Training rehabilitation equipment pressure detection method

Abstract

The invention discloses a training rehabilitation equipment pressure detection method. The method comprises the following steps: acquiring piezoresistance data of a sensor; calculating a pressure value; acquiring motion parameters; and evaluating the training effect. According to the technical scheme, 10 Hz ADC sampling and left and right partition sensors are adopted, the pressure detection error is smaller than or equal to 0.5 kg, and the motion parameter delay is smaller than 100 ms; bluetooth / NFC dual-mode connection is integrated, a mobile phone APP is supported to check data in real time, the thickness is smaller than 20 mm, and the device adapts to family and professional training scenes; pressure and stride frequency are monitored, and through left and right foot balance analysis, response time evaluation, stride frequency, explosive force, grounding time under movement and left and right balance of a movement state are recovered, so that movement injuries (such as sprains caused by uneven stress of ankle joints) are prevented in an auxiliary manner; the compression resistance of the TPU supercritical foaming material is 20% better than that of traditional EVA, seamless integration of the sensor and the pad body is achieved through the plastic embedding technology, and the foot-cracking feeling is avoided.

Description

Technical Field

[0001] This invention relates to the field of training and rehabilitation equipment technology, and in particular to a method for pressure detection of training and rehabilitation equipment. Background Technology

[0002] With the increasing awareness of fitness among the general public and the growing demand for more scientific professional sports training, the functional limitations of training mats as basic sports equipment are becoming increasingly apparent. Currently, traditional training mats are mostly made of materials such as EVA and rubber, providing only physical protection through shock absorption and cushioning, and cannot achieve real-time collection and quantitative analysis of exercise data.

[0003] The following are the disadvantages of existing technologies:

[0004] Data collection gaps: The inability to capture biomechanical parameters during exercise (such as cadence, step pressure, hang time, and differences in force exertion between the left and right feet) leads to the evaluation of training effectiveness relying on the subjective judgment of coaches or users, resulting in poor accuracy and large errors.

[0005] Limited functionality: It serves only as a passive protective tool, lacking an active feedback mechanism. It cannot provide real-time guidance on key indicators such as movement standardization and force balance, making it difficult to meet personalized training needs.

[0006] Injury warning gap: It is impossible to identify abnormal movement posture or overtraining risks in advance through data trend analysis, which increases the probability of sports injuries.

[0007] Limitations of the technical solution: Existing smart sports devices (such as smartwatches and wristbands) mostly focus on basic physiological data such as heart rate and steps, and cannot provide specific data support for agility training scenarios (such as jumping, changing direction, and reaction speed).

[0008] To address the aforementioned shortcomings, this invention aims to provide a pressure detection method for training and rehabilitation equipment. Through collaborative innovation of hardware and algorithms, this invention breaks through the functional boundaries of traditional training mats, providing fitness enthusiasts and professional athletes with an intelligent training solution that integrates protection, monitoring, and guidance. Summary of the Invention

[0009] The main technical problem solved by this invention is to provide a method for pressure detection of training and rehabilitation equipment, thereby solving one or more of the problems in the prior art.

[0010] To solve the above-mentioned technical problems, the present invention adopts a technical solution as follows: a method for pressure detection of training and rehabilitation equipment, characterized by comprising the following steps:

[0011] (1) Obtain the piezoresistive data of the sensor: by collecting the voltage signal of the sensor, the piezoresistive data of the sensor is calculated by combining Kirchhoff's law and Ohm's law;

[0012] (2) Calculate the pressure value: Based on the correspondence between the pressure resistance data and the preset proportional coefficient, calculate the bearing pressure value of the training and rehabilitation equipment;

[0013] (3) Obtain motion parameters: Record the number of times the pressure value changes and the peak interval time within a preset time by using a timer to determine the number of jumps, interval time and motion frequency of the target motion;

[0014] (4) Evaluate the training effect: Compare the pressure value, number of jumps, interval time and exercise frequency with the preset exercise standards, and output the training standardization evaluation results.

[0015] In some implementations, step (1) of "calculating the piezoresistive data of the sensor by combining Kirchhoff's laws and Ohm's law" includes:

[0016] Selected based on input voltage A closed loop consisting of a fixed resistor R1, a sensor equivalent resistance R2, and a ground terminal is used to obtain the loop current I = using Kirchhoff's Voltage Law (KVL). / (R1+R2), then calculate the sensor output voltage using Ohm's law. =I*R2, solve simultaneously to get the resistance value of R2 as the piezoresistive data.

[0017] In some implementations, the "preset proportional coefficient" in step (2) is calibrated in the following way: before the sensor leaves the factory, a proportional coefficient k is obtained by applying a mapping relationship between a known pressure value and the corresponding piezoresistive data, such that the pressure value N = k * R, where R is the piezoresistive data calculated in step (1); the preset proportional coefficient is dynamically calibrated through environmental parameters (temperature, humidity), and the calibration formula is as follows: Where a, b, and c are calibration coefficients. is the initial coefficient, T is the temperature, and H is the humidity.

[0018] In some implementations, step (3) "recording via timer" includes:

[0019] Continuous sampling ADC (analog-to-digital converter) is used to obtain real-time changes in pressure values;

[0020] The ADC signal is sampled periodically to count the number of pressure changes within a preset time period.

[0021] The peak interval of the ADC signal is sampled periodically to record the time difference between adjacent pressure peaks and troughs.

[0022] In some implementations, the "motion frequency" in step (3) is calculated by dividing the number of pressure changes within a preset time by the preset time to obtain the average motion frequency per unit time.

[0023] In some implementations, the “interval time” in step (3) includes: the time interval between two adjacent pressure changes, and the recovery response time from the peak value to the trough value in a single pressure change.

[0024] In some implementations, the "preset exercise standard" in step (4) is a training intensity standard defined by a sports association or in the field of rehabilitation medicine, including the pressure threshold corresponding to the target weight, the range of standard jump counts, and the range of standard interval times; the preset exercise standard is dynamically adjusted based on user tags (weight, rehabilitation stage, exercise goal), and the standard database is optimized through transfer learning algorithms; the preset exercise standard supports dynamic adjustment based on user tags:

[0025] User tagging system: including weight (kg), rehabilitation stage (post-operative / recovery period / intensification period), and exercise goals (agility training / balance training / endurance training).

[0026] Dynamic threshold optimization: By using transfer learning algorithms, real-time user data is compared with historical data of similar tagged groups to optimize personalized thresholds (e.g., the stress threshold is reduced by 20% and the recovery reaction time threshold is relaxed by 15% in the postoperative rehabilitation group).

[0027] Self-updating mechanism: After every 5 training sessions, the system automatically updates the user model and gradually improves the training standards (e.g., step frequency standards are increased by 5% per week).

[0028] In some implementations, the "training standardization evaluation result" in step (4) includes:

[0029] When the pressure value exceeds or falls below the pressure threshold, an "abnormal training intensity" prompt is output.

[0030] When the number of jumps or the interval time deviates from the standard range, an "abnormal training rhythm" prompt is output;

[0031] When the exercise frequency meets the standard range, a "Training intensity meets the standard" prompt is output;

[0032] When the pressure peak decay slope is greater than 50 kg / ms, an "Insufficient landing cushioning" warning will be output; when the pressure difference between the left and right feet increases by more than 10% during continuous training, an "Effective imbalance risk" warning will be output.

[0033] In some embodiments, the fixed resistor R1 has a resistance of 1kΩ to 10kΩ, and the input voltage is... The value range is 3V~5V.

[0034] In some implementations, the sensor is a piezoresistive sensor, and the timer is integrated into the MCU (microcontroller unit) with a sampling frequency of not less than 10Hz.

[0035] The beneficial effects of this invention are as follows: This technical solution uses 10Hz ADC sampling and left and right partition sensors, with a pressure detection error ≤0.5kg and motion parameter delay <100ms; it integrates Bluetooth / NFC dual-mode connection, supports real-time data viewing via mobile APP, and has a thickness of less than 20mm, making it suitable for home and professional training scenarios; it not only monitors pressure and cadence, but also assists in preventing sports injuries (such as sprains caused by uneven ankle force) through left and right foot balance analysis, recovery reaction time assessment, cadence, explosive power, ground contact time during exercise, and left and right balance during exercise; the TPU supercritical foam material has 20% better compression resistance than traditional EVA, and the embedded molding process achieves seamless integration of the sensor and the pad, avoiding discomfort under the feet. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein:

[0037] Figure 1 This is a flowchart of a pressure detection method for training and rehabilitation equipment according to the present invention. Detailed Implementation

[0038] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. 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.

[0039] like Figure 1 As shown, this invention includes: a pressure detection method for training and rehabilitation equipment, which collects pressure signals through a piezoresistive sensor and combines circuit analysis and algorithm processing to achieve real-time monitoring and evaluation of motion data; the following details the specific steps and hardware structure:

[0040] (a) Acquiring the piezoresistive data of the sensor

[0041] Hardware Basics: Training and rehabilitation equipment (such as training mats) has a built-in piezoresistive sensor. The sensor is connected in series with a fixed resistor R1 (1kΩ~10kΩ) to form a voltage divider circuit. Input voltage A voltage of 3V~5V is applied across the circuit, and the equivalent resistance of the sensor is R2. The circuit module is integrated into the ECU (electronic control unit) at the edge of the training pad and is connected to the sensor via wires.

[0042] Piezoresistive data calculation: The ECU acquires the sensor output voltage through the ADC module. The resistance value of R2 is derived based on Kirchhoff's Voltage Law (KVL) and Ohm's Law:

[0043] Loop current:

[0044] Output voltage:

[0045] Solving the system of equations simultaneously, we get: The real-time piezoresistive data R of the sensor is calculated using the above formula.

[0046] (ii) Calculate the pressure value

[0047] Proportional coefficient calibration: The proportional coefficient k is determined through a pressure calibration experiment before the sensor leaves the factory. The specific method is as follows: apply a known pressure value N (such as 10kg, 50kg, 100kg), record the corresponding piezoresistive data R, and fit a linear relationship to obtain the result. (k is a constant, unit: N / Ω).

[0048] Real-time pressure calculation: The ECU substitutes the piezoresistive data R obtained in step (I) into the formula. It can calculate the pressure value currently borne by the training mat with an accuracy of ±0.5kg.

[0049] Environmental adaptive calibration: To eliminate the influence of temperature and humidity on sensor accuracy, this method introduces a dynamic calibration mechanism.

[0050] 1. Environmental parameter acquisition: The circuit module integrates a temperature and humidity sensor (measurement range: temperature 0-40℃, humidity 30%-80%) to collect environmental data in real time;

[0051] 2. Calibration formula optimization: The proportional coefficient kk is dynamically adjusted using a three-dimensional fitting formula.

[0052] in: These are the factory calibration baseline coefficients, where T is the real-time temperature (°C), H is the real-time humidity (%), and a, b, ca, b, c are calibration coefficients (obtained through fitting experimental data, for example, a=-0.002, b=-0.001, c=0.00001).

[0053] 3. Calibration trigger conditions: Automatic calibration every 30 minutes, or immediate calibration when environmental parameters change by more than ±5℃ / ±10%, to ensure that the pressure detection error is stable for a long time ≤0.5kg.

[0054] (III) Obtaining motion parameters

[0055] Data sampling and timer configuration: Before starting, the ECU starts the MCU timer (sampling frequency ≥10Hz) to continuously sample the ADC signal and record the real-time changes in pressure value.

[0056] Timed sampling includes:

[0057] (a) Number of pressure changes: Count the number of times the pressure value jumps from a low threshold (e.g., 5kg) to a high threshold (e.g., 30kg) within a preset time (e.g., 1 minute), corresponding to the "number of jumps";

[0058] (b) Peak interval time: Record the time difference between adjacent pressure peaks (at the moment of takeoff) and troughs (at the moment of landing), and calculate the "hang time" and "recovery reaction time";

[0059] (c) Frequency of motion: (using the formula) Calculate the average intensity of motion per unit time.

[0060] Left and right foot data differentiation: The training pad has two independent sensors built in, one for the left foot and one for the right foot, to collect pressure data. The ECU distinguishes the left and right areas through channel labels, enabling independent analysis of single-foot pressure and step frequency.

[0061] (iv) Evaluating the training effectiveness

[0062] Standard Comparison: The ECU has a built-in standard database defined by sports associations, which includes pressure thresholds corresponding to different weights (e.g., the standard jumping pressure range for a 70kg adult is 40~60kg), standard stride frequency (e.g., agility training requires ≥2.5 times / second), and recovery reaction time (e.g., ≤0.3 seconds).

[0063] Personalized standard call process:

[0064] 1. When a user uses the app for the first time, they can input their weight, rehabilitation stage, and exercise goals to generate an initial user tag.

[0065] 2. The ECU loads baseline parameters of similar users (such as a standard dataset of 'postoperative rehabilitation users aged 25-30') from the cloud database based on the tags.

[0066] 3. During training, real-time data is compared with personalized thresholds. For example, the pressure threshold of a 70kg postoperative user is automatically adjusted to 30-50kg (the default standard is 40-60kg).

[0067] Output results:

[0068] (1) If the pressure value exceeds the threshold, a "rapid short beep" (3 times / second) will be emitted by the buzzer to indicate "abnormal training intensity";

[0069] (2) If the cadence or recovery time deviates from the standard range, the Bluetooth module will synchronize the data to the mobile APP and display "Training Rhythm Deviation" and adjustment suggestions;

[0070] (3) If all parameters meet the standards, the APP generates a “Training Intensity Meets Standards” report, which includes details such as a pressure distribution heatmap and left and right foot balance coefficients.

[0071] (4) Multimodal damage risk warning:

[0072] Insufficient landing cushioning: Extract the attenuation slope of the peak pressure at the moment of landing (pressure drop rate within 0-100ms). When the slope is >50kg / ms, the buzzer will emit a 'two short and one long' warning sound, and the APP will display 'Insufficient landing cushioning, it is recommended to increase the hip flexion angle';

[0073] Imbalance in force exertion: If the pressure difference between the left and right feet increases by more than 10% in three consecutive training sessions, the system will send a 'risk of imbalance in force exertion' warning and generate a correction plan (such as 'left single-leg balance training, 3 sets × 10 times per day').

[0074] Historical trend analysis: The app stores 30 days of exercise data and dynamically displays changes in force exertion on the left and right feet through a pressure distribution heatmap, helping users monitor the effect of posture correction over the long term.

[0075] Example: Applied to a smart agility training mat

[0076] 1. Training mat structure

[0077] Main material: TPU supercritical foaming process, density 0.07~0.09g / cm³, energy feedback rate 85%~89%, thickness 10mm, size 1100mm×340mm;

[0078] Sensor distribution: Two piezoresistive sensors (detection range 10~200kg) are symmetrically embedded on the left and right sides, and are integrally formed with the foam layer through the embedding process. The wires are connected to the circuit module through the internal channel.

[0079] Circuit module: Located at the logo of the training pad, it includes an ECU (integrated MCU, Bluetooth 5.0, NFC module), a 3.7V polymer battery (500mAh), a Type-C charging port and a buzzer, and the shell is waterproof.

[0080] 2. Pressure detection process (1) The user stands in the center of the training mat, with both feet on the left and right sensor areas respectively. The ECU quickly connects to the mobile APP via NFC and starts the detection; (2) When jumping, the sensor is compressed, causing the resistance of R2 to change. The ECU collects the data in real time. And calculate the pressure value:

[0081] If the left sensor pressure resistance R=500Ω and the proportional coefficient k=0.2N / Ω, then the pressure on the left foot N=0.2×500=100N (about 10.2kg); (3) The timer records the time of the first jump (t1=0.5s) and landing (t2=0.8s), calculates the hang time=0.3s, and the movement frequency=60 times / minute (1 time / second); (4) The APP compares the data with the "Adult Agility Training Standard": the hang time of 0.3s meets the standard (≤0.4s), and the step frequency of 1 time / second is lower than the standard (≥1.2 times / second), prompting "the step frequency is too slow, it is recommended to increase the arm swing speed".

[0082] The working principle of this technical solution is as follows:

[0083] Data acquisition layer: Piezoresistive sensors convert mechanical pressure into resistance changes and output voltage signals through voltage divider circuits;

[0084] Signal processing layer: The ECU samples the voltage through the ADC module, calculates the piezoresistive data by combining the circuit law, and then converts it into a pressure value through the proportional coefficient;

[0085] Motion analysis layer: Timers record the timing of pressure changes, extract parameters such as the number of jumps and hang time, and generate motion frequency and recovery reaction time through algorithms;

[0086] Results Feedback Layer: Compares motion parameters with a standard database and outputs a multi-dimensional evaluation report via a buzzer and an app.

[0087] The advantages of this technical solution are:

[0088] High precision and real-time performance: Employs 10Hz ADC sampling and left and right partitioned sensors, with pressure detection error ≤0.5kg and motion parameter delay <100ms;

[0089] Intelligent and portable: It integrates Bluetooth / NFC dual-mode connectivity, supports real-time data viewing via mobile APP, and is less than 20mm thick, making it suitable for home and professional training scenarios;

[0090] Multifunctional assessment: It not only monitors stress and cadence, but also helps prevent sports injuries (such as sprains caused by uneven stress on the ankle joint) through left and right foot balance analysis, recovery reaction time assessment, cadence, explosive power, ground contact time during exercise, and left and right balance during exercise.

[0091] Durability and comfort: TPU supercritical foam material has 20% better compression resistance than traditional EVA, and the embedded molding process enables seamless integration of sensors and pads, avoiding discomfort underfoot.

[0092] Those skilled in the art can apply this method to other rehabilitation equipment such as yoga mats and trampolines by adjusting the number of sensors, sampling frequency, or standard database, and all such applications fall within the scope of protection of this invention.

[0093] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention specification, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method of training rehabilitation equipment pressure detection, characterized by: The method comprises the following steps: (1) obtaining the piezoresistive data of the sensor: by collecting the voltage signal of the sensor, the piezoresistive data of the sensor is calculated based on the Kirchhoff's law and Ohm's law; (2) calculating the pressure value: based on the corresponding relationship between the piezoresistive data and the preset proportional coefficient, the bearing pressure value of the training rehabilitation equipment is calculated; (3) obtaining the motion parameters: by recording the number of changes of the pressure value within a preset time and the peak interval time through a timer, the jumping number, interval time and motion frequency of the target motion are determined; (4) evaluating the training effect: comparing the pressure value, jumping number, interval time and motion frequency with the preset motion standard, and outputting the training standard evaluation result.

2. The pressure detection method of a training rehabilitation equipment according to claim 1, characterized in that: In step (1), "calculating the piezoresistive data of the sensor based on the Kirchhoff's law and Ohm's law" includes: A closed loop is selected by an input voltage , a fixed resistor R1, a sensor equivalent resistor R2, and a ground terminal. Kirchhoff's voltage law (KVL) is applied to obtain a loop current I= / (R1+R2). The sensor output voltage =I*R2 is calculated by Ohm's law, and the resistance value of R2 is obtained as the piezoresistive data.

3. The method of claim 1, wherein: The "preset proportion coefficient" in step (2) is calibrated by the following method: before the sensor is shipped, a proportion coefficient k is fitted by applying a mapping relationship between a known pressure value and corresponding piezoresistance data, so that the pressure value N=k*R, where R is the piezoresistance data calculated in step (1); the preset proportion coefficient is dynamically calibrated by environmental parameters (temperature, humidity), and the calibration formula is where a, b, c are calibration coefficients, is the initial coefficient, T is the temperature, and H is the humidity.

4. The method of claim 1, wherein: In step (3), "recording through a timer" includes: Using continuous sampling ADC (analog-to-digital conversion) to obtain the real-time changes of the pressure value; Timing the number of changes of the ADC signal to count the number of pressure changes within a preset time; Timing the peak interval of the ADC signal to record the time difference between adjacent high and low peak values.

5. The method of claim 1, wherein: In step (3), "motion frequency" is calculated by dividing the number of pressure changes within a preset time by the preset time to obtain the average motion frequency per unit time.

6. The method of claim 1, wherein: In step (3), "interval time" includes the time interval between adjacent pressure changes and the recovery reaction time from high peak to low peak in a single pressure change.

7. The method of claim 1, wherein: In step (4), "preset motion standard" is the training intensity standard defined by the sports association or the field of rehabilitation medicine, including the pressure threshold corresponding to the target body weight, the standard jumping number range and the standard interval time range; the preset motion standard is dynamically adjusted based on the user label, and the standard database is optimized by a transfer learning algorithm.

8. The method of claim 1, wherein: In step (4), "training standard evaluation result" includes: When the pressure value is higher or lower than the pressure threshold, output "training intensity abnormal" prompt; When the jumping number or interval time deviates from the standard range, output "training rhythm abnormal" prompt; When the motion frequency meets the standard range, output "training intensity meets the standard" prompt; When the pressure peak decay slope is greater than 50 kg / ms, output 'insufficient landing cushion' prompt; when the left and right foot pressure difference increase is greater than 10%, output 'force imbalance risk' warning.

9. The method of claim 1, wherein: The resistance value of the fixed resistor R1 is 1kΩ~10kΩ, and the input voltage is 3V~5V.

10. The method of claim 1, wherein: The sensor is a piezoresistive sensor, and the timer is integrated in the MCU, with a sampling frequency not less than 10 Hz.

Images