Michael Hüebner

Prof. Dr. Michael Hüebner

Computer Engineering, Brandenburg University of Technology Cottbus-Senftenberg, Universitätsplatz 1, 01968 Senftenberg, Germany
orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
5 May 2022 in Sensors
Verified
Journal Article
Open access
PDF file
PSPriscile Suawa
Priscile Suawa
TMTenia Meisel
Tenia Meisel
MJMarcel Jongmanns
Marcel Jongmanns
Michael HüebnerMichael Hüebner
Michael Hüebner
MRMarc Reichenbach
Marc Reichenbach
Only with new sensor concepts in a network, which go far beyond what the current state-of-the-art can offer, can current and future requirements for flexibility, safety, and security be met. The combination of data from many sensors allows a richer representation of the observed phenomenon, e.g., system degradation, which can facilitate analysis and decision-making processes. This work addresses the topic of predictive maintenance by exploiting sensor data fusion and artificial intelligence-based analysis. With a dataset such as vibration and sound from sensors, we focus on studying paradigms that orchestrate the most optimal combination of sensors with deep learning sensor fusion algorithms to enable predictive maintenance. In our experimental setup, we used raw data obtained from two sensors, a microphone, and an accelerometer installed on a brushless direct current (BLDC) motor. The data from each sensor were processed individually and, in a second step, merged to create a solid base for analysis. To diagnose BLDC motor faults, this work proposes to use data-level sensor fusion with deep learning methods such as deep convolutional neural networks (DCNNs) for their ability to automatically extract relevant information from the input data, the long short-term memory method (LSTM), and convolutional long short-term memory (CNN-LSTM), a combination of the two previous methods. The results show that in our setup, sound signals outperform vibrations when used individually for training. However, without any feature selection/extraction step, the accuracy of the models improves with data fusion and reaches 98.8%, 93.5%, and 73.6% for the DCNN, CNN-LSTM, and LSTM methods, respectively, 98.8% being a performance that, according to our reading, has never been reached in the analysis of the faults of a BLDC motor without first going through the extraction of the characteristics and their fusion by traditional methods. These results show that it is possible to work with raw data from multiple sensors and achieve good results using deep learning methods without spending time and resources on selecting appropriate features to extract and methods to use for feature extraction and data fusion.

6 March 2020 in Journal of Electronic Testing
Verified
Journal Article
Closed access
PDF file
Ambika Prasad ShahAmbika Prasad Shah
Ambika Prasad Shah
SVSantosh Kumar Vishvakarma
Santosh Kumar Vishvakarma
Michael HüebnerMichael Hüebner
Michael Hüebner

10 January 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
SSSamuel Souza da Silva
Samuel Souza da Silva
MCMatheus Cardoso
Matheus Cardoso
LNLucas Giovani Nardo
Lucas Giovani Nardo
Erivelton NepomucenoErivelton Nepomuceno
Erivelton Nepomuceno
Michael HüebnerMichael Hüebner
Michael Hüebner
JAJanier Arias
Janier Arias
Chaotic systems have been applied in many applications involving instrumentation and measurements, such as in sensors and control systems, due to their pseudo-random proprieties. However, reproducing chaos in digital systems is challenging because of the dynamical degradation of chaotic digital systems and, consequently, their intrinsic periodic orbits. Many techniques have been employed to guarantee a sufficiently large period, making them suitable for such applications. Nevertheless, few papers pay attention to the effects of using different numerical representations on chaos degradation and, at the same time, keeping key design parameters, such as few logical resources and power consumption. Thus, this paper aims to provide a new hardware architecture for a chaos-based PRNG using the Half-Unit-Biased (HUB) format for fixed-point numbers by bi-coupling the tent map in conjunction with the Bernoulli map, causing a significant impact on its logical resources and performance. Results show that the HUB format is more effective than the standard fixed-point numerical representation and that the proposed approach is chaotic, with pseudo-randomness.

15 February 2021 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
FSFernando F. dos Santos
Fernando F. dos Santos
MBMarcelo Brandalero
Marcelo Brandalero
MSMichael B. Sullivan
Michael B. Sullivan
PBPedro M. Basso
Pedro M. Basso
Michael HüebnerMichael Hüebner
Michael Hüebner
PRPaolo Rech
Paolo Rech
Duplication with Comparison (DWC) is an effective software-level solution to improve the reliability of computing devices. However, it introduces performance and energy consumption overheads that could be unsuitable for high-performance computing or real-time safety-critical applications. In this article, we present Reduced-Precision Duplication with Comparison (RP-DWC) as a means to lower the overhead of DWC by executing the redundant copy in reduced precision. RP-DWC is particularly suitable for modern mixed-precision architectures, such as NVIDIA GPUs, that feature dedicated functional units for computing with programmable accuracy. We discuss the benefits and challenges associated with RP-DWC and show that the intrinsic difference between the mixed-precision copies allows for detecting most, but not all, errors. However, as the undetected faults are the ones that fall into the difference between precisions, they are the ones that produce a much smaller impact on the application output and, thus, might be tolerated. We investigate RP-DWC impact into fault detection, performance, and energy consumption on Volta GPUs. Through fault injection and beam experiment, using three microbenchmarks and four real applications, we show that RP-DWC achieves an excellent coverage (up to 86 percent) with minimal overheads (as low as 0.1 percent time and 24 percent energy consumption overhead).


6 December 2021 in IEEE Transactions on Emerging Topics in Computing
Verified
Journal Article
Open access
FFFlorian Fricke
Florian Fricke
MBMarcelo Brandalero
Marcelo Brandalero
SLSascha Liehr
Sascha Liehr
SKSimon Kern
Simon Kern
KMKlas Meyer
Klas Meyer
Michael HüebnerMichael Hüebner
Michael Hüebner
Mass Spectrometry (MS) and Nuclear Magnetic Resonance Spectroscopy (NMR) are valuable analytical and quality control methods for most industrial chemical processes as they provide information on the concentrations of individual compounds and by-products. These processes are traditionally carried out manually and by a specialist, which takes a substantial amount of time and prevents their utilization for real-time closed-loop process control. This article presents recent advances from two projects that use Artificial Neural Networks (ANNs) to address the challenges of automation and performance-efficient realizations of MS and NMR. In the first part, a complete toolchain has been realized to develop simulated spectra and train ANNs to identify compounds in MS. In the second part, a limited number of experimental NMR spectra have been augmented by simulated spectra, to train an ANN with better prediction performance and speed than state-of-the-art analysis. These results suggest that, in the context of the digital transformation of the process industry, we are now on the threshold of a strongly simplified use of MS and MRS and the accompanying data evaluation by machine-supported procedures, and can utilize both methods much wider for reaction and process monitoring or quality control.