TY - CHAP A1 - Gómez Zuluaga, Mauricio Andrés A1 - Ordikhani, Ahmad A1 - Bauer, Christoph A1 - Glösekötter, Peter T1 - Development and implementation of a neural network-based abnormal state prediction system for a piston pump T2 - IWANN2021 N2 - Piston pumps play a key role in factory automation and their availability is very critical for the smooth running of production processes. Modern installations, such as production plants and machines, are becoming increasingly complex. Therefore, the probability of a complete system failure due to a single critical component also increases. Maintenance processes with intelligent devices are therefore very important to achieve maximum economic efficiency and safety. Periodic or continuous monitoring of system components provides key information about the current physical state of the system, enabling early detection of emerging failures. Knowledge of future failures makes it possible to move from the concept of preventive maintenance to intelligent predictive maintenance. In this way, consequential damage and complete system failure can be avoided, maximizing system availability and safety. This paper reflects the development and implementation of a neural network system for abnormal state prediction of piston pumps. After a short introduction into piston pumps and their potential abnormal states, statistical and periodical analysis are presented. Then the design and implementation of suitable neural networks are discussed. Finally, a conclusion is drawn and the observed accuracies as well as potential next steps are discussed. KW - Development and implementation Y1 - 2021 SN - 978-3-030-85029-6 U6 - http://dx.doi.org/10.1007/978-3-030-85030-2_24 PB - Springer Nature Switzerland AG 2021 ER - TY - CHAP A1 - Rörup, Tim A1 - Glösekötter, Peter A1 - Pomares, Hector A1 - Ruiz, Ignacio T1 - Deep Learning Based Neural Network for Six-Class-Classification of Alzheimer's Disease Stages Based on MRI Images T2 - IWANN2021 N2 - State of the art classifiers split Alzheimer’s disease progression into a limited number of stages and use a comparatively small database. For the best treatment, it is desirable to have the highest resolution from the progression of the disease. This paper proposes a reliable deep convolutional neural network for the classification of six different Alzheimer’s disease stages based on Magnetic Resonance Imaging (MRI). The peculiarity of this paper is the introduction of a new, sixth, disease stage, and the large amount of data that has been taken into account. Additionally, not only the testing accuracy is analyzed, but also the robustness of the classifier to have feedback on how certain the neural network makes its predictions. KW - Deep Learning Y1 - 2021 U6 - http://dx.doi.org/10.1007/978-3-030-85030-2_1 SP - 3 EP - 14 PB - Springer International Publishing ER - TY - JOUR A1 - Löchte, Andre A1 - Rojas Ruiz, Ignacio A1 - Glösekötter, Peter T1 - Battery State Estimation with ANN and SVR Evaluating Electrochemical Impedance Spectra Generalizing DC Currents JF - Applied Sciences N2 - The demand for energy storage is increasing massively due to the electrification of transport and the expansion of renewable energies. Current battery technologies cannot satisfy this growing demand as they are difficult to recycle, as the necessary raw materials are mined under precarious conditions, and as the energy density is insufficient. Metal–air batteries offer a high energy density as there is only one active mass inside the cell and the cathodic reaction uses the ambient air. Various metals can be used, but zinc is very promising due to its disposability and non-toxic behavior, and as operation as a secondary cell is possible. Typical characteristics of zinc–air batteries are flat charge and discharge curves. On the one hand, this is an advantage for the subsequent power electronics, which can be optimized for smaller and constant voltage ranges. On the other hand, the state determination of the system becomes more complex, as the voltage level is not sufficient to determine the state of the battery. In this context, electrochemical impedance spectroscopy is a promising candidate as the resulting impedance spectra depend on the state of charge, working point, state of aging, and temperature. Previous approaches require a fixed operating state of the cell while impedance measurements are being performed. In this publication, electrochemical impedance spectroscopy is therefore combined with various machine learning techniques to also determine successfully the state of charge during charging of the cell at non-fixed charging currents. Keywords: electrochemical impedance spectroscopy; artificial neural networks; support vector regression; zinc-air battery; state estimation; state of charge KW - Battery State Estimation Y1 - 2021 SN - 978-84-1117-173-1 U6 - http://dx.doi.org/10.3390/app12010274 VL - 12 IS - 1 SP - 275 ER -