Shadowless lamp quality control system based on digital processing

Abstract

The invention provides a shadowless lamp quality control system based on digital processing, and relates to the technical field of intelligent manufacturing. A polishing area division module; a polishing quality simulation detection module; a quality deviation analysis module; the polishing parameter optimization module is used for carrying out polishing parameter optimization based on a polishing processing twin model and a predetermined polishing evaluation function so as to meet the polishing workload of the second stage and generate a first optimized polishing parameter; and the polishing control module is used for executing polishing control of the second stage according to the second starting node and the first optimized polishing parameter. The technical problems that due to the fact that machining defects in the reflector polishing process cannot be accurately detected and corrected in time, the overall polishing precision and quality are poor, and the production quality of operating shadowless lamp products is poor can be solved, the polishing machining defects can be effectively corrected in time in a targeted mode, and the production efficiency is improved. And the effect of improving the polishing precision and the polishing quality of the reflector is achieved.

Description

Technical Field

[0001] The present application relates to the field of intelligent manufacturing technology, and in particular to a shadowless lamp quality control system based on digital processing. Background Art

[0002] The integral reflective surgical shadowless lamp is a surgical lighting device that uses an integral reflective optical system. It can provide uniform, shadowless lighting to help doctors clearly see the surgical site during surgery. The integral reflector is the core component of the surgical shadowless lamp, which consists of one or more reflectors to reflect and focus the light source to provide uniform lighting in the surgical area.

[0003] At present, during the production and processing of existing integral reflective surgical shadowless lamps, it is impossible to accurately detect and promptly correct processing defects that occur during the polishing process of the reflector, resulting in poor overall polishing accuracy and polishing quality of the reflector, which ultimately causes technical problems such as poor production quality of surgical shadowless lamp products. Summary of the invention

[0004] The purpose of this application is to provide a shadowless lamp quality control system based on digital processing, so as to solve the technical problem that during the production and processing of the existing integral reflective surgical shadowless lamp, the processing defects occurring during the polishing process of the reflector cannot be accurately detected and corrected in time, resulting in poor overall polishing accuracy and polishing quality of the reflector, and ultimately causing poor production quality of surgical shadowless lamp products.

[0005] In view of the above problems, the present application provides a shadowless lamp quality control system based on digital processing, wherein the system includes: a polishing index division module, which is used to read the polishing index and polishing process of the target reflector, determine multiple polishing stages based on the polishing process, divide the polishing index according to the multiple polishing stages, and obtain a stage polishing index set; a polishing area division module, which is used to divide the reflector to be polished into areas based on the single polishing area of ​​the grinding wheel, and determine multiple polishing sub-areas, wherein each polishing sub-area has a unique serial number mark; a polishing quality simulation detection module, which is used to perform a polishing operation on a first sub-area based on a predetermined polishing path, and after the operation is completed, perform image acquisition on the first sub-area through an optical microscope, and perform polishing quality simulation detection based on the microscopic image of the first sub-area to obtain a first stage detection result, wherein the first sub-area is the multiple polishing areas. For any one of the photon areas, one polishing operation is a polishing operation of the first stage; a quality deviation analysis module is used to select the second stage polishing index from the polishing index set of the stage, perform quality deviation analysis on the first stage detection result according to the second stage polishing index, and set the deviation analysis result as the second stage polishing workload; a polishing parameter optimization module is used to optimize the polishing parameters based on the polishing process twin model and the predetermined polishing evaluation function, with the purpose of meeting the second stage polishing workload, and generate the first optimized polishing parameters; a polishing control module is used to determine the second starting node according to the first serial number of the first sub-area, feed back the second starting node and the first optimized polishing parameter to the polishing control unit, execute the polishing control of the second stage of the first sub-area, until the entire polishing process is completed, wherein the second starting node is the starting time node of the second stage.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: By reading the polishing index and polishing process of the target reflector, a plurality of polishing stages are determined based on the polishing process, and the polishing index is divided according to the plurality of polishing stages to obtain a stage polishing index set; then, based on the single polishing area of ​​the grinding wheel, the reflector to be polished is divided into regions to determine a plurality of polishing sub-regions, wherein each polishing sub-region has a unique serial number mark; further, based on a predetermined polishing path, a polishing operation is performed on the first sub-region, and after the operation is completed, an image of the first sub-region is captured by an optical microscope, and a polishing quality simulation test is performed based on the microscopic image of the first sub-region to obtain a first-stage test result, wherein the first sub-region is any one of the plurality of polishing sub-regions, and a single polishing operation is the first stage. Polishing operation; then, selecting the second-stage polishing index from the stage polishing index set, performing quality deviation analysis on the first-stage detection result according to the second-stage polishing index, and setting the deviation analysis result as the second-stage polishing workload; then, based on the polishing processing twin model and the predetermined polishing evaluation function, optimizing the polishing parameters for the purpose of meeting the second-stage polishing workload, and generating the first optimized polishing parameters; finally, determining the second starting node according to the first serial number of the first sub-area, feeding back the second starting node and the first optimized polishing parameters to the polishing control unit, executing the polishing control of the second stage of the first sub-area, until the entire polishing process is completed, wherein the second starting node is the starting time node of the second stage. That is to say, by dividing the polishing index according to multiple polishing stages, a stage polishing index set is obtained; on the other hand, the single polishing area of ​​the grinding wheel is used as a reference to divide the reflector to be polished into regions to determine multiple polishing sub-regions; then, after a polishing operation is completed, a polishing quality simulation test is performed based on the microscopic image of the first sub-region to obtain the first stage test result, and then the quality deviation analysis of the first stage test result is performed according to the second stage polishing index, and the deviation analysis result is set as the second stage polishing workload; further based on the polishing processing twin model and the predetermined polishing evaluation function, the polishing parameter optimization is performed to meet the second stage polishing workload, and the first optimized polishing parameter is generated; finally, the second starting node is determined based on the first serial number of the first sub-region, and the polishing control of the second stage of the first sub-region is performed according to the second starting node and the first optimized polishing parameter until the entire polishing process is completed. The precision and accuracy of the polishing defect detection during the polishing process of the reflector can be improved, so that the processing defects can be timely and effectively corrected, so as to improve the polishing accuracy and polishing quality of the reflector and meet the technical effect of the production requirements of the surgical shadowless lamp product.

[0007] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0009] Figure 1 This is a structural schematic diagram of a shadowless lamp quality control system based on digital processing in this application; Figure 2 This is a flow chart of obtaining the first-stage detection results in a shadowless lamp quality control system based on digital processing in the present application.

[0010] Description of reference numerals: Polishing index division module 11, polishing area division module 12, polishing quality simulation detection module 13, quality deviation analysis module 14, polishing parameter optimization module 15, polishing control module 16. DETAILED DESCRIPTION

[0011] This application provides a shadowless lamp quality control system based on digital processing, which solves the technical problem that during the production and processing of the existing integral reflective surgical shadowless lamp, the processing defects that occur during the polishing process of the reflector cannot be accurately detected and corrected in time, resulting in poor overall polishing accuracy and polishing quality of the reflector, and ultimately causing poor production quality of surgical shadowless lamp products. The precision and accuracy of polishing defect detection during the polishing process of the reflector can be improved, so that the processing defects can be targeted and effectively corrected in time, achieving the technical effect of improving the polishing accuracy and polishing quality of the reflector and meeting the production requirements of surgical shadowless lamp products.

[0012] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0013] For examples, please see the attached Figure 1 The present application provides a shadowless lamp quality control system based on digital processing, including: The polishing index division module 11 is used to read the polishing index and polishing process of the target reflector, determine multiple polishing stages based on the polishing process, divide the polishing index according to the multiple polishing stages, and obtain a stage polishing index set.

[0014] Specifically, the integral reflective surgical shadowless lamp is a surgical lighting device that uses an integral reflective optical system. It can provide uniform and shadowless lighting effects. The integral reflector is the core component of the surgical shadowless lamp. This application is used to optimize the polishing process of the integral reflector to achieve the purpose of improving the polishing accuracy and polishing quality of the reflector. First, read the polishing index and polishing process of the target reflector, where the polishing index refers to the expected processing index of the target reflector, including surface roughness, reflectivity, and micro-defect constraints, etc., which can be set according to actual conditions; the polishing process refers to the entire polishing process of the target reflector polishing process. Then, based on the characteristics and experience of the polishing process, determine the key steps and stages in the polishing process, which include rough polishing, medium polishing, fine polishing, etc.

[0015] The polishing indicators are further divided according to multiple polishing stages, that is, the polishing indicators are divided according to the expected goals of each polishing stage to obtain the stage polishing indicators corresponding to each polishing stage, that is, each polishing stage has a set of specific polishing indicators, which together define the polishing goals of this stage, and obtain the stage polishing indicator set.

[0016] The polishing area division module 12 is used to divide the reflector to be polished into areas based on the single polishing area of ​​the grinding wheel, and determine a plurality of polishing sub-areas, wherein each polishing sub-area has a unique serial number mark.

[0017] Specifically, first, according to the size of the grinding wheel and the polishing process, determine the area of ​​the reflector that the grinding wheel can cover in one polishing operation. This area can be circular, square or other geometric shapes, depending on the design of the grinding wheel and the polishing requirements. Then, based on the single polishing area of ​​the grinding wheel, the reflector to be polished is divided into regions, that is, the surface of the reflector is divided into multiple equal polishing sub-regions to ensure that each sub-region can be fully covered by the grinding wheel, and the size and shape of each polishing sub-region should match the single polishing area of ​​the grinding wheel. Finally, a unique serial number or mark is assigned to each polishing sub-region for identification and management during the polishing process. These marks can be numbers, letters or symbols to ensure that each sub-region has a clear identification. In this way, the uniformity and efficiency of the polishing process can be ensured, wherein each sub-region is divided according to the single polishing area of ​​the grinding wheel, which ensures that each region is properly polished and helps to improve the polishing quality of the reflector.

[0018] The polishing quality simulation detection module 13 is used to perform a polishing operation on the first sub-area based on a predetermined polishing path, collect images of the first sub-area through an optical microscope after the operation is completed, and perform a polishing quality simulation detection based on the microscopic image of the first sub-area to obtain a first-stage detection result, wherein the first sub-area is any one of the multiple polishing sub-areas, and the one polishing operation is a first-stage polishing operation.

[0019] Specifically, first, according to a predetermined polishing path and process parameters, a polishing operation is performed on the first sub-region, the first sub-region is any one of the multiple polishing sub-regions, and the one polishing operation is a polishing operation of the first stage, and the first stage is the first processing stage of multiple polishing stages. Then, after the one polishing operation of the first sub-region is completed, an optical microscope is used to collect images of the polished first sub-region, wherein appropriate magnification and lighting conditions are selected to ensure that the details of the polishing region can be clearly observed, and a microscopic image of the first sub-region is obtained.

[0020] Further, artificial intelligence methods such as convolutional neural networks, BP neural networks, and digital twins are used to simulate the polishing quality of the microscopic images of the first sub-region, such as: training a convolutional neural network model for surface feature extraction; predicting the polishing state based on the digital twin model; obtaining the first stage test results, which include the predicted surface roughness, predicted reflectivity, and predicted microscopic defect characteristics after the first stage of processing. By using artificial intelligence methods such as convolutional neural networks, BP neural networks, and digital twins to simulate the polishing quality of the microscopic images of the first sub-region, the intelligence and automation of polishing quality detection can be improved, while the efficiency and accuracy of detection can be improved, defects in the polishing process can be discovered in a timely manner, and a basis for subsequent polishing optimization control can be provided.

[0021] The quality deviation analysis module 14 is used to select the second stage polishing index from the stage polishing index set, perform quality deviation analysis on the first stage detection result according to the second stage polishing index, and set the deviation analysis result as the second stage polishing workload.

[0022] Specifically, first, the second stage polishing index is selected from the stage polishing index set, wherein the second stage is the next polishing stage adjacent to the first stage; then, the quality deviation of the first stage detection result is performed according to the second stage polishing index, such as: surface roughness deviation calculation, etc.; the deviation calculation result is obtained, wherein the deviation calculation result is the difference between the second stage polishing index and the first stage detection result; then the deviation analysis result is set as the second stage polishing workload. By setting the next stage polishing workload based on the deviation calculation and analysis results, the processing defects of the previous polishing stage can be corrected in a timely and effective manner, thereby realizing accurate control and optimization of the overall polishing process, and improving the overall polishing accuracy and polishing quality.

[0023] The polishing parameter optimization module 15 is used to optimize the polishing parameters based on the polishing process twin model and the predetermined polishing evaluation function to meet the second stage polishing workload and generate the first optimized polishing parameters.

[0024] Specifically, digital twin technology is a virtual model based on a physical entity or system. Through real-time data synchronization and simulation, it can realize the state monitoring, performance evaluation and optimization control of the entity or system. Based on digital twin technology, simulation modeling is carried out according to the attribute information of the polishing equipment and the material properties of the reflector, and a polishing processing twin model is built. Through this polishing processing twin model based on digital twin technology, virtual simulation and prediction of the polishing process can be realized. Create an evaluation function, which will be used to evaluate the polishing quality under different polishing parameter combinations. The evaluation function includes key indicators such as surface roughness, reflectivity, and the number of micro defects.

[0025] Then, based on the polishing process twin model and the predetermined polishing evaluation function, the polishing parameters are optimized for the purpose of satisfying the polishing workload of the second stage, wherein the polishing parameters include polishing speed, polishing pressure and polishing time. For example, the polishing parameters can be optimized by using an optimization algorithm. The goal of the optimization algorithm is to maximize the polishing evaluation function to meet the requirements of the polishing workload of the second stage. The first optimized polishing parameters are obtained according to the optimization results, wherein the first optimized polishing parameters are used to guide the polishing operation of the second stage to improve the polishing quality and production efficiency.

[0026] The polishing control module 16 is used to determine the second starting node according to the first serial number of the first sub-area, feed back the second starting node and the first optimized polishing parameter to the polishing control unit, and execute the polishing control of the second stage of the first sub-area until the entire polishing process is completed, wherein the second starting node is the starting time node of the second stage.

[0027] Specifically, first, the starting time node analysis of the second stage is performed according to the first serial number of the first sub-area. For example, the second starting node can be obtained by superimposing the current time node and the polishing time of the remaining sub-areas before the first sub-area, wherein the second starting node is the starting time node of the second stage. Then, the second starting node and the first optimized polishing parameter are sent to the polishing control unit, wherein the polishing control unit is an integrated system for controlling the working state and parameter settings of the polishing equipment. Then, the polishing control unit performs the polishing control of the second stage of the first sub-area according to the feedback parameters and the starting node. For example, the control unit adjusts the parameter settings of the polishing equipment, such as polishing speed, polishing pressure, polishing time, etc., to achieve the expected polishing effect. Repeat the above steps to perform polishing optimization control on each polishing sub-area until the entire polishing process is completed.

[0028] A shadowless lamp quality control system based on digital processing is provided, comprising: a polishing index division module, which is used to read the polishing index and polishing process of a target reflector, determine multiple polishing stages based on the polishing process, divide the polishing index according to the multiple polishing stages, and obtain a stage polishing index set; a polishing area division module, which is used to divide the reflector to be polished into areas based on a single polishing area of ​​a grinding wheel, and determine multiple polishing sub-areas, wherein each polishing sub-area has a unique serial number mark; a polishing quality simulation detection module, which is used to perform a polishing operation on a first sub-area based on a predetermined polishing path, collect images of the first sub-area through an optical microscope after the operation is completed, and perform a polishing quality simulation detection based on the microscopic image of the first sub-area to obtain a first-stage detection result, wherein the first sub-area is any of the multiple polishing sub-areas. One, a polishing operation is a polishing operation of the first stage; a quality deviation analysis module, used to select the second stage polishing index from the polishing index set of the stage, perform quality deviation analysis on the first stage detection result according to the second stage polishing index, and set the deviation analysis result as the second stage polishing workload; a polishing parameter optimization module, used to optimize the polishing parameters based on the polishing processing twin model and the predetermined polishing evaluation function, with the purpose of meeting the second stage polishing workload, and generate the first optimized polishing parameters; a polishing control module, used to determine the second starting node according to the first serial number of the first sub-area, feed back the second starting node and the first optimized polishing parameter to the polishing control unit, execute the polishing control of the second stage of the first sub-area, until the entire polishing process is completed, wherein the second starting node is the starting time node of the second stage. It can solve the technical problem that during the production and processing of the existing integral reflective surgical shadowless lamp, the overall polishing accuracy and polishing quality of the reflector are poor due to the inability to accurately detect and timely correct the processing defects that occur during the polishing process of the reflector, which ultimately causes the production quality of the surgical shadowless lamp product to be poor. By dividing the polishing indicators according to multiple polishing stages, a stage polishing indicator set is obtained; on the other hand, based on the single polishing area of ​​the grinding wheel, the reflector to be polished is divided into regions to determine multiple polishing sub-regions; then after one polishing operation is completed, a polishing quality simulation test is performed based on the microscopic image of the first sub-region to obtain the first-stage test result, and then a quality deviation analysis is performed on the first-stage test result according to the second-stage polishing indicator, and the deviation analysis result is set as the second-stage polishing workload; further based on the polishing processing twin model and the predetermined polishing evaluation function, the polishing parameters are optimized for the purpose of meeting the second-stage polishing workload, and the first optimized polishing parameters are generated; finally, the second starting node is determined based on the first serial number of the first sub-region, and the second-stage polishing control of the first sub-region is executed according to the second starting node and the first optimized polishing parameter until the entire polishing process is completed.The precision and accuracy of polishing defect detection during the polishing process of the reflector can be improved, so that the processing defects can be timely and effectively corrected in a targeted manner, thereby achieving the technical effect of improving the polishing accuracy and polishing quality of the reflector and meeting the production requirements of surgical shadowless lamp products.

[0029] Furthermore, the polishing index division module 11 is also used for: The polishing indicators include surface roughness, reflectivity and micro defect constraints.

[0030] Specifically, the polishing indicators of the target reflector include surface roughness, reflectivity and micro-defect constraints, which can be set by technical personnel in this field according to actual processing requirements. Surface roughness refers to the degree of microscopic unevenness on the surface of the optical element, which directly affects the reflection and scattering of light and is an important indicator for evaluating polishing quality; reflectivity refers to the ability of the optical element to reflect light. The higher the reflectivity, the better the performance of the optical element, which is usually used to evaluate the optical properties of the optical element; microscopic defects include scratches, pits, etc. These defects will affect the optical properties and mechanical strength of the optical element, and therefore need to be strictly controlled.

[0031] Further, as attached Figure 2 As shown, the polishing quality simulation detection module 13 is also used for: The microscopic image of the first sub-area is input into a feature extraction channel, and a polishing feature set is output, wherein the polishing feature set includes a particle feature set, a ripple feature set, a texture feature set, a scratch feature set and a dent feature set, and the feature extraction channel is constructed based on a convolutional neural network; the particle feature set, the ripple feature set and the texture feature set are input into a surface evaluation model, and a predicted roughness is output; reflectivity is predicted based on the scratch feature set, the dent feature set and the predicted roughness, and the predicted reflectivity is output; the scratch feature set, the dent feature set, the predicted roughness and the predicted reflectivity are used as the first stage detection results.

[0032] Specifically, a convolutional neural network is a deep learning model that can automatically learn features in an image and extract them. First, a feature extraction channel is constructed based on a convolutional neural network, wherein the extracted features of the feature extraction channel include particle features, ripple features, texture features, scratch features, and dent features; then, sample data is retrieved based on the extracted features, and supervised training is performed on the feature extraction channel to obtain a feature extraction channel that meets the expected indicators. Then, the microscopic image of the first sub-area is input into the feature extraction channel to automatically identify and classify microscopic defects in the polishing process to obtain a polishing feature set, wherein the polishing feature set includes a particle feature set, a ripple feature set, a texture feature set, a scratch feature set, and a dent feature set.

[0033] BP neural network is a multi-layer feedforward neural network, which is trained by error back propagation algorithm. A surface evaluation model is constructed based on BP neural network. The surface evaluation model is a neural network model that can be iteratively optimized in machine learning, which is used to predict surface roughness according to polishing features; then the particle feature set, ripple feature set and texture feature set are input into the surface evaluation model, and the predicted roughness is output. On the other hand, based on the target light source information, reflector material properties, scratch feature set, dent feature set and predicted roughness, reflectivity simulation prediction is performed to obtain predicted reflectivity. Finally, the scratch feature set, the dent feature set, the predicted roughness and the predicted reflectivity are used as the first stage detection results.

[0034] Furthermore, the polishing quality simulation detection module 13 is also used for: Acquire the material properties of the reflector, and use the material properties of the reflector as constraints to retrieve a sample data set through an Internet search, wherein the sample data includes a sample particle feature set, a sample corrugation feature set, a sample texture feature set, and a sample surface roughness; divide the sample data set into M equal parts, and select M times with replacement from the M data sets to construct a first data set, and continue to iterate and select M times to obtain M data sets; use the M data sets to perform supervised training and cross-validation on the BP neural network to obtain M surface evaluation units that meet the expected convergence constraints, and build a surface evaluation model based on the M surface evaluation units, wherein the output of the surface evaluation model is the mode of the output results of the M surface evaluation units.

[0035] Specifically, first, the reflector material properties are obtained, wherein the reflector material properties include material type, size information, surface structure and other features; then, the reflector material properties are used as constraints, and a sample data set is retrieved online based on big data technology, wherein the sample data includes a sample particle feature set, a sample ripple feature set, a sample texture feature set and a sample surface roughness, and the sample particle feature set, the sample ripple feature set, the sample texture feature set and the sample surface roughness have a corresponding relationship. Then, the sample data set is divided into M equal parts, ensuring that the size and structure of each data set are as consistent as possible to ensure the representativeness of each data set, and M data sets are obtained, and further, M data sets are selected with replacement from the M data sets M times, that is, each time a data set is selected, a data set is randomly selected from the M data sets, and then replaced to construct the first data set, and then the above selection process is repeated, each time M times, M different data sets are obtained.

[0036] Based on the BP neural network, an initial surface evaluation unit is constructed, wherein the input of the initial surface evaluation unit is a particle feature set, a ripple feature set and a texture feature set, and the output is surface roughness; then, the BP neural network is supervised and cross-validated using M data sets until M surface evaluation units that meet the expected convergence constraints are obtained, wherein the expected convergence constraints are model training requirements, which can be set according to actual conditions, wherein the supervised training and cross-validation process is to use the data set for supervised training, and adjust the weights and biases of the network to minimize the prediction error until the preset number of training times is met; then, the data set is exchanged, and different data sets are used for verification training until the expected convergence constraints are met. Finally, a surface evaluation model is built based on M surface evaluation units, wherein the output of the surface evaluation model is the mode of the output results of the M surface evaluation units, which refers to the value that appears the most times in a set of data, and it can reflect the common prediction results of most surface evaluation units. In this way, a surface evaluation model based on M surface evaluation units can be constructed, which can integrate the information of multiple evaluation units, thereby improving the accuracy and robustness of the prediction.

[0037] Furthermore, the polishing quality simulation detection module 13 is also used for: Obtain target light source information, wherein the target light source information includes light source brightness, light source color temperature, spectral distribution and luminous flux; based on the target light source information, the reflector material properties, the scratch feature set, the dent feature set and the predicted roughness, perform N simulated reflectivity tests in a simulation platform to obtain N reflectivities, and calculate the reflectivity mean; calculate the deviation values ​​of the N reflectivities and the reflectivity mean in turn, select the reflectivity with a deviation value less than a predetermined deviation threshold as the standard reflectivity, calculate the mean of multiple standard reflectivities, and set the standard reflectivity mean as the predicted reflectivity.

[0038] Specifically, the target light source information of the target surgical shadowless lamp product is obtained, wherein the target light source information includes light source brightness, light source color temperature, spectral distribution and luminous flux. Then, based on the target light source information, the reflector material properties, the scratch feature set, the dent feature set and the predicted roughness, N simulated reflectivity tests are performed in the simulation platform. First, a digital twin model is created on the simulation platform, which accurately replicates the optical components in the actual polishing process. The digital twin model should include key parameters such as the size, shape, material properties, surface roughness and microscopic defects of the components; then, according to the light source characteristics in actual applications, the target light source information, reflector material property information, scratch feature set, dent feature set and predicted roughness are input into the simulation platform; and N simulated reflectivity tests are further performed in the simulation platform. In each test, according to the input parameters, the interaction between the incident light and the reflector is simulated, the distribution and intensity of the reflected light are calculated, N reflectivities are obtained, and the mean value of the N reflectivities is calculated to obtain the mean reflectivity.

[0039] The deviation values ​​of N reflectivities and the mean reflectivity are further calculated in sequence to obtain N deviation values, and the N deviation values ​​are judged according to a predetermined deviation threshold, wherein the predetermined deviation threshold can be set according to actual conditions to eliminate abnormal values ​​in the simulation test process and improve the accuracy of the test reflectivity data. The reflectivity with a deviation value less than the predetermined deviation threshold is selected as the standard reflectivity, and then the mean of multiple standard reflectivities is calculated, and the mean of the standard reflectivity is set as the predicted reflectivity, so as to improve the accuracy and reliability of the predicted reflectivity setting.

[0040] Furthermore, the polishing parameter optimization module 15 is also used for: Based on the digital twin technology, simulation modeling is performed according to the attribute information of the polishing equipment and the material properties of the reflector, and a polishing process twin model is built; based on the polishing process twin model and the predetermined polishing evaluation function, the polishing parameters are optimized with the constraint of satisfying the polishing workload of the second stage, and the first optimized polishing parameters are obtained, wherein the polishing parameters include polishing speed, polishing pressure and polishing time.

[0041] Specifically, based on the digital twin technology, according to the property information of the polishing equipment, a virtual model of the polishing equipment is created using computer-aided design (CAD) software; according to the properties of the reflector material, a virtual model of the reflector material is created using computer-aided engineering (CAE) software; then the virtual model of the polishing equipment is combined with the virtual model of the reflector material to form a twin model of the polishing process. Further, based on the twin model of the polishing process, simulated polishing is performed, the fitness of the polishing parameters is evaluated based on a predetermined polishing evaluation function, and the polishing parameters are optimized using an optimization algorithm, wherein the polishing parameters include polishing speed, polishing pressure and polishing time, and the first optimized polishing parameters are obtained according to the optimization results.

[0042] Furthermore, the polishing parameter optimization module 15 is also used for: The expression of the predetermined polishing evaluation function is: ; in, is the fitness of the i-th polishing parameter, is the first weight, is the second weight, is the third weight, is the fourth weight, is the fifth weight, is the simulated surface roughness after the i-th polishing parameter processing, is the surface roughness of the second stage polishing workload, is the simulated reflectivity after the i-th polishing parameter processing, is the reflectivity of the second stage polishing workload, is the polishing time of the i-th polishing parameter, is the total amount of defect features after processing with the i-th polishing parameter, is the energy consumption of the i-th polishing parameter.

[0043] Specifically, in the predetermined polishing evaluation function, is the fitness of the i-th polishing parameter, the i-th polishing parameter is any polishing parameter, wherein the greater the fitness, the better the overall polishing quality; is the first weight, is the second weight, is the third weight, is the fourth weight, is the fifth weight, wherein the sum of the first weight, the second weight, the third weight, the fourth weight and the fifth weight is 1, and the specific weight value is set based on the influence of the indicator on the overall polishing quality. The greater the influence, the greater the corresponding weight; is the simulated surface roughness after the i-th polishing parameter processing, is the surface roughness of the second stage polishing workload, is the simulated reflectivity after the i-th polishing parameter processing, is the reflectivity of the second stage polishing workload, is the polishing time of the i-th polishing parameter, is the total amount of defect features after processing with the i-th polishing parameter, is the energy consumption of the i-th polishing parameter.

[0044] Furthermore, the polishing parameter optimization module 15 is also used for: Obtain a rated threshold value of a polishing parameter, wherein the rated threshold value of the polishing parameter includes a polishing speed threshold value, a polishing pressure threshold value, and a polishing time threshold value; randomly select a parameter from the polishing speed threshold value, the polishing pressure threshold value, and the polishing time threshold value to combine, generate multiple initial polishing parameters, and simulate polishing the multiple initial polishing parameters through a polishing process twin model to obtain multiple simulated polishing results; evaluate the multiple simulated polishing results based on the predetermined polishing evaluation function to obtain multiple fitnesses, set the initial polishing parameters as initial solutions, arrange the multiple initial solutions from large to small according to the fitnesses, and generate an initial solution sequence; set the first X initial solutions of the initial solution sequence as the first solution, and the last Y initial solutions as the last solution, and take the X first solutions as the center, and perform an evaluation on the Y last solutions. The solutions are randomly clustered to obtain X domains, where Y is an integer multiple of X, and the number of tail solutions in each domain is the same; within the X domains, the first solution in the domain is taken as the optimization direction, and the tail solutions in the domain are optimized once according to the preset optimization step length to obtain X update domains, where if the tail solution after adjustment does not meet the rated threshold of the polishing parameter, no adjustment is performed; X update domains are identified, and if the fitness of the tail solution in the update domain is greater than the fitness of the first solution, the first solution is updated and replaced by the tail solution; iterative optimization is continued until the predetermined optimization number constraint is met, X current domains are output, and the first solution of the optimal current domain is selected as the first optimized polishing parameter, where the optimal current domain is the domain with the largest sum of fitness among the X current domains.

[0045] Specifically, a polishing parameter rated threshold is obtained, wherein the polishing parameter rated threshold includes a polishing speed threshold, a polishing pressure threshold, and a polishing time threshold; then a parameter is randomly selected from the polishing speed threshold, the polishing pressure threshold, and the polishing time threshold to obtain a first initial polishing parameter, and multiple initial polishing parameters are generated using the same method; then multiple initial polishing parameters are simulated polished using a polishing twin model to obtain multiple simulated polishing results. Multiple simulated polishing results are further evaluated based on the predetermined polishing evaluation function to obtain multiple fitness levels.

[0046] The initial polishing parameters are set as the initial solution, and then multiple initial solutions are arranged from large to small according to fitness to generate an initial solution sequence; further, the first X initial solutions of the initial solution sequence are set as the head solution, and the last Y initial solutions are set as the tail solution, where the sum of X and Y is the number of initial solutions, and Y is an integer multiple of X; then, with the X head solutions as the center, the Y tail solutions are randomly clustered to obtain X fields, where the number of tail solutions in each field is the same.

[0047] In X domains, the first solution in the domain is used as the optimization direction, and the tail solution in the domain is optimized once according to the preset optimization step length, wherein the preset optimization step length includes the polishing speed adjustment step length, the polishing pressure adjustment step length and the polishing time adjustment step length, and in the optimization adjustment process, if the tail solution after adjustment does not meet the rated threshold of the polishing parameter, the tail solution is not adjusted, and X updated domains are obtained. Further identify X updated domains, if there is a tail solution in the updated domain whose fitness is greater than the fitness of the first solution, the tail solution is used to update and replace the first solution. Continue to iterate the optimization until the predetermined optimization number constraint is met. The predetermined optimization number constraint can be set according to the optimization requirements, wherein the higher the required accuracy, the greater the predetermined optimization number, output X current domains, and select the domain with the largest sum of fitness in the X current domains as the optimal current domain, and at the same time select the first solution of the optimal current domain as the first optimized polishing parameter.

[0048] By using the above optimization algorithm to optimize the polishing parameters, since the algorithm has a strong global search capability, it can avoid falling into the local optimum and improve the accuracy and comprehensiveness of the first optimized polishing parameters.

[0049] In summary, the shadowless lamp quality control system based on digital processing provided by this application has the following technical effects: 1. By dividing the polishing index according to multiple polishing stages, a stage polishing index set is obtained; on the other hand, the single polishing area of ​​the grinding wheel is used as a reference to divide the reflector to be polished into regions to determine multiple polishing sub-regions; then, after a polishing operation is completed, a polishing quality simulation test is performed based on the microscopic image of the first sub-region to obtain the first stage test result, and then the quality deviation analysis of the first stage test result is performed according to the second stage polishing index, and the deviation analysis result is set as the second stage polishing workload; further based on the polishing processing twin model and the predetermined polishing evaluation function, the polishing parameter optimization is performed to meet the second stage polishing workload, and the first optimized polishing parameter is generated; finally, the second starting node is determined based on the first serial number of the first sub-region, and the polishing control of the second stage of the first sub-region is performed according to the second starting node and the first optimized polishing parameter until the entire polishing process is completed. The precision and accuracy of the polishing defect detection during the polishing process of the reflector can be improved, so that the processing defects can be timely and effectively corrected, so as to achieve the technical effect of improving the polishing accuracy and polishing quality of the reflector and meeting the production requirements of the surgical shadowless lamp product.

[0050] 2. By using artificial intelligence methods such as convolutional neural networks, BP neural networks and digital twins to simulate the polishing quality detection of the microscopic image of the first sub-area, the intelligence and automation of polishing quality detection can be improved. At the same time, the efficiency and accuracy of detection can be improved, and defects in the polishing process can be discovered in time, providing a basis for subsequent polishing optimization control.

[0051] 3. By setting the polishing workload of the next stage based on the deviation calculation and analysis results, the processing defects of the previous polishing stage can be corrected in a timely and effective manner, thereby achieving precise control and optimization of the overall polishing process and improving the overall polishing accuracy and polishing quality.

[0052] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0053] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. The shadowless lamp quality control system based on digital processing is characterized by: include: A polishing index division module is used to read the polishing index and polishing process of the target reflector, determine multiple polishing stages based on the polishing process, divide the polishing index according to the multiple polishing stages, and obtain a stage polishing index set; A polishing area division module is used to divide the reflector to be polished into regions based on the single polishing area of ​​the grinding wheel, and determine multiple polishing sub-regions, wherein each polishing sub-region has a unique serial number mark; A polishing quality simulation detection module is used to perform a polishing operation on a first sub-region based on a predetermined polishing path, collect images of the first sub-region through an optical microscope after the operation is completed, and perform a polishing quality simulation detection based on the microscopic image of the first sub-region to obtain a first-stage detection result, wherein the first sub-region is any one of the multiple polishing sub-regions, and the one polishing operation is a first-stage polishing operation; A quality deviation analysis module, used for selecting a second-stage polishing index from the stage polishing index set, performing a quality deviation analysis on the first-stage detection result according to the second-stage polishing index, and setting the deviation analysis result as the second-stage polishing workload; A polishing parameter optimization module, for optimizing the polishing parameters based on the polishing process twin model and the predetermined polishing evaluation function, with the purpose of satisfying the second-stage polishing workload, and generating the first optimized polishing parameters; A polishing control module is used to determine a second starting node according to the first serial number of the first sub-area, feed back the second starting node and the first optimized polishing parameter to the polishing control unit, and execute the polishing control of the second stage of the first sub-area until the entire polishing process is completed, wherein the second starting node is the starting time node of the second stage.

2. The shadowless lamp quality control system based on digital processing according to claim 1 is characterized in that: The polishing indicators include surface roughness, reflectivity and micro defect constraints.

3. The shadowless lamp quality control system based on digital processing according to claim 2 is characterized in that: The polishing quality simulation detection module is also used for: Inputting the first sub-region microscopic image into a feature extraction channel, and outputting a polishing feature set, wherein the polishing feature set includes a particle feature set, a ripple feature set, a texture feature set, a scratch feature set, and a dent feature set, and the feature extraction channel is constructed based on a convolutional neural network; The particle feature set, the corrugation feature set and the texture feature set are input into the surface evaluation model, and the predicted roughness is output; Predicting reflectivity based on the scratch feature set, the dent feature set and the predicted roughness, and outputting the predicted reflectivity; The scratch feature set, the dent feature set, the predicted roughness and the predicted reflectivity are used as the first stage detection results.

4. The shadowless lamp quality control system based on digital processing according to claim 3 is characterized in that: The polishing quality simulation detection module is also used for: Acquire the material properties of the reflector, and use the material properties of the reflector as a constraint to retrieve and acquire a sample data set through an Internet search, wherein the sample data includes a sample particle feature set, a sample ripple feature set, a sample texture feature set, and a sample surface roughness; The sample data set is divided into M equal parts, and M data sets are selected with replacement M times to construct the first data set, and the iterative selection is continued M times to obtain M data sets; The BP neural network is supervised trained and cross-validated using M data sets to obtain M surface evaluation units that meet the expected convergence constraints. A surface evaluation model is built based on the M surface evaluation units, where the output of the surface evaluation model is the mode of the output results of the M surface evaluation units.

5. The shadowless lamp quality control system based on digital processing according to claim 4 is characterized in that: The polishing quality simulation detection module is also used for: Acquire target light source information, wherein the target light source information includes light source brightness, light source color temperature, spectral distribution and luminous flux; Based on the target light source information, the reflector material properties, the scratch feature set, the dent feature set and the predicted roughness, N simulated reflectivity tests are performed in the simulation platform to obtain N reflectivities, and a reflectivity mean is calculated; The deviation values ​​of N reflectivities and the reflectivity mean are calculated in sequence, the reflectivity with a deviation value less than a predetermined deviation threshold is selected as the standard reflectivity, the mean of the standard reflectivities is calculated, and the mean of the standard reflectivity is set as the predicted reflectivity.

6. The shadowless lamp quality control system based on digital processing according to claim 4 is characterized in that: The polishing parameter optimization module is also used for: Based on digital twin technology, simulation modeling is performed according to the property information of the polishing equipment and the material properties of the reflector to build a polishing processing twin model; Based on the polishing process twin model and the predetermined polishing evaluation function, the polishing parameters are optimized with the second stage polishing workload as the constraint condition to obtain the first optimized polishing parameters, wherein the polishing parameters include polishing speed, polishing pressure and polishing time.

7. The shadowless lamp quality control system based on digital processing according to claim 6 is characterized in that: The polishing parameter optimization module is also used for: The expression of the predetermined polishing evaluation function is: ； in, is the fitness of the i-th polishing parameter, is the first weight, is the second weight, is the third weight, is the fourth weight, is the fifth weight, is the simulated surface roughness after the i-th polishing parameter processing, is the surface roughness of the second stage polishing workload, is the simulated reflectivity after the i-th polishing parameter processing, is the reflectivity of the second stage polishing workload, is the polishing time of the i-th polishing parameter, is the total amount of defect features after processing with the i-th polishing parameter, is the energy consumption of the i-th polishing parameter.

8. The shadowless lamp quality control system based on digital processing according to claim 7 is characterized in that: The polishing parameter optimization module is also used for: Obtaining polishing parameter rated thresholds, wherein the polishing parameter rated thresholds include a polishing speed threshold, a polishing pressure threshold, and a polishing time threshold; A parameter is randomly selected from a polishing speed threshold, a polishing pressure threshold, and a polishing time threshold to be combined to generate a plurality of initial polishing parameters, and the plurality of initial polishing parameters are simulated for polishing by a polishing process twin model to obtain a plurality of simulated polishing results; Evaluate multiple simulated polishing results based on the predetermined polishing evaluation function to obtain multiple fitnesses, set initial polishing parameters as initial solutions, arrange the multiple initial solutions from large to small according to the fitnesses, and generate an initial solution sequence; The first X initial solutions of the initial solution sequence are set as the first solutions, and the last Y initial solutions are set as the last solutions. The Y last solutions are randomly clustered with the X first solutions as the center to obtain X domains, where Y is an integer multiple of X, and the number of last solutions in each domain is the same. In X domains, the first solution in the domain is taken as the optimization direction, and the tail solution in the domain is optimized once according to the preset optimization step length to obtain X updated domains, wherein if the tail solution after adjustment does not meet the rated threshold of the polishing parameter, no adjustment is performed; Identify X update areas. If the fitness of the tail solution in the update area is greater than the fitness of the first solution, then use the tail solution to update and replace the first solution. Continue to iterate and optimize until the predetermined optimization number constraint is met, output X current fields, and select the first solution of the optimal current field as the first optimized polishing parameter, wherein the optimal current field is the field with the largest sum of fitness among the X current fields.

Images