Centrifugal Pump Fault Detection with Convolutional Neural Network Transfer Learning

The centrifugal pump is the workhorse of many industrial and domestic applications, such as water supply, wastewater treatment and heating. While modern pumps are reliable, their unexpected failures may jeopardise safety or lead to significant financial losses. Consequently, there is a strong demand for early fault diagnosis, detection and predictive monitoring systems. Most prior work on machine-learning based centrifugal pump fault detection is based on either synthetic data, simulation or data from test rigs in controlled laboratory conditions. In this research paper, we attempt to detect centrifugal pump faults using data collected from real operational pumps deployed in various places in collaboration with a specialist pump engineering company. The detection is done by binary classifying visual features of DQ/Concordia patterns with residual networks. Besides using a real dataset, the paper employs transfer learning from image detection domain to systematically solve a real-life problem in engineering domain. By feeding DQ image data to popular and high-performance residual network (e.g ResNet-34), the proposed approach achieved up to 85.51% of classification accuracy.