The aim of the presented investigation is to explore the time gap between an anomaly appearance in continuously measured parameters of the device and a failure, related to the end of the remaining resource of the device-critical component. In this investigation, we propose a recurrent neural network to model the time series of the parameters of the healthy device to detect anomalies by comparing the predicted values with the ones actually measured. An experimental investigation was performed on SCADA estimates received from different wind turbines with failures. A recurrent neural network was used to predict the temperature of the gearbox. The comparison of the predicted temperature values and the actual measured ones showed that anomalies in the gearbox temperature could be detected up to 37 days before the failure of the device-critical component. The performed investigation compared different models that can be used for temperature time-series modeling and the influence of selected input features on the performance of temperature anomaly detection.

Misuse activity in computer networks constantly creates new challenges and difficulties to ensure data confidentiality, integrity, and availability. The capability to identify and quickly stop the attacks is essential, as the undetected and successful attack may cause losses of critical resources. The anomaly-based intrusion detection system (IDS) is a valuable security tool that is capable of detecting new, previously unseen attacks. Anomaly-based IDS sends an alarm when it detects an event that deviates from the behavior characterized as normal. This paper analyses the use of the histogram-based outlier score (HBOS) to detect anomalies in the computer network. Experimental results of different histogram creation methods and the influence of the number of bins on the performance of anomaly detection are presented. Experiments were conducted using an NSL-KDD dataset.

The total internal reflection ellipsometry (TIRE) method was used for the excitation and study of the sensitivity features of surface plasmon polariton (SPP) and Bloch surface waves (BSWs) resonances. For the BSWs generation distributed Bragg gratings were formed on the tops of the substrates (BK7 glass substrate), which had six bilayers of ~120 nm SiO₂ and ~40 nm TiO₂ and 40 nm of TiO₂ on the top. The SPP sample consisted of the BK7 glass prism and a gold layer (45 nm). Numerical calculations of the optical dispersions and the experimental TIRE data have shown that SPP resonance overtake the BSWs in wavelength scanning by a factor of about 17. However, for the ellipsometric parameters Ψ and Δ in the vicinity of excitations, the BSW sensitivity is comparable with SPP. The obtained resolutions were ${\Delta }_{SPP}=7.14\times {10}^{-6}RIU$ , ${\Psi }_{SPP}=1.7\times {10}^{-5}RIU$ for the SPP and ${\Delta }_{BSW}=8.7\times {10}^{-6}RIU$ , ${\Psi }_{BSW}=2.7\times {10}^{-5}RIU$ for the BSW. The capabilities of both surface excitations are discussed from the sensitivity point of view in the design of these advanced biosensors.

The modification of the proportional–integral (PI) controller with the variable proportional constant for tracking of the grid-connected photovoltaic microinverter output current has been proposed. The obtained results show that in the case when the proportional constant of the PI controller varies in time according to the appropriate law, the microinverter output current sinus shape distortions decrease as compared to the case when the ordinary PI controller is used. The operation of the microinverter with the proposed controller was investigated for the cases when the electrical grid voltage sinus shape is not distorted and when it is distorted by the higher harmonics.

The piezoelectric ringing phenomenon in Pockels cells based on the beta barium borate crystals was analyzed in this work. The investigation results show that piezoelectric ringing is caused by multiple high voltage pulses with a frequency in the range from 10 kHz up to 1 MHz. Experimental investigation of frequency response and Discrete Fourier transformation was used for analysis. The method of piezoelectric ringing investigation based on the analysis of difference of real and simulated optical signals spectrums was proposed. The investigations were performed for crystals with 3 × 3 × 25 mm, 4 × 4 × 25 mm and 4 × 4 × 20 mm dimensions. It was estimated that piezoelectric ringing in the beta barium borate crystal with dimensions of 3 × 3 mm × 25 mm occurred at the 150, 205, 445, 600 and 750 kHz frequencies of high voltage pulses.

The thyristor-controlled reactor (TCR) compensator for smooth asymmetric compensation of reactive power in a low-voltage utility grid is proposed in this work. Two different topologies of compensator were investigated: topology based on a single-cored three-phase reactor and topology with separate reactors for every phase. The investigation of the proposed TCR compensator was performed experimentally using a developed experimental test bench for 12 kVAr total reactive power. The obtained results show that employment of separate reactors for every phase allows us to control the reactive power in every phase independently, and that the TCR compensator with three single-phase reactors is suitable for smooth and asymmetric compensation of reactive power in a low-voltage utility grid.