Real-time Motion State Research Articles

Gait Recognition and Assistance Parameter Prediction Determination Based on Kinematic Information Measured by Inertial Measurement Units.

The gait recognition of exoskeletons includes motion recognition and gait phase recognition under various road conditions. The recognition of gait phase is a prerequisite for predicting exoskeleton assistance time. The estimation of real-time assistance time is crucial for the safety and accurate control of lower-limb exoskeletons. To solve the problem of predicting exoskeleton assistance time, this paper proposes a gait recognition model based on inertial measurement units that combines the real-time motion state recognition of support vector machines and phase recognition of long short-term memory networks. A recognition validation experiment was conducted on 30 subjects to determine the reliability of the gait recognition model. The results showed that the accuracy of motion state and gait phase were 99.98% and 98.26%, respectively. Based on the proposed SVM-LSTM gait model, exoskeleton assistance time was predicted. A test was conducted on 10 subjects, and the results showed that using assistive therapy based on exercise status and gait stage can significantly improve gait movement and reduce metabolic costs by an average of more than 10%.

Research on Trajectory Prediction Algorithm for Low-altitude Emergency Rescue Aircraft

With the rapid development of general aviation, this aviation solution is widely used in emergencies such as natural disasters, major accidents, and social security problems because of its fast start-up speed, high rescue efficiency, and less restrictions. In this paper, state-dependent mode transition hybrid estimation (SDTHE) is combined with the improved intent inference algorithm (IIIA) to obtain a more accurate trajectory prediction algorithm. The algorithm overcomes the shortcoming of the hypothesis that the likelihood function is zero in the interactive multiple model algorithm (IMM), and considers the real-time motion state and mode of the aircraft, so that the final prediction result is more accurate.

Comparison Study of Heart Rate Variability at Resting and Real-time Motional States

This study aims to discover the characteristics of heart rate variability of resting and real-time motional states in healthy population. The ECG data of 16 healthy young subjects during 5-minute resting and motion periods were recorded respectively. After that, the R wave was extracted through Hilbert transformation and the RR interval time series was computed. The calculations for HRV parameters in time and frequency domains, Poincaré scatter plots and the detrended fluctuation analysis were conducted. Our study finds that, the measures of real-time motion in time domain (Mean RR, SDNN and RMSSD), the measures in frequency domain (VLF, LF, HF, TP), and the measures of Poincaré scatter plots are significantly less than those of resting state (P <0.001). The measure of long-term fractal exponent (α2) in real-time motion state is significantly higher than resting state (P <0.05). Between the two states, there are no statistically significant differences in other parameters of frequency domain (LF norm, HF norm, LF/HF) and short-term fractal exponent (α1), P>0.05. This study suggests that, the results can provide new characteristic signatures and statistical evidence for sport medicine or rehabilitation medicine.

Intent pattern recognition of lower-limb motion based on mechanical sensors

Based on the regularity nature of lower-limb motion, an intent pattern recognition approach for above-knee prosthesis is proposed in this paper. To remedy the defects of recognizer based on electromyogram U+0028 EMG U+0029, we develop a pure mechanical sensor architecture for intent pattern recognition of lower-limb motion. The sensor system is composed of an accelerometer, a gyroscope mounted on the prosthetic socket, and two pressure sensors mounted under the sole. To compensate the delay in the control of prosthesis, the signals in the stance phase are used to predict the terrain and speed in the swing phase. Specifically, the intent pattern recognizer utilizes intraclass correlation coefficient U+0028 ICC U+0029 according to the Cartesian product of walking speed and terrain. Moreover, the sensor data are fused via Dempster-Shafer U+02BC s theory. And hidden Markov model U+0028 HMM U+0029 is used to recognize the realtime motion state with the reference of the prior step. The proposed method can infer the prosthesis user U+02BC s intent of walking on different terrain, which includes level ground, stair ascent, stair descent, up and down ramp. The experiments demonstrate that the intent pattern recognizer is capable of identifying five typical terrain-modes with the rate of 95.8%. The outcome of this investigation is expected to substantially improve the control performance of powered above-knee prosthesis.

The effect of axis coupling on machine tool dynamics determined by tool deviation

High acceleration forces of machine tool with kinetic coupling as the dominating coupling forces may deform the machine structure and result in the tool deviation. In this paper, a dynamic model of a three-axis gantry milling machine tool considering axis coupling effects is proposed to model the varying dynamic behavior and evaluate the Tool Center Point (TCP) position deviations. The effect of axis coupling force on the stiffness changes of kinematic joints is analyzed. The variations of the frequencies and frequency response functions with respect to position parameters are calculated. And the TCP deviation affected by axial coupling in real-time motion state is discussed in detail. The results show that it is able to obtain an excellent match between the simulations and the measurements. The simulation and experimental results show that: (1) the natural frequencies and the receptance are greatly changed when the TCP is moving along the X-axis or the Z-axis, where the maximum changing of natural frequencies is up to 10% and response magnitude up to 2 times; (2) the elastic deformation and vibration of machine tool are caused by the coupling forces in acceleration and braking, which detrimentally affect dynamic response of the TCP. Thus, the model proposed in this paper represents the important effects for comprehension of machine dynamic behavior and for further compensation in future.

An Unstructured Moving Grid Scheme for Shock Impacting on Material Interface

An unstructured moving grid scheme is applied to track the real-time motion state of the material interface with large-scale deformation induced by shock in the compressible multi-material flow. The material interface is denoted as a special internal boundary which is made up of unstructured grid edges, and on both sides of that there exist grids used for the two different materials. Riemann problem is solved in order to track the motion of the grid points on the material interface, and the local re-meshing technique is also applied to cope with the large-scale deformation of the moving grids near the interface, especially for the case of strong shocks existing in the multi-material flows. Simultaneously, the material interface is also defined as a kind of grid-deforming boundary in case grid volumes are negative. To obtain the resolution of the whole multi-material flow domain, the arbitrary Lagrangian-Eulerian (ALE) is discretized using Harten-Lax-van Leer-Contact (HLLC) scheme. Several numerical calculations from shock-interface examples demonstrate that this moving grid technique is feasible and effective in tracking the real-time motion state of the material interface.

Intelligent Car Movement Monitoring System Based on LabView

To resolve the problems that it’s difficult to observe the data of real-time motion state and controls parameters, and difficult to determine the running strategy, we come up with a system design based on virtual instruments and wireless data collection. This system can not only collect the intelligent car’s running speed, steering engine angle and wheelpath, but also draw the racing track, select and optimize the running strategy. This system has been proved that it can monitor the intelligent car accurately which shortens the debugging period greatly.

Using extension method for health analysis system of a fitness device

This paper used foot-operated fitness equipment, a power generation system and a biomedical measurement system to construct a fitness system for fitness exercise, energy storage and diagnosing the user’s movement conditions. The diagnostic mode is that the rotation speed and output power of pedal-dynamo are converted into the mileage and calorie consumption of the user’s pedaling movement. Second, the biomedical measurement module can diagnose the user’s movement health status timely according to the heartbeat signals and the consumed calories while the user is in exercise. The diagnostic data were integrated using touch tablet PC and LabVIEW software for the image controlled man-machine interface. The user can observe the real-time motion state through the virtual instrument interface. The built-in program can diagnose the health status, and count the total generation and movement process after exercise.