A Two-Step Unsupervised Learning Approach to Diagnose Machine Fault Using Big Data


  • V. J. Sharmila Loyola-ICAM College of Engineering and Technology
  • D. Jemi Florinabel Dr. Sivanthi Aditanar College of Engineering




The modern industrial sector requires an intelligent fault diagnosis system to ensure reliable and safe processing
since traditional methods require expert diagnosis, which consumes time and requires labor. Furthermore, diagnostic
results are influenced by the expert’s expertise and in-depth knowledge of the machine. The objective of this paper is
to solve the manual intervention problem and improve the fault diagnosis. We propose a novel two-stage unsupervised
learning algorithm based on artificial intelligence (AI) that learns fault features efficiently from raw vibration signals.
To accomplish the aforementioned goal, we encapsulate the two-stage learning technique such as sparse filtering and
Rectified Linear Unit (ReLU) regression function. As a first step, we used a two-layer neural network sparse filtering
procedure to extract vibration signals’ features. Based on vibration signals, ReLU regression determines the health
condition of the machine in the second phase. ReLU is a linear function that improves the performance of neural network training. Here we utilized a sigmoid and softmax regression function to compare the performance of ReLU. The
sigmoid function works well for binary classification, whereas softmax works well for multiclass classification. A database of motor-bearing vibration signals containing signals about four different health conditions of machines, such
as Inner race faults (IF), Outer race faults (OF), and rolling faults (RF). The sparse filter is evaluated on different input
and output dimensions, which significantly increases the learning accuracy. We classified the health condition using
ReLU and achieved 93.8% accuracy, which is higher than sigmoid and softmax. Through the two-step learning process, machine fault diagnosis is enhanced, as well as big data is effectively handled.