A multi-dimensional performance grading system and method for dental shell appliance membrane materials

Abstract

The present application relates to the technical field of dental instrument material performance evaluation, in particular to a multi-dimensional performance grading evaluation system and method for dental shell instrument membrane materials. The system includes a hierarchical modeling module, an index collection module, a data processing module, a weight adjustment module and a result output module, constructs three layers of performance structure of basic clinical safety layer, core correction function layer and advanced service efficiency layer, and is associated with dimensional indexes such as clinical quality characteristics, biological safety, orthodontic mechanical characteristics, processing process characteristics and appearance characteristics. The measured data are obtained by standardized testing, normalized processing and dynamic weight adjustment combined with a rule engine or a machine learning model to generate a comprehensive score and grade determination. The present application overcomes the defects of index dispersion, lack of weight and hierarchical division in the prior art, realizes objective and comparable evaluation of the performance of different membrane materials, and improves the scientificity of clinical application and industry research and development.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of dental material detection and evaluation, in particular to a multi-dimensional performance grading and evaluation system and method for dental shell-shaped appliance membrane materials, which belongs to the comprehensive technical application field of oral orthodontic and restorative material performance detection, data analysis and clinical adaptability evaluation. The present application can be applied to laboratory detection and performance grading and evaluation of membrane materials for dental shell-shaped appliances such as clear aligners, occlusal splints, attachment templates, and mouthguards. BACKGROUND

[0002] In recent years, clear aligner technology has been widely used in orthodontic treatment, and one of its core components is a shell-shaped dental appliance (i.e., a clear aligner) made of a thermoplastic polymer membrane material. This type of membrane needs to serve in a complex oral humid and hot environment for a long time, and through its shape and elastic recovery properties, it applies a continuous and controllable orthodontic force to the teeth, thereby achieving the gradual movement of the teeth. The existing clear aligner membrane often appears failure modes such as wear, occlusal collapse, and mouthguard detachment in actual use, resulting in a generally insufficient 50% tooth movement rate. One of the key reasons is that the material's viscoelastic behavior causes creep and stress relaxation, causing the orthodontic force to rapidly decay over time. To maintain treatment effectiveness, clinicians often need to shorten the replacement cycle or add force attachments, increasing treatment costs and patient discomfort.

[0003] In terms of material performance, there are still deficiencies in the research and stable supply of high-performance membrane raw materials in China, and high-hardness particle raw materials almost completely rely on imports. Existing membrane materials differ significantly in core performance parameters such as storage modulus, mechanical loss, and glass transition temperature (Tg), which directly affect the stress retention, recovery ability, and wearing comfort of the aligner. For example, multi-layer composite membranes can achieve shape recovery within 5 to 15 seconds at 80°C to 100°C through the shape memory polymer (SMP) effect, and some products can still maintain a high stress retention rate after cyclic heating and cooling; while some single-layer materials perform poorly in clinical fracture rate and fatigue life.

[0004] In order to ensure that the product meets the clinical needs in terms of safety, treatment efficiency, durability, and appearance perception, several detection standards related to biological safety, mechanical properties, processing technology, and appearance characteristics have been established at home and abroad, such as ISO10993 series, ISO 527-1, ASTM D790, ISO 4287, etc. These standards have clear specifications for testing methods, conditions, and judgment requirements for individual performance, to some extent, promoting the standardization of membrane material detection.

[0005] However, the evaluation system in the prior art is fragmented. Different standards are independent of each other, and there is a lack of unified framework structure and weight distribution mechanism, resulting in that the detection results often stay at the level of listing and comparing single indicators. In actual application, various materials may perform outstandingly in some performance indicators, but have short boards in other indicators. Without unified weights and hierarchical division, it is difficult to comprehensively integrate these scattered indicators into intuitive and objective judgments of advantages and disadvantages, and it is also difficult to directly guide the material selection and optimization of clinicians or researchers.

[0006] In addition, the traditional evaluation method does not grade the importance of performance indicators according to clinical attention and application scenarios. For example, biological safety, as a basic requirement, determines whether the material can enter clinical application; orthodontic mechanical properties directly affect the efficiency of treatment and patient experience; and advanced service performance indicators are related to long-term stability and aesthetics. However, in the existing method, these indicators are treated equally, and there is a lack of hierarchical structure reflecting the differences in their clinical importance. This not only causes "same weight" misguidance among different performance dimensions, but also makes it impossible to highlight the priority of key indicators in material performance optimization.

[0007] In view of the above problems, the present application first proposes a multi-dimensional performance evaluation system based on hierarchical grading theory. The system structures the performance of the membrane material into three levels of basic clinical safety layer, core orthodontic function layer and advanced service performance layer, and sets performance dimensions and quantitative indicators closely related to clinical needs under each level. By introducing a weight distribution and dynamic adjustment mechanism, the present application can form a hierarchical comprehensive score according to the importance of the indicators and the differences in the detection results, and accurately reflect the overall performance level of different materials.

[0008] This innovative method not only overcomes the disadvantages of "isolated indicators and lack of comparability" in the existing evaluation system, but also establishes a quantifiable, traceable and expandable industry-wide evaluation framework. Its technical value lies in that the advantages and disadvantages of the invisible orthodontic appliance membrane material can be clearly presented in a data-based and structured manner, providing a scientific basis for material research and development, clinical material selection and industry standard formulation, and providing important support for the healthy development of the entire industry in the material end. SUMMARY

[0009] In one possible implementation, a multi-dimensional performance grading evaluation system for dental shell appliance membrane materials is provided, including a hierarchical modeling module for constructing a performance structure including a basic clinical safety layer, a core orthodontic function layer and an advanced service performance layer, each level being associated with at least one indicator or combination thereof in the following performance dimensions: clinical quality characteristics, biological safety, orthodontic mechanical properties, processing technology characteristics and appearance characteristics.

[0010] In a possible implementation, the basic clinical safety layer is used to characterize whether the material meets the basic usability, and the associated evaluation indexes include at least one or a combination of biological safety, durability, decomposition resistance or swelling characteristics in an oral environment, and elastic modulus; wherein the cytotoxicity inhibition rate is not more than 5% (mass percentage), tested according to the ISO 10993-5 standard; and the elastic modulus is between 800 and 2400 MPa, measured at 23±2°C according to the ISO 527-1 standard.

[0011] In a possible implementation, the core correction function layer is used to characterize the clinical treatment efficiency and effect of the material, and the associated evaluation indexes include at least one or a combination of yield strain rate, stress relaxation rate, and molding process adaptability; wherein the yield strain rate is not less than 2%, tested according to the ISO 527-1 standard; the 24-hour stress relaxation rate is not higher than 15%, tested under static loading in a 37±1°C water bath; and the thickness deviation after thermoforming is not more than ±10%, calculated by comparing a three-dimensional scan with a CAD design model.

[0012] In a possible implementation, the advanced service performance layer is used to characterize the ability of the material in high-level clinical efficiency, long-term durability, and sensory performance, and the associated evaluation indexes include at least one or a combination of shape memory polymer performance, fatigue resistance, dye resistance, light transmittance, and mechanical recovery; wherein the shape recovery rate is not less than 90% after heating for 5 to 15 seconds in a 80°C to 100°C water bath, tested according to the ASTM D790 test method; the ΔE color difference value is not higher than 3, measured according to the CIELab standard under a D65 light source; and the 24-hour creep rate is not higher than 3%, measured at 37±1°C according to the ISO 899-2 standard.

[0013] In a possible implementation, the index acquisition module is further included, configured to acquire measured data of the evaluation indexes by a mechanical testing device, a dynamic mechanical analysis device, a color measurement instrument, a three-dimensional scanning device, and a biological evaluation device, which are respectively used to measure yield stress, tear strength, stress relaxation rate, elastic modulus, yield strain rate, thermal deformation uniformity, surface roughness Ra value, chroma value, cell activity reduction rate, and extractable concentration.

[0014] In a possible implementation, the data processing module is further included, configured to normalize the evaluation index data and calculate scores in the hierarchy and dimension, and the normalization method is Si = (Xi - Xmin) / (Xmax -Xmin), where Si is the index score, Xi is the measured value, Xmin and Xmax are the empirical minimum value and maximum value of the index, respectively.

[0015] In a possible implementation, a weight adjustment module is further included, and the weight adjustment module includes: a weight adjustment engine configured to construct an index correlation model based on a detection result; a prediction model configured to input measured data and combine historical training data to calculate a weight adjustment factor by using a polynomial regression, a random forest, or a gradient boosting algorithm; and a parameter updating unit configured to automatically update weights of each level, dimension, and index according to the weight adjustment factor.

[0016] In a possible implementation, the weight adjustment factor is generated according to one or a combination of the following trigger conditions: when a stress relaxation rate is higher than 15%, the weight of an initial correction force index in an orthodontic mechanical property dimension is increased by 5% to 15%; when a surface roughness Ra measured according to the ISO 4287 standard is greater than 0.8 microns, the weight of a light transmittance index in an appearance property dimension is reduced by 10%; and when a diaphragm creep rate is higher than 3%, the weight of a hysteresis loss index in a high-level service performance layer is increased.

[0017] In a possible implementation, a result output module is further included, configured to output a level score, a dimension score, and a comprehensive score, and generate a structured report including a level radar chart, a Ra value distribution map, a stress-strain curve chart, a shape memory recovery curve, and a performance level suggestion; wherein the performance level is divided into three levels A, B, and C according to the comprehensive score, A level represents that the comprehensive score is greater than or equal to 0.85, B level represents that 0.70 is less than the comprehensive score, and C level represents that the comprehensive score is less than 0.70.

[0018] In a possible implementation, a multi-dimensional performance grading evaluation method for a dental shell instrument diaphragm material is provided, including the following steps: S1, constructing a performance structure including a basic clinical safety layer, a core correction function layer, and a high-level service performance layer, and associating at least one evaluation index in five dimensions of clinical quality characteristics, biological safety, orthodontic mechanical properties, processing technology characteristics, and appearance characteristics for each level; S2, obtaining measured data of the evaluation index by using a mechanical testing device, a biological evaluation device, and a surface or optical measurement device, and testing according to a corresponding international or national standard; S3, performing normalization processing on the measured data, and calculating an index score by using a formula Si = (Xi - Xmin) / (Xmax - Xmin); S4, calling a rule engine or a machine learning model, and dynamically adjusting weights of each level and dimension according to a detection result, wherein historical training data is combined to correct and calibrate a prediction result in the weight adjustment process; S5, calculating a comprehensive score S_total = Σ_j (W_j × Σ_i (w_ij × S_ij)), and generating a comprehensive evaluation report including a level score, a dimension score, a map, a level judgment, and an adaptability analysis, and outputting a performance level according to an A / B / C grading strategy.

[0019] Based on the above technical scheme, the multi-dimensional performance grading evaluation system and method for dental shell-shaped instrument membrane material of the present application realizes comprehensive, objective and quantifiable evaluation of the invisible orthodontic appliance membrane material by constructing a multi-level performance structure covering the basic clinical safety layer, the core orthodontic function layer and the advanced service efficiency layer, and combining normalized calculation, dynamic weight adjustment and multi-dimensional visual output. The system can not only reflect the comprehensive performance of the material in terms of biological safety, mechanical properties, processing adaptability and sensory performance, but also can optimize the weight according to the measured data and historical samples, improve the adaptability and prediction accuracy of the evaluation model to different materials and clinical scenes, and thus provide a scientific basis for material research and development, clinical selection and quality grading. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0021] Figure 1 The figure is a schematic diagram of the overall structure of the multi-dimensional performance grading evaluation system for dental shell-shaped instrument membrane material of the present application.

[0022] Figure 2 The figure is a schematic diagram of the pyramid architecture of the performance level structure of the present application.

[0023] Figure 3 The figure is a schematic diagram of the association between each performance level and performance dimension of the present application.

[0024] Figure 4 The figure is a schematic diagram of each detection device and its measurement index in the index collection module of the present application.

[0025] Figure 5 The figure is a flowchart of the multi-dimensional performance grading evaluation method of the present application. DETAILED DESCRIPTION

[0026] For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application clearer, the following describes the embodiments of the present application through specific examples. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in the present specification. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. The present application can also be implemented or applied through other different specific embodiments, and each detail in the present specification can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0027] It should be noted that the following describes various aspects of embodiments within the scope of the present application. It should be apparent that the aspects described herein can be embodied in a wide variety of forms and that any particular structure and / or function described herein is merely illustrative. Based on the present application, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, the devices and / or methods can be implemented using any number and combination of the aspects set forth herein. In addition, this device and / or method can be implemented using other structures and / or functionality in addition to or other than one or more of the aspects set forth herein.

[0028] The specific embodiments of the present application are further described below with reference to the accompanying drawings. It should be understood that the following embodiments are only used to illustrate the technical solutions of the present application, but not to limit the protection scope of the present application.

[0029] As shown in the Figure 1 The present embodiment discloses a multi-dimensional performance grading evaluation system for dental shell-shaped instrument membrane material, which comprises a system interface layer, a core function layer, a data and model resource layer, and an external detection device layer, and the modules are cooperatively operated through data link and control instructions. The system described in the present embodiment can realize multi-dimensional, hierarchical and traceable performance grading evaluation of dental shell-shaped instrument membrane material through the cooperation between the modules, and is suitable for various application scenarios such as material research and development, quality detection and clinical adaptability verification.

[0030] The system interface layer is used to provide a unified human-computer interaction and data exchange portal for user terminals (including clinical application parties, material researchers, and quality testing agencies), supports access to the system through a graphical interface (GUI) or a REST protocol-based application program interface (API), and completes functions such as initiation of evaluation tasks, data uploading, parameter configuration, report downloading, and historical record inquiry.

[0031] The core function layer includes:

[0032] a. Hierarchical modeling module, used to build a three-layer performance structure model of the basic clinical safety layer, the core orthodontic function layer, and the high-level service efficiency layer, and to associate at least one performance dimension and its quantitative evaluation index under each layer, such as biological safety, orthodontic mechanical properties, processing technology characteristics, appearance characteristics, and clinical quality characteristics. This module supports parameterized modeling and allows adjustment of layer definitions and index mapping relationships under different evaluation scenarios.

[0033] b. Index collection module, used to interface with external testing equipment, obtain multi-dimensional performance raw data of the film material according to a preset collection protocol, and add batch number, timestamp, and tester information to the data to realize traceability of the data source. The collected data types include but are not limited to mechanical properties data, thermal mechanical properties data, optical properties data, three-dimensional geometric feature data, and biological safety data.

[0034] c. Data processing module, used to perform integrity check, outlier rejection, normalization processing, and dimension alignment on the collected raw data. The normalization method can use the minimum-maximum value normalization formula Si = (Xi-Xmin) / (Xmax-Xmin), where Xi is the measured value, Xmin and Xmax are the empirical minimum and maximum values, respectively. The positive and negative indicators are processed in the same direction to ensure the comparability of the score calculation.

[0035] d. Weight adjustment module, including a rule engine and a prediction model. The prediction model can use algorithms such as polynomial regression, random forest, or gradient boosting decision tree (GBDT), and combines historical sample data and current test results to calculate weight adjustment factors for each layer, each dimension, and each index, and updates the scoring model in real time through a parameter update unit. This module supports dynamic weight adjustment based on trigger conditions, such as increasing the weight of relevant indicators in the orthodontic mechanical property dimension when the stress relaxation rate exceeds a set threshold.

[0036] e. The comprehensive scoring and grading module is used to calculate the comprehensive score S_total = Σ_j (W_j × Σ_i (w_ij × S_ij)) based on the adjusted weights and normalized index scores. It can also use the Top-Order Solution Approximation Method (TOPSIS) for verification, and finally classify the material properties into three levels: A, B, and C.

[0037] f. The results output module generates a structured evaluation report, which includes scores for each level, scores for each dimension, a comprehensive score, and corresponding radar charts, Ra value distribution maps, stress-strain curves, shape memory recovery curves, and other graphs. It also provides performance level and suitability recommendations. This module supports exporting the report to PDF, HTML, and other formats, or sending it back to the user terminal via the system interface layer.

[0038] The data and model resource layer includes raw datasets, feature and standard libraries, historical sample libraries, model repositories and version repositories, as well as an audit and traceability log database, which support the various operations and result archiving of the core functional layer. The historical sample library stores membrane performance data and clinical feedback results from different batches and sources, the model repository records the parameters and feature distributions of each version of the model, and the audit log is used to record parameter changes and data retrieval during the scoring process.

[0039] The external testing equipment layer includes mechanical testing devices, dynamic thermomechanical analyzers (DMTA), spectrophotometers, 3D scanning equipment, and biological evaluation devices. Each device connects to the index acquisition module via wired or wireless data interfaces to achieve automated transmission and registration of testing data.

[0040] In one embodiment of the present invention, such as Figure 2 The diagram illustrates a pyramid structure for a multidimensional performance grading and evaluation system of dental shell-shaped instrument membrane materials. This diagram visually demonstrates the division of performance levels and the key performance indicators they encompass in a three-layer structure, facilitating the grading, management, and evaluation of the comprehensive performance of materials under different clinical needs.

[0041] Specifically, the bottom layer is the basic clinical safety layer, used to characterize whether a material meets basic usability requirements. This layer includes performance indicators at least as follows: biocompatibility (tested according to ISO 10993), ability to provide corrective force, ease of processing, aesthetic appearance, and mechanical properties such as elastic modulus, glass transition temperature (Tg), and color. The performance of this layer is a prerequisite for a material to enter clinical use; if the requirements of this layer are not met, further evaluation is unnecessary.

[0042] The intermediate layer is a core orthodontic function layer, which is used to characterize whether the material can effectively achieve treatment efficiency and effect in orthodontic treatment. The performance indicators included in this layer at least include: providing light and stable orthodontic force, better anti-staining performance, excellent wear resistance, good tear resistance, and low stress relaxation rate, etc.; the corresponding quantitative indicators can include elastic modulus, stain resistance, wear resistance, tear strength, and stress relaxation rate, etc. The performance of this layer directly affects the stability of the orthodontic treatment period and the patient experience.

[0043] The uppermost layer is a high-level service performance layer, which is used to characterize whether the material has high-level performance retention ability and differentiated sensory advantage in long-term clinical use. The performance indicators included in this layer at least include: deformation resistance performance (such as yield strain rate, yield stress), fatigue resistance performance (such as bending resistance, fatigue life), high resilience performance, and mechanical loss and hysteresis under cyclic loading, etc. The performance of this layer guarantees that the material can still maintain excellent performance in the complex oral environment of high load and long period, which embodies the high-end performance characteristics of this type of material.

[0044] In one specific embodiment of the present application, as shown in Figure 3 A correlation analysis diagram of performance levels and performance dimensions is provided for intuitively displaying the corresponding relationship between each performance level and the corresponding performance dimension and its importance.

[0045] Specifically, the horizontal axis of the embodiment represents the performance dimension, including biological safety, orthodontic mechanical properties, processing process properties, appearance properties, and clinical quality properties; the vertical axis represents the performance level, including the basic clinical safety layer, the core orthodontic function layer, and the high-level service performance layer.

[0046] In the basic clinical safety layer, the cytotoxicity inhibition rate index under the biological safety dimension is detected by ISO 10993-5 standard, and the critical value is not more than 5% (mass percent); the elastic modulus index under the orthodontic mechanical properties dimension is measured according to ISO 527-1 standard at 23±2℃, and the value range is 800MPa to 2400MPa; the water absorption rate index under the processing process properties dimension is controlled to be not higher than 1.5mg / cm², which is suitable for evaluation of long-term oral service conditions.

[0047] In the core orthodontic function layer, the stress relaxation rate index under the orthodontic mechanical properties dimension is tested under static loading in water bath at 37±1℃, which is required to be not higher than 15%; the thermoforming deviation index under the processing process properties dimension is calculated by comparing and calculating three-dimensional scanning and CAD model, and the deviation should be not more than ±10%; the surface roughness Ra value under the appearance properties dimension is measured according to ISO4287 standard, and the limit value is 0.8μm.

[0048] In the advanced service performance layer, the ΔE color difference value under the appearance characteristics dimension should be measured under a D65 light source according to the CIE Lab standard and should not exceed 3; the clinical breakage rate under the clinical quality characteristics dimension should be controlled below 0.8%; and the shape recovery rate under the orthodontic mechanical characteristics dimension should be measured according to the ASTM D790 standard after heating in a water bath at 80°C to 100°C for 5 to 15 seconds and its recovery rate should not be less than 90%.

[0049] In this embodiment, the position of each bubble corresponds to its respective performance level and performance dimension. The bubble size reflects the importance of the indicator within that level and dimension combination, and the bubble color distinguishes different performance types. The background uses thermal chromatography to display the comprehensive performance score range for each level-dimensional combination.

[0050] In addition, Figure 3 The text also specifically highlights the shape memory characteristic index under the orthodontic mechanical properties dimension in the advanced service performance layer. This area is a key innovation zone, highlighting the important role of this index in improving the clinical service performance of membranes.

[0051] In one embodiment of the present invention, such as Figure 4 The diagram illustrates a testing system flowchart for comprehensive performance evaluation of diaphragm materials used in invisible orthodontic devices. Starting with diaphragm samples, the system acquires performance index data across various dimensions using multiple testing devices. This data is then normalized and weighted by a unified data processing module to form a standardized dataset suitable for comprehensive evaluation.

[0052] Specifically, the membrane samples are first assigned to multiple testing devices to perform the following categories of tests:

[0053] Mechanical performance testing equipment: used to obtain key indicators of the diaphragm's mechanical properties, including at least yield stress (according to ISO 527-1), tear strength (according to ASTM D412), elastic modulus (according to ISO 527-1), yield strain rate (according to YY / T 1819), impact toughness (according to ISO 179), and stress relaxation rate at 37±1℃.

[0054] Dynamic thermomechanical analyzer (DMTA): used to analyze the thermo-mechanical response characteristics of diaphragm materials, including at least creep rate (according to ISO 899-2), storage modulus, loss factor tanδ, and glass transition temperature.

[0055] Color measuring instrument (spectrophotometer): used to evaluate the optical properties of films, including at least ΔE color difference (CIELab / D65), transmittance (according to ASTM D1003), Lab value, and stain resistance.

[0056] Three-dimensional scanning device (three-coordinate positioning instrument): used for determining the geometric and dimensional stability of the film, including at least thermal deformation uniformity, thickness deviation, geometric matching degree, and volume shrinkage rate, etc.

[0057] Biological evaluation device (cell culture system): used for evaluating the biocompatibility of the film, including at least cell activity, oral mucosa irritation, cytotoxicity inhibition rate (according to ISO 10993-5), and extractable concentration (according to ISO 10993-12), etc.

[0058] The raw data obtained by various detection devices will be uniformly summarized into a raw data set and input into a data processing module. In this module, the system normalizes the data from different sources and adjusts according to the preset weight to eliminate the dimensional differences and influences between different test methods, so that the final output comprehensive performance evaluation data has comparability and consistency.

[0059] In one embodiment of the present application, after the film material is subjected to multi-dimensional performance testing (such as the detection system process shown in the foregoing Figure 4 After the multi-source heterogeneous data obtained is subjected to comprehensive analysis and hierarchical evaluation. This embodiment specifically describes the implementation process of the algorithm module.

[0060] First, the raw data from different test devices is imported into the data preprocessing unit through the data acquisition interface. In this unit, the following steps are performed:

[0061] a. Data cleaning: missing values are completed (such as using mean substitution, interpolation method, etc.), and obvious outliers are removed (3σ principle or box plot outlier detection method can be used).

[0062] b. Data normalization: for performance indicators of different dimensions, the data is mapped to the [0, 1] interval using the range standardization (Min-Max Normalization), the formula is as follows:

[0063] x' = (x-x_min) / (x_max-x_min)

[0064] Where x is the original data, x_min and x_max are the minimum and maximum values of the index in the sample set, respectively.

[0065] c. Weight setting: According to the importance of the indicators in clinical application, the weight is calculated by Analytic Hierarchy Process (AHP). In the AHP process, the expert group compares the indicators two by two to form a judgment matrix, and the rationality of the weight is confirmed by consistency check (CR≤0.1).

[0066] Subsequently, the construction and calculation of the comprehensive evaluation model are entered. In order to balance the interpretability and calculation efficiency, the weighted comprehensive scoring method and the TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method are combined to perform performance grading. Among them, the weighted comprehensive scoring method multiplies the normalized index value by the corresponding weight, and sums the weighted results to obtain the comprehensive score of each sample; the TOPSIS analysis constructs the ideal optimal solution and the worst solution on the basis of the normalized matrix, calculates the Euclidean distance of each sample to the optimal solution and the worst solution, and obtains the relative closeness. In actual application, the following grading strategy is adopted in the embodiment:

[0067] a. The comprehensive score and the relative closeness are combined to construct a two-dimensional evaluation space;

[0068] b. The K-means clustering algorithm is used to automatically group the sample points in the two-dimensional space (k=3, corresponding to the basic clinical safety layer, the core correction function layer, and the high-level service efficiency layer);

[0069] c. The cluster centers are determined by the principle of maximizing the inter-class distance and minimizing the intra-class variance, and are dynamically updated after each new sample is added.

[0070] In software implementation, the embodiment uses Python language, combined with open source libraries such as numpy, pandas, scikit-learn, to realize the above algorithm modules, and seamlessly connects with the data processing module of the test system through the built-in API. The algorithm runs on a workstation equipped with GPU acceleration to ensure that the calculation can be completed within 1 second when the number of samples reaches thousands.

[0071] In an embodiment of the present application, for the contact lens film samples after the aforementioned multi-dimensional performance detection and comprehensive algorithm analysis, the system will automatically generate a comprehensive evaluation report. The embodiment specifically describes the generation method, tool selection and landing implementation of the report.

[0072] Firstly, the report generation module receives the output data from the comprehensive evaluation algorithm module, including but not limited to: normalized scores of each performance dimension (such as biological safety, orthodontic mechanical properties, processing technology properties, appearance properties, and clinical quality properties); hierarchical results of each performance level (basic clinical safety level, core correction function level, and advanced service efficiency level); weighted comprehensive score and relative closeness degree of TOPSIS; clustering group number and corresponding clinical evaluation label.

[0073] In the data processing stage, the report generation module performs the following operations:

[0074] a. Data structuring: The above results are double-indexed according to performance dimensions and levels to form a standardized data table (such as CSV or JSON format) that can be called by visualization tools.

[0075] b. Index interpretation: The system automatically calls corresponding technical standards (such as ISO10993-5, ASTM D412, etc.) and threshold definitions from the built-in index explanation database, and compares them with the test values for annotation.

[0076] c. Abnormal identification: For indicators that do not meet the standards, the system highlights them with symbols or text prompts and gives possible reason prompts (for example, "stress relaxation rate is too high, suggest optimizing molecular chain structure").

[0077] In terms of visual presentation, this embodiment selects Python + Matplotlib / Seaborn or Tableau / Power BI visualization tools to generate the following types of charts as needed, including but not limited to: performance radar chart, used to show the relative level of the sample in each performance dimension; performance level pyramid chart, used to map the positioning of the sample in the three-level performance structure; score comparison bar chart, used to compare the comprehensive score and key indicator differences between the target sample and the competitor; clustering distribution scatter plot, used to display the clustering distribution of different samples in the two-dimensional evaluation space.

[0078] The report output part supports multiple formats and methods. In one embodiment, the system calls ReportLab or LaTeX modules to automatically typeset data tables and charts into formal technical reports suitable for archiving and patent submission. In another embodiment, based on Flask / Django + ECharts or Plotly Dash framework, the comprehensive evaluation results are presented in the form of an interactive dashboard, which can be shared within the R&D team. In another embodiment, the report data is pushed to the enterprise's PLM (Product Lifecycle Management) system or MES (Manufacturing Execution System) through RESTful API, realizing the closed loop of production and quality management.

[0079] In the implementation, the report generation module of the embodiment is deployed in a local server or a cloud computing environment (such as AWS, Ali Cloud) with GPU acceleration, and automatically generates reports through a timing task, and supports historical data retrieval and trend analysis functions.

[0080] Compared with the traditional manual collation of detection results, the comprehensive evaluation report of the embodiment does not require manual intervention from data collection, analysis to report generation; all indicators are explained and labeled according to international or industry standards to ensure consistency and comparability of the results; each report is bound to a unique sample number and a generation timestamp, facilitating quality traceability and patent evidence retention; the report template and visualization content can be dynamically adjusted according to subsequent newly added performance indicators or evaluation models.

[0081] In the prior art, the performance detection of different contact lens film materials is often completed by multiple independent institutions or devices, and there is a lack of unified collection standard and data interface between various indicators, resulting in scattered detection results and difficulty in direct integration, affecting the scientificity and comparability of subsequent comprehensive analysis. The present application integrates mechanical testing, dynamic mechanical analysis, optical detection, three-dimensional scanning and biological evaluation and other types of equipment in the data collection module to form a unified data collection process and interface protocol, ensuring that detection data from different sources can be processed and compared in the same coordinate system. This multi-source data fusion method significantly improves the stability and repeatability of the evaluation system, providing a solid foundation for subsequent grading evaluation.

[0082] In addition, the detection results in the prior art are often presented in the form of scattered raw data or single charts, lacking systematic and visualized comprehensive output, which is not convenient for clinicians, researchers and production enterprises to make intuitive decisions. The present application converts the multi-dimensional and multi-level scoring results into structured radar charts, heat maps, stress-strain curves and shape recovery curves through the comprehensive evaluation report output module, and generates performance grade recommendations combined with grading strategies. This visual and comparable output method not only improves the result interpretation efficiency, but also establishes a unified and intuitive material advantage and disadvantage judgment tool for the industry, promoting the benign competition and continuous optimization of the material end.

[0083] In one embodiment of the present application, the steps are as shown in Figure 5 only a preferred embodiment of the present application. As Figure 5As shown, a multi-dimensional performance grading evaluation method for dental shell appliance membrane materials is provided. The method sequentially includes modeling and level configuration, index detection and data acquisition, data integrity and consistency verification, normalization and alignment, weight optimization and condition trigger adjustment, comprehensive score calculation, grading and report output, and incremental update based on clinical feedback. Through the process of "detection-verification-normalization-weight optimization-score-grading-feedback", the multi-dimensional indicators are converted into quantifiable and traceable comprehensive evaluation results, which are suitable for material research and development screening, production quality control and clinical selection decision.

[0084] Firstly, a three-layer performance structure is established, including a basic clinical safety layer, a core orthodontic function layer, and an advanced service efficiency layer. Each layer is associated with quantifiable performance dimensions and indicators, including at least one of biological safety, orthodontic mechanical properties, processing technology characteristics, appearance characteristics, and clinical quality characteristics, or a combination thereof. This configuration is used for subsequent data mapping and grading target alignment.

[0085] Secondly, the membrane sample is sent to a mechanical testing device, a dynamic mechanical thermal analysis device (DMTA), a spectrophotometer, a three-dimensional scanning device, and a biological evaluation device for detection, obtaining raw data such as yield stress, elastic modulus, stress relaxation rate, creep rate, light transmittance, color difference, surface roughness Ra, thickness deviation, extractable concentration, and cytotoxicity inhibition rate, forming a raw data set and recording sample number and batch information for traceability.

[0086] Thirdly, the integrity of the raw data is checked. If missing or abnormal data is found, missing value completion (such as mean substitution or interpolation) is performed, and statistical methods are used to identify and remove outliers (such as 3σ principle or box plot method). Subsequently, consistency and rule verification are performed. Those who do not pass are returned for re-detection or review, and the reason and batch are noted in the data record to achieve traceability throughout the process.

[0087] Then, the data that pass the verification are normalized and dimensionally aligned. Preferably, range standardization is used. For negative indicators with "the smaller the better", the direction is first unified and then normalized to ensure comparability between different indicators.

[0088] Then, in the weight optimization stage, a rule engine works with the prediction model. The prediction model can be a polynomial regression, random forest or gradient boosting algorithm, and the weight adjustment factor is calculated based on normalized data and historical samples; the rule engine constrains or corrects the adjustment factor according to the preset trigger conditions, including but not limited to: (1) when the stress relaxation rate is greater than 15%, the weight of the "initial correction force" index in the orthodontic force mechanical property dimension is increased by 5% to 15%; (2) when the surface roughness Ra measured according to ISO 4287 is greater than 0.8 microns, the weight of the "transparency" index in the appearance property dimension is reduced by 10%; (3) when the creep rate is greater than 3%, the weight of the "hysteresis loss" index in the advanced service performance layer is increased by 5% to 10%. After the above optimization, the latest configuration of the hierarchical weight Wj and the dimension / index weight wij is obtained, which is used for comprehensive scoring.

[0089] Finally, the total score S_total is calculated, using the formula: S_total = Σ_j ( W_j × Σ_i ( w_ij× S_ij ) ), where S_ij is the score of the i-th index under the j-th level, wij is the corresponding index weight, and Wj is the level weight. To improve robustness, the relative closeness Ci of TOPSIS can be introduced to cross-check the comprehensive score to reduce the bias of a single evaluation method. According to the comprehensive score, the grading strategy is executed: A grade for comprehensive score ≥ 0.85; B grade for 0.70 ≤ comprehensive score < 0.85; C grade for comprehensive score < 0.70. The system automatically generates a structured report, which at least includes level score, dimension score, comprehensive score, grade judgment and adaptability suggestion; at the same time, it can be accompanied by a radar chart, Ra value distribution map, stress-strain curve and (if any) shape memory recovery curve. The report binds the sample number, test batch, model version and generation timestamp to ensure quality traceability.

[0090] In this process, if clinical feedback or retest data is obtained, the system will include the new data into the historical sample library, update the feature distribution and model parameters, and realize incremental learning and parameter calibration; if there is no new data, the method process ends. Through this closed loop, the adaptability and prediction accuracy of the weight configuration can be continuously improved.

[0091] Although the traditional evaluation method of invisible orthodontic film lists several physical, chemical and biological performance indicators, it lacks a clear hierarchical division and weight allocation mechanism, making it difficult to reflect the clinical value of the material. The present application realizes the adaptive adjustment of different performance dimensions in the comprehensive score by constructing a three-layer structure of basic clinical safety layer, core orthodontic function layer and advanced service efficiency layer, and introducing a dynamic weight optimization mechanism based on rule engine and machine learning model. This design can dynamically respond to changes in test results, improving the flexibility and scientificity of the evaluation, thereby providing a quantitative standard that can distinguish between good and bad, guide research and development, and select materials for the industry.

[0092] In an embodiment of the present application, a multi-layer shape memory polymer (SMP) film is selected as the evaluation object. The film is composed of a high-resilience polyester layer and a heat-triggered recovery layer, with a thickness of 0.75 mm, prepared by hot pressing lamination process.

[0093] First, the film is cut into 50 mm × 6 mm × thickness long strip samples according to GB / T 1040.2-2006 standard, with smooth edges and no burrs. Each group of samples is not less than 5 pieces, and is placed in an environment of 23±2℃, relative humidity 50±5% for 24 hours.

[0094] Then, the test method refers to ASTM D790, combined with ISO 11359 thermal mechanical property determination method: (1) heat the sample in 80℃, 85℃, 90℃, 95℃, 100℃ water bath for 5 seconds, 10 seconds, 15 seconds respectively; (2) the sample is pre-bent to 180° U shape before heating; (3) observe the shape recovery process immediately after heating without external force, record the shape change by three-dimensional scanning system, calculate the shape recovery rate R_f = (θ_r / θ_0) × 100%, where θ_r is the recovery angle, θ_0 is the initial deformation angle.

[0095] Subsequently, taking the Pro Neo series film as an example, the shape recovery rate is 95% under the condition of heating at 85℃ for 10 seconds, and 91% under the condition of 80℃, both higher than the standard threshold of 90%. Compared with the contrast material (single layer polyester), the recovery rate is increased by about 35%, and the recovery rate is increased by about 12%.

[0096] The shape memory performance data obtained by the above test can be directly used for the advanced service efficiency layer evaluation dimension of the present application system. For materials with a shape recovery rate higher than 90%, they perform well in clinical practice, with high reset accuracy, good wearing adaptability, stable orthodontic force, and can significantly improve the treatment efficiency and patient comfort of the clear aligner.

[0097] Finally, the test results are input as input data through the index collection module of the application, and after normalization by the data processing module, they participate in the comprehensive score calculation. In the weight adjustment module, if the clinical feedback indicates that the shape memory characteristic is significantly better than the average level, the weight of this index in the advanced service performance layer can be automatically increased by 5% to 10%, so as to more accurately reflect its contribution in the overall performance.

[0098] In the existing evaluation standard of invisible aligner materials, the shape memory characteristic is usually a single thermodynamic or mechanical test index, and is not directly related to the adaptability and long-term service performance in the clinical treatment process, resulting in that its technical value cannot be fully utilized. The application includes the shape memory characteristic in the advanced service performance layer, and analyzes it in combination with the mechanical recovery and fatigue resistance, so as to evaluate the stability and recovery performance of the material in the complex oral environment from the actual clinical needs. This layered inclusion not only increases the weight of the index in the comprehensive evaluation, but also provides an evaluation method closer to the clinical application for the industry.

[0099] To verify the technical effect of the application, three kinds of commercially available invisible aligner film materials are respectively evaluated according to the existing single test standard and the layered and graded evaluation system of the application. The existing method needs to list the test results one by one, and each index lacks a unified weight and level judgment, so it is difficult to draw a comprehensive conclusion. The method of the application generates an intuitive radar chart and performance grade judgment by normalizing the test data of each level and each performance dimension, weight distribution and comprehensive score calculation. The results show that the system of the application can clearly reveal the differences in basic clinical safety, core treatment function and advanced service performance of each sample, and give an overall grade judgment. Among them, sample A reaches A level in the comprehensive score, which is obviously better than sample B and sample C; and this conclusion is difficult to directly draw in the existing scattered single index comparison. This shows that the application overcomes the defects of the existing evaluation method, such as lack of weight, no level division and non-intuitive comparison of results, and has significant practical value and popularization significance.

[0100] Finally, it should be pointed out that: the above examples are only used to illustrate the technical solutions of the application, but not to limit them; although the application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the application.

Claims

1. A multidimensional performance grading and evaluation system for dental shell-shaped instrument diaphragm materials, characterized in that, It includes a hierarchical modeling module for constructing a performance structure comprising a basic clinical safety layer, a core orthodontic function layer, and an advanced service performance layer. Each layer is associated with at least one or a combination of the following performance dimensions: clinical quality characteristics, biosafety, orthodontic biomechanical characteristics, manufacturing process characteristics, and appearance characteristics.

2. The system according to claim 1, characterized in that, The basic clinical safety layer is used to characterize whether the material meets basic usability requirements. The associated evaluation indicators include at least one or a combination of biocompatibility, durability, resistance to degradation or swelling in the oral environment, and elastic modulus. The cytotoxicity inhibition rate is not more than 5% (mass percentage), tested according to ISO 10993-5 standard; the elastic modulus is between 800 and 2400 MPa, measured according to ISO 527-1 standard at 23±2℃.

3. The system according to claim 1, characterized in that, The core corrective functional layer is used to characterize the clinical treatment efficiency and effect of the material. The associated evaluation indicators include at least one or a combination of yield strain rate, stress relaxation rate and molding process adaptability. Among them, the yield strain rate is not less than 2%, tested according to ISO 527-1 standard; the 24-hour stress relaxation rate is not higher than 15%, tested under static loading in a water bath at 37±1℃; the thickness deviation after thermoforming is not more than ±10%, calculated by comparing three-dimensional scanning with CAD design model.

4. The system according to claim 1, characterized in that, The advanced service performance layer is used to characterize the material's ability to achieve high levels of clinical efficacy, long-term durability, and sensory performance. The associated evaluation indicators include at least one or a combination of shape memory polymer (SMP) properties, fatigue resistance, stain resistance, light transmittance, and mechanical recovery. Specifically, the shape recovery rate after heating in a water bath at 80°C to 100°C for 5 to 15 seconds is not less than 90%, according to the ASTM D790 test method; the ΔE color difference value is not higher than 3, measured according to the CIE Lab standard under a D65 light source; and the 24-hour creep rate is not higher than 3%, measured according to the ISO 899-2 standard at 37±1°C.

5. The system according to claim 1, characterized in that, It also includes an index acquisition module, which is used to acquire measured data of the evaluation index through mechanical testing device, dynamic thermomechanical analysis (DMTA) equipment, color measuring instrument, three-dimensional scanning device and biological evaluation device. The equipment is used to measure yield stress, tear strength, stress relaxation rate, elastic modulus, yield strain rate, thermal deformation uniformity, surface roughness Ra value, color value, cell activity decline rate and extractable concentration.

6. The system according to claim 1, characterized in that, It also includes a data processing module, which is used to normalize the evaluation index data and calculate the score in terms of hierarchy and dimension. The normalization method is: Si = (Xi - Xmin) / (Xmax - Xmin), where Si is the index score, Xi is the measured value, and Xmin and Xmax are the empirical minimum and maximum values ​​of the index, respectively.

7. The system according to claim 1, characterized in that, It also includes a weight adjustment module, which includes: (1) Weight adjustment engine, used to build an indicator association model based on the detection results; (2) Prediction model, using multinomial regression, random forest or gradient boosting algorithm, inputting actual test data and combining historical training data to calculate the weight adjustment factor; (3) Parameter update unit, used to automatically update the weights of each level, dimension and indicator according to the weight adjustment factor.

8. The system according to claim 7, characterized in that, The weight adjustment factor is generated based on one or a combination of the following triggering conditions: (1) When the stress relaxation rate is higher than 15%, the weight of the initial orthodontic force index under the orthodontic mechanical properties dimension is increased by 5% to 15%; (2) When the surface roughness Ra measured according to ISO 4287 standard exceeds 0.8 micrometers, the weight of the light transmittance index under the appearance properties dimension is reduced by 10%; (3) When the diaphragm creep rate is higher than 3%, the weight of the hysteresis loss index in the advanced service performance layer is increased.

9. The system according to claim 1, characterized in that, It also includes a results output module, which outputs hierarchical scores, dimensional scores, and comprehensive scores, and generates a structured report containing hierarchical radar charts, Ra value distribution maps, stress-strain curves, shape memory recovery curves, and performance level recommendations. The performance level is divided into three levels: A, B, and C, based on the comprehensive score. Level A indicates a comprehensive score ≥ 0.85, Level B indicates a comprehensive score < 0.85 (0.70 ≤ comprehensive score), and Level C indicates a comprehensive score < 0.

70.

10. A multidimensional performance grading and evaluation method for dental shell-shaped instrument diaphragm materials, characterized in that, Includes the following steps: S1, construct a performance structure including a basic clinical safety layer, a core orthodontic function layer and an advanced service performance layer, and associate at least one of the five dimensions of clinical quality characteristics, biosafety, orthodontic mechanical characteristics, processing technology characteristics and appearance characteristics with each level; S2, the measured data of the evaluation index are obtained through mechanical testing device, biological evaluation device and surface or optical measurement device, and the test is carried out in accordance with the corresponding international or national standards; S3, normalize the measured data and calculate the index score using the formula Si = (Xi-Xmin) / (Xmax-Xmin); S4, invoke the rule engine or machine learning model to dynamically adjust the weights of each level and dimension based on the detection results; during the weight adjustment process, the prediction results are corrected and calibrated by combining historical training data; S5 calculates the comprehensive score S_total = Σ_j (W_j × Σ_i (w_ij × S_ij)), and generates a comprehensive evaluation report that includes hierarchical scores, dimensional scores, graphs, level judgments and suitability analysis, and outputs the performance level according to the A / B / C grading strategy.

Images