Issue link: https://industrialengineer.epubxp.com/i/826827
46 ISE Magazine | www.iise.org/ISEmagazine Analytics for process design and improvement a timely summary of the analytic sources, statistical summaries and explanations and required inferences. There's always the risk that the team could see simulation modeling as nothing more than complex programming and code, so modeling ex- perts should constantly refer to and revise the process mapping to ensure a cohesive team effort. 7. Redefine and revise the operational intelligence simulation models to ensure long-term relevance and success. The design efforts of this team are based on the best data and collective knowledge members can collect. Plan and expect timely gates of significant team decisions. However, details and revisions should be refined and revised throughout the assignment. The ongoing predicted operational costs can begin with an optimal solution that can be improved as ad- ditional analytics and models are recycled and adapted by new analytics. 8. Develop and document the long-term roles, re- sponsibilities and measures of analytics success. Orga- nizations should use analytics and simulation modeling in a selective manner. This tool can be improved for future use in terms of proper assignment selection, individual capabili- ties and passions, consistent statistical and simulation models and processes, standard operating procedures and defined team expectations. Carefully measuring lessons learned and refining this process will ensure the organization's modeling success. In addition, an organization's experience with these design as- sessment tools will determine appropriate timing and mile- stone expectations during future assignments. Actionable operational intelligence modeling success Recent successes in the appropriate use of analytics and opera- tional intelligence included stories about an automotive com- ponent manufacturer, a maker of electric motors and pumps, and a car company. Success story 1: The first automotive component manu- facturer used current asset performance analytics to model, predict and prevent nonplanned lost time in production. The company was servicing all of the major U.S. automotive com- panies with customer-specific versions and options of its prod- ucts. The asset investment was the major production cost, and the production philosophy to maximize return demanded a 24/7 production operation and schedule. The production re- quirements did not require JIT (just-in-time) delivery but cer- tainly were limited by reasonable working capital quantities, containers and space. Therefore, frequent changeovers, typi- cally one per shift, on each of the production lines provided an opportunity for process variation. In addition, processing parameters were often product-specific, conditional to the current environment and dependent upon technical decisions made by varied personnel. Process control charts were in place based on timely opera- tor interactions and internal MES (manufacturing execution system) designs. The overall OEE performance was 60 percent to 70 percent for each line over a typical month. A major is- sue is that the process controls were based on the best his- torical knowledge of the asset and program designers. These people are extremely knowledgeable and could be considered industry experts. However, there were nearly 100 processing parameters realistically associated with any instant of produc- tion for just one line. Monitoring these parameters across the product and conditional mixes required assumptions of ex- pected tolerances and allowed technical personnel on site the autonomy to make decisions. The contemporary ability to collect extremely granular, high performance time-series data gives management the statistical ability to drive significant im- provement. A pilot team was established. Team members followed a sys- tematic approach, using a wide range of predictive analytics to identify what process parameters correlated to OEE losses. The immediate outcomes were driven by team-directed statis- tical simulation models of process variations, unexpected cor- relations, tolerance adjustments and other analytical tools that provided significant knowledge to the technical and manage- rial leadership. Specific process controls that limited operator interactions, new and adjusted MES controls of processing pa- rameters and streaming feedback of processing performance has driven the OEE performance on this line to nearly 85 percent. This represented nearly a 40 percent improvement over the past year. In addition, process performance moving forward will offer a sustainable improvement opportunity as process and product parameters change. This program has been es- tablished across all of the parallel lines within this facility with similar improvement results. Success story 2: The second success story involves stra- tegic planning for a new factory design. One of the world's leading suppliers of mission-critical electric motors and pumps for the oil, gas, nuclear, industrial and chemical markets relied on predictive simulation and analytics to plan an ambitious growth strategy and successfully communicate this vision of change to employees, customers and investors. To capitalize on opportunities across a number of its growing markets, the company recognized that it needed to undertake a business transformation project that focused on maximizing efficiency, aligning capacity to demand and boosting profitability. Having already achieved substantial growth (from $22 mil- lion in 2011 to $32 million by 2015), the next stage was devel- oping a plan that would double its main manufacturing facility in size to increase the number of units it could produce. In the past, the organization used Excel to perform opera- tional analysis and macro-level strategic planning. Given the importance and scale of the change required to meet acceler- ating demand, the executive management team decided that