Lightweight structural design method and device for optical lens

Abstract

The present invention belongs to the field of lens technology, and discloses a lightweight structural design method and device for an optical lens; the method comprises: obtaining lens customization demand data, wherein the lens customization demand data comprises lens optical performance demand data, lens physical performance demand data and customer demand budget; processing the lens customization demand data using a feature extraction method to obtain a customized demand structure set; constructing a lens customization demand data tree according to the customized demand structure set; obtaining a lens customization material set according to the lens customization demand data tree; and performing lightweight tuning on the lens according to the lens customization material set and the lens customization demand data tree; this solution realizes lightweight tuning of the lens while meeting the personalized needs of customers through intelligent lens demand analysis, optimization modeling and adaptive tuning, thereby improving the flexibility and accuracy of lens lightweight design.

Description

Technical Field

[0001] The present invention relates to the field of lens technology, and more particularly to a method and device for designing a lightweight structure of an optical lens. Background Art

[0002] The current design of lightweight lens structures usually relies on experience-driven material selection and structural optimization methods, lacking a systematic analysis of customer customization requirements, resulting in difficulty in achieving a balance between optical performance, mechanical strength, and manufacturing costs in material selection. In addition, existing lens design methods often only consider all requirements together, ignoring the priority and hierarchy of lens requirements, resulting in insufficient flexibility in lens material selection. It is difficult to achieve precise optimization of lens materials while meeting the key optical properties of the lens, thus affecting the overall performance and production feasibility of the lens. At the same time, traditional optimization algorithms fail to fully consider the multi-level demand relationship of the lens during the lens lightweighting process, and cannot achieve adaptive adjustment of the lens material usage, making it difficult for lens design to balance lightweighting with multi-dimensional performance requirements such as optics and mechanics.

[0003] Therefore, how to provide an intelligent and precise lens material selection and lens lightweight structure optimization method based on the customization needs of lenses, ensure that the lens achieves the maximum lightweight while meeting the optical, mechanical and other performance requirements, and improve the utilization rate of lens materials and reduce the cost of lens production, has become a technical problem that needs to be urgently solved in the optical industry. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned objectives, the present invention provides the following technical solution: a lightweight structural design method for an optical lens, comprising:

[0005] Obtaining lens customization demand data, wherein the lens customization demand data includes lens optical performance demand data, lens physical performance demand data, and customer demand budget;

[0006] Using feature extraction methods to process lens customization demand data to obtain a set of customized demand structures;

[0007] Construct a lens customization requirement data tree based on the customization requirement structure set;

[0008] Obtaining a lens customization material set according to the lens customization requirement data tree;

[0009] The lens is lightweight tuned according to the lens customized material set and lens customized demand data tree.

[0010] Furthermore, the method for lightweight tuning of the lens according to the lens customized material set and the lens customized requirement data tree includes:

[0011] Step 500: The number of lens customized materials in the lens customized material set is recorded as DZSL, and the lens customized demand data tree and DZSL lens customized materials are respectively input into the material usage model to obtain the lens material usage interval corresponding to the DZSL lens customized materials; initialize the lens material population containing H lens material candidate solutions; set the maximum number of iterations to ZDCS, set zdcs=1, and the value range of zdcs is 1 to ZDCS;

[0012] Step 501: Evaluate the lens material fitness values corresponding to H candidate lens material solutions in the lens material population;

[0013] Step 502: Sort the fitness values of the H lens materials in descending order, and select the first G lens materials with the best fitness values to form an elite population of lens materials;

[0014] Step 503: Perform mutation operations on the lens material elite population according to the preset method to obtain F mutated lens material candidate solutions and add them to the lens material elite population; overlay the lens material elite population onto the lens material population, and set H = G + F;

[0015] Step 504: Let zdcs = zdcs + 1. If zdcs is less than or equal to ZDCS, continue executing Step 501 to Step 503. If zdcs is greater than ZDCS, select the lens material candidate solution with the largest lens material fitness value from the lens material population as the optimal solution for lens material lightweighting.

[0016] Furthermore, a method for performing a mutation operation on the lens material elite population according to a preset method to obtain F candidate solutions of mutated lens materials includes:

[0017] A first fitness threshold and a second fitness threshold are preset, and the first fitness threshold is smaller than the second fitness threshold; an elite population of lens materials is divided according to the first fitness threshold and the second fitness threshold to obtain a material high fitness set, a material medium fitness set, and a material low fitness set;

[0018] Random crossover is performed in the material high fitness set to obtain Candidate solutions of lens materials are added to the material high fitness set;

[0019] The lens material candidate solutions in the material fitness set are randomly crossed with the lens material candidate solutions in the material high fitness set to obtain The candidate solutions of lens materials are added to the fitness set in the material; random crossover is performed in the fitness set in the material to obtain Candidate solutions of lens materials are added to the fitness set of materials;

[0020] The lens material candidate solutions in the material low fitness set are randomly crossed with the lens material candidate solutions in the material high fitness set to obtain The candidate solutions of lens materials are added to the material low fitness set; random crossover is performed in the material low fitness set to obtain Candidate solutions of lens materials are added to the material low fitness set;

[0021] when When , the random crossover operation is stopped, and F candidate solutions of variant lens materials are obtained.

[0022] Furthermore, the method for constructing the lens customization requirement data tree includes:

[0023] Step 200: The height of the preset lens customization requirement data tree is , An integer greater than 0, preset Customized requirement priority thresholds, The priority threshold for customized requirements is , ; Let sg = 1, the value range of sg is 1 to SG;

[0024] Step 201: If sg is equal to 1, then the customized requirement priority value in the customized requirement structure set is greater than or equal to The customized requirement structure is constructed into the sg-th layer of the lens customized requirement data tree;

[0025] If sg is greater than 1 and less than or equal to , then the customized requirement priority value in the customized requirement structure set is greater than or equal to and less than The customized requirement structure is constructed into the sg-th layer of the lens customized requirement data tree;

[0026] If sg is equal to , then the customized requirement priority value in the customized requirement structure set is less than The customized requirement structure is constructed into the sg-th layer of the lens customized requirement data tree;

[0027] Step 202: Let sg = sg + 1. If sg is less than or equal to SG, continue to execute Step 201; if sg is greater than SG, obtain the lens customization requirement data tree and end the current process.

[0028] Furthermore, the method for obtaining the customized demand structure set includes:

[0029] Step 100: record the number of customization requirements in the lens customization requirement data as DZ, set dz=1, and the value range of dz is 1 to DZ; construct DZ customization requirements into a lens customization requirement set;

[0030] Step 101: Input the dzth customization requirement in the lens customization requirement set into the requirement priority value model to obtain the corresponding customization requirement priority value;

[0031] Step 102: Construct the dzth customized requirement and the customized requirement priority value into a corresponding customized requirement structure;

[0032] Step 103: Add the dzth customized requirement structure to the customized requirement structure collection;

[0033] Step 104: Let dz = dz + 1. If dz is less than or equal to DZ, continue executing Step 101 to Step 103. If dz is greater than DZ, obtain the customized requirement structure set and end the current process.

[0034] Furthermore, the method for obtaining a lens customization material set according to the lens customization requirement data tree includes:

[0035] Step 300: The material selection layer number of the lens customization requirement data tree is CLS, and the value range of CLS is 1 to , let cls=1, the value range of cls is 1 to CLS; build a temporary storage set of CLS demand structures;

[0036] Step 301: Add lens customization requirement data tree The customized requirement structure is added to the cls-th requirement structure temporary storage collection, The number of customized requirement structures at the cls-th layer; if cls is greater than 1, the customized requirement structure in the cls-1-th requirement structure temporary storage set is added to the cls-th requirement structure temporary storage set;

[0037] Step 302: Input the temporary storage set of the cls-th requirement structure into the lens material model to obtain the cls-th lens applicable material set;

[0038] Step 303: Let cls = cls + 1. If cls is less than or equal to CLS, continue executing Step 301 to Step 302. If cls is greater than CLS, obtain CLS lens-applicable material sets, analyze and process the CLS lens-applicable material sets according to a preset method, and obtain a lens customized material set.

[0039] Furthermore, the method of analyzing and processing the CLS lens applicable material sets according to a preset method to obtain a lens customized material set includes:

[0040] Step 400: Take the intersection of CLS demand structure temporary storage sets to obtain the demand structure temporary storage intersection; let cls=1;

[0041] Step 401: Obtain the clsth temporary storage set of demand structures; if the clsth temporary storage set of demand structures does not contain the customized demand structure in the temporary intersection set of demand structures, then use the clsth temporary storage set of demand structures as the clsth demand structure deduplication set and directly execute Step 402;

[0042] If the clsth demand structure temporary storage set contains the customized demand structure in the demand structure temporary storage intersection set, then delete the customized demand structure in the demand structure temporary storage intersection set from the clsth demand structure temporary storage set to obtain the clsth demand structure deduplication set, and execute Step 402;

[0043] Step 402: Set cls = cls + 1. If cls is less than or equal to CLS, continue to Step 401; if cls is greater than CLS, continue to Step 403.

[0044] Step 403: Construct a total set of demand structures from the deduplicated set of CLS demand structures, count the number of each customized demand structure in the total set of demand structures, sort the total set of demand structures in descending order according to the number of customized demand structures, select the first N customized demand structures from the total set of demand structures after descending order; and construct the first N customized demand structures and the temporarily stored intersection of the demand structures into a lens customized material set.

[0045] Furthermore, the training method of the material usage model includes:

[0046] Preliminarily collecting a material usage dataset, the material usage dataset comprising Y groups of material usage data and lens material usage intervals corresponding to the Y groups of material usage data, where Y is a positive integer greater than 0, and the material usage data comprising a lens customization requirement data tree and lens customization materials; dividing the material usage dataset into a training set and a validation set, wherein the training set is used to train a material usage model, and the validation set is used to evaluate the generalization performance of the material usage model;

[0047] During the material usage model training process, minimizing the cross-entropy loss function is used as the optimization goal. An early stopping strategy is used to monitor the performance of the validation set, and the model performance is optimized by continuously adjusting the network parameters. When the prediction accuracy on the validation set reaches the preset accuracy, training is stopped. The material usage model is trained using a deep neural network based on a multilayer perceptron.

[0048] The material usage data is converted into a high-dimensional feature vector. The input layer of the material usage model receives the high-dimensional feature vector, and the hidden layer extracts the nonlinear relationship in the material usage data. Finally, the output layer of the material usage model calculates the probability distribution of the lens material usage interval through the softmax activation function, and outputs the lens material usage interval corresponding to the maximum probability as the final prediction result.

[0049] The lens material model is obtained by the same training method as the material dosage model.

[0050] Furthermore, the training method of the demand priority value model includes:

[0051] Pre-collect a demand priority value dataset, the demand priority value dataset including Q groups of demand priority value data and customized demand priority values corresponding to the Q groups of demand priority value data, where Q is a positive integer greater than 0, and the demand priority value data includes customized demands; divide the demand priority value dataset into a training set and a validation set, the training set being used to learn demand priority value model parameters, and the validation set being used to evaluate the generalization ability of the demand priority value model to avoid overfitting;

[0052] During the training process of the demand priority value model, a dynamic learning rate adjustment strategy is combined with an early stopping mechanism to minimize the cross-entropy loss function as the optimization goal. When the performance of the validation set meets the preset requirements, training is automatically stopped to ensure the convergence of the demand priority value model. The demand priority value model is implemented based on the neural network model architecture. The neural network model consists of an input layer, a hidden layer, and an output layer. The input layer receives the demand priority value data and converts it into a high-dimensional feature vector. The hidden layer uses an activation function to extract the nonlinear pattern of the demand priority value data. The output layer calculates the probability distribution of the customized demand priority value through the softmax activation function, and uses the customized demand priority value corresponding to the maximum probability as the prediction result and outputs it.

[0053] A lightweight structure design device for an optical lens, which implements the lightweight structure design method for an optical lens, comprises:

[0054] A demand collection module is used to obtain lens customization demand data, wherein the lens customization demand data includes lens optical performance demand data, lens physical performance demand data and customer demand budget;

[0055] A first processing module is used to process the lens customization requirement data using a feature extraction method to obtain a customization requirement structure set;

[0056] A second processing module is used to construct a lens customization requirement data tree according to the customization requirement structure set;

[0057] A material selection module is used to obtain a lens customization material set based on the lens customization requirement data tree;

[0058] The lens tuning module is used to perform lightweight tuning on the lens based on the lens customized material set and the lens customized demand data tree.

[0059] Compared with the prior art, the lightweight structure design method and device of the optical lens of the present invention have the following technical effects and advantages:

[0060] This solution precisely collects and progressively processes lens customization requirements to construct a lens customization requirement data tree. Combining this data tree with a machine learning model, it derives a set of suitable lens materials, enabling intelligent, precise, and efficient lens material selection. This significantly enhances the flexibility and stability of lightweight lens structural design. By accumulating requirements layer by layer, material selection meets high-priority requirements while also taking into account secondary requirements, avoiding coupling issues caused by one-time input and improving the accuracy and interpretability of material selection.

[0061] The lens customization demand data tree and the specific lens customization materials are combined to obtain the lens material usage range of the lens customization material. On this basis, the elite retention and mutation strategies of the genetic algorithm are improved to achieve customized dynamic optimization and adjustment of the lens material candidate solutions, thereby achieving adaptive adjustment of the lens material usage, and then achieving the optimal lightweight solution, which ensures the stability of key lens performance such as optical and mechanical properties, and also meets customer customization needs.

[0062] In summary, this solution achieves lightweight tuning of lenses while meeting customers' personalized needs through intelligent demand analysis, optimized modeling, and adaptive tuning. It also improves the flexibility, precision, and stability of lightweight lens design, increases material utilization, and reduces production costs. It has broad application prospects and significant economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is a structural diagram of a lightweight structural design device for an optical lens according to Example 1 of the present invention;

[0064] Figure 2 This is a flow chart of a lightweight structure design method for an optical lens according to Example 3 of the present invention;

[0065] Figure 3 A structural diagram of a lightweight structural design device for an optical lens according to Example 2 of the present invention;

[0066] Figure 4 A flow chart of a method for lightweight tuning of a lens based on a lens customized material set and a lens customized requirement data tree;

[0067] Figure 5 Schematic diagram of the lens customization requirement data tree. DETAILED DESCRIPTION

[0068] The technical solutions in the embodiments of the present invention will be described in detail, clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. It should be noted that the specific embodiments described below are only used to better illustrate and describe the technical solutions of the present invention, and are intended to enable those skilled in the art to better understand and implement the present invention, and should not be construed as limiting the scope of protection of the present invention. Without departing from the spirit and essence of the present invention, those skilled in the art may modify, adjust or make equivalent replacements based on the contents disclosed in the present invention, and these should all be regarded as the scope of protection of the present invention.

[0069] Example 1

[0070] See also Figure 1 As shown, the lightweight structure design device for the optical lens described in this embodiment includes a demand collection module, a first processing module, a second processing module, a material selection module and a lens tuning module. Each module realizes data transmission through wired and / or wireless connections.

[0071] The demand collection module is used to obtain lens customization demand data, which includes lens optical performance demand data, lens physical performance demand data and customer demand budget; the lens optical performance demand data includes lens refractive index, lens transmittance, lens chromatic aberration, lens aberration and lens focal length, and the lens physical performance demand data includes lens weight, lens thickness, lens strength, lens durability and lens temperature stability; the lens refractive index, lens transmittance, lens chromatic aberration, lens aberration, lens focal length, lens weight, lens thickness, lens strength, lens durability, lens temperature stability and customer demand budget are all customized demands.

[0072] It's important to note that aberration is a key concept in the lens field. When light passes through a lens, due to the lens's geometry, material properties, and the complexity of the light's propagation path, it cannot perfectly converge to a single focal point, resulting in blur, distortion, and dispersion in the image. These phenomena are collectively referred to as aberrations. The description of lens aberrations relies on specific quantitative metrics, such as wavefront error (RMS, PV), modulation transfer function (MTF), and Strehl ratio. These quantitative metrics can clearly measure the impact of aberrations on image quality, thereby meeting customer demands for clarity and precision.

[0073] The first processing module is used to process the lens customization requirement data using a feature extraction method to obtain a customization requirement structure set.

[0074] The method for obtaining the customized requirement structure set includes:

[0075] Step 100: Record the number of customization requirements in the lens customization requirement data as DZ, preset the initial value of dz to 1, and the value range of dz is 1 to DZ; construct DZ customization requirements into a lens customization requirement set;

[0076] Step 101: Obtain the dzth customization requirement from the lens customization requirement set, input the dzth customization requirement into the requirement priority value model, and obtain the customization requirement priority value corresponding to the dzth customization requirement;

[0077] Step 102: Construct the dzth customized requirement and the customized requirement priority value into a customized requirement structure corresponding to the dzth customized requirement;

[0078] Step 103: Add the dzth customized requirement structure to the customized requirement structure collection;

[0079] Step 104: Let dz = dz + 1. If dz is less than or equal to DZ, continue executing Step 101 to Step 103. If dz is greater than DZ, obtain the customized requirement structure set and end the current process.

[0080] The training method of the demand priority value model includes:

[0081] Pre-collect a demand priority value dataset, the demand priority value dataset including Q groups of demand priority value data and customized demand priority values corresponding to the Q groups of demand priority value data, where Q is a positive integer greater than 0, and the demand priority value data includes customized demands; divide the demand priority value dataset into a training set and a validation set, the training set being used to learn demand priority value model parameters, and the validation set being used to evaluate the generalization ability of the demand priority value model to avoid overfitting;

[0082] During the training process of the demand priority value model, a dynamic learning rate adjustment strategy is combined with an early stopping mechanism to minimize the cross-entropy loss function as the optimization goal. When the performance of the validation set meets the preset requirements, training is automatically stopped to ensure the convergence of the demand priority value model. The demand priority value model is implemented based on the neural network model architecture. The neural network model consists of an input layer, a hidden layer, and an output layer. The input layer receives the demand priority value data and converts it into a high-dimensional feature vector. The hidden layer uses an activation function to extract the complex nonlinear pattern of the demand priority value data. The output layer calculates the probability distribution of the customized demand priority value through the softmax activation function, and uses the customized demand priority value corresponding to the maximum probability as the prediction result and outputs it.

[0083] The second processing module is used to construct a lens customization requirement data tree according to the customization requirement structure set.

[0084] The method for constructing the lens customization requirement data tree includes:

[0085] Step 200: The height of the preset lens customization requirement data tree is , An integer greater than 0, preset Customized requirement priority thresholds, The priority threshold for customized requirements is , ; The initial value of sg is preset to 1, and the value range of sg is 1 to SG;

[0086] Step 201: If sg is equal to 1, obtain the customized requirement priority value greater than or equal to from the customized requirement structure set The customized requirement structure of the customized requirement priority value is greater than or equal to The customized requirement structure is constructed into the sg-th layer of the lens customized requirement data tree;

[0087] If sg is greater than 1, and sg is less than or equal to , then obtain the customized requirement priority value greater than or equal to from the customized requirement structure set and less than The customized requirement structure of the customized requirement priority value is greater than or equal to and less than The customized requirement structure is constructed into the sg-th layer of the lens customized requirement data tree;

[0088] If sg is equal to , then the customized requirement priority value obtained from the customized requirement structure set is less than The customized demand structure of the customized demand priority value is less than The customized requirement structure is constructed into the sg-th layer of the lens customized requirement data tree;

[0089] Step 202: Let sg = sg + 1. If sg is less than or equal to SG, continue to execute Step 201; if sg is greater than SG, obtain the lens customization requirement data tree and end the current process.

[0090] It should be noted that the lens customization requirement data tree is as follows Figure 5 As shown, customized requirements with high priority values are placed at the upper level of the lens customized requirement data tree, and customized requirements with low priority values are placed at the lower level of the lens customized requirement data tree, so as to clearly display the hierarchical structure of different customized requirements and help technical personnel in this field to better consider customized requirements in subsequent development, design and optimization processes.

[0091] The material selection module is used to obtain a lens customized material set according to the lens customization requirement data tree.

[0092] The method for obtaining a lens customized material set according to the lens customized requirement data tree includes:

[0093] Step 300: The material selection layer number of the preset lens customization requirement data tree is CLS, and the value range of CLS is 1 to , the initial value of cls is preset to 1, and the value range of cls is 1 to CLS; construct CLS temporary demand structure sets, and the CLS temporary demand structure sets are all empty sets when constructed;

[0094] Step 301: Obtain the customized requirement structure of the cls layer from the lens customized requirement data tree; record the number of customized requirement structures of the cls layer as ,Will The customized requirement structure is added to the cls-th requirement structure temporary storage set; if cls is greater than 1, the customized requirement structure in the cls-1-th requirement structure temporary storage set is added to the cls-th requirement structure temporary storage set;

[0095] Step 302: Input the temporary storage set of the cls-th requirement structure into the lens material model to obtain the cls-th lens applicable material set;

[0096] Step 303: Let cls = cls + 1. If cls is less than or equal to CLS, continue executing Step 301 to Step 302. If cls is greater than CLS, obtain CLS lens-applicable material sets, analyze and process the CLS lens-applicable material sets according to a preset method, and obtain a lens customized material set.

[0097] The training method of the lens material model includes:

[0098] Preliminarily collecting a lens material dataset, the lens material dataset comprising P groups of lens material data and a set of lens applicable materials corresponding to the P groups of lens material data, where P is a positive integer greater than 0, and the lens material data comprising a temporary set of requirement structures; dividing the lens material dataset into a training set and a validation set, wherein the training set is used to train a lens material model, and the validation set is used to evaluate the generalization performance of the lens material model;

[0099] During lens material model training, minimizing the cross-entropy loss function is used as the optimization objective. An early stopping strategy is used to monitor the performance of the validation set, and model performance is optimized by continuously adjusting network parameters. When the prediction accuracy on the validation set reaches a preset accuracy, the lens material model is considered to have converged and training is stopped. The lens material model is trained using a deep neural network based on a multilayer perceptron.

[0100] The lens material data is converted into a high-dimensional feature vector; the input layer of the lens material model receives the high-dimensional feature vector, and the nonlinear relationship in the lens material data is extracted through the hidden layer. Finally, the output layer of the lens material model calculates the probability distribution of the lens applicable material set through the softmax activation function, and outputs the lens applicable material set corresponding to the maximum probability as the final prediction result.

[0101] It should be noted that processing the lens customization requirement data tree in a layered, progressive manner not only improves flexibility, accuracy, and interpretability, but also provides more refined material optimization solutions for complex demand environments. By analyzing and meeting each layer of requirements in a hierarchical and orderly manner, material selection is gradually optimized, ensuring that key lens performance is maintained while also considering and adjusting secondary lens requirements. This allows for dynamic adaptation to different application scenarios, supports rapid adjustment under changing lens requirements, and ensures the rationality and adaptability of material selection. In contrast, a one-time input approach for all customization requirements, while providing a rapid overall assessment when lens requirements are less coupled, lacks flexibility and is difficult to meet the requirements for gradual optimization of complex customization requirements. Furthermore, this one-time input approach often leads to instability in lens material selection due to the mutual influence of lens requirements, making it difficult to balance all lens requirements. Therefore, when it comes to lens material selection and optimization, a layered, progressive approach allows for more precise control to meet the needs of high-precision applications.

[0102] The method for analyzing and processing the CLS lens applicable material set according to the preset method to obtain the lens customized material set includes:

[0103] Step 400: Take the intersection of CLS demand structure temporary storage sets to obtain the demand structure temporary storage intersection; let cls=1;

[0104] Step 401: Obtain the clsth temporary storage set of demand structures; if the clsth temporary storage set of demand structures does not contain the customized demand structure in the temporary intersection set of demand structures, then use the clsth temporary storage set of demand structures as the clsth demand structure deduplication set and directly execute Step 402;

[0105] If the clsth demand structure temporary storage set contains the customized demand structure in the demand structure temporary storage intersection set, then delete the customized demand structure in the demand structure temporary storage intersection set from the clsth demand structure temporary storage set to obtain the clsth demand structure deduplication set, and execute Step 402;

[0106] Step 402: Set cls = cls + 1. If cls is less than or equal to CLS, continue to Step 401; if cls is greater than CLS, continue to Step 403.

[0107] Step 403: Construct a total set of demand structures from the deduplicated set of CLS demand structures, count the number of each customized demand structure in the total set of demand structures, sort the total set of demand structures in descending order according to the number of customized demand structures, select the first N customized demand structures from the total set of demand structures after descending order; and construct the first N customized demand structures and the temporarily stored intersection of the demand structures into a lens customized material set.

[0108] The lens tuning module is used to perform lightweight tuning on the lens based on the lens customized material set and the lens customized demand data tree.

[0109] like Figure 4 As shown, the method for lightweight tuning of the lens based on the lens customized material set and the lens customized requirement data tree includes:

[0110] Step 500: The number of lens customized materials in the lens customized material set is recorded as DZSL, and the lens customized demand data tree and DZSL lens customized materials are respectively input into the material usage model to obtain the lens material usage range corresponding to DZSL lens customized materials; the lens material usage range is , The lower limit of the lens material usage range for the customized material of the dzslth lens, The upper limit of the lens material usage range for the customized material of the dzslth lens;

[0111] Initialize a lens material population, wherein the lens material population includes H candidate lens material solutions, wherein the candidate lens material solutions are lens material combinations that meet the lens customization requirement data tree, and the usage amounts of the lens materials in the lens material combinations are all within the corresponding lens material usage range; preset a maximum number of iterations to ZDCS, preset an initial value of zdcs to 1, and a value range of zdcs to 1 to ZDCS, and execute Step 501;

[0112] Step 501: perform lens material fitness evaluation on H candidate lens material solutions in the lens material population, obtain lens material fitness values corresponding to the H candidate lens material solutions, and execute Step 502;

[0113] Step 502: sort the H lens material fitness values in descending order, select the first G lens material fitness values from the H lens material fitness values after descending order, construct the lens material candidate solutions corresponding to the G lens material fitness values into a lens material elite population, and execute Step 503;

[0114] Step 503: Perform a mutation operation on the lens material elite population according to a preset method to obtain F mutated lens material candidate solutions, and add the F mutated lens material candidate solutions to the lens material elite population; overlay the lens material elite population onto the lens material population, set H = G + F, and execute Step 504;

[0115] Step 504: Let zdcs = zdcs + 1. If zdcs is less than or equal to ZDCS, continue to execute Step 501. If zdcs is greater than ZDCS, select the lens material candidate solution with the largest lens material fitness value from the lens material population as the optimal solution for lens material lightweighting.

[0116] The training method of the material usage model includes:

[0117] Preliminarily collecting a material usage dataset, the material usage dataset comprising Y groups of material usage data and lens material usage intervals corresponding to the Y groups of material usage data, where Y is a positive integer greater than 0, and the material usage data comprising a lens customization requirement data tree and lens customization materials; dividing the material usage dataset into a training set and a validation set, wherein the training set is used to train a material usage model, and the validation set is used to evaluate the generalization performance of the material usage model;

[0118] During the material usage model training process, minimizing the cross-entropy loss function is used as the optimization goal. An early stopping strategy is used to monitor the performance of the validation set, and the model performance is optimized by continuously adjusting the network parameters. When the prediction accuracy on the validation set reaches the preset accuracy, the material usage model is considered to have converged and training is stopped. The material usage model is trained using a deep neural network based on a multilayer perceptron.

[0119] The material usage data is converted into a high-dimensional feature vector; the input layer of the material usage model receives the high-dimensional feature vector, and the nonlinear relationship in the material usage data is extracted through the hidden layer. Finally, the output layer of the material usage model calculates the probability distribution of the lens material usage interval through the softmax activation function, and outputs the lens material usage interval corresponding to the maximum probability as the final prediction result.

[0120] The method for obtaining the lens material adaptability value includes:

[0121] ;

[0122] ;

[0123] ;

[0124] ;

[0125] in, is the lens material fitness value of the h-th lens material candidate solution, is the quality function of the h-th lens material candidate solution, is the optical performance function of the h-th lens material candidate solution, is the constraint penalty term, is a constant, is the hth candidate lens material solution The quality of the customized materials of each lens, For the The density of the material of each lens is customized, For the The reflectivity of each lens’ customized material, Customize the reflectivity in the lens requirement data tree. is the dzth constraint in the hth candidate solution for lens material, is the penalty coefficient, and is the fitness coefficient, DZ is the number of customized requirements, is the cosecant function, is the secant function.

[0126] The method of performing mutation operation on the lens material elite population according to a preset method to obtain F candidate solutions of mutated lens materials includes:

[0127] Presetting a first fitness threshold and a second fitness threshold, wherein the first fitness threshold is smaller than the second fitness threshold;

[0128] The lens material candidate solutions whose lens material fitness values in the lens material elite population are greater than or equal to the second fitness threshold are constructed into a material high fitness set; the lens material candidate solutions whose lens material fitness values in the lens material elite population are greater than or equal to the first fitness threshold and less than the second fitness threshold are constructed into a material medium fitness set; the lens material candidate solutions whose lens material fitness values in the lens material elite population are less than the first fitness threshold are constructed into a material low fitness set;

[0129] Compare the candidate solutions of lens materials in the material high fitness set with the candidate solutions of lens materials in the material high fitness set. times randomly crossed with each other, and we get Candidate solutions for lens materials The candidate solutions of lens materials are added to the material high fitness set;

[0130] Compare the candidate solutions of lens materials in the fitness set of materials with the candidate solutions of lens materials in the high fitness set of materials. times randomly crossed with each other, and we get candidate solutions of lens materials; compare the candidate solutions of lens materials in the fitness set of the material with the candidate solutions of lens materials in the fitness set of the material. times randomly crossed with each other, and we get Candidate solutions for lens materials; Candidate solutions for lens materials and The candidate solutions of lens materials are added to the fitness set of materials;

[0131] Compare the candidate solutions of lens materials in the material low fitness set with the candidate solutions of lens materials in the material high fitness set. times randomly crossed with each other, and we get candidate solutions for lens materials; perform random crossover among the low fitness set of materials, and obtain Candidate solutions for lens materials; Candidate solutions for lens materials and The candidate solutions of lens materials are added to the low fitness set of materials;

[0132] when When , the random crossover operation is stopped, and F candidate solutions of variant lens materials are obtained.

[0133] Example 2

[0134] See also Figure 3 As shown, this embodiment provides a lightweight structural design device for an optical lens, further comprising:

[0135] The threshold setting module is used to dynamically set the first fitness threshold and the second fitness threshold according to the lens customization requirement data tree and G lens material fitness values.

[0136] The method for dynamically setting a first fitness threshold and a second fitness threshold according to a lens customization requirement data tree and G lens material fitness values includes:

[0137] Constructing G lens material fitness values into a lens material fitness value set;

[0138] The lens customization requirement data tree and the lens material fitness value set are input into the threshold setting model to obtain a first fitness threshold and a second fitness threshold.

[0139] The training method of the threshold setting model includes:

[0140] Preliminarily collecting a threshold setting dataset, the threshold setting dataset comprising S groups of threshold setting data and first and second fitness thresholds corresponding to the S groups of threshold setting data, where S is a positive integer greater than 0, the threshold setting data comprising a lens customization requirement data tree and a set of lens material fitness values; dividing the threshold setting dataset into a training set and a validation set, the training set being used to learn threshold setting model parameters, and the validation set being used to evaluate the generalization ability of the threshold setting model to avoid overfitting;

[0141] During the training process of the threshold setting model, a dynamic learning rate adjustment strategy is combined with an early stopping mechanism to minimize the cross-entropy loss function as the optimization goal. When the performance of the validation set meets the preset requirements, training is automatically stopped to ensure the convergence effect of the threshold setting model. The threshold setting model is implemented based on the neural network model architecture. The neural network model consists of an input layer, a hidden layer, and an output layer. The input layer receives the threshold setting data and converts it into a high-dimensional feature vector. The hidden layer uses an activation function to extract the complex nonlinear pattern of the threshold setting data. The output layer calculates the probability distribution of the first fitness threshold and the second fitness threshold through the softmax activation function, and uses the first fitness threshold and the second fitness threshold corresponding to the maximum probability as the prediction results and outputs them.

[0142] It should be noted that this method makes full use of the multi-level demand information contained in the lens customization demand data tree, and combines it with the lens material fitness value set, so that the threshold setting can be accurately calculated based on the multi-dimensional demand characteristics and the distribution of lens material fitness values, avoiding the limitations of the traditional static threshold setting method and improving the accuracy and adaptability of the fitness threshold.

[0143] The construction of a set of lens material fitness values enables the threshold setting model to comprehensively analyze the fitness distribution of candidate materials, ensuring that the first fitness threshold and the second fitness threshold can be dynamically adjusted according to the global characteristics of the material fitness, thereby achieving efficient screening of lens materials with different performance requirements and improving the flexibility and specificity of material selection.

[0144] Based on the lens customization requirement data tree and the lens material fitness value set, the first fitness threshold and the second fitness threshold are dynamically set, which not only improves the accuracy and flexibility of lens material selection, but also enhances the adaptability to different customization requirements, ensuring the coordinated optimization of the lens's optical performance, mechanical performance and lightweight goals.

[0145] Example 3

[0146] See also Figure 2 As shown, this embodiment provides a lightweight structure design method for an optical lens, further comprising:

[0147] Obtaining lens customization demand data, wherein the lens customization demand data includes lens optical performance demand data, lens physical performance demand data, and customer demand budget;

[0148] Using feature extraction methods to process lens customization demand data to obtain a set of customized demand structures;

[0149] Construct a lens customization requirement data tree based on the customization requirement structure set;

[0150] Obtaining a lens customization material set according to the lens customization requirement data tree;

[0151] The lens is lightweight tuned according to the lens customized material set and lens customized demand data tree.

Claims

1. A lightweight structural design method for an optical lens, characterized in that: include: Obtaining lens customization demand data, wherein the lens customization demand data includes lens optical performance demand data, lens physical performance demand data, and customer demand budget; Using feature extraction methods to process lens customization demand data to obtain a set of customized demand structures; Construct a lens customization requirement data tree based on the customization requirement structure set; Obtaining a lens customization material set according to the lens customization requirement data tree; Perform lightweight tuning on the lens based on the lens customized material set and lens customized demand data tree; The method of constructing a lens customization requirement data tree according to a customization requirement structure set includes: The height of the lens customization requirement data tree is preset to SG, and there are SG-1 decreasing customization requirement priority thresholds. ;sg is the loop index variable; If sg is equal to 1, the customization requirement priority value is greater than or equal to The structure of is constructed as the first layer of the lens customization requirement data tree; if sg is greater than 1 and less than or equal to , set the customization requirement priority value to be greater than or equal to and less than The structure of is constructed as the sg layer of the lens customization requirement data tree; if sg is equal to SG, the customization requirement priority value is less than The structure of is constructed as the SG layer of the lens customization requirement data tree; and the lens customization requirement data tree is constructed layer by layer in a loop until it is completed; The method for obtaining a lens customized material set according to the lens customized requirement data tree includes: Based on the customization requirements of each layer in the lens customization requirement data tree, the corresponding lens applicable material set is constructed layer by layer. By intersecting and deduplicating the material sets of each layer and sorting and screening them according to the frequency of occurrence of the requirement structure, a lens customization material set that takes into account different priorities and hierarchical requirements is obtained.

2. The lightweight structure design method of an optical lens according to claim 1, characterized in that: Methods for lightweight lens tuning include: Step 500: The number of lens customized materials in the lens customized material set is recorded as DZSL, and the lens customized demand data tree and DZSL lens customized materials are respectively input into the material usage model to obtain the lens material usage interval corresponding to the DZSL lens customized materials; initialize the lens material population containing H lens material candidate solutions; set the maximum number of iterations to ZDCS, set zdcs=1, and the value range of zdcs is 1 to ZDCS; Step 501: Evaluate the lens material fitness values corresponding to H candidate lens material solutions in the lens material population; Step 502: Sort the fitness values of the H lens materials in descending order, and select the first G lens materials with the best fitness values to form an elite population of lens materials; Step 503: Perform mutation operations on the lens material elite population according to the preset method to obtain F mutated lens material candidate solutions and add them to the lens material elite population; overlay the lens material elite population onto the lens material population, and set H = G + F; Step 504: Let zdcs = zdcs + 1. If zdcs is less than or equal to ZDCS, continue executing Step 501 to Step 503. If zdcs is greater than ZDCS, select the lens material candidate solution with the largest lens material fitness value from the lens material population as the optimal solution for lens material lightweighting.

3. The lightweight structure design method of an optical lens according to claim 2, characterized in that: The method for obtaining F candidate solutions of variant lens materials includes: A first fitness threshold and a second fitness threshold are preset, and the first fitness threshold is smaller than the second fitness threshold; an elite population of lens materials is divided according to the first fitness threshold and the second fitness threshold to obtain a material high fitness set, a material medium fitness set, and a material low fitness set; Random crossover is performed in the material high fitness set to obtain Candidate solutions of lens materials are added to the material high fitness set; The lens material candidate solutions in the material fitness set are randomly crossed with the lens material candidate solutions in the material high fitness set to obtain The candidate solutions of lens materials are added to the fitness set in the material; random crossover is performed in the fitness set in the material to obtain Candidate solutions of lens materials are added to the fitness set of materials; The lens material candidate solutions in the material low fitness set are randomly crossed with the lens material candidate solutions in the material high fitness set to obtain The candidate solutions of lens materials are added to the material low fitness set; random crossover is performed in the material low fitness set to obtain Candidate solutions of lens materials are added to the material low fitness set; when When , the random crossover operation is stopped, and F candidate solutions of variant lens materials are obtained.

4. The lightweight structure design method of an optical lens according to claim 3, characterized in that: The method for constructing the lens customization requirement data tree includes: Step 200: The height of the preset lens customization requirement data tree is , An integer greater than 0, preset Customized requirement priority thresholds, The priority threshold for customized requirements is , ; Let sg = 1, the value range of sg is 1 to SG; Step 201: If sg is equal to 1, then the customized requirement priority value in the customized requirement structure set is greater than or equal to The customized requirement structure is constructed into the sg-th layer of the lens customized requirement data tree; If sg is greater than 1 and less than or equal to , then the customized requirement priority value in the customized requirement structure set is greater than or equal to and less than The customized requirement structure is constructed into the sg-th layer of the lens customized requirement data tree; If sg is equal to , then the customized requirement priority value in the customized requirement structure set is less than The customized requirement structure is constructed into the sg-th layer of the lens customized requirement data tree; Step 202: Let sg = sg + 1. If sg is less than or equal to SG, continue to execute Step 201; if sg is greater than SG, obtain the lens customization requirement data tree and end the current process.

5. The lightweight structure design method of an optical lens according to claim 4, characterized in that: The method for obtaining the customized requirement structure set includes: Step 100: record the number of customization requirements in the lens customization requirement data as DZ, set dz=1, and the value range of dz is 1 to DZ; construct DZ customization requirements into a lens customization requirement set; Step 101: Input the dzth customization requirement in the lens customization requirement set into the requirement priority value model to obtain the corresponding customization requirement priority value; Step 102: Construct the dzth customized requirement and the customized requirement priority value into a corresponding customized requirement structure; Step 103: Add the dzth customized requirement structure to the customized requirement structure collection; Step 104: Let dz = dz + 1. If dz is less than or equal to DZ, continue executing Step 101 to Step 103. If dz is greater than DZ, obtain the customized requirement structure set and end the current process.

6. The lightweight structure design method of an optical lens according to claim 5, characterized in that: The method for obtaining a lens customized material set according to the lens customized requirement data tree includes: Step 300: The material selection layer number of the lens customization requirement data tree is CLS, and the value range of CLS is 1 to , let cls=1, the value range of cls is 1 to CLS; build a temporary storage set of CLS demand structures; Step 301: Add lens customization requirement data tree The customized requirement structure is added to the cls-th requirement structure temporary storage collection, The number of customized requirement structures at the cls-th layer; if cls is greater than 1, the customized requirement structure in the cls-1-th requirement structure temporary storage set is added to the cls-th requirement structure temporary storage set; Step 302: Input the temporary storage set of the cls-th requirement structure into the lens material model to obtain the cls-th lens applicable material set; Step 303: Let cls = cls + 1. If cls is less than or equal to CLS, continue executing Step 301 to Step 302. If cls is greater than CLS, obtain CLS lens-applicable material sets, analyze and process the CLS lens-applicable material sets according to a preset method, and obtain a lens customized material set.

7. The lightweight structure design method of an optical lens according to claim 6, characterized in that: The method for analyzing and processing the CLS lens applicable material set according to the preset method to obtain the lens customized material set includes: Step 400: Take the intersection of CLS demand structure temporary storage sets to obtain the demand structure temporary storage intersection; let cls=1; Step 401: Obtain the clsth temporary storage set of demand structures; if the clsth temporary storage set of demand structures does not contain the customized demand structure in the temporary intersection set of demand structures, then use the clsth temporary storage set of demand structures as the clsth demand structure deduplication set and directly execute Step 402; If the clsth demand structure temporary storage set contains the customized demand structure in the demand structure temporary storage intersection set, then delete the customized demand structure in the demand structure temporary storage intersection set from the clsth demand structure temporary storage set to obtain the clsth demand structure deduplication set, and execute Step 402; Step 402: Set cls = cls + 1. If cls is less than or equal to CLS, continue to Step 401; if cls is greater than CLS, continue to Step 403. Step 403: Construct a total set of demand structures from the deduplicated set of CLS demand structures, count the number of each customized demand structure in the total set of demand structures, sort the total set of demand structures in descending order according to the number of customized demand structures, select the first N customized demand structures from the total set of demand structures after descending order; and construct the first N customized demand structures and the temporarily stored intersection of the demand structures into a lens customized material set.

8. The lightweight structure design method of an optical lens according to claim 7, characterized in that: The training method of the material usage model includes: Preliminarily collecting a material usage dataset, the material usage dataset comprising Y groups of material usage data and lens material usage intervals corresponding to the Y groups of material usage data, where Y is a positive integer greater than 0, and the material usage data comprising a lens customization requirement data tree and lens customization materials; dividing the material usage dataset into a training set and a validation set, wherein the training set is used to train a material usage model, and the validation set is used to evaluate the generalization performance of the material usage model; During the material usage model training process, minimizing the cross-entropy loss function is used as the optimization goal. An early stopping strategy is used to monitor the performance of the validation set, and the model performance is optimized by continuously adjusting the network parameters. When the prediction accuracy on the validation set reaches the preset accuracy, training is stopped. The material usage model is trained using a deep neural network based on a multilayer perceptron. The material usage data is converted into a high-dimensional feature vector. The input layer of the material usage model receives the high-dimensional feature vector, and the hidden layer extracts the nonlinear relationship in the material usage data. Finally, the output layer of the material usage model calculates the probability distribution of the lens material usage interval through the softmax activation function, and outputs the lens material usage interval corresponding to the maximum probability as the final prediction result. The lens material model is obtained by the same training method as the material dosage model.

9. The lightweight structure design method of an optical lens according to claim 8, characterized in that: The training method of the demand priority value model includes: Pre-collect a demand priority value dataset, the demand priority value dataset including Q groups of demand priority value data and customized demand priority values corresponding to the Q groups of demand priority value data, where Q is a positive integer greater than 0, and the demand priority value data includes customized demands; divide the demand priority value dataset into a training set and a validation set, the training set being used to learn demand priority value model parameters, and the validation set being used to evaluate the generalization ability of the demand priority value model to avoid overfitting; During the training process of the demand priority value model, a dynamic learning rate adjustment strategy is combined with an early stopping mechanism to minimize the cross-entropy loss function as the optimization goal. When the performance of the validation set meets the preset requirements, training is automatically stopped to ensure the convergence of the demand priority value model. The demand priority value model is implemented based on the neural network model architecture. The neural network model consists of an input layer, a hidden layer, and an output layer. The input layer receives the demand priority value data and converts it into a high-dimensional feature vector. The hidden layer uses an activation function to extract the nonlinear pattern of the demand priority value data. The output layer calculates the probability distribution of the customized demand priority value through the softmax activation function, and uses the customized demand priority value corresponding to the maximum probability as the prediction result and outputs it.

10. A lightweight structure design device for an optical lens, implementing the lightweight structure design method for an optical lens according to any one of claims 1 to 9, characterized in that: include: A demand collection module is used to obtain lens customization demand data, wherein the lens customization demand data includes lens optical performance demand data, lens physical performance demand data and customer demand budget; A first processing module is used to process the lens customization requirement data using a feature extraction method to obtain a customization requirement structure set; A second processing module is used to construct a lens customization requirement data tree according to the customization requirement structure set; A material selection module is used to obtain a lens customization material set based on the lens customization requirement data tree; The lens tuning module is used to perform lightweight tuning on the lens based on the lens customized material set and the lens customized demand data tree.

Images