Machine learning can predict the mechanical properties of polymers - A machine learning algorithm can use X-ray diffraction data from polymers to predict the behaviour of new materials.
Symbolic image
Computer-generated image
polymers such as polypropylene are fundamental materials in the modern world, found in everything from computers to cars. Because of their ubiquity, it’s vital that materials scientists know exactly how each newly developed polymer will perform under different preparation conditions. Thanks to a new study, which was published in Science and Technology of Advanced Materials, scientists can now use machine learning to determine what to expect from a new polymer.
Predicting the mechanical properties of new polymers, such as their tensile strength or flexibility, usually involves putting them through destructive and costly physical tests. However, a team of researchers from Japan, led by Dr. Ryo Tamura, Dr. Kenji Nagata, and Dr. Takashi Nakanishi from the National Institute for Materials Science in Tsukuba, showed that machine learning can predict the material properties of polymers. They developed the method on a group of polymers called homo-polypropylenes, using X-ray diffraction patterns of the polymers under different preparation conditions to provide detailed information about their complex structure and features.
“Machine learning can be applied to data from existing materials to predict the properties of unknown materials,” Drs. Tamura, Nagata, and Nakanishi explain. “However, to achieve accurate predictions, it’s essential to use descriptors that correctly represent the features of these materials.”
Thermoplastic crystalline polymers, such as polypropylene, have a particularly complex structure that is further altered during the process of molding them into the shape of the end product. It was, therefore, important for the team to adequately capture the details of the polymers’ structure with X-ray diffraction and to ensure that the machine learning algorithm could identify the most important descriptors in that data.The new method accurately captured the structural changes of commonly used plastic Polypropylene during the molding process into the end product.
To that end, they analysed two datasets using a tool called Bayesian spectral deconvolution, which can extract patterns from complex data. The first dataset was X-ray diffraction data from 15 types of homo-polypropylenes subjected to a range of temperatures, and the second was data from four types of homo-polypropylenes that underwent injection molding. The mechanical properties analysed included stiffness, elasticity, the temperature at which the material starts to deform, and how much it would stretch before breaking.
The team found that the machine learning analysis accurately linked features in the X-ray diffraction imagery with specific material properties of the polymers. Some of the mechanical properties were easier to predict from the X-ray diffraction data, while others, such as the stretching break point, were more challenging.
“We believe our study, which describes the procedure used to provide a highly accurate machine learning prediction model using only the X-ray diffraction results of polymer materials, will offer a nondestructive alternative to conventional polymer testing methods,” the NIMS researchers say.
The team also suggested that their Bayesian spectral deconvolution approach could be applied to other data, such as X-ray photoelectron spectroscopy, and used to understand the properties of other materials, both inorganic and organic.
“It could become a test case for future data-driven approaches to polymer design and science,” the NIMS team says.
Ryo Tamura, Kenji Nagata, Keitaro Sodeyama, Kensaku Nakamura, Toshiki Tokuhira, Satoshi Shibata, Kazuki Hammura, Hiroki Sugisawa, Masaya Kawamura, Teruki Tsurimoto, Masanobu Naito, Masahiko Demura, Takashi Nakanishi; "Machine learning prediction of the mechanical properties of injection-molded polypropylene through X-ray diffraction analysis"; Science and Technology of Advanced Materials, 2024-8-5
Most read news
Original publication
Ryo Tamura, Kenji Nagata, Keitaro Sodeyama, Kensaku Nakamura, Toshiki Tokuhira, Satoshi Shibata, Kazuki Hammura, Hiroki Sugisawa, Masaya Kawamura, Teruki Tsurimoto, Masanobu Naito, Masahiko Demura, Takashi Nakanishi; "Machine learning prediction of the mechanical properties of injection-molded polypropylene through X-ray diffraction analysis"; Science and Technology of Advanced Materials, 2024-8-5
Topics
Organizations
Reading synthetic polymers as data storage more efficiently
Insights on molecular dynamics in the ultrashort time window following UV excitation
KIT researchers produce metamaterial that stretches and compresses differently than conventional materials
Using a library of 1,000+ agrochemicals, scientists saw significant changes in behaviour and long-term survival of different insect populations
By automating routine tasks, scientists can focus on higher-level research questions, paving the way for faster breakthroughs
A cost-effective solution that delivers more energy
Salt batteries
AI learns chemical connections
Research team synthesises three-dimensional ring structures as potential alternatives to biologically active flat rings
"This is a factor that must be taken into account in future risk assessments of these substances"
New technology for the precise diagnosis of electric vehicle batteries using small currents
Groundbreaking discovery in understanding how air pollution forms at the molecular level
"This research...has potential applications across various fields, including chemistry and biology, where precise molecular detection is essential"
Research Focus: Sustainability, Safety, Performance
"Nature often provides the solution to problems that concern it" - without the example of the giant manta rays, research might not have come up with this idea at all
“By overcoming the key challenge of current technology, our results have the potential to drive the global transition towards clean energy solutions”
3D structures of biomolecules
High concentrations of academic patents at some universities and in some countries
The latest and most innovative FFF system designed for highest usability, robustness and data quality
Spinsolve is a revolutionary multinuclear NMR spectrometer that provides the best performance
Analyze macroscopic samples with microscopic resolution (5 µm) in seconds
From now on, don't miss a thing: Our newsletter for the chemical industry, analytics, lab technology and process engineering brings you up to date every Tuesday and Thursday. The latest industry news, product highlights and innovations - compact and easy to understand in your inbox. Researched by us so you don't have to.
“This is fundamentally new”
Groundbreaking innovation with high appeal for numerous potential customers in the core markets of battery electrolyte salts and agrochemicals
Aerleum raises $6M in seed round
Unique material created to solve a persistent failure problem
"For the first time, a solid-phase synthesis of COFs has been developed that works completely without solvents"
Sustainability in the focus of chemical research
A study opens up new ways to produce important chemical compounds
“2024 is our year – we've scaled up three products, secured investor backing, brought new talent onboard and successfully launched our first commercial application"
Researchers investigate the effectiveness of combustion processes
BASF is setting a new direction for portfolio steering, capital allocation and performance culture
Finding could help turn trees into affordable, greener industrial chemicals
Findings have possible implications for reproductive technologies
Higher diagnostic accuracy than standard tests
The new findings could contribute towards the development of new medical treatments
Europe's unique partnership accelerates research in healthy and sustainable nutrition
New DNA analyses spark controversy over origins
Investigation of the symbiosis between bacteria and birds leads to the discovery of new natural products with antimicrobial properties
34 years of innovation for an animal-friendly and sustainable future
Tattoo inks in Europe are mislabeled and some contain banned ingredients
Gustavo Gusto produces with a PV system from E.ON
Scientific milestone provides deeper insights into the evolution and biology of Octopus vulgaris
Study identifies key molecules and possible approaches to improve the vaccination response
Smart protection against food waste
Ethically safe, fast, cost-effective and reliable
Dysfunctional mitochondria disrupt the gut microbiome
Like building with Lego bricks
Already, Bacillus subtilis is indispensable in many industries, and many more innovations are expected
Brazil nuts can contain unusually high levels of radioactive radium
Inspired by nature - Light-controlled bio-based OptoAssays can diagnose diseases more easily and cost-effectively
Surprising discovery revealed an entirely new dimension to gene regulation
German Environmental Aid forces McDonald's to offer mandatory reusable packaging
Researchers analyse the effects
Luxembourg Institute of Health reveals critical link between fibre intake, gut bacteria, B vitamins and immune health
A new review study is the first to systematically show the harmful effects of nano- and microplastics on bees and other beneficial insects
DNA provides almost 32,000 species
The simple and cost-effective method developed using a few simple but effective tricks
Researchers find ground beef packs bigger muscle-building punch than soy-based alternative
By automating routine tasks, scientists can focus on higher-level research questions, paving the way for faster breakthroughs