MAY-JUN 2017

Issue link:

Contents of this Issue


Page 16 of 53

INTECH MAY/JUNE 2017 17 PROCESS AUTOMATION do not produce results. The solution is to find new approaches to using this data that fit within the pragmatic constraints of most industrial and manufacturing settings. Approaches that: l can be deployed quickly, with very limited upfront investment l do not require any significant new infrastructure l are usable by the existing business or opera- tions team l deliver results quickly Current approaches and their limitations Control systems Control systems are the starting point and cen- ter of attention when it comes to process data. Advanced process control approaches, and more specifically multivariate model predictive control approaches, are viable ways to take ad vantage of expanded process data availability to improve process performance. These tech- niques require process-specific control system expertise and significant upfront and continu- ing investments. They are only feasible where they can be applied to specific problems with substantial and predictable payoff. Ad hoc monitoring capabilities Outside of the process control systems, a variety of ad hoc approaches are employed to use process data for operational benefit. These approaches center around a process historian or other data store and include: l dashboards l rules and thresholds l formulas and theory-based models These ad hoc approaches are essential and support many key operational needs, but they are also severely limited in their ability to scale with growing data volumes. Operational dash- boards rely on people to interpret them. The more data presented, the more difficult the in - terpretations. Writing effective rules and thresh- olds requires expert understanding of the sys- tem, and their applicability is often brittle with respect to the system state. Incremental addi- tion of thresholds and alerts can quickly lead to alarm fatigue. Similarly, creating formulas and theory-based models requires domain expertise in addition to controlled, well-understood envi- ronments and systems. Forensic analyses and process optimization In many situations, retained process data is used primarily in historical analyses. For exam - ple, a root-cause analysis is undertaken after an unexpected downtime event or drop in prod - uct quality. Periodic process improvement projects examine his- torical data to bench- mark key performance indicators and to iden - tify systemic issues and opportunities for change. This type of data analysis is essen - tial, but it is also exper- tise and time intensive, and limited in its scope of applicability. Be - cause of the time and human capital required, these types of analyses can only be employed when the benefits are clear, and even then only infrequently. I n addition, backward-looking analyses cannot identify arising problems. Big data projects Industrial and manufacturing operations are the ultimate producers of big data volumes, far exceeding the e-commerce and search domains that put big data on the map. Machine learning and other technologies associated with big data are clearly applicable to process data analysis, but the "big project" approach used in other ap- plication areas has not worked well for industri- al and manufacturing operations applications. A typical project takes several months to complete and requires machine-learning experts, frequent interactions with subject-matter experts, and custom software development. In most cases, periodic follow-up projects are required to keep the models up to date with evolving process and equip- ment conditions. Successful big data application examples like speech recognition, fraud detection, or recom- mendation engines generally provide large, en during paybacks from vast troves of data that justify the initial investments. Industrial and manufacturing operations applications are ex tremely numerous, but are much smaller and more context-specific in their applicability. Big data projects have achieved very limited success in industrial and manufacturing operations, and many organizations have learned to distrust the approach altogether. Pragmatic pattern recognition and classification If current approaches fail to provide a scalable path, what are the viable alternatives? One op- tion that is gaining traction is using prepack- aged machine-learning (ML) technologies that extend existing data storage infrastructure, like process historians. By narrowing the capability FAST FORWARD l Using process data is a fundamental means of improving operations. l Industrial and manufacturing operations data analysis is a different type of "big data" challenge than those faced in e-commerce, social media, search, or other domains. l Consider using machine learning, along with your subject-matter experts, as a more pragmatic way of achieving real-time process control optimization.

Articles in this issue

Archives of this issue

view archives of InTech - MAY-JUN 2017