance of a batch of aluminum wire is decreasing too rapidly, it will conclude that the material has a 40% scrap risk after 3 months. The risk distribution statistically presents the scrap probability of all materials, forming a distribution similar to a heat map.

[0044] Finally, the conductor raw material storage grid is dynamically mapped based on multiple conductor fit evaluation sequences and conductor scrap risk distribution to generate a conductor raw material evaluation grid. This means that the results of fit and scrap risk are superimposed on the storage grid, resulting in a more comprehensive evaluation grid. In the conductor raw material evaluation grid, each node not only contains the storage characteristics of the raw material but also is associated with fit and scrap risk information. The management system can then identify a batch of materials that meets production requirements and has a low scrap risk, thus prioritizing its selection. Nodes with high scrap risk and low fit are marked as secondary choices or to be eliminated.

[0045] Furthermore, this application also includes: traversing the detection sequences of each conductor raw material to extract a first conductor raw material detection sequence; constructing a first conductor feature vector set based on the first conductor raw material detection sequence; activating the conductor fit evaluation model, the conductor fit evaluation model including multiple conductor fit evaluation indicators, the multiple conductor fit evaluation indicators including electrical feature fit, mechanical feature fit, and structural feature fit; inputting the wire and cable production requirements and the first conductor feature vector set into the conductor fit evaluation model to obtain a first fit evaluation result; performing a weighted calculation on the first fit evaluation result according to the fit weight conditions of the multiple conductor fit evaluation indicators to obtain a first conductor comprehensive fit; and encapsulating the first fit evaluation result and the first conductor comprehensive fit into a first conductor fit evaluation sequence.

[0046] Specifically, each conductor material detection sequence is accessed sequentially, and the first conductor material detection sequence is randomly extracted. Based on the first conductor material detection sequence, a first conductor feature vector set is constructed, including the first conductor electrical feature vector, the first conductor mechanical feature vector, and the first conductor structural feature vector.

[0047] Then, a machine learning model is configured as a conductor fit evaluation model. The conductor fit evaluation model includes multiple conductor fit evaluation indicators, which include electrical characteristic fit, mechanical characteristic fit, and structural characteristic fit. Electrical characteristic fit reflects the degree to which the material's ability to conduct current matches the requirements. Mechanical characteristic fit assesses whether the material's strength and toughness meet production requirements. Structural characteristic fit analyzes whether the internal and external structural characteristics of the material are stable and reliable.

[0048] Next, the production requirements of wires and cables and the first conductor feature vector set are input into the conductor fit evaluation model to obtain the first result of the fit evaluation. That is, the specific demand parameters proposed by the production end are combined with the performance data of the material. The conductor fit evaluation model can compare the demand and performance vectors and calculate the fit, thereby obtaining a result that measures the degree of fit between the material and the demand.

[0049] Subsequently, the first result of the conductor fit evaluation is weighted according to the fit weight conditions of multiple indicators in the conductor fit evaluation to obtain the first comprehensive conductor fit. That is, the weights of electrical, mechanical, and structural indicators differ under different production requirements. For example, for high-voltage cables, the weight of electrical performance may be 0.6, mechanical performance 0.3, and structural performance 0.1, while for low-voltage cables, the weight of electrical performance may decrease to 0.4, and mechanical performance may increase to 0.4. Through weighted calculation, a comprehensive fit result can be obtained.

[0050] Finally, the first result of the fit evaluation and the comprehensive fit of the first conductor are packaged into a first conductor fit evaluation sequence, which retains the result of each individual evaluation and also packages the weighted comprehensive result into a complete data set.

[0051] Furthermore, this application also includes: retrieving scrap events based on a first conductor raw material detection sequence to obtain a conductor scrap event set; performing a raw material performance twin evaluation on the conductor scrap event set based on the first conductor raw material detection sequence to obtain a raw material performance twin evaluation set; allocating attention to each scrap risk sample within the conductor scrap event set based on the raw material performance twin evaluation set to obtain a scrap risk attention map; performing a fusion calculation on each scrap risk sample based on the scrap risk attention map to generate a first conductor scrap risk coefficient, and adding the first conductor scrap risk coefficient to the conductor scrap risk distribution.

[0052] Specifically, based on the first conductor material detection sequence, scrap event retrieval is performed, matching historical scrap cases to identify situations potentially similar to the current material, thus obtaining a conductor scrap event set. Scrap event retrieval refers to searching the database for past cases of materials being phased out due to insufficient performance.

[0053] Next, a material performance twin evaluation is performed on the conductor scrap event set based on the first conductor material detection sequence to obtain a material performance twin evaluation set. This involves establishing a virtual performance mapping relationship by comparing the current material detection results with data patterns from historical scrap events. Material performance twin evaluation refers to using a digital model to replicate a virtual object that closely resembles the actual material, thereby simulating performance under different conditions. For example, if the detection sequence shows that the resistivity increase trend of a batch of copper wire at high temperatures is similar to the copper wire curve of a historical scrap event, then the twin evaluation will indicate a potential risk to the copper wire under high-temperature conditions.

[0054] Then, attention is assigned to each scrap risk sample within the conductor scrap event set based on the raw material performance twin evaluation set, resulting in a scrap risk attention map. Attention assignment is a calculation method used to determine the most noteworthy factor among multiple risk factors. Scrap risk samples refer to specific reasons leading to material rejection, such as excessively high resistivity, insufficient tensile strength, or uneven grain structure. The scrap risk attention map is a weighted distribution diagram indicating the proportion of contribution of different risks to the final scrap probability; for example, resistivity issues might have a weight of 0.5, mechanical strength issues 0.3, and structural defects 0.2.

[0055] Finally, based on the attention map of scrap risk, each scrap risk sample is fused and calculated to generate the first conductor scrap risk coefficient. This first conductor scrap risk coefficient is then added to the conductor scrap risk distribution. In other words, by comprehensively considering the weights and influences of each risk sample, a total risk value is calculated. The first conductor scrap risk coefficient is a quantitative indicator representing the probability of scrapping; for example, 0.72 represents a 72% risk. The conductor scrap risk distribution is the set of all conductor scrap risk coefficients, used to visually display the risk level of different raw materials. For example, if a batch of copper wire has good electrical properties but slightly weak mechanical properties, the fusion calculation might yield a risk coefficient of 0.6, while another batch of copper wire has significant deficiencies in both electrical and mechanical properties, potentially yielding a risk coefficient of 0.85.

[0056] Furthermore, this application also includes: collecting storage characteristic data of the insulating sheath raw material warehouse to construct an insulating sheath raw material storage grid; performing multi-degree-of-freedom performance testing on each insulating sheath raw material in the insulating sheath raw material warehouse to obtain multiple insulating sheath raw material data; performing extrusion production risk prediction on the multiple insulating sheath raw material data based on the extrusion production accident event set to obtain an extrusion production risk distribution; performing scrap risk prediction on the multiple insulating sheath raw material data to obtain an insulating sheath scrap risk distribution; and dynamically mapping the insulating sheath raw material storage grid based on the extrusion production risk distribution and the insulating sheath scrap risk distribution to generate the insulating sheath raw material evaluation grid.

[0057] Specifically, the storage characteristic data of the insulation sheath raw material warehouse is collected to construct an insulation sheath raw material storage grid. This involves acquiring various basic information about the insulation sheath raw materials in the warehouse, such as storage time, ambient temperature and humidity, batch origin, and inventory quantity, which constitute the storage characteristic data. This storage characteristic data allows for the establishment of a storage grid, uniformly recording the storage conditions and status of the raw materials, facilitating subsequent correlation with performance testing and risk analysis.

[0058] Multi-degree-of-freedom performance testing was conducted on each insulating sheath material in the raw material library, resulting in multiple data sets for each batch of insulating sheath materials. This means that the performance of each batch of insulating sheath materials was tested from different perspectives. The multi-degree-of-freedom tests covered multiple aspects, including electrical insulation strength, mechanical tensile strength, thermal stability, abrasion resistance, and flame retardancy. The test results will form multiple datasets, each corresponding to the performance of a batch of materials.

[0059] Extrusion production risk prediction is performed on multiple insulating sheath raw material data based on extrusion production accident event sets to obtain the extrusion production risk distribution. This involves analyzing potential risks to current raw materials during extrusion using historical extrusion accident cases. The extrusion production accident event set refers to various problems collected in actual production, such as uneven melting due to insufficient temperature resistance, air bubbles caused by excessive moisture content, or mold blockage due to poor flowability. By comparing the extrusion production accident event set with test data, the degree of risk of raw materials during extrusion can be predicted, ultimately forming a risk distribution. For example, if a batch of material is found to have a heat resistance of only 80 degrees Celsius, while the process requirement is 100 degrees Celsius, then the risk of an accident during extrusion will be marked as high.

[0060] By predicting the scrap risk based on data from multiple insulating sheath raw materials, a scrap risk distribution is obtained. This involves predicting whether raw materials may need to be scrapped due to insufficient performance or deterioration in storage conditions before production and use. The scrap risk prediction is based on test data; for example, if the insulation strength of a batch of materials is below 18 kV / mm or shows signs of oxidation during storage, it may be judged as having a high scrap risk. The scrap risk distribution categorizes the scrap probability of different batches of materials, helping to avoid losses before use.

[0061] Based on the risk distribution of extrusion production and the risk distribution of insulation sheath scrap, a dynamic mapping is performed on the raw material storage grid for insulation sheaths to generate an evaluation grid for the raw materials. This involves mapping the obtained extrusion and scrap risk results to the raw material information in the storage grid and updating the position of the raw materials in the evaluation system in real time. Dynamic mapping means that as the detection data or risk prediction results change, the storage grid also adjusts accordingly, ultimately forming a complete evaluation grid that can intuitively display the overall status of each batch of raw materials.

[0062] Furthermore, this application also includes: identifying accident types based on the extrusion production accident event set to obtain an extrusion accident type set; tracing accident paths based on the extrusion production accident event set to obtain an extrusion production accident path set; training an accident tree based on the extrusion production accident path set to obtain an extrusion production risk prediction model; subjecting the extrusion production accident path set to random perturbation to obtain an extrusion accident perturbation path set; reinforcing the extrusion production risk prediction model based on the extrusion accident perturbation path set to generate an extrusion production risk prediction channel; and inputting the multiple insulating sheath raw material data into the extrusion production risk prediction channel to obtain the extrusion production risk distribution.

[0063] Specifically, accident type identification is performed based on the extrusion production accident event set to obtain an extrusion accident type set. This involves classifying historically recorded extrusion production accidents to form a set of accident types. The extrusion production accident event set refers to a summary of data on various abnormal situations that occur during the extrusion of wires and cables, such as bubbles caused by excessive moisture in the raw material, unstable insulation layer thickness due to uneven temperature, and surface cracks due to equipment wear. Accident type identification involves categorizing complex accidents, such as into raw material problems, equipment problems, and process operation problems, ultimately resulting in an extrusion accident type set for subsequent analysis.

[0064] By tracing the accident paths of the extrusion production accident type set based on the event set of extrusion production accidents, an extrusion production accident path set is obtained. This involves tracking and analyzing the formation process of each accident type. An accident path is a causal chain from the source of the problem to the final accident result. For example, excessive moisture content in raw materials → water vapor evaporation during heating → bubble formation → bulging on the insulation layer surface → product defectiveness. By tracing these paths, an extrusion production accident path set can be formed, providing structured causal information for predictive models.

[0065] Accident tree training is performed on the set of accident paths in extrusion production to obtain an extrusion production risk prediction model. This involves constructing a tree-like logical relationship model using accident path information, known as an accident tree. Accident tree training optimizes and corrects the structure of the accident tree using existing accident path data, enabling more accurate risk prediction. For example, if the top-level event in an accident tree is a defective insulation layer, the lower levels might break it down into causes such as abnormal temperature, voltage fluctuations, and impure raw materials, each of which can be further subdivided into smaller components. Through training, an extrusion production risk prediction model can be obtained to calculate the probability of an accident occurring under certain input conditions.

[0066] By randomly perturbing the existing set of extrusion production accident paths, a new set of perturbed extrusion accident paths is obtained. This involves introducing random variables into the existing accident paths to simulate new situations that may arise in reality. The random perturbation process may include adjusting the weights of causal relationships in the paths or adding uncertain variables. For example, adding a perturbation factor of "ambient humidity fluctuation" to the path related to raw material moisture content can create a new set of accident perturbed paths, preventing the model from relying too heavily on existing cases and improving its generalization ability.

[0067] The extrusion production risk prediction model is reinforced by training a set of extrusion accident disturbance paths to generate an extrusion production risk prediction channel. This involves re-inputting the model with disturbed accident paths and continuously adjusting parameters to enable the model to make accurate judgments even in more complex situations. The result of this reinforcement training is a more robust extrusion production risk prediction channel that can not only handle existing accident types but also make reasonable predictions of potential new accidents that have not yet occurred.

[0068] Multiple raw material data for insulating sheaths are input into the extrusion production risk prediction channel to obtain the extrusion production risk distribution. This involves inputting the previously detected multi-dimensional raw material performance data into a pre-trained prediction channel to calculate the potential risk level during the extrusion production process. The extrusion production risk distribution is an output that demonstrates the probability of accidents occurring in different batches of raw materials during production.

[0069] Furthermore, this application also includes: constructing a shielding filler raw material storage grid based on the storage dataset of the shielding filler raw material library; predicting the expected performance of the shielding filler raw materials based on the production needs of the wires and cables, and constructing a raw material performance expectation space; performing performance testing based on the shielding filler raw material library to obtain data for each shielding filler raw material; evaluating the deviation risk of each shielding filler raw material data based on the raw material performance expectation space to obtain a raw material performance risk distribution; predicting the scrap risk based on each shielding filler raw material data to obtain a shielding filler raw material scrap risk distribution; and dynamically mapping the shielding filler raw material storage grid based on the raw material performance risk distribution and the shielding filler raw material scrap risk distribution to generate the shielding filler raw material evaluation grid.

[0070] Specifically, based on the storage dataset of the shielding filler material warehouse, a storage grid for shielding filler materials is constructed. This involves collecting relevant storage information from the warehouse, including inventory quantity, batch origin, storage conditions, and material status, and then generating a computable and analyzable storage grid through data structuring. The shielding filler material warehouse is a dedicated storage area for shielding layers and filler materials used in cables, such as aluminum foil shielding tape, copper wire braided layers, and flame-retardant fillers. The storage grid is a multi-dimensional data organization form that allows materials to be distributed in an orderly manner according to their properties within the grid, facilitating analysis and management.

[0071] Based on the production needs of wires and cables, the expected performance of shielding filler materials is predicted, and the expected performance space of the materials is constructed. That is, based on the production goals of different types of wires and cables, the ideal performance indicators required by the shielding filler materials are calculated.

[0072] Performance testing is conducted using a shielding filler material library to obtain data for each material. This involves testing each batch of shielding or filler materials in the library and collecting their actual performance indicators. Performance testing may include multiple aspects such as conductivity, mechanical strength, thermal stability, corrosion resistance, and flame retardancy. For example, a batch of copper wire shielding mesh might be tested and found to have a weaving density of 95% and a conductivity of 58 MSiemens per meter; a batch of flame-retardant filler might be tested and found to have an oxygen index of 30% and a thermal decomposition point of 350 degrees Celsius. The test results are ultimately compiled into a shielding filler material dataset.

[0073] Based on the expected performance space of the raw materials, a deviation risk assessment is performed on the data of each shielding filling material to obtain the raw material performance risk distribution. This involves comparing the actual performance obtained from testing with the ideal expected space, calculating the magnitude of the deviation, and thus assessing the risk level. Deviation risk assessment is a crucial step in determining whether a material meets production requirements. For example, if the thickness deviation of a batch of aluminum foil shielding tape exceeds 5%, it may lead to a decrease in shielding effectiveness, thereby increasing the risk level. The raw material performance risk distribution involves classifying and statistically distributing the risks of all batches of raw materials. For instance, 60 batches might be in the low-risk zone, 30 batches in the medium-risk zone, and 10 batches in the high-risk zone.

[0074] Based on the data of each shielding filling material, a scrap risk prediction is made to obtain the scrap risk distribution of the shielding filling material. That is, the possible scrap probability is estimated based on the performance data and service life of the material. The scrap risk prediction not only considers the current test data, but also takes into account the aging characteristics of the material, environmental adaptability, and historical decommissioning cases. For example, a batch of filling material will significantly absorb moisture within 2 years in a high humidity environment, thus affecting the insulation stability, and the scrap risk of the material will be marked as high; another batch of copper wire shielding material, if the anti-oxidation treatment is well done, may have a lower scrap risk. The final scrap risk distribution can intuitively reflect the materials that need to be used as soon as possible and the materials that are still safe.

[0075] The shielding filler raw material storage grid is dynamically mapped based on the performance risk distribution and the scrap risk distribution of the raw materials, generating an evaluation grid for the shielding filler raw materials. This involves comprehensively mapping both performance risk and scrap risk onto the storage grid, dynamically adjusting the position and level of each raw material within the grid. The resulting evaluation grid clearly shows raw materials that meet performance requirements and have low risk, which can be prioritized; raw materials that, while still meeting performance standards, have a high scrap risk and need to be used quickly; and raw materials already in the high-risk zone, which are advised to be discontinued from production.

[0076] Furthermore, this application also includes: the first conductor feature vector set includes a first conductor electrical feature vector, a first conductor mechanical feature vector, and a first conductor structural feature vector.

[0077] Specifically, the first conductor feature vector set includes parameters related to electrical energy transmission, such as the first conductor electrical feature vector, the first conductor mechanical feature vector, and the first conductor structural feature vector. The first conductor mechanical feature vector represents the conversion of the material's mechanical properties into a data set. It includes indicators such as tensile strength, elongation, and bending performance, reflecting the stability and durability of the wire and cable raw materials during actual processing and use. The first conductor structural feature vector refers to the numerical storage of the material's microscopic and macroscopic structural characteristics.

[0078] Furthermore, this application also includes: the adaptation weight conditions include electrical feature adaptation weight, mechanical feature adaptation weight and structural feature adaptation weight.

[0079] Specifically, the fit weighting conditions include electrical characteristic fit weighting, mechanical characteristic fit weighting, and structural characteristic fit weighting. Electrical characteristic fit weighting refers to the impact on evaluating electrical performance; for example, conductivity and resistivity are relatively important for high-voltage transmission cables. Mechanical characteristic fit weighting reflects the importance of properties such as tensile strength, elongation, and flexural life to the final fit. Structural characteristic fit weighting refers to the importance of parameters such as crystallinity, density uniformity, and surface defect rate. For example, in the production of high-reliability environmental cables, structural stability directly determines lifespan and is used to balance the dependence on electrical and mechanical characteristics.

[0080] In summary, the wire and cable raw material screening method combined with data analysis provided in this application has the following technical effects: by achieving the technical goal of multi-dimensional, dynamic and intelligent comprehensive evaluation and automatic grading screening of wire and cable raw materials, it can improve the efficiency of raw material use, reduce the risk of scrap, optimize material matching relationships, ensure production safety, and improve the overall performance and economic benefits of cable products.

[0081] Example 2: Based on the same inventive concept as the wire and cable raw material screening method combining data analysis in the foregoing examples, this application also provides a wire and cable raw material screening system combining data analysis. Please refer to the appendix. Figure 2 The system includes: an instruction sending module 1, used to receive raw material screening instructions sent from the wire and cable production end to the wire and cable raw material library, the wire and cable raw material library including conductor raw material library, insulation sheath raw material library and shielding filler raw material library, the raw material screening instructions including wire and cable production requirements; a conductor raw material evaluation grid construction module 2, used to perform fit analysis on the conductor raw material library based on the wire and cable production requirements and according to the conductor fit evaluation model to construct a conductor raw material evaluation grid; an insulation sheath raw material evaluation grid construction module 3, used to perform extrusion production risk analysis on the insulation sheath raw material library based on the wire and cable production requirements and according to the extrusion production accident event set to construct an insulation sheath raw material evaluation grid; a shielding filler raw material evaluation grid establishment module 4, used to perform performance risk analysis on the shielding filler raw material library based on the wire and cable production requirements to establish a shielding filler raw material evaluation grid; a multi-dimensional raw material evaluation grid generation module 5, used to integrate the conductor raw material evaluation grid, the insulation sheath raw material evaluation grid and the shielding filler raw material evaluation grid to generate a multi-dimensional raw material evaluation grid; and an automatic grading and screening module 6, used to automatically grade and screen the wire and cable raw material library according to the multi-dimensional raw material evaluation grid.

[0082] Furthermore, the wire and cable raw material screening system combined with data analysis is also used for: collecting storage characteristic information of the conductor raw material warehouse and constructing a conductor raw material storage grid; performing multi-dimensional performance testing on each conductor raw material in the conductor raw material warehouse to obtain a test sequence for each conductor raw material; evaluating the suitability of conductor raw materials based on the test sequences of each conductor raw material, according to the wire and cable production requirements and the conductor suitability evaluation model, to obtain multiple conductor suitability evaluation sequences; predicting the scrap risk of each conductor raw material based on the test sequences of each conductor raw material to obtain a conductor scrap risk distribution; and dynamically mapping the conductor raw material storage grid based on the multiple conductor suitability evaluation sequences and the conductor scrap risk distribution to generate the conductor raw material evaluation grid.

[0083] Furthermore, the wire and cable raw material screening system combined with data analysis is also used for: traversing the detection sequences of each conductor raw material and extracting a first conductor raw material detection sequence; constructing a first conductor feature vector set based on the first conductor raw material detection sequence; activating the conductor fit evaluation model, which includes multiple conductor fit evaluation indicators, including electrical feature fit, mechanical feature fit, and structural feature fit; inputting the wire and cable production requirements and the first conductor feature vector set into the conductor fit evaluation model to obtain a first fit evaluation result; performing a weighted calculation on the first fit evaluation result according to the fit weight conditions of the multiple conductor fit evaluation indicators to obtain a first comprehensive conductor fit; and encapsulating the first fit evaluation result and the first comprehensive conductor fit into a first conductor fit evaluation sequence.

[0084] Furthermore, the wire and cable raw material screening system combined with data analysis is also used for: retrieving scrap events based on the first conductor raw material detection sequence to obtain a conductor scrap event set; performing raw material performance twin evaluation on the conductor scrap event set based on the first conductor raw material detection sequence to obtain a raw material performance twin evaluation set; allocating attention to each scrap risk sample in the conductor scrap event set based on the raw material performance twin evaluation set to obtain a scrap risk attention map; performing fusion calculation on each scrap risk sample based on the scrap risk attention map to generate a first conductor scrap risk coefficient, and adding the first conductor scrap risk coefficient to the conductor scrap risk distribution.

[0085] Furthermore, the wire and cable raw material screening system combined with data analysis is also used for: collecting storage characteristic data of the insulation sheath raw material warehouse and constructing an insulation sheath raw material storage grid; performing multi-degree-of-freedom performance testing on each insulation sheath raw material in the insulation sheath raw material warehouse to obtain multiple insulation sheath raw material data; predicting extrusion production risks based on the extrusion production accident event set to obtain an extrusion production risk distribution; predicting scrap risks based on the multiple insulation sheath raw material data to obtain an insulation sheath scrap risk distribution; and dynamically mapping the insulation sheath raw material storage grid based on the extrusion production risk distribution and the insulation sheath scrap risk distribution to generate the insulation sheath raw material evaluation grid.

[0086] Furthermore, the wire and cable raw material screening system combined with data analysis is also used for: identifying accident types based on the extrusion production accident event set to obtain an extrusion accident type set; tracing the accident paths of the extrusion accident type set based on the extrusion production accident event set to obtain an extrusion production accident path set; training an accident tree based on the extrusion production accident path set to obtain an extrusion production risk prediction model; subjecting the extrusion production accident path set to random perturbation to obtain an extrusion accident perturbation path set; reinforcing the extrusion production risk prediction model based on the extrusion accident perturbation path set to generate an extrusion production risk prediction channel; and inputting the multiple insulation sheath raw material data into the extrusion production risk prediction channel to obtain the extrusion production risk distribution.

[0087] Furthermore, the wire and cable raw material screening system combined with data analysis is also used for: constructing a shielding filler raw material storage grid based on the storage dataset of the shielding filler raw material library; predicting the expected performance of shielding filler raw materials based on the production needs of the wire and cable, and constructing a raw material performance expectation space; performing performance testing based on the shielding filler raw material library to obtain data for each shielding filler raw material; evaluating the deviation risk of each shielding filler raw material data based on the raw material performance expectation space to obtain a raw material performance risk distribution; predicting the scrap risk based on each shielding filler raw material data to obtain a shielding filler raw material scrap risk distribution; and dynamically mapping the shielding filler raw material storage grid based on the raw material performance risk distribution and the shielding filler raw material scrap risk distribution to generate the shielding filler raw material evaluation grid.

[0088] Furthermore, the wire and cable raw material screening system that combines data analysis is also used for: the first conductor feature vector set includes the first conductor electrical feature vector, the first conductor mechanical feature vector, and the first conductor structural feature vector.

[0089] Furthermore, the wire and cable raw material screening system that combines data analysis is also used for: the fit weight conditions include electrical characteristic fit weight, mechanical characteristic fit weight and structural characteristic fit weight.

[0090] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The wire and cable raw material screening method and specific examples combined with data analysis in the foregoing embodiment one are also applicable to the wire and cable raw material screening system combined with data analysis in this embodiment. Through the foregoing detailed description of the wire and cable raw material screening method combined with data analysis, those skilled in the art can clearly understand the wire and cable raw material screening system combined with data analysis in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0091] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0092] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for screening raw materials for wires and cables based on data analysis, characterized in that: include: Receive raw material screening instructions sent from the wire and cable production end to the wire and cable raw material warehouse. The wire and cable raw material warehouse includes a conductor raw material warehouse, an insulation sheath raw material warehouse, and a shielding filling raw material warehouse. The raw material screening instructions include the wire and cable production requirements. Based on the aforementioned wire and cable production requirements, the conductor raw material library is analyzed for compatibility using a conductor compatibility evaluation model, and a conductor raw material evaluation grid is constructed. Based on the aforementioned wire and cable production requirements, an extrusion production risk analysis is performed on the insulation sheath raw material library according to the extrusion production accident event set, and an evaluation grid for insulation sheath raw materials is constructed. Based on the wire and cable production requirements, a performance risk analysis was conducted on the shielding filler raw material library, and an evaluation grid for shielding filler raw materials was established. The conductor material evaluation grid, the insulation sheath material evaluation grid, and the shielding fill material evaluation grid are integrated to generate a multi-dimensional material evaluation grid. The wire and cable raw material library is automatically graded and screened based on the multidimensional raw material evaluation grid.

2. The method for screening wire and cable raw materials by combining data analysis as described in claim 1, characterized in that, Based on the aforementioned wire and cable production requirements, the conductor material library is analyzed for compatibility using a conductor compatibility evaluation model, and a conductor material evaluation grid is constructed, including: Collect the storage characteristic information of the conductor raw material warehouse and construct a conductor raw material storage grid; Multidimensional performance testing was performed on each conductor material in the conductor material library to obtain the test sequence for each conductor material. Based on the detection sequences of each conductor material, the conductor material compatibility is evaluated according to the wire and cable production requirements and the conductor compatibility evaluation model to obtain multiple conductor compatibility evaluation sequences. Based on the detection sequence of each conductor material, the scrap risk of each conductor material is predicted to obtain the conductor scrap risk distribution; The conductor raw material storage grid is dynamically mapped based on the multiple conductor fit evaluation sequences and the conductor scrap risk distribution to generate the conductor raw material evaluation grid.

3. The method for screening wire and cable raw materials by combining data analysis as described in claim 2, characterized in that, Based on the aforementioned conductor material detection sequences, conductor material compatibility is evaluated according to the wire and cable production requirements and the conductor compatibility evaluation model, resulting in multiple conductor compatibility evaluation sequences, including: Traverse all the conductor material detection sequences and extract the first conductor material detection sequence; Based on the first conductor raw material detection sequence, a first conductor feature vector set is constructed; Activate the conductor fit evaluation model, which includes multiple conductor fit evaluation indicators, including electrical characteristic fit, mechanical characteristic fit, and structural characteristic fit. The wire and cable production requirements and the first conductor feature vector set are input into the conductor fit evaluation model to obtain the first fit evaluation result; The first result of the conductor fit evaluation is weighted and calculated according to the fit weight conditions of the multiple indicators of the conductor fit evaluation to obtain the first conductor comprehensive fit. The first result of the fit evaluation and the first conductor comprehensive fit are encapsulated into a first conductor fit evaluation sequence.

4. The method for screening wire and cable raw materials by combining data analysis as described in claim 2, characterized in that, Based on the detection sequences of each conductor material, a scrap risk prediction is performed for each conductor material to obtain a conductor scrap risk distribution, including: Based on the first conductor raw material detection sequence, scrap events are retrieved to obtain a conductor scrap event set; Based on the first conductor raw material detection sequence, a raw material performance twin evaluation is performed on the conductor scrap event set to obtain a raw material performance twin evaluation set; Based on the raw material performance twin evaluation set, attention is allocated to each scrap risk sample in the conductor scrap event set to obtain a scrap risk attention map; The scrap risk samples are fused and calculated based on the scrap risk attention map to generate a first conductor scrap risk coefficient, and the first conductor scrap risk coefficient is added to the conductor scrap risk distribution.

5. The method for screening wire and cable raw materials by combining data analysis as described in claim 1, characterized in that, Based on the aforementioned wire and cable production requirements, an extrusion production risk analysis is performed on the insulation sheath raw material library according to the extrusion production accident event set, and an evaluation grid for insulation sheath raw materials is constructed, including: Collect the storage characteristic data of the insulation sheath raw material warehouse and construct an insulation sheath raw material storage grid; Multi-degree-of-freedom performance tests were performed on each insulating sheath material in the insulating sheath material library to obtain multiple insulating sheath material data. Based on the extrusion production accident event set, extrusion production risk prediction is performed on the multiple insulating sheath raw material data to obtain the extrusion production risk distribution; Based on the data of the multiple insulating sheath raw materials, the scrap risk is predicted to obtain the scrap risk distribution of the insulating sheaths; The raw material storage grid for insulating sheaths is dynamically mapped based on the extrusion production risk distribution and the insulating sheath scrap risk distribution to generate the raw material evaluation grid for insulating sheaths.

6. The method for screening wire and cable raw materials by combining data analysis as described in claim 5, characterized in that, Based on the extrusion production accident event set, extrusion production risk prediction is performed on the multiple insulating sheath raw material data to obtain the extrusion production risk distribution, including: Based on the set of extrusion production accident events, accident types are identified to obtain a set of extrusion accident types. Based on the set of extrusion production accident events, the set of extrusion accident types is traced to obtain a set of extrusion production accident paths. Based on the set of extrusion production accident paths, an accident tree is trained to obtain an extrusion production risk prediction model. Random perturbation is performed on the extrusion production accident path set to obtain the extrusion accident perturbation path set; The extrusion production risk prediction model is reinforced and trained based on the extrusion accident disturbance path set to generate an extrusion production risk prediction channel. The data of the multiple insulating sheath raw materials are input into the extrusion production risk prediction channel to obtain the extrusion production risk distribution.

7. The method for screening wire and cable raw materials by combining data analysis as described in claim 1, characterized in that, Based on the aforementioned wire and cable production requirements, a performance risk analysis was conducted on the shielding filler material library, and an evaluation grid for the shielding filler materials was established, including: Based on the storage dataset of the shielded filling raw material warehouse, a shielded filling raw material storage grid is constructed; Based on the aforementioned wire and cable production requirements, the expected performance of shielding filling materials is predicted, and a material performance expectation space is constructed. Performance testing was conducted based on the aforementioned shielding filler material library to obtain data for each shielding filler material; Based on the expected performance space of the raw materials, the deviation risk assessment of the data of each shielding filling raw material is performed to obtain the risk distribution of raw material performance. Based on the data of each shielding filling material, the scrap risk is predicted to obtain the scrap risk distribution of the shielding filling material. The shielding filler material storage grid is dynamically mapped based on the raw material performance risk distribution and the shielding filler material scrap risk distribution to generate the shielding filler material evaluation grid.

8. The method for screening wire and cable raw materials by combining data analysis as described in claim 3, characterized in that, The first conductor feature vector set includes the first conductor electrical feature vector, the first conductor mechanical feature vector, and the first conductor structural feature vector.

9. The method for screening wire and cable raw materials by combining data analysis as described in claim 3, characterized in that, The adaptation weight conditions include electrical feature adaptation weight, mechanical feature adaptation weight, and structural feature adaptation weight.

10. A wire and cable raw material screening system combining data analysis, characterized in that, The steps for implementing the wire and cable raw material screening method combining data analysis as described in any one of claims 1 to 9 include: The instruction sending module is used to receive raw material screening instructions sent from the wire and cable production end to the wire and cable raw material library. The wire and cable raw material library includes a conductor raw material library, an insulation sheath raw material library, and a shielding filling raw material library. The raw material screening instructions include wire and cable production requirements. The conductor raw material evaluation grid construction module is used to analyze the suitability of the conductor raw material library based on the wire and cable production requirements and the conductor suitability evaluation model, and construct the conductor raw material evaluation grid. The insulation sheath raw material evaluation grid construction module is used to analyze the extrusion production risks of the insulation sheath raw material library based on the production needs of the wire and cable and the extrusion production accident event set, and to construct the insulation sheath raw material evaluation grid. The shielding filler material evaluation grid establishment module is used to perform performance risk analysis on the shielding filler material library according to the wire and cable production requirements, and establish a shielding filler material evaluation grid. A multi-dimensional raw material evaluation grid generation module is used to integrate the conductor raw material evaluation grid, the insulation sheath raw material evaluation grid, and the shielding filler raw material evaluation grid to generate a multi-dimensional raw material evaluation grid. An automatic grading and screening module is used to automatically grade and screen the wire and cable raw material library according to the multi-dimensional raw material evaluation grid.

Images