For the propose of increasing the reliability in hostile environment, techniques of fault diagnosis have been reported for three-phase voltage source inverter (VSI). Based on the average current Park's Vector method, this paper proposes a fuzzy-based fault diagnosis method for the VSI in the three-phase permanent-magnet synchronous motor drive. By utilizing the phase current information, the fault symptom variables are calculated by using the average current Park's Vector method. The fuzzy logic approach is applied to process the fault symptom variables and get the faulty information of power switches. Compared with other fuzzy logic methods, the fuzzy logic design, fuzzy inputs and fuzzy rules are different. The proposed fault diagnosis method can detect and locate not only the single or multiple open-circuit faults but also the intermittent faults in power switches, which can improve the reliability of the motor drive system. The effectiveness of the proposed method is validated by both simulation and experiments.

For the purpose of reducing cost and volume, as well as to increase reliability in hostile environments, techniques of reconstructing three-phase current through a single current sensor have been reported for a three-phase alternating current motor vector control system. Based on the phase current reconstruction method, this paper proposes a novel open-circuit fault diagnosis method for the low-power voltage source inverter in the three-phase permanent-magnet synchronous motor drive. Other than sampling the single dc-link current sensor, the zero voltage vector sampling method (ZVVSM) is adopted to implement the fault diagnosis. By placing the single current sensor at a special position, ZVVSM is able to sample current during the two zero voltage vectors and reconstruct the three-phase currents. The reconstructed three-phase currents are used to generate the diagnostic variables that can detect and locate the faulty power switches. The PWM modulation strategy remains unchanged in this method and the reconstructed phase currents are with less waveform distortion and less harmonic contents, which are suitable for the fault diagnosis. The effectiveness of the proposed method is verified by experiments.

Learning-Enabled Components (LECs), such as neural networks, are broadly employed in Cyber-Physical Systems (CPSs) to tackle a wide variety of complex tasks in high-uncertainty environments. However, the training dataset is inevitably incomplete, and Out-Of-Distribution (OOD) data not encountered during the LEC training may lead to erroneous predictions, jeopardizing the safety of the system. In this paper, we first analyze the causes of OOD data and define various types of OOD data in learning-enabled CPSs. We propose an approach to effectively detect OOD data for both classification and regression problems. The proposed approach incorporates the variational autoencoder for classification and regression model to the Inductive Conformal Anomaly Detection (ICAD) framework, enabling the detection algorithm to take into consideration not only the LEC inputs but also the LEC outputs. We evaluate the approach using extensive experiments for both classification and regression tasks, and the experimental results validate the effectiveness of the proposed method for detecting different types of OOD data. Furthermore, the execution time of detection is relatively short; therefore, the proposed approach can be used for real-time detection.

Detection of deception attacks is pivotal to ensure the safe and reliable operation of cyber-physical systems (CPS). Detection of such attacks needs to consider time-series sequences and is very challenging especially for autonomous vehicles that rely on high-dimensional observations from camera sensors. The paper presents an approach to detect deception attacks in real-time utilizing sensor observations, with a special focus on high-dimensional observations. The approach is based on inductive conformal anomaly detection (ICAD) and utilizes a novel generative model which consists of a variational autoencoder (VAE) and a recurrent neural network (RNN) that is used to learn both spatial and temporal features of the normal dynamic behavior of the system. The model can be used to predict the observations for multiple time steps, and the predictions are then compared with actual observations to efficiently quantify the nonconformity of a sequence under attack relative to the expected normal behavior, thereby enabling real-time detection of attacks using high-dimensional sequential data. We evaluate the approach empirically using two simulation case studies of an advanced emergency braking system and an autonomous car racing example, as well as a real-world secure water treatment dataset. The experiments show that the proposed method outperforms other detection methods, and in most experiments, both false positive and false negative rates are less than 10%. Furthermore, execution times measured on both powerful cloud machines and embedded devices are relatively short, thereby enabling real-time detection.

Cyber-physical systems (CPSs) use learning-enabled components (LECs) extensively to cope with various complex tasks under high-uncertainty environments. However, the dataset shifts between the training and testing phase may lead the LECs to become ineffective to make large-error predictions, and further, compromise the safety of the overall system. In our paper, we first provide the formal definitions for different types of dataset shifts in learning-enabled CPS. Then, we propose an approach to detect the dataset shifts effectively for regression problems. Our approach is based on the inductive conformal anomaly detection and utilizes a variational autoencoder for regression model which enables the approach to take into consideration both LEC input and output for detecting dataset shifts. Additionally, in order to improve the robustness of detection, layer-wise relevance propagation (LRP) is incorporated into our approach. We demonstrate our approach by using an advanced emergency braking system implemented in an open-source simulator for self-driving cars. The evaluation results show that our approach can detect different types of dataset shifts with a small number of false alarms while the execution time is smaller than the sampling period of the system.