Manufacturing Engineering Magazine – April 2018
By Carlos Mélendez
The next cycle of technology disruption is upon us. Artificial Intelligence (AI) is taking hold in every industry and manufacturing is no exception. AI enables companies—from medical device and electronics manufacturers to pharmaceutical firms—to leverage their Big Data and IoT investments to see new patterns and insights and to perform tasks more efficiently and quickly than ever before. AI algorithms will sit side by side with workers on key decisions by offering intelligent advisory.
When workers are free to focus on strategic tasks and let AI algorithms perform the mundane ones, innovation is fostered and efficiency and product quality improve. To understand how AI is being applied in manufacturing, it’s important to understand what preceded it.
In the 1910s, factory workers began working on the first assembly lines. Between the mid-1950s and the 1970s, industrial robots entered the plant with no real intelligence and limited operational capabilities. They performed one or two sets of repetitive tasks in highly controlled environments. In the 1980s, industrial robots began to be used in large numbers. All of this technology helped manufacturers operate more efficiently.
Today, AI-based software is enabling machinery to teach itself how to optimize performance, identify the best processes, and train itself to achieve a desired outcome—all while guaranteeing compliance to Six Sigma standards.
AI: Leveraging the Power of the Internet of Things
The growth of the Internet of Things (IoT), which is enabling data collected from sensors attached to manufactured products in the field to relay critical information back to the plant, is enabling a new level of data-driven AI insights. For example, a product may pass inspection in the plant, under climate-controlled conditions, yet when in use outdoors in cold weather, unanticipated problems may arise.
In Puerto Rico, Wovenware helped develop an AI solution for a medical device manufacturer. It takes sensory data collected from the manufacturing process and predicts when a production line device is unfixable and should be scrapped. Likewise, AI is being used in other plants to predict manufacturing failures before products are shipped. Manufacturing data from IoT sensors and manufacturing execution systems are being used to develop custom, deep-learning algorithms that can identify faulty products before they reach consumers. This can reduce liability, replacement and warranty costs, and, more importantly, save lives.
AI is also transforming manufacturing through predictive maintenance. For example, one technique uses AI to determine when machinery maintenance should be performed. This generates cost savings and improves operations compared to routine maintenance.
At a Puerto Rico-based pharmaceutical manufacturing firm, AI is being used to drive robots that are performing quality testing as well as sorting, categorizing and packaging pills.
According to a Frost & Sullivan report, development of smart and safe robots using machine learning techniques will be a prime area of focus. While humans are still needed for logical, reasonable and ethical decision making, the report said that cognitive technologies that allow machines to detect changing manufacturing scenarios and then respond in real time will lessen the need for hands-on intervention. Another report, by Gartner, stated that although AI will eliminate 1.8 million jobs, it will create 2.3 million jobs by spurring innovation and growth.
AI is transforming how products are designed, delivered and manufactured. It is also enabling smarter factories and plant operations, as well as more and higher-quality products. To remain competitive, manufacturers must embrace it not to replace human intelligence, but to augment it.
Published at :