Fault monitoring and diagnostics are important to ensure reliability of electric motors. Efficient algorithms for fault detection improve reliability, yet development of cost-effective and reliable classifiers for diagnostics of equipment is challenging, in particular due to unavailability of well-balanced datasets, with signals from properly functioning equipment and those from faulty equipment. Thus, we propose to use a Bayesian neural network to detect and classify faults in electric motors, given its efficacy with imbalanced training data. The performance of the proposed network is demonstrated on real life signals, and a robustness analysis of the proposed solution is provided.

This study introduces a stochastic model designed to evaluate the long-term degradation of Electronic Security Systems (ESS) as critical components of Physical Protection Systems (PPS). Recognizing the significant financial investments in security systems and the evolving nature of threats, our model aims to provide a more dynamic assessment of PPS effectiveness over time. Traditional methodologies, such as the Estimated Adversary Sequence Interruption (EASI), often overlook the degradation factor, potentially leading to mismanagement and increased vulnerability. Our model incorporates various stochastic parameters, including aging, adversary knowledge growth, and technological improvements, to simulate the decline in system effectiveness. We present a comprehensive computational framework using Python, demonstrating the model’s application through a case study involving different ESS components with varied ages. The results highlight the necessity for proactive maintenance strategies and dynamic policy-making to sustain PPS effectiveness. This paper underscores the importance of integrating degradation factors into PPS evaluation to enhance security infrastructure management against evolving threats.

Teaching in pandemic was a challenge for everyone. Keeping students interested in lectures was hard. Motivating them to laboratory work even more so. In this paper we present the case study of our successful course of numerical methods. We describe tools that we have used, its structure, and show survey results suggesting that we are doing something right. Objectively, we can see that challenges of remote learning give an opportunity to reach for tools that are available and generate new qualities in teaching.