FEATURE SMART FACTORIES & AUTOMATION
IT’S TIME TO INTRODUCE YOUR FACTORY TO ITS DIGITAL TWIN
A
digital twin is an exact, virtual replica of a real product, process and service.
By applying real and virtual scenarios side-by-side, manufacturers can trial digital simulations before implementing in factories. Designed to simulate and offer information on real-world operating conditions, a digital twin responds to changes, predicts outcomes and provides optimal decision recommendations.
DIGITAL TWN CONCEPT While the concept of digital twin has been around for a while, the combination of lower computing costs and sophisticated mathematical optimisation has primed digital twin to spread across the manufacturing sector. In fact, industrial manufacturers such as Boeing are already testing and perfecting the use of this technology. An early adopter, the world’s largest aerospace company has leveraged the exchange of data between its virtual and real operations to dramatically shorten the construction and release of its commercial jetliners. The capabilities of digital twin can span the whole manufacturing sector, from the highest level of the production process and networked materials, down to the lowest level of work instructions. Throughout the production line and even extending into the supply chain, digital twin involves machines observing humans and operations, mathematically modelling motions and decisions, and then computationally improving itself in search of better procedures and outcomes. These learnings and improvements are then introduced to workers and equipment in the real world, allowing manufacturers to achieve a greater level of predictability and self-improvement.
26 MAY 2018 | FACTORY EQUIPMENT Looking at customer segmentation,
digital twin can help manufacturers take this process one-step further by creating individual profiles and models for each customer. Separate from product production, digital twins can evaluate the execution of the supply chain process for each unique customer and propose the optimal material and human resources required. Through optimisation, the digital twin can also consider all supply and demand factors to set the pricing for the logistics and transport services that a customer will most likely accept.
FACTORS TO CONSIDER However, before jumping in headfirst there are some factors manufacturers must consider before introducing digital twin to the factory. Firstly, traditional modelling software was not designed for the sheer variety and volume of data available today. Given digital models are only as good as the data available for analysis, software re-tooling is often required to capture and distil data into something useful to rethink design, build, and operation of a factory. With that said, manufacturers shouldn’t shy away from experimenting with a digital twin, rather test and think how this model can be extended once new sources of useful data become available. Secondly, having implemented digital
twin, manufacturers have to trust that outputs and simulations are not biased and results are verifiable. A robust AI governance programme is key, and must meet the standards of regulators, stakeholders, and customers. With the European Union’s General Data Protection Regulation (GDPR) set to take full effect in May 2018, manufacturers must ensure
Despite it being a corporate catch phrase, ‘Industry 4.0’ – the blurring of digital and material worlds – has caught on and become a reality in manufacturing. A lot has been said about how predicative analytics, artificial intelligence (AI) and the Internet of Things (IoT) are set to transform industrial processes, but there’s one trend that has the potential to transform factories – the Digital Twin. By Kris Kosmala, general manager, Asia Pacific, Quintiq
the relevant privacy rules and audit procedures are in place as a digital twin is likely to include sensitive customer data. Lastly, manufacturers need the
computational capacity to efficiently manage human behaviours in digital twin simulations. This is especially crucial for organisations intending to calibrate autonomous robots or systems based on the output of the twin, as it can be difficult to accurately capture the human behavioural triggers within a mathematical virtual twin. While it might appear daunting, these
considerations are in fact quite manageable and worth the effort. Gartner predicts that by 2021 half of large industrial companies will use digital twins and these organisations are set to gain a 10 per cent improvement in effectiveness – a significant gain for a manufacturer’s balance sheet. Separate from the bottom line, the ability to create and evaluate multiple scenarios prior to making a real world decision means manufacturers can extend value to their employees, partners, and customers. The American paediatrician Dr
Benjamin Spock famously said: “You know more than you think you do,” and this sentiment applies to modern manufacturers. Organisations need only to look in the mirror to understand the challenges and opportunities they face – and a digital twin is the best mirror to gain a truly competitive edge.
Quintiq
www.quintiq.com / FACTORYEQUIPMENT
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56
