Enhancing Maintenance Strategies for Manufacturing Operations

The National Institute of Standards and Technology (NIST) is engaged in multiple research efforts to advance the design, deployment, and assessment of maintenance-supporting capabilities (e.g., monitoring, diagnostics, and prognostics) to increase reliability of and decrease downtime in manufacturing systems. 

Manufacturing processes are becoming more complex, with increased integration of Industrial Internet of Things (IIoT) technologies, greater process reconfigurability to support product customization, and demands for higher precision. Technological evolution has also led to an increased awareness of manufacturing process performance and health through the generation and analysis of more targeted datasets. While greater complexity and reconfigurability have brought additional challenges to effectively maintaining processes and equipment, timely-actionable intelligence from emergent data sources can offer more insight into devising effective maintenance strategies. 

Data to support maintenance activities in manufacturing environments can be generated from multiple sources including human-generated datasets and those automatically produced by a process, piece of equipment, or external sensor. Maintenance Work Orders (MWOs) are one example of human-generated data. Maintenance personnel create and augment MWOs throughout the life of a piece of equipment to track health status, capture faults/failures, and document repairs/solutions. Robot-level data (e.g., joint-level and tool-center-position data) is an example of an equipment-generated dataset. This data is typically generated by a robot’s controller at a specific frequency where it can be analyzed to identify its performance, existing health state, and predicted future health state. 

Collectively, two projects are developing publicly-available products and resources to enhance maintenance strategies within manufacturing operations. The Monitoring, Diagnostics, and Prognostics for Manufacturing Operations project seeks to develop and deploy measurement science to promote the implementation, verification, and validation of advanced monitoring, diagnostic, and prognostic technologies to minimize unplanned downtime and optimize planned downtime in manufacturing operations. Complementing this effort, the Knowledge Extraction and Application project aims to develop and deploy advances in standards, measurement science, and software tools using actionable, computable, domain knowledge and data in operations and logistics to improve the reliability, quality, and efficiency of advanced manufacturing systems.