Abstract
This study presents an approach for fault detection and classification in a DC drive system. The fault is detected by a classical Luenberger observer. After the fault detection, the fault classification is started. The fault classification, the main contribution of this paper, is based on a representation which combines the Subctrative Clustering algorithm with an adaptation of Particle Swarm Clustering.
Highlights
Fault detection and analysis is a very important strategy that is commonly employed in the industry with the purpose of allowing a cost-effective maintenance policy, keeping productivity standards and ensuring safety
A fault diagnosis procedure is divided into two tasks: i) fault detection, indicating the occurrence of some fault in a monitored system; and ii) fault classification, establishing the type and/or location of the fault
The literature presents several classes of strategies to deal with fault detection and isolation (FDI) [7]
Summary
Fault detection and analysis is a very important strategy that is commonly employed in the industry with the purpose of allowing a cost-effective maintenance policy, keeping productivity standards and ensuring safety. The idea of the second step, the main contribution of this paper, is to deal with the fault classification in a new way, using an adaptation of Particle Swarm Clustering. 1.1 Contributions In this paper is proposed an algorithm, adapted from cPSC ([27]) and denoted as New cPSC (NcPSC), which optimizes the hit rate and the total number of groups (classes) of a data set It is a supervised algorithm which combines the following functionalities:. The faults on sensors are: armature current sensor fault, field current sensor fault and machine speed sensor fault Considering these fault types (see Table 1), the complete model is described in (2.2). It is possible to see which variables are affected after the occurrence of faults
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have