Muscle fatigue detection method and detection equipment

Abstract

The invention discloses a muscle fatigue detection method and detection equipment, and relates to the technical field of muscle fatigue detection.The detection method comprises the following steps that S1, an air bag with a pressure sensor and a blood oxygen sensor is kept on the body of a user, the air bag is inflated to keep the pressure sensor and the blood oxygen sensor close to the body of the user; s2, a pressure sensor and a blood oxygen sensor collect pressure data and blood oxygen data of the muscle surface respectively, and the collected data are transmitted to a processing unit to be processed and analyzed; muscle fatigue is detected through the pressure sensor and the blood oxygen sensor, during detection, the sensors are kept close to each other in an air bag inflating and pressurizing mode, the pressure of the air bag can be correspondingly set according to different pressure requirements, and the device is better in crowd applicability and more suitable for being used for a long period.

Description

Technical Field

[0001] The present invention relates to the technical field of muscle fatigue detection, and particularly relates to a muscle fatigue detection method and a detection device. Background Art

[0002] Muscle fatigue is an important issue in the fields of sports science and rehabilitation medicine, and has an important impact on human health and maintaining normal functions. In the prior art, there are various detection methods for muscle fatigue, but most of them have problems such as complex equipment and inconvenient operation. For this reason, the Chinese utility model with the publication number CN216090526U proposes a "muscle tension degree detection device", which uses a pressure sensor to reflect the tremor state of the muscle, makes a preliminary judgment, and then allows the subject to perform specific actions, and uses an electromyography sensor to obtain the change of the electromechanical signal. The combination of the two can relatively accurately judge the muscle tension and fatigue degree of the subject. And it is equipped with a blood oxygen sensor to make the detection and judgment results more accurate.

[0003] However, when it is in use, in order to be held in use through an elastic band, after being used for a period of time, the attenuation of its elastic band is obvious, which is not conducive to long-term use. Summary of the Invention

[0004] The present invention aims to provide a technical solution that can solve the above problems to overcome the above situations.

[0005] To achieve the above purpose, the present invention provides the following technical solution: A muscle fatigue detection method, the detection method includes the following steps: Step S1: Hold an airbag with a pressure sensor and a blood oxygen sensor on the user's body, and inflate the airbag to keep the pressure sensor and the blood oxygen sensor close to the user's body; Step S2: The pressure sensor and the blood oxygen sensor respectively collect the pressure data and blood oxygen data on the muscle surface, and the collected data is transmitted to the processing unit for processing and analysis.

[0006] As a further solution of the present invention: In step S2, the processing unit judges the stiffness of the muscle according to the change of the pressure data of the pressure sensor, and combines the change of the blood oxygen data to confirm the muscle fatigue degree.

[0007] As a further solution of the present invention: In step S2, the collected blood oxygen data includes blood oxygen concentration data.

[0008] As a further solution of the present invention: In step S2, the processing unit first performs filtering and denoising processing on the pressure data of the pressure sensor; then, judges the stiffness of the muscle according to the processed pressure data; at the same time, combines the change of the blood oxygen concentration data to confirm the muscle fatigue degree.

[0009] As a further aspect of the present invention: In step S2, the processing unit processes and analyzes the received data, including: Step S201: Decompose the signal into main and slave channels through CEEMDAN-MPE joint decomposition; screen the high-entropy IMF components in the main channel, capture the noise floor in the slave channel, and achieve cross-modal synchronization through Hilbert-Huang phase alignment.

[0010] As a further aspect of the present invention: In step S2, the processing unit's processing and analysis of the received data further includes: Step S202: Implement frequency-domain constrained filtering on the IMF components through a CLMS dynamic filter, synchronously generate an aliasing degree feedback coefficient in the range of 0-1, and dynamically adjust the filtering weights every 10 ms.

[0011] As a further aspect of the present invention: In step S2, the processing unit's processing and analysis of the received data further includes: Step S203: Implement entropy weight allocation on the main and slave channel data based on the spatio-temporal domain feature pool, use the hyperbolic tangent function for non-linear mapping to suppress feature saturation, and output a decision result with both classification probability distribution and continuous value prediction.

[0012] The present invention provides the following technical solution: A muscle fatigue detection device, including an inflatable and deflatable airbag, a holding member provided on the airbag for holding the airbag on the user's body, a pressure sensor provided on the airbag for detecting the muscle pressure of the user, and a blood oxygen sensor for detecting the blood oxygen of the user; It further includes a processing unit, which receives the pressure signal from the pressure sensor and the blood oxygen signal from the blood oxygen sensor, and performs processing and analysis. When performing muscle fatigue detection, run the muscle fatigue detection method described in the above claims.

[0013] As a further aspect of the present invention: The holding member includes a holding sleeve, and the airbag is provided inside the holding sleeve; When the holding sleeve is sleeved on the user's body, the airbag is formed between the protective sleeve and the user's body; When the inflated airbag presses against the user's body, the airbag is formed to press the pressure sensor and the blood oxygen sensor against the user's body.

[0014] As a further aspect of the present invention: It further includes a controller and a pneumatic regulation unit for inflating and deflating the airbag.

[0015] Compared with the prior art, the beneficial effects of the present technical solution are as follows: The pressure sensor and the blood oxygen sensor are used to detect muscle fatigue. During the detection, the airbag is inflated and pressurized to keep the sensors close to the user's body. The pressure of the airbag can be set correspondingly according to different pressure requirements, which has better applicability to different people and is more suitable for long-term use.

[0016] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0018] Figure 1 is a flowchart of the muscle fatigue detection method of the present invention; Figure 2 is a schematic diagram of the holding sleeve of the detection device of the present invention sleeved on the leg; Figure 3 is a schematic structural diagram of the detection device of the present invention.

[0019] The corresponding reference numerals in the drawings are explained as follows: Airbag - 1, Pressure sensor - 2, Blood oxygen sensor - 3, Holding sleeve - 4, Mounting sleeve - 5, Controller - 6, Air pump - 7, Pipe fitting - 8, Electric control valve - 9, Installation space - 10, Processing unit - 11. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0021] Please refer to Figures 1-3 , a muscle fatigue detection method, the detection method includes the following steps: Step S1, holding an airbag with a pressure sensor and a blood oxygen sensor on the user's body, and inflating the airbag to keep the pressure sensor and the blood oxygen sensor close to the user's body; Step S2: The pressure sensor and the blood oxygen sensor respectively collect the pressure data and blood oxygen data on the muscle surface, and the collected data is transmitted to the processing unit for processing and analysis.

[0022] This detection method uses a pressure sensor and a blood oxygen sensor to detect muscle fatigue. During detection, the sensor is closely held by inflating and pressurizing the airbag, and the pressure of the airbag can be correspondingly set according to different pressure requirements, with better applicability to the crowd and more suitable for long-term use.

[0023] In some embodiments, in step S2, the processing unit determines the stiffness of the muscle based on the change in the pressure data of the pressure sensor, and combines the change in the blood oxygen data to confirm the degree of muscle fatigue.

[0024] In some embodiments, in step S2, the collected blood oxygen data includes blood oxygen concentration data. For example, the blood pressure sensor uses a blood oxygen concentration sensor.

[0025] In addition to the pressure sensor, this detection method also introduces a blood oxygen concentration sensor. The change in blood oxygen concentration is closely related to the degree of muscle fatigue. By measuring the blood oxygen concentration, the muscle fatigue situation can be assisted in judgment, further improving the comprehensiveness and accuracy of the detection.

[0026] In some embodiments, the pressure sensor uses a thin-film pressure strain sensor, for example.

[0027] In some embodiments, in step S2, the processing unit first performs filtering and denoising processing on the pressure data of the pressure sensor; then, determines the stiffness of the muscle based on the processed pressure data; at the same time, combines the change in the blood oxygen concentration data to confirm the degree of muscle fatigue.

[0028] In some embodiments, multiple pressure sensors are used to perform detection simultaneously at different positions, and the pressure data of different pressure sensors are mutually calibrated to improve the detection accuracy.

[0029] In this embodiment, in step S2, the processing and analysis of the received data by the processing unit include: S201: Decompose the signal into the main and slave channels through CEEMDAN-MPE joint decomposition; screen the high-entropy value IMF components in the main channel (such as entropy threshold > 4.2 bit), capture the noise floor in the slave channel, and achieve cross-modal synchronization through Hilbert-Huang phase alignment; S202: Implement frequency-domain constrained filtering on the IMF components through a CLMS dynamic filter, synchronously generate the aliasing degree feedback coefficient in the 0-1 interval, and dynamically adjust the filtering weight every 10 ms; S203. Implement entropy weight allocation for the master and slave channel data based on the spatio-temporal domain feature pool (high entropy channel weight ≥ 65%), use the hyperbolic tangent function for non-linear mapping to suppress feature saturation, and finally output a dual-mode decision result with both classification probability distribution (Softmax) and continuous value prediction (±0.1% accuracy).

[0030] In some embodiments, in step S2, the processing unit receives data in the following manner: real-time receive a multi-modal signal matrix including pressure signals and blood oxygen signals through a sliding window (such as 200 ms / 30% overlap rate), and trigger the processing flow after encapsulation by CRC-16 check.

[0031] In this embodiment, in step S201, the CEEMDAN-MPE joint decomposition includes CEEMDAN decomposition parameter setting, MPE noise component determination, and noise reference signal generation.

[0032] In some embodiments, in the CEEMDAN decomposition parameter setting, Process the pressure signal as follows: For low-frequency pressure signals (such as 0.1 - 5 Hz), use low-amplitude white noise injection ( = 0.1), the decomposition layer number m = 8, and the termination condition is that the extreme point of the residual signal ≤ 2.

[0033] Process the blood oxygen signal as follows: For high-frequency blood oxygen signals (such as 0.5 - 20 Hz), use high-amplitude white noise ( = 0.3), the decomposition layer number m = 12, and the residual energy threshold is set to 1% of the original signal energy.

[0034] In some embodiments, in the MPE noise component determination, The calculation method of multi-scale permutation entropy (MPE) is as follows: Calculate the permutation entropy of each IMF component for scales s = 1 to s = 5, and the formula is: where is the symbol sequence probability distribution; The screening of noise IMFs is as follows: For the pressure signal: IMFs with MPE < 0.35 are determined as noise (such as baseline drift, power frequency interference).

[0035] For the blood oxygen signal: IMFs with MPE > 0.72 are determined as motion artifacts (such as limb swing noise).

[0036] In some embodiments, in the noise reference signal generation, the screened noise IMFs are superimposed to generate a noise reference signal n(t) in the same frequency band as the original signal for subsequent filtering.

[0037] In this embodiment, the CLMS dynamic filter is composed of parallel LMS (Least Mean Square) and RLS (Recursive Least Square) sub-filters, and the output is the weighted sum of the two: ‌LMS filter‌: Suitable for the slow time-varying characteristics of the pressure signal, the step size .

[0038] ‌RLS filter‌: Suitable for the fast transient noise of the blood oxygen signal, the forgetting factor .

[0039] In this embodiment, in step S202, the ‌weight iteration formula is‌: where is the learning rate, and e(t) is the error between the desired signal and the filtered output.

[0040] ‌The initial weight assignment is‌: The pressure signal is dominated by LMS ( ), and it has better suppression of steady-state noise.

[0041] The blood oxygen signal is dominated by RLS ( 2), and it has a faster response to burst noise.

[0042] Through simulation comparison experiments, the signal-to-noise ratio of this filter under mixed noise (Gaussian white noise + motion artifacts) is increased to 15.2 dB.

[0043] In this embodiment, in step S203, pressure signal feature extraction ‌Pressure Change Rate (PCR): Quantifies the instantaneous intensity of muscle contraction, and the calculation formula is: In some embodiments, if the PCR continuously increases, it indicates that the muscle enters a compensatory contraction state, which can be correspondingly recognized as cumulative fatigue.

[0044] In this embodiment, in step S203, blood oxygen signal feature extraction ‌Oxygen Desaturation Rate (ODR)‌: Reflects the degree of imbalance between local tissue oxygen supply and consumption, and the calculation formula is: In some embodiments, the ‌threshold setting‌: ODR < -0.5% / s for 10 seconds can be correspondingly recognized as over-fatigue.

[0045] In this embodiment, in step S203, the ‌weight calculation method is‌: Dynamically adjust the fusion weight of pressure and blood oxygen characteristics according to the real-time signal-to-noise ratio (SNR): Definition of SNR: Comprehensive fatigue index: In this embodiment, by designing the above-mentioned closed-loop technical architecture of "CEEMDAN-MPE decomposition - CLMS dynamic filtering - entropy weight fusion", this architecture effectively decomposes efficiency (such as a 40% improvement) through the CEEMDAN-MPE joint decomposition method, breaks through the mode mixing limit, combines the CLMS closed-loop optimization and pipeline acceleration technology, and achieves smaller feature errors (such as ≤ 3%) and higher signal-to-noise ratio gains (such as ≥ 15 dB) while ensuring low latency (such as ≤ 25 ms).

[0046] In this embodiment, a muscle fatigue detection device is actually proposed. The detection device includes an inflatable and deflatable airbag 1, a holding member for holding the airbag 1 on the user's body is provided on the airbag 1, a pressure sensor 2 for detecting the muscle pressure of the user and a blood oxygen sensor 3 for detecting the blood oxygen of the user are provided on the airbag 1.

[0047] The detection device further includes a processing unit 11. The processing unit 11 receives the pressure signal of the pressure sensor 2 and the blood oxygen signal of the blood oxygen sensor 3, and performs processing and analysis.

[0048] When performing muscle fatigue detection, run the muscle fatigue detection method in any one of the above embodiments.

[0049] In some embodiments, the holding member includes a holding sleeve 4, and the airbag 1 is provided inside the holding sleeve 4.

[0050] When the holding sleeve 4 is sleeved on the user's body (such as the hand or leg), the airbag 1 is formed between the protective sleeve 4 and the user's body, so that when the holding sleeve 4 is sleeved on the user's body and the airbag 1 is inflated, the inflated airbag 1 forms a pressure on the user's body under the restriction of the holding sleeve 4, so that the airbag 1 can be held on the user's body.

[0051] When the inflated airbag 1 presses on the user's body, the airbag 1 makes the pressure sensor 2 and the blood oxygen sensor 3 close to the user's body.

[0052] In some embodiments, the pressure sensor 2 and the blood oxygen sensor 3 are mounted on one side of the airbag 1 corresponding to the user's body. When the inflated airbag 1 presses against the user's body, the airbag 1 constitutes pressing the pressure sensor 2 and the blood oxygen sensor 3 mounted on one side of the airbag 1 against the user's body.

[0053] Combined with the holding effect formed after the holding sleeve 4 is restricted, the pressure sensor 2 and the blood oxygen sensor 3 can be kept close to the user's body. In some embodiments, an installation sleeve 5 is further provided on the airbag 1. When the holding sleeve 4 is sleeved on the user's body (such as the hand or leg), the installation sleeve 5 is located between the airbag 1 and the user's body; the pressure sensor 2 and the blood oxygen sensor 3 are mounted on the installation sleeve 5. When the inflated airbag 1 presses against the user's body, the airbag 1 constitutes pressing the installation sleeve 5 against the user's body, thereby forming pressing the pressure sensor 2 and the blood oxygen sensor 3 on the installation sleeve 5 against the user's body.

[0054] Combined with the holding effect formed after the holding sleeve 4 is restricted, the pressure sensor 2 and the blood oxygen sensor 3 can be kept close to the user's body. In some embodiments, an installation space 10 is formed between the holding sleeve 4 and the installation sleeve 5, and the airbag 1 is arranged in the installation space 10.

[0055] Preferably, the connection lines of the pressure sensor 2 and the blood oxygen sensor 3 can be arranged through the installation space 10 to reduce the contact between the connection lines and the user's body.

[0056] In some embodiments, a plurality of installation bags (not shown) are provided on one side of the holding sleeve 4 corresponding to the airbag. The plurality of installation bags are divided into an installation bag for installing the pressure sensor and an installation bag for installing the blood oxygen sensor, and the pressure sensor and the blood oxygen sensor are respectively arranged on the corresponding installation bags.

[0057] On the side of the installation sleeve close to the user's body, a window corresponding to the installation bag is opened (not shown), and a transparent isolation member covering the installation window is further connected to the side of the installation sleeve close to the user's body. The transparent isolation member is, for example, a transparent film.

[0058] By arranging the pressure sensor and the blood oxygen sensor on one side of the installation sleeve corresponding to the airbag, direct contact between the pressure sensor and the blood oxygen sensor and the user's body is avoided, and direct contact between sweat and the pressure sensor and the blood oxygen sensor is avoided.

[0059] In some embodiments, the holding sleeve 4, the installation sleeve 5, and the airbag 1 are made of soft materials.

[0060] For example, both the holding sleeve 4 and the installation sleeve 5 are made of cloth, and the airbag 1 is made of rubber material.

[0061] In some embodiments, a plurality of airbags 1 are provided, and the plurality of airbags 1 are arranged at intervals along the length direction of the holding sleeve 4. Independent compression of multiple parts can be formed by the plurality of airbags.

[0062] In some embodiments, a plurality of pressure sensors corresponding one-to-one to the plurality of airbags are configured. Accordingly, it can be used to form fatigue detection of multiple muscles. The blood oxygen data collected by the blood oxygen sensor can be used for auxiliary judgment of fatigue conditions of multiple muscles, constituting a one-to-many auxiliary judgment of the blood oxygen sensor and the plurality of pressure sensors.

[0063] In some embodiments, the detection device further includes a controller 6 and a pneumatic regulation unit for inflating and deflating the airbag 1.

[0064] In some embodiments, the pneumatic regulation unit includes an air pump 7, and the air port of the air pump 7 is communicated with the airbag 1 through a pipe fitting 8.

[0065] In some embodiments, an electric control valve 9 is provided on the pipe fitting 8. The electric control valve 9 has a first valve state that enables the air pump to pump air into the airbag, and the electric control valve 9 also has a second valve state that enables the airbag to exhaust air. For example, the electric control valve is a three-way electric control valve.

[0066] In some embodiments, when there are multiple airbags, a communication main pipe is further configured. The communication main pipe is communicated with the air port of the air pump. Each airbag has the above-mentioned pipe fitting and electric control valve. The pipe fitting is used to communicate the corresponding airbag with the communication main pipe, and the inflation and deflation are controlled by the corresponding electric control valve. Independent inflation and deflation control of multiple airbags by a single air pump is realized.

[0067] In some embodiments, after confirming the degree of muscle fatigue, an airbag massage control corresponding to the degree of muscle fatigue is output.

[0068] The output airbag massage control is an inflation and deflation control for the airbag corresponding to the degree of muscle fatigue, forming a continuous massage action of inflating to squeeze the muscle - deflating to relieve the squeeze.

[0069] For example, when it is confirmed that the muscle is relatively fatigued, the time of airbag massage is increased; when it is confirmed that the degree of muscle fatigue is relatively low, the time of airbag massage is correspondingly reduced.

[0070] For another example, when it is confirmed that the muscle is relatively fatigued, during the inflation and extrusion stage, the extrusion force is correspondingly increased, for example, the inflation time of the airbag is increased; when it is confirmed that the degree of muscle fatigue is relatively low, during the inflation and extrusion stage, the extrusion force is correspondingly reduced, for example, the inflation time of the airbag is reduced.

[0071] In some embodiments, graded massage can be performed according to the calculation result. For example: When 0.5 ≤ F(t) < 0.75, it is recognized as level I fatigue, and massage control corresponding to a lower fatigue level is performed. When F(t) ≥ 0.75, it is recognized as level II fatigue, and massage control corresponding to a higher fatigue level is performed.

[0072] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be encompassed by the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

Claims

1. A muscle fatigue detection method, characterized in that: The detection method includes the following steps: Step S1, holding an airbag having a pressure sensor and a blood oxygen sensor on the user's body, and inflating the airbag to keep the pressure sensor and the blood oxygen sensor close to the user's body; Step S2: The pressure sensor and the blood oxygen sensor collect pressure data and blood oxygen data on the muscle surface respectively, and the collected data are transmitted to the processing unit for processing and analysis.

2. The muscle fatigue detection method according to claim 1, characterized in that: In step S2, the processing unit determines the stiffness of the muscle according to the change of the pressure data of the pressure sensor, and confirms the degree of muscle fatigue in combination with the change of the blood oxygen data.

3. The muscle fatigue detection method according to claim 1, characterized in that: In step S2, the collected blood oxygen data includes blood oxygen concentration data.

4. The muscle fatigue detection method according to claim 3, characterized in that: In step S2, the processing unit first filters and denoises the pressure data of the pressure sensor; then, determines the stiffness of the muscle based on the processed pressure data; and at the same time, confirms the degree of muscle fatigue in combination with the change in blood oxygen concentration data.

5. The muscle fatigue detection method according to claim 1 or 3, characterized in that: In step S2, the processing unit processes and analyzes the received data including: Step S201, decompose the signal into master and slave channels through CEEMDAN-MPE joint decomposition; the master channel filters the high entropy IMF component, the slave channel captures the noise floor, and realizes cross-modal synchronization through Hilbert-Huang phase alignment.

6. The muscle fatigue detection method according to claim 5, characterized in that: In step S2, the processing unit processes and analyzes the received data further comprising: Step S202: frequency-domain constrained filtering is performed on the IMF component through a CLMS dynamic filter, and an aliasing degree feedback coefficient in the range of 0-1 is synchronously generated, and the filtering weight is dynamically adjusted every 10 ms.

7. The muscle fatigue detection method according to claim 6, characterized in that: In step S2, the processing unit processes and analyzes the received data further comprising: Step S203: Based on the spatiotemporal feature pool, entropy weights are allocated to the master and slave channel data, and feature saturation is suppressed by nonlinear mapping using the hyperbolic tangent function, so as to output a decision result that has both classification probability distribution and continuous value prediction.

8. A muscle fatigue detection device, characterized in that: The airbag includes an inflatable and deflated airbag, a retaining member for retaining the airbag on the user's body, a pressure sensor for detecting the user's muscle pressure and a blood oxygen sensor for detecting the user's blood oxygen; The system also includes a processing unit, which receives the pressure signal of the pressure sensor and the blood oxygen signal of the blood oxygen sensor, and performs processing and analysis. When performing muscle fatigue detection, the muscle fatigue detection method described in any one of claims 1 to 7 is executed.

9. The muscle fatigue detection device according to claim 8, characterized in that: The retaining member comprises a retaining sleeve, and the airbag is arranged on the inner side of the retaining sleeve; When the protective cover is put on the user's body, the airbag is located between the protective cover and the user's body; When the inflated airbag is pressed against the user's body, the airbag structure brings the pressure sensor and the blood oxygen sensor close to the user's body.

10. The muscle fatigue detection device according to claim 8 or 9, characterized in that: It also includes a controller and an air pressure regulating unit for inflating and deflating the airbag.

Images