A Support Vector Selection Method For Fast Fault Diagnosis Of Home Service Robot

With the rapid development of society and technology, home service robot is becoming cheaper and smarter. Facing with the difficulties of aging and shortage of labor, we can use home service robot (HSR) as a good companion and servant. However, the security and reliability problems have become bottlenecks in this field. It is meaningful to do researches on fault diagnosis of HSR. Due to its excellent performance in small sample learning, Support Vector Machine (SVM) is a powerful tool for many pattern recognition applications which include fault diagnosis. However, SVM suffers a lot from the high complexity of training time and memory space. This paper proposes a novel support vector selection (SVS) method which can accelerate the training speed of SVM. Experimental results using artificial data and fault samples of HSR are given to validate the effectiveness of the proposed method.