Advanced Analytics in Automotive Manufacturing
Published on : Monday 30-11--0001
Today, manufacturing generates and accounts for a full third of all data involved in business and industry, and, as companies move to the Digital Enterprise, this is only going to increase significantly in the future. The role of data in manufacturing has been typically understated, if not misinterpreted or underutilised. That is rapidly changing, as data, and the actionable information derived from it, forms the backbone of the Digital Enterprise which will be the centrepiece for advanced manufacturing of the 21st century. The focus of this report is on automotive manufacturing.
What to do with this vast amount of manufacturing data in the automotive sector, including both historical data saved in repositories, and data generated by current production systems, machines, and equipment is the challenge facing manufacturers as factories move into the era of the digital enterprise and advanced manufacturing. Predictive and prescriptive analytics and Big Data technologies will be the key enablers to leverage this “new” data.
IIoT networks will connect real-time data and production events taking place on the factory floor to enterprise systems and decision makers that must rely on actionable information. While this is certainly not a new concept, IIoT will provide production line information based on an emerging generation of intelligent sensors, machines and systems. While IIoT provides the connectivity and intelligence, analytics will spawn the next generation of continuous process improvement (CPI) that will function more accurately and correctly by using manufacturing-based Big Data and applying advanced analytics.
These analytics enabled production systems will allow a re-purposing of event-driven manufacturing, where bottom-up collaborative production systems use operational intelligence, visibility, demand-pull, and a synchronised supply chain to drive the manufacturing process based on an intelligent event-oriented environment. The primary differentiator is that today IIoT and advanced analytics provide a pervasively connected and intelligent system of systems combined with analytics engines that can turn the unstructured data of manufacturing into actionable information and actually implement the concepts of event-driven manufacturing.
Advanced Manufacturing Needs Advanced Analytics
As we examine the areas of performance analytics, operational intelligence, and closed-loop PLM it is clear that each discipline supports the basic concepts of continuous process improvement and validating the as-built to as-designed. Furthermore, the anticipated progression of advanced analytics is going beyond predictive to prescriptive analytics, where we bring together Big Data, statistical sciences, rules-based logic, and machine learning to empirically discover and reveal the origins of the complex problems, and then determine decision-based options to resolve them.
Analytics for the Factory and Product Development
We have been discussing for some time now how manufacturing and production systems in the automotive sector will undergo significant changes with the emergence of IIoT technologies, smart and connected factories and supply chains. There has been a steady progression from simply monitoring machines and production lines to optimising production processes using predictive and prescriptive analytics, and eventually even the autonomous lights out factories of the future. While this is indeed the progression that appears to be taking place, there are two distinct sets of predictive analytics solution sets emerging: one for product development and one for factory operations.
Let us focus initially on the factory and how analytics is being applied in the manufacturing of products and production operations. Again, this is a case of leading PLM solutions providers offering advanced analytics solutions applied to the manufacturing processes and to operational optimisation. The common objective is to use predictive and prescriptive analytics to improve the overall performance of production operations. Additionally, these analytics solutions all use various forms of machine learning algorithms and other statistical and rules-based methods to examine and identify patterns in the production process. The goal is to apply an operational intelligence approach to achieve a closed-loop mechanism that first validates the as-built to the as-designed, and second looks for ways to improve both the product and the manufacturing process.
There is a growing consensus among those in the manufacturing community that one of the largest sources of Big Data is contained in the vast repository of production records. This would include completed operational and executed work records, quality assurance records, work flow histories, operational deviations and variations, engineering changes, machine and tooling metrics, material data, and many other records related to the production process. Most of this data has been maintained and archived due to the situation where certain industries, such as automotive have mandated regulatory requirements. Today's operational analytics applications for manufacturing are able to glean through this production process Big Data and using both predictive and more importantly, prescriptive analytics engines that use machine learning, multi-variant statistics, and rules-based logic to empirically reveal the origins of the most complex problems and suggest decision options to solve them.
So now let's move to the product development side of the coin and predictive analytics. In the case of product design it is more about product test simulation tools, multi-discipline systems engineering methods, and an emerging branch of product development called predictive engineering analytics (PEA).
One of the most sought after but elusive goals of product design engineering is to validate that you have achieved all the design criteria in the as-built product. That is, closing the loop between the as-built to the as-designed, and validating that the physical product will meet all design criteria before the product is manufactured. This is where the concept of the digital twin is now being applied to product design criteria.
The digital twin is where the physical and virtual worlds of the product including its engineering design and operational functions are connected and merged to enable everything from design improvements, continuous process improvements in manufacturing, conditional states of the machine/system, to operations and maintenance. An important aspect of the digital twin concept is that products can be designed with the intent of being smart and connected while providing operational data for predictive analytics. This is particularly useful as it helps contain costs and expensive recalls in the automotive industry.
Advanced analytics is becoming a permanent and critical element of today’s manufacturing processes, product design, and maintenance and service of equipment and products in the field. As companies re-examine methods and approaches to improving product design and process improvement of production systems, analytics will become a requirement for process improvement applied across the entire design/simulate/build/maintain lifecycle. Next generation analytics applications based on machine learning will allow manufacturers to use operational intelligence solutions based on analysis of the Big Data found in manufacturing. Companies will be able to detect and determine best practices for their manufacturing process based on examination and analysis of the vast repository of manufacturing data. Advanced analytics will serve as one of the necessary technologies that will enable advanced manufacturing and the factories of the future.