7 Industry 4.0 trends for 2020
03 January 2020
Industry 4.0 is making manufacturing more productive & profitable than ever before. Jos Martin, Senior Engineering Manager at provider of mathematical computing software for engineers & scientists, MathWorks tells us about 7 major trends he expects to see in 2020 that can help professionals foresee the technologies that will define the next decade – and where factory of the future is headed.
This article was originally featured in EPDT's 1H 2020 IoT & Industry 4.0 supplement, included in the January 2020 issue of EPDT magazine [read the digital issue]. Sign up to receive your own copy each month.
There will of course be challenges along the way, such as meeting increasing demand for personalised and customised goods, reducing waste and handling resources more responsibly, but with creativity and ingenuity, these can be tackled, and the benefits can be realised. So, what is on the horizon?
1.Standardised protocols for seamless interoperability of connected machines
It will be important to ensure interconnectivity, with machines and modules being dynamically rearranged in the factory. Standardised protocols like OPC UA TSN will play a key role in ensuring that equipment from different vendors interoperates seamlessly. Cumbersome cabling and cable runs will disappear and be replaced with wireless protocols like 5G and its successors. But machines will not only be connected with each other, but also to cloud systems where elastic calculation power is available for running powerful algorithms on business and engineering data.
2. Reinforcement learning goes next level
AI (artificial intelligence) programs trained with reinforcement learning (RL) are beating human players in board games like Go and chess, but it’s doing so much more for Industry 4.0. RL is helping engineers implement controllers and decision-making algorithms for complex systems such as robots and autonomous systems, automated driving, control design and robotics. We’ll see successes where RL is used as a component to improve a larger system. Key enablers are easier tools for engineers to build and train RL policies, generate lots of simulation data for training, easy integration of RL agents into system simulation tools and code generation for embedded hardware. RL could power breakthroughs in more autonomous, even driverless, operation of mobile plant equipment within an industrial setting.
3. Collaborative robots work hand-in-hand with humans
The automation industry has been discussing the vision of “sample size one” for some time – how production lines can produce one of a kind, without running into long changeover-times or other inefficiencies. With Industry 4.0, this vision must eventually come true to meet the requirement of full individualisation in production. To meet this, machines cannot be set up in a fixed, inflexible manner on the shop floor, where they are commissioned, parameterised and tuned for one specific product that is produced over and over again for months or even years. Tomorrow’s production lines must be flexible – built from multiple mechatronic modules that can easily be rearranged, with more and more robots or “cobots” (collaborative robots working hand in hand with human workers), and AI that parameterises and tunes the machines according to the next – individualised – item that is manufactured on the line.
4.Simulation makes virtual commissioning a reality
As software complexity and the number of possible combinations of modularised software components grows, performing comprehensive tests on the physical machine gets harder and more time consuming, and will eventually become impossible. Given this, it will be vitally important to perform virtual commissioning of the software to verify the absence of errors and to validate if requirements are met, based on simulation models, before the physical production line is even in place. Innovation leaders like Krones, the leading manufacturer of bottle filling lines worldwide, are already using multi-domain simulation models for virtual commissioning today.
5. Predictive maintenance and AI evolve with edge computing
As edge computing devices and industrial controllers develop, they are offering a rapidly growing calculation power. In conjunction with the use of cloud systems, they are paving the way for a new dimension of production system software functionality. AI algorithms will dynamically optimise the throughput of the entire production line, while minimising the consumption of energy and other resources. This will help teams and their organisations not only minimise waste, and deliver on corporate social responsibility policies, but also crucially save money. Predictive maintenance will evolve and consider data not only from one machine or site, but across multiple factories and across equipment from different vendors. Depending on the requirements, the algorithms will be deployed on non-real-time platforms, as well as on real-time systems like PLCs, as Beckhoff recently demonstrated at Hanover Messe in Germany.
6. Higher quality data removes some hurdles for AI deployment
We know training accurate AI models requires lots of data, and analyst surveys do name data quality as a top barrier to successful adoption of AI. In 2020, simulation will help lower this barrier. While you often have lots of data for normal system operation, what you really need is data from anomalies or critical failure conditions. This is especially true for predictive maintenance applications, such as accurately predicting remaining useful life for a pump on an industrial site. Since creating failure data from physical equipment would be destructive and expensive, the best approach is to generate data from simulations representing failure behaviour and use the synthesised data to train an accurate AI model. Simulation will quickly become a key enabler for AI-driven systems.
7. Not only data scientists will rule the roost
Out of all the trends, the biggest will be on the human beings working in the factory of the future. By capitalising on technology and tools, more engineers and scientists, not just data scientists, will work on AI. The factory of the future requires engineers who can build models, dealing with large data sets and handling the respective development tools in order to address the above trends. Therefore, companies building and operating industrial equipment need to change their job postings and hire skilled engineers with a completely different profile to be ready for a future in which Industry 4.0 is merely the beginning.
From collaborative robots working hand-in-hand with humans to simulation making virtual commissioning a reality, there are a whole host of trends we will see in 2020 define the factory of the future. Adapting to these changes won’t be easy, but with teamwork and the right tools it is achievable.
Contact Details and Archive...