Explore the vast range of titles available.

Perception sensors such as camera, radar, and lidar have gained considerable popularity in the automotive industry in recent years. In order to reach the next step towards automated driving it is necessary to implement fault diagnosis systems together with suitable mitigation solutions in automotive perception sensors. This is a crucial prerequisite, since the quality of an automated driving function strongly depends on the reliability of the perception data, especially under adverse conditions. This publication presents a systematic review on faults and suitable detection and recovery methods for automotive perception sensors and suggests a corresponding classification schema. A systematic literature analysis has been performed with focus on lidar in order to review the state-of-the-art and identify promising research opportunities. Faults related to adverse weather conditions have been studied the most, but often without providing suitable recovery methods. Issues related to sensor attachment and mechanical damage of the sensor cover were studied very little and provide opportunities for future research. Algorithms, which use the data stream of a single sensor, proofed to be a viable solution for both fault detection and recovery.

High voltage direct current (HVDC) transmission is an economical option for transmitting a large amount of power over long distances. Initially, HVDC was developed using thyristor-based current source converters (CSC). With the development of semiconductor devices, a voltage source converter (VSC)-based HVDC system was introduced, and has been widely applied to integrate large-scale renewables and network interconnection. However, the VSC-based HVDC system is vulnerable to DC faults and its protection becomes ever more important with the fast growth in number of installations. In this paper, detailed characteristics of DC faults in the VSC-HVDC system are presented. The DC fault current has a large peak and steady values within a few milliseconds and thus high-speed fault detection and isolation methods are required in an HVDC grid. Therefore, development of the protection scheme for a multi-terminal VSC-based HVDC system is challenging. Various methods have been developed and this paper presents a comprehensive review of the different techniques for DC fault detection, location and isolation in both CSC and VSC-based HVDC transmission systems in two-terminal and multi-terminal network configurations.

With the development of the new generation of information technology, artificial intelligence, cloud computing and big data are gradually becoming powerful engines of the smart grid. In recent years, people have been exploring how to reduce the dependence on human experience in the field of transmission line inspection. Therefore, transmission line inspection has attracted wide attention because of its high intelligence, flexibility and reliability. In this paper, we would like to present a survey on the intelligent transmission line inspection based on unmanned aerial vehicle (UAV). Firstly, the origin and development of intelligent electric power inspection are reviewed, and then the process of intelligent transmission line inspection and three key issues, i.e., path planning of UAV, trajectory tracking, and fault detection and diagnosis are presented in details. Finally, the challenges and future solutions are pointed out for power inspection.

Process fault detection and diagnosis (FDD) is a predominant task to ensure product quality and process reliability in modern industrial systems. Those traditional FDD techniques are largely based on diagnostic experience. These methods have met significant challenges with immense expansion of plant scale and large numbers of process variables. Recently, deep learning has become the newest trends in process control. The upsurge of deep neural networks (DNNs) in leaning highly discriminative features from complicated process data has provided practitioners with effective process monitoring tools. This paper is to present a review and full developing route of deep learning-based FDD in complex process industries. Firstly, the nature of traditional data projection-based and machine learning-based FDD methods is discussed in process FDD. Secondly, the characteristics of deep learning and their applications in process FDD are illustrated. Thirdly, these typical deep learning techniques, e.g., transfer learning, generative adversarial network, capsule network, graph neural network, are presented for process FDD. These DNNs will effectively solve these problems of fault detection, fault classification, and fault isolation in process. Finally, the developing route of DNN-based process FDD techniques is highlighted for future work.

Stochastic resonance (SR), as a noise-enhanced signal processing tool, has been extensively investigated and widely applied to mechanical fault detection. However, mechanical degradation process is continuous where the current value of a mechanical state variable, e.g., vibration, is highly dependent on its previous values, and the widely used SR methods in mechanical fault detection, mainly focusing on integer-order SR, neglect the dependence among the values of the mechanical state variable and are unable to utilize such a dependence to enhance weak fault characteristics embedded in a signal that records the values of the mechanical state variable as time varies. Inspired by fractional-order derivative that characterizes memory-dependent properties and reflects the high dependence between current and previous values of the state variable of a system, a second-order SR method enhanced by fractional-order derivative is developed to enhance weak fault characteristics for mechanical fault detection by using strong background noise, which is able to utilize the dependence among the values of a mechanical state variable to enhance weak fault characteristics embedded in a signal. Numerical analyses show that output signal-to-noise ratio (SNR) versus fractional order in the second-order bistable SR system induced by fractional-order derivative depicts a typical feature of SR. Even the second-order bistable SR system induced by fractional-order derivative is similar to the optimal moving filter by fine-tuning the system parameters and scaling factor. Experimental data including a bearing with slight flaking on the outer race and a gear with scuffing from wind turbine drivetrain are used to validate the feasibility of the proposed method. The experimental results indicate that the proposed method is able to not only suppress multiscale noise embedded in a signal but also enhance the benefits of noise to mechanical fault detection. In addition, the comparison with other advanced signal processing methods demonstrates that the proposed method outperforms the integer-order SR methods, even kurtogram and maximum correlated kurtosis deconvolution in extracting weak fault characteristics of machinery overwhelmed by strong background noise.

This paper proposes an H_/H fault detection observer method by using generalized output for a class of polytopic linear parameter-varying (LPV) systems. As the main contribution, with the aid of the relative degree of output, a new output vector is generated by gathering the original output and its time derivative, and it is feasible to consider H_ actuator fault sensitivity in the entire frequency for the new system. In order to improve actuator and sensor fault sensitivity as well as guarantee robustness against disturbances, simultaneously, an H_/H fault detection observer is designed for the new LPV polytopic system. Besides, the design conditions of the proposed observer are transformed into an optimization problem by solving a set of linear matrix inequalities (LMIs). Numerical simulations are provided to illustrate the effectiveness of the proposed method.

Solar energy has received great interest in recent years, for electric power generation. Furthermore, photovoltaic (PV) systems have been widely spread over the world because of the technological advances in this field. However, these PV systems need accurate monitoring and periodic follow-up in order to achieve and optimize their performance. The PV systems are influenced by various types of faults, ranging from temporary to permanent failures. A PV system failure poses a significant challenge in determining the type and location of faults to quickly and cost-effectively maintain the required performance of the system without disturbing its normal operation. Therefore, a suitable fault detection system should be enabled to minimize the damage caused by the faulty PV module and protect the PV system from various losses. In this work, different classifications of PV faults and fault detection techniques are presented. Specifically, thermography methods and their benefits in classifying and localizing different types of faults are addressed. In addition, an overview of recent techniques using different artificial intelligence tools with thermography methods is also presented.

Transient stability is important in power systems. Disturbances like faults need to be segregated to restore transient stability. A comprehensive review of fault diagnosing methods in the power transmission system is presented in this paper. Typically, voltage and current samples are deployed for analysis. Three tasks/topics; fault detection, classification, and location are presented separately to convey a more logical and comprehensive understanding of the concepts. Feature extractions, transformations with dimensionality reduction methods are discussed. Fault classification and location techniques largely use artificial intelligence (AI) and signal processing methods. After the discussion of overall methods and concepts, advancements and future aspects are discussed. Generalized strengths and weaknesses of different AI and machine learning-based algorithms are assessed. A comparison of different fault detection, classification, and location methods is also presented considering features, inputs, complexity, system used and results. This paper may serve as a guideline for the researchers to understand different methods and techniques in this field.

The development of information technology and process technology have been enhanced the rapid changes in high-tech products and smart manufacturing, specifications become more sophisticated. Large amount of sensors are installed to record equipment condition during the manufacturing process. In particular, the characteristics of sensor data are temporal. Most the existing approaches for time series classification are not applicable to adaptively extract the effective feature from a large number of sensor data, accurately detect the fault, and provide the assignable cause for fault diagnosis. This study aims to propose a multiple time-series convolutional neural network (MTS-CNN) model for fault detection and diagnosis in semiconductor manufacturing. This study incorporates data augmentation with sliding window to generate amounts of subsequences and thus to enhance the diversity and avoid over-fitting. The key features of equipment sensor can be learned automatically through stacked convolution-pooling layers. The importance of each sensor is also identified through the diagnostic layer in the proposed MTS-CNN. An empirical study from a wafer fabrication was conducted to validate the proposed MTS-CNN and compare the performance among the other multivariate time series classification methods. The experimental results demonstrate that the MTS-CNN can accurately detect the fault wafers with high accuracy, recall and precision, and outperforms than other existing multivariate time series classification methods. Through the output value of the diagnostic layer in MTS-CNN, we can identify the relationship between each fault and different sensors and provider valuable information to associate the excursion for fault diagnosis.

Sensor fault detection and isolation (SFDI) is a fundamental topic in unmanned aerial vehicle (UAV) development, where attitude estimation plays a key role in flight control systems and its accuracy is crucial for UAV reliability. In commercial drones with low maximum take-off weights, typical redundant architectures, based on triplex, can represent a strong limitation in UAV payload capabilities. This paper proposes an FDI algorithm for low-cost multi-rotor drones equipped with duplex sensor architecture. Here, attitude estimation involves two 9-DoF inertial measurement units (IMUs) including 3-axis accelerometers, gyroscopes and magnetometers. The SFDI algorithm is based on a particle filter approach to promptly detect and isolate IMU faulted sensors. The algorithm has been implemented on a low-cost embedded platform based on a Raspberry Pi board. Its effectiveness and robustness were proved through experimental tests involving realistic faults on a real tri-rotor aircraft. A sensitivity analysis was carried out on the main algorithm parameters in order to find a trade-off between performance, computational burden and reliability.