KAIST employs image-recognition AI to determine battery composition and conditions
THE KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY (KAIST)
An international collaborative research team has developed an image recognition technology that can accurately determine the elemental composition and the number of charge and discharge cycles of a battery by examining only its surface morphology using AI learning.
KAIST (President Kwang-Hyung Lee) announced on July 2nd that Professor Seungbum Hong from the Department of Materials Science and Engineering, in collaboration with the Electronics and Telecommunications Research Institute (ETRI) and Drexel University in the United States, has developed a method to predict the major elemental composition and charge-discharge state of NCM cathode materials with 99.6% accuracy using convolutional neural networks (CNN)*.
*Convolutional Neural Network (CNN): A type of multi-layer, feed-forward, artificial neural network used for analyzing visual images.
The research team noted that while scanning electron microscopy (SEM) is used in semiconductor manufacturing to inspect wafer defects, it is rarely used in battery inspections. SEM is used for batteries to analyze the size of particles only at research sites, and reliability is predicted from the broken particles and the shape of the breakage in the case of deteriorated battery materials.
The research team decided that it would be groundbreaking if an automated SEM can be used in the process of battery production, just like in the semiconductor manufacturing, to inspect the surface of the cathode material to determine whether it was synthesized according to the desired composition and that the lifespan would be reliable, thereby reducing the defect rate.
< Figure 1. Example images of true cases and their grad-CAM overlays from the best trained network. >
The researchers trained a CNN-based AI applicable to autonomous vehicles to learn the surface images of battery materials, enabling it to predict the major elemental composition and charge-discharge cycle states of the cathode materials. They found that while the method could accurately predict the composition of materials with additives, it had lower accuracy for predicting charge-discharge states. The team plans to further train the AI with various battery material morphologies produced through different processes and ultimately use it for inspecting the compositional uniformity and predicting the lifespan of next-generation batteries.
Professor Joshua C. Agar, one of the collaborating researchers of the project from the Department of Mechanical Engineering and Mechanics of Drexel University, said, "In the future, artificial intelligence is expected to be applied not only to battery materials but also to various dynamic processes in functional materials synthesis, clean energy generation in fusion, and understanding foundations of particles and the universe."
Professor Seungbum Hong from KAIST, who led the research, stated, "This research is significant as it is the first in the world to develop an AI-based methodology that can quickly and accurately predict the major elemental composition and the state of the battery from the structural data of micron-scale SEM images. The methodology developed in this study for identifying the composition and state of battery materials based on microscopic images is expected to play a crucial role in improving the performance and quality of battery materials in the future."
< Figure 2. Accuracies of CNN Model predictions on SEM images of NCM cathode materials with additives under various conditions. >
This research was conducted by KAIST’s Materials Science and Engineering Department graduates Dr. Jimin Oh and Dr. Jiwon Yeom, the co-first authors, in collaboration with Professor Josh Agar and Dr. Kwang Man Kim from ETRI. It was supported by the National Research Foundation of Korea, the KAIST Global Singularity project, and international collaboration with the US research team. The results were published in the international journal npj Computational Materials on May 4. (Paper Title: “Composition and state prediction of lithium-ion cathode via convolutional neural network trained on scanning electron microscopy images”)
Figure 2. Accuracies of CNN Model predictions on SEM images of NCM cathode materials with additives under various conditions.
CREDIT
KAIST Materials Imaging and Integration Lab
JOURNAL
npj Computational Materials
METHOD OF RESEARCH
Meta-analysis
SUBJECT OF RESEARCH
Not applicable
ARTICLE TITLE
Composition and state prediction of lithium-ion cathode via convolutional neural network trained on scanning electron microscopy images
Novel strategy stabilizes zinc-ion batteries
HEFEI INSTITUTES OF PHYSICAL SCIENCE, CHINESE ACADEMY OF SCIENCES
According to research published in Energy Storage Materials recently, a team led by Prof. HU Linhua from Hefei Institutes of Physical Science of Chinese Academy of Sciences proposed a general principle through evaluating the highest occupied molecular orbital (HOMO) energy level of molecules and employed it as a critical descriptor to select non-sacrificial anionic surfactant electrolyte additives for stabilizing Zn anodes, realizing sustainable regulation effect with inhibited Zn dendrite growth and side-reactions.
"That means the anionic surfactant electrolyte additive sodium dodecyl benzene sulfonate (SDBS) with high HOMO energy level can stop harmful zinc dendrites from growing and make the batteries better at being recharged and reused," said Dr. LI ZHAO Qian, member of the team.
Aqueous zinc-ion batteries (AZIBs) have nowadays stimulated widespread attention for their safety, reliability, and cost-effectiveness. The severe Zn dendrite growth and severe side-reactions have become the major roadblock to the widespread commercialization of AZIBs. Anionic surfactants, as a category of typical non-sacrificial additives, have a long history of application in metallurgy as corrosion-inhibiting and deestering agents for Zn plating. Therefore, choosing a suitable anionic surfactant additive promises to fundamentally obtain highly stable and reversible metal anodes.
In this study, researchers proposed and demonstrated a general descriptor by evaluating HOMO energy level to select non-sacrificial surfactant additives of electrolyte for stabilizing Zn anodes. Three typical anionic surfactants molecules including SDBS, sodium dodecyl sulfonate (SDS), and sodium p-ethylbenzene sulfonate (SEBS) with non-sacrificial behaviors and different HOMO energy levels are chosen as additives, and the influence of HOMO energy levels on coordination and adsorption effects are investigated for the first time. Experimental and calculational results demonstrate that SDBS with the highest HOMO energy level exhibits the strongest coordination and adsorption effects, which extremely improves the stability and reversibility of Zn anode.
"The battery worked for over 3200 hours in the test, even at high power levels, which is 30 times longer than with the original electrolyte," explained Dr. LI Zhaoqian.
They also tested the battery with different materials and found that it worked well with them, even after many cycles. They assembled Zn//Cu batteries with average Coulomb efficiency of 98.15% after 800 cycles. Meanwhile, the Zn//NH4V4O10 full battery delivers a long-term stability with capacity retention of 93.5% after 8000 cycles.
This research provided a promising strategy for screening optimal electrolyte additives for high performance AZIBs, and was expected to be applied to other metal batteries, according to the team.
JOURNAL
Energy Storage Materials
ARTICLE TITLE
Non-sacrificial anionic surfactant with high HOMO energy level as a general descriptor for zinc anode
Battery4Life: New COMET centre for battery safety led by Graz University of Technology
Researchers will team up with national and international partners to make batteries safer, more sustainable and to extend their service life. The FFG, the provinces of Styria and Upper Austria and companies are investing about 19 million euros in total
GRAZ UNIVERSITY OF TECHNOLOGY
It is a great success for Graz University of Technology (TU Graz) and proof of the outstanding expertise of its researchers in the rapidly developing field of battery technology: the Austrian Research Promotion Agency FFG has approved the application for the new COMET K1 centre "Battery4Life". Together with international partners from science and industry, a team led by Christian Ellersdorfer from the Vehicle Safety Institute will work on improving the safety, service life and sustainability of batteries. The FFG is funding the project with a total of around 6.5 million euros, the Province of Styria is contributing 2.6 million euros and Upper Austria 0.6 million euros. In addition, the partners from the automotive and electronics industries are investing around nine million euros over the scheduled project term of four years.
By obtaining approval for the K1 centre Battery4Life, TU Graz is further expanding its position as Austria's most successful university in the FFG's COMET programme. "I am very pleased about the funding for Battery4Life," says TU Graz Rector Horst Bischof. "It demonstrates the outstanding expertise in battery research that we have been able to build up at Graz University of Technology together with industrial partners over many years. Together with the HyCentA hydrogen research centre, our Inffeld campus is becoming a hub for energy storage technology.
Safe battery operation over the entire life cycle
Driven by the expansion of e-mobility, the demand for batteries is increasing rapidly, and large sums of money are being invested in research projects worldwide to increase the capacity of batteries and develop new storage materials. " Given the large number of battery types, there is a growing need for research into their safe operation in a wide range of applications and throughout their entire life cycle," says Christian Ellersdorfer. The COMET centre Battery4Life builds on the COMET project SafeLIB in its work and can also draw on a state-of-the-art test centre in the field of battery safety (Battery Safety Center Graz) located at campus Inffeld. In the SafeLib project, the Institute for Vehicle Safety has developed new experimental approaches and virtual processes. The researchers want to further optimise these in Battery4Life and expand them to include artificial intelligence approaches in order to achieve even more precise predictions with a smaller number of experiments and less computing power.
Second lives for used batteries
The competence centre is also exploring methods to reliably assess the safety status of used batteries in particular. Suitable decommissioned batteries, for example from electric cars, could then be reused as stationary power storage units and would not have to be scrapped, which would greatly improve sustainability. When developing the assessment procedures, the researchers will take into account not only technical aspects but also economic efficiency and legal issues relating to data protection, warranty and liability.
Partners from eight countries
The scientific partners include a number of Graz University of Technology institutes as well as universities and research centres from Austria, Germany, Belgium, France, Switzerland and the USA. Corporate partners include AVL List, AVL DiTEST, Infineon, Fronius, Magna Steyr, Audi, BMW and Porsche.
Two other COMET centres received funding approval
In addition to Battery4Life, two existing COMET K1 centres in which TU Graz is involved have been awarded funding for a further four years: Pro2Future and the Polymer Competence Center Leoben.
This research is anchored in the Field of Expertise "Advanced Materials Science" and "Mobility & Production", two of five strategic foci of TU Graz.
No comments:
Post a Comment