By David Stonehouse, global consulting leader, Connected Enterprise Services, Rockwell Automation
The value of industrial analytics is the results they deliver.
For a brewery, analytics delivered a 60% boost in throughput. For a pet food producer, it delivered more than $800,000 in annual energy-cost savings. For a cosmetics plant, it delivered a 90% reduction in line stoppages.
Without a doubt, the ability to collect raw data and turn it into useful information for workers is essential to staying competitive. But what if you’re unsure about how to bring analytics to your operations? Or what if you have a goal to deploy analytics but no defined strategy in place?
Fortunately, implementing analytics doesn’t have to be a mystery or an overwhelming task. Those that already have made the journey provide helpful lessons for how you can begin your own.
What You Need
Industrial analytics is built around four core elements: people, data, connectivity and analytics software.
1. People: Data scientists are vital to deploying analytics. However, your everyday use of analytics shouldn’t hinge on these specialized workers.
New analytics technologies work almost as a data-scientist-in-a-box to structure your data up front. Then, non-data specialists can freely access, manipulate and analyze the data. This “self-service” analytics approach allows almost any employee in your company to use data to solve various issues.
2. Data: It’s critical to identify what data you want to collect and where it will come from. You may collect some data from your people, but most of it will come from connected technologies known as the Industrial Internet of Things (IIoT). These technologies can include device-level components such as sensors, actuators and drives; machine- or line-level components such as controllers; and enterprise-level components such as software systems.
3. Connectivity: Analytics requires seamless connectivity across your plant floor. This means you need to unify any disparate systems that have created “islands” of information. It also means you need to provide the bandwidth for both current and future traffic needs.
Standardizing your plant-floor network on a technology like EtherNet/IP™ can help you achieve real-time control and information. Pre-engineered network products and services such as Industrial Data Centers or Infrastructure-as-a-Service (IaaS) offerings also can reduce your network design and configuration time.
4. Analytics Software: Look for analytics software that delivers the best value to your organization. The software’s most basic job is to add context to data. Context allows you to combine and compare different data to get a deeper understanding of your operations. Instead of simply getting an oven temperature reading, for instance, data contextualization can give you that reading at a certain time, for a specific recipe, and during a specific shift. Then you can track your key performance indicators (KPIs) and factors that contribute to them.
Your analytics software can and should also do much more than contextualize data. For example, it should allow users to drill down into specific analytics to investigate anomalies or troubleshoot issues. It can even use machine learning to monitor your operations and trigger automatic control adjustments if a process falls outside allowable parameters.
Early Decisions
The previous four elements form the foundation upon which your analytics will be built and executed. But you also will need to make some key decisions early on to help ensure success over the long term.
Solve Business Needs. Your analytics investment can pay for itself. However, it’s important that your investment is tied to specific business outcomes, and isn’t merely about the technology. Build a strategy for your investment around a specific need, such as improving overall equipment effectiveness (OEE). Then determine the OEE boost required to meet your return on investment (ROI) goal. You can then use that ROI to fund subsequent analytics initiatives.
Make Security a Priority. Security isn’t something you add to your analytics strategy or network upgrade. It should be holistic, extending from edge devices to the enterprise. Start with a security assessment to identify risks and potential threats. Then deploy a defense-in-depth (DiD) security approach to guard against threats on multiple fronts. And work only with trusted vendors that can help you meet your security goals.
Work with Your Partners. Your existing industry partners can play an important role in your analytics strategy. On-machine analytics from your OEM, for example, can help maximize the performance and durability of your production assets. With just a gateway device installed on a machine, the OEM can deliver analytics via cloud-based applications.
Get the Support You Need. Finally, make use of available services and resources. They can help you get the most value from your analytics deployment and alleviate whatever challenges you’re facing.
Reference architectures, for example, can help you design and implement your network upgrade. Training and certification programs can equip your employees with the skills they need to design, deploy and oversee a secure information infrastructure. In addition, connected services can help you deploy analytics, or even take on key roles for you, such as remote monitoring.
Get Started
It has never been easier to deploy analytics. The foundation you need in place is well established, as demonstrated here. New technologies can put the power of your data into the hands of workers who need it.
Now, deploying industrial analytics shouldn’t be a question of “Where do I begin?,” but “When can I get started?”
The Journal From Rockwell Automation and Our PartnerNetwork™ is published by Putman Media, Inc.
