• 1

Current Challenges of AI Standardisation in the Digitising Industry

Ovidiu Vermesan, Marcello Coppola, Reiner John, Cristina De Luca, Roy Bahr, Giulio Urlini

Abstract: The digital transformation of industrial sectors is highly dynamic, and stan- dardisation plays an essential role in achieving the objectives set for this transformation. In this context, AI standardisation efforts and industry AI efforts are intertwined. Industrial AI applications rely on standardisation to build and sustain trust in industrial AI. Conversely, standardisation relies on industrial AI applications to play an important role in forming emerging AI standards. Although the challenges involved differ from those of similar processes in the consumer market, AI standardisation a lever for the indus- try’s digitalisation journey. This article provides an overview of the role of AI standardisation in digitising industry and the related objectives, while presenting several requirements and challenges impacting standardisation. Furthermore, it summarises the AI standards landscape and activities within Standards Development Organisations (SDOs), outlines industrial stakehold- ers’ approaches, and provides recommendations for an AI standardisation roadmap (in which the industry should focus on AI standards work). Its con- cluding remarks relate to AI standardisation activities, priorities in industrial environments, and certification efforts to conceptualise new approaches to conformance and acceptance criteria.

Continue Reading

Aspects of Foreign Object Detection in a Wireless Charging System for Electric Vehicles Using Passive Inductive Sensors

Abstract: If the energy transfer for charging the traction battery of an electric vehicle takes place wirelessly and with inductive components, the active area of the charging system must be monitored for safety reasons for the presence or intrusion of metallic objects that do not belong to the charging system. In the past, different concepts for such monitoring have been described. In this paper, passive inductive sensors are used and characterized based on practical measurements. With this type of sensor, the detectability of metallic foreign objects is very closely related to the characteristics of the magnetic field of the charging system. By optimizing the geometry of the sensor coils, the authors show how foreign object detection can be improved even in areas with low excitation of the foreign objects and the sensor coils by the magnetic field. For this purpose, a charging system, with which charging powers of up to 10 kW have been realized in the past, and standardized test objects are used. Furthermore, the thermal behavior of the metallic test objects was documented, which in some cases heated up to about 300 °C and above in a few minutes in the magnetic field of the charging system. The results show the capability of passive inductive sensors to detect metallic foreign objects. Based on the measurements shown here, the next step will be to simulate the charging system and the foreign object detection in order to establish the basis for a virtual development and validation of such systems.

Continue Reading

MetaFS: Model-driven Fault Simulation Framework

Endri Kaja, Nicolas Gerlin, Monideep Bora, Keerthikumara Devarajegowda, Dominik Stoffel, Wolfgang Kunz, Wolfgang Ecker

Abstract: The adoption of new technologies by the automotive industry drives the need for electronic component suppliers to assess and scrutinize the risk of technologies that are being integrated into the safety-critical systems. To cope with these challenges, engineers are constantly looking for highly automated and efficient functional safety approaches to achieve the required certifications for their designs. In this paper, we propose MetaFS, a metamodel-based simulator-independent fault simulation framework that provides multi-purpose fault injection strategies such as statistical fault injection, direct fault injection, and exhaustive fault injection. The framework enables the injection of stuck-at faults, single-event transients, single-event upsets as well as timing faults. The proposed approach scales to a wide range of RISC-V based CPU subsystems with support for various RISC-V ISA standard extensions and, additional safety and security related custom instruction extensions. The subsystems were running the Dhrystone application and a specific in-house Fingerprint calculation application respectively. A minimal effort of 1 person-day was required to conduct 22 different fault simulation campaigns, providing significant data regarding subsystem failure rates.

Continue Reading

Fast and Accurate Model-Driven FPGA-based System-Level Fault Emulation

Endri Kaja, Nicolas Gerlin, Monideep Bora, Gabriel Rutsch, Keerthikumara Devarajegowda, Dominik Stoffel, Wolfgang Kunz, Wolfgang Ecker

Abstract: Safety-critical designs need to ensure reliable operations even under a hostile working environment with a certain degree of confidence. Continuous technology scaling has resulted in designs being more susceptible to the risk of failure. As a result, the safety requirements are constantly evolving and becoming more stringent. For validating and measuring the robustness of safety-critical designs, fault injection methods are employed within the design flows. To ensure safety requirements’ compliance, and at the same time to cope with the ever-increasing complexity of modern SoCs, the existing design flows become inadequate as the process is repetitive, time-tedious, and requires high manual efforts. In this paper, a fully automated, fast and accurate, fault emulation framework based on the FPGA platform is proposed that enables a high level of controllability and observability for fault injection. The approach uses model-driven engineering concepts and automates various fault injection campaigns, namely, statistical fault injection (SFI), direct fault injection (DFI), and exhaustive fault injection (EFI). A novel design architecture tailored for the FPGA platform is also proposed to improve the overall productivity of performing fault emulation. The proposed approach scales to a wide variety of RISC-V based CPU subsystems with varying complexity in size and features. The experimental results demonstrate a significant gain in the fault emulation performance by a factor of 2.75x to 47.57x when compared to the standard simulation-based fault injection methods..

Continue Reading

The Java2CSP Debugging Tool Utilizing Constraint Solving and Model-Based Diagnosis Principles

Franz Wotawa, Vlad Andrei Dumitru

Abstract: Localizing faults in programs and repairing them is considered a difficult, time-consuming, but necessary activity of software engineering to assure programs fulfilling their expected behavior during operation. In this paper, we introduce the Java2CSP debugging tool implementing the principles of model-based diagnosis for fault localization, which can be accessed over the internet using an ordinary web browser. Java2CSP makes use of a constraint representation of a program together with a failing test case for reporting debugging candidates. The tool supports a non-object-oriented subset of the programming language Java. Java2CSP is not supposed to be used in any production environment. Instead, the tool has been developed for providing a prototypical implementation of a debugger using constraints. We present the underlying foundations behind Java2CSP, discuss some preliminary results, and show how the tool can also be used for test case generation and other applications.

Continue Reading

Ethical Considerations and Trustworthy Industrial AI Systems

Ovidiu Vermesan, Cristina De Luca, Reiner John, Marcello Coppola, Björn Debaillie, Giulio Urlini

Abstract: The ethics of AI in industrial environments is a new field within applied ethics, with notable dynamics but no well-established issues and no standard overviews. It poses many more challenges than similar consumer and general business applications, and the digital transformation of industrial sectors has brought into the ethical picture even more considerations to address. This relates to integrating AI and autonomous learning machines based on neural networks, genetic algorithms, and agent architectures into manufacturing processes. This article presents the ethical challenges in industrial environments and the implications of developing, implementing, and deploying AI technologies and applications in industrial sectors in terms of complexity, energy demands, and environmental and climate changes. It also gives an overview of the ethical considerations concerning digitis- ing industry and ways of addressing them, such as potential impacts of AI on economic growth and productivity, workforce, digital divide, alignment with trustworthiness, transparency, and fairness. Additionally, potential issues concerning the concentration of AI tech- nology within only a few companies, human-machine relationships, and behavioural and operational misconduct involving AI are examined. Manufacturers, designers, owners, and operators of AI—as part of auton- omy and autonomous industrial systems—can be held responsible if harm is caused. Therefore, the need for accountability is also addressed, particularly related to industrial applications with non-functional requirements such as safety, security, reliability, and maintainability supporting the means of AI- based technologies and applications to be auditable via an assessment either internally or by a third party. This requires new standards and certification schemes that allow AI systems to be assessed objectively for compliance and results to be repeatable and reproducible. This article is based on work, findings, and many discussions within the context of the AI4DI project.

Continue Reading

A Passive Testing Approach using a Semi-Supervised Intrusion Detection Model for SCADA Network Traffic

Herbert Mühlburger, Franz Wotawa

Abstract: Worldwide cyber-attacks constantly threaten the security of available infrastructure relying on cyber-physical systems. Infrastructure companies use passive testing approaches such as anomaly-based intrusion detection systems to observe such systems and prevent attacks. However, the effectiveness of intrusion detection systems depends on the underlying models used for detecting attacks and the observations that may suffer from scarce data availability. Hence, we need research on a) passive testing methods for obtaining appropriate detection models and b) for analysing the impact of the scarceness of data for improving intrusion detection systems. In this paper, we contribute to these challenges. We build on former work on supervised intrusion detection of power grid substation SCADA network traffic where a real-world data set (APG data set) is available. In contrast to previous work, we use a semi-supervised model with recurrent neural network architectures (i.e., LSTM Autoencoders and sequence models). This model only considers samples of ordinary data traffic without attacks to learn an adequate detection model. We outline the underlying foundations regarding the machine learning approach used. Furthermore, we present and discuss the obtained experimental results and compare them with prior results on supervised machine learning approaches. The source code of this work is available at:https: //github.com/muehlburger/semi-supervised-intrusion-detection-scada

Continue Reading

Design of a Tightly-Coupled RISC-V Physical Memory Protection Unit for Online Error Detection

Nicolas Gerlin, Endri Kaja, Monideep Bora, Keerthikumara Devarajegowda, Dominik Stoffel, Wolfgang Kunz, Wolfgang Ecker

Abstract: While semiconductors are becoming more efficient generation after generation, the continuous technology scaling leads to numerous reliability issues due, amongst others, to variations in transistors characteristics, manufacturing defects, component wear-out, or interference from external and internal sources. Induced bit flips and stuck-at-faults can lead to a system failure. Security-critical systems often use Physical Memory Protection (PMP) modules to enforce memory isolation. The standard loosely-coupled approach eases the implementation but creates overhead in area and performance, limiting the number of protected areas and their size. While delivering great support against malicious software and induced faults, better performance would benefit safety tasks by preventing the program from jumping into an undesired region and giving wrong outputs.We propose a novel model-driven approach to resolve these limitations by generating a tightly-coupled RISC-V PMP, which reduces the impact of run-time reconfiguration. We also discuss guidelines on configuring a PMP to minimize the overhead on performance and memory, and provide an area estimation for each possible PMP design instance. We formally verified a RISC-V Core with a PMP and evaluated its performance with the Dhrystone Benchmark. The presented architecture shows a performance gain of about 3 times against the standard implementation. Furthermore, we observed that adding the PMP feature to a RISC-V SoC led to a negligible performance loss of less than 0.1% per thousand PMP reconfigurations..

Continue Reading

Contaminations on Lidar Sensor Covers: Performance Degradation Including Fault Detection and Modeling as Potential Applications

Birgit Schlager, Thomas Goelles, Stefan Muckenhuber, Daniel Watzenig

Abstract: Lidar sensors play an essential role in the perception system of automated vehicles. Fault Detection, Isolation, Identification, and Recovery (FDIIR) systems are essential for increasing the reliability of lidar sensors. Knowing the influence of different faults on lidar data is the first crucial step towards fault detection for lidar sensors in automated vehicles. We investigate the influences of sensor cover contaminations on the output data, i.e., on the lidar point cloud and full waveform. Different contamination types were applied (dew, dirt, artificial dirt, foam, water, and oil) and the influence on the output data of the single beam lidar RIEGL LD05-A20 and the automotive mechanically spinning lidar Ouster OS1-64 was evaluated. The LD05-A20 measurements show that dew, artificial dirt, and foam lead to unwanted reflections at the sensor cover. Dew, artificial dirt over the entire transmitter, and foam measurements lead to severe faults, i.e., complete sensor blindness. The OS1-64 measurements also show that dew can lead to almost complete sensor blindness. The results look promising for further studies on fault detection and isolation, since the different contamination types lead to different symptom combinations.

Continue Reading

Formally Modeling Autonomous Vehicles in LNT for Simulation and Testing

Lina Marsso, Radu Mateescu, Lucie Muller, Wendelin Serwe

Abstract: We present two behavioral models of an autonomous vehicle and its interaction with the environment. Both models use the formal modeling language LNT provided by the CADP toolbox. This paper discusses the modeling choices and the challenges of our autonomous vehicle models, and also illustrates how formal validation tools can be applied to a single component or the overall vehicle.

Continue Reading

Acknowledgement

ArchitectECA2030 has been accepted for funding within (ECSEL JU) in collaboration with the European Union’s H2020 Framework Programs under grant agreement No 877539.

The project will receive an ECSEL JU funding up to 4 M€ completed with national budgets from national funding authorities in Germany, Netherlands, Czech Republic, Austria and Norway.  

Project Facts

Short Name: ArchitectECA2030

Full Name: Trustable architectures with acceptable residual risk for the electric, connected and automated cars

Duration:  01/07/2020- 30/06/2023

Total Costs: ~ € 13,6 Mio.

Consortium: 20 partners from 8 countries

Coordinator: Infineon Technologies AG

Funding

 

Horizon 2020
Horizon 2020

 

    

National Funding

National Funding

 


Social

Twitter

Twitter

    

LinkedIn

LinkedIn

 

Information

Impress

Imprint

   

Impress

Privacy Policy


 


Contact

Twitter
Contact