Active closed-loop fitting degree control method for intelligent protective glasses

Abstract

The invention provides an active closed-loop fitting degree control method for intelligent protective glasses, and belongs to the technical field of intelligent wearable equipment and man-machine interaction control. According to the method, wearing state data are collected by integrating a pressure sensor, a distance sensor and a temperature and humidity sensor, the temperature difference delta Tdew between the lens surface temperature and the air dew point temperature is calculated to quantify the fogging risk, and comprehensive evaluation is carried out in combination with the fitting state; a control instruction is generated according to a preset priority rule, high-risk anti-fog and oppression discomfort conditions are processed preferentially, and a micro-actuator is driven to dynamically adjust the fitting degree of the glasses; the control effect is continuously optimized through closed-loop feedback, and parameter self-learning based on user behaviors is supported. According to the scheme, intelligent cooperative balance of sealing performance, comfort and anti-fog performance is achieved, the self-adaptive capacity and user experience of the protective glasses in a complex environment are improved, and the protective glasses are suitable for being applied to multiple scenes such as industry and medical treatment.

Description

Technical Field

[0001] The technical field of this application is intelligent wearable devices and human-computer interaction control technology, specifically involving an active closed-loop fit control method for intelligent protective glasses. Background Technology

[0002] With the widespread application of smart wearable devices in industrial safety, medical protection, and augmented reality, smart protective glasses, as a key carrier of human-computer interaction and physical barriers, directly depend on the quality of their dynamic fit to the wearer's face. An ideal fit must ensure airtightness to block harmful particles or liquids while also providing comfort for extended wear and mitigating the risk of lens fogging caused by changes in ambient temperature and humidity. However, current technologies generally treat fit as a static or single-objective problem, making it difficult to achieve adaptive and coordinated control under multiple constraints within a limited space. This results in a significant reduction in actual protective effectiveness and user experience.

[0003] While active fit adjustment technology has initially incorporated sensing and actuation units, its control logic still heavily relies on simplified assumptions about facial geometry. Some solutions attempt to invert facial contours through pressure distribution, but neglect the non-rigidity and time-varying characteristics of soft tissue, as well as the perturbation effect of sensor measurements on local deformation, resulting in a lack of robustness in real-world wearing scenarios for the constructed mapping model. Other designs stack multiple functional modules to address anti-fogging or dust removal needs, but these subsystems are isolated from each other, failing to establish a quantitative correlation between fit, sealing, and environmental risk, and lacking a priority-based dynamic decision-making mechanism, thus unable to intelligently balance conflicting objectives.

[0004] Existing technologies generally suffer from hardware redundancy and rigid control. The multiple micro-actuators deployed to achieve multi-degree-of-freedom adjustment not only exceed the spatial limitations of the eyeglass structure, but their complex driving logic also significantly increases power consumption and cost. More critically, current systems generally employ a threshold-triggered "stimulus-response" model, unable to predict environmental changes (such as fogging thresholds) or continuously optimize control parameters based on individual differences. Therefore, on a strictly constrained miniaturized platform, there is an urgent need for a closed-loop fit control method that integrates multimodal perception, rule-driven decision-making, and personalized learning capabilities to truly achieve an organic unity of safety, comfort, and functional stability. Summary of the Invention

[0005] This application provides an active closed-loop fit control method for smart protective glasses, which can solve the technical problems of traditional protective glasses being unable to balance sealing, wearing comfort and anti-fog performance in dynamic use environments, and lacking intelligent decision-making and personalized adaptation capabilities.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: An active closed-loop fit control method for smart protective glasses includes the following steps: Step S1, Multi-source information perception: Acquire measurement data from pressure sensors, distance sensors, and temperature and humidity sensors located at key contact points of smart protective glasses; Step S2, Comprehensive assessment of fit and risk: Based on the measurement data from the pressure sensor, distance sensor, and temperature and humidity sensor, a real-time fit status assessment result and a fogging risk level are calculated; wherein, the fogging risk level is calculated by determining the temperature difference ΔT between the lens surface temperature and the dew point temperature of the air near the lens. dew To determine; Step S3, Intelligent Collaborative Decision Making: Based on the fit status assessment results and fogging risk level, control commands are generated according to preset priority decision rules. The priority decision rules include: when the fogging risk level exceeds a preset risk threshold, an anti-fog adjustment command is triggered first; when the pressure value exceeds a comfort pressure threshold, a relaxation command is triggered; when the gap value exceeds a gap threshold or the pressure value is lower than a sealing pressure threshold, a tightening command is triggered. Step S4, drive execution adjustment: The control command is sent to the micro-drive actuator integrated on the glasses, which drives the actuator to change the fit between the glasses and the face; Step S5, closed-loop feedback: After the adjustment is performed, return to step S1 to form a closed-loop control circuit.

[0007] Furthermore, in step S2, the temperature difference ΔT between the lens surface temperature and the dew point temperature of the air near the lens is calculated. dew Specifically, this includes: the temperature T measured by the temperature and humidity sensor. air Calculate the dew point temperature T based on the relative humidity RH. dew The internal surface temperature T of the lens was estimated using an empirical model. surface ; through the T surface and T dew Calculate ΔT dew =T surface -T dew .

[0008] Furthermore, the preset priority decision rule in step S3 is specifically as follows: when ΔT dew When the temperature difference is less than the first temperature difference threshold, it is determined to be a high risk of fogging, triggering an anti-fogging adjustment command; when the pressure value P is greater than the maximum comfort pressure P... max When the gap value D is greater than the maximum allowable gap D, a relaxation command is triggered.threshold Or the pressure value P is less than the minimum sealing pressure P min When the maximum comfort pressure is greater than the minimum sealing pressure, a tightening command is triggered.

[0009] Specifically, the anti-fog adjustment command includes controlling the micro-drive actuator to slightly relax, so as to create an anti-fog gap between the glasses and the face.

[0010] Furthermore, the active closed-loop fit control method for smart protective glasses also includes a parameter self-learning step: recording the sensor data combination when the user manually adjusts the glasses or when the system reaches a stable state; and adaptively adjusting at least one of the comfort pressure threshold, sealing pressure threshold, gap threshold, and risk threshold based on the recorded data.

[0011] Furthermore, the key contact areas in step S1 include at least one of the nose pad area, the inner contact area of ​​the temple, and the lower edge area of ​​the frame.

[0012] Furthermore, the real-time fit status assessment in step S2 includes a sealing status assessment and a comfort assessment; wherein, the sealing status assessment is based on the gap value and the pressure value; and the comfort assessment is based on the pressure value and its distribution characteristics.

[0013] Furthermore, in step S4, changing the fit between the glasses and the face is achieved by adjusting at least one of the following methods: temple clamping force, nose pad support height, or frame curvature.

[0014] Furthermore, step S3 also includes a motion state compensation step: acquiring inertial measurement unit data to sense the user's head motion state; and dynamically adjusting the priority decision rule according to the motion state.

[0015] Furthermore, in step S5, the cycle period of the closed-loop control loop is adaptively adjusted according to the rate of change of the sensor data.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention constructs a complete closed-loop control system of "perception-evaluation-decision-execution-feedback", and achieves multi-objective collaborative optimization of sealing performance, comfort and anti-fog performance on the basis of a single micro-drive actuator, which significantly reduces system complexity and power consumption and improves the feasibility of miniaturization; 2. Introduce a model based on the lens surface temperature and the dew point temperature difference ΔT. dew The fog risk quantification model, combined with priority decision rules, enables the system to have predictive fog prevention capabilities, and can actively adjust ventilation conditions before fog occurs, breaking through the traditional passive response mode. 3. The proposed multi-level priority decision-making mechanism can dynamically coordinate conflicting goals such as safety, sealing and comfort, prioritize the handling of high-risk events, and support dynamic adjustment of rules under motion conditions, thereby enhancing the robustness and adaptability of the system in complex usage scenarios. 4. By recording steady-state or user-labeled data and adaptively updating key threshold parameters, the system can gradually adapt to the facial features and subjective preferences of individual users, achieve long-term personalized optimization, and improve user experience stickiness; 5. The control logic is built entirely on measurable physical quantities, without relying on complex modeling or unreliable inference. The technical path is clear, the engineering implementation is strong, and it is suitable for a variety of application scenarios such as industrial dust prevention, medical isolation, and augmented reality. Attached Figure Description

[0017] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings.

[0018] Figure 1 This is a schematic diagram of the overall technical solution architecture of the active closed-loop fit control method for smart protective glasses proposed in this invention. Figure 2 This is a schematic diagram of the core principle framework of intelligent collaborative control based on multi-source perception and priority decision rules in this invention; Figure 3 This is a flowchart illustrating the logical process framework for the comprehensive assessment of bonding status and fogging risk in this invention. Figure 4 This is a schematic diagram of the multi-level interaction relationship and data flow between the micro-drive actuator and the multi-target adjustment mechanism in this invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0020] refer to Figure 1 This invention proposes an active closed-loop fit control method for smart protective glasses. The method comprises five core functional modules: a multi-source information sensing unit, a fit status and risk comprehensive assessment module, an intelligent collaborative decision-making engine, a micro-drive actuator, and a closed-loop feedback adjustment mechanism. Each component interacts with the other via an embedded controller for high-speed data exchange and command scheduling, constructing a complete "perception-assessment-decision-execution-feedback" closed-loop control system.

[0021] The method includes the following steps: Step S1, Multi-source information perception: Acquire measurement data from pressure sensors, distance sensors, and temperature and humidity sensors located at key contact points of smart protective glasses.

[0022] Specifically, the key contact areas include at least one of the nose pad area, the inner contact area of ​​the temple, and the lower edge area of ​​the frame. In terms of engineering implementation, the pressure sensor employs a flexible piezoresistive thin-film array with a thickness not exceeding 0.2 mm. It possesses high sensitivity (range 0 to 5 kPa, resolution better than 10 Pa) and good biocompatibility, and can be fitted to the inner side of the silicone pad of the nose pad and under the soft pad at the end of the temple for real-time monitoring of local contact pressure and its two-dimensional distribution. The distance sensor uses a miniature infrared time-of-flight ranging module, measuring 3 mm x 3 mm x 1 mm, deployed on the inner side of the lower edge of the frame and the bottom of the nose pad. It is used for non-contact measurement of the instantaneous gap between the eyeglass frame and facial skin, with an effective ranging range of 0 to 5 mm and an accuracy of ±0.1 mm. The temperature and humidity sensor uses a digital integrated chip with a package size of 2 mm x 2 mm, installed in a concealed position on the inner side of the lens near the bridge of the nose, for synchronously collecting ambient air temperature T. air The temperature measurement range is -10 to 60 degrees Celsius with an accuracy of ±0.3 degrees Celsius, and the humidity measurement range is 0% to 100% with an accuracy of ±2%. All sensors are connected to the central microcontroller unit (MCU) via a low-power I2C bus. The sampling frequency is initially set to 10 Hz and can be dynamically adjusted according to the adaptive mechanism in subsequent step S5. After analog-to-digital conversion, the sensor data is stored in a local buffer in the form of structured data packets, including timestamps, sensor type identifiers, physical quantity values, and checksums, ensuring data integrity and timing consistency.

[0023] Step S2, Comprehensive assessment of fit and risk: Based on the measurement data from the pressure sensor, distance sensor, and temperature and humidity sensor, a real-time fit status assessment result and a fogging risk level are calculated; wherein, the fogging risk level is calculated by determining the temperature difference ΔT between the lens surface temperature and the dew point temperature of the air near the lens. dew To determine.

[0024] refer to Figure 3 The diagram shown illustrates the logical flow framework for the comprehensive assessment of the fit and fogging risk. The assessment process is divided into two parallel sub-tasks: sealing condition assessment, comfort assessment, and fogging risk quantification.

[0025] The sealing condition assessment is based on the gap value D and the pressure value P. First, the gap value D for each key area is read from the distance sensor. If the D for any area is greater than the preset maximum allowable gap D... threshold If the value is typically 1.5 mm, a preliminary assessment indicates a risk of seal failure. Simultaneously, the pressure distribution map output by the pressure sensor array is analyzed, and the average pressure P in the effective sealing area is calculated. seal If Pseal Less than the minimum sealing pressure P min (Typical value is 0.8 kPa), then the sealing force is considered insufficient. Only when the gap value D in all areas is less than or equal to D... threshold And P seal Greater than or equal to P min Only then can it be confirmed that the current state is in a valid sealing condition.

[0026] The comfort assessment is based on the pressure value P and its distribution characteristics. The average reading P of all pressure sensing units is calculated. avg And identify the local peak pressure P peak If P avg Greater than the maximum comfort pressure P max (Typical value is 2.5 kPa) or P peak If the local tolerance threshold is exceeded (typically 4.0 kPa), it is considered an uncomfortable state.

[0027] Furthermore, a pressure distribution uniformity index U is introduced, defined as the ratio of the standard deviation to the mean, i.e., U = σ(P) / P avg σ(P) is the standard deviation of the pressure sensor reading. When U is greater than 0.6, it indicates that the pressure is concentrated at a few points, which can easily cause local pressure and is also marked as potential discomfort.

[0028] The fogging risk quantification was accomplished using an empirical model. This was based on T measured by a temperature and humidity sensor. air And RH, calculate the dew point temperature T using the Magnus formula. dew :

[0029] Among them, dimensionless temperature The constants are a = 17.27 and b = 237.7. The internal surface temperature T of the lens is estimated using an empirical model. surface The above model considers ambient temperature, human body radiant heat, and the thermal conductivity of the lens material, and is simplified to... ,in The facial skin temperature (approximately 33 degrees Celsius) is estimated indirectly using an infrared sensor. , , For example, pre-calibration coefficients =0.6, =0.35, =1.2. Calculate the temperature difference ΔT. dew = T surface - T dew When ΔT dewWhen the value approaches zero or even becomes negative, it indicates that the surface temperature of the lens has dropped to or below the dew point, water vapor is about to condense, and the risk of fogging is extremely high.

[0030] Step S3, Intelligent Collaborative Decision Making: Based on the fit status assessment results and fogging risk level, control commands are generated according to preset priority decision rules. The priority decision rules include: when the fogging risk level exceeds a preset risk threshold, an anti-fog adjustment command is triggered first; when the pressure value exceeds a comfort pressure threshold, a relaxation command is triggered; when the gap value exceeds a gap threshold or the pressure value is lower than a sealing pressure threshold, a tightening command is triggered.

[0031] refer to Figure 2 The diagram shows the core principle framework of intelligent collaborative control. The decision engine employs a hierarchical arbitration mechanism to ensure that high-risk events are handled first. The preset priority decision rule is specifically: when ΔT... dew When the temperature difference is less than the first temperature threshold (e.g., -0.5 degrees Celsius), it is considered a high risk of fogging and triggers an anti-fogging adjustment command; when the pressure value P is greater than the maximum comfort pressure P... max When the gap value D is greater than the maximum allowable gap D, a relaxation command is triggered. threshold Or the pressure value P is less than the minimum sealing pressure P min When the maximum comfort pressure is greater than the minimum sealing pressure, a tightening command is triggered; this ensures that a basic seal is maintained within the comfort range.

[0032] Specifically, the anti-fog adjustment command includes controlling the micro-drive actuator to slightly relax, creating an anti-fog gap between the glasses and the face. The gap width is precisely controlled between 0.3 and 0.8 millimeters, sufficient to promote air convection and reduce local humidity without compromising the overall seal.

[0033] Furthermore, step S3 also includes a motion state compensation step: acquiring inertial measurement unit (IMU) data to sense the user's head movement state; and dynamically adjusting the priority decision rule based on the motion state. The IMU module is integrated inside the temple and includes a three-axis accelerometer and a gyroscope with a sampling rate of 100 Hz. When the system detects that the user is in a state of vigorous movement, it automatically increases the sealing pressure threshold P. min The pressure is increased to 1.2 kPa, and comfort-related relaxation commands are temporarily suppressed to prevent accidental air leakage due to shaking. When sitting or walking slowly, the system can appropriately relax the sealing requirements to prioritize comfort.

[0034] Step S4, drive execution adjustment: The control command is sent to a micro-drive actuator integrated on the glasses, which then changes the fit between the glasses and the face.

[0035] refer to Figure 4 The diagram illustrates the multi-level interaction and data flow of the micro-drive actuator and multi-target adjustment mechanism. This invention uses a single shape memory alloy (SMA) cable as the core actuator, running between the temple hinge and the nose pad support structure. The SMA cable has a diameter of 0.15 mm and can contract by 0.5 mm within 100 milliseconds after being energized, returning to its original position via a built-in spring after power-off. By precisely controlling the current magnitude and duration using pulse width modulation (PWM) signals, continuous adjustment of at least one of the following can be achieved: temple clamping force, nose pad support height, or frame curvature. For example, a tightening command corresponds to applying a high duty cycle PWM signal to the SMA, causing it to contract and thus increasing the clamping force of the temple on the head; a loosening command reduces the duty cycle or cuts off the current, allowing the spring to rebound; an anti-fog adjustment command applies a brief, low-intensity pulse, generating a controllable micron-level displacement to create a localized ventilation gap. The actuator's drive circuit includes overcurrent protection and temperature monitoring to prevent overheating failure due to frequent operation.

[0036] Step S5, closed-loop feedback: After the adjustment is performed, return to step S1 to form a closed-loop control circuit.

[0037] The cycle period of the closed-loop control loop is adaptively adjusted based on the rate of change of sensor data. The system continuously monitors the sum of the absolute values ​​of the first derivatives of the data from each sensor. If the sum of these absolute values ​​exceeds a preset dynamic threshold, the sampling frequency is increased from 10 Hz to 20 Hz to capture rapid changes. If the data changes smoothly for five consecutive cycles, the frequency is reduced to 5 Hz to save energy. This adaptive mechanism significantly extends battery life.

[0038] Furthermore, this invention proposes an active closed-loop fit control method for smart protective glasses, which also includes a parameter self-learning step: recording sensor data combinations when the user manually adjusts the glasses or when the system reaches a steady state; based on the recorded data, adaptively adjusting at least one of the comfort pressure threshold, sealing pressure threshold, gap threshold, and risk threshold. A steady state is defined as a fluctuation amplitude of all sensor readings less than 5% of their range within 30 consecutive seconds. The system stores these steady-state data points and their corresponding user satisfaction labels (which can be implicitly collected through a companion app; satisfaction is considered complete if the user does not manually intervene) in local non-volatile memory. After weekly or cumulatively reaching 100 valid samples, the system starts an online learning algorithm, updating each threshold using a sliding window averaging method. For example, a new P... max P is set to the historically comfortable state. avg The 95th percentile, the new P min Then P is in an effective sealed state sealThe 5th percentile value. This mechanism allows the system to gradually adapt to individual users' facial contours, skin sensitivity, and subjective preferences, achieving long-term personalized optimization.

[0039] The foregoing has shown and described the basic principles, main features, and advantages of this invention. Those skilled in the art should understand that this invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of this invention. Various changes and modifications can be made to this invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claims. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. An active closed-loop fit control method for smart protective glasses, characterized in that, Includes the following steps: Step S1, Multi-source information perception: Acquire measurement data from pressure sensors, distance sensors, and temperature and humidity sensors located at key contact points of smart protective glasses; Step S2, Comprehensive assessment of fit and risk: Based on the measurement data from the pressure sensor, distance sensor, and temperature and humidity sensor, a real-time fit status assessment result and a fogging risk level are calculated; wherein, the fogging risk level is calculated by determining the temperature difference ΔT between the lens surface temperature and the dew point temperature of the air near the lens. dew To determine; Step S3, Intelligent Collaborative Decision Making: Based on the fit status assessment results and fogging risk level, control commands are generated according to preset priority decision rules. The priority decision rules include: when the fogging risk level exceeds a preset risk threshold, an anti-fog adjustment command is triggered first; when the pressure value exceeds a comfort pressure threshold, a relaxation command is triggered; when the gap value exceeds a gap threshold or the pressure value is lower than a sealing pressure threshold, a tightening command is triggered. Step S4, drive execution adjustment: The control command is sent to the micro-drive actuator integrated on the glasses, which drives the actuator to change the fit between the glasses and the face; Step S5, closed-loop feedback: After the adjustment is performed, return to step S1 to form a closed-loop control circuit.

2. The method according to claim 1, characterized in that, In step S2, the temperature difference ΔT between the lens surface temperature and the dew point temperature of the air near the lens is calculated. dew Specifically, this includes: the temperature T measured by the temperature and humidity sensor. air Calculate the dew point temperature T based on the relative humidity RH. dew The internal surface temperature T of the lens was estimated using an empirical model. surface ; through the T surface and T dew Calculate ΔT dew =T surface -T dew .

3. The method according to claim 1, characterized in that, The preset priority decision rule mentioned in step S3 is specifically as follows: when ΔT dew When the temperature difference is less than the first temperature difference threshold, it is determined to be a high risk of fogging, triggering an anti-fogging adjustment command; when the pressure value P is greater than the maximum comfort pressure P... max When this occurs, the relaxation command is triggered; When the gap value D is greater than the maximum allowable gap D threshold Or the pressure value P is less than the minimum sealing pressure P min When the maximum comfort pressure is greater than the minimum sealing pressure, a tightening command is triggered.

4. The method according to claim 3, characterized in that, The anti-fog adjustment command includes controlling the micro-drive actuator to slightly relax, so as to create an anti-fog gap between the glasses and the face.

5. The method according to claim 1, characterized in that, It also includes a parameter self-learning step: recording the sensor data combination when the user manually adjusts or when the system reaches a stable state; and adaptively adjusting at least one of the comfort pressure threshold, sealing pressure threshold, gap threshold, and risk threshold based on the recorded data.

6. The method according to claim 1, characterized in that, The key contact areas mentioned in step S1 include at least one of the nose pad area, the inner contact area of ​​the temple, and the lower edge area of ​​the frame.

7. The method according to claim 1, characterized in that, The real-time fit status assessment in step S2 includes a sealing status assessment and a comfort assessment; wherein, the sealing status assessment is based on the gap value and the pressure value; and the comfort assessment is based on the pressure value and its distribution characteristics.

8. The method according to claim 1, characterized in that, The change in the fit between the glasses and the face in step S4 is achieved by adjusting at least one of the following methods: the clamping force of the temples, the support height of the nose pads, or the curvature of the frame.

9. The method according to claim 1, characterized in that, Step S3 also includes a motion state compensation step: acquiring inertial measurement unit data to sense the user's head motion state; and dynamically adjusting the priority decision rule according to the motion state.

10. The method according to claim 1, characterized in that, The cycle period of the closed-loop control loop described in step S5 is adaptively adjusted according to the rate of change of the sensor data.

Images