Model-based Stochastic Error Propagation Analysis for Cyber-Physical Systems

Fabarisov, Tagir; Yusupova, Nafisa; Ding, Kai; Morozov, Andrey; Janschek, Klaus

doi:10.12700/aph.17.8.2020.8.2

Cited by 5 publications

(1 citation statement)

References 17 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Only resilient businesses are ready for the impending catastrophe. (Fabarisov, 2020) The Fourth Industrial Revolution is being fuelled by several factors that will influence its course, including:…”

Section: Resilience In Industry 40mentioning

confidence: 99%

Resilience 4.0: Charting the Path to the Future with a Literature Review

Di Nardo,

Gallab,

Salvatore

et al. 2023

Preprint

View full text Add to dashboard Cite

The Industry 4.0 represents new era of production, characterized by a deep integration between digital technologies and physical systems. Cyber physical systems, cyber resilience protection and workers' safety are key elements of this transformation. To ensure the benefits of Industry 4.0 realized in a secure way, it is crucial to focus on workers' safety, cyber resilience protection and human-centric and CPS systems security and privacy. However, to fully realize the potential of Industry 4.0, it is important to address these challenges and ensure that the benefits of digitalization are balanced with the needs of workers and the protection of critical infrastructure. The concept of Industry 5.0 is emerging as the next step in this evolution, emphasizing the importance of sustainability, human-centered design, and a focus on creating a better future for all.

show abstract

Section: Resilience In Industry 40mentioning

confidence: 99%

Resilience 4.0: Charting the Path to the Future with a Literature Review

Di Nardo,

Gallab,

Salvatore

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Navigating contemporary challenges and future prospects in digital industry evolution

Gallab,

Di Nardo,

Naciri

2024

Discov Appl Sci

View full text Add to dashboard Cite

The advent of the digital industry, also known as Industry 4.0 is a transformation period in manufacturing, where the integration of digital technologies with physical systems is underlined. This transformation is crucial for the pillars of cyber-physical systems (CPS), cyber resilience protection, and workers’ safety, which collectively from the cornerstone of Industry 4.0. Ensuring the secure exploitation of Industry 4.0’s advantages necessitates a dedicated focus on workers’ safety, cyber resilience protection, and the security and privacy of human-centric CPS systems. However, the full realization of Industry 4.0’s potential hinges upon effectively addressing these challenges and aligning the benefits of digitalization with the exigencies of worker well-being and safeguarding critical infrastructure. This study is a comprehensive literature review on this digital era, focusing on CPS, resilience, and workers’ safety. The review aims to summarise current research and advancements, offering insights for researchers, practitioners, and decision-makers. By identifying gaps in knowledge, the study lays the foundations for additional research and supports ongoing progress in the digital industry. Industry 4.0 embodies a new era of manufacturing integrating digital technologies with a focus on sustainability and human-centric design, supported by CPS, resilience, and worker’s safety. This necessitate addressing challenges to ensure benefits align with worker needs and infrastructure protection.

show abstract

Multi-agent deep reinforcement learning concept for mobile cyber-physical systems control

Петренко

Gurchinskiy

2021

E3S Web Conf.

View full text Add to dashboard Cite

High complexity of mobile cyber physical systems (MCPS) dynamics makes it difficult to apply classical methods to optimize the MCPS agent management policy. In this regard, the use of intelligent control methods, in particular, with the help of artificial neural networks (ANN) and multi-agent deep reinforcement learning (MDRL), is gaining relevance. In practice, the application of MDRL in MCPS faces the following problems: 1) existing MDRL methods have low scalability; 2) the inference of the used ANNs has high computational complexity; 3) MCPS trained using existing methods have low functional safety. To solve these problems, we propose the concept of a new MDRL method based on the existing MADDPG method. Within the framework of the concept, it is proposed: 1) to increase the scalability of MDRL by using information not about all other MCPS agents, but only about n nearest neighbors; 2) reduce the computational complexity of ANN inference by using a sparse ANN structure; 3) to increase the functional safety of trained MCPS by using a training set with uneven distribution of states. The proposed concept is expected to help address the challenges of applying MDRL to MCPS. To confirm this, it is planned to conduct experimental studies.

show abstract

Model-based Stochastic Error Propagation Analysis for Cyber-Physical Systems

Cited by 5 publications

References 17 publications

Resilience 4.0: Charting the Path to the Future with a Literature Review

Resilience 4.0: Charting the Path to the Future with a Literature Review

Navigating contemporary challenges and future prospects in digital industry evolution

Multi-agent deep reinforcement learning concept for mobile cyber-physical systems control

Contact Info

Product

Resources

About