The Internet of Things is revolutionizing all areas of our lives. Manufacturing Industry 4.0 is a revolution as transformative as the first industrial revolution that began nearly three hundred years ago. Over the past few years major manufacturers of industrial control products, as well as smaller software companies and start-ups, have been developing and introducing software and software tools to provide analytics and artificial intelligence to improve both manufacturing processes as well as products manufactured. Advancements in manufacturing analytics are coming fast and furious.
But not all manufacturing analytics are totally new. Many companies began to develop and use process analytics years ago. There were limitations in what these systems could do because they were limited by the computing power and communication systems available at the time. The advent of more powerful computers and the cloud have rapidly enhanced the capabilities now available. Using these analytic tools, it is possible to find process malfunctions before they occur, predict product response performance, summarize massive and complex data to an actionable data subset and as a result reduce the manufacture of off-specification product.
There are many industries that can benefit from these analysis tools. Manufacturers across chemical, agrochemicals, petrochemicals, and cosmetics all share similar manufacturing challenges. They are concerned about optimizing yield, energy consumption, product quality, and reduction of run to run variability across different process plants. Dealing with multiple plant operations can be challenging because of differences in systems, processes, business definitions, and equipment.
One such tool, Process Monitor, is a powerful shop floor tool used by Optimation Technology to identify and quantify process variability. This tool allows for order-based viewing and analysis to complement the more typical date/time schema. It focuses users on run to run consistency for any combination of products or equipment.
The Process Monitor toolset provides powerful calculating functions, statistical process control charts, user generated analysis scripts and modeling functions to visualize the process and to guide users investigating the root causes of variability, machine breakdowns, and waste. The analysis function allows users to capture key features of the order aligned time series (noise level, patterns, etc.) and convert them to order based control charts. Advanced users can go even further and use advanced data analytics including multivariate algorithms to view variability across all control charts and to correlate to product quality response variables.
Process Monitor utilizes the proof of concept approach. The goal of this approach is to configure and align process data to drive immediate performance improvements. Typically, a proof-of-concept is a 12-week project involving four (4) weeks of consulting to identify the key parameters, and 8 weeks to configure and deploy the solution. Optimation is actively engaged, as a systems integrator, using Process Monitor tools and techniques to effectively improve almost any manufacturing process. Collecting data from the Automation Control System (typically operating in a PLC), the Manufacturing Execution System (MES), Laboratory Information Systems (LIMS), and Data Historians provides enough information to carry out the necessary analytics.