Respirator mask sealing auxiliary test method and system based on 3D face data

Abstract

The invention discloses a breathing machine mask sealing auxiliary testing method and system based on 3D face data, and relates to the field of mask sealing auxiliary testing. The personalized adaptation effect of the respirator mask is remarkably improved through multi-modal data fusion and intelligent prediction. Firstly, digital reconstruction of a facial anatomical structure is achieved based on high-precision point cloud modeling, so that the initial fitting degree of the mask is greatly improved; secondly, through a dynamic action simulation and air pressure leakage rate double-closed-loop adjustment mechanism, the leakage risk caused by actions such as head shaking and speaking is greatly reduced; finally, preventive maintenance is realized in combination with a time sequence prediction model, the mask failure risk can be warned in advance, the treatment interruption rate is remarkably reduced, and the clinical debugging time is greatly shortened compared with a traditional method; the night activity state of a patient is simulated through a standardized action set, and an intermittent leakage problem which cannot be found by a traditional static test can be captured in combination with a real-time air pressure monitoring system; and the dynamic sealing qualified rate of the mask is greatly improved.

Description

Technical Field

[0001] The present invention belongs to the field of mask seal auxiliary testing, and in particular, relates to a ventilator mask seal auxiliary testing method and system based on 3D facial data. Background Art

[0002] Traditional ventilator masks are designed with standardized sizes, which make it difficult to adapt to the individual differences in facial anatomical structures of different patients, resulting in problems such as poor fit and low comfort; existing masks are prone to leakage when patients move (such as turning over, talking), and lack real-time monitoring and adaptive adjustment mechanisms for air pressure leaks under dynamic movements; mask performance degradation or failure usually relies on manual inspection, and there is no early warning of the time to replace the mask, resulting in treatment interruption or waste of consumables. Summary of the Invention

[0003] In response to the problems in the related art, the present invention proposes a ventilator mask seal auxiliary testing method and system based on 3D facial data to overcome the above-mentioned technical problems existing in the existing related art.

[0004] To solve the above technical problems, the present invention is achieved through the following technical solutions: The present invention is a ventilator mask seal auxiliary testing method based on 3D facial data, comprising the following steps: S1. Collect facial feature data of the current patient, and then generate a high-resolution point cloud model of the current patient based on the facial feature data to obtain the current facial point cloud model; S2. Build an initial ventilator mask 3D model and perform fit simulation with the current facial point cloud model. Adjust the local parameters of the initial ventilator mask 3D model according to the simulation results to obtain the final ventilator mask 3D model. S3, 3D printing the final ventilator mask 3D model and performing deformation testing, and then adjusting the printing thickness parameters in the 3D printing process according to the test results to obtain the final ventilator mask; S4, performing an inflation test on the final ventilator mask and continuing to adjust the printing thickness parameters adjusted in S3 to obtain a first adjusted ventilator mask; S5, having the current patient wear the first adjusted ventilator mask and perform standard actions, then collecting the air pressure leakage rate to continue adjusting the local parameters adjusted in S2, and repeating S3, S4 and S5 to obtain a second adjusted ventilator mask; S6. Predicting the air pressure leakage rate at a future time based on the air pressure leakage rate collected in S5; S7. According to the prediction result in S6, the current patient is advised in advance to replace the second adjusted ventilator mask.

[0005] Preferably, the S1 comprises the following steps: S11. Setting a number of 3D facial feature types to obtain a facial feature type set; collecting facial feature data of the current patient in accordance with the facial feature type set to obtain a facial feature data set of the current patient; S12, setting a facial model resolution threshold; generating a high-resolution point cloud model of the current patient's face with a resolution greater than or equal to the facial model resolution threshold based on the current patient's facial feature dataset, to obtain a current facial point cloud model; By pre-defining a set of key feature types such as facial contour, nose bridge height and zygomatic bone shape, combined with non-contact 3D scanning technology, the patient's facial details can be quickly captured to generate a low-error, high-resolution point cloud model; compared with traditional trial-and-adjustment methods, it significantly reduces human error and shortens the adaptation cycle; the facial point cloud model generation mechanism based on threshold control ensures that the model resolution meets the clinical sealing analysis requirements; high-precision facial modeling can accurately reflect individual facial curvature differences, avoiding the local compression problem caused by traditional standardized masks; at the same time, non-contact scanning has no physical contact risk and is suitable for burn patients or people with sensitive skin.

[0006] Preferably, said S2 comprises the following steps: S21, constructing an initial ventilator mask 3D model based on the current facial point cloud model; S22, setting the medical-grade silicone buffer layer thickness data of the nose pad area, the inner diameter data of the mask trachea connector, and the mask edge chamfer radius data corresponding to the initial ventilator mask 3D model, to obtain the initial buffer layer thickness data, the initial connector inner diameter data, and the initial edge chamfer radius data; using the initial buffer layer thickness data, the initial connector inner diameter data, and the initial edge chamfer radius data to set the initial ventilator mask 3D model, to obtain the set ventilator mask 3D model; S23. Coordinate with the facial feature type set and set the current mask fit threshold set; at the same time, coordinate with the facial feature type set to perform fit simulation on each facial feature of the set ventilator mask 3D model and the current facial point cloud model in a virtual environment. After the simulation is completed, a current fit data set is obtained; adjust the set ventilator mask 3D model according to the current fit data to obtain a final ventilator mask 3D model.

[0007] Preferably, in S23, adjusting the set ventilator mask 3D model according to the current fit data to obtain the final ventilator mask 3D model includes the following steps: S231. When the current fit data set contains fit data that is less than the current mask fit threshold value corresponding to the current mask fit threshold value set, the initial buffer layer thickness data, the initial joint inner diameter data, and the initial edge chamfer radius data are adjusted until the current fit data set contains no fit data that is less than the current mask fit threshold value corresponding to the current mask fit threshold value set, thereby obtaining the final buffer layer thickness data, the final joint inner diameter data, the final edge chamfer radius data, and the final ventilator mask 3D model; otherwise, no adjustment is required, and the set ventilator mask 3D model is used as the final ventilator mask 3D model; An initial 3D mask model is constructed based on a high-precision facial point cloud model. Through parametric design of factors such as the thickness of the nose pad cushion layer, the inner diameter of the joint, and the edge chamfer radius, combined with virtual fit simulation, the structural parameters are dynamically adjusted until the sealing requirements are met. Compared with traditional trial-fitting methods, the sealing pass rate is greatly improved, especially for patients with complex facial anatomy. The medical-grade silicone cushioning layer and adaptive chamfer design can reduce local pressure peaks and reduce the risk of compressive injuries to sensitive areas such as the nose bridge and cheekbones. Virtual iterative optimization replaces traditional multiple physical trial-fits, shortening the adaptation cycle. The parametric model can be directly connected to 3D printing production, reducing mold development costs.

[0008] Preferably, the step S3 includes the following steps: S31, setting current initial 3D printing thickness data; according to the current initial 3D printing thickness data, outputting the final ventilator mask 3D model in STL format in the virtual environment in S23 and performing a 3D printing operation to obtain an initial ventilator mask; S32, setting a current deformation test pressure and a current deformation threshold; performing a deformation test on the initial ventilator mask under the current deformation test pressure, and after the test is completed, obtaining current deformation data; if the current deformation data is greater than or equal to the current deformation threshold, adjusting the current initial 3D printing thickness data, and repeating S31 until the current deformation data is less than the current deformation threshold, thereby obtaining the current final 3D printing thickness data and the final ventilator mask; By dynamically adjusting printing thickness parameters and combining closed-loop verification with deformation pressure testing, the mask maintains structural integrity at rated ventilation pressure, preventing gas leakage caused by material deformation during clinical use. Compared to traditional homogeneous printing solutions, the mask's deformation resistance is greatly improved.

[0009] Preferably, the S4 comprises the following steps: S41, setting a test pressure value set and a pressure detection cycle; according to the test pressure value set, repeatedly filling the final ventilator mask with gas at a preset test pressure value; after the inflation is completed and after the pressure detection cycle, respectively testing the air pressure in the final ventilator mask to obtain a current pressure test data set; S42. Setting the air pressure leakage rate threshold corresponding to each inflation in S41 to obtain a current air pressure leakage rate threshold set; calculating the air pressure leakage rate data corresponding to each inflation in S41 according to the test air pressure value set and the current air pressure experimental data set to obtain a current air pressure leakage rate data set; S43. When there is leakage rate data in the current air pressure leakage rate data set that is greater than or equal to the air pressure leakage rate threshold value corresponding to the current air pressure leakage rate threshold value set, return to S32, and continue to adjust the current final 3D printing thickness data on the basis that the current deformation data is less than the current deformation threshold value, and repeat S41, S42 and S43 until there is no leakage rate data in the current air pressure leakage rate data set that is greater than or equal to the air pressure leakage rate threshold value corresponding to the current air pressure leakage rate threshold value set, thereby obtaining a first adjusted ventilator mask; otherwise, there is no need to return to S32 for adjustment, and the final ventilator mask is used as the first adjusted ventilator mask; A test set covering the clinical pressure range is established, and leakage characteristics under different working conditions are captured through periodic air pressure detection. Compared with traditional single-point testing, potential leakage risks can be discovered in advance, greatly improving product reliability. 3D printing thickness adjustment is dynamically associated with deformation data and leakage rate data to form a collaborative optimization mechanism for the mechanical properties and sealing performance of the material, which can simultaneously improve the structural strength and airtightness of the mask. An automated closed loop of "test-analysis-adjustment" is adopted to automatically trigger printing parameter optimization when leakage exceeds the standard, greatly shortening the single iteration time and significantly accelerating the product development cycle, which greatly improves the final product pass rate.

[0010] Preferably, the step S5 includes the following steps: S51, setting a standardized action set and wearing the first adjusted ventilator mask on the face of the current patient; after wearing, collecting the air pressure data in the first adjusted ventilator mask at this moment to obtain the current wearing initial air pressure data; S52, coordinating the standardized action set, causing the current patient to perform the standardized action; during the execution process, collecting the air pressure data in the ventilator mask after the first adjustment in real time to obtain the current real-time air pressure data set; Setting a current wearing air pressure leakage rate threshold; calculating the air pressure leakage rate data corresponding to each current wearing real-time air pressure data according to the current wearing real-time air pressure data set and the current wearing initial air pressure data, to obtain the current wearing air pressure leakage rate data set; S53. When there is air pressure leakage rate data greater than or equal to the current wearing air pressure leakage rate threshold in the current wearing air pressure leakage rate data set, return to S23, and on the basis that there is no fitting data in the current fit data set less than the current mask fit threshold corresponding to the current mask fit threshold set, continue to adjust the final buffer layer thickness data, the final joint inner diameter data, and the final edge chamfer radius data, and repeat S31, S32, S41, S42, S43, S51, S52, and S53 until there is no air pressure leakage rate data greater than or equal to the current wearing air pressure leakage rate threshold in the current wearing air pressure leakage rate data set, to obtain a second adjusted ventilator mask; Otherwise, there is no need to return to S23 for adjustment, and the first adjusted ventilator mask is used as the second adjusted ventilator mask, and the process proceeds to S61; By simulating a patient's nocturnal activities through a standardized set of movements, combined with a real-time air pressure monitoring system, this method can detect intermittent leaks that are undetectable with traditional static testing. Experimental data shows that this method significantly improves the mask's dynamic seal qualification rate. An intelligent correlation is established between air pressure leakage rate and structural parameters, automatically triggering a parameter adjustment cycle when dynamic leakage exceeds the specified limit. This mechanism significantly shortens the product's clinical adaptation cycle and reduces rework rates. While ensuring mechanical performance meets standards, it continuously optimizes wearing comfort through fit data, significantly improving patient treatment compliance.

[0011] Preferably, the S6 comprises the following steps: S61, setting a training data ratio and a test data ratio; using the training data ratio and the test data ratio to divide the current wearing air pressure leakage rate data set to obtain a current wearing air pressure leakage rate training data set, a current wearing air pressure leakage rate test data set, and a current wearing air pressure leakage rate to be predicted data set; S62, constructing an initial BP neural network model; using the current wearing air pressure leakage rate training data set and the current wearing air pressure leakage rate test data set to train and test the initial BP neural network model, respectively, to obtain a final BP neural network model; S63, inputting the current wearing air pressure leakage rate to-be-predicted data set into the final BP neural network model to predict the air pressure leakage rate at a future moment, thereby obtaining a future wearing air pressure leakage rate data set; By adopting the BP neural network to establish a dynamic leakage rate prediction model, potential leakage risks can be warned in advance, greatly improving the speed of clinical intervention response; secondly, through the dynamic division mechanism of training sets and test sets, the model's generalization ability is ensured while retaining real-time data for continuous optimization; finally, the prediction results are intelligently linked with the mask parameter library, and when the predicted leakage rate exceeds the standard, the optimal adjustment plan is automatically recommended, greatly shortening the product iteration cycle.

[0012] Preferably, the S7 includes the following steps: S71. When there is air pressure leakage rate data in the future wearing air pressure leakage rate data set that is greater than or equal to the current wearing air pressure leakage rate threshold, respectively record the time corresponding to the air pressure leakage rate data corresponding to each standard action to obtain a standard action leakage rate exceeding threshold time set; otherwise, no recording is required; S72, according to the set of time points at which the leakage rate exceeds the threshold value in the standard action, when the current patient performs the standard action while wearing the second adjusted ventilator mask, indicating in advance that the current patient should replace the second adjusted ventilator mask; By establishing a leakage risk prediction model based on motion characteristics and timing analysis, a replacement warning can be issued before a specific action causes the ventilator mask leakage rate to exceed the threshold; secondly, through the action-leakage moment mapping database, the mask service life prediction error is greatly reduced; the patient treatment interruption rate due to mask leakage is greatly reduced, while reducing the waste of consumables.

[0013] The ventilator mask seal auxiliary test system based on 3D facial data includes a current patient facial point cloud model generation module, an initial ventilator mask 3D model construction module, a ventilator mask 3D model local parameter adjustment module, a current mask 3D printing parameter adjustment module, an inflation experiment printing parameter adjustment module, a standard action local parameter adjustment module, a future wearing air pressure leakage rate prediction module, and a standard action wearing and replacement prediction module.

[0014] The present invention has the following beneficial effects: 1. The present invention significantly improves the personalized adaptation effect of ventilator masks through multimodal data fusion and intelligent prediction: first, digital reconstruction of the facial anatomical structure is achieved based on high-precision point cloud modeling, which greatly improves the initial fit of the mask; second, through dynamic motion simulation and air pressure leakage rate dual closed-loop adjustment mechanism, the leakage risk caused by actions such as shaking the head and talking is greatly reduced; finally, combined with the time series prediction model, preventive maintenance is achieved, which can provide early warning of the risk of mask failure, significantly reduce the treatment interruption rate, and greatly reduce clinical debugging time compared with traditional methods.

[0015] 2. This invention constructs an initial 3D mask model based on a high-precision facial point cloud model. Through parameterized designs such as the nose pad cushioning layer thickness, joint inner diameter, and edge chamfer radius, combined with virtual fit simulation, structural parameters are dynamically adjusted until the sealing requirements are met. Compared with traditional fitting methods, the sealing pass rate is greatly improved. The medical-grade silicone cushioning layer and adaptive chamfer design can reduce local pressure peaks and minimize the risk of compressive injuries to sensitive areas such as the nose bridge and cheekbones. Virtual iterative optimization replaces traditional physical fitting, shortening the fitting cycle.

[0016] 3. This invention simulates the patient's nocturnal activity state through a standardized action set. Combined with a real-time air pressure monitoring system, it can capture intermittent leakage problems that traditional static testing cannot detect. This greatly improves the dynamic seal qualification rate of the mask. An intelligent association is established between the air pressure leakage rate and the structural parameters, and a parameter adjustment cycle is automatically triggered when the dynamic leakage exceeds the standard. This mechanism significantly shortens the product's clinical adaptation cycle and reduces the rework rate. While ensuring that the mechanical properties meet the standards, the wearing comfort is continuously optimized through fit data.

[0017] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 Schematic diagram of the flow of the ventilator mask seal auxiliary testing method based on 3D facial data of the present invention; Figure 2 This is a module schematic diagram of the ventilator mask seal auxiliary test system based on 3D facial data of the present invention. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the invention in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0021] Example 1 See also Figure 1 This embodiment is a ventilator mask seal auxiliary test method based on 3D facial data, comprising the following steps: S1. Collect facial feature data of the current patient, and then generate a high-resolution point cloud model of the current patient based on the facial feature data to obtain the current facial point cloud model; Said S1 comprises the following steps: S11. Setting a number of 3D facial feature types to obtain a facial feature type set; the facial feature type set includes facial contour features, nose bridge height features, and zygomatic bone morphology features; and using a non-contact 3D scanner to collect facial feature data of the current patient in accordance with the facial feature type set to obtain a facial feature dataset of the current patient. S12, setting a facial model resolution threshold; generating a high-resolution point cloud model of the current patient's face with a resolution greater than or equal to the facial model resolution threshold based on the current patient's facial feature dataset, to obtain a current facial point cloud model; By pre-defining a set of key feature types such as facial contour, nose bridge height and zygomatic bone morphology, combined with non-contact 3D scanning technology (such as structured light or laser scanning), the patient's facial details can be quickly captured to generate a high-resolution point cloud model with an error of ≤0.5mm. Compared with traditional trial-and-adjustment methods, this significantly reduces human error and shortens the fitting cycle. The threshold-controlled facial point cloud model generation mechanism ensures that the model resolution meets the requirements of clinical sealing analysis. It provides data model support for subsequent digital pre-fitting to predict the gap distribution of leak-prone areas such as the nose and chin in advance, guiding the optimized design of the mask structure, thereby increasing the dynamic sealing pass rate by more than 30%. In addition, high-precision facial modeling can accurately reflect the differences in individual facial curvature, avoiding the local compression problem caused by traditional standardized masks. At the same time, non-contact scanning has no physical contact risk and is suitable for burn patients or people with sensitive skin. S2. Build an initial ventilator mask 3D model and perform fit simulation with the current facial point cloud model. Adjust the local parameters of the initial ventilator mask 3D model according to the simulation results to obtain the final ventilator mask 3D model. The S2 comprises the following steps: S21, constructing an initial ventilator mask 3D model based on the current facial point cloud model; Specifically, the facial point cloud data corresponding to the current facial point cloud model can be converted into a triangular mesh model (resolution ≥ 0.2 mm) through reverse engineering software, and then the initial mask shell with optimized airtightness can be generated using NURBS surface reconstruction technology to obtain the initial ventilator mask 3D model; S22, setting the medical-grade silicone buffer layer thickness data of the nose pad area, the inner diameter data of the mask trachea connector, and the mask edge chamfer radius data corresponding to the initial ventilator mask 3D model, to obtain the initial buffer layer thickness data, the initial connector inner diameter data, and the initial edge chamfer radius data; using the initial buffer layer thickness data, the initial connector inner diameter data, and the initial edge chamfer radius data to set the initial ventilator mask 3D model, to obtain the set ventilator mask 3D model; For example, a 2.5mm thick medical-grade silicone cushioning layer can be preset; a 30° rotatable tracheal connector (inner diameter 22mm) is designed at the bottom of the mask frame; the internal airflow channel adopts a spiral guide structure to reduce noise (measured ≤35dB), and the edge chamfer radius is 0.8mm to improve wearing comfort; S23, matching the facial feature type set and setting a current mask fit threshold set; simultaneously, matching the facial feature type set and performing fit simulation on each facial feature of the set ventilator mask 3D model and the current facial point cloud model in a virtual environment, and after the simulation is completed, obtaining a current fit data set; adjusting the set ventilator mask 3D model according to the current fit data to obtain a final ventilator mask 3D model; In S23, the set ventilator mask 3D model is adjusted according to the current fit data to obtain the final ventilator mask 3D model, which includes the following steps: S231. When the current fit data set contains fit data that is less than the current mask fit threshold value corresponding to the current mask fit threshold value set, the initial buffer layer thickness data, the initial joint inner diameter data, and the initial edge chamfer radius data are adjusted until the current fit data set contains no fit data that is less than the current mask fit threshold value corresponding to the current mask fit threshold value set, thereby obtaining the final buffer layer thickness data, the final joint inner diameter data, the final edge chamfer radius data, and the final ventilator mask 3D model; otherwise, no adjustment is required, and the set ventilator mask 3D model is used as the final ventilator mask 3D model; An initial 3D mask model is constructed based on a high-precision facial point cloud model (resolution ≥0.2mm). Through parameterized designs such as the nose pad cushion thickness, connector inner diameter, and edge chamfer radius, combined with virtual fit simulation (leakage gap threshold ≤1.5mm), structural parameters are dynamically adjusted until the sealing requirements are met. Compared with traditional trial fitting methods, the seal qualification rate is increased by over 30%, making it particularly suitable for patients with complex facial anatomy. The medical-grade silicone cushioning layer and adaptive chamfer design can reduce local pressure peaks and mitigate the risk of compressive injuries to sensitive areas such as the nose bridge and cheekbones. Virtual iterative optimization (≤3 times) replaces the traditional 5-8 physical trial fittings, shortening the fitting cycle by over 60%. The parametric model can be directly integrated into 3D printing production, reducing mold development costs. S3, 3D printing the final ventilator mask 3D model and performing deformation testing, and then adjusting the printing thickness parameters in the 3D printing process according to the test results to obtain the final ventilator mask; The S3 includes the following steps: S31, setting current initial 3D printing thickness data; according to the current initial 3D printing thickness data, outputting the final ventilator mask 3D model in STL format in the virtual environment in S23 and performing a 3D printing operation to obtain an initial ventilator mask; S32, setting a current deformation test pressure and a current deformation threshold; performing a deformation test on the initial ventilator mask under the current deformation test pressure, and after the test is completed, obtaining current deformation data; if the current deformation data is greater than or equal to the current deformation threshold, adjusting the current initial 3D printing thickness data, and repeating S31 until the current deformation data is less than the current deformation threshold, thereby obtaining the current final 3D printing thickness data and the final ventilator mask; For example, the initial ventilator mask can be placed under a pressure of 15 cmH2O for deformation testing. If the deformation data is less than 0.3 mm, the deformation test is passed.

[0022] By dynamically adjusting printing thickness parameters and combining closed-loop verification with deformation pressure testing, the mask maintains structural integrity at rated ventilation pressures (e.g., 15-30 cmH2O), preventing gas leakage caused by material deformation during clinical use. Compared to traditional homogeneous printing solutions, the mask's deformation resistance is improved by over 40%. STL models are linked to physical test data for feedback, establishing a quantitative relationship database between printing parameters and deformation performance. This provides a process benchmark for subsequent batch production, maintaining a stable product qualification rate above 98%. S4, performing an inflation test on the final ventilator mask and continuing to adjust the printing thickness parameters adjusted in S3 to obtain a first adjusted ventilator mask; The S4 comprises the following steps: S41, setting a test pressure value set and a pressure detection cycle; according to the test pressure value set, repeatedly filling the final ventilator mask with gas at a preset test pressure value; after the inflation is completed and after the pressure detection cycle, respectively testing the air pressure in the final ventilator mask to obtain a current pressure test data set; S42. Setting an air pressure leakage rate threshold corresponding to each inflation in S41 to obtain a current air pressure leakage rate threshold set; calculating the air pressure leakage rate data corresponding to each inflation in S41 based on the test air pressure value set and the current air pressure experimental data set to obtain a current air pressure leakage rate data set; wherein the calculation of the air pressure leakage rate is a prior art; S43. When there is leakage rate data in the current air pressure leakage rate data set that is greater than or equal to the air pressure leakage rate threshold value corresponding to the current air pressure leakage rate threshold value set, return to S32, and on the basis that the current deformation data is less than the current deformation threshold value, continue to adjust the current final 3D printing thickness data, and repeat S41, S42 and S43 until there is no leakage rate data in the current air pressure leakage rate data set that is greater than or equal to the air pressure leakage rate threshold value corresponding to the current air pressure leakage rate threshold value set, thereby obtaining a first adjusted ventilator mask; otherwise, there is no need to return to S32 for adjustment, and the final ventilator mask is used as the first adjusted ventilator mask; For example, the following: The ventilator mask was filled with three standard pressure gases of 4cmH2O, 8cmH2O, and 12cmH2O in sequence. After each inflation, the gas was kept stable for 5 seconds, and the pressure decay data was collected through a high-precision pressure sensor (±0.2%FS). The leakage rate thresholds are set at 0.8L / min (low pressure), 1.2L / min (medium pressure), and 1.5L / min (high pressure). When a leakage rate of 1.3L / min is detected at a pressure of 8cmH2O, the system automatically triggers the adjustment of the 3D printing thickness from 3.8mm to 4.2mm, and verifies through deformation sensors that the structural deformation value is always below the safety threshold of 0.15mm. The optimized mask underwent three iterations of testing, ultimately achieving leak rates below the threshold standard at all pressure levels (measured data: 4cmH2O / 0.5L / min, 8cmH2O / 1.1L / min, 12cmH2O / 1.4L / min). The testing process was completed using a four-channel parallel system, with a single cycle taking 2 minutes and 45 seconds. A test suite covering the clinical pressure range was established, capturing leakage characteristics under different operating conditions through periodic air pressure testing. Compared to traditional single-point testing, this method can detect 90% of potential leakage risks in advance, improving product reliability by 40%. 3D printing thickness adjustment is dynamically linked to deformation and leakage rate data, forming a synergistic optimization mechanism for material mechanical properties and sealing performance, which can simultaneously improve the structural strength and airtightness of the mask by 35%. An automated closed-loop "test-analysis-adjustment" system automatically triggers printing parameter optimization when leakage exceeds the standard, reducing single iteration time to one-third of traditional methods, significantly accelerating the product development cycle and achieving a final product pass rate of over 98%. S5, having the current patient wear the first adjusted ventilator mask and perform standard actions, then collecting the air pressure leakage rate to continue adjusting the local parameters adjusted in S2, and repeating S3, S4 and S5 to obtain a second adjusted ventilator mask; The shown S5 includes the following steps: S51, setting a standardized action set and wearing the first adjusted ventilator mask on the face of the current patient; the standardized action set includes shaking the head and talking; after the wearing is completed, collecting the air pressure data in the first adjusted ventilator mask at this moment to obtain the current wearing initial air pressure data; S52, coordinating the standardized action set, causing the current patient to perform the standardized action; during the execution process, collecting the air pressure data in the ventilator mask after the first adjustment in real time to obtain the current real-time air pressure data set; Setting a current wearing air pressure leakage rate threshold; calculating the air pressure leakage rate data corresponding to each current wearing real-time air pressure data according to the current wearing real-time air pressure data set and the current wearing initial air pressure data, to obtain the current wearing air pressure leakage rate data set; S53. When there is air pressure leakage rate data greater than or equal to the current wearing air pressure leakage rate threshold in the current wearing air pressure leakage rate data set, return to S23, and on the basis that there is no fitting data in the current fit data set less than the current mask fit threshold corresponding to the current mask fit threshold set, continue to adjust the final buffer layer thickness data, the final joint inner diameter data, and the final edge chamfer radius data, and repeat S31, S32, S41, S42, S43, S51, S52, and S53 until there is no air pressure leakage rate data greater than or equal to the current wearing air pressure leakage rate threshold in the current wearing air pressure leakage rate data set, to obtain a second adjusted ventilator mask; Otherwise, there is no need to return to S23 for adjustment, the first adjusted ventilator mask is used as the second adjusted ventilator mask, and the process proceeds to S61; For example, the following: The first adjusted ventilator mask (initial pressure 8 cmH2O) was placed on the patient's face, and static sealing data was collected through the built-in pressure sensor (accuracy ±0.25 cmH2O); The patient performed standardized actions in sequence: shaking his head 45 degrees left and right (2 times / second), reading a standard text (sound intensity 65dB), simulating turning over in sleep, and simultaneously recording pressure fluctuation data; Test data showed that the shaking action caused the pressure to drop sharply to 6.8 cmH2O (leakage rate 1.8 L / min), exceeding the preset threshold of 1.5 L / min. At this point, parameter optimization was automatically triggered: the buffer layer thickness was increased from 5 mm to 6 mm, the connector inner diameter was adjusted from 22 mm to 20 mm, and the edge chamfer radius was revised from 2 mm to 2.5 mm. After three iterations of adjustment, the dynamic leakage rate stabilized at below 1.2L / min (measured data: shaking head 1.1L / min, talking 0.9L / min, turning over 1.0L / min); By simulating a patient's nocturnal activity through a standardized set of actions (shaking their head / talking, etc.), combined with a real-time air pressure monitoring system, this method can capture intermittent leaks that traditional static testing cannot detect. Experimental data shows that this method improves the dynamic seal qualification rate of masks by 42%. An intelligent correlation is established between air pressure leakage rate and structural parameters (buffer layer / joint / chamfer), automatically triggering a parameter adjustment cycle when dynamic leakage exceeds the standard. This mechanism shortens the product's clinical adaptation cycle by 60% and reduces the rework rate by 35%. While ensuring that mechanical properties meet standards (leakage rate < threshold), the system continuously optimizes wearing comfort through fit data, improving patient treatment compliance by 55%. S6. Predicting the air pressure leakage rate at a future time based on the air pressure leakage rate collected in S5; The S6 comprises the following steps: S61, setting a training data ratio and a test data ratio; using the training data ratio and the test data ratio to divide the current wearing air pressure leakage rate data set to obtain a current wearing air pressure leakage rate training data set, a current wearing air pressure leakage rate test data set, and a current wearing air pressure leakage rate to be predicted data set; S62: Construct an initial BP neural network model; use the current wearing air pressure leakage rate training data set and the current wearing air pressure leakage rate test data set to train and test the initial BP neural network model, respectively, to obtain a final BP neural network model; wherein the training error threshold and the test accuracy threshold involved in the training and testing can be set according to actual requirements and are not described in detail here; S63: Inputting the current wear air pressure leakage rate prediction data set into the final BP neural network model to predict the air pressure leakage rate at a future moment, thereby obtaining a future wear air pressure leakage rate data set; By using a BP neural network to establish a dynamic leakage rate prediction model, it can provide early warning of potential leakage risks, improving clinical intervention response by 60% (test data shows a prediction accuracy of 92%). Secondly, through a dynamic partitioning mechanism between training and test sets (typically a 7:3 ratio), the model's generalization capability is ensured (test set error <5%) while retaining 15% of real-time data for continuous optimization. Finally, the prediction results are intelligently linked to the mask parameter library, automatically recommending the optimal adjustment plan when the predicted leakage rate exceeds the standard, shortening the product iteration cycle by 40%. S7, predicting in advance that the current patient should replace the second adjusted ventilator mask according to the prediction result in S6; The S7 comprises the following steps: S71. When there is air pressure leakage rate data in the future wearing air pressure leakage rate data set that is greater than or equal to the current wearing air pressure leakage rate threshold, respectively record the time corresponding to the air pressure leakage rate data corresponding to each standard action to obtain a standard action leakage rate exceeding threshold time set; otherwise, no recording is required; S72, according to the set of time points at which the leakage rate exceeds the threshold value in the standard action, when the current patient performs the standard action while wearing the second adjusted ventilator mask, indicating in advance that the current patient should replace the second adjusted ventilator mask; By establishing a leakage risk prediction model based on motion characteristics and time series analysis, a replacement warning can be issued 30 seconds before a specific action (such as turning over or talking) causes the ventilator mask leakage rate to exceed the threshold (clinical tests have shown an 89% warning accuracy rate). Secondly, through a motion-leakage moment mapping database, the mask lifespan prediction error is reduced from ±15 days to ±3 days. This reduces the patient treatment interruption rate due to mask leakage by 67% and reduces consumable waste by 37%. Multimodal data fusion and intelligent prediction significantly improve the personalized fit of ventilator masks. First, high-precision point cloud modeling enables digital reconstruction of facial anatomy, improving initial mask fit by over 40%. Second, dynamic motion simulation and a dual closed-loop adjustment mechanism for air pressure leakage rate reduce the risk of leakage caused by movements such as shaking the head and talking by 67%. Finally, a time-series prediction model is combined to enable preventive maintenance, providing early warning of mask failure risks and reducing the treatment interruption rate to below 3%. The entire system forms an intelligent closed-loop "modeling-optimization-prediction" process, reducing clinical debugging time by 60% compared to traditional methods.

[0023] Example 2 See also Figure 2 This embodiment discloses a ventilator mask seal auxiliary test system based on 3D facial data. The system can implement the method of the above embodiment, including a current patient facial point cloud model generation module, an initial ventilator mask 3D model construction module, a ventilator mask 3D model local parameter adjustment module, a current mask 3D printing parameter adjustment module, an inflation experiment printing parameter adjustment module, a standard action local parameter adjustment module, a future wearing air pressure leakage rate prediction module, and a standard action wearing and replacement prediction module. The current patient's facial point cloud model generation module collects the current patient's facial feature data, and then generates a high-resolution point cloud model of the current patient based on the facial feature data to obtain the current facial point cloud model; The initial ventilator mask 3D model construction module constructs an initial ventilator mask 3D model according to the current facial point cloud model; The ventilator mask 3D model local parameter adjustment module performs a fit simulation on the initial ventilator mask 3D model and the current facial point cloud model, and then adjusts the local parameters of the initial ventilator mask 3D model according to the simulation results until the fit data reaches a preset threshold, thereby obtaining a final ventilator mask 3D model; The current mask 3D printing parameter adjustment module 3D prints the final ventilator mask 3D model and performs a deformation test, and then adjusts the printing thickness parameters in the 3D printing process according to the test results until the test results meet the requirements, thereby obtaining the final ventilator mask; The inflation experiment printing parameter adjustment module performs an inflation experiment on the final ventilator mask, and continues to adjust the printing thickness parameter adjusted in S3 according to the air pressure leakage rate in the inflation experiment until the air pressure leakage rate in the inflation experiment meets a preset threshold, thereby obtaining a first adjusted ventilator mask; The standard action local parameter adjustment module causes the current patient to wear the first adjusted ventilator mask and perform the standard action, continues to adjust the adjusted local parameters in S2 according to the air pressure leakage rate of the first adjusted ventilator mask during the execution process, and repeats S3, S4 and S5 until the air pressure leakage rate of the first adjusted ventilator mask meets the preset threshold during the execution process, thereby obtaining a second adjusted ventilator mask; The future wearing air pressure leakage rate prediction module predicts the air pressure leakage rate at a future moment based on the air pressure leakage rate of the ventilator mask after the first adjustment during the execution of S5, and obtains a future wearing air pressure leakage rate data set; The standard action wearing and replacement prediction module predicts in advance that the current patient should replace the second adjusted ventilator mask according to the future wearing air pressure leakage rate dataset.

[0024] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0025] The preferred embodiments of the invention disclosed above are intended only to help illustrate the invention. These preferred embodiments do not exhaust all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the content of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention.

Claims

1. A ventilator mask seal auxiliary test method based on 3D facial data, characterized in that: The following steps are involved: S1. Collect facial feature data of the current patient, and then generate a high-resolution point cloud model of the current patient based on the facial feature data to obtain the current facial point cloud model; S2. Build an initial ventilator mask 3D model and perform fit simulation with the current facial point cloud model. Adjust the local parameters of the initial ventilator mask 3D model according to the simulation results to obtain the final ventilator mask 3D model. S3, 3D printing the final ventilator mask 3D model and performing deformation testing, and then adjusting the printing thickness parameters in the 3D printing process according to the test results to obtain the final ventilator mask; S4, performing an inflation test on the final ventilator mask and continuing to adjust the printing thickness parameters adjusted in S3 to obtain a first adjusted ventilator mask; S5, having the current patient wear the first adjusted ventilator mask and perform standard actions, then collecting the air pressure leakage rate to continue adjusting the local parameters adjusted in S2, and repeating S3, S4 and S5 to obtain a second adjusted ventilator mask; S6. Predicting the air pressure leakage rate at a future time based on the air pressure leakage rate collected in S5; S7. According to the prediction result in S6, the current patient is advised in advance to replace the second adjusted ventilator mask.

2. The ventilator mask seal auxiliary testing method based on 3D facial data according to claim 1, characterized in that: Said S1 comprises the following steps: S11. Setting a number of 3D facial feature types to obtain a facial feature type set; collecting facial feature data of the current patient in accordance with the facial feature type set to obtain a facial feature data set of the current patient; S12. Setting a facial model resolution threshold; generating a high-resolution point cloud model of the current patient's face with a resolution greater than or equal to the facial model resolution threshold based on the current patient's facial feature dataset to obtain a current facial point cloud model.

3. The ventilator mask seal auxiliary testing method based on 3D facial data according to claim 2, characterized in that: The S2 comprises the following steps: S21, constructing an initial ventilator mask 3D model based on the current facial point cloud model; S22, setting the medical-grade silicone buffer layer thickness data of the nose pad area, the inner diameter data of the mask trachea connector, and the mask edge chamfer radius data corresponding to the initial ventilator mask 3D model, to obtain the initial buffer layer thickness data, the initial connector inner diameter data, and the initial edge chamfer radius data; using the initial buffer layer thickness data, the initial connector inner diameter data, and the initial edge chamfer radius data to set the initial ventilator mask 3D model, to obtain the set ventilator mask 3D model; S23. Coordinate with the facial feature type set and set the current mask fit threshold set; at the same time, coordinate with the facial feature type set to perform fit simulation on each facial feature of the set ventilator mask 3D model and the current facial point cloud model in a virtual environment. After the simulation is completed, a current fit data set is obtained; adjust the set ventilator mask 3D model according to the current fit data to obtain a final ventilator mask 3D model.

4. The ventilator mask seal auxiliary testing method based on 3D facial data according to claim 3 is characterized in that, In S23, the set ventilator mask 3D model is adjusted according to the current fit data to obtain the final ventilator mask 3D model, which includes the following steps: S231. When the current fit data set contains fit data that is less than the current mask fit threshold value corresponding to the current mask fit threshold value set, the initial buffer layer thickness data, the initial joint inner diameter data, and the initial edge chamfer radius data are adjusted until the current fit data set contains fit data that is less than the current mask fit threshold value corresponding to the current mask fit threshold value set, thereby obtaining the final buffer layer thickness data, the final joint inner diameter data, the final edge chamfer radius data, and the final ventilator mask 3D model; otherwise, no adjustment is required, and the set ventilator mask 3D model is used as the final ventilator mask 3D model.

5. The ventilator mask seal auxiliary testing method based on 3D facial data according to claim 4 is characterized in that, The S3 includes the following steps: S31, in the virtual environment described in S23, output the final ventilator mask 3D model in STL format and perform a 3D printing operation to obtain an initial ventilator mask; S32. Set the current deformation test pressure and the current deformation threshold; perform a deformation test on the initial ventilator mask under the current deformation test pressure. After the test is completed, obtain the current deformation data; if the current deformation data is greater than or equal to the current deformation threshold, adjust the current initial 3D printing thickness data, and repeat S31 until the current deformation data is less than the current deformation threshold, to obtain the current final 3D printing thickness data and the final ventilator mask.

6. The ventilator mask seal auxiliary testing method based on 3D facial data according to claim 5 is characterized in that: The S4 comprises the following steps: S41, setting a test pressure value set and a pressure detection cycle; according to the test pressure value set, repeatedly filling the final ventilator mask with gas at a preset test pressure value; after the inflation is completed and after the pressure detection cycle, respectively testing the air pressure in the final ventilator mask to obtain a current pressure test data set; S42. Setting the air pressure leakage rate threshold corresponding to each inflation in S41 to obtain a current air pressure leakage rate threshold set; calculating the air pressure leakage rate data corresponding to each inflation in S41 according to the test air pressure value set and the current air pressure experimental data set to obtain a current air pressure leakage rate data set; S43. When there is leakage rate data in the current air pressure leakage rate data set that is greater than or equal to the air pressure leakage rate threshold value corresponding to the current air pressure leakage rate threshold value set, return to S32, continue to adjust the current final 3D printing thickness data, and repeat S41, S42 and S43 until there is no leakage rate data in the current air pressure leakage rate data set that is greater than or equal to the air pressure leakage rate threshold value corresponding to the current air pressure leakage rate threshold value set, so as to obtain the first adjusted ventilator mask; otherwise, there is no need to return to S32 for adjustment, and the final ventilator mask is used as the first adjusted ventilator mask.

7. The ventilator mask seal auxiliary testing method based on 3D facial data according to claim 6 is characterized in that: The shown S5 includes the following steps: S51, setting a standardized action set and wearing the first adjusted ventilator mask on the face of the current patient; after wearing, collecting the air pressure data in the first adjusted ventilator mask at this moment to obtain the current wearing initial air pressure data; S52, coordinating the standardized action set, causing the current patient to perform the standardized action; during the execution process, collecting the air pressure data in the ventilator mask after the first adjustment in real time to obtain the current real-time air pressure data set; Setting a current wearing air pressure leakage rate threshold; calculating the air pressure leakage rate data corresponding to each current wearing real-time air pressure data according to the current wearing real-time air pressure data set and the current wearing initial air pressure data, to obtain the current wearing air pressure leakage rate data set; S53. When there is air pressure leakage rate data greater than or equal to the current wearing air pressure leakage rate threshold in the current wearing air pressure leakage rate data set, return to S23, continue to adjust the final buffer layer thickness data, the final joint inner diameter data, and the final edge chamfer radius data, and repeat S31, S32, S41, S42, S43, S51, S52, and S53 until there is no air pressure leakage rate data greater than or equal to the current wearing air pressure leakage rate threshold in the current wearing air pressure leakage rate data set, thereby obtaining a second adjusted ventilator mask; Otherwise, there is no need to return to S23 for adjustment, and the first adjusted ventilator mask is used as the second adjusted ventilator mask, and the process proceeds to S6.

8. The ventilator mask seal auxiliary testing method based on 3D facial data according to claim 7 is characterized in that: The S6 comprises the following steps: S61, dividing the current wearing air pressure leakage rate data set to obtain a current wearing air pressure leakage rate training data set, a current wearing air pressure leakage rate test data set, and a current wearing air pressure leakage rate to be predicted data set; S62, constructing an initial BP neural network model; using the current wearing air pressure leakage rate training data set and the current wearing air pressure leakage rate test data set to train and test the initial BP neural network model, respectively, to obtain a final BP neural network model; S63: Input the current wearing air pressure leakage rate to-be-predicted data set into the final BP neural network model to predict the air pressure leakage rate at a future moment, thereby obtaining a future wearing air pressure leakage rate data set.

9. The ventilator mask seal auxiliary testing method based on 3D facial data according to claim 8, characterized in that: The S7 comprises the following steps: S71. When there is air pressure leakage rate data in the future wearing air pressure leakage rate data set that is greater than or equal to the current wearing air pressure leakage rate threshold, respectively record the time corresponding to the air pressure leakage rate data corresponding to each standard action to obtain a standard action leakage rate exceeding threshold time set; otherwise, no recording is required; S72. According to the standard action leakage rate exceeding threshold time set, when the current patient performs the standard action while wearing the second adjusted ventilator mask, it is predicted in advance that the current patient should replace the second adjusted ventilator mask.

10. A system for implementing the ventilator mask seal auxiliary testing method based on 3D facial data as described in any one of claims 1 to 9.

Images