An increasing number of unhardened commercial-off-the-shelf embedded devices are deployed under harsh operating conditions and in highly-dependable systems. Due to the mechanisms of hardware degradation that affect these devices, ageing detection and monitoring are crucial to prevent critical failures. In this paper, we empirically study the propagation delay of 298 naturally-aged FPGA devices that are deployed in the European XFEL particle accelerator. Based on in-field measurements, we find that operational devices show significantly slower switching frequencies than unused chips, and that increased gamma and neutron radiation doses correlate with increased hardware degradation. Furthermore, we demonstrate the feasibility of developing machine learning models that estimate the switching frequencies of the devices based on historical and environmental data.

Ageing detection and failure prediction are essential in many Internet of Things (IoT) deployments, which operate huge quantities of embedded devices unattended in the field for years. In this paper, we present a large-scale empirical analysis of natural SRAM wear-out using 154 boards from a generalpurpose testbed. Starting from SRAM initialization bias, which each node can easily collect at startup, we apply various metrics for feature extraction and experiment with common machine learning methods to predict the age of operation for this node. Our findings indicate that even though ageing impacts are subtle, our indicators can well estimate usage times with an R2score of 0.77 and a mean error of 24% using regressors, and with an Fl score above 0.6 for classifiers applying a six-months resolution.

Anomaly detection algorithms solve the problem of identifying unexpected values in data sets. Such algorithms have been classically used for cleaning unlabelled data sets from potentially unwanted values. However, the ability to detect outlying values in data sets can also be used to detect anomalies in systems. Semi-supervised anomaly detection algorithms learn from data for known correct behavior. Such algorithms have been used in various fields, e.g., system security, fault detection, medical applications.In this paper, we use the Area Under the Receiver Operating Characteristic (AUROC) score to evaluate algorithms for semi-supervised anomaly detection when applied to high-integrity distributed digital systems. We identify the relevant parameter for each algorithm and observe how the parameter influences the score and the runtime.

High precision temperature control of the RF GUN is necessary to optimally accelerate thousands of electrons within the injection part of the European X-ray free-electron laser XFEL and the Free Electron Laser FLASH. A difference of the RF GUN temperature from the reference value of only 0.01 K leads to detuning of the cavity and thus limits the performance of the whole facility. Especially in steady-state operation there are some undesired temperature oscillations when using classical standard control techniques like PID control. That is why a model based approach is applied here to design the RF GUN temperature controller for the free-electron lasers. A thermal model of the RF GUN and the cooling facility is derived based on heat balances, considering the heat dissipation of the Low-Level RF power. This results in a nonlinear model of the plant. The parameters are identified by fitting the model to data of temperature, pressure and control signal measurements of the FLASH facility, a pilot test facility for the European XFEL. The derived model is used for controller design. A linear model predictive controller was implemented in MATLAB/Simulink and tuned to stabilize the temperature of the RF GUN in steady-state operation. A test of the controller in simulation shows promising results.