Biblio

The error-resiliency of Artificial Intelligence (AI) hardware accelerators is a major concern, especially when they are deployed in mission-critical and safety-critical applications. In this paper, we propose a neuron fault tolerance strategy for Spiking Neural Networks (SNNs). It is optimized for low area and power overhead by leveraging observations made from a large-scale fault injection experiment that pinpoints the critical fault types and locations. We describe the fault modeling approach, the fault injection framework, the results of the fault injection experiment, the fault-tolerance strategy, and the fault-tolerant SNN architecture. The idea is demonstrated on two SNNs that we designed for two SNN-oriented datasets, namely the N-MNIST and IBM's DVS128 gesture datasets.

Continuous development of Internet of Things, big data and other emerging technologies has brought new challenges to the reliability of security-critical system products in various industries. Fault detection and evaluation in the early stage of software plays an important role in improving the reliability of software. However, fault prediction and evaluation, which are currently focused on the early stage of software, hardly provide high guidance for actual project development. In this study, a fault diagnosis method based on object-oriented Bayesian network (OOBN) is proposed. Starting from the time dimension and internal logic, a two-dimensional metric fault propagation model is established to calculate the failure rate of each early stage of software respectively, and the fault relationship of each stage is analyzed to find out the key fault units. In particular, it explores and validates the relationship between the failure rate of code phase and the failure caused by faults in requirement analysis stage and design stage in a train control system, to alert the developer strictly accordance with the industry development standards for software requirements analysis, design and coding, so as to reduce potential faults in the early stage. There is evidence that the study plays a crucial role to optimize the cost of software development and avoid catastrophic consequences.

Incipient faults are faults at their initial stages and occur before permanent faults occur. It is very important to detect incipient faults timely and accurately for the safe and stable operation of the power system. At present, most of the detection methods for incipient faults are designed for the detection of a single device’s incipient fault, but a unified detection for multiple devices cannot be achieved. In order to increase the fault detection capability and enable detection expandability, this paper proposes a waveform vector embedding (WVE) method to embed incipient fault waveforms of different devices into waveform vectors. Then, we utilize the waveform vectors and formulate them into a waveform dictionary. To improve the efficiency of embedding the waveform signature into the learning process, we build a loss function that prevents overflow and overfitting of softmax function during when learning power system waveforms. We use the real data collected from an IEEE Power & Energy Society technical report to verify the feasibility of this method. For the result verification, we compare the superiority of this method with Logistic Regression and Support Vector Machine in different scenarios.

The power grid is considered to be the most critical piece of infrastructure in the United States because each of the other fifteen critical infrastructures, as defined by the Cyberse-curity and Infrastructure Security Agency (CISA), require the energy sector to properly function. Due the critical nature of the power grid, the ability to detect anomalies in the power grid is of critical importance to prevent power outages, avoid damage to sensitive equipment and to maintain a working power grid. Over the past few decades, the modern power grid has evolved into a large Cyber Physical System (CPS) equipped with wide area monitoring systems (WAMS) and distributed control. As smart technology advances, the power grid continues to be upgraded with high fidelity sensors and measurement devices, such as phasor measurement units (PMUs), that can report the state of the system with a high temporal resolution. However, this influx of data can often become overwhelming to the legacy Supervisory Control and Data Acquisition (SCADA) system, as well as, the power system operator. In this paper, we propose using a deep learning (DL) convolutional neural network (CNN) as a module within the Automatic Network Guardian for ELectrical systems (ANGEL) Digital Twin environment to detect physical faults in a power system. The presented approach uses high fidelity measurement data from the IEEE 9-bus and IEEE 39-bus benchmark power systems to not only detect if there is a fault in the power system but also applies the algorithm to classify which bus contains the fault.

In photovoltaic (PV) systems, machine learning-based methods have been used for fault detection and diagnosis in the past years, which require large amounts of data. However, fault types in a single PV station are usually insufficient in practice. Due to insufficient and non-identically distributed data, packet loss and privacy concerns, it is difficult to train a model for diagnosing all fault types. To address these issues, in this paper, we propose a decentralized federated learning (FL)-based fault diagnosis method for insulated gate bipolar transistor (IGBT) open-circuits in PV inverters. All PV stations use the convolutional neural network (CNN) to train local diagnosis models. By aggregating neighboring model parameters, each PV station benefits from the fault diagnosis knowledge learned from neighbors and achieves diagnosing all fault types without sharing original data. Extensive experiments are conducted in terms of non-identical data distributions, various transmission channel conditions and whether to use the FL framework. The results are as follows: 1) Using data with non-identical distributions, the collaboratively trained model diagnoses faults accurately and robustly; 2) The continuous transmission and aggregation of model parameters in multiple rounds make it possible to obtain ideal training results even in the presence of packet loss; 3) The proposed method allows each PV station to diagnose all fault types without original data sharing, which protects data privacy.

The modular exponentiation is crucial to the RSA cryptographic protocol, and variants inspired by the Montgomery ladder have been studied to provide more secure algorithms. In this paper, we abstract away the iterative conditional branching used in the Montgomery ladder, and formalize systems of equations necessary to obtain what we call the semi-interleaved and fully-interleaved ladder properties. In particular, we design fault-injection attacks able to obtain bits of the secret against semi-interleaved ladders, including the Montgomery ladder, but not against fully-interleaved ladders that are more secure. We also apply these equations to extend the Montgomery ladder for both the semi- and fully-interleaved cases, thus proposing novel and more secure algorithms to compute the modular exponentiation.

Data driven classification models are useful to assess quality of manufactured electronics. Because decisions are taken based on the models, their veracity is relevant, covering aspects such as accuracy, transparency and clarity. The proposed BB-Stepwise algorithm aims to improve the classification model transparency and accuracy of black box models. K-Nearest Neighbours (KNN) is a black box model which is easy to implement and has achieved good classification performance in different applications. In this paper KNN-Stepwise is illustrated for fault detection of electronics devices. The results achieved shows that the proposed algorithm was able to improve the accuracy, veracity and transparency of KNN models and achieve higher transparency and clarity, and at least similar accuracy than when using Decision Tree models.

Industrial robots are playing an important role in now a day industrial productions. However, due to the increasing in robot hardware modules and the rapid expansion of software modules, the reliability of operating systems for industrial robots is facing severe challenges, especially for the light-weight edge computing platforms. Based on current technologies on resource security isolation protection and access control, a novel resource management model for real-time edge system of multiple robot arms is proposed on light-weight edge devices. This novel resource management model can achieve the following functions: mission-critical resource classification, resource security access control, and multi-level security data isolation transmission. We also propose a fault location and isolation model on each lightweight edge device, which ensures the reliability of the entire system. Experimental results show that the robot operating system can meet the requirements of hierarchical management and resource access control. Compared with the existing methods, the fault location and isolation model can effectively locate and deal with the faults generated by the system.

Recent years, more and more testing criteria for deep learning systems has been proposed to ensure system robustness and reliability. These criteria were defined based on different perspectives of diversity. However, there lacks comprehensive investigation on what are the most essential diversities that should be considered by a testing criteria for deep learning systems. Therefore, in this paper, we conduct an empirical study to investigate the relation between test diversities and erroneous behaviors of deep learning models. We define five metrics to reflect diversities in neuron activities, and leverage metamorphic testing to detect erroneous behaviors. We investigate the correlation between metrics and erroneous behaviors. We also go further step to measure the quality of test suites under the guidance of defined metrics. Our results provided comprehensive insights on the essential diversities for testing criteria to exhibit good fault detection ability.

This paper explains how the commonly occurring DOS and Brute Force attacks on computer networks can be efficiently detected and network performance improved, which reduces costs and time. Therefore, network administrators attempt to instantly diagnose any network issues. The experimental work used the SNMP-MIB parameter datasets, which are collected via a specialised MIB dataset consisting of seven types of attack as noted in section three. To resolves such issues, this researched carried out several important contributions which are related to fault management concerns in computer network systems. A central task in the detection of the attacks relies on MIB feature behaviours using the suggested SFCM method. It was concluded that the DOS and Brute Force fault detection results for three different clustering methods demonstrated that the proposed SFCM detected every data point in the related group. Consequently, the FPC approached 1.0, its highest record, and an improved performance solution better than the EM methods and K-means are based on SNMP-MIB variables.

Power system intelligent terminal equipment is widely used in real-time monitoring, data acquisition, power management, power distribution and other tasks of smart grid. The power system intelligent terminal can obtain various information of users and power companies in the power grid, but there is still a lack of protection means for the connection and communication process of the terminal components. In this paper, a novel method based on improved deep belief network(IDBN) is proposed to accomplish the business-level security monitoring and attack detection of power system terminal. A non-intrusive business-level monitoring platform for power system terminals is established, which uses energy metering intelligent terminals as an example for non-intrusive data collection. Based on this platform, the I-DBN extracts the spatial and temporal attack characteristics of the external monitoring data of the system. Some fault conditions and cyber attacks of the model have been simulated to demonstrate the effectiveness of the proposed detection method and the results show excellent performance. The method and platform proposed in this paper can be extended to other services in the power industry, providing a theoretical basis and implementation method for realizing the security monitoring of power system intelligent terminals from the business level.

Elliptical curve cryptography (ECC) is being used more and more in public key cryptosystems. Its main advantage is that, at a given security level, key sizes are much smaller compared to classical asymmetric cryptosystems like RSA. Smaller keys imply less power consumption, less cryptographic computation and require less memory. Besides performance, security is another major problem in embedded devices. Cryptosystems, like ECC, that are considered mathematically secure, are not necessarily considered safe when implemented in practice. An attacker can monitor these interactions in order to mount attacks called fault attacks. A number of countermeasures have been developed to protect Montgomery Scalar Multiplication algorithm against fault attacks. In this work, we proposed an efficient countermeasure premised on duplication scheme and the scrambling technique for Montgomery Scalar Multiplication algorithm against fault attacks. Our approach is simple and easy to hardware implementation. In addition, we perform injection-based error simulations and demonstrate that the error coverage is about 99.996%.

Fault detection in a machine at earlier stage can prevent severe damage and loss to the industries. Fault detection techniques are broadly classified into three categories; signature extraction-based, model-based and knowledge-based approach. Model-based techniques are efficient for raising an alarm signal if there is any fault in the machine. This paper focuses on one such model based-technique to identify the internal faults of induction machine. The model developed is deployed in the end to make it feasible to use in real time. K-Nearest Neighbors (KNN) and grid search cross validation (CV) have been used to train and optimize the model to give the best results. The advantage of proposed algorithm is the accuracy in prediction which has been seen to be 80%. Finally, a user friendly interface has been built using Flask, a python web framework.

In fault diagnosis of industrial process, there are usually more than one variable that are faulty. When multiple faults occur, the generalized reconstruction-based contribution can be helpful while traditional RBC may make mistakes. Due to the correlation between the variables, these faults usually propagate to other normal variables, which is called smearing effect. Thus, it is helpful to consider the pervious fault diagnosis results. In this paper, a data-driven fault diagnosis method which is based on generalized RBC and bayesian decision is presented. This method combines multi-dimensional RBC and bayesian decision. The proposed method improves the diagnosis capability of multiple and minor faults with greater noise. A numerical simulation example is given to show the effectiveness and superiority of the proposed method.

This paper addresses analysis and design of multiple fault diagnosis for a class of Lipschitz nonlinear system. In order to automatically estimate multi-fault parameters efficiently, a new method of multi-fault diagnosis based on the differential evolution algorithm (DE) is proposed. Finally, a series of experiments validate the feasibility and effectiveness of the proposed method. The simulation show the high accuracy of the proposed strategies in multiple abrupt faults diagnosis.

Principal Component Analysis (PCA) is a basic method of fault diagnosis based on multivariate statistical analysis. It utilizes the linear correlation between multiple process variables to implement process fault diagnosis and has been widely used. Traditional PCA fault diagnosis ignores the impact of faults with different magnitudes on detection accuracy. Based on a variety of data processing methods, this paper proposes a multi-level and multi-granularity principal component analysis method to make the detection results more accurate.

Neural Network is used in many applications and guarding its performance against faults is a research challenge. Self-healing neural network is a promising concept for achieving reliability, which is the ability to detect and fix a fault in the system automatically. Most of the current self-healing neural network are based on replication of hardware nodes which causes significant area overhead. The proposed self-healing approach results in a modest area overhead and it is suitable for complex neural network. The proposed method is based on a shared operation and a spare node in each layer which compensates for any faulty node in the layer. Each faulty node will be compensated by its neighbor node, and the neighbor node performs the faulty node as well as its own operations sequentially. In the case the neighbor is faulty, the spare node will compensate for it. The proposed method is implemented using VHDL and the simulation results are obtained using Altira 10 GX FPGA for a different number of nodes. The area overhead is very small for a complex network. The reliability of the proposed method is studied and compared with the traditional neural network.

Heterogeneous Networks (Het Nets) are introduced to fulfill the increasing demands of wireless communications. To be manageable, it is expected that these networks are self-organized and in particular, self-healing to detect and relief faults autonomously. In the Cooperative Cell Outage Detection (COD), the Macro-Base Station (MBS) and a group of Femto-Base Stations (FBSs) in a specific range are cooperatively communicating to find out if each FBS is working properly or not. In this paper, we discuss the impacts of the cooperation range on the detection delay and accuracy and then conclude that there is an optimal amount for cooperation range which maximizes detection accuracy. We then derive the optimal cooperative range that improves the detection accuracy by using network parameters such as FBS's transmission power, noise power, shadowing fading factor, and path-loss exponent and investigate the impacts of these parameters on the optimal cooperative range. The simulation results show the optimal cooperative range that we proposed maximizes the detection accuracy.

Implementation of self-healing control system in smart grid is a persisting challenge. Self-Healing control strategy is the important guarantee to implement the smart grid. In addition, it is the support of achieving the secure operation, improving the reliability and security of distribution grid, and realizing the smart distribution grid. Although self-healing control system concept is presented in smart grid context, but the complexity of distribution network structure recommended to choose advanced control and protection system using a self-healing, this system must be able to heal any disturbance in the distribution system of smart grid to improve efficiency, resiliency, continuity, and reliability of the smart grid. This review focuses mostly on the key technology of self-healing control, gives an insight into the role of self-healing in distribution system advantages, study challenges and opportunities in the prospect of utilities. The main contribution of this paper is demonstrating proposed architecture, control strategy for self-healing control system includes fault detection, fault localization, faulted area isolation, and power restoration in the electrical distribution system.

Root cause analysis (RCA) is a common and recurring task performed by operators of cellular networks. It is done mainly to keep customers satisfied with the quality of offered services and to maximize return on investment (ROI) by minimizing and where possible eliminating the root causes of faults in cellular networks. Currently, the actual detection and diagnosis of faults or potential faults is still a manual and slow process often carried out by network experts who manually analyze and correlate various pieces of network data such as, alarms, call traces, configuration management (CM) and key performance indicator (KPI) data in order to come up with the most probable root cause of a given network fault. In this paper, we propose an automated fault detection and diagnosis solution called adaptive root cause analysis (ARCA). The solution uses measurements and other network data together with Bayesian network theory to perform automated evidence based RCA. Compared to the current common practice, our solution is faster due to automation of the entire RCA process. The solution is also cheaper because it needs fewer or no personnel in order to operate and it improves efficiency through domain knowledge reuse during adaptive learning. As it uses a probabilistic Bayesian classifier, it can work with incomplete data and it can handle large datasets with complex probability combinations. Experimental results from stratified synthesized data affirmatively validate the feasibility of using such a solution as a key part of self-healing (SH) especially in emerging self-organizing network (SON) based solutions in LTE Advanced (LTE-A) and 5G.

This paper presents a solution to a multiple-model based stochastic active fault diagnosis problem over the infinite-time horizon. A general additive detection cost criterion is considered to reflect the objectives. Since the system state is unknown, the design consists of a perfect state information reformulation and optimization problem solution by approximate dynamic programming. An adaptive particle filter state estimation algorithm based on the efficient sample size is proposed to maintain the estimate quality while reducing computational costs. A reduction of information statistics of the state is carried out using non-resampled particles to make the solution feasible. Simulation results illustrate the effectiveness of the proposed design.

A novel method, consisting of fault detection, rough set generation, element isolation and parameter estimation is presented for multiple-fault diagnosis on analog circuit with tolerance. Firstly, a linear-programming concept is developed to transform fault detection of circuit with limited accessible terminals into measurement to check existence of a feasible solution under tolerance constraints. Secondly, fault characteristic equation is deduced to generate a fault rough set. It is proved that the node voltages of nominal circuit can be used in fault characteristic equation with fault tolerance. Lastly, fault detection of circuit with revised deviation restriction for suspected fault elements is proceeded to locate faulty elements and estimate their parameters. The diagnosis accuracy and parameter identification precision of the method are verified by simulation results.

When supporting commercial or defense systems, a perennial challenge is providing effective test and diagnosis strategies to minimize downtime, thereby maximizing system availability. Potentially one of the most effective ways to maximize downtime is to be able to detect and isolate as many faults in a system at one time as possible. This is referred to as the "multiple-fault diagnosis" problem. While several tools have been developed over the years to assist in performing multiple-fault diagnosis, considerable work remains to provide the best diagnosis possible. Recently, a new model for evolutionary computation has been developed called the "Factored Evolutionary Algorithm" (FEA). In this paper, we combine our prior work in deriving diagnostic Bayesian networks from static fault isolation manuals and fault trees with the FEA strategy to perform abductive inference as a way of addressing the multiple-fault diagnosis problem. We demonstrate the effectiveness of this approach on several networks derived from existing, real-world FIMs.

In this paper, we investigate detectability and identifiability of attacks on linear dynamical systems that are subjected to external disturbances. We generalize a concept for a security index, which was previously introduced for static systems. The index exactly quantifies the resources necessary for targeted attacks to be undetectable and unidentifiable in the presence of disturbances. This information is useful for both risk assessment and for the design of anomaly detectors. Finally, we show how techniques from the fault detection literature can be used to decouple disturbances and to identify attacks, under certain sparsity constraints.

Implementation attacks and more specifically Power Analysis (PA) (the dominant type of side channel attack) and fault injection (FA) attacks constitute a pragmatic hazard for scalar multiplication, the main operation behind Elliptic Curve Cryptography. There exists a wide variety of countermeasures attempting to thwart such attacks that, however, few of them explore the potential of alternative number systems like the Residue Number System (RNS). In this paper, we explore the potential of RNS as an PA-FA countermeasure and propose an PA-FA resistant scalar multiplication algorithm and provide an extensive security analysis against the most effective PA-FA techniques. We argue through a security analysis that combining traditional PA-FA countermeasures with lightweight RNS countermeasures can provide strong PA-FA resistance.