Why does the packaging industry need simulation?
Almost every product that arrives at your doorstep or on the shelf of your local supermarket survived the journey fresh, clean and intact because of its packaging. From salt to smartphones, the packaging of consumer goods must be carefully designed to ensure that it doesn’t cause issues in the production line and that it is strong and waterproof enough to withstand the stresses of shipping, while also being lightweight and attractive to purchasers. Sustainability targets are adding an extra level of challenge, as material use must be reduced and the proportion of recycled, recyclable or biodegradable materials increased.
Finite element analysis (FEA) simulation with SIMULIA Abaqus technology helps designers and packaging managers to understand the performance of packaging in real-world scenarios without needing to build physical prototypes. It also powers design of experiments (DoE) and optimization studies that can explore the entire design space to find the best trade-off between different factors.
Simulation is most useful when used from the beginning of the design cycle. Unified modeling and simulation (MODSIM) allows simulation to be used during the initial concept stages, with the simulation model constructed directly from the design data. This not only speeds up the development process, it also means that potential problems can be noticed earlier and the root causes identified and resolved.
How does AI and machine learning help packaging simulation?
AI-enabled MODSIM is the next step for MODSIM, using the power of machine learning to make simulation much faster and therefore more useful for designers. With classic finite element analysis, for each design variant, the physics must be simulated again from scratch. AI machine learning can provide results for any design variant in moments and accelerates the process.
Only a few simulations covering a representative area of the design space for the packaging need to be performed. These are then used to train a neural network, which learns how the geometry relates to its physical properties. Both time transient and stationary scalar physical responses as well as 3D full field prediction can be modeled, resulting in an information-rich and much more productive environment for product design.
The resulting surrogate model is validated against further simulations, and if an acceptable level of accuracy is reached, it can then be used to calculate the behavior of the packaging for any design variant.
Using machine learning, designers can find the best trade-offs within seconds and understand the impact of a design change with real-time feedback. Exploring more of the design space can significantly shorten the package development process while achieving ambitious cost, weight, and sustainability targets. With AI-enabled MODSIM, the simulation and machine learning tools are also available in an easy-to-use interface, bringing them to non-expert users. Rather than replacing human work, AI works alongside the designer, providing instant feedback about the design.
Discover more about Dassault Systèmes SIMULIA AI solutions for packaging simulation
You can always view the collection of materials on the Machine Learning Wiki in the SIMULIA Community. This Wiki includes a detailed explanation of training neural networks with simulation data and links to articles and webinars on the subject.
Conclusion
AI and machine learning are helping the CPG industry to meet the challenges of modern packaging design. Machine learning accelerates the simulation and design exploration process, helping designers to reduce weight and cost and improve strength and sustainability. AI solutions from Dassault Systèmes integrate into their established CPG industry workflows, combining machine learning technology with best-in-class physics simulation technology.
Interested in the latest in simulation? Looking for advice and best practices? Want to discuss simulation with fellow users and Dassault Systèmes experts? The SIMULIA Community is the place to find the latest resources for SIMULIA software and to collaborate with other users. The key that unlocks the door of innovative thinking and knowledge building, the SIMULIA Community provides you with the tools you need to expand your knowledge, whenever and wherever.
Katie is the Editor of the SIMULIA blog, an expert in engineering and scientific communication, and a strategic digital marketer. Katie has a BA in English and Writing from the University of Rhode Island and a MS in Technical Communication from Northeastern University. She is also a proud SIMULIA advocate, passionate about democratizing simulation for all audiences. Katie is a native Rhode Islander who lives just outside of her favorite city, Providence. She is a true New Englander and loves sharing all the cool things NE has to offer. She enjoys a variety of hobbies including history, astronomy, science/technology, science fiction, true crime, fashion and anything associated with nature and the outdoors. She is also mom to a 5-year old budding engineer and two crazy rescue pups.