Multi-mode-based self-adaptive stretch sock control method and control method

Abstract

According to the multi-mode-based self-adaptive stretch sock and the control method, the real-time vein blood flow speed and the real-time posture information are received at the same time, and the pressure adjusting instruction is calculated in a nonlinear mode through the pre-defined fuzzy rule base. And the real-time attitude information is used for determining the basic pressure of dynamic adjustment, and finally a target pressure value is obtained, so that qualitative change from single-parameter adjustment to multi-situation self-adaption is realized.

Description

Technical Field

[0001] This invention relates to the field of elastic stockings technology, and in particular to a multimodal adaptive elastic stockings control method and control method. Background Technology

[0002] Varicose veins, deep vein thrombosis, and other venous return disorders are common clinical problems. Gradient compression stockings are a basic non-pharmacological intervention that provides decreasing static external pressure from the ankle to the leg, assisting the calf muscle pump and promoting venous blood return to the heart.

[0003] However, traditional graduated compression stockings provide a fixed pressure. The venous hemodynamics of the human body are significantly affected by posture, activity level, and individual physiological differences. For example, when standing, the hydrostatic pressure in the lower limb veins is significantly increased due to gravity, requiring higher auxiliary pressure; while when lying down, the hydrostatic pressure is almost zero, and applying the same pressure as when standing may excessively compress tissues and arteries. For patients with both varicose veins and cardiovascular diseases such as hypertension, this "one-size-fits-all" pressure pattern poses potential risks.

[0004] To overcome the problem of static pressure, some "active compression" or "intelligent compression" solutions have emerged in the existing technology: Active compression garments based on shape memory alloys (SMA) (such as US20150073318A1, WO2015038599A1): These patents disclose the use of SMA threads integrated into textiles, using electrothermal control of SMA deformation to adjust the tightness of the garment. However, they typically lack closed-loop feedback control based on deep physiological parameters; their pressure regulation is mostly based on preset programs or simple commands (such as user input), rather than on real-time blood flow status.

[0005] Portable pneumatic sequential compression devices (e.g., US7354410B2): This patent describes a portable pneumatic compression system with feedback control. One of its feedback mechanisms is the measurement of "venous refill time," a periodic, low-frequency physiological parameter. The system uses VRT to adjust the "rest time" between compression cycles. This is a time-based periodic adjustment, rather than the real-time pressure amplitude adjustment based on blood flow velocity as discussed in this invention. Another feedback mechanism in this patent is a pressure sensor, but its purpose is to maintain a preset, static target pressure value, rather than dynamically changing that target value.

[0006] Therefore, it is evident that the existing technology has the following shortcomings: The feedback parameters are indirect and low-frequency, making real-time optimization impossible: the VRT parameter it uses is a periodic, low-frequency time parameter that requires measurement only once every tens of seconds to several minutes. This prevents the system from responding quickly to instantaneous changes in blood flow velocity caused by posture changes, brief muscle activity, etc. The control objective is to adjust the cycle "interval," rather than the pressure "magnitude," therefore it cannot optimize hemodynamic effects in real time within a single compression cycle.

[0007] Lacking context awareness, pressure application is inaccurate: One solution lacks integrated posture sensors. Therefore, the system cannot distinguish whether the user is lying down, sitting, or standing. Since the effect of gravity on venous return varies greatly across different postures, a fixed target pressure value clearly cannot guarantee both safety and effectiveness in all postures.

[0008] The linear control logic struggles to handle the uncertainties of physiological systems: its pressure control loop employs traditional PID control, aiming to maintain a fixed preset pressure. The biological blood flow system exhibits high nonlinearity, time-varying characteristics, and individual variability. A fixed target pressure and a linear control strategy are insufficient to achieve both safe and effective control under various disturbances, lacking the intelligence to cope with complex physiological states. Summary of the Invention

[0009] To address the problems existing in the prior art, the present invention aims to provide a multimodal adaptive elastic stocking control method and control method, which enables the output of the elastic stockings to better match physiological needs.

[0010] To achieve the above objectives, the present invention adopts the following technical solution: A multimodal adaptive elastic stocking control method includes: The system acquires the user's multimodal perception parameters in real time, including: real-time posture information, real-time pressure information, and real-time venous blood flow velocity. Real-time venous blood flow velocity is converted into fuzzy linguistic variables of blood flow velocity, and real-time attitude information is converted into fuzzy linguistic variables of attitude. Determining the basic pressure value based on attitude fuzzy linguistic variables; The pressure adjustment value is determined based on real-time pressure information, blood flow velocity fuzzy linguistic variables, and posture fuzzy linguistic variables. The target pressure value is calculated based on the pressure adjustment value and the baseline pressure value. The target pressure value is the pressure that the adaptive elastic stockings need to generate. As a further improvement of the present invention, before the steps of converting real-time venous blood flow velocity into fuzzy linguistic variables of blood flow velocity and converting real-time posture information into fuzzy linguistic variables of posture, and before the steps of converting real-time venous blood flow velocity into fuzzy linguistic variables of blood flow velocity and converting real-time posture information into fuzzy linguistic variables of posture, the invention further includes: Safety detection is performed based on real-time stress information.

[0011] As a further improvement of the present invention, the step of performing safety detection based on real-time pressure information includes: Set a safe pressure threshold; If the real-time pressure information is greater than the safe pressure threshold, the pressure value of the compression stockings will be adjusted directly.

[0012] As a further improvement of the present invention, the step of determining the pressure adjustment value based on the target pressure value, real-time pressure information, blood flow velocity fuzzy linguistic variable, and posture fuzzy linguistic variable includes: Call the rule base to match the fuzzy set of pressure adjustment values ​​corresponding to the fuzzy linguistic variables of blood flow velocity and posture. Transform the fuzzy set of pressure adjustment values ​​into pressure adjustment values.

[0013] As a further improvement of the present invention, the step of calculating the target pressure value based on the pressure adjustment value and the baseline pressure value includes: Add the pressure adjustment value and the base pressure value to obtain the target pressure value.

[0014] The present invention also provides a multimodal adaptive elastic stocking for implementing the above-mentioned adaptive elastic stocking control method, comprising: a stocking body, a blood flow sensing module, an attitude sensing module, a pressure sensing module, a processing unit, and an execution unit, wherein the blood flow sensing module, the attitude sensing module, the pressure sensing module, and the execution unit are disposed on the stocking body; The blood flow sensing module is used to acquire the user's real-time venous blood flow velocity; The attitude sensing module is used to acquire the user's real-time attitude information; The pressure sensing module is used to acquire the user's real-time pressure information; The processing unit is used to determine the target pressure value based on the attitude fuzzy linguistic variable, and to determine the pressure adjustment value based on the target pressure value, real-time pressure information, blood flow velocity fuzzy linguistic variable, and attitude fuzzy linguistic variable. The execution unit is used to control the pressure generated by the sock body.

[0015] As a further improvement of the present invention, the blood flow sensing module includes: a flexible Doppler ultrasound probe and a textile electrode integrated into the sock body.

[0016] As a further improvement of the present invention, the attitude sensing module includes a three-axis accelerometer.

[0017] As a further improvement of the present invention, the pressure sensing module includes: a flexible pressure sensor.

[0018] As a further improvement of the present invention, the execution unit includes: a shape memory alloy coil and a wire.

[0019] The beneficial effects of this invention are as follows: By integrating two key pieces of information—real-time venous blood flow velocity and real-time posture information—this invention achieves context-aware pressure control, enabling the pressure output of the elastic stockings to precisely match physiological needs. A fuzzy logic controller is employed as the core algorithm to handle the nonlinearity and uncertainty of biological systems, achieving more intelligent and compliant control. Attached Figure Description

[0020] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments.

[0021] Figure 1 This is a flowchart of the adaptive elastic stocking control method described in Example 1; Figure 2 This is a circuit diagram of the adaptive elastic stockings described in Example 2. Detailed Implementation

[0022] To make the technical problems solved by the present invention, the technical solutions adopted, and the technical effects achieved clearer, the technical solutions of the embodiments of the present invention will be further described in detail below. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] Example 1 This embodiment provides a multimodal adaptive elastic stocking control method. Before implementation, initialization work is required, including loading preset parameters such as base pressure values ​​P_base(Supine), P_base(Sitting), and P_base(Standing) (e.g., 15, 25, 35 mmHg) under different postures, safety pressure threshold P_max (e.g., 60 mmHg), a base pressure comparison table under different body postures, a rule base and membership function of the fuzzy logic controller.

[0024] like Figure 1 As shown, the adaptive elastic stocking control method includes: S1. Real-time acquisition of multimodal sensing parameters, including: real-time pressure information between the elastic stockings and the user's skin P_interface, real-time posture information Posture of the user, and real-time venous blood flow velocity of the user V_actual.

[0025] Specifically, real-time posture information (Posture), real-time pressure information (P_interface), and real-time venous blood flow velocity (V_actual) are acquired periodically or continuously, and then filtered and calibrated, such as by using low-pass filtering to remove noise.

[0026] S2. Safety detection based on real-time pressure information P_interface. This step is a high-priority closed-loop safety assurance mechanism. Its core function is to monitor risks in real time, intervene immediately and enforce safety operations when the real-time pressure information P_interface is displayed, and run it before subsequent steps to avoid damage to blood vessels or skin in the lower limbs due to excessive pressure from the elastic stockings.

[0027] In the safety detection step, if the real-time pressure information P_interface is less than the safe pressure threshold P_max, it means that the elastic stockings are currently in a safe state and can proceed to the next processing step; if the real-time pressure information P_interface is greater than or equal to the safe pressure threshold P_max, it means that the elastic stockings are currently in a dangerous state. The pressure value of the elastic stockings is directly adjusted to forcibly implement pressure reduction control, so that it drops below the safe pressure threshold P_max. Only after it is restored to the safe range can the next step be restarted.

[0028] S3. Convert the real-time venous blood flow velocity V_actual into a fuzzy linguistic variable for blood flow velocity, and convert the real-time posture information Posture into a fuzzy linguistic variable for posture. Through this step, the clear real-time posture information Posture and the real-time venous blood flow velocity V_actual are fuzzified: The fuzzy set of blood flow velocity V_actual is defined as: {Very low (VL), Low (L), Normal (N), High (H)}.

[0029] Very Low (VL): 0–5 cm / s; Low (L): 5–10 cm / s; Normal (N): 10–20 cm / s; High (H): ≥20~30 cm / s and above.

[0030] It should be noted that appropriate overlap intervals can be designed between the various fuzzy sets, and these values ​​can be optimized and adjusted based on clinical or benchtop trials.

[0031] The fuzzy set of posture is defined as: {lying down (S), sitting (Si), standing (St)}.

[0032] S4. Determine the base pressure value P_base based on the fuzzy linguistic variables of the posture. Specifically, obtain the fuzzy set of postures by looking up a table. This table uses the user's posture as an index and provides the range and optimal value of the base pressure P_base for each posture: Supine position (S): P_base = 10~20 mmHg, preferred value 15 mmHg; Sitting posture (Si): P_base = 20~30 mmHg, preferred value 25 mmHg; Standing (St): P_base = 30~40 mmHg, preferred value 35 mmHg.

[0033] By following the steps above, the corresponding base pressure value P_base can be obtained from the table based on the real-time attitude information Posture, and used as the initial value of the target pressure value P_target.

[0034] S5. Determine the pressure adjustment value ΔP based on real-time pressure information P_interface, blood flow velocity fuzzy linguistic variables, and posture fuzzy linguistic variables. The rule base is invoked to match the fuzzy set of pressure adjustment values ​​ΔP corresponding to the fuzzy linguistic variables of blood flow velocity and posture; the fuzzy set of pressure adjustment values ​​ΔP is transformed into a clear and accurate pressure adjustment value ΔP_crisp through algorithms such as the centroid method.

[0035] The rule base includes a set of correspondences between posture, blood flow velocity (V_actual), and pressure adjustment (ΔP). The rule base explicitly encodes differentiated pressure response strategies to changes in blood flow velocity under different postures. The rule base design is based on venous hemodynamics and physiological safety boundaries.

[0036] Rule examples from the rule base: RULE 1: IF (Posture IS St) AND (V_actual IS L) THEN (ΔP IS LI) RULE 2: IF (Posture IS S) AND (V_actual IS L) THEN (ΔP IS SI) RULE 3: IF (Posture IS St) AND (V_actual IS N) THEN (ΔP IS M) RULE 4: IF (Posture IS Si) AND (V_actual IS H) THEN (ΔP IS SD) RULE 5: IF (Posture IS S) AND (V_actual IS H) THEN (ΔP IS LB) ... The pressure adjustment value ΔP is defined as the change in target pressure during the current control cycle. The fuzzy set of the pressure adjustment value ΔP is defined as: {Significant decrease (LB), Small decrease (SD), Maintain (M), Small increase (SI), Significant increase (LI)}, specifically quantified into the following fuzzy sets: Significant Decrease (LB): ΔP ∈ [ 20, 10] mmHg, and the control result can be limited to P_target_new ≤ P_base 10 mmHg; Slight Decrease (SD): ΔP ∈ [ 10, 5 mmHg; Maintain (M): ΔP ∈ [ 2, +2] mmHg, is considered as no substantial adjustment to the target pressure; Small Increase (SI): ΔP ∈ [+5, +10] mmHg; Large Increase (LI): ΔP ∈ [+10, +20] mmHg, and the control result can be limited to P_target_new ≥ P_base + 10 mmHg.

[0037] In the implementation of fuzzy logic, each fuzzy set is also described by a predefined membership function, and its boundary points and peak points are given numerically in the specification so that those skilled in the art can implement the control algorithm accordingly.

[0038] S6. Calculate the target pressure value based on the pressure adjustment value and the base pressure value. The target pressure value is the pressure that the adaptive elastic stockings need to generate, i.e., P_target = P_base(Posture) + ΔP_crisp. Finally, P_target is converted into a specific control signal and output, such as outputting the PWM duty cycle. After waiting for one control cycle, return to step S2 and continue running to achieve adaptive control of the elastic stockings.

[0039] This embodiment chooses a fuzzy logic controller instead of a traditional PID controller because hemodynamic systems are typically complex nonlinear systems. Fuzzy logic controllers do not require precise mathematical models; instead, they simulate the decision-making process of human experts based on "if-then" rules. This allows them to better handle noise, individual differences, and the complex, nonlinear relationship between real-time venous blood flow velocity V_actual and the required pressure in the real-time venous blood flow velocity V_actual signal. For example, the same "low" blood flow velocity may require a "significant increase" in pressure when standing, but only a "small increase" when lying down. This linguistic, nonlinear mapping is precisely what fuzzy logic controllers excel at.

[0040] This embodiment simultaneously receives real-time venous blood flow velocity (V_actual) and real-time posture information (Posture), and nonlinearly calculates pressure adjustment commands using a predefined fuzzy rule base. The real-time posture information (Posture) is used to determine the base target pressure (P_base) for dynamic adjustment. Compared to existing technologies that use a single, low-frequency VRT parameter to adjust the time interval, or use pressure sensors to maintain static pressure, this embodiment introduces posture perception as a fundamental dimension of the control logic and integrates it with blood flow velocity within a fuzzy logic framework for decision-making, achieving a qualitative leap from "single-parameter adjustment" to "multi-scenario adaptive control."

[0041] This embodiment establishes a high-priority safety detection independent of the main fuzzy logic controller loop. This safety detection continuously monitors the real-time pressure information P_interface and compares it with a fixed safety threshold P_max. The main fuzzy logic controller's instructions are only executed within the safety range; otherwise, safety decompression is forcibly implemented. By explicitly distinguishing between the real-time pressure information P_interface into "servo" and "safety" layers, a layered control architecture is constructed, ensuring the inherent safety of the system under any abnormal conditions (such as algorithm failure, actuator malfunction, or sock misalignment).

[0042] Example 2 This embodiment provides a multimodal adaptive elastic stocking for implementing the adaptive elastic stocking control method in Embodiment 1, such as... Figure 2 As shown, the device includes: a sock body, a blood flow sensing module, a posture sensing module, a pressure sensing module, a processing unit, and an execution unit. The blood flow sensing module, posture sensing module, pressure sensing module, and execution unit are mounted on the sock body. The blood flow sensing module is used to acquire the user's real-time venous blood flow velocity; the posture sensing module is used to acquire the user's real-time posture information; the pressure sensing module is used to acquire the user's real-time pressure information; the processing unit is used to determine the target pressure value based on posture fuzzy linguistic variables, and to determine the pressure adjustment value based on the target pressure value, real-time pressure information, blood flow velocity fuzzy linguistic variables, and posture fuzzy linguistic variables; the execution unit is used to control the pressure generated by the sock body.

[0043] Specifically, the blood flow sensor module is used to measure the real-time venous blood flow velocity in the lower limbs (such as the popliteal vein or femoral vein). The blood flow sensor module can indirectly obtain blood flow velocity parameters by using a flexible Doppler ultrasound probe or by implementing impedance volumetric recording (IPG) through textile electrodes integrated into the sock body. The blood flow sensor module outputs the real-time venous blood flow velocity V_actual. It should be noted that if a flexible Doppler ultrasound probe is used, a separate drive circuit is required; in this case, the drive circuit can be placed on a box attached to the sock body.

[0044] The attitude sensing module is mainly implemented by a three-axis accelerometer to identify the user's basic posture (such as: lying down, sitting, standing). By analyzing the accelerometer data in the direction of gravity, these three postures can be reliably distinguished. The attitude sensing module outputs real-time attitude information.

[0045] The pressure sensing module consists of several flexible pressure sensors distributed on the sock body (such as the ankle and calf), such as piezoresistive or capacitive textile sensors, used to measure the real-time pressure information P_interface exerted by the elastic sock on the skin.

[0046] The processing unit is a microprocessor unit that receives and processes all signals from the blood flow sensing module, attitude sensing module, and pressure sensing module. Internally, it runs a core hierarchical intelligent control algorithm and outputs control signals to the actuator layer. The processing unit can be installed in smart wearable devices, such as smartwatches.

[0047] The actuator is a flexible actuator integrated into the fabric structure of the elastic stockings. For example, it can be a shape memory alloy (SMA) coil or wire. The SMA actuator contracts through the Joule heating effect, thereby tightening the fabric and generating pressure. The processing unit controls the current applied to the SMA via pulse width modulation (PWM), thus precisely controlling its contraction amount and final pressure.

[0048] In summary, the present invention has the following technical effects: By integrating real-time venous blood flow velocity and real-time posture information—two key pieces of information—contextual awareness of pressure control is achieved, enabling precise matching of the pressure output of the compression stockings with physiological needs. A fuzzy logic controller is employed as the core algorithm to handle the nonlinearity and uncertainty of biological systems, achieving smarter and more compliant control. It is no longer a "one-size-fits-all" static pressure, nor simply a low-frequency feedback that adjusts the rhythm; instead, it achieves intervention at the correct time (based on posture) and with the correct force (based on blood flow velocity), significantly improving the effectiveness and comfort of treatment. Furthermore, an independent safety detection coverage loop based on real-time pressure information monitoring is introduced, using the real-time pressure information P_interface as an independent, high-priority safety barrier. This completely eliminates the possibility of pressure exceeding the safety limit under any circumstances due to system failure, preventing tissue damage and arterial ischemia.

[0049] The above technologies can provide users with an adaptive pressure management solution that effectively promotes venous return while maximizing wearable safety.

[0050] In this description, references to terms such as "an embodiment," "example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example.

[0051] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style of the specification is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

[0052] The technical principles of the present invention have been described above with reference to specific embodiments. These descriptions are merely for explaining the principles of the invention and should not be construed as limiting the scope of protection of the invention in any way. Based on this explanation, those skilled in the art can readily conceive of other specific embodiments of the invention without inventive effort, and these embodiments will all fall within the scope of protection of the present invention.

Claims

1. A multi-modal based adaptive control method for stretch socks, the method comprising: The method comprises the following steps: real-time acquisition of multi-modal sensing parameters, including real-time pressure information between the compression socks and the user's skin, real-time posture information of the user, and real-time venous blood flow velocity of the user; converting the real-time venous blood flow velocity into a blood flow velocity fuzzy language variable and converting the real-time posture information into a posture fuzzy language variable; determining a basic pressure value based on the posture fuzzy language variable; determining a pressure adjustment value based on the real-time pressure information, the blood flow velocity fuzzy language variable, and the posture fuzzy language variable; calculating a target pressure value based on the pressure adjustment value and the basic pressure value, wherein the target pressure value is the pressure required to be generated by the adaptive compression socks.

2. The adaptive compression stocking control method of claim 1, wherein, Before the step of converting the real-time venous blood flow velocity into a blood flow velocity fuzzy language variable and converting the real-time posture information into a posture fuzzy language variable, the method further comprises the following step: performing safety detection based on the real-time pressure information.

3. The adaptive compression stocking control method of claim 2, wherein, The step of performing safety detection based on the real-time pressure information comprises the following steps: setting a safety pressure threshold value; if the real-time pressure information is greater than or equal to the safety pressure threshold value, directly adjusting the pressure value of the compression socks.

4. The adaptive compression stocking control method of claim 1, wherein, The step of determining a pressure adjustment value based on the target pressure value, the real-time pressure information, the blood flow velocity fuzzy language variable, and the posture fuzzy language variable comprises the following steps: calling a rule base to match a pressure adjustment value fuzzy set corresponding to the blood flow velocity fuzzy language variable and the posture fuzzy language variable; converting the pressure adjustment value fuzzy set into a pressure adjustment value.

5. The adaptive compression stocking control method of claim 4, wherein, The method comprises the following steps: The step of calculating a target pressure value based on the pressure adjustment value and the basic pressure value comprises the following step: adding the pressure adjustment value and the basic pressure value to obtain the target pressure value.

6. A multi-modal based adaptive compression hosiery characterized in that, A self-adaptive compression sock control method as claimed in any one of claims 1-9, comprising a sock body, a blood flow sensing module, a posture sensing module, a pressure sensing module, a processing unit, and an execution unit, wherein the blood flow sensing module, the posture sensing module, the pressure sensing module, and the execution unit are arranged on the sock body; The blood flow sensing module is configured to acquire real-time venous blood flow velocity of a user. The posture sensing module is configured to acquire real-time posture information of the user. The pressure sensing module is configured to acquire real-time pressure information of the user. The processing unit is configured to determine a target pressure value based on a posture fuzzy language variable and to determine a pressure adjustment value based on the target pressure value, real-time pressure information, a blood flow velocity fuzzy language variable, and the posture fuzzy language variable. The execution unit is configured to control the pressure generated by the sock body.

7. The self-adapting compression hosiery according to claim 6, wherein, The blood flow sensing module comprises a flexible Doppler ultrasound probe and a textile electrode integrated in the sock body.

8. The self-adapting compression hosiery of claim 6, wherein, The posture sensing module comprises a three-axis accelerometer.

9. The self-adapting compression hosiery of claim 6, wherein, The pressure sensing module comprises a flexible pressure sensor.

10. The self-adapting compression hosiery of claim 6, wherein, The execution unit comprises a shape memory alloy coil and a wire.

Images