Why fix what is not broken? That’s a common sentiment among traditional manufacturing leaders, but have you heard about the Industrial Internet of Things (IIoT)?
But what if you could predict when something will break and address it during scheduled downtime? What if you could identify a potential problem in advance and prevent any downtime at all?
The Industrial Internet of Things (IIoT) is aimed at doing just that. With a constant flow of process parameters and data points, Industrial Internet of Things (IIoT) can give manufacturing leaders a crystal ball into the future.
What is the Industrial Internet of Things (IIoT)?
The Internet of Things (IoT) connects all sorts of everyday objects such as light bulbs, radios, ovens, and more. IoT allows for “smart” devices that can gather data, share it, and perform functions without the user even present.
When IoT is extended to the industrial world, it becomes IIoT where information technology meets manufacturing operations. IIoT may include robotics, software-defined production, machine-to-machine communication, artificial intelligence, and more. IIoT is one of a suite of tools that can play a role in the modern manufacturing environment.
Benefits of Industrial Internet of Things (IIoT) Implementation
Each piece of a manufacturing process has a slew of possible data points that can track its efficiency and effectiveness. These parameters might include time to complete a process step, raw material waste, product yield, temperature measurements, and more. With equipment connected to IIoT, your machinery can send parameters to a centralized database for analysis.
The potential benefits of IIoT and machine analytics include:
- Lowering operating costs through more uptime, efficiency, and less raw material waste,
- Improving quality by identifying key drivers impacting the process,
- Reducing time to market with improved throughput,
- And, ultimately, increasing revenue.
Imagine if your product was heavily temperature sensitive. If you had a constant stream of the temperature during the assembly process, you could correlate successful batches against those with lower quality.
“Just by managing the temperature better, you can save on scrap material that you might have to rework or throw away,” said Daniel Nichols, a senior software engineer with AutomationNth, a leading automated manufacturing systems and solutions provider.
More companies are adopting IIoT as it becomes readily available and less expensive to implement. More than 80 percent of large companies had adopted at least one IIoT solution by 2019, according to a Microsoft survey.
“It is easy to implement now that wireless Internet and Ethernet connections are available,” Nichols said. “It’s easy to tap into data and send it out. And, some disruptors in the manufacturing space have really shown the value of having intimate, granular knowledge of their process.”
A recent AutomationNth client sought the company’s help in tracking vibrations on their assembly line. As motors wear down, they create more vibration. With the constant flow of vibration data, the client could prevent unscheduled downtime by proactively replacing motors that would soon fail.
Other manufacturers in industries such as the automotive and bioengineering space, are using IIoT to track key quality parameters at off-site contract manufacturing plants. At other companies, IIoT solutions track which operators touch the process at each step and identify individuals who might need retraining or your top employees who may have valuable best practices to share with other operators.
Getting Started with Industrial Internet of Things (IIoT)
A few basic things are needed to start tracking your process with Industrial Internet of Things (IIoT) technologies. Manufacturers can start with just a single, significant parameter that has an important role in the quality, yield, or efficiency.
Step 1: Identify Data Points Needed
The process of IIoT implementation needs to start on the plant floor.
“Go down to the plant floor and talk to the operators and the shift managers,” Nichols said. “They know what data they need to do well in the process – to increase yield or uptime.”
Once you have a description of the key parameters that you need to track, think about how you can measure and record it over time. Perhaps you need sensors that can track time, vibrations, air quality, temperature, or a variety of other factors.
Another approach is to start with the machine that represents the biggest bottleneck in your process. This will likely give you the highest ROI on your implementation.
Step 2: Gather the Right Skills
A successful Industrial Internet of Things (IIoT) implementation is going to require proper identification of the needed parameters, a good architecture for gathering and storing that data, and provide data analysis and visualization for the manufacturer’s leadership.
This is the step where many manufacturers benefit from hiring outside expertise like manufacturing systems integrators, Nichols said. Data engineers can work with the client to determine the best way to capture data. Then, data scientists can help turn that data into usable insights to change the manufacturing process.
Step 3: Capture the Data
The types of solutions needed to gather data will be highly dependent on the machinery itself. Newer machines may have a Programmable Logic Controller (PLC) that will provide data while other machines may already have PC-based controllers. In other cases, you can install an overlay solution with sensors. When all else fails, operators can track and input data sources such as yield numbers or amount of downtime.
Step 4: Analyze the Data
This is the step that causes the biggest headaches for a lot of manufacturers. Most manufacturers have the know-how needed to identify the processes to track and the data points. But leaders become overwhelmed once a large amount of data starts streaming into a database.
“That is where the automation expertise meets the data scientists,” Nichols said.
Not many manufacturers have in-house experience with data science and visualization. Tying together all the “big data” — many data points, across multiple machines, over a series of time – and using it to make meaningful change is both the goal and the largest obstacle.
At AutomationNth, consultants use the OEE Optimizer Solution, a custom developed machine analytics tool, to build web-based dashboards that display key metrics in a user-friendly way. The historical dashboard tracks downtime events, reject reasons, good parts and bad parts, and more. Interactive graphics help users to quickly identify the biggest issues and drill down to the lowest levels of detail for troubleshooting.
For some manufacturers, a clean way to quickly see the data is enough to provide necessary insights. Others may also need to work with a consultant to understand the findings.
Step 5: Use What You Learned
It’s not enough to merely track your processes, manufacturing leadership must communicate and act on the findings. That is where you will see the real ROI in terms of reduced inefficiency, waste, and downtime – which means increased productivity.
Overcoming Potential Industrial Internet of Things IIoT Pitfalls
While the potential benefits of Industrial Internet of Things (IIoT) integration are many, so are the potential pitfalls. Here are three possible stumbling blocks and how to prevent them.
Charging Ahead without a Business Case
The most successful Industrial Internet of Things (IIoT) implementations start as a potential solution to a real problem, not a solution in search of a problem. When you have a real problem, it’s easier to define the data you will need to gather and to sell leadership on the need for investment. This also makes it easier to track ongoing ROI on the project.
“If you have a crystal clear use case for what is the problem you are trying to solve, it makes all the other decisions around adopting new technologies easier and everything is more successful,” Nichols said.
Failing to Standardize Data
Many manufacturers have built their processes over time and therefore have more than one set of software to integrate when it comes to data collection. It can be difficult to standardize data in a way that makes it useful for analysis. Outside experts can help with that.
“The more integrations you have – getting data from one database to another – the more errors you will have,” he said. “It’s ideal to have a central hub with 100 percent up time and redundancy.”
When manufacturers have the advantage of starting from scratch, they need to set down standards for how the data will be collected, stored, and analyzed from the outset.
Lacking Analysis and Follow-Through on Data
Most manufacturers understand their processes well and can define the parameters they need to track. Engineers find installing the necessary sensors or actuators relatively straightforward. But, when the data starts coming in large quantities, that’s where manufacturers tend to get stuck.
“I have seen where companies get someone to come and set this up and they don’t know what to do with the data. The analytics portion of this is a big hole in a lot of manufacturer’s repertoire,” Nichols said. “They have engineers, but having someone to design the dashboard and highlight the information that is important is a totally different skill set.”
Role of AI, Big Data Analytics, and IIoT in Manufacturing
In this thought-provoking article in IndustryWeek, Larry Fast discusses the potential impact of new capabilities like Big Data Analytics, AI, and IIOT in manufacturing. There are several points he made that I found interesting. He highlights how IIOT in manufacturing is becoming more prevalent:
- 79% of companies have started an IoT initiative.
- 44% of manufacturers have a defined digital strategy.
Larry discusses some of the barriers preventing manufacturers from gaining the full benefit from Big Data, AI and IIOT, highlighting ERP systems as an issue:
“Corporations are still spending untold millions of dollars buying “new” ERP systems that still rely mostly on traditional thinking and reporting. Further, report formatting, because of the same outdated thinking, isn’t structured in a way to get actionable, real-time reporting. Why can’t the ERP system simply be linked to the machine’s PLC and provide data in real time? Or must we always have a secondary system, often not integrated with anything else, to have what shop floor people need to more effectively manage the business minute by minute, hour by hour?
ERP programs must be redesigned and cleaned up in concert with these new access systems. In fact, one might wonder why access programs would even be required if the ERP systems provided the same capability? In any case, until ERP programs smash long-standing paradigms and catch up with state-of-the-art manufacturing needs, they will continue to represent a formidable constraint to achieving the full impact of the improvement potential that is now obviously possible.”
He also makes an important note here about the need to start the high level conversations about IIOT in manufacturing:
But now is the time for all C-Suite leaders to follow these technologies carefully, partner up with thought leaders in this area, and strategize how to be among the companies who get up to speed early and commit to the new technology — in fact, even help develop it.
The topics of Big Data, AI, and IIOT in manufacturing are discussed frequently at Automation NTH as we make plans to help our customers adopt these capabilities.
Smart Manufacturing with AutomationNth
AutomationNth provides customers with world-class automated manufacturing systems and solutions. Its services include automation consulting, custom automation systems, and automation optimization.
To learn more about implementing Industrial Internet of Things (IIoT) in your manufacturing or how AutomationNth can help your business, contact us today.