In order to solve the real-time control problem of hand rehabilitation exoskeleton robot, a motion angle decoding model was proposed based on surface EMG signal and synchronous motion angle value. The long short-term memory neural network was used to construct the hand motion angle decoding model. During recognition, EMG signal and synchronous angle signal are sent to the model for decoding, and the output of the model is the angle prediction value after 200ms. The experimental results show that the combination of motion angle signal and EMG signal can significantly improve the decoding ability of the model.
This paper introduced the development of a hand rehabilitation therapy system based on virtual reality technology aimed at encouraging stroke patients with hand movement disorders to undertake rehabilitation exercises. The system uses Leap Motion controller, Unity3D development platform and Visual Studio2019 integrated development environment to design, including three modules: game module, interaction module, adaptive module. The game module includes physical simulation, collision detection, audio-visual feedback and other functions, which can better immerse patients in the virtual environment. The interaction module realizes the function of collecting and transmitting the hand movement information and interacting with the game module. According to the patient's performance, the adaptive module, such as game time and object size, can adjust the internal parameters of the system reasonably and appropriately, so as to match the task with the patient's ability. The system has the characteristics of self-adaptation, strong immersion and simple deployment, which can improve the fun of training and the sense of gain of players, and lay the foundation for stroke patients to carry out hand function rehabilitation training at home.
KEYWORDS: Control systems, Education and training, Signal processing, Sensors, Neural networks, Motion models, Electromyography, Design and modelling, Electrodes, Motion detection
At present, the hand rehabilitation training system mainly adopts passive rehabilitation training method, and the training mode is relatively simple, which cannot reflect the movement intention of patients. This paper has designed and produced a kind of predictive control based on the methods of electricity hand rehabilitation training system, the system can according to your hand on the multi-channel sEMG predict intentions and movement angle, and then drive the exoskeleton robot assisted hand movement, as reflected in training patients' movement intentions, to realize active rehabilitation training. In order to achieve the compliance of the control and prevent the secondary injury to patients, this paper designed the exoskeleton manipulator sliding mode control method. The simulation results and experimental results verify the correctness of the design. The sEMG acquisition and prediction system can accurately predict the motion intention of patients, and the steady-state error of the final control can be kept within 5 degrees, with good accuracy and reliability, which is expected to be applied in the hand rehabilitation training of stroke patients.
KEYWORDS: Electroencephalography, Feature extraction, Education and training, Detection and tracking algorithms, Machine learning, Data modeling, Signal processing, Deep learning, Brain-machine interfaces, Matrices
Aiming at the problems that the traditional classification and recognition methods of left and right-handed motor imagery EEG signals require prior knowledge and feature extraction requires manual design, the process is cumbersome, and the recognition accuracy is not high, A one-dimensional CNN-LSTM network model that can automatically learn signal features is proposed based on the public motor imagery dataset. The CNN-LSTM network model uses a one-dimensional CNN network to automatically learn and extract the deep-level features of EEG time series, and send the feature sequence to the LSTM classifier for classification. The recognition accuracy of the proposed algorithm is 93.57%. Compared with other algorithms, the proposed algorithm can obtain higher recognition accuracy, and at the same time, it can omit the tedious data preprocessing and feature extraction steps. The proposed method is of great significance to the research on brain-computer interface recognition algorithms.
Regardless of many researches done in recent years, most wind turbines are still unable to reach their design lifetime [5]. Failures in the gearbox, especially in the planetary stage, have been a major cause of reliability problems in the modern wind energy turbine system. The following paper proposes a fault diagnosis method based on the strain signal of the ring gear. First, the strain signal is collected from the side of the ring gear using FBG sensors in normal condition and faulty condition. Then the collected strain signal is processed and analyzed. In the time-domain analysis, traditional statistical indicators like Peak to Peak, Kurtosis, Crest factor and Peak value are adopted. The analysis results show the effectiveness of the proposed method for identifying tooth crack fault of the ring gear.
A large-range three-coil coaxial optical fiber displacement sensor for measuring the air gap of a direct-drive wind turbine is designed in this paper so as to overcome the problem that the traditional reflective optical fiber sensor has a small measuring range. The mathematical model of the modulation function of the three-coil coaxial large-range fiber displacement sensor is established by using the simplified geometric optical reflection spot model, so that the ratio compensation mechanism under different combinations is analyzed and compared, and the parameters affecting the characteristics of the sensor, including the fiber core radius R and the numerical aperture NA of the transmitting fiber, and the number of receiving fiber loops in the second, third and fourth layers of the sensor probe are analyzed by simulation. The results show: As the number of laps of the receiving fiber turns, the sensor range is significantly improved, and its sensitivity is improved, but the corresponding initial dead zone is also increased; the smaller the numerical aperture of the transmitting fiber, the larger the linear range of the output characteristic curve; the larger the radius of the fiber core, the larger the linear range of the output characteristic curve, but the corresponding initial dead zone becomes larger and the sensitivity is reduced, so that the final selected design parameters of the system are given by analysis. Finally, through the sensor characteristics experiment, the actual measurement range of the sensor probe is consistent with the theoretical simulation results, and its measuring range can reach 3.5mm- 8.5mm.
There is temperature and pressure cross-sensitivity when using ordinary fiber to detect pressure. In order to solve this problem, a fiber Bragg grating pressure and temperature sensor based on double equal thickness and equal strength cantilever beam was proposed in this paper. Feasibility of the structure was verified by theoretical analysis and simulation. The first sensing element of the sensor is a cantilever beam with equal thickness and strength. It mainly consists of temperature-strain sensitization zone of bimetal and load-bearing zone of stress-strain optical fiber. The second sensing element consists of two fiber Bragg gratings with different grating spacing distributed on a single fiber along the axial direction. The distance between these two gratings are predetermined. Because the initial grating spacing of the two fiber Bragg gratings is different, the corresponding demodulated wavelength varies and possesses a certain wavelength difference as well. Hence, the measurement of two different parameters can be realized. The first Bragg grating is fixed on the bimetal temperature sensing region and cannot measure pressure as it does not vary with external pressure. The theoretical derivation of optical fiber sensing proves that the distance between the two peaks (the wavelength difference between the two peaks) of the second Bragg grating reflectance spectrum is only proportional to the pressure and independent of temperature variation. From this principle, the pressure is measured. The simulation results reveal that the proposed structure can realize two-parameter measurement of pressure and temperature. The fiber Bragg grating detection device has the advantages of low cost, stable and reliable operation.
In order to complete the high-speed wavelength demodulation of output signal of Fiber Bragg Grating (FBG) sensing unit, an edge filter wavelength demodulation system is established in this paper. This wavelength demodulation system uses a reference FBG as an edge filter. First, the mathematical model of the system is built based on demodulation principle. In the model, the spectrum of FBG is simplified to Gaussian distribution. The model describes the relationship between the output voltage and input wavelength differential. According to the research above, the hardware and software of this demodulation system are developed. Besides, a calibration method of the system is proposed. Finally, experiments are carried out. According to the experiment results, the sensitivity of the wavelength demodulation system is 6.3mV/pm. When the demodulation frequency is up to 5kHz, the wavelength resolution is 0.23pm. This system has many advantages, such as simple structure, low cost and high resolution in high speed wavelength demodulation
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.