Beyond Spare Parts: 3D Printing And Machine Learning

Stefan Krauss

The concept of 3D printing isn’t a new one. In fact, it’s been around for more than 30 years – long before it became popular in consumer settings. In industries like automotive and aerospace, we call it additive manufacturing – the process of creating something new by layering materials, like plastic, metal, or concrete, using computer-modeled designs.

This approach is extremely versatile, allowing manufacturing teams to visualize large design projects through miniature scale models, design and create small runs of custom parts and equipment for customers, and prototype new products. As 3D printing speeds increase, Gartner predicts the 3D printing industry will be a $4.6 billion market by 2019.

Until now, the primary application for 3D printing in discrete industries has been prototyping new parts and equipment. But there’s significant room for expansion, especially in the efficient fabrication of spare parts.

Most discrete manufacturers are already producing spare parts, but few have adopted tactical 3D printing as an update to their process. The lead time currently required to create many spare parts can be both long and expensive, so the only way to ensure these parts are available to the customer in a timely fashion is to create and store them in advance. This process is inefficient and cost-prohibitive for the manufacturer – resulting in higher costs and longer wait times for customers. 3D printing provides a turnkey solution to this problem, and gives manufacturers the opportunity to supply their customers with high-quality parts, on-demand, when they are needed most.

Even more exciting, with innovations in other emerging technologies concurrently maturing, 3D printing is just the start of what manufacturers can do to enhance their production process for spare parts. While 3D printing certainly expedites creation, storage and delivery, it’s still a reactionary operation at its core. Instead of relying on customers to tell them when to print these parts, discrete manufacturers must transform their operations to think proactively – leveraging machine learning (ML) to solve maintenance issues before they occur.

As 3D printing capabilities grow, maintenance teams face a variety of challenges, including the number of parts that can be printed and increasing demand from customers for faster delivery. Regardless of these challenges, their goals remain the same: to ensure that parts are available and shipped to a customer in a timely fashion. As such, it’s critical that manufacturers evolve to meet this demand by incorporating machine learning into their process.

Machine learning technology identifies, analyzes, and monitors nearly infinite amounts of data, allowing it to provide a real-time status of processes and machinery. When implemented in a discrete manufacturing setting, teams can use ML to analyze the life remaining on a specific part or piece of equipment, and flag system failures before they happen. Similarly, when synchronized with a predetermined replacement schedule, ML can help proactively identify when it’s time for a customer to replace their parts – thereby avoiding unplanned downtime for machinery that would otherwise need to be taken out of service.

Manufacturers could combine this predictive maintenance with their ability to 3D print spare parts efficiently to become full-service vendors for their customers. Those who do so will not only serve as true leaders in spare parts manufacturing, but also in customer service.

With technology disrupting nearly every type of enterprise business model, customers are demanding more, and have higher expectations than ever before. They expect materials on time and on-hand when they need them, and they expect their suppliers to adjust accordingly. Discrete manufacturers producing spare parts must meet this demand by incorporating 3D printing, in conjunction with ML, to help quickly deliver high-quality spare parts to customers ahead of demand.

Manufacturers who can take advantage of ML to predict when equipment and parts will fail, then subsequently employ 3D printing to proactively print and ship replacement parts ahead of these failures, will enjoy significantly reduced spare parts costs and delivery times, and higher customer satisfaction.

Learn how to innovate at scale by incorporating individual innovations back to the core business to drive tangible business value by reading “Accelerating Digital Transformation in Industrial Machinery and Components.”

 


Stefan Krauss

About Stefan Krauss

Stefan Krauss is the general manager for Discrete Industries at SAP. Together with his team, he is responsible for the integrated management of the industries Aerospace & Defense, Automotive, High Tech and Industrial Machinery & Components – spanning development, solution management, sales and marketing, value engineering, partner management, services and support. The mission of this unit is to deliver industry cloud solutions that help SAP customers sustainably innovate and grow their business, operate safely, and develop their people.