Markus Maier
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Markus Maier has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Alisa Rupenyan
ETH Switzerland
3 shared publications - Konrad Wegener
Institute for Machine Tools and Manufacturing, Eidgenössische Technische Hochschule Zurich, 8092 Zurich, Switzerland
2 shared publications - Aldo Steinfeld
ETH Zurich
1 shared publication C. Bobst
Agathon AG, Gurzelenstr 1, CH-4512 Bellach, Switzerland
1 shared publication- Christian Bobst
Agathon AG, Bellach, Switzerland
1 shared publication Christopher Konig
Automatic Control Laboratory, ETH Zrich, Zrich, Switzerland
1 shared publication
Latest Publications
- 5 January 2026
- Published by Fuji Technology Press Ltd. in International Journal of Automation Technology
- Vol. 20 (1) , 57-77
Intelligent Grinding
Grinding is a process that still today largely depends on the skill and experience of the operator. For grinding, no generalized computer-aided manufacturing tool exists as for milling, and the grinding machine manufacturers have their proprietary process planning tools for the path planning. The success of a grinding process furthermore depends on a suitable conditioning of the grinding wheel and not only on the appropriate selection of the process parameters. Skilled operators are, on the one hand, capable of setting up the process in shorter time than their less skilled colleagues and with immediate success. Artificial intelligence, driven by sufficiently increased computational performance, is increasingly capable of handling manufacturing processes, particularly as these processes become more complicated and experience-based. Therefore, extending the machine’s ability towards what today is the task of the operator, namely process planning feeding the vision of “operator integrated” is a breakthrough in zero defect manufacturing and first part right for grinding processes. The paper conceptualizes an intelligent grinding machine that uses ontologies, applies rule-based planning tools, makes use of physical as well as autonomous modeling, and is capable of learning. Moreover, the processes of grinding and dressing are fully monitored so that a self-learning ability is provided. Learning is fed from different sources, from monitoring, from other machines requiring filters built on physical models, and from the operator with the ability to deal with incomplete, unstructured, and unreliable data. From this the way, how such a machine communicates with operators must be completely different than today. Research results and literature are provided to discuss the different aspects like machine state monitoring, process monitoring, and parameter selection for an optimized grinding process.
- 5 January 2026
- Published by Fuji Technology Press Ltd. in International Journal of Automation Technology
- Vol. 20 (1) , 57-77
Intelligent Grinding
Grinding is a process that still today largely depends on the skill and experience of the operator. For grinding, no generalized computer-aided manufacturing tool exists as for milling, and the grinding machine manufacturers have their proprietary process planning tools for the path planning. The success of a grinding process furthermore depends on a suitable conditioning of the grinding wheel and not only on the appropriate selection of the process parameters. Skilled operators are, on the one hand, capable of setting up the process in shorter time than their less skilled colleagues and with immediate success. Artificial intelligence, driven by sufficiently increased computational performance, is increasingly capable of handling manufacturing processes, particularly as these processes become more complicated and experience-based. Therefore, extending the machine’s ability towards what today is the task of the operator, namely process planning feeding the vision of “operator integrated” is a breakthrough in zero defect manufacturing and first part right for grinding processes. The paper conceptualizes an intelligent grinding machine that uses ontologies, applies rule-based planning tools, makes use of physical as well as autonomous modeling, and is capable of learning. Moreover, the processes of grinding and dressing are fully monitored so that a self-learning ability is provided. Learning is fed from different sources, from monitoring, from other machines requiring filters built on physical models, and from the operator with the ability to deal with incomplete, unstructured, and unreliable data. From this the way, how such a machine communicates with operators must be completely different than today. Research results and literature are provided to discuss the different aspects like machine state monitoring, process monitoring, and parameter selection for an optimized grinding process.
- 15 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 70 (2) , 2128-2138
Safety-Aware Cascade Controller Tuning Using Constrained Bayesian Optimization
This article presents an automated, model-free, data-driven method for the safe tuning of PID cascade controller gains based on Bayesian optimization. The optimization objective is composed of data-driven performance metrics and modeled using Gaussian processes. The safety requirement is imposed via a barrier-like term in the objective, which is introduced to account for operational changes in the system. We further introduce a data-driven constraint that captures the stability requirements from system data. Numerical evaluation shows that the proposed approach outperforms relay feedback autotuning and quickly converges to the global optimum, thanks to a tailored stopping criterion. We demonstrate the performance of the method through simulations and experiments. For experimental implementation, in addition to the introduced safety constraint, we integrate a method for automatic detection of the critical gains and extend the optimization objective with a penalty depending on the proximity of the current candidate points to the critical gains. The resulting automated tuning method optimizes system performance while ensuring stability and standardization.
- 15 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 70 (2) , 2128-2138
Safety-Aware Cascade Controller Tuning Using Constrained Bayesian Optimization
This article presents an automated, model-free, data-driven method for the safe tuning of PID cascade controller gains based on Bayesian optimization. The optimization objective is composed of data-driven performance metrics and modeled using Gaussian processes. The safety requirement is imposed via a barrier-like term in the objective, which is introduced to account for operational changes in the system. We further introduce a data-driven constraint that captures the stability requirements from system data. Numerical evaluation shows that the proposed approach outperforms relay feedback autotuning and quickly converges to the global optimum, thanks to a tailored stopping criterion. We demonstrate the performance of the method through simulations and experiments. For experimental implementation, in addition to the introduced safety constraint, we integrate a method for automatic detection of the critical gains and extend the optimization objective with a penalty depending on the proximity of the current candidate points to the critical gains. The resulting automated tuning method optimizes system performance while ensuring stability and standardization.
- 16 May 2020
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 108 (1-2) , 539-552
Self-optimizing grinding machines using Gaussian process models and constrained Bayesian optimization
- 16 May 2020
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 108 (1-2) , 539-552
Self-optimizing grinding machines using Gaussian process models and constrained Bayesian optimization
- 1 November 2019
- Published by MM Publishing, s.r.o. in MM Science Journal
- Vol. 2019 (04) , 3192-3199
SENSORS AS AN ENABLER FOR SELF-OPTIMIZING GRINDING MACHINES
Today, an operator performs experiments to adaptively select grinding process parameters using observations, expert knowledge, and rules of thumb. Self-optimizing grinding machines cannot use operator observations and must therefore extract enough information out of the grinding process. In this study, a holistic sensor set-up as foundation for self-optimizing machines are presented exemplarily for cup wheel grinding machines. In-process detection of grinding burn, based on temperature and gas measurements, is tested and compared. Afterwards, the influence of input variables such as feed rate and cutting speed on grinding cost, grinding burn, and surface roughness are investigated.
- 1 November 2019
- Published by MM Publishing, s.r.o. in MM Science Journal
- Vol. 2019 (04) , 3192-3199
SENSORS AS AN ENABLER FOR SELF-OPTIMIZING GRINDING MACHINES
Today, an operator performs experiments to adaptively select grinding process parameters using observations, expert knowledge, and rules of thumb. Self-optimizing grinding machines cannot use operator observations and must therefore extract enough information out of the grinding process. In this study, a holistic sensor set-up as foundation for self-optimizing machines are presented exemplarily for cup wheel grinding machines. In-process detection of grinding burn, based on temperature and gas measurements, is tested and compared. Afterwards, the influence of input variables such as feed rate and cutting speed on grinding cost, grinding burn, and surface roughness are investigated.
- 1 August 2019
- Published by Elsevier in CIRP Journal of Manufacturing Science and Technology
- Vol. 26, 81-87
Bayesian optimization for autonomous process set-up in turning
- 1 August 2019
- Published by Elsevier in CIRP Journal of Manufacturing Science and Technology
- Vol. 26, 81-87
Bayesian optimization for autonomous process set-up in turning
- 14 July 2013
- Published by ASME International
Metal Oxide Reduction Using a Solar-Driven Vacuum Thermogravimeter
We present a kinetic study performed in a solar-driven vacuum thermogravimeter (solar-TG), in which solid reactants are directly exposed to high-flux irradiation while their weight change is continuously monitored. The system allows testing under a total vacuum pressure as low as 10 mbar. With this arrangement, the rate of thermochemical reactions can be examined under the same radiative heat transfer characteristics and heating rates typical of solar reactors. The solar-TG system is used to investigate metal oxides redox cycles for splitting H2O and CO2 and for high-temperature heat storage. Operation of the metal oxide reduction under vacuum pressures is of special interest because it eliminates the need for purge gas, thus simplifying the process and avoiding energy penalties associated with inert gas recycling.
- 14 July 2013
- Published by ASME International
Metal Oxide Reduction Using a Solar-Driven Vacuum Thermogravimeter
We present a kinetic study performed in a solar-driven vacuum thermogravimeter (solar-TG), in which solid reactants are directly exposed to high-flux irradiation while their weight change is continuously monitored. The system allows testing under a total vacuum pressure as low as 10 mbar. With this arrangement, the rate of thermochemical reactions can be examined under the same radiative heat transfer characteristics and heating rates typical of solar reactors. The solar-TG system is used to investigate metal oxides redox cycles for splitting H2O and CO2 and for high-temperature heat storage. Operation of the metal oxide reduction under vacuum pressures is of special interest because it eliminates the need for purge gas, thus simplifying the process and avoiding energy penalties associated with inert gas recycling.