In this paper, machine learning techniques will be used to classify different PCB layouts given their electromagnetic frequency spectra. These spectra result from a simulated near-field measurement of electric field strengths at different locations. Measured values consist of real and imaginary parts (amplitude and phase) in X, Y and Z directions. Training data was obtained in the time domain by varying transmission line geometries (size, distance and signaling). It was then transformed into the frequency domain and used as deep neural network input. Principal component analysis was applied to reduce the sample dimension. The results show that classifying different designs is possible with high accuracy based on synthetic data. Future work comprises measurements of real, custom-made PCB with varying parameters to adapt the simulation model and also test the neural network. Finally, the trained model could be used to give hints about the error’s cause when overshooting EMC limits.

In this work, methods will be evaluated to numerically calculate the passive electrical parameters of planar coils. These parameters can then be used to optimize inductive applications such as wireless power transmission. The focus here will be on inductive localization, which uses high-frequency magnetic fields and the resulting induced voltage to provide localization through the coupling parameter mutual inductance. To achieve localization with high accuracy and best possible operation (resonance, signal strength, etc.), the coil parameters need to be well known. For this reason, some numerical methods for the calculation of these quantities are presented and validated. In addition, the physical effects are thereby considered in more detail, allowing the localization procedure to be better optimized compared to simulative black-box methods. The goal should be a dedicated simulation platform for planar coils to be able to develop training data for neural networks and to test and optimize localization algorithms.

In the manufacture of real wood products, defects can quickly occur during the production process. To quickly sort out these defects, a system is needed that finds damage in the irregularly structured surfaces of the product. The difficulty in this task is that each surface is visually different and no standard defects can be defined. Thus, damage detection using correlation does not work, so this paper will test different machine learning methods. To evaluate different machine learning methods, a data set is needed. For this reason, the available samples were recorded manually using a static fixed camera. Subsequently, the images were divided into sub-images, which resulted in a relatively small data set. Next, a convolutional neural network (CNN) was constructed to classify the images. However, this approach did not lead to a generalized solution, so the dataset was hashed using the a- and pHash. These hash values were then trained with a fully supervised system that will later serve as a reference model, in the semi-supervised learning procedures. To improve the supervised model and not have to label every data point, semi-supervised learning methods are used in the following. For this purpose, the CEAL method (wrapper method) is considered in the first and then the Π-Model (intrinsically semi-supervised).

In this publication important aspects for the implementation of inductive locating are explained. The miniaturized sensor platform called Sens-o-Spheres is used as an application of this locating method. The sensor platform is applied in bioreactors in order to obtain the environmental parameters, which makes a localization by magnetic fields necessary. Since the properties of magnetic fields in the localization area are very different from the wave characteristics, the principle of inductive localization is investigated in this publication and explained by using electrical equivalent circuit diagrams. Thereby, inductive localization uses the coupling or the mutual inductivities between coils, which is noticeable by an induced voltage. Therefore some properties and procedures are explained to extract the location of Sens-o-Spheres or other industrial sensor platforms from the couplings of the coils. One method calculates the location from an adapted ratio calculation and the other method uses neural networks and stochastic filters to obtain the results. In the end, these results are evaluated and compared.

During the industrial processing of materials for the manufacture of new products, surface defects can quickly occur. In order to achieve high quality without a long time delay, it makes sense to inspect the work pieces so that defective work pieces can be sorted out right at the beginning of the process. At the same time, the evaluation unit should come close the perception of the human eye regarding detection of defects in surfaces. Such defects often manifest themselves by a deviation of the existing structure. The only restriction should be that only matt surfaces should be considered here. Therefore in this work, different classification and image processing algorithms are applied to surface data to identify possible surface damages. For this purpose, the Gabor filter and the FST (Fused Structure and Texture) features generated with it, as well as the salience metric are used on the image processing side. On the classification side, however, deep neural networks, Convolutional Neural Networks (CNN), and autoencoders are used to make a decision. A distinction is also made between training using class labels and without. It turns out later that the salience metric are best performed by CNN. On the other hand, if there is no labeled training data available, a novelty classification can easily be achieved by using autoencoders as well as the salience metric and some filters.

In this publication, further elements of the newly developed inductive localization in the near field are presented. The advantage of inductive localization is the usage of the magnetic fields, which have a very low influence of non-metallic materials in the environment and thus follows good applications in the area of medicine and biochemistry. This allows a precise localization of sensor platforms in inhomogeneous mixtures of materials, where classical methods have major problems with inhomogeneous dielectric conductivity or density. The calculation of the localization of the searched object differs from other methods such as ultrasound or electromagnetic waves due to the source-free propagation of the magnetic field. Therefore, new mathematical evaluation methods and systematic adaptations are necessary, which are presented in this paper in circuit analysis. For this purpose, the exact circuit influences of one coil and the influence of another coil are investigated and which resonance circuit should be selected for both coils for a inductive localization with optimized signal strength.

In this publication, the near-field to far-field transformation using the self-built near-field scanner NFS3000 is examined with regard to its geometry. This device allows to measure electric and magnetic fields in small distances to the DUT (Device under Test) with high geometric precision and high sensitivity. Leading to a fast examination of EMC (Electromagnetic Compatibility) problems, because the electromagnetic properties are better understandable and therefore easier to solve than e.g. measurements in a far-field chamber. In addition, it is possible to extrapolate the near-fields into the far-field and to determine the radiation pattern of antennas and emitting objects. For this purpose, this paper deals with the basis of this transformation, the so-called surface equivalence theorem. This principle is then adapted to the measurement of near-field scanners and implemented accordingly. Due to the non-ideal design of the near-field scanner, the effects on a far-field transformation are finally presented and discussed.

This paper presents a new methodology by using a multiple coil array for energy transmission. The complex current strengths of the transmitting coil array are calculated by having the knowledge about of the mutual inductances and the symmetries of the transmitting coil array, so that its resulting magnetic field mainly penetrates only the receiving coil and is strongly attenuated outside. This method is used for an optimized wireless energy transmission but can also be implemented for other inductive applications.

For the measurement of process data in bioreactors, very small wireless sensors are currently under development to replace the conventional rod probes. The so-called Sens-o-Spheres measure the temperature and in future the oxygen content and the pH of fluids. In order to evaluate the distribution of the measured values within the process, it is necessary to locate the wireless sensors. Because of the small size of the sphere (diameter 8 mm), inhomogeneous ambient media and the size of the reactor (less than 2 m), an inductive locating by magnetic fields with a frequency of f = 13.56 MHz is necessary. Since the behaviour of the magnetic field is very different from that of the electromagnetic wave, new locating methods are required, which are presented in this paper.