A method and system for optimizing process parameters of cable braiding layer

Abstract

The present invention relates to the technical field of cable manufacturing process, and discloses a process parameter optimization method and system for a cable braided layer, the method comprising acquiring material performance data and process parameters; modeling based on a support vector machine according to the material performance data and the process parameters to obtain a mapping relationship model; analyzing the relationship between a braiding angle parameter and surface size fluctuation according to the mapping relationship model to obtain an ideal braiding angle parameter; optimizing a braiding density parameter according to the ideal braiding angle parameter to obtain an ideal braiding density parameter; performing a stability analysis of a braiding tension parameter according to the ideal braiding density parameter and the mapping relationship model to obtain an ideal braiding tension parameter and an ideal process parameter; and iteratively analyzing the process parameter collaborative optimization algorithm according to the ideal process parameter to obtain the final process parameter. The present method can realize the control of the consistency of the surface size of the braided layer by optimizing the braiding process parameters.

Description

Technical Field

[0001] The present invention relates to the technical field of cable manufacturing technology, and in particular to a method and system for optimizing process parameters of a cable braided layer. Background Art

[0002] At present, in the field of cable manufacturing, precise control of the surface dimensions of the braided layer is a key technical bottleneck that affects the reliability of cable products. As power transmission equipment develops towards large capacity and high voltage, the requirements for matching the mechanical strength and electrical performance of the cable braided layer are becoming more and more stringent. Surface dimension fluctuations exceeding ±0.5mm can cause local electric field distortion and induce insulation breakdown risks. However, factors such as differences in the physical properties of braided materials, the coupling of multiple process parameters, and the hysteresis of the dynamic response of equipment have caused the surface dimension qualification rate under the traditional production model to be lower than 75% for a long time, which seriously restricts the mass production of high-end cable products.

[0003] In one prior art, the cable braiding layer surface dimension detection method mainly adopts the mode of offline sampling detection combined with manual parameter adjustment, relying on the operator to visually inspect the appearance of the braiding layer and use simple tools to sample and measure the dimensions of key points. When adjusting the process parameters, the braiding angle or tension value is modified in a single dimension based on experience, lacking systematic parameter correlation analysis; at the same time, the existing method uses a preset process parameter template for production, without considering the influence of different material properties on parameter sensitivity, resulting in a significant increase in surface dimension fluctuations when the material is replaced; in addition, the prior art does not establish a dynamic association between the mechanical characteristics of the equipment and the process parameters, resulting in a large deviation in the parameter optimization results when executed on the equipment side. For example, the traditional control algorithm does not integrate the equipment status data, and the control error is significantly enlarged after long-term operation. It can be seen that in the prior art, due to the isolation of parameter adjustment, lack of dynamic adaptability and insufficient control accuracy, it is difficult to control the consistency of the surface dimension of the braided layer by optimizing the braiding process parameters. Summary of the invention

[0004] The present invention provides a method and system for optimizing the process parameters of a cable braided layer, so as to control the consistency of the surface dimensions of the braided layer by optimizing the braiding process parameters.

[0005] In a first aspect, in order to solve the above technical problems, the present invention provides a method for optimizing process parameters of a cable braided layer, comprising:

[0006] Obtain material performance data and process parameters of the cable braiding layer;

[0007] According to the material performance data and the process parameters, modeling is performed based on a support vector machine to obtain a mapping relationship model between material performance and process parameters;

[0008] According to the mapping relationship model and the process parameters, the relationship between the braiding angle parameter and the surface size fluctuation is analyzed, and the parameters are optimized to obtain the ideal braiding angle parameter;

[0009] According to the ideal braiding angle parameter and the mapping relationship model, the braiding density parameter is optimized in combination with the preset dimensional accuracy requirement to obtain the ideal braiding density parameter;

[0010] According to the ideal braiding angle parameter, the ideal braiding density parameter and the mapping relationship model, a stability analysis of the braiding tension parameter is performed, the tension control scheme is optimized, and the ideal braiding tension parameter and the ideal process parameter are obtained;

[0011] According to the ideal process parameters, a process parameter collaborative optimization algorithm is used for iterative analysis to obtain final process parameters.

[0012] In an optional embodiment, the obtaining of material performance data of the cable braided layer and process parameters of the cable braided layer includes:

[0013] Obtain the physical property data of the braided material during the production process of the cable braid layer and the mechanical property data of the braided material during the production process of the cable braid layer;

[0014] Wherein, the material performance data of the cable braided layer includes the physical performance data and the mechanical performance data;

[0015] Extracting preset initial braiding angle parameters, initial braiding density parameters and initial braiding tension parameters;

[0016] Performing standardization processing according to the material performance data, the initial braiding angle parameter, the initial braiding density parameter and the initial braiding tension parameter to obtain the process parameters of the cable braiding layer;

[0017] The process parameters include a braiding angle parameter, a braiding density parameter and a braiding tension parameter.

[0018] In an optional implementation, the modeling based on the material property data and the process parameters is performed based on a support vector machine to obtain a mapping relationship model between material properties and process parameters, including:

[0019] According to the material performance data and the process parameters, a model is constructed using a multivariate linear regression method to obtain an initial mapping relationship model between the material performance and the process parameters;

[0020] According to the initial mapping relationship model, a fitting degree calculation is performed to obtain the fitting degree of the initial mapping relationship model;

[0021] According to the fitting degree and the initial mapping relationship model, a support vector machine kernel function is used to transform and reconstruct the feature space to obtain a high-dimensional mapping relationship model;

[0022] According to the high-dimensional mapping relationship model, a cross-validation method is used to optimize the penalty factor and kernel function parameters to obtain a mapping relationship model between material properties and process parameters.

[0023] In an optional implementation, analyzing the relationship between the braiding angle parameter and the surface size fluctuation according to the mapping relationship model and the process parameters, optimizing the parameters, and obtaining the ideal braiding angle parameter includes:

[0024] According to the mapping relationship model and the process parameters, the dynamic response relationship between the change of the braiding angle parameter and the surface size fluctuation is analyzed to obtain the sensitivity coefficient of the braiding angle parameter to the surface size;

[0025] According to the sensitivity coefficient and the mapping relationship model, analyzing the association weight matrix between the braiding angle parameter and the material performance data to obtain the angle adjustment constraint condition;

[0026] According to the angle adjustment constraint conditions, a gradient descent method is used to calculate the loss function of the surface size fluctuation threshold and the material performance matching degree to obtain the optimal braiding angle parameter;

[0027] According to the optimal braiding angle parameter, a dynamic response curve is calculated to obtain a fluctuation attenuation rate;

[0028] When the fluctuation attenuation rate is within the preset standard range, the optimal braiding angle parameter is determined to be the ideal braiding angle parameter. When the fluctuation attenuation rate is outside the preset standard range, the optimal braiding angle parameter is back-propagated and optimized to obtain the ideal braiding angle parameter.

[0029] In an optional embodiment, the optimization of the weaving density parameters is performed according to the ideal weaving angle parameters and the mapping relationship model in combination with the preset dimensional accuracy requirements to obtain the ideal weaving density parameters, including:

[0030] According to the mapping relationship model, a nonlinear relationship analysis is performed between the weaving density parameter and the surface size fluctuation to obtain a weaving density nonlinear relationship model;

[0031] According to the nonlinear relationship model of braiding density and the ideal braiding angle parameter, a function analysis is performed in combination with a preset dimensional accuracy requirement to obtain a braiding density parameter optimization function;

[0032] According to the weaving density parameter optimization function, a genetic algorithm is used to perform iterative calculation to obtain a weaving density parameter solution set that satisfies the surface size fluctuation constraint;

[0033] According to the weaving density parameter solution set and the weaving density nonlinear relationship model, the convergence of the surface size fluctuation is analyzed, and the solution with the best convergence in the weaving density parameter solution set is determined as the ideal weaving density parameter.

[0034] In an optional embodiment, the stability analysis of the braiding tension parameter is performed according to the ideal braiding angle parameter, the ideal braiding density parameter and the mapping relationship model, the tension control scheme is optimized, and the ideal braiding tension parameter is obtained, including:

[0035] According to the mapping relationship model, a dynamic correlation analysis between the weaving tension parameter and the mechanical structure of the equipment is performed to obtain the dynamic response characteristics of the transmission system;

[0036] According to the dynamic response characteristics of the transmission system, a timing anomaly detection algorithm is used to perform a weaving tension parameter fluctuation analysis to obtain an abnormal weaving tension fluctuation range;

[0037] According to the abnormal fluctuation range of the braiding tension, a parameter optimization objective function of the tension control system is constructed to obtain a braiding tension parameter adjustment strategy;

[0038] According to the braiding tension parameter adjustment strategy, a tension optimization algorithm is used to perform robustness analysis to obtain a robustness evaluation result;

[0039] According to the robustness evaluation result, the braiding tension parameter adjustment strategy, the ideal braiding angle parameter and the ideal braiding density parameter, the braiding tension parameter is comprehensively optimized to obtain the ideal braiding tension parameter;

[0040] The ideal process parameters include the ideal braiding angle parameter, the ideal braiding density parameter and the ideal braiding tension parameter.

[0041] In an optional implementation, the process parameters are iteratively analyzed using a process parameter collaborative optimization algorithm to obtain final process parameters according to the ideal process parameters, including:

[0042] According to the ideal process parameters, multi-dimensional parameter optimization is performed to construct a process parameter collaborative optimization space including a weaving angle parameter, a weaving density parameter and a weaving tension parameter;

[0043] According to the process parameter collaborative optimization space, a preset mechanical rigidity threshold and a preset transmission efficiency threshold are combined for collaborative constraint to obtain a first process parameter combination;

[0044] Initializing a collaborative optimization algorithm for process parameters according to the first process parameter combination;

[0045] According to the process parameter collaborative optimization algorithm, perform process parameter collaborative optimization iteration to obtain a second process parameter combination, and record the number of iterations;

[0046] Determine whether the second process parameter combination is better than the first process parameter combination, if so, use the second process parameter combination as the first process parameter combination; if not, discard the second process parameter combination;

[0047] Continue to the next iteration, when the number of iterations is greater than or equal to the preset number of iterations, output the current first process parameter combination as the final process parameter.

[0048] In a second aspect, the present invention provides a process parameter optimization system for a cable braided layer, comprising:

[0049] A data acquisition module, used to acquire material performance data and process parameters of the cable braiding layer;

[0050] A mapping modeling module, used to perform modeling based on a support vector machine according to the material performance data and the process parameters to obtain a mapping relationship model between material performance and process parameters;

[0051] An angle optimization module, used to analyze the relationship between the braiding angle parameter and the surface size fluctuation according to the mapping relationship model and the process parameters, perform parameter optimization, and obtain the ideal braiding angle parameter;

[0052] A density optimization module, used to optimize the weaving density parameters according to the ideal weaving angle parameters and the mapping relationship model in combination with preset dimensional accuracy requirements to obtain the ideal weaving density parameters;

[0053] A tension optimization module, used to perform stability analysis of the weaving tension parameters according to the ideal weaving angle parameters, the ideal weaving density parameters and the mapping relationship model, optimize the tension control scheme, and obtain the ideal weaving tension parameters and ideal process parameters;

[0054] The result output module is used to iteratively analyze the ideal process parameters using a process parameter collaborative optimization algorithm to obtain final process parameters.

[0055] In a third aspect, the present invention also provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the process parameter optimization method of the cable braiding layer described in any one of the above is implemented.

[0056] In a fourth aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned process parameter optimization methods for the cable braiding layer.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] The present invention discloses a method for optimizing process parameters of a cable braided layer, comprising obtaining material performance data and process parameters of the cable braided layer; modeling based on a support vector machine according to the material performance data and the process parameters to obtain a mapping relationship model between material performance and process parameters; analyzing the relationship between braiding angle parameters and surface size fluctuations according to the mapping relationship model and the process parameters, optimizing parameters to obtain ideal braiding angle parameters; optimizing braiding density parameters according to the ideal braiding angle parameters and the mapping relationship model in combination with preset dimensional accuracy requirements to obtain ideal braiding density parameters; performing stability analysis of braiding tension parameters according to the ideal braiding angle parameters, the ideal braiding density parameters and the mapping relationship model, optimizing the tension control scheme to obtain ideal braiding tension parameters and ideal process parameters; and iteratively analyzing the process parameter collaborative optimization algorithm according to the ideal process parameters to obtain final process parameters.

[0059] The present invention realizes the collaborative optimization control of weaving process parameters through the following technical steps: first, the material performance data of the cable braiding layer and the process parameters of the cable braiding layer are obtained, and then a mapping relationship model between the material performance data and the process parameters is established, breaking through the limitations of traditional single parameter adjustment, and incorporating the coupling effects of the braiding angle parameters, the braiding density parameters, and the braiding tension parameters into a unified analysis framework, so as to solve the problem of local optimal failure caused by isolated parameter optimization; then, the mapping relationship model between material performance and process parameters constructed based on support vector machine reveals the multi-parameter coupling law, and according to the model, the dynamic response relationship between the braiding angle parameters and the surface size fluctuations is analyzed and the gradient descent method is used to optimize to the ideal braiding angle parameters, and then the ideal braiding density parameters are iteratively calculated by genetic algorithm in combination with the preset dimensional accuracy requirements, and the evidence theory is further integrated to perform stability analysis of the tension parameters on the ideal braiding angle parameters and the ideal braiding density parameters and optimize the tension control scheme, and finally the process parameter collaborative optimization algorithm is used to perform global iterative verification and dynamic weight adjustment on multiple parameters to generate the final process parameters that meet the dual constraints of surface size accuracy and equipment reliability. Through the systematic connection of the above steps, the present invention breaks through the limitations of traditional single parameter static adjustment and constructs a dynamic collaborative optimization mechanism of material properties, process parameters and equipment status, thereby achieving the consistency of the surface size of the braided layer by optimizing the braiding process parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a schematic flow chart of a method for optimizing process parameters of a cable braided layer provided by a first embodiment of the present invention;

[0061] Figure 2 It is a schematic diagram of the structure of a process parameter optimization system for a cable braided layer provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0062] 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.

[0063] Reference Figure 1 The first embodiment of the present invention provides a method for optimizing process parameters of a cable braided layer, comprising the following steps:

[0064] S11, obtaining material performance data of the cable braid layer and process parameters of the cable braid layer;

[0065] S12, performing modeling based on a support vector machine according to the material property data and the process parameters to obtain a mapping relationship model between material properties and process parameters;

[0066] S13, analyzing the relationship between the braiding angle parameter and the surface size fluctuation according to the mapping relationship model and the process parameters, performing parameter optimization, and obtaining an ideal braiding angle parameter;

[0067] S14, optimizing the weaving density parameters according to the ideal weaving angle parameters and the mapping relationship model in combination with the preset dimensional accuracy requirements to obtain the ideal weaving density parameters;

[0068] S15, performing stability analysis of braiding tension parameters according to the ideal braiding angle parameters, the ideal braiding density parameters and the mapping relationship model, optimizing the tension control scheme, and obtaining ideal braiding tension parameters and ideal process parameters;

[0069] S16, according to the ideal process parameters, adopt the process parameter collaborative optimization algorithm to iteratively analyze and obtain the final process parameters.

[0070] In step S11, it is necessary to obtain material performance data of the cable braiding layer and process parameters of the cable braiding layer.

[0071] In one implementation, obtaining material performance data of the cable braided layer and process parameters of the cable braided layer includes:

[0072] Obtain physical property data of the braided material during the production process of the cable braided layer and mechanical property data of the braided material during the production process of the cable braided layer; wherein the material property data of the cable braided layer includes the physical property data and the mechanical property data; extract the preset initial braiding angle parameter, initial braiding density parameter and initial braiding tension parameter; perform standardization processing according to the material property data, the initial braiding angle parameter, the initial braiding density parameter and the initial braiding tension parameter to obtain the process parameters of the cable braided layer; the process parameters include braiding angle parameter, braiding density parameter and braiding tension parameter.

[0073] In step S12, it is necessary to perform modeling based on the material property data and the process parameters based on a support vector machine to obtain a mapping relationship model between the material property and the process parameters.

[0074] In one implementation, the modeling based on the material property data and the process parameters is performed based on a support vector machine to obtain a mapping relationship model between material properties and process parameters, including:

[0075] According to the material performance data and the process parameters, a model is constructed by using a multivariate linear regression method to obtain an initial mapping relationship model between material performance and process parameters; according to the initial mapping relationship model, a fitting degree calculation is performed to obtain the fitting degree of the initial mapping relationship model; according to the fitting degree and the initial mapping relationship model, a support vector machine kernel function transformation is used to reconstruct the feature space to obtain a high-dimensional mapping relationship model; according to the high-dimensional mapping relationship model, a cross-validation method is used to optimize the penalty factor and the kernel function parameters to obtain a mapping relationship model between material performance and process parameters.

[0076] It should be noted that the mapping relationship model between material properties and process parameters is a mathematical model that characterizes the nonlinear correlation between the physical properties, mechanical properties and process parameters of the woven material. Its construction process includes: first, the initial mapping relationship model is established by the multivariate linear regression method, and the material performance indicators that have a significant impact on the surface size fluctuation are screened out by the fitting calculation; when the initial model fitting degree is insufficient, the support vector machine kernel function transformation is used to map the low-dimensional process parameter space to the high-dimensional feature space to capture the implicit coupling law of the process parameters; further, the penalty factor and the radial basis kernel function parameters are optimized by the cross-validation method, the model complexity and generalization ability are balanced, and finally the mapping relationship model between material properties and process parameters is obtained. The specific application of the mapping relationship model in parameter optimization is reflected in: in the optimization stage of the weaving angle parameters, the parameter sensitivity coefficient output by the model guides the gradient descent direction; when the weaving density parameters are corrected, the search space of the genetic algorithm is limited according to the nonlinear constraints generated by the model; in the tension stability analysis, the model is used to predict the dynamic response characteristics of the equipment under different combinations of weaving tension parameters, providing data support for the evidence theory evaluation, thereby forming a multi-parameter collaborative control mechanism throughout the entire process optimization process.

[0077] In step S13, it is necessary to analyze the relationship between the braiding angle parameter and the surface size fluctuation according to the mapping relationship model and the process parameters, perform parameter optimization, and obtain the ideal braiding angle parameter.

[0078] In one implementation, the relationship between the braiding angle parameter and the surface size fluctuation is analyzed according to the mapping relationship model and the process parameters, and the parameters are optimized to obtain the ideal braiding angle parameter, including:

[0079] According to the mapping relationship model and the process parameters, the dynamic response relationship between the change in the weaving angle parameter and the surface size fluctuation is analyzed to obtain the sensitivity coefficient of the weaving angle parameter to the surface size; according to the sensitivity coefficient and the mapping relationship model, the associated weight matrix of the weaving angle parameter and the material performance data is analyzed to obtain the angle adjustment constraint condition; according to the angle adjustment constraint condition, the gradient descent method is used to calculate the loss function of the surface size fluctuation threshold and the material performance matching degree to obtain the optimal weaving angle parameter; according to the optimal weaving angle parameter, the dynamic response curve is calculated to obtain the fluctuation attenuation rate; when the fluctuation attenuation rate is within the preset standard range, the optimal weaving angle parameter is determined to be the ideal weaving angle parameter, and when the fluctuation attenuation rate is outside the preset standard range, the optimal weaving angle parameter is back-propagated and optimized to obtain the ideal weaving angle parameter.

[0080] It should be noted that the calculation process of the sensitivity coefficient is expressed by the following formula:

[0081]

[0082] In the formula, is the sensitivity coefficient, Indicates the braiding angle parameter; Indicates the braiding density parameter, Indicates the braiding tension parameter, Represents the mapping relationship model function, is the slight change of the angle parameter.

[0083] In step S14, it is necessary to optimize the weaving density parameters according to the ideal weaving angle parameters and the mapping relationship model in combination with the preset dimensional accuracy requirements to obtain the ideal weaving density parameters.

[0084] In one implementation, the optimization of the weaving density parameters is performed according to the ideal weaving angle parameters and the mapping relationship model in combination with preset dimensional accuracy requirements to obtain the ideal weaving density parameters, including:

[0085] According to the mapping relationship model, a nonlinear relationship analysis is performed between the weaving density parameters and the surface size fluctuation to obtain a weaving density nonlinear relationship model; according to the weaving density nonlinear relationship model and the ideal weaving angle parameters, a function analysis is performed in combination with preset dimensional accuracy requirements to obtain a weaving density parameter optimization function; according to the weaving density parameter optimization function, a genetic algorithm is used to perform iterative calculations to obtain a weaving density parameter solution set that meets the surface size fluctuation constraints; according to the weaving density parameter solution set and the weaving density nonlinear relationship model, the convergence of the surface size fluctuation is analyzed, and the solution with the best convergence in the weaving density parameter solution set is determined to be the ideal weaving density parameter.

[0086] In step S15, it is necessary to perform stability analysis of the weaving tension parameters according to the ideal weaving angle parameters, the ideal weaving density parameters and the mapping relationship model, optimize the tension control scheme, and obtain the ideal weaving tension parameters and ideal process parameters.

[0087] In one implementation, the stability analysis of the braiding tension parameters is performed according to the ideal braiding angle parameters, the ideal braiding density parameters and the mapping relationship model, the tension control scheme is optimized, and the ideal braiding tension parameters and ideal process parameters are obtained, including:

[0088] According to the mapping relationship model, a dynamic correlation analysis is performed between the weaving tension parameters and the mechanical structure of the equipment to obtain the dynamic response characteristics of the transmission system; according to the dynamic response characteristics of the transmission system, a timing anomaly detection algorithm is used to perform a weaving tension parameter fluctuation analysis to obtain the abnormal weaving tension fluctuation range; according to the abnormal weaving tension fluctuation range, a parameter optimization objective function of the tension control system is constructed to obtain a weaving tension parameter adjustment strategy; according to the weaving tension parameter adjustment strategy, a tension optimization algorithm is used to perform a robustness analysis to obtain a robustness evaluation result; according to the robustness evaluation result, the weaving tension parameter adjustment strategy, the ideal weaving angle parameters and the ideal weaving density parameters, a comprehensive optimization of the weaving tension parameters is performed to obtain the ideal weaving tension parameters; the ideal process parameters include the ideal weaving angle parameters, the ideal weaving density parameters and the ideal weaving tension parameters.

[0089] It should be noted that the ideal weaving tension parameter refers to the optimal tension value range that can stabilize the dynamic response characteristics of the equipment transmission system within a preset range under the premise of meeting the surface size accuracy requirements. It is obtained by the following technical means: extracting the dynamic correlation data of the tension parameter and the mechanical structure of the equipment based on the mapping relationship model, using the time series anomaly detection algorithm to identify the periodic abnormal pattern in the tension fluctuation, and constructing the tension optimization objective function containing the equipment rigidity attenuation coefficient, sensor sampling frequency and other constraints; calculating the robustness evaluation value of the objective function under the preset equipment state through the tension optimization algorithm, combining the coupling effect of the ideal weaving angle parameter and the weaving density parameter on the tension fluctuation, and using the back propagation algorithm to iteratively correct the tension control strategy to obtain the ideal weaving tension parameter. The ideal process parameter is a synergistic parameter combination composed of an ideal weaving angle parameter, an ideal weaving density parameter and an ideal weaving tension parameter. Its application process includes: when the parameter combination is input into the equipment control system, the dynamic effect of each parameter adjustment on the mechanical structure is predicted according to the mapping relationship model, and the transmission system compensation coefficient and the tension control frequency are synchronously adjusted; real-time monitoring of parameter execution deviation during the production process, when the weaving angle deviation is detected, the parameter re-optimization process based on the evidence theory is automatically triggered to ensure the dynamic adaptability of the process parameter combination.

[0090] In step S16, it is necessary to use a process parameter collaborative optimization algorithm to iteratively analyze according to the ideal process parameters to obtain final process parameters.

[0091] In one implementation, the iterative analysis using a process parameter collaborative optimization algorithm to obtain final process parameters according to the ideal process parameters includes:

[0092] According to the ideal process parameters, multi-dimensional parameter optimization is performed to construct a collaborative optimization space of process parameters including weaving angle parameters, weaving density parameters and weaving tension parameters; according to the collaborative optimization space of process parameters, a preset mechanical rigidity threshold and a preset transmission efficiency threshold are combined to perform collaborative constraints to obtain a first process parameter combination; according to the first process parameter combination, a process parameter collaborative optimization algorithm is initialized; according to the process parameter collaborative optimization algorithm, process parameter collaborative optimization iterations are performed to obtain a second process parameter combination, and the number of iterations is recorded; it is determined whether the second process parameter combination is better than the first process parameter combination, and if so, the second process parameter combination is used as the first process parameter combination; if not, the second process parameter combination is discarded; and the next iteration is continued. When the number of iterations is greater than or equal to the preset number of iterations, the current first process parameter combination is output as the final process parameter.

[0093] In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0094] The following describes the working process of the present invention using a common scenario as an example. Figure 2 , which is Figure 1 Schematic diagram of the working scenario of the method.

[0095] This embodiment uses a continuous production line for copper core cable braiding as the implementation scenario. The production line is equipped with a braiding machine, a tension controller, a visual inspection system, and a central control unit. When the system is started, the central control unit begins to execute the surface size detection and parameter optimization process of the present invention:

[0096] The system first collects the material performance data and process parameters of the cable braiding layer through the data acquisition module. Specifically, the sensor network obtains the physical and mechanical performance data of the braided material in real time, and extracts the braiding angle, braiding density and braiding tension. After standardized processing, these data form a set of process parameters including braiding angle parameters, braiding density parameters and braiding tension parameters, providing structured input for subsequent modeling.

[0097] Afterwards, based on the collected material performance data and process parameters, the initial mapping relationship model is first constructed using the multivariate linear regression method, and the model accuracy is judged by calculating the degree of fit. When the initial model is not sufficiently fitted, the support vector machine optimization process is triggered: the process parameter space is reconstructed into a high-dimensional feature space using kernel function transformation to capture the nonlinear relationship between material performance and process parameters; the penalty factor and kernel function parameters are further optimized by the cross-validation method, and finally a mapping relationship model that can accurately predict surface dimensional fluctuations is generated. The mapping relationship model continues to provide key data support in subsequent parameter optimization, such as quantifying the sensitivity coefficient of braiding angle changes to dimensional fluctuations.

[0098] Next, the dynamic response relationship between the braiding angle parameter and the surface size fluctuation is analyzed based on the mapping relationship model. By calculating the sensitivity coefficient of the braiding angle parameter to the surface size, the constraint conditions for angle adjustment are determined, and a loss function including the size fluctuation threshold and the material performance matching degree is constructed. The gradient descent method is used to iteratively optimize the loss function. When the calculated optimal braiding angle parameter shows that the fluctuation attenuation rate meets the preset standard in the dynamic response curve, it is determined as the ideal braiding angle parameter; if the attenuation rate exceeds the threshold, the model weight is corrected by the back propagation algorithm and recalculated until the stability requirements are met, and then it is determined as the ideal braiding angle parameter.

[0099] After obtaining the ideal braiding angle parameters, the density optimization module starts the braiding density parameter optimization process. The mapping relationship model analyzes the nonlinear relationship between the braiding density parameters and the surface size fluctuations, and generates a constraint function that meets the preset dimensional accuracy requirements. The genetic algorithm performs iterative calculations under this constraint, continuously optimizes the density parameter solution set through selection, crossover, and mutation operations, and finally selects the parameters with the best convergence as the ideal braiding density parameters. This process simultaneously verifies the influence of the braiding density parameters on the mechanical properties of the material, ensuring that the optimization results maintain the structural integrity of the material while meeting the dimensional accuracy.

[0100] Subsequently, the stability analysis of the weaving tension parameters was carried out, and the dynamic correlation characteristics of the weaving tension parameters and the mechanical structure of the equipment were extracted based on the mapping relationship model. The time series anomaly detection algorithm was used to identify the periodic abnormal patterns in the tension fluctuations. The parameter optimization objective function was constructed according to the abnormal fluctuation interval, and the tension optimization algorithm was used for robustness evaluation. The ideal weaving tension parameters were generated through weight adjustment and strategy correction in combination with the coupling effect of the ideal weaving angle and density parameters on the tension. The ideal process parameters finally defined include the optimized ideal weaving angle parameters, ideal weaving density parameters and ideal weaving tension parameters, forming a preliminary synergistic parameter combination.

[0101] The result output module globally verifies the ideal process parameters through the process parameter collaborative optimization algorithm. The algorithm constructs a process parameter collaborative optimization space including the ideal weaving angle parameter, the ideal weaving density parameter and the ideal weaving tension parameter, sets the mechanical rigidity threshold and the transmission efficiency threshold as collaborative constraints, and obtains the first process parameter combination. Starting from the first process parameter combination, the process parameter collaborative optimization algorithm is initialized, and the process parameter collaborative optimization iteration is performed according to the process parameter collaborative optimization algorithm to obtain the second process parameter combination, and the number of iterations is recorded. Then, it is determined whether the second process parameter combination is better than the first process parameter combination. If so, the second process parameter combination is used as the first process parameter combination; if not, the second process parameter combination is discarded; continue to the next iteration, and when the number of iterations is greater than or equal to the preset number of iterations, the current first process parameter combination is output as the final process parameter. In this process, the system continuously monitors the parameter execution effect. If a material change or a change in the equipment status is detected, the adaptive adjustment process is immediately triggered to maintain the stability of the parameter combination by dynamically updating the mapping relationship model and the optimization strategy.

[0102] Through the above working process, the present invention realizes closed-loop control of the entire process from data collection, model building to multi-parameter collaborative optimization. In the copper core cable production scenario, the system shortens the parameter adjustment cycle of several hours required for traditional manual debugging to a minute-level response of the automated process, and at the same time significantly improves the surface dimensional consistency by dynamically associating material properties, process parameters and equipment status. When the production line switches to aluminum alloy materials, the system automatically reconstructs the feature space and re-optimizes the parameter combination, avoiding the problem of decreased pass rate due to differences in material properties in traditional methods. This fully verifies the technical advantage of the present invention in achieving dimensional consistency control by intelligently optimizing the braiding process parameters in a complex production environment.

[0103] In summary, the present invention discloses a method for optimizing the process parameters of a cable braided layer, comprising obtaining material performance data and process parameters of a cable braided layer; performing modeling based on a support vector machine according to the material performance data and the process parameters to obtain a mapping relationship model between material performance and process parameters; analyzing the relationship between braiding angle parameters and surface dimension fluctuations according to the mapping relationship model and the process parameters, performing parameter optimization, and obtaining ideal braiding angle parameters; optimizing braiding density parameters according to the ideal braiding angle parameters and the mapping relationship model in combination with preset dimensional accuracy requirements to obtain ideal braiding density parameters; performing stability analysis of braiding tension parameters according to the ideal braiding angle parameters, the ideal braiding density parameters and the mapping relationship model, optimizing the tension control scheme, and obtaining ideal braiding tension parameters and ideal process parameters; and iteratively analyzing the process parameter collaborative optimization algorithm according to the ideal process parameters to obtain final process parameters.

[0104] The present invention realizes the collaborative optimization control of weaving process parameters through the following technical steps: first, the material performance data of the cable braiding layer and the process parameters of the cable braiding layer are obtained, and then a mapping relationship model between the material performance data and the process parameters is established, breaking through the limitations of traditional single parameter adjustment, and incorporating the coupling effects of the braiding angle parameters, the braiding density parameters, and the braiding tension parameters into a unified analysis framework, so as to solve the problem of local optimal failure caused by isolated parameter optimization; then, the mapping relationship model between material performance and process parameters constructed based on support vector machine reveals the multi-parameter coupling law, and according to the model, the dynamic response relationship between the braiding angle parameters and the surface size fluctuations is analyzed and the gradient descent method is used to optimize to the ideal braiding angle parameters, and then the ideal braiding density parameters are iteratively calculated by genetic algorithm in combination with the preset dimensional accuracy requirements, and the evidence theory is further integrated to perform stability analysis of the tension parameters on the ideal braiding angle parameters and the ideal braiding density parameters and optimize the tension control scheme, and finally the process parameter collaborative optimization algorithm is used to perform global iterative verification and dynamic weight adjustment on multiple parameters to generate the final process parameters that meet the dual constraints of surface size accuracy and equipment reliability. Through the systematic connection of the above steps, the present invention breaks through the limitations of traditional single parameter static adjustment and constructs a dynamic collaborative optimization mechanism of material properties, process parameters and equipment status, thereby achieving the consistency of the surface size of the braided layer by optimizing the braiding process parameters.

[0105] Reference Figure 2 The second embodiment of the present invention provides a process parameter optimization system for a cable braid layer, comprising:

[0106] A data acquisition module, used to acquire material performance data and process parameters of the cable braiding layer;

[0107] A mapping modeling module, used to perform modeling based on a support vector machine according to the material performance data and the process parameters to obtain a mapping relationship model between material performance and process parameters;

[0108] An angle optimization module, used to analyze the relationship between the braiding angle parameter and the surface size fluctuation according to the mapping relationship model and the process parameters, perform parameter optimization, and obtain the ideal braiding angle parameter;

[0109] A density optimization module, used to optimize the weaving density parameters according to the ideal weaving angle parameters and the mapping relationship model in combination with preset dimensional accuracy requirements to obtain the ideal weaving density parameters;

[0110] A tension optimization module, used to perform stability analysis of the weaving tension parameters according to the ideal weaving angle parameters, the ideal weaving density parameters and the mapping relationship model, optimize the tension control scheme, and obtain the ideal weaving tension parameters and ideal process parameters;

[0111] The result output module is used to iteratively analyze the ideal process parameters using a process parameter collaborative optimization algorithm to obtain final process parameters.

[0112] It should be noted that a process parameter optimization system for a cable braided layer provided in an embodiment of the present invention is used to execute all process steps of a process parameter optimization method for a cable braided layer in the above embodiment. The working principles and beneficial effects of the two correspond one to one, and thus will not be repeated herein.

[0113] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a cable braiding layer process parameter optimization program. When the processor executes the computer program, the steps in the above-mentioned embodiments of the cable braiding layer process parameter optimization method are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are implemented, such as the mapping modeling module.

[0114] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0115] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0116] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0117] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0118] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0119] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0120] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for optimizing process parameters of a cable braided layer, characterized in that: Executed by a computer, including: Obtain the material performance data and process parameters of the cable braid layer, including: Obtain the physical property data of the braided material during the production process of the cable braid layer and the mechanical property data of the braided material during the production process of the cable braid layer; Wherein, the material performance data of the cable braided layer includes the physical performance data and the mechanical performance data; Extracting preset initial braiding angle parameters, initial braiding density parameters and initial braiding tension parameters; Performing standardization processing according to the material performance data, the initial braiding angle parameter, the initial braiding density parameter and the initial braiding tension parameter to obtain the process parameters of the cable braiding layer; The process parameters include braiding angle parameters, braiding density parameters and braiding tension parameters; According to the material performance data and the process parameters, modeling is performed based on a support vector machine to obtain a mapping relationship model between material performance and process parameters; According to the mapping relationship model and the process parameters, the relationship between the braiding angle parameter and the surface size fluctuation is analyzed, and the parameters are optimized to obtain the ideal braiding angle parameter; According to the ideal braiding angle parameter and the mapping relationship model, the braiding density parameter is optimized in combination with the preset dimensional accuracy requirement to obtain the ideal braiding density parameter; According to the ideal braiding angle parameter, the ideal braiding density parameter and the mapping relationship model, a stability analysis of the braiding tension parameter is performed, and the tension control scheme is optimized to obtain the ideal braiding tension parameter and the ideal process parameter, including: According to the mapping relationship model, a dynamic correlation analysis between the weaving tension parameter and the mechanical structure of the equipment is performed to obtain the dynamic response characteristics of the transmission system; According to the dynamic response characteristics of the transmission system, a timing anomaly detection algorithm is used to perform a weaving tension parameter fluctuation analysis to obtain an abnormal weaving tension fluctuation range; According to the abnormal fluctuation range of the braiding tension, a parameter optimization objective function of the tension control system is constructed to obtain a braiding tension parameter adjustment strategy; According to the braiding tension parameter adjustment strategy, a tension optimization algorithm is used to perform robustness analysis to obtain a robustness evaluation result; According to the robustness evaluation result, the braiding tension parameter adjustment strategy, the ideal braiding angle parameter and the ideal braiding density parameter, the braiding tension parameter is comprehensively optimized to obtain the ideal braiding tension parameter; The ideal process parameters include the ideal braiding angle parameter, the ideal braiding density parameter and the ideal braiding tension parameter; According to the ideal process parameters, a process parameter collaborative optimization algorithm is used for iterative analysis to obtain final process parameters.

2. The process parameter optimization method of the cable braided layer according to claim 1, characterized in that: The modeling based on the material performance data and the process parameters is performed based on a support vector machine to obtain a mapping relationship model between material performance and process parameters, including: According to the material performance data and the process parameters, a model is constructed using a multivariate linear regression method to obtain an initial mapping relationship model between the material performance and the process parameters; According to the initial mapping relationship model, a fitting degree calculation is performed to obtain the fitting degree of the initial mapping relationship model; According to the fitting degree and the initial mapping relationship model, a support vector machine kernel function is used to transform and reconstruct the feature space to obtain a high-dimensional mapping relationship model; According to the high-dimensional mapping relationship model, a cross-validation method is used to optimize the penalty factor and kernel function parameters to obtain a mapping relationship model between material properties and process parameters.

3. The process parameter optimization method of the cable braiding layer according to claim 1 is characterized in that: The step of analyzing the relationship between the braiding angle parameter and the surface size fluctuation according to the mapping relationship model and the process parameters, optimizing the parameters, and obtaining the ideal braiding angle parameter includes: According to the mapping relationship model and the process parameters, the dynamic response relationship between the change of the braiding angle parameter and the surface size fluctuation is analyzed to obtain the sensitivity coefficient of the braiding angle parameter to the surface size; According to the sensitivity coefficient and the mapping relationship model, analyzing the association weight matrix between the braiding angle parameter and the material performance data to obtain the angle adjustment constraint condition; According to the angle adjustment constraint conditions, a gradient descent method is used to calculate the loss function of the surface size fluctuation threshold and the material performance matching degree to obtain the optimal braiding angle parameter; According to the optimal braiding angle parameter, a dynamic response curve is calculated to obtain a fluctuation attenuation rate; When the fluctuation attenuation rate is within the preset standard range, the optimal braiding angle parameter is determined to be the ideal braiding angle parameter. When the fluctuation attenuation rate is outside the preset standard range, the optimal braiding angle parameter is back-propagated and optimized to obtain the ideal braiding angle parameter.

4. The process parameter optimization method of the cable braiding layer according to claim 1 is characterized in that: The optimizing of the weaving density parameters according to the ideal weaving angle parameters and the mapping relationship model in combination with the preset dimensional accuracy requirements to obtain the ideal weaving density parameters includes: According to the mapping relationship model, a nonlinear relationship analysis is performed between the weaving density parameter and the surface size fluctuation to obtain a weaving density nonlinear relationship model; According to the nonlinear relationship model of braiding density and the ideal braiding angle parameter, a function analysis is performed in combination with a preset dimensional accuracy requirement to obtain a braiding density parameter optimization function; According to the weaving density parameter optimization function, a genetic algorithm is used to perform iterative calculation to obtain a weaving density parameter solution set that satisfies the surface size fluctuation constraint; According to the weaving density parameter solution set and the weaving density nonlinear relationship model, the convergence of the surface size fluctuation is analyzed, and the solution with the best convergence in the weaving density parameter solution set is determined as the ideal weaving density parameter.

5. The process parameter optimization method of the cable braiding layer according to claim 1 is characterized in that: The process of iteratively analyzing the ideal process parameters using a process parameter collaborative optimization algorithm to obtain final process parameters includes: According to the ideal process parameters, multi-dimensional parameter optimization is performed to construct a process parameter collaborative optimization space including a weaving angle parameter, a weaving density parameter and a weaving tension parameter; According to the process parameter collaborative optimization space, a preset mechanical rigidity threshold and a preset transmission efficiency threshold are combined for collaborative constraint to obtain a first process parameter combination; Initializing a collaborative optimization algorithm for process parameters according to the first process parameter combination; According to the process parameter collaborative optimization algorithm, perform process parameter collaborative optimization iteration to obtain a second process parameter combination, and record the number of iterations; Determine whether the second process parameter combination is better than the first process parameter combination, if so, use the second process parameter combination as the first process parameter combination; if not, discard the second process parameter combination; Continue to the next iteration, when the number of iterations is greater than or equal to the preset number of iterations, output the current first process parameter combination as the final process parameter.

6. A process parameter optimization system for a cable braided layer, characterized in that: A method for optimizing the process parameters of a cable braided layer according to any one of claims 1 to 5, comprising: A data acquisition module, used to acquire material performance data and process parameters of the cable braiding layer; A mapping modeling module, used to perform modeling based on a support vector machine according to the material performance data and the process parameters to obtain a mapping relationship model between material performance and process parameters; An angle optimization module, used to analyze the relationship between the braiding angle parameter and the surface size fluctuation according to the mapping relationship model and the process parameters, perform parameter optimization, and obtain the ideal braiding angle parameter; A density optimization module, used to optimize the weaving density parameters according to the ideal weaving angle parameters and the mapping relationship model in combination with preset dimensional accuracy requirements to obtain the ideal weaving density parameters; A tension optimization module, used to perform stability analysis of the weaving tension parameters according to the ideal weaving angle parameters, the ideal weaving density parameters and the mapping relationship model, optimize the tension control scheme, and obtain the ideal weaving tension parameters and ideal process parameters; The result output module is used to iteratively analyze the ideal process parameters using a process parameter collaborative optimization algorithm to obtain final process parameters.

7. An electronic device, characterized in that: It comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the process parameter optimization method of the cable braiding layer as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the process parameter optimization method for the cable braiding layer according to any one of claims 1 to 5.

Images