Muscle fatigue injury analysis evaluation system
By acquiring muscle signals through flexible strain sensors and electrode pads, and combining them with host computer processing and neural network prediction models, the problem of relying on subjective feelings in the analysis of muscle fatigue damage in existing technologies has been solved, and accurate automatic analysis has been achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- THE SECOND AFFILIATED HOSPITAL OF NAVAL MEDICAL UNIVERSITY PLA
- Filing Date
- 2024-12-05
- Publication Date
- 2026-06-05
AI Technical Summary
In existing technologies, the analysis of muscle fatigue injury relies on the patient's subjective feelings and the doctor's professional experience, which leads to inaccurate analysis results.
Flexible strain sensors and electrode pads are used to collect muscle deformation signals and surface electromyography signals. These signals are then transmitted to the controller via a signal acquisition module. The controller performs noise reduction, filtering, and enhancement processing using a host computer, and automatically analyzes the data using a BP neural network prediction model.
It enables accurate and automated analysis of muscle fatigue-related injuries, reducing subjective errors and improving the accuracy of analysis results.
Smart Images
Figure CN122140258A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of muscle fatigue injury technology, and in particular to a muscle fatigue injury analysis and evaluation system. Background Technology
[0002] Muscle fatigue injury refers to chronic, overuse injury caused by excessive muscle activity or sustained tension while at rest. Depending on the cause, muscle fatigue injury can be classified as acute or chronic muscle strain. Typical symptoms include localized muscle pain, tenderness, and dysfunction. Symptoms can recur and are most common in areas of high stress, such as the lower back and shoulders.
[0003] Currently, in clinical practice, the main approach to muscle fatigue injuries is to have patients describe their subjective feelings. Based on these feelings, doctors then use their professional experience to make an analysis and judgment. However, over-reliance on the analysis and judgment of patients' subjective feelings and doctors' professional experience can easily lead to large errors in the analysis of muscle fatigue injuries and inaccurate results. Summary of the Invention
[0004] This invention addresses the problems and shortcomings of existing technologies by providing a muscle fatigue injury analysis and evaluation system.
[0005] The present invention solves the above-mentioned technical problems through the following technical solution:
[0006] This invention provides a muscle fatigue injury analysis and evaluation system, characterized in that it includes a flexible strain sensor and a main unit. The main unit includes a main unit housing, a mounting plate fixed to the back of the main unit housing, an electrode plate disposed at the center of the back of the mounting plate, and an adhesive layer disposed around the electrode plate on the back of the mounting plate. The main unit housing contains a signal acquisition module, a controller, and a wireless communication module. The flexible strain sensor is attached to the muscle of the human body to be tested, and the main unit is also attached to the muscle of the human body to be tested through the adhesive layer, so that the electrode plate is attached to the muscle of the human body to be tested.
[0007] The flexible strain sensor is used to sense the deformation signal of human muscles, the electrode plate is used to sense the surface electromyography signal of human muscles, and the signal acquisition module is used to acquire the deformation signal sensed by the flexible strain sensor and the surface electromyography signal sensed by the electrode plate and transmit them to the controller.
[0008] The controller is used to upload deformation signals and surface electromyography signals to the host computer via a wireless communication module;
[0009] The host computer is used to acquire the deformation signal and surface electromyography signal of the muscle of the human body to be tested within a certain period of time. The deformation signal is denoised to remove the noise component in the signal to obtain the denoised deformation signal. The surface electromyography signal is denoised to remove the noise component in the signal to obtain the denoised surface electromyography signal.
[0010] The host computer is also used to filter the denoised deformation signal to remove unwanted frequency components or enhance the frequency components of interest to obtain the filtered deformation signal, and to filter the denoised surface electromyography signal to remove unwanted frequency components or enhance the frequency components of interest to obtain the filtered surface electromyography signal.
[0011] The host computer is also used to enhance the filtered deformation signal to improve the clarity and contrast of the signal, thereby obtaining the enhanced deformation signal; and to enhance the filtered surface electromyography signal to improve the clarity and contrast of the signal, thereby obtaining the enhanced surface electromyography signal.
[0012] The host computer is also used to extract features from the enhanced deformation signal to obtain deformation features, extract features from the enhanced surface electromyography signal to obtain electromyography features, input the deformation features and electromyography features into the trained neural network prediction model for prediction, and output whether the muscles of the human body to be tested have muscle fatigue damage. If yes, it analyzes and displays information that the muscles of the human body to be tested have muscle fatigue damage; if no, it analyzes and displays information that the muscles of the human body to be tested do not have muscle fatigue damage.
[0013] The denoising algorithm used in the denoising process is the wavelet denoising algorithm.
[0014] The filtering process uses a bandpass filter.
[0015] The enhancement process utilizes histogram equalization and contrast enhancement techniques.
[0016] The main unit housing also contains a battery, which powers the signal acquisition module, controller, and wireless communication module.
[0017] The deformation features include time-frequency deformation features and frequency domain deformation features, and the electromyographic features include time-frequency electromyographic features and frequency domain electromyographic features.
[0018] The neural network prediction model is a neural network prediction model constructed using a BP neural network.
[0019] The positive and progressive effects of this invention are as follows:
[0020] This invention can automatically collect deformation signals and surface electromyography (EMG) signals corresponding to the muscles of the human body to be tested. The deformation signals and EMG signals are subjected to noise reduction, filtering, and signal enhancement processing, respectively. Furthermore, feature extraction is performed to obtain deformation features and EMG features. The deformation features and EMG features are input into a trained neural network prediction model for prediction. The model can predict whether the muscles of the human body to be tested have muscle fatigue damage. This invention does not rely on the patient's subjective feelings or the doctor's professional experience for analysis and judgment, and the analysis and evaluation results are accurate. Attached Figure Description
[0021] Figure 1 This is a control principle diagram of a muscle fatigue injury analysis and evaluation system according to a preferred embodiment of the present invention.
[0022] Figure 2 This is a schematic diagram of the structure of the muscle fatigue injury analysis and evaluation system according to a preferred embodiment of the present invention. Detailed Implementation
[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, 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.
[0024] like Figure 1-2 As shown, this embodiment provides a muscle fatigue injury analysis and evaluation system, which includes a flexible strain sensor 10 and a main unit 20. The main unit 20 includes a main unit housing 21, and a mounting plate 22 is fixed to the back of the main unit housing 21. An electrode sheet 23 is disposed at the middle position of the back of the mounting plate 22. An adhesive layer is disposed around the electrode sheet 23 on the back of the mounting plate 22. A battery 24, a signal acquisition module 25, a controller 26, and a wireless communication module 27 are disposed inside the main unit housing 21. The battery 24 supplies power to the signal acquisition module 25, the controller 26, and the wireless communication module 27. The flexible strain sensor 10 is attached to the muscle of the human body to be tested, and the main unit 20 is also attached to the muscle of the human body to be tested through the adhesive layer, so that the electrode sheet 23 is attached to the muscle of the human body to be tested.
[0025] The flexible strain sensor 10 includes a flexible substrate 11. A first pinch piece 12 and a second pinch piece 13 are respectively attached to both ends of the upper surface of the flexible substrate 11. A conductive layer 14 is attached to the upper surface of the flexible substrate 11 between the first pinch piece 12 and the second pinch piece 13. One end of the conductive layer 14 is connected to one end of a positive electrode 15. The other end of the positive electrode 15 is sandwiched between the flexible substrate 11 and the first pinch piece 12 and is welded to one end of a positive wire 16 passing through the first pinch piece 12. The other end of the positive wire 16 is connected to the interface 251 of the signal acquisition module 25. The other end of the conductive layer 14 is connected to one end of a negative electrode 17. The other end of the negative electrode 17 is sandwiched between the flexible substrate 11 and the first pinch piece 12 and is welded to one end of a negative wire 18 passing through the first pinch piece 12. The other end of the negative wire 18 is connected to the interface 251 of the signal acquisition module 25.
[0026] Furthermore, a lower protective sheet 19 is attached to the lower surface of the flexible substrate 11, and the lower protective sheet 19 covers the lower surface of the flexible substrate 11. An upper protective sheet 110 is attached to the upper surface of the first pinch sheet 12, the conductive layer 14, and the second pinch sheet 13, and the upper protective sheet 110 covers the upper surface of the first pinch sheet 12, the conductive layer 14, and the second pinch sheet 13. The upper protective sheet 110 and the lower protective sheet 19 are bonded together.
[0027] In this embodiment, the flexible strain sensor 10 and the electrode sheet 23 are both electrically connected to the signal acquisition module 25, the signal acquisition module 25 and the wireless communication module 27 are both electrically connected to the controller 26, and the controller 26 communicates with the host computer 30 through the wireless communication module 27.
[0028] The flexible strain sensor 10 is used to sense the deformation signal of human muscle, the electrode 23 is used to sense the surface electromyography signal of human muscle, and the signal acquisition module 25 is used to acquire the deformation signal sensed by the flexible strain sensor 10 and the surface electromyography signal sensed by the electrode 23 and transmit them to the controller 26.
[0029] The controller 26 is used to upload deformation signals and surface electromyography signals to the host computer 30 via the wireless communication module 27.
[0030] The host computer 30 is used to acquire deformation signals and surface electromyography (EMG) signals corresponding to the muscles of the human body under test over a period of time. The deformation signals are denoised to remove noise components, resulting in denoised deformation signals. Similarly, the surface EMG signals are denoised to remove noise components, resulting in denoised surface EMG signals. The denoising algorithm used is a wavelet denoising algorithm.
[0031] The host computer 30 is also used to filter the denoised deformation signal to remove unwanted frequency components or enhance the frequency components of interest, thereby obtaining a filtered deformation signal, and to filter the denoised surface electromyography (EMG) signal to remove unwanted frequency components or enhance the frequency components of interest, thereby obtaining a filtered EMG signal. A bandpass filter is used for the filtering process.
[0032] The host computer 30 is also used to enhance the filtered deformation signal to improve its clarity and contrast, thereby obtaining an enhanced deformation signal, and to enhance the filtered surface electromyography (EMG) signal to improve its clarity and contrast, thereby obtaining an enhanced EMG signal. The enhancement processing utilizes histogram equalization and contrast enhancement methods.
[0033] The host computer 30 is also used to extract features from the enhanced deformation signal to obtain time-frequency deformation features and frequency domain deformation features, and to extract features from the enhanced surface electromyography (EMG) signal to obtain time-frequency EMG features and frequency domain EMG features. The time-frequency deformation features, frequency domain deformation features, time-frequency EMG features, and frequency domain EMG features are input into a trained neural network prediction model constructed using a BP neural network for prediction. The model outputs whether the muscles in the human body to be tested have muscle fatigue damage. If yes, it analyzes and displays information that the muscles in the human body to be tested have muscle fatigue damage; if no, it analyzes and displays information that the muscles in the human body to be tested do not have muscle fatigue damage.
[0034] While specific embodiments of the present invention have been described above, those skilled in the art should understand that these are merely illustrative examples, and the scope of protection of the present invention is defined by the appended claims. Those skilled in the art can make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but all such changes and modifications fall within the scope of protection of the present invention.
Claims
1. A muscle fatigue injury analysis and evaluation system, characterized in that, It includes a flexible strain sensor and a main unit. The main unit includes a main unit housing, a mounting plate fixed to the back of the main unit housing, an electrode plate disposed in the middle of the back of the mounting plate, and an adhesive layer disposed around the electrode plate on the back of the mounting plate. The main unit housing contains a signal acquisition module, a controller, and a wireless communication module. The flexible strain sensor is attached to the muscle of the human body to be tested, and the main unit is also attached to the muscle of the human body to be tested through the adhesive layer so that the electrode plate is attached to the muscle of the human body to be tested. The flexible strain sensor is used to sense the deformation signal of human muscles, the electrode plate is used to sense the surface electromyography signal of human muscles, and the signal acquisition module is used to acquire the deformation signal sensed by the flexible strain sensor and the surface electromyography signal sensed by the electrode plate and transmit them to the controller. The controller is used to upload deformation signals and surface electromyography signals to the host computer via a wireless communication module; The host computer is used to acquire the deformation signal and surface electromyography signal of the muscle of the human body to be tested within a certain period of time. The deformation signal is denoised to remove the noise component in the signal to obtain the denoised deformation signal. The surface electromyography signal is denoised to remove the noise component in the signal to obtain the denoised surface electromyography signal. The host computer is also used to filter the denoised deformation signal to remove unwanted frequency components or enhance the frequency components of interest to obtain the filtered deformation signal, and to filter the denoised surface electromyography signal to remove unwanted frequency components or enhance the frequency components of interest to obtain the filtered surface electromyography signal. The host computer is also used to enhance the filtered deformation signal to improve the clarity and contrast of the signal, thereby obtaining the enhanced deformation signal; and to enhance the filtered surface electromyography signal to improve the clarity and contrast of the signal, thereby obtaining the enhanced surface electromyography signal. The host computer is also used to extract features from the enhanced deformation signal to obtain deformation features, extract features from the enhanced surface electromyography signal to obtain electromyography features, input the deformation features and electromyography features into the trained neural network prediction model for prediction, and output whether the muscles of the human body to be tested have muscle fatigue damage. If yes, it analyzes and displays information that the muscles of the human body to be tested have muscle fatigue damage; if no, it analyzes and displays information that the muscles of the human body to be tested do not have muscle fatigue damage.
2. The muscle fatigue injury analysis and evaluation system as described in claim 1, characterized in that, The flexible strain sensor includes a flexible substrate. A first pinch piece and a second pinch piece are respectively attached to both ends of the upper surface of the flexible substrate. A conductive layer is attached to the upper surface of the flexible substrate, between the first and second pinch pieces. One end of the conductive layer is connected to one end of a positive electrode. The other end of the positive electrode is sandwiched between the flexible substrate and the first pinch piece and is welded to one end of a positive electrode wire passing through the first pinch piece. The other end of the positive electrode wire is connected to a signal acquisition module. The other end of the conductive layer is connected to one end of a negative electrode. The other end of the negative electrode is sandwiched between the flexible substrate and the first pinch piece and is welded to one end of a negative electrode wire passing through the first pinch piece. The other end of the negative electrode wire is connected to the signal acquisition module.
3. The muscle fatigue injury analysis and evaluation system as described in claim 1, characterized in that, The denoising process employs a wavelet denoising algorithm.
4. The muscle fatigue injury analysis and evaluation system as described in claim 1, characterized in that, The filtering process uses a bandpass filter.
5. The muscle fatigue injury analysis and evaluation system as described in claim 1, characterized in that, The enhancement process utilizes histogram equalization and contrast enhancement techniques.
6. The muscle fatigue injury analysis and evaluation system as described in claim 1, characterized in that, The main unit housing also contains a battery, which powers the signal acquisition module, controller, and wireless communication module.
7. The muscle fatigue injury analysis and evaluation system as described in claim 1, characterized in that, The deformation features include time-frequency deformation features and frequency domain deformation features, and the electromyographic features include time-frequency electromyographic features and frequency domain electromyographic features.
8. The muscle fatigue injury analysis and evaluation system as described in claim 1, characterized in that, The neural network prediction model is a neural network prediction model constructed using a BP neural network.