Mason of Schneider Electric

Failure Mode and Effects Analysis (FMEA) has long been a foundational method in reliability engineering for identifying potential failures, assessing their impacts, and guiding risk mitigation. Over decades, engineers have developed extensive expertise, structured processes, and valuable knowledge bases through FMEA studies. As engineering systems become increasingly complex and data-rich, there is a growing opportunity to augment these established practices with modern artificial intelligence techniques to extract deeper insights and enable more scalable reliability analysis.

This presentation explores a knowledge-graph–based framework that extends traditional FMEA into a knowledge reasoning system. In this approach, system components, failure modes, causal relationships, operational conditions, and observed events are represented as interconnected entities within a knowledge graph. This structure allows diverse sources of information – including expert knowledge, historical maintenance records, field observations, design documentation, and operational data – to be integrated into a unified and machine-interpretable representation.

Once structured in this form, AI-driven reasoning methods can operate on the graph to support reliability analysis. Intelligent agents can traverse hierarchical system models – from components to subsystems and full systems – to infer potential failure propagation pathways, identify hidden dependencies, and highlight emerging risks. By reasoning across multiple levels of abstraction, the framework enables engineers to analyze reliability both locally and system-wide.

The knowledge graph also supports continuous knowledge enrichment. As new operational insights, inspection results, or expert assessments become available, they can be incorporated into the graph, allowing the reliability model to evolve over time and accumulate organizational knowledge.

By combining established FMEA practices with knowledge graphs and AI reasoning, this approach aims to enhance the depth, speed, and adaptability of reliability analysis. The presentation will discuss the conceptual architecture of the framework and demonstrate how integrating AI with traditional reliability engineering knowledge can support more informed decision-making throughout the lifecycle of complex industrial systems.

Biography:

Mason Pishahang is a multidisciplinary engineer whose work focuses on the development of tools and analytical frameworks aimed at improving the safety and reliability of complex engineering systems through the application of artificial intelligence and data-driven methodologies. He holds Master of Science degrees in Mining Engineering and Mechanical Engineering, and subsequently earned both his M.S. and Ph.D. degrees in Civil Engineering from the University of California, Los Angeles (UCLA). During his doctoral studies, he conducted research at the Center for Reliability Science and Engineering within the UCLA Garrick Institute for Risk Sciences, where his work focused on a range of risk and reliability challenges, including wildfire risk management and risk modeling of natural gas pipeline systems. Over the past several years, Mason has worked extensively on prognostics and health management (PHM) across multiple industrial sectors. His work emphasizes the application of data science and artificial intelligence to improve failure prediction, reliability assessment, and maintenance decision-making in complex industrial environments. Mason is also the developer of DataBruin, a suite of visual software tools designed to enable reliability engineers to perform data preprocessing and artificial intelligence–based modeling through an intuitive interface that requires no programming. The platform is intended to facilitate broader adoption of advanced analytics among engineering teams working with operational and reliability data. He currently serves as the Design for Safety and Reliability (DfSR) Regional Lead for North America at Schneider Electric, where he collaborates with engineering teams to ensure that products and systems are designed to meet rigorous standards of safety and reliability.