(187e) Next-Generation Process Monitoring for Iot-Enabled Smart Manufacturing

Authors: 
He, Q. P., Auburn University
Wang, J., Auburn University
Manufacturing process operation databases are massive because of the use of process operation and control computers and information systems. With ever-accelerating advancement of information, communication, sensing and characterization technologies, such as industrial Internet of Things (IoT) and high-throughput instruments, it is expected that the data generated from manufacturing will grow exponentially, generating so called ‘big data’. 4 V’s are often used to characterize the essence of big data: Volume (from terabytes (~1012) to zettabytes (~1021)), Variety (from structured to unstructured), Velocity (from batch to online streaming), and Veracity (from well calibrated and cleansed data to less trustworthy and uncleansed data). Big Data is arguably a major focus for the next round of the transformation of advanced manufacturing. One of the focuses of smart manufacturing is to create manufacturing intelligence from real-time data to support accurate and timely decision-making. Big data analytics such as statistical process monitoring (SPM) is expected to contribute significantly to the advancement of smart manufacturing.

In this work, we first present a roadmap of statistical process monitoring, which divides the development of statistical process monitoring into three generations: 1st generation: statistical process control (SPC); 2nd generation: multivariate statistical process monitoring (MSPM); and 3rd generation: yet to be properly defined and named. For the first two generation of process monitoring methods, their development history was briefly reviewed, significant contribution to manufacturing discussed, and major limited identified. For the next-generation, i.e., 3rd generation, process monitoring methods, their desired capabilities are discussed, and recent developments in the area are summarized.

Next, some major challenges that process monitoring could face in addressing the 4 V’s of Big Data, i.e., volume, variety, velocity and veracity, are discussed. In our opinion, to effectively address the 4V-challenges associated with Big Data, drastically different approaches are needed. Specifically, we expect that process feature based monitoring, instead of process variable based monitoring, may offer an effective way to address these challenges, and could play a significant role in the enhancement of process monitoring for smart manufacturing.

Finally, some of the future opportunities and application areas brought by IoT-enabled smart manufacturing are discussed, which include feature identification and extraction, self-adaptive modeling, preventive maintenance and sensor fault self-correction.

Checkout

This paper has an Extended Abstract file available; you must purchase the conference proceedings to access it.

Checkout

Do you already own this?

Pricing


Individuals

AIChE Members $150.00
AIChE Graduate Student Members Free
AIChE Undergraduate Student Members Free
Non-Members $225.00