RESUMEN
In general, sanding robots that move as if drawing a line along a surface are mainly used when sanding objects with a large area; however, they require a long working time, and it is difficult to secure a uniform sanded area. This study focuses on large-area sanding robots, such as those for ships, storage tanks, and tank lorries, and proposes an adaptive belt tension robot equipped with a 4-point supported belt mechanism capable of sanding variable curved surfaces. In addition, a sanding normal force prediction formula is proposed to describe the sanding performance of the contact surface. This equation consists of the concentrated load function due to the belt movement and the normal force due to the vertical and horizontal elongation of the belt. A video image analysis was performed to calculate the sanding area. Therefore, we determined whether the area was uniformly sanded. The dimensions of the test bench (W × D × H) were 1700 mm × 1450 mm × 900 mm. Experiments were performed using the proposed techniques on convex specimens with radii of 725, 1000, and 2100 mm. The sanding performance was improved by 43 % compared with that of a general belt-sanding robot.
RESUMEN
Balanced posture without dizziness is achieved via harmonious coordination of visual, vestibular, and somatosensory systems. Specific frequency bands of center of pressure (COP) signals during quiet standing are closely related to the sensory inputs of the sensorimotor system. In this study, we proposed a deep learning-based novel protocol using the COP signal frequencies to estimate the equilibrium score (ES), a sensory system contribution. Sensory organization test was performed with normal controls (n=125), patients with Meniere's disease (n=72) and vestibular neuritis (n=105). The COP signals preprocessed via filtering, detrending and augmenting during quiet standing were converted to frequency domains utilizing Short-time Fourier Transform. Four different types of CNN backbone including GoogleNet, ResNet-18, SqueezeNet, and VGG16 were trained and tested using the frequency transformed data of COP and the ES under conditions #2 to #6. Additionally, the 100 original output classes (1 to 100 ESs) were encoded into 50, 20, 10 and 5 sub-classes to improve the performance of the prediction model. Absolute difference between the measured and predicted ES was about 1.7 (ResNet-18 with encoding of 20 sub-classes). The average error of each sensory analysis calculated using the measured ES and predicted ES was approximately 1.0%. The results suggest that the sensory system contribution of patients with dizziness can be quantitatively assessed using only the COP signal from a single test of standing posture. This study has potential to reduce balance testing time (spent on six conditions with three trials each in sensory organization test) and the size of computerized dynamic posturography (movable visual surround and force plate), and helps achieve the widespread application of the balance assessment.
