Smart Manufacturing enabled by AI methods, digital twins, and semantic technologies
AI has a unique role in making manufacturing smarter and thus more agile, resource efficient, circular and "Invented for life".
Making manufacturing smarter with the help of AI, digital twins, and semantic technologies is my passion.
I have been with Bosch since 2018. My work aims at developing AI methods that combine -- via symbolic reasoning and machine learning -- manufacturing knowledge captured as semantic conceptual models, digital twins, and knowledge graphs with production data. Such methods allow us to enhance and democratize industrial data analytics and analyses as well as develop industrial AI solutions, for example, semantically-enhanced machine learning pipelines for monitoring discrete manufacturing operations. I aim for solutions that are based on solid theory and have high impact in Industry 4.0. I am active in international scientific and engineering communities. For example, I have more than 130 scientific publications and several of them were awarded with or nominated for the best paper award at top-tier venues. In 2021 I was ranked Nr 18 among ""AI 2000 Knowledge Engineering Most Influential Scholars"" according to AMiner. Moreover, I participate in publicly funded projects with multiple academic and industrial partners and currently I am running three projects like this at Bosch.
- Senior expert in AI methods for semantic digital twins and knowledge graphs. Bosch Center for Artificial Intelligence, Renningen (Germany)
- Research Scientist. Bosch Center for Artificial Intelligence, Renningen (Germany)
- Associate Professor, Department of Informatics, University of Oslo (Norway)
- Senior Research Fellow, University of Oxford (UK)
- Research Visits to Telecom Paris (France), INRIA Saclay (France), University of Oxford (UK), University of Edinburgh (UK)
- PhD in Computer Science, Free University of Bozen-Bolzano (Italy)
- MSc in Computational Logics, double-degree between TU Dresden (Germany) and Free University of Bozen-Bolzano (Italy)
- BSc in Mechanics and Mathematics, Novosibirsk State University (Russia)
Xu Zou, Qinkai Zheng, Yuxiao Dong, Xinyu Guan, Evgeny Kharlamov, Jialiang Lu, Jie TangTDGIA: Effective Injection Attacks on Graph Neural Networks
- KDD 2021: 2461-2471
Jialin Zhao, Yuxiao Dong, Ming Ding, Evgeny Kharlamov, Jie TangAdaptive Diffusion in Graph Neural Networks
- NeurIPS 2021
Wenzheng Feng, Jie Zhang, Yuxiao Dong, Yu Han, Huanbo Luan, Qian Xu, Qiang Yang, Evgeny Kharlamov, Jie TangGraph Random Neural Networks for Semi-Supervised Learning on Graphs
- NeurIPS 2020
Baifan Zhou, Yulia Svetashova, Andre Gusmao, Ahmet Soylu, Gong Cheng, Ralf Mikut, Arild Waaler, Evgeny KharlamovSemML: Facilitating development of ML models for condition monitoring with semantics
- J. Web Semant. Volume 71, November 2021
Interview with Evgeny Kharlamov
Senior expert in AI methods for semantic digital twins and knowledge graphs
Please tell us what fascinates you most about research.
I am fascinated with solving open problems to make the world a better place to live.
What makes research done at Bosch so special?
Bosch has a unique AI-centered goal: by 2025 all Bosch products should either contain AI or have been developed or manufactured with its help. This, and the fact that Bosch has more than 400 locations worldwide many of which are factories, provide a unique opportunity for researchers fascinated with smart and AI-powered manufacturing. This opportunity can be found in creating AI-based manufacturing solutions, deploying and evaluating them, and in making a real impact in manufacturing. Moreover, Bosch offers a unique infrastructure with everything researchers need to support their work. Note also that Bosch is a global provider of manufacturing solutions, thus the impact we have in Bosch goes global with Bosch products.
What research topics are you currently working on at Bosch?
My main research work is on AI-based methods with applications in automation and optimization of manufacturing processes. The methods I am developing combine symbolic representation and reasoning with machine learning. They allow one to account for both the manufacturing knowledge captured as semantic conceptual model, digital twins, and knowledge graphs and production data. My current research topics range from fundamental aspects of graph neural networks to standardization of semantic digital twins and end-user oriented tools to explore industrial data or to develop ML solutions over such data.
What are the biggest scientific challenges in your field of research?
The main scientific challenge in my area is a deep integration of symbolically represented domain knowledge that comes with logical reasoning and machine learning that comes with neural networks. Such integration will enable explainable and trustable AI-solutions which are vital for industry.
How do the results of your research become part of solutions "Invented for life"?
For Bosch Industry 4.0 and smart manufacturing are in the heart of technology “Invented for life” since they aim at production with a constant decrease of errors, resource consumption and CO2 emission.