8 Industrial IoT Trends in 2019 | Seebo Blog
A food and beverage manufacturer deploys software with machine learning algorithms applied to OT data from one…
Capitalizing on technological advancements in industrial manufacturing, companies are taking bolder steps to improve growth and operational efficiency in 2019. Here’s a look at the top trends and predictions for industrial IoT in the coming year.
It’s no surprise that worldwide technology spending on the Internet of Things is forecasted to reach $1.2 trillion by 2022 (IDC).
Manufacturers are looking to solve the complex problem of consolidating all production systems — OT and IT data, BI, quality management, and production processes — into a single data model. And they know that those who manage it successfully can beat their competitors in the process. For this reason, adoption of IoT devices and services is set to hit 20% in 2019 (IDC).
But the question isn’t “what”, it’s “how”: there are numerous Industrial IoT solutions to target a myriad of business problems, and manufacturers can only budget for a few POCs or solutions at a time.
With so many possibilities for improvement, where will manufacturers, investors, and governments choose to put their money?
Based on research, we’ve identified the trends that will continue to gain traction in 2019. These are the actions manufacturers will take to better manage operations, deliver improved products and services, and grow business smarter.
8 2019 Trends in Industry 4.0:
Going beyond POCs
If 2018 was the year of IIoT proof of concepts, 2019 will be the year manufacturers move from early proof of concepts to deploying pilots for Industry 4.0 solutions, such as predictive maintenance, digital twin, and predictive quality.
Industry 4.0 solutions are so new that we still lack data for much of the ROI from Industry 4.0 initiatives.
Here is an example:
Predictive maintenance is the headline subject at practically all of the recent and upcoming international Industry 4.0 conferences. But predictive analytics in manufacturing still requires months of collecting enough data to act upon before providing full ROI.
Furthermore, while some manufacturers have reached the predictive stage, very few early adopters have reached the prescriptive analytics phase.
But that is about to change.
With major players in food & beverage, chemicals, and other giant industries deploying Factory 4.0 solutions, there will be more information about how these solutions are effectively implemented per industry by this time next year.
The rise of industrial AI in manufacturing
AI and Industrial IoT are merging to digitize production processes to increase productivity and reduce downtime. Machine learning algorithms for manufacturing are being formulated and tailored to specific production line challenges — such as reducing production waste, improving process stability, minimizing unplanned downtime, and eliminating process disturbances
What does this mean on a practical level?
Search “AI in manufacturing”, and you’ll read articles about more accurate insights into the manufacturing process, and reaching a higher OEE than was possible through previous methods. These aren’t just superlatives — the vast scope of IoT use cases makes manufacturing the most logical field for AI applications.
AI and machine learning are a wide umbrella term for a multitude of different algorithms and applications; many of the trends below are part of that shift towards integrating AI solutions into existing manufacturing processes.
Contextualizing OT data — and tools for contextual analysis
OT and IT have been converging for some time, and ‘collaboration’ used to be the goal — but many manufacturers are taking their operational and IT data a step further to improve the relevance and accuracy of data-driven insights.
What is that step?
The only way for manufacturers to measure the right data, and reach accurate conclusions, is by combining all the relevant operational data from the plant or line environment with business context data from the IT systems.
Are you contextualizing your OT data with the following dimensions?
- Production process flows
- Production recipes
- Batch and product details
- Quality test results
Here’s an example of data contextualization in predictive maintenance:
A food and beverage manufacturer deploys software with machine learning algorithms applied to OT data from one production line, searching for patterns that predict asset breakdown.
But this software doesn’t take into consideration alerts from quality control tests, or which batch and product is being manufactured.
So an oven could overheat for specific recipes — but without the context of the recipe the machine learning algorithm could never yield accurate, actionable insights to the production team.
In the coming year, manufacturers will be budgeting for systems that help them glean manufacturing excellence insights through the lens of process and business data that influence the production environment.
Using digital twins
Digital twins are virtual copies of a physical entity that link to the entity, often in real-time. In the manufacturing world, digital twins support many industry 4.0 solutions, from automated root cause analysis, to predictive quality, predictive maintenance, inventory intelligence, and supply chain optimization.
Digital twins are most commonly used in the areas of design, modeling and simulation, so it’s not surprising that they were a buzzword in 2018, the year of Industrial IoT pilots.
In 2019, we will not only see greater adoption of the digital twin in general, but also an expansion in their popular use: more digital twins used to optimize production processes rather than the individual assets in day-to-day operations and processes.
These ‘full’ digital twins’ will incorporate process data that will help manufacturers reach more accurate insights, whether by deep-diving into individual machines or viewing the high-level process architecture to identify and address manufacturing inefficiencies.
Early adopters are already using digital twin software to improve the accuracy of predictive AI applications, and more manufacturers will adopt this approach in the coming year.
As devices become more powerful in 2019, more manufacturers will take advantage of local data processing and AI capabilities, also known as edge computing.
By 2020, IoT sensors and devices will generate over 5.07.5 zettabytes of data.
Manufacturers are for the most part already collecting data, but managing it via cloud computing puts a financial strain on manufacturers — not to mention the security risks of storing all your raw data in the cloud.
Edge computing helps businesses by analyzing and storing data close to its source decrease time and expenses related to data analytics, as well as improving data security.
Multiple machines in one production line monitoring vibration of machine components.That’s hundreds of data points per second.
Uploading all that data to the cloud for cleansing, processing, aggregating and analysis is redundant.
In edge computing, each machine in the line is connected to an edge computer to collect, store, and preprocess OT data.
The edge computer not only processes vibration data, for example, but also performs feature extraction to select a predefined amount and type of vibration data — highs and lows within a given time frame, for example — to go to the cloud.
Even this basic level of data analysis processing performed at the source streamlines the process of aggregating production line data to an incredible degree. There is much less historical and real-time data for machine learning algorithms to sort through, speeding up findings that could affect everything from yield to uptime to product quality.
Edge computing also cuts down on the cost of data storage in a cloud: a dozen data points for every ten thousand measured. Limiting the raw production data sent to the cloud also mitigates data security risks.
Mobile Industry 4.0– ERP and quality management systems.
The arrival of 5G next-gen mobile networks heralds greater adoption of IIoT applications.
Due to 5G and other advancements in mobile tech, 2019 will see a rise in real-time IIoT applications and the use of IIOT for teams once excluded from direct interaction with the technologies involved.
For example, while many ERP systems are now integrated with Industry 4.0 systems and even include applications, such as MES, most of these systems do not support all the user roles and business functions related to the manufacturing floor.
This is unfortunate, since many of the solutions forecasted to grow in adoption, such as operator productivity and inventory intelligence, must be accessible to teams on the factory floor.
Expect to see a rise in companies offering apps specializing in different user personas, such as quality management software apps, or applications with different dashboards per business role.
Supply chain optimization
What was once purely a logistical function, now has their own business models and optimization processes.
Coupled with this, Online-consumer trends have dramatically changed customer expectations for on-demand services, transparency, speed, and efficiency. Supply Chain 4.0 is a way to meet the new demands and changing supply chain landscape through digitization.
Supply chain optimization can and does utilize many of the other top Industry 4.0 trends for 2019: Digital twins, mobile apps, and AI-powered predictive tools. Artificial Intelligence will be imbedded in common supply chain processes.
Accurate — Digitally map the supply chain and real-time production and product data create transparency and increase the accuracy of inventory data.
Faster — Advanced forecasting tools, coupled with real-time data on spare parts supply and demand, will create process where finished products reach their destination faster.
Flexible — real-time data leaves room for flexibility in the distribution process
Securing IIoT endpoints
Enterprises are already invested in securing their OT infrastructure, to the same degree as they do their IT systems. However, the clear and present threat to organization’s cybersecurity, coupled with the boom in Industrial IoT adoption, will see OOT security and ICS security go mainstream in manufacturing plants, whatever the size or industry.
It won’t be easy; securing IoT devices or machines is becoming increasingly difficult, so much so that Microsoft recently released a list of best practices for IoT devices.
And with the proliferation of edge computing comes a plethora of new industrial IoT endpoints, i.e. devices with computational capabilities and network connectivity (iiconsortium.org). So even the bonus of securing data by sending less to the cloud comes with the added risk of increase endpoints.
Despite this, the gain to businesses in developing smart production lines is clear enough that securing data is becoming less of a deterrent to manufacturers who want to increase yield and improve operational efficiency through AI.
Industrial IoT Predictions for 2019
We’re seeing more and more deployment of Industrial IoT solutions that are revolutionizing the manufacturing landscape digitally — transforming customer relationships, differentiating offerings, and driving massive operational improvements to meet the growing demands on production.
Based on these trends, industrial IoT early adopters are positioned to be five times as likely to generate revenue from Industry 4.0 initiatives compared to late adopters. But take note — companies must first decide which business value drivers they want to contribute to. Only then, can they align their digital strategy with the business goals they are targeting in order to manage, secure, and operate IoT platforms and processes effectively.