Fault detection at rotating machinery with the help of vibration sensors offers the possibility to detect damage to machines at an early stage and to prevent production downtimes by taking appropriate measures. The analysis of the vibration data using methods of machine learning promises a significant reduction in the associated analysis effort and a further improvement in diagnostic accuracy. Here we publish a dataset which is used as a basis for the development and evaluation of algorithms for unbalance detection. For this purpose, unbalances of various sizes were attached to a rotating shaft using a 3Dprinted holder. In a speed range from approx. 630 RPM to 2330 RPM, three sensors were used to record vibrations on the rotating shaft at a sampling rate of 4096 values per second. A development and an evaluation dataset are available for each unbalance strength. Using the dataset recorded in this way, fully connected and convolutional neural networks, Hidden Markov Models and Random Forest classifications on the basis of automatically extracted time series features were tested. With a prediction accuracy of 98.6 % on the evaluation dataset, the best result could be achieved with a fully-connected neural network that receives the scaled FFT-transformed vibration data as input.

Light-matter interaction with two-dimensional materials gained significant attention in recent years leading to the reporting of weak and strong coupling regimes, and effective nano-laser operation with various structures. Particularly, future applications involving monolayer materials in waveguide-coupled on-chip integrated circuitry and valleytronic nanophotonics require controlling, directing and optimizing photoluminescence. In this context, photoluminescence enhancement from monolayer transition-metal dichalcogenides on patterned semiconducting substrates becomes attractive. It is demonstrated in our work using focussed-ion-beam-etched GaP and monolayer WS 2 suspended on hexagonal-BN buffer sheets. We present a unique optical microcavity approach capable of both efficient in-plane and out-ofplane confinement of light, which results in a WS 2 photoluminescence enhancement by a factor of 10 compared to the unstructured substrate at room temperature. The key concept is the combination of interference effects in both the horizontal direction using a bull's-eye-shaped circular Bragg grating and in vertical direction by means of a multiple reflection model with optimized etch depth of circular air-GaP structures for maximum constructive interference effects of the applied pump and expected emission light.

A theoretical variation between the two distinct light–matter coupling regimes, namely weak and strong coupling, becomes uniquely feasible in open optical Fabry—Pérot microcavities with low mode volume, as discussed here. In combination with monolayers of transition-metal dichalcogenides (TMDCs) such as WS2, which exhibits a large exciton oscillator strength and binding energy, the room-temperature observation of hybrid bosonic quasiparticles, referred to as exciton–polaritons and characterized by a Rabi splitting, comes into reach. In this context, our simulations using the transfer-matrix method show how to tailor and alter the coupling strength actively by varying the relative field strength at the excitons’ position – exploiting a tunable cavity length, a transparent PMMA spacer layer and angle-dependencies of optical resonances. Continuously tunable coupling for future experiments is hereby proposed, capable of real-time adjustable Rabi splitting as well as switching between the two coupling regimes. Being nearly independent of the chosen material, the suggested structure could also be used in the context of light–matter-coupling experiments with quantum dots, molecules or quantum wells. While the adjustable polariton energy levels could be utilized for polariton-chemistry or optical sensing, cavities that allow working at the exceptional point promise the exploration of topological properties of that point.

Analyzing vibration data using deep neural networks is an effective way to detect damages in rotating machinery at an early stage. However, the black-box approach of these methods often does not provide a satisfactory solution because the cause of classifications is not comprehensible to humans. Therefore, this work investigates the application of the explainable AI (XAI) algorithms to convolutional neural networks for vibration-based condition monitoring. Thus, the three XAI algorithms GradCAM, LRP and LIME with a modified perturbation strategy are applied to classifications based on the Fourier transform as well as the order analysis of the vibration signal. The following visualization as frequency-RPM maps and order-RPM maps allows for an effective assessment of saliency values for variable periodicity of the data, which translates to a varying rotation speed of a real-world machine. To compare the explanatory power of the XAI methods, investigations are first carried out with a synthetic data set with known class-specific characteristics. Both a visual and a quantitative analysis of the resulting saliency maps are presented. Then, a real-world data set for vibration-based imbalance classification on an electric motor, which runs at a broad range of rotation speeds, is used. The results indicate that the investigated algorithms are each partially successful in providing sample-specific saliency maps which highlight class-specific features and omit features which are not relevant for classification.

Early damage detection and classification by condition monitoring systems is crucial to enable predictive maintenance of manufacturing systems and industrial facilities. Data analysis can be improved by applying machine learning algorithms and fusion of data from heterogenous sensors. This paper presents an approach for a step-wise integration of classifications gained from vibration and acoustic emission sensors in order to combine the information from signals acquired in the low and high frequency ranges. A test rig comprising a drive train and bearings with small artificial damages is used for acquisition of experimental data. The results indicate that an improvement of damage classification can be obtained using the proposed algorithm of combining classifiers for vibrations and acoustic emissions.

Chiral photonics opens new pathways to manipulate light–matter interactions and tailor the optical response of metasurfaces and ‐materials by nanostructuring nontrivial patterns. Chirality of matter, such as that of molecules, and light, which in the simplest case is given by the handedness of circular polarization, have attracted much attention for applications in chemistry, nanophotonics and optical information processing. The design of chiral photonic structures using two machine learning methods, the evolutionary algorithm, and neural network approach, for rapid and efficient optimization of optical properties for dielectric metasurfaces, is reported. The design recipes obtained for visible light in the range of transition‐metal dichalcogenide exciton resonances show a frequency‐dependent modification in the reflected light's degree of circular polarization, that is represented by the difference between left‐ and right‐circularly polarized intensity. Our results suggest the facile fabrication and characterization of optical nanopatterned reflectors for chirality‐sensitive light–matter coupling scenarios employing tungsten disulfide as possible active material with features such as valley Hall effect and optical valley coherence.

No abstract

No abstract