Max Robotics — Global Service Robot Directory + US Certification

About

Hanlin Zeng is a researcher specializing in intelligent fault diagnosis, health assessment, and predictive maintenance for industrial robots. His work sits at the intersection of deep learning, signal processing, and industrial automation, with a particular focus on developing data-driven solutions to the complex challenges of robot condition monitoring. Zeng's most impactful contribution is his attention-enhanced multi-modal deep learning algorithm for compound fault diagnosis, which addresses the critical need to simultaneously identify multiple concurrent faults in robotic systems — a problem with direct implications for reducing industrial downtime and maintenance costs (36 citations). Complementing this, his HMM-TCN-based health assessment framework combines hidden Markov models with temporal convolutional networks to enable precise, automated state prediction for robot mechanical axes, replacing costly and inefficient manual inspection methods (33 citations). Further broadening his contributions, Zeng has pioneered metric learning approaches for whole-robot health indicator modeling and explored triplet network architectures to overcome the persistent challenge of limited training data in fault diagnosis scenarios. Collectively, his research advances the frontier of intelligent manufacturing by making industrial robots more reliable, self-aware, and easier to maintain — capabilities increasingly vital in modern Industry 4.0 environments.