An automated system for testing the quality of dentures
Through the denture quality detection automation system, environmental simulation and dynamic load simulation technology are used, combined with support vector machine and finite element analysis, the problem that traditional detection technology cannot accurately evaluate denture performance and durability is solved, and efficient and accurate detection and optimization are achieved , ensure product quality and safety.
Patent Information
- Application Number
- CN202411239689.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-09-05
AI Technical Summary
Traditional denture quality inspection technology relies on manual visual inspection and simple mechanical testing, and cannot accurately evaluate product performance and durability, resulting in the product leaving the factory without meeting the best quality standards, affecting user experience and market competitiveness.
An automated denture quality detection system was designed, including environmental simulation module, material stability prediction module, dynamic load simulation module and mechanical response analysis module. Through support vector machine algorithm and finite element analysis, the real oral environment and chewing behavior are simulated and the real oral environment and chewing behavior are identified. Potential weaknesses in materials and design, providing performance optimization solutions.
It improves the accuracy and efficiency of inspection, ensures that denture products meet high standards of performance and safety in actual use, reduces human errors, and provides strong support for quality assurance.
Smart Images

Figure CN118780135B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of quality inspection, and in particular to an automated system for inspecting the quality of artificial teeth. Background Art
[0002] Quality inspection technology refers to a series of methods and tools used to evaluate product or material conformity, performance, safety and other quality standards. This technical field spans multiple industrial and technological fields, including manufacturing, biomedicine, food safety and electronic engineering. Its purpose is to ensure that products meet established quality standards before leaving the factory or being put into use, thereby ensuring user safety, improving product reliability and meeting regulatory requirements. Quality inspection methods can be divided into destructive testing and non-destructive testing, including visual inspection, dimensional measurement, performance testing, material analysis, and automated and intelligent inspection technologies.
[0003] Among them, the denture quality inspection automation system is a system that is specifically designed to automatically inspect the quality of denture products. It aims to ensure that denture products meet medical health standards and user needs in terms of size, shape, material, and function through efficient and accurate means. The introduction of this system is intended to replace or assist traditional manual inspection methods, and to improve the overall quality and safety of denture products by reducing human errors and improving inspection efficiency and accuracy. The purpose is to ensure that each denture product meets high quality standards through technical means, thereby protecting the health and user experience of the user.
[0004] Traditional denture quality inspection technology usually relies on manual visual inspection or simple mechanical testing, which has certain limitations in operation. It is unable to accurately evaluate the performance and durability of the product, resulting in the product leaving the factory without meeting the optimal quality standards, which in turn affects the user experience and the market competitiveness of the product. In terms of dynamic load simulation and mechanical response analysis, traditional technology may lack efficient simulation means and analysis tools, making it difficult to accurately evaluate and predict the performance of materials under actual load conditions, resulting in blind spots in design and material selection, resulting in denture products failing to fully meet the expected standards in terms of quality, performance and safety, affecting the user experience and health and safety. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose an automatic system for detecting the quality of dentures.
[0006] In order to achieve the above object, the present invention adopts the following technical solution: an automated system for detecting denture quality, the system comprising:
[0007] The environmental simulation module sets environmental parameters based on the simulated environmental test chamber, creates a simulated oral denture use environment, and generates simulated environmental parameters;
[0008] The environmental data analysis module collects and analyzes the material expansion, color change, and surface wear data of the denture based on the simulated environmental parameters to obtain environmental stress response data;
[0009] The material stability prediction module uses a support vector machine algorithm based on the environmental stress response data to identify key environmental factors affecting material stability, predict the performance of denture materials in long-term use, and obtain material stability prediction results;
[0010] The dynamic load simulation module is based on the oral chewing wear simulation test machine. By setting differentiated chewing force and frequency, it simulates the force changes and frequency when humans chew food and obtains dynamic load simulation parameters.
[0011] The mechanical response analysis module monitors and records the stress distribution of the denture when it is subjected to the simulated chewing force based on the dynamic load simulation parameters, identifies potential weaknesses in the denture design and materials through a finite element analysis method, and obtains mechanical response analysis results;
[0012] The performance optimization suggestion module formulates a matching design adjustment strategy and material selection optimization plan based on the mechanical response analysis results and material stability prediction results to obtain a denture performance optimization plan.
[0013] The present invention has improvements in that the simulated environmental parameters include set temperature range, humidity range, pH value, food particle friction simulation parameters, and chemical contact simulation parameters; the environmental stress response data include material expansion rate, color change degree, surface wear depth, and wear pattern image; the material stability prediction results include key environmental factors affecting material stability, material performance prediction data, and analysis information on key reasons for material performance degradation; the dynamic load simulation parameters include simulated chewing force range, chewing frequency, chewing pattern type, and simulated chewing action duration; the mechanical response analysis results include stress distribution information, deformation data, potential weak point location identification, and material fatigue life prediction; the denture performance optimization plan includes denture thickness, curvature adjustment, material selection, surface treatment technology, and internal structure optimization plan.
[0014] The present invention is improved in that the environmental data analysis module comprises:
[0015] The physical reaction monitoring submodule monitors and records the physical reaction of the denture under the simulated oral environment conditions, including the expansion and contraction data of the material, by deploying sensors and camera equipment based on the simulated environment parameters, and generates physical reaction monitoring data;
[0016] The surface wear assessment submodule assesses and records the degree of wear of the denture surface under the influence of simulated food particle friction and chemical contact, including wear depth and wear pattern, based on the physical reaction monitoring data, and generates surface wear assessment data;
[0017] The color change analysis submodule uses a camera to capture the color changes of the denture material after it has been subjected to simulated oral environmental conditions based on the surface wear assessment data, and evaluates the color stability and aesthetic durability of the denture material by analyzing the degree and pattern of the color change to obtain environmental stress response data.
[0018] The present invention is improved in that the material stability prediction module comprises:
[0019] The environmental factor analysis submodule classifies the data based on the environmental stress response data, marks the test data under differentiated environmental conditions, including temperature, humidity, pH and contact reaction of chemical substances, uses the support vector machine algorithm to analyze the data, identifies the key factors affecting the stability of denture materials, and obtains the key environmental factor data;
[0020] The performance prediction submodule predicts the performance of the material in long-term use based on the key environmental factor data, analyzes the stability change of the material under the target environmental factors, predicts the future performance trend of the denture material, and obtains the material performance prediction result;
[0021] The cause analysis submodule analyzes the root causes of performance changes based on the material performance prediction results, including changes in the physical and chemical properties of the material and the interactive effects of environmental factors, identifies key causes that affect material stability and performance, and generates material stability prediction results.
[0022] The present invention is improved in that the support vector machine algorithm is according to the formula:
[0023] ;
[0024] Calculate the distance from each sample point to the separating hyperplane, identify the key factors affecting the stability of denture materials, and obtain the key environmental factor data, where: is the sample point to be classified, is the support vector, For the class label of each support vector, is the Lagrange multiplier for each support vector, is the bias term, For sample points The weight coefficient of is the regularization parameter, is the environmental factor influence function, For environmental factors, Represents the weighted vector and The inner product of is the total number of environmental factors, is the number of support vectors, is the classification decision function.
[0025] The present invention is improved in that the mechanical response analysis module comprises:
[0026] The stress monitoring submodule configures a stress sensor on the denture sample based on the dynamic load simulation parameters, records the stress distribution of the sample when it is subjected to the simulated chewing force, analyzes the stress concentration area, and generates stress distribution data;
[0027] The deformation variable measurement submodule uses a camera to record the deformation process of the denture sample during the stress process based on the stress distribution data, and quantifies the deformation degree, identifies the deformation rate and deformation area, and generates deformation variable data;
[0028] Based on the deformation data, the weakness location submodule uses the finite element analysis method to analyze the stress and deformation data, identify potential weak areas in the denture design and materials, including locations where stress and deformation exceed thresholds, and obtain mechanical response analysis results.
[0029] The present invention is improved in that the finite element analysis method is according to the formula:
[0030] ;
[0031] Calculate the stress value of the material, where is the elastic modulus, is the dependent variable, is the stress value, is the temperature influence coefficient, is the current temperature, is the reference temperature, is the chemical substance influence coefficient, is the current chemical concentration, is the reference chemical concentration, is the humidity influence coefficient, is the current humidity, For reference humidity.
[0032] The present invention is improved in that the performance optimization suggestion module includes:
[0033] The design parameter adjustment submodule analyzes the influence of the differentiated design parameters on the denture performance, including the thickness and curvature of the denture, based on the mechanical response analysis results, and predicts the influence of parameter changes on the performance, formulates a target design parameter combination, and generates optimized design parameters;
[0034] The material selection optimization submodule evaluates the contribution of differentiated materials to improving the performance of dentures based on the optimization design parameters, selects matching material combinations based on the mechanical properties, wear resistance and color stability of the materials, and generates a material selection optimization plan;
[0035] The manufacturing process improvement submodule analyzes the potential impact of differentiated manufacturing processes on the performance of denture products based on the material selection optimization plan, including surface treatment technology and internal structure optimization, formulates process measures to match material selection, and obtains a denture performance optimization plan.
[0036] Compared with the prior art, the advantages and positive effects of the present invention are:
[0037] In the present invention, by creating a test environment close to real oral conditions, the practicability and accuracy of the test are enhanced. The application of support vector machine algorithm makes the prediction of material properties more accurate and can effectively identify key environmental factors affecting material stability. By simulating human chewing behavior, a scientific basis is provided for the testing of denture bearing force and durability. The application of finite element analysis method can identify potential weaknesses in denture design and materials, and improve denture design and material selection, ensuring that each denture product can maintain high standards of performance and safety in actual use, improving detection efficiency and accuracy, reducing human errors, and providing strong support for the quality assurance of denture products. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] Figure 1 A module diagram of an automated system for quality inspection of dentures is proposed for the present invention;
[0039] Figure 2 A system framework diagram of an automated system for denture quality inspection is proposed for the present invention;
[0040] Figure 3 A schematic diagram of an environmental simulation module in an automated denture quality inspection system is proposed for the present invention;
[0041] Figure 4 A schematic diagram of an environmental data analysis module in an automated denture quality inspection system is provided for the present invention;
[0042] Figure 5 A schematic diagram of a material stability prediction module in an automated denture quality inspection system is provided for the present invention;
[0043] Figure 6 A schematic diagram of a dynamic load simulation module in an automated denture quality inspection system is provided for the present invention;
[0044] Figure 7A schematic diagram of a mechanical response analysis module in an automated denture quality inspection system is provided for the present invention;
[0045] Figure 8 A schematic diagram of a performance optimization suggestion module in an automated denture quality inspection system is proposed for the present invention. DETAILED DESCRIPTION
[0046] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0047] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. Example
[0048] See also Figure 1 ,The present invention provides a technical solution: an automated system for denture quality inspection, the system comprising an environmental simulation module, an environmental data analysis module, a material stability prediction module, a dynamic load simulation module, a mechanical response analysis module, and a performance optimization suggestion module;
[0049] The environmental simulation module is based on the simulated environmental test chamber, and the environmental parameters are set, including adjusting the temperature range to 5°C to 45°C, the humidity range to 30% to 90%RH, and the pH to pH4 to 9, to simulate the target oral environment and the effects of long-term chemical contact, including simulating the friction of food particles on dentures and the effects of alcohol and sugary drinks on dentures, creating a simulated oral denture use environment, and generating simulated environmental parameters;
[0050] The environmental data analysis module deploys sensors and cameras based on simulated environmental parameters to capture the physical response of dentures under various simulated conditions, collect and analyze data on material expansion, color change, and surface wear of dentures, and obtain environmental stress response data;
[0051] The material stability prediction module is based on environmental stress response data and uses the support vector machine algorithm to analyze the material response data under differentiated environmental conditions, identify key environmental factors that affect material stability, and apply deep neural networks to analyze data relationships to predict the performance of denture materials in long-term use and obtain material stability prediction results;
[0052] The dynamic load simulation module is based on the oral chewing wear simulation test machine. By setting differentiated chewing force and frequency, it simulates the force changes and frequency when humans chew food, including simulating chewing, grinding and other chewing modes, and applies dynamic loads to the denture samples to obtain dynamic load simulation parameters.
[0053] The mechanical response analysis module uses stress sensors to monitor and record the stress distribution of the denture when it is subjected to simulated chewing force based on dynamic load simulation parameters. It uses video to capture the deformation process of the denture and uses the finite element analysis method to analyze the collected deformation and stress distribution data, identify potential weaknesses in the denture design and materials, and obtain mechanical response analysis results.
[0054] The performance optimization suggestion module is based on the mechanical response analysis results and material stability prediction results. It uses neural networks to analyze the performance of various denture designs under simulated usage conditions, uses regression analysis methods to optimize design parameters, and identifies key design improvements that can improve the mechanical properties and durability of dentures. Based on potential improvement points, it develops matching design adjustment strategies and material selection optimization plans to optimize the overall performance and user experience of dentures and obtain a denture performance optimization plan.
[0055] The simulated environmental parameters include the set temperature range, humidity range, pH value, food particle friction simulation parameters, and chemical contact simulation parameters. The environmental stress response data include material expansion rate, color change degree, surface wear depth, and wear pattern image. The material stability prediction results include key environmental factors affecting material stability, material performance prediction data, and analysis information on key reasons for material performance degradation. The dynamic load simulation parameters include simulated chewing force range, chewing frequency, chewing pattern type, and simulated chewing action duration. The mechanical response analysis results include stress distribution information, deformation data, potential weak point location identification, and material fatigue life prediction. The denture performance optimization plan includes denture thickness, curvature adjustment, material selection, surface treatment technology, and internal structure optimization plan.
[0056] See also Figure 2 and Figure 3 ,The environmental simulation module includes a temperature and humidity control submodule, a pH simulation submodule, and a specific environment simulation submodule;
[0057] The temperature and humidity control submodule is based on the simulated environmental test chamber, and adjusts the temperature and humidity in the test chamber to stabilize the temperature between 5°C and 45°C, and the humidity is controlled within the range of 30% to 90%, simulating the different oral environment conditions, and generating the specific process of temperature and humidity control data as follows;
[0058] The temperature and humidity control submodule is based on a simulated environmental experimental chamber. By adjusting the temperature control system and humidity control device in the chamber, the target temperature range parameters of the temperature control system are set to 5°C to 45°C, and the target humidity range parameters of the humidity control device are set to 30% to 90%. The control script is written in Python, and the SciPy and NumPy libraries are used for numerical calculations to implement the PID control algorithm to accurately adjust the real-time temperature and humidity, ensuring that the chamber environment operates stably according to the preset parameters, thereby simulating different oral environmental conditions, and recording temperature and humidity data to generate temperature and humidity control data.
[0059] The pH simulation submodule adjusts the chemical substances added in the experimental chamber based on the temperature and humidity control data, changes the pH in the environment, controls the pH between pH 4 and 9, and simulates the oral environment under differentiated eating habits and oral hygiene conditions. The specific process of obtaining the pH adjustment data is as follows;
[0060] The pH simulation submodule is based on the temperature and humidity control data. It operates by injecting pre-proportioned acid-base adjustment chemical solutions into the experimental chamber, calculating the volume ratio of the required chemical solutions to adjust the pH value of the liquid in the chamber, and using Python scripts combined with the Pandas library for data analysis and processing. The micropump injection system is controlled to accurately control the amount of chemical solution added, and the pH is controlled between pH 4 and 9 to simulate the oral environment under differentiated eating habits and oral hygiene conditions. The pH value data is recorded to obtain the pH adjustment data.
[0061] The specific environment simulation submodule simulates the target oral use environment conditions based on the pH adjustment data, including adding simulated food particles and chemicals, including alcohol and sugary drinks, into the experimental chamber to simulate the friction of food particles on the dentures and the long-term contact effects of chemicals, creating an oral environment that simulates the use situation. The specific process of generating simulated environment parameters is as follows;
[0062] The specific environment simulation submodule is based on the pH adjustment data and operates by adding simulated food particles and chemicals into the experimental chamber. The simulated food particles are spread into the chamber using a fine dispersion system, and simulated chemicals such as artificial alcohol and sugary solutions are injected through a metering pump system. A control program written in Python is used to visualize the environmental impact using the Matplotlib library, simulate the friction of food particles on dentures and the long-term contact effects of chemicals, collect environmental data under simulated conditions, and generate simulated environmental parameters.
[0063] See also Figure 2 and Figure 4 ,The environmental data analysis module includes a physical reaction monitoring submodule, a surface wear assessment submodule, and a color change analysis submodule;
[0064] The physical reaction monitoring submodule monitors and records the physical reaction of the denture under the simulated oral environment conditions, including the expansion and contraction data of the material, based on the simulated environmental parameters by deploying sensors and cameras. The specific process of generating physical reaction monitoring data is as follows;
[0065] The physical reaction monitoring submodule monitors the expansion and contraction of materials based on simulated environmental parameters by deploying sensors and cameras. It uses the Python programming language and the OpenCV library for image processing and analysis, and uses image analysis technology to track and record the deformation of materials under different environmental conditions, thereby accurately calculating the expansion or contraction data of the material. The data directly reflects the physical response of the material to changes in the simulated oral environment, generating physical reaction monitoring data.
[0066] The surface wear assessment submodule evaluates and records the degree of wear of the denture surface under the influence of simulated food particle friction and chemical contact based on the physical reaction monitoring data, including wear depth and wear pattern. The specific process of generating surface wear assessment data is as follows;
[0067] The surface wear assessment submodule evaluates the degree of denture surface wear based on physical reaction monitoring data, and uses the Matplotlib library to visualize the data. The wear depth and wear pattern are presented in a graphical way to facilitate the analysis of the wear of the material surface after experiencing simulated food particle friction and chemical contact. By comparing the image data before and after wear, the area and depth changes of the wear area are calculated to generate surface wear assessment data.
[0068] The color change analysis submodule uses a camera to capture the color changes of the denture material after experiencing the simulated oral environment conditions based on the surface wear assessment data. By analyzing the degree and pattern of color changes, the color stability and aesthetic durability of the denture material are evaluated. The specific process of obtaining the environmental stress response data is as follows;
[0069] The color change analysis submodule is based on the surface wear assessment data. It uses a camera to capture the color changes of the denture material and performs color analysis operations. It uses Python and the PIL library to process the image data. Specifically, it analyzes the images before and after the color change, and uses color histogram matching technology to evaluate the degree and pattern of color change. It allows for accurate quantification of color changes, provides a direct basis for evaluating the color stability of the material, and obtains environmental stress response data.
[0070] See also Figure 2 and Figure 5 ,The material stability prediction module includes an environmental factor analysis submodule, a performance prediction submodule, and a cause analysis submodule;
[0071] The environmental factor analysis submodule classifies the data based on the environmental stress response data, marks the test data under differentiated environmental conditions, including temperature, humidity, pH and chemical contact reactions, and uses the support vector machine algorithm to analyze the data to identify the key factors affecting the stability of denture materials. The specific process of obtaining the key environmental factor data is as follows;
[0072] The environmental factor analysis submodule classifies and labels the data based on the environmental stress response data. It uses Python language for programming and Scikit-learn library to implement the support vector machine algorithm. The support vector machine algorithm is used for supervised learning. Temperature, humidity, pH and chemical contact reaction are used as feature inputs for model training. The model parameters are optimized through cross-validation, such as adjusting the C value and kernel function type to improve classification accuracy, so as to identify the environmental factors that have the most significant impact on the stability of denture materials, and record the data of key environmental factors to obtain key environmental factor data.
[0073] The support vector machine algorithm follows the formula:
[0074] ;
[0075] Calculate the distance from each sample point to the separating hyperplane, identify the key factors affecting the stability of denture materials, and obtain the key environmental factor data, where: is the sample point to be classified, is the support vector, For the class label of each support vector, is the Lagrange multiplier for each support vector, is the bias term, For sample points The weight coefficient reflects the importance of the sample point in the classification decision. is a regularization parameter used to balance the complexity of the model and the training error. is the environmental factor influence function, Environmental factors, including temperature, humidity, pH and chemical contact reactions, Represents the weighted vector and The inner product of is the total number of environmental factors, indicating the number of different types of environmental factors considered in the analysis, such as temperature, humidity, pH, and chemical exposure reactions. is the number of support vectors, which refers to the total number of sample points in the training data set that are identified by the model as having an important influence on the classification decision. is a classification decision function, which is used to classify the input sample points The features of the sample point are used to calculate the decision result of whether the sample point is classified as positive or negative. The value of is determined according to the distance from the sample point to the classification hyperplane and the influence of environmental factors taken into account. A positive value indicates that the sample is classified as a positive class, and a negative value indicates that the sample is classified as a negative class.
[0076] The specific implementation process of the improved formula is as follows:
[0077] Classify and label the environmental stress response data, determine the characteristic input of each sample point, including temperature, humidity, pH and chemical contact reaction, and calculate the weight coefficient of the sample point by analyzing the influence of the characteristics of the sample point on the classification results in the historical data , set the regularization parameter , select the best one through cross-validation method To avoid overfitting, for each environmental factor Applying influence functions , The function is learned based on historical data and is used to quantify the impact of different environmental factors on sample classification. The improved support vector machine algorithm is used for model training and parameter optimization to identify the environmental factors that have the most significant impact on the stability of denture materials.
[0078] The performance prediction submodule predicts the performance of the material in long-term use based on the key environmental factor data, analyzes the stability changes of the material under the target environmental factors, and predicts the future performance trend of the denture material. The specific process of obtaining the material performance prediction results is as follows;
[0079] The performance prediction submodule performs material performance prediction operations based on key environmental factor data. It uses Python language, cooperates with TensorFlow and Keras libraries to build a deep neural network model. The model structure is defined to include an input layer, multiple hidden layers and an output layer. The input layer receives key environmental factor data, and the hidden layer uses the ReLU activation function for feature extraction. The output layer predicts the long-term performance of the material. The optimizer selects Adam, and the loss function uses mean_squared_error. The model is trained through a large amount of environmental factor data to predict the stability changes of the material under the action of the target environmental factors, and finally obtain the material performance prediction results.
[0080] The cause analysis submodule analyzes the root causes of performance changes based on the material performance prediction results, including changes in the physical and chemical properties of the material, the interaction of environmental factors, and identifies the key causes that affect material stability and performance. The specific process for generating material stability prediction results is as follows;
[0081] The cause analysis submodule performs root cause analysis on the material performance prediction results, processes and analyzes the prediction result data using Python programming and the Pandas library, explores the changes in the physical and chemical properties of materials and the interaction between environmental factors, and identifies the key causes that affect material stability and performance through comprehensive analysis. It pays special attention to correlation analysis and regression analysis of data to reveal the specific mechanisms by which different environmental factors affect material performance and generate material stability prediction results.
[0082] See also Figure 2 and Figure 6 ,The dynamic load simulation module includes a chewing force simulation submodule, a frequency adjustment submodule, and a mode setting submodule;
[0083] The chewing force simulation submodule is based on an oral chewing wear simulation test machine. The test machine is set to simulate the force of human chewing food, and the simulated force is adjusted to cover the actual chewing force range, providing basic simulation conditions for chewing differentiated types of food. The specific process of generating basic chewing force parameters is as follows;
[0084] The chewing force simulation submodule is based on the oral chewing wear simulation test machine to perform the test machine's drive unit control operation. The operation is implemented through the Python programming language, using the PySerial library to communicate with the test machine's control interface, and sending instructions to adjust the test machine's motor speed and torque output parameters to simulate the different forces when humans chew food, providing basic simulation conditions for the chewing of differentiated types of food. The operation is designed to ensure that the simulated force covers the actual force range from mild to strong chewing. The motor status feedback is read through the PySerial library to ensure the accuracy of parameter adjustment and generate basic chewing force parameters.
[0085] The frequency adjustment submodule adjusts the frequency of chewing action based on the basic chewing force parameters, simulates multiple chewing frequencies, matches the actual conditions of differentiated food textures and chewing habits, and generates the chewing frequency adjustment parameters in the following specific process;
[0086] The frequency adjustment submodule adjusts the chewing action frequency of the testing machine through software based on the basic chewing force parameters. The control script is written in Python and the NumPy library is used for numerical calculations to determine the optimal frequency setting for the chewing action. The motor speed setting value at different chewing rates is calculated to match the actual conditions of different food textures and chewing habits. The motor speed is controlled by adjusting the frequency converter to achieve precise adjustment of the chewing frequency and generate the chewing frequency adjustment parameters.
[0087] The mode setting submodule adjusts parameters based on the chewing frequency, sets the chewing mode, including chewing and grinding actions, simulates the chewing of differentiated foods, and generates the dynamic load simulation parameters. The specific process is as follows;
[0088] The mode setting submodule adjusts parameters based on the chewing frequency and sets the test machine to simulate different chewing modes. It uses the Python programming language in conjunction with the Pandas library for data management. Operations include writing action sequences to simulate different chewing modes, such as simple chewing and complex grinding actions, to accurately simulate the chewing behavior of humans when eating different foods. It uses the Pandas library to process and analyze the chewing force and frequency data in different modes to ensure the diversity and practicality of the test machine's action sequences. It calls the action sequences through the control software to realistically simulate the behavior of chewing foods of different textures and generate dynamic load simulation parameters.
[0089] See also Figure 2 and Figure 7 ,The mechanical response analysis module includes a stress monitoring submodule, a deformation variable measurement submodule, and a weak point locating submodule;
[0090] The stress monitoring submodule configures stress sensors on the denture samples based on the dynamic load simulation parameters, records the stress distribution of the samples when subjected to simulated chewing force, analyzes the stress concentration area, and generates stress distribution data in the following specific process;
[0091] Based on the dynamic load simulation parameters, the stress monitoring submodule configures stress sensors on the denture samples and performs stress distribution monitoring operations. This operation is implemented through a Python script, using the PySerial library to achieve data communication with the stress sensor, reading the stress value output by the sensor through the serial port, and using the Pandas library for data organization and preliminary analysis to mark stress concentration areas. The data is visualized through the Matplotlib library, thereby intuitively displaying the stress distribution of the sample under simulated chewing force and generating stress distribution data.
[0092] The deformation measurement submodule uses a camera to record the deformation process of the denture sample during the stress process based on the stress distribution data, and quantifies the deformation degree, identifies the deformation rate and deformation area, and generates the deformation data. The specific process is as follows;
[0093] The deformation measurement submodule is based on stress distribution data. It uses high-speed camera equipment to record the deformation process of the denture sample during the force process and performs deformation analysis operations. The OpenCV library is used for image processing, and image registration technology is used to compare the image differences before and after deformation. Image processing technology such as edge detection is used to identify the deformation area. Numerical calculations are performed through the Numpy library to quantify the degree of deformation, thereby identifying the deformation rate and specific deformation area and generating deformation data.
[0094] The weakness location submodule uses the finite element analysis method to analyze stress and deformation data based on deformation data, and identifies potential weak areas in denture design and materials, including locations where stress and deformation exceed thresholds. The specific process of obtaining mechanical response analysis results is as follows;
[0095] The weakness location submodule performs weakness identification operations based on the deformation data using the finite element analysis method. It uses a Python script to call the FEniCS library for finite element simulation, including setting the physical conditions of the simulation, such as material properties and boundary conditions, taking the deformation data as input parameters, and using the solver provided by FEniCS to perform numerical simulation of stress and deformation. It identifies areas where stress and deformation exceed preset thresholds, which are potential weaknesses in the denture design and materials. It uses the Matplotlib library to visualize the simulation results and obtain the mechanical response analysis results.
[0096] The finite element analysis method is based on the formula:
[0097] ;
[0098] Calculate the stress value of the material, where The elastic modulus indicates the force that a material can withstand per unit deformation and is a measure of the material's ability to resist deformation. is the strain, that is, the change in unit length of the material under the action of force, which reflects the degree of deformation of the material. is the stress value, which indicates the force inside the material resisting being stretched or compressed. It is the magnitude of the force per unit area. is the temperature influence coefficient, which is used to quantify the influence of temperature change on material stress. is the current temperature, which indicates the temperature value in the experiment or actual environment. is the reference temperature, usually the temperature value under standard or design conditions, is the chemical influence coefficient, which quantifies the influence of chemical concentration changes on material stress. is the current chemical concentration, indicating the concentration value of the chemical in the experiment or actual environment. is the concentration of the reference chemical substance, usually the concentration value of the chemical substance under standard or design conditions, is the humidity influence coefficient, which quantifies the influence of humidity change on material stress. is the current humidity, indicating the humidity value in the experiment or actual environment. The reference humidity is usually the humidity value under standard or design conditions.
[0099] The specific implementation process of the improved formula is as follows:
[0100] Collect the current temperature in the experimental or actual environment , Chemical Concentration , and humidity and determine the value relative to the reference condition , , The reference conditions are usually based on standard environmental settings or environmental parameters preset during material design, and the temperature influence coefficients are determined experimentally or extracted from the literature. 、Chemical substance impact coefficient , and humidity influence coefficient The specific value of represents the sensitivity of different environmental factors to the material stress. The parameter value is substituted into the improved formula, and the numerical simulation is performed using Python script and FEniCS library. During the simulation process, the physical conditions of the simulation are set, including material properties and boundary conditions. The material properties are Expression, and use the collected environmental factor change data as input parameters to calculate stress through the solver provided by FEniCS and deformation If the solution results show that the stress or deformation in some areas exceeds the preset threshold, the area is identified as a potential weak point. The Matplotlib library is used to visualize the solution results, which facilitates the analysis and understanding of which factors have the most significant impact on the stability of the material, and then obtains the mechanical response analysis results.
[0101] See also Figure 2 and Figure 8 ,The performance optimization suggestion module includes the design parameter adjustment submodule, the material selection optimization submodule, and the manufacturing process improvement submodule;
[0102] The design parameter adjustment submodule analyzes the impact of differentiated design parameters on denture performance, including the thickness and curvature of the denture, based on the mechanical response analysis results, and predicts the impact of parameter changes on performance, formulates target design parameter combinations, and generates the specific process of optimized design parameters as follows;
[0103] The design parameter adjustment submodule analyzes the impact of differentiated design parameters on denture performance based on the mechanical response analysis results. It uses Python language for scripting, uses the SciPy library for scientific calculations, and uses the least squares method to fit the relationship between the thickness and curvature of the denture and the performance. It predicts the performance changes of the denture under different design parameter combinations, and uses the Matplotlib library to visualize the prediction results to assist in deciding the optimal design parameter combination and generate optimized design parameters.
[0104] The material selection optimization submodule evaluates the contribution of differentiated materials to improving denture performance based on the optimized design parameters, selects matching material combinations based on the mechanical properties, wear resistance, and color stability of the materials, and generates the specific process of the material selection optimization solution as follows;
[0105] The material selection optimization submodule evaluates the contribution of different materials to improving the performance of dentures based on the optimized design parameters, uses the Pandas library for data management and analysis, calculates the comprehensive performance indicators of each material based on the material's attribute data such as mechanical properties, wear resistance and color stability, uses the decision tree algorithm to classify materials and select the most suitable material combination, and uses the Seaborn library to visualize the results, thereby selecting the most matching material combination and generating a material selection optimization plan.
[0106] The manufacturing process improvement submodule analyzes the potential impact of differentiated manufacturing processes on the performance of denture products based on the material selection optimization plan, including surface treatment technology and internal structure optimization, and formulates process measures to match material selection. The specific process of obtaining the denture performance optimization plan is as follows;
[0107] The manufacturing process improvement submodule analyzes the potential impact of different manufacturing processes on the performance of denture products based on the material selection optimization plan. It implements the machine learning model by calling the SciKit-Learn library. Specifically, it uses the random forest algorithm to analyze the impact of different surface treatment technologies and internal structure optimization plans on performance. During the operation, the algorithm parameters such as the number and depth of trees are set, and the model is trained and verified to identify the manufacturing process measures that can maximize the performance of dentures and generate a denture performance optimization plan.
[0108] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.
Claims
1. An automated system for denture quality inspection, characterized in that: The system comprises: The environmental simulation module sets environmental parameters based on the simulated environmental test chamber, creates a simulated oral denture use environment, and generates simulated environmental parameters; The environmental data analysis module collects and analyzes the material expansion, color change, and surface wear data of the denture based on the simulated environmental parameters to obtain environmental stress response data; The material stability prediction module uses a support vector machine algorithm based on the environmental stress response data to identify key environmental factors affecting material stability, predict the performance of denture materials in long-term use, and obtain material stability prediction results; The support vector machine algorithm is based on the formula: ; Calculate the distance from each sample point to the separating hyperplane, identify the key factors affecting the stability of denture materials, and obtain the key environmental factor data, where: is the sample point to be classified, is the support vector, For each support vector, the class label, is the Lagrange multiplier for each support vector, is the bias term, For sample points The weight coefficient of is the regularization parameter, is the environmental factor influence function, For environmental factors, Represents the weighted vector and The inner product of is the total number of environmental factors, is the number of support vectors, is the classification decision function; The dynamic load simulation module is based on the oral chewing wear simulation test machine. By setting differentiated chewing force and frequency, it simulates the force changes and frequency when humans chew food and obtains dynamic load simulation parameters. The mechanical response analysis module monitors and records the stress distribution of the denture when it is subjected to the simulated chewing force based on the dynamic load simulation parameters, identifies potential weaknesses in the denture design and materials through a finite element analysis method, and obtains mechanical response analysis results; The finite element analysis method is according to the formula: ; Calculate the stress value of the material, where is the elastic modulus, is the dependent variable, is the stress value, is the temperature influence coefficient, is the current temperature, is the reference temperature, is the chemical substance influence coefficient, is the current chemical concentration, is the reference chemical concentration, is the humidity influence coefficient, is the current humidity, is the reference humidity; The performance optimization suggestion module formulates a matching design adjustment strategy and material selection optimization plan based on the mechanical response analysis results and material stability prediction results to obtain a denture performance optimization plan.
2. The denture quality detection automation system according to claim 1, characterized in that: The simulated environmental parameters include set temperature range, humidity range, pH value, food particle friction simulation parameters, and chemical contact simulation parameters; the environmental stress response data include material expansion rate, color change degree, surface wear depth, and wear pattern image; the material stability prediction results include key environmental factors affecting material stability, material performance prediction data, and analysis information on key reasons for material performance degradation; the dynamic load simulation parameters include simulated chewing force range, chewing frequency, chewing pattern type, and simulated chewing action duration; the mechanical response analysis results include stress distribution information, deformation data, potential weak point location identification, and material fatigue life prediction; the denture performance optimization plan includes denture thickness, curvature adjustment, material selection, surface treatment technology, and internal structure optimization plan.
3. The denture quality detection automation system according to claim 1, characterized in that: The environmental data analysis module includes: The physical reaction monitoring submodule monitors and records the physical reaction of the denture under the simulated oral environment conditions, including the expansion and contraction data of the material, by deploying sensors and camera equipment based on the simulated environment parameters, and generates physical reaction monitoring data; The surface wear assessment submodule assesses and records the degree of wear of the denture surface under the influence of simulated food particle friction and chemical contact, including wear depth and wear pattern, based on the physical reaction monitoring data, and generates surface wear assessment data; The color change analysis submodule uses a camera to capture the color changes of the denture material after it has been subjected to simulated oral environmental conditions based on the surface wear assessment data, and evaluates the color stability and aesthetic durability of the denture material by analyzing the degree and pattern of the color change to obtain environmental stress response data.
4. The denture quality detection automation system according to claim 1, characterized in that: The material stability prediction module comprises: The environmental factor analysis submodule classifies the data based on the environmental stress response data, marks the test data under differentiated environmental conditions, including temperature, humidity, pH and contact reaction of chemical substances, uses the support vector machine algorithm to analyze the data, identifies the key factors affecting the stability of denture materials, and obtains the key environmental factor data; The performance prediction submodule predicts the performance of the material in long-term use based on the key environmental factor data, analyzes the stability change of the material under the target environmental factors, predicts the future performance trend of the denture material, and obtains the material performance prediction result; The cause analysis submodule analyzes the root causes of performance changes based on the material performance prediction results, including changes in the physical and chemical properties of the material and the interactive effects of environmental factors, identifies key causes that affect material stability and performance, and generates material stability prediction results.
5. The denture quality detection automation system according to claim 1, characterized in that: The mechanical response analysis module includes: The stress monitoring submodule configures a stress sensor on the denture sample based on the dynamic load simulation parameters, records the stress distribution of the sample when it is subjected to the simulated chewing force, analyzes the stress concentration area, and generates stress distribution data; The deformation variable measurement submodule uses a camera to record the deformation process of the denture sample during the stress process based on the stress distribution data, and quantifies the deformation degree, identifies the deformation rate and deformation area, and generates deformation variable data; Based on the deformation data, the weakness location submodule uses the finite element analysis method to analyze the stress and deformation data, identify potential weak areas in the denture design and materials, including locations where stress and deformation exceed thresholds, and obtain mechanical response analysis results.
6. The denture quality detection automation system according to claim 1, characterized in that: The performance optimization suggestion module includes: The design parameter adjustment submodule analyzes the influence of the differentiated design parameters on the denture performance, including the thickness and curvature of the denture, based on the mechanical response analysis results, and predicts the influence of parameter changes on the performance, formulates a target design parameter combination, and generates optimized design parameters; The material selection optimization submodule evaluates the contribution of differentiated materials to improving the performance of dentures based on the optimization design parameters, selects matching material combinations based on the mechanical properties, wear resistance and color stability of the materials, and generates a material selection optimization plan; The manufacturing process improvement submodule analyzes the potential impact of differentiated manufacturing processes on the performance of denture products based on the material selection optimization plan, including surface treatment technology and internal structure optimization, formulates process measures to match material selection, and obtains a denture performance optimization plan.
