scholarly journals Challenges of Machine Learning Applied to Safety-Critical Cyber-Physical Systems

2020 ◽  
Vol 2 (4) ◽  
pp. 579-602
Author(s):  
Ana Pereira ◽  
Carsten Thomas
Keyword(s):  
Machine Learning ◽  
Autonomous Driving ◽  
Cyber Physical Systems ◽  
Shop Floor ◽  
Safety Engineering ◽  
Safety Hazards ◽  
Physical Systems ◽  
Safety Critical ◽  
Holistic Approaches ◽  
Transportation Vehicle

Machine Learning (ML) is increasingly applied for the control of safety-critical Cyber-Physical Systems (CPS) in application areas that cannot easily be mastered with traditional control approaches, such as autonomous driving. As a consequence, the safety of machine learning became a focus area for research in recent years. Despite very considerable advances in selected areas related to machine learning safety, shortcomings were identified on holistic approaches that take an end-to-end view on the risks associated to the engineering of ML-based control systems and their certification. Applying a classic technique of safety engineering, our paper provides a comprehensive and methodological analysis of the safety hazards that could be introduced along the ML lifecycle, and could compromise the safe operation of ML-based CPS. Identified hazards are illustrated and explained using a real-world application scenario—an autonomous shop-floor transportation vehicle. The comprehensive analysis presented in this paper is intended as a basis for future holistic approaches for safety engineering of ML-based CPS in safety-critical applications, and aims to support the focus on research onto safety hazards that are not yet adequately addressed.

scholarly journals Sharpening the Scythe of Technological Change: Socio-Technical Challenges of Autonomous and Adaptive Cyber-Physical Systems

Designs ◽  
2018 ◽  
Vol 2 (4) ◽  
pp. 52 ◽  
Author(s):  
Daniela Cancila ◽  
Jean-Louis Gerstenmayer ◽  
Huascar Espinoza ◽  
Roberto Passerone
Keyword(s):  
Artificial Intelligence ◽  
Cyber Physical Systems ◽  
Paradigm Change ◽  
Safety Engineering ◽  
Technical Aspects ◽  
Physical Systems ◽  
Safety Critical ◽  
New Knowledge ◽  
Self Adaptation

Autonomous and Adaptative Cyber-Physical Systems (ACPS) represent a new knowledge frontier of converging “nano-bio-info-cogno” technologies and applications. ACPS have the ability to integrate new `mutagenic’ technologies, i.e., technologies able to cause mutations in the society. Emerging approaches, such as artificial intelligence techniques and deep learning, enable exponential speedups for supporting increasingly higher levels of autonomy and self-adaptation. In spite of this disruptive landscape, however, deployment and broader adoption of ACPS in safety-critical scenarios remains challenging. In this paper, we address some challenges that are stretching the limits of ACPS safety engineering, including tightly related aspects such as ethics and resilience. We argue that a paradigm change is needed that includes the entire socio-technical aspects, including trustworthiness, responsibility, liability, as well as the ACPS ability to learn from past events, anticipate long-term threads and recover from unexpected behaviors.

scholarly journals Reliable Industry 4.0 Based on Machine Learning and IoT for Analyzing, Monitoring, and Securing Smart Meters

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 487 ◽  
Author(s):  
Mahmoud Elsisi ◽  
Karar Mahmoud ◽  
Matti Lehtonen ◽  
Mohamed M. F. Darwish
Keyword(s):  
Machine Learning ◽  
Smart Grids ◽  
Industry 4.0 ◽  
Learning Algorithm ◽  
Cyber Physical Systems ◽  
The Internet ◽  
Smart Meters ◽  
Industrial Environment ◽  
Physical Systems ◽  
Smart Machines

The modern control infrastructure that manages and monitors the communication between the smart machines represents the most effective way to increase the efficiency of the industrial environment, such as smart grids. The cyber-physical systems utilize the embedded software and internet to connect and control the smart machines that are addressed by the internet of things (IoT). These cyber-physical systems are the basis of the fourth industrial revolution which is indexed by industry 4.0. In particular, industry 4.0 relies heavily on the IoT and smart sensors such as smart energy meters. The reliability and security represent the main challenges that face the industry 4.0 implementation. This paper introduces a new infrastructure based on machine learning to analyze and monitor the output data of the smart meters to investigate if this data is real data or fake. The fake data are due to the hacking and the inefficient meters. The industrial environment affects the efficiency of the meters by temperature, humidity, and noise signals. Furthermore, the proposed infrastructure validates the amount of data loss via communication channels and the internet connection. The decision tree is utilized as an effective machine learning algorithm to carry out both regression and classification for the meters’ data. The data monitoring is carried based on the industrial digital twins’ platform. The proposed infrastructure results provide a reliable and effective industrial decision that enhances the investments in industry 4.0.

scholarly journals Graceful extensibility in asset management: extending the capacity to adapt in managing cyber-physical railway systems

2021 ◽  
Author(s):  
Jan-jaap Moerman ◽  
Jan Maarten Schraagen ◽  
Jan Braaksma ◽  
Leo van Dongen
Keyword(s):  
Asset Management ◽  
Adaptive Systems ◽  
New Technologies ◽  
Autonomous Driving ◽  
Cyber Physical Systems ◽  
Transportation Systems ◽  
Rolling Stock ◽  
Railway Transportation ◽  
Physical Systems ◽  
Railway Systems

AbstractGraceful extensibility has been recently introduced and can be defined as the ability of a system to extend its capacity to adapt when surprise events challenge its boundaries. It provides basic rules that govern adaptive systems. Railway transportation systems can be considered cyber-physical systems that comprise interacting digital, analog, physical, and human components engineered for safe and reliable railway transport. This enables autonomous driving, new functionalities to achieve higher capacity, greater safety, and real-time health monitoring. New rolling stock introductions require continuous adaptations to meet the challenges of these complex railway systems as an introduction takes several years to complete and deals with changing stakeholder demands, new technologies, and technical constraints which cannot be fully predicted in advance. To sustain adaptability when introducing new rolling stock, the theory of graceful extensibility might be valuable but needs further empirical testing to be useful in the field. This study contributes by assessing the proto-theorems of graceful extensibility in a case study in the railway industry by means of adopting pattern-matching analysis. The results of this study indicate that the majority of theoretical patterns postulated by the theory are corroborated by the data. Guidelines are proposed for further operationalization of the theory in the field. Furthermore, case results indicate the need to adopt management approaches that accept indeterminism as a complement to the prevailing deterministic perspective, to sustain adaptability and deal effectively with surprise events. As such, this study may serve other critical asset introductions dealing with cyber-physical systems in their push for sustained adaptability.

Sign in / Sign up

Export Citation Format

Share Document