Chang-Cheng Lo

About

Chang-Cheng Lo is a researcher whose work sits at the intersection of mechanical engineering and deep learning, with a primary focus on intelligent fault diagnosis and prognostics for rotating machinery. His most notable contribution is the development of a one-dimensional convolutional neural network (1-D CNN) that uses a hybrid loss function—combining classification and clustering losses—to predict the remaining useful life of bearings and gears. This approach, detailed in his 2020 paper "Prognosis of Bearing and Gear Wears Using Convolutional Neural Network with Hybrid Loss Function," has garnered 29 citations, reflecting its practical value in condition-based maintenance. By training the network directly on raw vibration signals from both normal and faulty components, Lo’s method eliminates the need for manual feature extraction, making it both efficient and robust. His work is particularly impactful for industries reliant on heavy machinery, where early wear detection can prevent catastrophic failures. Lo’s research bridges the gap between traditional signal processing and modern AI, offering a scalable solution for real-time monitoring systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Prognosis of Bearing and Gear Wears Using Convolutional Neural Network with Hybrid Loss Function

   29 citations · 2020

Key Collaborators

Contact & Links