20th IMEKO TC10 Conference on "Measurement for Diagnostics, Optimization and Control to Support Competitiveness and Innovation"

Session

Session 2: Artificial intelligence, machine learning and data science for Diagnostics, Optimization & Control

Session 2

28 Sept 2026, 14:00

Lisbon

Conveners

Session 2: Artificial intelligence, machine learning and data science for Diagnostics, Optimization & Control: Sessions Chair: Dr. Gustavo Esteves Coelho

• Gustavo Esteves Coelho (Laboratório Nacional de Engenharia Civil (LNEC))

Description

Session Chair: Dr. Gustavo Esteves Coelho

33. Fault location and identification in the RIAA equalizer based on the frequency analysis

Piotr Bilski (Warsaw University of Technology)

28/09/2026, 14:00

T5 - Artificial intelligence, machine learning and data science for Diagnostics, Optimization & Control.

Oral presentation

The paper presents the approach to diagnose
the RIAA equalizer, which is widely used in the high
quality audio industry during the music recording. As
the circuit is discrete, it is possible to select the partially
accessible nodes for response measurement, therefore
analysis of their usefulness for the fault location and
identification. The cumulative power of the response at
each node...

21. Single-Agent Reinforcement Learning in MultiAgent Production Environments: Effects of Action and Observation Overlap

Bence Pálvölgyi (HUN-REN SZTAKI)

28/09/2026, 14:20

T5 - Artificial intelligence, machine learning and data science for Diagnostics, Optimization & Control.

Oral presentation

Abstract – Reinforcement Learning (RL) has demonstrated strong performance in production and manufacturing systems, where decision processes can be modeled as single-agent environments with welldefined state and action spaces. However, more complex real-world production processes inherently involve multiple interacting entities, making MultiAgent Reinforcement Learning (MARL) the natural tool...

25. When Multimodal Fusion Fails: A Study of Pose-Vibration Fusion for Robot Fault Diagnosis

Zeqi Wei (Xi'an Jiaotong University), Prof. Ruqiang Yan (Xi'an Jiaotong University)

28/09/2026, 14:40

T5 - Artificial intelligence, machine learning and data science for Diagnostics, Optimization & Control.

Oral presentation

Industrial robots inevitably suffer from performance degradation and mechanical faults during long-term operation, making accurate fault diagnosis essential for ensuring system reliability and reducing maintenance costs. Recently, multimodal fault diagnosis methods have attracted increasing attention because multiple sensor modalities are generally assumed to provide complementary fault...

20. Parallelized Reinforcement Learning Environment for Industrial Production Optimization

Dr Zsolt Janos Viharos (Institute for Computer Science and Control (SZTAKI))

28/09/2026, 15:00

T5 - Artificial intelligence, machine learning and data science for Diagnostics, Optimization & Control.

Oral presentation

Abstract – Reinforcement Learning (RL) has shown strong potential in optimizing production and manufacturing systems, where complex decisionmaking processes can be modeled as sequential control problems. However, training RL agents in such environments is often computationally expensive and sensitive to stochasticity, leading to unstable learning dynamics and long convergence times. This paper...

16. Anomaly detection of ventilation fan by training a variational auto-encoder with current waveforms of brushless DC motor

Yuko Hiranaka

28/09/2026, 15:20

T3 - Condition monitoring and maintenance of industrial processes, plants and complex systems.

Oral presentation

Anomalies in motor-driven equipment can be detected potentially by measuring the current of the driving motor. We attempt to utilize unsupervised learning of motor current to detect load fluctuations and bearing anomalies in ventilation fans. By training a variational auto-encoder on the cyclic current waveforms of a motor under normal conditions, anomalies—such as deviations in cycle length,...

17. State of Charge Estimation of Energy Storage Systems using a Flexible Reward based Reinforcement Learning Approach

Dr Valentina Bianchi (Università di Parma)

28/09/2026, 15:40

Oral presentation

Abstract – A flexible reward-based reinforcement learning (RL) approach for the state of charge (SoC) estimation of energy storage systems (ESSs) i.e. a Lithium-ion battery (LiB) and a hybrid supercapacitor (HSC), is presented in this research. The data acquisition for the Panasonic 18650 LiB is carried out through constant current – constant voltage (CC-CV) procedure whereas, for the...