Previous Article in Journal
Fine-Tuning LLaMA2 for Summarizing Discharge Notes: Evaluating the Role of Highlighted Information
Previous Article in Special Issue
QiGSAN: A Novel Probability-Informed Approach for Small Object Segmentation in the Case of Limited Image Datasets
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
BDCC
Volume 10
Issue 1
10.3390/bdcc10010005
BDCC-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Machine Learning Based Impact Sensing Using Piezoelectric Sensors: From Simulated Training Data to Zero-Shot Experimental Application

by
Petros Gkertzos
1,*,
Johannes Gerritzen
2,
Constantinos Tsakonas
3,
Stefanos H. Panagiotou
3,
Athanasios Kotzakolios
1,
Ioannis Katsidimas
1,
Andreas Hornig
2,4,5,
Siavash Ghiasvand
4,
Maik Gude
2,
Vassilis Kostopoulos
1,* and
Sotiris Nikoletseas
3
1
Applied Mechanics & Vibrations Laboratory, Department of Mechanical Engineering and Aeronautics, University of Patras, Rio Campus, 26500 Patras, Greece
2
Institute of Lightweight Engineering and Polymer Technology (ILK), TUD Dresden University of Technology, Holbeinstraße 3, 01307 Dresden, Germany
3
Computer Engineering and Informatics Department, University of Patras, 26504 Patras, Greece
4
Center for Scalable Data Analytics and Artificial Intelligence Dresden/Leipzig (ScaDS.AI), TUD Dresden University of Technology, Strehlener Str. 14, 01069 Dresden, Germany
5
Department of Engineering Science, University of Oxford Parks Road, Oxford OX1 3PJ, UK
*
Authors to whom correspondence should be addressed.
Big Data Cogn. Comput. 2026, 10(1), 5; https://doi.org/10.3390/bdcc10010005
Submission received: 28 September 2025 / Revised: 6 December 2025 / Accepted: 17 December 2025 / Published: 23 December 2025
(This article belongs to the Special Issue Recent Advances in Machine Learning Methods for Imperfect Large-Scale Data)
Versions Notes

Abstract

Modern impact monitoring systems combine multiple inputs with machine learning (ML) models for impact detection, localization, and event assessment. Their accuracy relies on large, event-representative datasets, used for algorithmic development and ML model training. High-fidelity numerical models can provide augmented datasets by overcoming the cost and time limitations of experimental methods. This research presents an end-to-end numerical methodology for impact detection based on simulation (training) and experimental (testing) data. Initially, a finite element model (FEM) of our experimental setup utilizing piezoelectric transducer (PZT) sensors mounted on a thermoplastic plate is created. From the experimental impact signals, a few consistent cases are identified for feature extraction. A design of experiments explores the range of each parameter, and through surrogate optimization, the material and piezoelectric properties of the setup are determined. Subsequently, a virtual dataset, involving multiple impact cases, is created to train the ML models performing impact detection. Testing with experimental data shows results consistent with literature studies that used only experimental data for both training and testing. This work provides a systematic methodology for representative dataset generation and impact monitoring through ML, while addressing accurate FEM parameter identification from a few experimental tries.
Keywords: finite element model (FEM); impact sensing; piezoelectric transducer (PZT); parameter fitting; surrogate based optimization; machine learning finite element model (FEM); impact sensing; piezoelectric transducer (PZT); parameter fitting; surrogate based optimization; machine learning

Share and Cite

MDPI and ACS Style

Gkertzos, P.; Gerritzen, J.; Tsakonas, C.; Panagiotou, S.H.; Kotzakolios, A.; Katsidimas, I.; Hornig, A.; Ghiasvand, S.; Gude, M.; Kostopoulos, V.; et al. Machine Learning Based Impact Sensing Using Piezoelectric Sensors: From Simulated Training Data to Zero-Shot Experimental Application. Big Data Cogn. Comput. 2026, 10, 5. https://doi.org/10.3390/bdcc10010005

AMA Style

Gkertzos P, Gerritzen J, Tsakonas C, Panagiotou SH, Kotzakolios A, Katsidimas I, Hornig A, Ghiasvand S, Gude M, Kostopoulos V, et al. Machine Learning Based Impact Sensing Using Piezoelectric Sensors: From Simulated Training Data to Zero-Shot Experimental Application. Big Data and Cognitive Computing. 2026; 10(1):5. https://doi.org/10.3390/bdcc10010005

Chicago/Turabian Style

Gkertzos, Petros, Johannes Gerritzen, Constantinos Tsakonas, Stefanos H. Panagiotou, Athanasios Kotzakolios, Ioannis Katsidimas, Andreas Hornig, Siavash Ghiasvand, Maik Gude, Vassilis Kostopoulos, and et al. 2026. "Machine Learning Based Impact Sensing Using Piezoelectric Sensors: From Simulated Training Data to Zero-Shot Experimental Application" Big Data and Cognitive Computing 10, no. 1: 5. https://doi.org/10.3390/bdcc10010005

APA Style

Gkertzos, P., Gerritzen, J., Tsakonas, C., Panagiotou, S. H., Kotzakolios, A., Katsidimas, I., Hornig, A., Ghiasvand, S., Gude, M., Kostopoulos, V., & Nikoletseas, S. (2026). Machine Learning Based Impact Sensing Using Piezoelectric Sensors: From Simulated Training Data to Zero-Shot Experimental Application. Big Data and Cognitive Computing, 10(1), 5. https://doi.org/10.3390/bdcc10010005

Article Metrics

Back to TopTop