I agree We use cookies on this website to enhance your user experience. By clicking any link on this page you are giving your consent for us to set cookies. More info
Noemi Guerrer, Senior Manufacturing Engineer, Clark Pacific
Manufacturing Intelligence (MI) is waterman concept that is till new and in relative infancy. MI centers around the premise of utilizing software in conjunction with existing manufacturing operations to generate deep analytics that was built from the Industrial Internet of Things (IIoT) to drive production. Ultimately, MI is the idea of taking IIoT, digital twins, Clark Pacific Noemi Guerrer cloud management and technology, such as Virtual and Augmented Reality (VR/AR) and applying them to the manufacturing floor for improved data and function. These systems form the blueprint to becoming a plant with integrated MI. While simple as a general procedure, implementing MI is not easy and can be costly as it involves deep financial or time investments. The degree of difficulty will be determined by a plant’s digital maturity. Where to begin then? At the basis of MI is data. Begin by obtaining consistent data from a core product or process.
There is a great opportunity in data analytics through Machine Learning (ML) algorithms. These algorithms serve to find patterns in data that human intelligence could not reach or would require deep study. What should the acquired data look like? If the data is coming from a manufacturing facility, that data will often fall under supervised learning in ML which has two categories: Classification and Regression.
A classification problem would entail looking at a vast set of inputs that yield a class output.Take a flower for instance. Features such as size, shapes and colors could be noted to classify them as roses, daisies or lilies. Or, categories 0, 1 and 2 respectively. This could lead into a sorting process. 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.
There is a great opportunity in data analytics through machine learning algorithms
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 tolead 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 largescale 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. LaoTzuonce famously said, “A journey of a thousand miles begins with a single step.” Difficult though the path maybe, 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.