Internet of Things and Predictive Manufacturing – III

In Internet of Things (IOT)-enabled Predictive Manufacturing (PM), you manufacture hardware that you sell to your customers, but during the manufacturing process, you plant small gadgets (RFID, sensors, video monitoring, cameras, remote information distribution capabilities,  and actuators) that will monitor the hardware and create data for you on the state of your hardware as it […]

In Internet of Things (IOT)-enabled Predictive Manufacturing (PM), you manufacture hardware that you sell to your customers, but during the manufacturing process, you plant small gadgets (RFID, sensors, video monitoring, cameras, remote information distribution capabilities,  and actuators) that will monitor the hardware and create data for you on the state of your hardware as it leaves your manufacturing floor, gets shipped and delivered to your customer, goes through the deployment at the customer’s premises, and begins operation at the customer’s site or wherever the hardware may be deployed. Data collected on the hardware could include the temperature, humidity, location, some diagnostics on the state of the hardware, and so on. These data, which have to be communicated to you, the manufacturer – most likely via some cloud interactions, are instantaneous in time, meaning that you have an astronomically huge amount of data to process (analyze) for business and/or manufacturing intelligence. Processing the collected data allows you to assess the state of the hardware, communicate with the hardware, and remotely fix impending problems with it, even before the problems occur! By this means, you prevent a downtime at the customer’s site.
Thus, in the PM model, you continuously and remotely service the hardwareyou sell to a customer based on the predictive power you acquire from the data you collect remotely. The most common application of predictive analytics in manufacturing is expected to be preventive maintenance, by anticipating hardware degradation.
The requirements of PM include: a) the technology to collect data, b) the Internet capability and bandwidth to transfer the data to some cloud site, c) the storage capacity of the cloud servers, d) the Big Data analytics wherewithal to process petabytes of data, and e) the feedback to the hardware – using the Internet, with any requisite actuation capability.
Although PM, also referred to as Product as a Service (PaaS) in the earlier articles, has been espoused in this series, I should point out that this trend is quite new, and is, not by any means, the order of the day in manufacturing. In relative terms, only a handful of companies are trying out this new technology, as making decisions based on experience and guts is still very prevalent in manufacturing. Moreover, manufacturers continue to depend heavily on charts and spreadsheets. Mike Hitmar, product manager, manufacturing and supply chain at SAS, was quoted as saying: “Even in 2015 we’re finding that very large, multinational corporations still have manual processes such as Excel and pie charts to make forecasts.” At any rate, PM is gaining ground, and early pioneers of PM include the following companies.
General Electric: GE Aviation is using operational data collected by aircraft engine sensors to predict problems and proactively deploying maintenance services and analyzing aviation fuel usage, as a way to help the company’s airframe customers optimize engine performance and prevent downtime caused by the failure of an engine part.
Pratt & Whitney: As expected, P&W, a competitor of GE Aviation in the area of aircraft engine manufacturing, is also exploring PM by planting a plethora of sensors in its aircraft engines and other devices that it manufactures. The collected data goes into the analytic modules for prediction, yielding results that could hopefully drive optimum and automated engine maintenance. This capability will obviously make Pratt and Whitney’s airframe customers like Boeing, Airbus, Lockheed Martin, etc. very happy.
BMW: This German luxury auto maker is also hopping on the PM bandwagon by outfitting cars with myriads of improved (smaller, more precise, more durable, capable) sensors that collect data which are then sent back to BMW for predictive analytics that, in turn, drive remedial actions.
John Deere: This American farm equipment manufacturer has also recognized the need for PM, via its Field Connect IoT platform. Sensor-based data on weather conditions, soil temperature and wind speed are harnessed to help farmers improve crop yields while also providing preventive maintenance on the farm equipment.
Babolat: Babolat is one of the oldest manufacturers of racket sports equipment. The company offers an app that analyzes ball behavior, thereby helping players improve their game.
All Traffic Solutions: All Traffic Solutions is a manufacturer of traffic signs and safety equipment. The company offers its customers a range of subscription services that include remote equipment management and (remote) diagnostics.
To conclude this series on IOT and PM, I refer you to the book edited by OvidiuVermesan and Peter Friess entitled “Internet of Things – From Research and Innovation to Market Deployment,” by River Publishers (2014), for a detailed listing of the possibilities with IOT.  According to a promotion of the book: “The book aims to provide a broad overview of various topics of Internet of Things from the research, innovation and development priorities to enabling technologies, nanoelectronics, cyber physical systems, architecture, interoperability and industrial applications.”
Although PM does not receive much attention in the book, you will find a very long list of other applications, including Smart Food/Water Monitoring, Smart Health, Smart Living, Smart Environment Monitoring, Smart Energy, Smart Buildings, Smart Transport and Mobility, Smart Industry, and Smart City. (The word “Smart” is sometimes used synonymously with IOT in the book.)