For many in today’s tech-driven world, OT, or Operations Technology, is a term that has rarely or perhaps never been heard. Most are well-acquainted with IT, or Information Technology, and many interact with IT teams, systems, and resources on a daily basis.
What is OT, and why should I care?
First of all, OT has also been around for a long time, even if you didn’t know it. Manufacturers have long had teams dedicated to the day-to-day functioning of production lines. Logistics companies have warehouse operations teams. OT keeps power and manufacturing plants humming along. OT keeps the sorting lines moving at the postal service. And lost suitcases notwithstanding, the baggage handling system at modern airports is a marvel to behold — and the domain of OT.
In most cases, OT does its job quietly and behind the scenes. OT only gets discussed when something goes wrong — often spectacularly — such as when a production line goes down, which can materially impact a company’s delivery schedule and bottom line.
However, OT does matter to the rest of us outside of the production line, and it’s largely the fault and result of three little letters: I, O, and T. The Internet of Things (IoT), along with its big brother, the Industrial Internet of Things (IIoT), is having a profound impact on how next generation production operations will run.
Security has always been a major concern. Not surprisingly, it has long been the view of OT that the less the rest of the company has physical or logical access to a plant, the happier the OT team will be. In fact, most OT systems have existed within the four walls of the factory or plant and have been disconnected almost entirely from the outside world.
However, connected operations promise to dramatically increase efficiency, utilization, and collaboration. At the same time, IIoT and the cloud are rapidly changing the assumption of a disconnected operation, and making security a bigger concern in the process.
Use Cases of IIoT
Not unlike the rest of IoT, there are many use cases and solutions that impact IIoT, but three rise to the top in terms of scale, value, and potential impact. They are the low-hanging fruit that will most likely be where most enterprises take the next step in their industrial IoT journeys:
- Predictive Maintenance
- Autonomy and Control
- Field Service Engineering
Any machine with moving parts will eventually break down and require service. If a pipe bursts or a conveyor belt jams, production lines stop, and immediate repairs are required. These are examples of condition maintenance. Fortunately, many system parts have duty cycle ratings, and their replacements can be planned and scheduled. We refer to this as preventative maintenance. It is fair to say that planned / scheduled downtime for preventative maintenance is preferable to unplanned downtime for condition maintenance repairs.
Furthermore if a proactive replacement or repair can happen simultaneously with another condition repair, it is possible for field service teams to help avoid further unplanned downtime and larger, more costly repairs down the road.
On the other hand, changing parts just for the sake of changing them on a predetermined schedule may actually be a waste of time and capital. A part may be rated at 10,000 hours but in practice have a life of 20,000 hours. Others may fail well ahead of schedule. So what’s to be done? Is it worth changing that part on a schedule, or should you wait? How expensive is that part? What’s the lead time for procuring a replacement? Do I need to keep one in inventory, just in case, and pay for it as an insurance policy? How do you win at this game, keeping your line running at top efficiency while managing the financial risk?
These are difficult questions to answer, and they are the raison d’etre for Predictive Maintenance, which seeks a data-driven, best-of-both-worlds approach to optimally keeping the line running at reasonable cost.
Many systems and machines (although not all) have long been equipped with sensors that track telemetry or performance data. That data is typically raw and without context. Some companies (although not all) had the foresight to capture that raw data in a special database, called a data historian. More often than not, the data historian sits, in some cases for years, in an un- or underutilized fashion.
Raw data on its own is just that — for example, a giant table of temperature readings recorded every second that say 107 degrees. Not very useful on its own. Certainly a blip that suddenly shows 200 degrees and then returns back to 107 degrees might be a concern, or it could be a false positive. But what happens if 107 becomes 130 for a few hours or is trending upward? In general, the answer requires looking across the data to determine what it means. In other words, deriving context from the data.
Predictive maintenance is the art and data science associated with ingesting these massive pools of raw data, using them to train machine learning algorithms to derive context, and anticipating part failures with high statistical probability, and making recommendations on when parts should be proactively replaced before downtime occurs.
And now that the four-walled barriers between factory floors are coming down, we are beginning to see the migration of both historical and real-time data to the cloud for analysis — which in turn will enable better maintenance predictions in the future. And all those years or decades of “dark data” languishing in the data historian suddenly becomes useful in the cloud, where it is finally cost-effective to analyze.
Autonomy and Control
One of the greatest perceived barriers to adoption of IIoT on the factory floor or production line is based on security concerns (anyone remember Stuxnet?). At the same time, there is a practical concern that is based on latency.
We are now witnessing the next chapter in cloud adoption, and that is with increased cloud intelligence at the edge. What’s more, the ability to use the same cloud technologies, programming languages, and models — regardless of location — creates increased flexibility and efficiencies in development, maintenance, and operations costs.
Does it make sense for a production line to rely on a call to the cloud to determine whether or not to shut down a production line? No more than it does for an autonomous vehicle to act on the need to step on the brakes before colliding with the car in front of it.
Much of IIoT’s potential comes from real-time, local decision making and action on the basis of sensor data. Yet, the cloud still has an important role to play in helping enterprises look across locations, improving their decision algorithms, and effectively “honing the edge” to make better local decisions.
Recall the scenario with temperature readings every second. What is the “right” temperature threshold for a production line to slow down or be taken offline? The combined knowledge and experience across many locations and outputs from many predictive analytics algorithms helps lead to control algorithms that can be deployed at the edge, and in the process make best practice-based, data-driven local decisions.
Field Service Engineering
Field service team enablement and utilization are both critical components and benefits to an industrial IoT solution.
Sensor-enabled operations can tell when something has broken or is about to break, which in turn can be tied to proper scheduling and deployment of field service teams. This, however, is just the beginning of the impact: access to real-time sensor data can actually help field service teams make repairs and calibrate operations.
We are seeing the emergence of augmented reality and voice solutions as valuable tools in helping field service engineers do their jobs. Having headset or tablet access to exploded, 3D CAD drawings with detailed installation and configuration procedures, along with real-time sensor data, can significantly reduce repair times while increasing quality and safety.
And if holding a tablet in front of a machine part to examine its contents isn’t necessarily the most practical way of making repairs, a hands-free voice interface providing both instructions and real-time configuration/sensor data can be extremely helpful.
In many ways, the Internet of Things is still just getting started. With the arrival of the cloud and aiding technologies that can be deployed securely at the edge, we are witnessing OT gain confidence in implementing solutions that expand beyond their four walls. CTP, with our expertise in deploying both cloud and IoT solutions, along with our incredible team of experience designers, is well-positioned to assist you in operationalizing your industrial IoT needs.