Mihael Gudlin

Dr. Mihael Gudlin


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 March 2021 in Sensors
Verified
Journal Article
Open access
PDF file
DKDavor Kolar
Davor Kolar
DLDRAGUTIN LISJAK
DRAGUTIN LISJAK
Michał PająkMichał Pająk
Michał Pająk
Mihael GudlinMihael Gudlin
Mihael Gudlin
Intelligent fault diagnosis can be related to applications of machine learning theories to machine fault diagnosis. Although there is a large number of successful examples, there is a gap in the optimization of the hyper-parameters of the machine learning model, which ultimately has a major impact on the performance of the model. Machine learning experts are required to configure a set of hyper-parameter values manually. This work presents a convolutional neural network based data-driven intelligent fault diagnosis technique for rotary machinery which uses model with optimized hyper-parameters and network structure. The proposed technique input raw three axes accelerometer signal as high definition 1-D data into deep learning layers with optimized hyper-parameters. Input is consisted of wide 12,800 × 1 × 3 vibration signal matrix. Model learning phase includes Bayesian optimization that optimizes hyper-parameters of the convolutional neural network. Finally, by using a Convolutional Neural Network (CNN) model with optimized hyper-parameters, classification in one of the 8 different machine states and 2 rotational speeds can be performed. This study accomplished the effective classification of different rotary machinery states in different rotational speeds using optimized convolutional artificial neural network for classification of raw three axis accelerometer signal input. Overall classification accuracy of 99.94% on evaluation set is obtained with the CNN model based on 19 layers. Additionally, more data are collected on the same machine with altered bearings to test the model for overfitting. Result of classification accuracy of 100% on second evaluation set has been achieved, proving the potential of using the proposed technique.

30 January 2024 in Sustainability
Verified
Journal Article
Open access
PDF file
MHMiro Hegedić
Miro Hegedić
Mihael GudlinMihael Gudlin
Mihael Gudlin
MGMatija Golec
Matija Golec
Nataša TošanovićNataša Tošanović
Nataša Tošanović
Today’s businesses face a critical need to balance sustainability, environmental responsibility, and operational excellence. Integrating lean and green methodologies holds promise for achieving this balance but presents challenges in real-sector implementation. Despite extensive research in the scientific community, a universally accepted model for integrated lean and green implementation is lacking. Limited research also explores the impact of lean tools on environmental performance indicators. This study aims to identify key economic and environmental performance indicators and investigate how they are influenced by lean tools. The primary objective is to develop a decision-making model facilitating lean tool implementation based on a company’s priorities for economic and environmental performance. The methodology involves a literature review, complemented by questionnaires and interviews with experts from academia and the real sector. The findings show that commonly used lean tools positively influence economic and environmental indicators. The decision-making model, tailored to chosen criteria priorities, was successfully validated using simulated and real company data, which makes it a potentially valuable resource for companies navigating integrated lean and green methodologies. While the obtained results show promise, it is important to highlight the limitations arising from the regional focus on Croatia and the inclusion of a subset of the manufacturing industry.

1 January 2018 in Interdisciplinary Description of Complex Systems
Verified
Journal Article
Open access
MHMiro Hegedic
Miro Hegedic
Mihael GudlinMihael Gudlin
Mihael Gudlin

31 January 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Mihael GudlinMihael Gudlin
Mihael Gudlin
MHMiro Hegedić
Miro Hegedić
MGMatija Golec
Matija Golec
DKDavor Kolar
Davor Kolar
In the quest for industrial efficiency, human performance within manufacturing systems remains pivotal. Traditional time study methods, reliant on direct observation and manual video analysis, are increasingly inadequate, given technological advancements. This research explores the automation of time study methods by deploying deep learning models for action segmentation, scrutinizing the efficacy of various architectural strategies. A dataset, featuring nine work activities performed by four subjects on three product types, was collected from a real manufacturing assembly process. Our methodology hinged on a two-step video processing framework, capturing activities from two perspectives: overhead and hand-focused. Through experimentation with 27 distinctive models varying in viewpoint, feature extraction method, and the architecture of the segmentation model, we identified improvements in temporal segmentation precision measured with the F1@IoU metric. Our findings highlight the limitations of basic Transformer models in action segmentation tasks, due to their lack of inductive bias and the limitations of a smaller dataset scale. Conversely, the 1D CNN and biLSTM architectures demonstrated proficiency in temporal data modeling, advocating for architectural adaptability over mere scale. The results contribute to the field by underscoring the interplay between model architecture, feature extraction method, and viewpoint integration in refining time study methodologies.

22 June 2022 in Tehnički glasnik
Verified
Journal Article
Closed access
PDF file
MHMiro Hegedić
Miro Hegedić
Mihael GudlinMihael Gudlin
Mihael Gudlin
NŠNedeljko Štefanić
Nedeljko Štefanić
NTNataša Tošanović
Nataša Tošanović
AĐAnja Đenadija
Anja Đenadija
PGPetar Gregurić
Petar Gregurić
Accelerated technology developments caused by Industry 4.0 create problems in its implementation. One of the most important factors that hinder the transition of companies is ignorance and, therefore, the fear of new technologies present among employees. Learning factories have proven to be one of the best solutions for introducing employees to the technologies of Industry 4.0. Croatia is significantly behind in implementing the features of Industry 4.0, especially compared to more developed countries. To facilitate the transition of the Croatian industry to Industry 4.0, it is necessary to acquaint existing and future employees with its technologies through learning factories. There is currently only one learning factory in Croatia, which is too few. This paper presents the process of design and establishment of a learning factory at the Faculty of Mechanical Engineering and Naval Architecture in Zagreb, which facilitates research work and education of students and employees with Industry 4.0.

7 May 2025 in Tehnički glasnik
Verified
Journal Article
Open access
PDF file
DKDavor Kolar
Davor Kolar
DLDRAGUTIN LISJAK
DRAGUTIN LISJAK
Mihael GudlinMihael Gudlin
Mihael Gudlin
KMKarlo Miskovic
Karlo Miskovic
Predictive maintenance is essential for modern industrial systems, enabling early fault detection and efficient asset management. This paper presents an enhanced prognostic bearing test simulator that upgrades a laboratory platform for controlled accelerated degradation experiments. The system integrates a LabJack T7 Pro data acquisition unit with a web-based application, enabling automated data logging, structured storage, and remote visualization. These features reduce manual effort, improve data consistency, and enhance usability for real-time monitoring and experiment control. The developed platform supports diverse operating conditions and generates high-quality datasets for testing predictive maintenance strategies. The paper outlines the system architecture, data framework, and experimental validation, demonstrating its relevance for advancing diagnostics in rotating machinery.