Industrial Robot Fault Detection Based on Statistical Control Chart

Abstract

Industrial robots have long been used in production systems in order to improve productivity, quality and safety in automated manufacturing processes. There are significant implications for operator safety in the event of a robot malfunction or failure and an unforeseen robot stoppage due to different reasons has the potential to cause an interruption in the entire production line, resulting in economic and production losses. In this research a fault detection system based on statistical control chart has been designed. An experimental investigation was accomplished using the PUMA 560 robot. Vibration signals are captured from the robot when it executes a repetitive task and then some statistical features are extracted from the signals, by utilising a developed data acquisition system based on National instruments hardware and software. The extracted vibration features, which are related to the robot healthy and faulty states, have subsequently been used for building and testing a statistical control chart. The chart has been validated using part of the measured data set, not used within the design stage, which represents the robot operating conditions. Validation results indicate the successful detection of faults at the early stages using the key extracted parameters.