Articles | Volume 10, issue 2
https://doi.org/10.5194/jsss-10-233-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/jsss-10-233-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Regular research article
| 
24 Aug 2021
Regular research article |
| 24 Aug 2021
| 24 Aug 2021
Influence of synchronization within a sensor network on machine learning results
ZeMA – Center for Mechatronics and Automation Technology gGmbH, Saarbrücken, Germany
Yannick Robin
Lab for Measurement Technology, Department of Mechatronics, Saarland University, Saarbrücken, Germany
Sascha Eichstädt
Physikalisch-Technische Bundesanstalt, Braunschweig and Berlin, Germany
Andreas Schütze
ZeMA – Center for Mechatronics and Automation Technology gGmbH, Saarbrücken, Germany
Lab for Measurement Technology, Department of Mechatronics, Saarland University, Saarbrücken, Germany
Tizian Schneider
ZeMA – Center for Mechatronics and Automation Technology gGmbH, Saarbrücken, Germany
Lab for Measurement Technology, Department of Mechatronics, Saarland University, Saarbrücken, Germany
Related authors
Tanja Dorst, Tizian Schneider, Sascha Eichstädt, and Andreas Schütze
J. Sens. Sens. Syst., 12, 45–60, https://doi.org/10.5194/jsss-12-45-2023, https://doi.org/10.5194/jsss-12-45-2023, 2023
Short summary
Short summary
A fundamental problem of machine learning (ML) is measurement uncertainty and the influence on ML results. Measurement uncertainty, which is critical in hazardous gas detection, is directly addressed in this paper. A previously published toolbox is extended for regression. One of the benefits of this approach is obtaining a better understanding of where the overall system should be improved. This can be achieved by either improving the trained ML model or using a sensor with higher precision.
Tanja Dorst, Tizian Schneider, Sascha Eichstädt, and Andreas Schütze
J. Sens. Sens. Syst., 12, 45–60, https://doi.org/10.5194/jsss-12-45-2023, https://doi.org/10.5194/jsss-12-45-2023, 2023
Short summary
Short summary
A fundamental problem of machine learning (ML) is measurement uncertainty and the influence on ML results. Measurement uncertainty, which is critical in hazardous gas detection, is directly addressed in this paper. A previously published toolbox is extended for regression. One of the benefits of this approach is obtaining a better understanding of where the overall system should be improved. This can be achieved by either improving the trained ML model or using a sensor with higher precision.
Tobias Baur, Manuel Bastuck, Caroline Schultealbert, Tilman Sauerwald, and Andreas Schütze
J. Sens. Sens. Syst., 9, 411–424, https://doi.org/10.5194/jsss-9-411-2020, https://doi.org/10.5194/jsss-9-411-2020, 2020
Short summary
Short summary
Applications like air quality, fire detection and detection of explosives require selective and quantitative measurements in an ever-changing background of interfering gases. One main issue hindering the successful implementation of gas sensors in real-world applications is the lack of appropriate calibration procedures for advanced gas sensor systems. This article presents a calibration scheme for gas sensors based on gas profiles with unique randomized gas mixtures.
Caroline Schultealbert, Iklim Uzun, Tobias Baur, Tilman Sauerwald, and Andreas Schütze
J. Sens. Sens. Syst., 9, 283–292, https://doi.org/10.5194/jsss-9-283-2020, https://doi.org/10.5194/jsss-9-283-2020, 2020
Short summary
Short summary
We present a work on gas sensors that can for example be used for the assessment of indoor air quality. These sensors suffer from deterioration by siloxanes, so we investigated these effects by a distinct operation mode and exposition to this gas that allows us to interpret different reactions on the sensor surface. We found that all processes on the sensor surface are slowed down by this treatment and a self-compensation by the evaluation of oxygen adsorption processes is likely to be found.
Marius Rodner, Manuel Bastuck, Andreas Schütze, Mike Andersson, Joni Huotari, Jarkko Puustinen, Jyrki Lappalainen, and Tilman Sauerwald
J. Sens. Sens. Syst., 8, 261–267, https://doi.org/10.5194/jsss-8-261-2019, https://doi.org/10.5194/jsss-8-261-2019, 2019
Short summary
Short summary
To fulfil today's requirements, gas sensors have to become more and more sensitive and selective. In this work, we present a novel method to significantly enhance the effect of gate bias on the response of a SiC field-effect transistor by placing a lithium-doped tungsten oxide film beneath the gate. This enhancement, compared to undoped samples, opens new perspectives for static and transient signal generation, e.g. gate bias-cycled operation, and, thus, increasing sensitivity and selectivity.
Henrik Lensch, Manuel Bastuck, Tobias Baur, Andreas Schütze, and Tilman Sauerwald
J. Sens. Sens. Syst., 8, 161–169, https://doi.org/10.5194/jsss-8-161-2019, https://doi.org/10.5194/jsss-8-161-2019, 2019
Short summary
Short summary
The measurement of humidity in industrial applications is still an important research issue. Especially under rough operation conditions the current humidity sensor comes to its limitations. To this end, we are developing an integrated sensor system using a metal oxide sensor with impedance spectroscopy as multi-signal generation allowing the discrimination of humidity and reducing gases. The submitted paper focuses on the modeling of the humidity-dependent aspects of impedance.
Manuel Bastuck, Tobias Baur, and Andreas Schütze
J. Sens. Sens. Syst., 7, 489–506, https://doi.org/10.5194/jsss-7-489-2018, https://doi.org/10.5194/jsss-7-489-2018, 2018
Short summary
Short summary
Predictions about systems too complex for physical modeling can be made nowadays with data-based models. Our software DAV³E is an easy way to extract relevant features from cyclic raw data, a process often neglected in other software packages, based on mathematical methods, incomplete physical models, or human intuition. Its graphical user interface further provides methods to fuse data from many sensors, to teach a model the prediction of new data, and to check the model’s performance.
Tobias Baur, Caroline Schultealbert, Andreas Schütze, and Tilman Sauerwald
J. Sens. Sens. Syst., 7, 411–419, https://doi.org/10.5194/jsss-7-411-2018, https://doi.org/10.5194/jsss-7-411-2018, 2018
Short summary
Short summary
A novel method for the detection of short pulses of gas at very low concentrations is presented. Applying the method to a doped SnO2 detector, gas pulses down to a dosage of 1 ppb times seconds can be detected. The gas transport inside the detector is simulated using the finite element method (FEM) to optimize the gas transport and to keep response and recovery time as short as possible. With this approach, we have demonstrated a detection limit for ethanol below 47 fg.
Andreas Schütze, Nikolai Helwig, and Tizian Schneider
J. Sens. Sens. Syst., 7, 359–371, https://doi.org/10.5194/jsss-7-359-2018, https://doi.org/10.5194/jsss-7-359-2018, 2018
Short summary
Short summary
“Industrie 4.0” or the Industrial Internet of Things (IIoT) describe the current (r)evolution in industrial automation and control. This is fundamentally based on smart sensors, which generate data and allow further functionality from self-monitoring and self-configuration to condition monitoring of complex processes. The paper reviews the development of sensor technology over the last 2 centuries and highlights some of the potential that can be achieved with smart sensors and data analysis.
Sascha Eichstädt, Clemens Elster, Ian M. Smith, and Trevor J. Esward
J. Sens. Sens. Syst., 6, 97–105, https://doi.org/10.5194/jsss-6-97-2017, https://doi.org/10.5194/jsss-6-97-2017, 2017
Short summary
Short summary
The challenges in the analysis of dynamic measurements significantly limit the use of existing calibration facilities and mathematical methodologies. Several international research projects have developed methodologies for the treatment of dynamic measurements at the NMI level. The transfer to industry, though, remains challenging. Therefore, this work provides a link from these activities to industrial end-users by means of the new versatile and comprehensive software package
PyDynamic.
Martin Leidinger, Joni Huotari, Tilman Sauerwald, Jyrki Lappalainen, and Andreas Schütze
J. Sens. Sens. Syst., 5, 147–156, https://doi.org/10.5194/jsss-5-147-2016, https://doi.org/10.5194/jsss-5-147-2016, 2016
Short summary
Short summary
For the application of indoor air quality monitoring, two types of tungsten oxide gas sensor layers were prepared via pulsed laser deposition. Analysis of the structure of the produced layers showed that they consist of nanoparticles and agglomerates of nanoparticles. The sensors showed significant sensitivity and selectivity towards naphthalene in the ppb concentration range. The results were achieved using temperature cycled operation of the sensors and pattern recognition signal treatment.
M. Schüler, T. Sauerwald, and A. Schütze
J. Sens. Sens. Syst., 4, 305–311, https://doi.org/10.5194/jsss-4-305-2015, https://doi.org/10.5194/jsss-4-305-2015, 2015
Short summary
Short summary
We study the effect of HMDSO vapor on an SnO2-based gas sensor in temperature cycled operation (TCO). The poisoning can be quantified at early stages with a resolution of ±85 ppm*min using TCO. This approach provides a simple method for early detection of HMDSO poisoning.
The stability of gas discrimination by linear discriminant analysis (LDA) can be improved using normalization, which in turn facilitates a more accurate determination of the poisoning state by hierarchical LDA discrimination.
B. Schmitt, C. Kiefer, and A. Schütze
J. Sens. Sens. Syst., 4, 239–247, https://doi.org/10.5194/jsss-4-239-2015, https://doi.org/10.5194/jsss-4-239-2015, 2015
Short summary
Short summary
A novel sensor principle for determining binary fluid mixtures of known components is presented. A bluff body is placed in the fluid channel, causing the formation of a stationary pair of vortices behind the body. The length of the vortex pair depends on the mixture’s viscosity and thus its composition. It is measured by placing a microheater in the vortex area and making use of forced convection which changes with the size of the vortices.
D. Puglisi, J. Eriksson, C. Bur, A. Schuetze, A. Lloyd Spetz, and M. Andersson
J. Sens. Sens. Syst., 4, 1–8, https://doi.org/10.5194/jsss-4-1-2015, https://doi.org/10.5194/jsss-4-1-2015, 2015
Short summary
Short summary
This study aims at the development of high-performance and cost-efficient gas sensors for sensitive detection of three specific hazardous gases, i.e., formaldehyde, naphthalene, and benzene, commonly present in indoor environments in concentrations of health concern. We used silicon carbide field effect transistors to investigate the sensor performance and characteristics under different levels of relative humidity up to 60%, demonstrating excellent detection limits in the sub-ppb range.
C. Bur, M. Bastuck, A. Schütze, J. Juuti, A. Lloyd Spetz, and M. Andersson
J. Sens. Sens. Syst., 3, 305–313, https://doi.org/10.5194/jsss-3-305-2014, https://doi.org/10.5194/jsss-3-305-2014, 2014
M. Leidinger, T. Sauerwald, W. Reimringer, G. Ventura, and A. Schütze
J. Sens. Sens. Syst., 3, 253–263, https://doi.org/10.5194/jsss-3-253-2014, https://doi.org/10.5194/jsss-3-253-2014, 2014
Short summary
Short summary
An approach for detecting hazardous volatile organic compounds (VOCs) in ppb and sub-ppb concentrations is presented. Using metal oxide semiconductor (MOS) gas sensors in temperature cycled operation, VOCs in trace concentrations are successfully identified against a varying ethanol background of up to 2 ppm. For signal processing, linear discriminant analysis is applied to single sensor data and sensor fusion data. Integrated gas sensor systems using the same MOS sensors were characterized.
M. Schüler, T. Sauerwald, and A. Schütze
J. Sens. Sens. Syst., 3, 213–221, https://doi.org/10.5194/jsss-3-213-2014, https://doi.org/10.5194/jsss-3-213-2014, 2014
T. Bley, E. Pignanelli, and A. Schütze
J. Sens. Sens. Syst., 3, 121–132, https://doi.org/10.5194/jsss-3-121-2014, https://doi.org/10.5194/jsss-3-121-2014, 2014
M. Bastuck, C. Bur, A. Lloyd Spetz, M. Andersson, and A. Schütze
J. Sens. Sens. Syst., 3, 9–19, https://doi.org/10.5194/jsss-3-9-2014, https://doi.org/10.5194/jsss-3-9-2014, 2014
Related subject area
Measurement systems: Sensor networks
Information reuse of nondestructive evaluation (NDE) data sets
Six-degree-of-freedom pose estimation with µm/µrad accuracy based on laser multilateration
A new wireless sensor interface using dual-mode radio
Temperature estimation of induction machines based on wireless sensor networks
Isolated sensor networks for high-voltage environments using a single polymer optical fiber and LEDs for remote powering as well as data transmission
Indoor localization: novel RSSI approach based on analytical solution and two receivers
A wireless communication system for energy and environmental monitoring
An 868 MHz 7.5 µW wake-up receiver with −60 dBm sensitivity
Combination of clustering algorithms to maximize the lifespan of distributed wireless sensors
SmartGate – connecting wireless sensor nodes to the Internet
Frank Leinenbach, Christopher Stumm, Fabian Krieg, and Aaron Schneider
J. Sens. Sens. Syst., 13, 99–108, https://doi.org/10.5194/jsss-13-99-2024, https://doi.org/10.5194/jsss-13-99-2024, 2024
Short summary
Short summary
Essential steps for the establishment of a data cycle were discussed, boundary conditions were defined and possible technological solutions for the achievement of the objective were presented. The subaspects mentioned are data generation, archiving, database extraction and reuse. A special focus was on the data format DICONDE, whose structuring and archiving techniques primarily address test data. In addition, two examples were presented in which this schema was implemented.
Jan Nitsche, Matthias Franke, Nils Haverkamp, and Daniel Heißelmann
J. Sens. Sens. Syst., 10, 19–24, https://doi.org/10.5194/jsss-10-19-2021, https://doi.org/10.5194/jsss-10-19-2021, 2021
Short summary
Short summary
The estimation of the six-degree-of-freedom position and orientation of an end effector is of high interest in industrial robotics. High precision and data rates are important requirements when choosing an adequate measurement system. In this work, a six-degree-of-freedom pose estimation setup based on laser multilateration is described together with the measurement principle and self-calibration strategies used in this setup. In an experimental setup, data rates of 200 Hz are achieved.
Felix Huening, Holger Heuermann, Franz-Josef Wache, and Rami Audisho Jajo
J. Sens. Sens. Syst., 7, 507–515, https://doi.org/10.5194/jsss-7-507-2018, https://doi.org/10.5194/jsss-7-507-2018, 2018
Short summary
Short summary
Wireless sensor systems gain more and more importance for modern
industry 4.0and
internet of thingsapplications. This paper introduces a new wireless communication system that enables real-time and highly robust wireless communication. Using this system makes it possible to transfer any digital bus system transparently. Based on a prototype, measurements and evaluations of the new systems are demonstrated.
Yi Huang and Clemens Gühmann
J. Sens. Sens. Syst., 7, 267–280, https://doi.org/10.5194/jsss-7-267-2018, https://doi.org/10.5194/jsss-7-267-2018, 2018
Short summary
Short summary
We focus on the implementation of monitoring algorithms for the induction machine in WSNs. As there are restrictions on the sensor node, such as low cost, low power, weak calculation and small memory size, the algorithm should be simple and efficient. The model-based method is used for the temperature estimation algorithm development. The experiments prove that the KF algorithm implementation is suitable for real-time temperature estimation on a wireless sensor node.
Jakob Fischer, Timo Schuster, Christian Wächter, Michael Luber, Juri Vinogradov, Olaf Ziemann, and Rainer Engelbrecht
J. Sens. Sens. Syst., 7, 193–206, https://doi.org/10.5194/jsss-7-193-2018, https://doi.org/10.5194/jsss-7-193-2018, 2018
Short summary
Short summary
Many applications in high-voltage environments require electrically isolated sensors. We demonstrate a purely optical sensor link using only low-cost high-brightness LEDs and only one polymer optical fiber (POF) for remote powering of isolated electronic sensor nodes of as well as for data transmission of sensor data to a central unit. No optical couplers or special photo diodes are required, to save costs and reduce size. This enables us to install sensor networks in the field with low effort.
Ahmad Warda, Bojana Petković, and Hannes Töpfer
J. Sens. Sens. Syst., 6, 375–380, https://doi.org/10.5194/jsss-6-375-2017, https://doi.org/10.5194/jsss-6-375-2017, 2017
Short summary
Short summary
The paper introduces a novel method for 2-D localization of a target in the indoor environment using the RSSI approach with only two sensors. The proposed method reduces the number of sensors by one compared to the trilateration method, which uses at least three sensors for 2-D localization. The achieved accuracy under the white Gaussian noise condition is about 3.4 cm as an average of all positions inside the considered simulated environment.
Dmytro Krush, Christoph Cammin, Ralf Heynicke, Gerd Scholl, and Bernd Kaercher
J. Sens. Sens. Syst., 6, 19–26, https://doi.org/10.5194/jsss-6-19-2017, https://doi.org/10.5194/jsss-6-19-2017, 2017
Short summary
Short summary
A new wireless communication system (WCS) for sensor-actuator communication has been developed to facilitate energy and environmental monitoring on the shop floor of industrial production sites. Its wireless technology is presented in detail. The WCS is able to efficiently use the available spectrum together with the other wireless systems around. Measured results for the coexistence capability are shown.
Sadok Bdiri, Faouzi Derbel, and Olfa Kanoun
J. Sens. Sens. Syst., 5, 433–446, https://doi.org/10.5194/jsss-5-433-2016, https://doi.org/10.5194/jsss-5-433-2016, 2016
Short summary
Short summary
To promote WSNs for IoT, energy consumption must be reduced to enable more applications. The power need by a sensor node is governed by the radio component. A wake-up receiver is an ultra-low-power radio receiver. It serves for idle listening whilst leaving the node in sleep state. The main research focus of WuRxs is to reduce energy usage and to improve sensitivity. In this work, active components are carefully used to construct a 7.5 µW WuRx with −60 dBm sensitivity and a latency of 10 ms.
Derssie D. Mebratu and Charles Kim
J. Sens. Sens. Syst., 5, 63–72, https://doi.org/10.5194/jsss-5-63-2016, https://doi.org/10.5194/jsss-5-63-2016, 2016
Short summary
Short summary
Many different techniques have been introduced in an effort to maximize heterogeneous wireless sensor lifespan, but these techniques have focused on having the nodes in a cluster send their data to a selected cluster head node that, in turn, reports the data to the base station. Therefore, the choice of the number of clusters and the way the cluster head node is selected are the main focuses of this research paper.
G. U. Gamm, S. Sester, and L. M. Reindl
J. Sens. Sens. Syst., 2, 45–50, https://doi.org/10.5194/jsss-2-45-2013, https://doi.org/10.5194/jsss-2-45-2013, 2013
Cited articles
Beyer, K., Goldstein, J., Ramakrishnan, R., and Shaft, U.: When Is “Nearest
Neighbor” Meaningful?, in: Database Theory – ICDT'99, Springer, Berlin, Heidelberg, 217–235, 1999. a
Dorst, T.: Sensor data set of 3 electromechanical cylinder at ZeMA testbed
(2 kHz), Zenodo [data set], https://doi.org/10.5281/zenodo.3929385, 2019. a, b
Dorst, T., Ludwig, B., Eichstädt, S., Schneider, T., and Schütze, A.:
Metrology for the factory of the future: towards a case study in condition
monitoring, in: 2019 IEEE International Instrumentation and Measurement
Technology Conference, Auckland, New Zealand, 439–443,
https://doi.org/10.1109/I2MTC.2019.8826973, 2019. a
Dorst, T., Eichstädt, S., Schneider, T., and Schütze, A.: Propagation of uncertainty for an Adaptive Linear Approximation algorithm, in: SMSI 2020 – Sensor and Measurement Science International, 366–367, https://doi.org/10.5162/SMSI2020/E2.3, 2020. a
Dorst, T., Robin, Y., Schneider, T., and Schütze, A.: Automated
35 ML Toolbox for Cyclic Sensor Data, in: MSMM 2021, Github [code], available at: https://github.com/ZeMA-gGmbH/LMT-ML-Toolbox (last access: 23 August 2021), 2021b. a
Duda, R. O., Hart, P. E., and Stork, D. G.: Pattern Classification, in: A
Wiley-Interscience publication, 2nd Edn., Wiley, New York, 2001. a
Eichstädt, S.: Publishable Summary for 17IND12 Met4FoF “Metrology for the Factory of the Future”, Zenodo [data set], https://doi.org/10.5281/zenodo.4267955, 2020. a
Eichstädt, S. and Wilkens, V.: GUM2DFT – a software tool for uncertainty evaluation of transient signals in the frequency domain, Meas. Sci. Technol., 27, 055001, https://doi.org/10.1088/0957-0233/27/5/055001, 2016. a
Guyon, I. and Elisseeff, A.: An Introduction to Variable and Feature Selection, J. Mach. Learn. Res., 3, 1157–1182, 2003. a
Helwig, N., Schneider, T., and Schütze, A.: MoSeS-Pro: Modular sensor systems for real time process control and smart condition monitoring using
XMR-technology, in: Proc. 14th Symposium Magnetoresistive Sensors and Magnetic Systems, 21–22 March 2017, Wetzlar, Germany, 2017. a
Kohavi, R.: A Study of Cross-Validation and Bootstrap for Accuracy Estimation
and Model Selection, in: Proceedings of the 14th International Joint Conference on Artificial Intelligence – Volume 2, IJCAI'95, Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 1137–1143, 1995. a
Kononenko, I. and Hong, S. J.: Attribute selection for modelling, Future
Generat. Comput. Syst., 13, 181–195, https://doi.org/10.1016/S0167-739X(97)81974-7, 1997. a
Mörchen, F.: Time series feature extraction for data mining using DWT and
DFT, Technical Report 33, Department of Mathematics and Computer Science, University of Marburg, Marburg, Germany, 1–31, 2003. a
Olszewski, R. T., Maxion, R. A., and Siewiorek, D. P.: Generalized feature
extraction for structural pattern recognition in time-series data, PhD thesis, Carnegie Mellon University, USA, 2001. a
Rakotomamonjy, A.: Variable Selection Using SVM-based Criteria, J. Mach. Learn. Res., 3, 1357–1370, https://doi.org/10.1162/153244303322753706, 2003. a
Robnik-Šikonja, M. and Kononenko, I.: Theoretical and Empirical Analysis
of ReliefF and RReliefF, Mach. Learn., 53, 23–69, https://doi.org/10.1023/A:1025667309714, 2003. a
Schneider, T., Helwig, N., and Schütze, A.: Automatic feature extraction and
selection for classification of cyclical time series data, tm – Technisches
Messen, 84, 198–206, https://doi.org/10.1515/teme-2016-0072, 2017. a, b
Schneider, T., Helwig, N., Klein, S., and Schütze, A.: Influence of Sensor Network Sampling Rate on Multivariate Statistical Condition Monitoring of Industrial Machines and Processes, Proceedings, 2, 781,
https://doi.org/10.3390/proceedings2130781, 2018a. a
Schneider, T., Helwig, N., and Schütze, A.: Industrial condition monitoring with smart sensors using automated feature extraction and selection, Meas. Sci. Technol., 29, 094002, https://doi.org/10.1088/1361-6501/aad1d4, 2018b. a, b, c, d
Schneider, T., Klein, S., Helwig, N., Schütze, A., Selke, M., Nienhaus,
C., Laumann, D., Siegwart, M., and Kühn, K.: Big data analytics using
automatic signal processing for condition monitoring | Big Data Analytik mit automatisierter Signalverarbeitung für Condition Monitoring, in:
Sensoren und Messsysteme – Beitrage der 19. ITG/GMA-Fachtagung, 26–27 June 2018, Nürnberg, 259–262, 2018c. a
Schütze, A., Helwig, N., and Schneider, T.: Sensors 4.0 – Smart sensors and measurement technology enable Industry 4.0, J. Sens. Sens. Syst., 7, 359–371, https://doi.org/10.5194/jsss-7-359-2018, 2018. a
Sivrikaya, F. and Yener, B.: Time synchronization in sensor networks: a
survey, IEEE Network, 18, 45–50, 2004. a
Teh, H. Y., Kempa-Liehr, A. W., and Wang, K. I.-K.: Sensor data quality: a
systematic review, J. Big Data, 7, 11, https://doi.org/10.1186/s40537-020-0285-1, 2020. a
Tirado-Andrés, F. and Araujo, A.: Performance of clock sources and their
influence on time synchronization in wireless sensor networks, Int. J. Distrib. Sens. Netw., 15, 1–16, https://doi.org/10.1177/1550147719879372, 2019. a
Usuga Cadavid, J. P., Lamouri, S., Grabot, B., Pellerin, R., and Fortin, A.:
Machine learning applied in production planning and control: a state-of-the-art in the era of industry 4.0, J. Intel. Manufact., 31, 1531–1558, https://doi.org/10.1007/s10845-019-01531-7, 2020. a
Wold, S., Esbensen, K., and Geladi, P.: Principal component analysis,
Chemometr. Intel. Labor. Syst., 2, 37–52, https://doi.org/10.1016/0169-7439(87)80084-9, 1987.
a
Wong, S. C., Gatt, A., Stamatescu, V., and McDonnell, M. D.: Understanding Data Augmentation for Classification: When to Warp?, in: 2016 International
Conference on Digital Image Computing: Techniques and Applications (DICTA),
30 November–2 December 2016, Gold Coast, QLD, Australia, 1–6, https://doi.org/10.1109/DICTA.2016.7797091, 2016. a
Yiğitler, H., Badihi, B., and Jäntti, R.: Overview of Time
Synchronization for IoT Deployments: Clock Discipline Algorithms and Protocols, Sensors, 20, 5928, https://doi.org/10.3390/s20205928, 2020. a
Short summary
Synchronization problems within distributed sensor networks are a major challenge in the field of Industry 4.0. In this paper, artificially generated time shifts between sensor data and their influence on remaining useful lifetime prediction of electromechanical cylinders are investigated. It is shown that time shifts within sensor data lead to poor remaining useful lifetime predictions. However, this prediction can be significantly improved using various methods as shown in this contribution.
Synchronization problems within distributed sensor networks are a major challenge in the field...
