Online Fault Diagnosis of Industrial Robot Using IoRT and Hybrid Deep Learning Techniques: An Experimental Approach

Abstract

The Internet of Robotic Things (IoRT) is growing rapidly with new applications. Co-operatory robotics enables the sharing of information, autonomy, and fail-safe interaction with environment, humans, and other robots. They can also self-maintain, self-aware, and self-heal. To provide reliable and robust online monitoring of the industrial manipulator joint status, this article proposes a new IoRT architecture based on transfer learning (TL) techniques to detect manipulator fault. Robotic manipulator joint status are detected with high accuracy using a hybrid 1-D multichannel convolutional neural network (1D-MCNN), including matrix kernels and recurrent neural network (MCNN-RNN) technique. Moreover, a timestamp mapping method addresses the challenges associated with inconsistencies in sensor data timestamps. Existing data-driven methods struggle with the diverse operating conditions of industrial robots, where load and speed constantly fluctuate. To address this limitation, we propose a novel TL-based MCNN-RNN approach for joint fault diagnosis under varying work conditions. This method leverages the adaptability of TL while incorporating the inherent relations between different failure modes, enhancing the TL process. To demonstrate the performance of the suggested IoRT topology, various experimental scenarios are performed with data acquisition on six degree-of-freedom (DOF) UR16e (universal robot) manipulator. Based on the results, the proposed IoRT architecture can effectively visualize the joint fault status of the manipulator. As a result, TL architecture combined with MCNN-RNN provides an excellent accuracy of 99.03%in detecting faults on manipulator joints, which is significantly higher than traditional convolutional neural network (CNN), deep belief network (DBN), domain adversarial neural network (DANN), and conditional domain-adversarial network (CDAN).