JULY 20229MANUFACTURING TECHNOLOGY INSIGHTSprocess. Will a produced part meet certain quality thresholds? What quality class will be assigned to it? The machine with the ML algorithm would be able to make that decision and accept or reject parts on its own.Suppose the goal is to define if a formula will produce a product with certain performance characteristics like strength or elasticity. Then this is a regression problem. In regression, the output may be a gradient value of characteristics such as compressive force for concrete or elasticity for polymers. When prior data is given to a regression algorithm, a model is created to lead to those predictions. Whether it is as simple as two independent variables or as complex as 50+, the algorithm will find relationships the human mind would spend years to derive if it otherwise couldn't.Consider our case at Clark Pacific. Concrete mix design is derived from empirical data and standards set by the Precast/Prestressed Concrete Institute (PCI). The mix design is sensitive to the material makeup as well as environmental conditions which leads to great variance in the overall performance. Generating a new mix design and testing it for a compressive strength takes months to confirm or reject. We used a regression formula based on the data we already had from batch tickets to develop the model for predictions. With a 99.7% success rate, what took months now takes minutes to derive the formula and days to confirm it. ML algorithms also removes the need to have subject matter experts to make decisions and generate results. We didn't begin with a large-scale instrumentation setup to measure every possible thing, we worked with the technology and data we already had to get to this point. Our biggest hurdle was ensuring that the measured and compiled data was consistent.Looking at these concepts and wondering how it all ties into specific applications can be daunting and can potentially deter or delay the process in the first place. Lao Tzu once famously said, "A journey of a thousand miles begins with a single step." Difficult though the path may be, accomplishing MI will only be attainable if the smaller steps are taken first. We didn't all wake up one day knowing how to do math, read or run a manufacturing line. In human intelligence, we started with the basics and built up into complex lessons. In MI, start small, build a solid foundation and grow from there. We didn't all wake up one day knowing how to do math, read or run a manufacturing line. In human intelligence, we started with the basics and built up into complex lessons
< Page 8 | Page 10 >