In this episode of Reliability 4.0, we speak with Allen Garcia, mechanical engineer at Baker Hughes and PhD candidate at the University of Maryland, where his research centers on AI applications in engineering. Allen shares how he transitioned from traditional mechanical design to AI-powered reliability tools, offering a rare perspective from someone bridging deep technical experience with cutting-edge machine learning. He explains how large language models (LLMs) are helping engineers process work order data, generate knowledge graphs, and accelerate time-consuming tasks like FMEAs and RCAs.We also explore the future of AI-driven maintenance—from dynamic RCAs that update in real-time to domain-specific models built just for reliability and maintenance professionals. Allen weighs in on EasyRCA’s current AI features, the challenge of accuracy in industrial models, and the opportunity to build smarter tools without replacing human insight. Whether you’re an engineer curious about AI or a data scientist entering reliability, this is a grounded and insightful look at where the field is headed.
