When I look back on the evolution of the manufacturing industry, I always think of Henry Ford’s infamous quote: “Any customer can have a car painted any color that he wants, so long as it is black.”
Though Ford’s remark may have been playful, it was rooted in truth. While the Model T originally came in several colors, Ford later offered only one: black. Why? Quick-drying black paint was the only type that allowed for a full-speed assembly line.
Fast-forward to the present day, and the traditional assembly line is long gone. The availability of sensor data is driving a new era of smart manufacturing–Industry 4.0, also known as the fourth industrial revolution–that enables manufacturers to increase efficiency, customization, and automate decision-making by providing real-time analytics.
Using Data in New Ways
Let’s face it: manufacturing is a lot more complicated than it was in Ford’s day. The processes by which data is collected have evolved to include sensors, machine learning, and the ubiquitous Internet of Things. But the goal of nearly every manufacturer remains the same: to increase efficiencies and decrease costs.
By collecting data from sensors across the production line–both horizontally and vertically, from corporate-level systems down to the shop floor–manufacturers can gain a clearer picture of where efficiencies are (and are not) happening. With this information in hand, they can respond to events in near real-time, reducing both waste and downtime.
Here’s how it works: When a set of control limits are violated, the sensor systems trigger event data that, in turn, is displayed on numerous dashboards. This sensor-derived data allows you to do things like predict machine failure, which in turn helps you increase machine efficiency and reduce down time. For larger manufacturers, preventing such failures often means avoiding hundreds of thousands of dollars in losses.
Revolutionizing the Decision Making Process
Most business users today, manufacturers included, make decisions based on the metrics and insights they glean from business intelligence (BI) dashboards. In the fourth industrial age, the decision process has become part of the work process; in other words, it has moved from the factory floor to the business layer.
Using sensors and predictive analysis, you can automate decisions based on the information coming in – with no user input needed. Decisions are made (and displayed) right on the production line in near real-time – providing huge efficiency gains!
Eliminating Human Error
Today’s manufactures want adaptive systems that are driven by data. If the data can be read, then the system can make a decision and learn from its outcomes. Essentially, it makes decisions based on predetermined rules and then adapts based on the outcome.
In addition to increasing efficiency, these adaptive systems can cut down on errors. We all know humans make mistakes. But if you give them the right information at the right time, you can reduce human error in the process. For instance, LCD screens on the production line would display steps or schematics for factory workers to follow, and these would automatically get updated based on the data coming in.
Making a Global Impact
Ultimately, Industry 4.0 isn’t about individual manufacturers gaining visibility into the unit production line process – it’s about everyone. If enough manufacturers leverage data, we can affect lean efficiency across the global supply chain.
Manufacturers can determine exactly what they need and when. In turn, suppliers can make parts to order versus to stock. And now we’ve reduced the risk of obsolescence and saved money that would traditionally be tied up in inventory.
In the early 1900s, Ford made huge strides in manufacturing, but he ultimately couldn’t change the production line to meet the individual needs of his customers. Today, customers expect customized products. Through data-driven smart manufacturing, we can provide both mass production and customization simultaneously–and we can give customers exactly what they want.
David Hall-Tipping is the solutions manager at Logi Analytics, where he develops solution demonstrations to showcase how organizations across a variety of industry sectors can solve their unique analytics challenges. He holds a master degree in neuropharmacology from King’s College London.