Smart manufacturing requires quick decision making. This means product and process performance needs to be monitored and provide enough data for trend, root cause analysis and prediction. Many times this data resides in disparate locations (i.e. databases, machines, etc.) and behind proprietary interfaces, making data integration a daunting task. This requires users to go to individual machines to pull data and extra effort to establish a meaningful data integration and actionable information from it. Moreover, if the data requires assimilation with other production data or even transactional or supply chain data, engineers often have to run queries that need to be associated and merged before it can be analyzed. This is a task that makes data analysis costly and slow, while making effective real-time process control nearly impossible and expensive.
In our vision of smart manufacturing framework, we leverage the best technology blends to achieve Digital Transformation on the plant-floor processes and data. We envision this transformation as a leap step into an ecosystem of tools and information. In this work, we present initial steps in the direction of automated data acquisition, data harmonization, storage and processing capacity that will use the best of the edge and cloud computing environments to first solve smart manufacturing vision on a legacy electronic assembly manufacturing system. Our endeavor is to combine these initial two-level computing settings to create actionable analytics and visualization around electronic assembly processes by measuring machine performance in real time. This solution will allow the machine operators and production engineers to identify potential outliers in the production processes as they emerge and to unveil product quality tendencies that can be resolved faster and with anticipation.
Looking into the future, machine learning and other artificial intelligence tools will help us identify out of controls, trends and new correlations. This will reduce downtime and defects that will drive operations productivity.