This paper deals with the problem of fault detection and diagnosis of induction motor based on motor current signature analysis. Principal component analysis is used to reduce the three-phase current space to a 2-D space. Kernel density estimation (KDE) is adopted to evaluate the probability density functions of each healthy and faulty motor, which can be used as features in order to identify each fault. Kullback-Leibler divergence is used as an index to identify the dissimilarity between two probability distributions, and it allows automatic fault identification. The aim is also to improve computational performance in order to apply online a monitoring system. KDE is improved by fast Gaussian transform and a points reduction procedure. Since these techniques achieve a remarkable computational cost reduction with respect to the standard KDE, the algorithm can be used online. Experiments are carried out using two alternate current motors: an asynchronous induction machine and a single-phase motor. The faults considered to test the developed algorithm are cracked rotor, out-of-tolerance geometry rotor, and backlash. Tests are carried out at different load and voltage levels to show the proposed method performance.
The adoption of motor-rehabilitative therapies is highly demanded in a society where the average age of the population is constantly increasing. A recent trend to contain costs while providing high quality of healthcare services is to foster the adoption of self-care procedures, performed primarily in patients’ environments rather than in hospitals or healthcare structures, especially in the case of intensive and chronic patients’ rehabilitation.
This work presents a platform to enhance limb functional recovery through telerehabilitation sessions. It relies on a sensing system based on inertial sensors and data fusion algorithms, a module to provide bio-feedback tailored to the users, and a module dedicated to the physicians’ practices. The system design had to face several cyber-physical challenges due to the tight interaction between patient and sensors. For instance, integrating the body kinematics into the sensory processing improved the precision of measurements, simplified the calibration procedure, and made it possible to generate bio-feedback signals. The precision of the proposed system is presented through a set of experiments, showing a resolution below one degree in monitoring joint angles. A validation of the proposed solution has been performed through a medical trial on 50 patients affected by osteo-articular diseases.
The presented framework has been designed to operate in other application fields, such as neurological rehabilitation (e.g., Parkinson, Stroke, etc.), sports training, and fitness activities.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.