Study resilience of NN accelerators, especially fault characterization and mitigation.
problem Faults in hardware accelerators of NNs, especially at 10nm technology node.
method Characterized fault vulnerability of RTL NN components and developed a fault mitigation technique.
result Fault mitigation technique improves accuracy by 47.3%.
Mitigates faults in DNNs by clipping activation values, improving their resilience.
problem Fault tolerance of DNNs in safety-critical applications.
method Clipping activation functions to reduce impact of faulty weights.
result Significant improvement in classification accuracy (68.92%) for fault mitigation.
The paper investigates how reducing memory supply voltage improves DNN accuracy under bit-cell faults.
problem Reducing energy consumption in deep neural networks by lowering memory supply voltage introduces bit-cell faults.
method The authors explore the robustness of DNN architectures to bit-cell faults and propose a regularizer to mitigate their effects.
result Operating the system in a faulty regime can save energy without significantly reducing accuracy.
Machine learning aids self-healing in cellular networks, tackling data imbalance and cost sensitivity.
problem Challenges in applying machine learning for self-healing in cellular networks.
method Data-driven machine learning techniques addressing data imbalance, insufficiency, and cost sensitivity.
result Feasibility and effectiveness of cost-sensitive fault detection with imbalanced data.
Develops a data-driven fault diagnosis framework for time-series data.
problem Fault diagnosis of dynamic systems using imbalanced and unknown fault classes.
method Kullback-Leibler divergence, data-driven fault classification, open-set classification.
result Framework handles imbalanced datasets, class overlapping, and unknown faults.
Neural network residuals isolate and locate unknown faults.
problem Locating unknown faults in industrial systems.
method Neural network-based residuals combining physical insights and machine learning.
result Neural network residuals can isolate and locate unknown faults.
Meta-reinforcement learning improves fault-adaptive control efficiency.
problem Adaptive control under abrupt system faults with strict time constraints.
method Model-agnostic meta learning (MAML) with a fault library of prior policies.
result Improved sample efficiency and quick adaptation to new faults.
Ensemble models struggle with detecting mild faults.
problem Difficulty in detecting Intermediate-Severity faults due to their resemblance to normal conditions.
method Extensive experiments with ensemble models to identify and address common pitfalls.
result Designing more effective ensemble models for IS fault detection and diagnosis.
Proposes KIL-AdaVAE for fault detection and segmentation of unknown fault types.
problem Lack of labeled data for fault types in safety-critical systems.
method Implicit supervision with Deep Variational Autoencoders (VAE).
result Significant performance improvements in fault detection and segmentation.
Ranger improves DNNs' fault resilience without re-computation.
problem Transient faults in DNNs cause errors, reducing reliability.
method Range restriction to transform critical faults to benign faults.
result Significant improvement in error resilience (3x to 50x) with no accuracy loss.
New model evaluates how well models handle input faults.
problem Fault tolerance of models to input variations.
method Evaluates fault tolerance using information-based characteristic for arbitrary valid inputs.
result Proposes a new way to measure model robustness.
Residual generation helps diagnose engine faults using neural networks.
problem Fault diagnosis in engines with unknown classes and limited data.
method Grey-box recurrent neural networks incorporating physical insights.
result Improved fault classification and root cause identification.
DriveFI uses ML to find critical faults in AVs, saving time and resources.
problem Lack of end-to-end fault assessment in AVs under realistic scenarios.
method Machine learning-based fault injection engine (DriveFI) that identifies safety-critical faults.
result Found 561 safety-critical faults in less than 4 hours, compared to weeks of random injection.
TS-Fault benchmarks TSF models against structural faults.
problem Evaluating the robustness of time series forecasting models against structured events.
method TS-Fault uses parameterized fault scenarios with controllable difficulty.
result Three findings contradict common leaderboard intuition.
Paper proposes FTT-NAS to create fault-tolerant CNNs for edge devices.
problem Faults in edge devices affect deep learning applications.
method Formalized fault models, implemented FTT-NAS, incorporated FTT.
result Discovered CNNs outperform baseline architectures with fault tolerance.
Paper proposes using MC-dropout to detect and diagnose incipient faults in buildings.
problem Lack of labeled incipient fault data in buildings.
method Proposes using Monte Carlo dropout (MC-dropout) to enhance deep neural networks for fault detection.
result Demonstrates effectiveness of MC-dropout in indicating likely incipient fault types.
We introduce a differential geometric framework for describing families of quantum error-correcting codes and for understanding quantum fault tolerance. This work unifies the notion of topological fault tolerance with fault tolerance in other kinds of quantum error-correcting codes. In particular, we use fibre bundles …
Generative model predicts vehicle faults up to 1000 hours in advance.
problem Forecasting vehicle faults for predictive maintenance.
method Generative model trained on US Army data, incorporating real-world factors.
result Highly accurate predictions of time to first fault.
Paper proposes a predictive maintenance system for solar plants using big data.
problem Fault prediction in photovoltaic plants to reduce downtime and maintenance costs.
method Data-driven approach with unsupervised clustering and Pattern Recognition Neural Network.
result Effective prediction of both generic and specific faults, up to 7 days in advance.
Quantum computing improves fault diagnosis in industrial processes.
problem Fault detection and diagnosis in industrial process systems.
method Integrates quantum computing and deep learning to extract features and diagnose faults.
result Quantum-assisted deep learning achieves high fault detection rates (79.2% and 99.39%).
New taxonomy for SCADA-based wind turbine fault detection improves model performance.
problem Lack of consensus on feature causality in normal behavior models.
method Presented a new taxonomy based on causal relations between input features and target.
result Evaluation of different feature configurations on fault detection performance.
This study uses RNNs to diagnose faults in underwater thrusters.
problem Fault detection and diagnosis of underwater thrusters in harsh marine environments.
method Data-driven fault detection using Recurrent Neural Networks (RNNs) with empirical data.
result RNNs outperform residual-based feature extraction for fault classification.
New method improves fault detection by adding unsupervised learning to Monte Carlo dropout models.
problem Detecting and diagnosing incipient and unknown faults in deep neural networks.
method Augmenting Monte Carlo dropout models with unsupervised learning tasks.
result Improved fault detection and diagnosis performance, especially on out-of-distribution examples.
Study designs neural networks for fault localization, state estimation, and optimal PMU placement in power systems.
problem Fault localization, state estimation, and optimal PMU placement in power systems.
method Designs and compares various neural networks for fault localization, builds machine learning schemes for state estimation and parameter estimation, and designs an algorithm for optimal PMU placement.
result Comprehensive comparison of neural networks for fault localization shows that Graphical Convolutional NN and Neural Graph-based ODE perform best.
Deep learning diagnoses rotary machine faults without expert input.
problem Early detection of faults in rotary machinery to save time and money.
method Deep Convolutional Neural Network with three axis accelerometer signal input.
result High classification accuracy in fault diagnosis.
Deep Autoencoder using GANs detects faults in closed loop systems without labeled data.
problem Fault detection in closed loop uncertain dynamical systems.
method Generative Adversarial Network (GAN) based Autoencoder.
result The proposed method significantly outperforms traditional classifier-based methods.
New method detects bearing faults using multivariate statistical process control.
problem Early detection of bearing faults in rotating machinery.
method Multivariate statistical process control charts applied to Fourier transform features of fixed-time batches.
result Effectiveness in detecting bearing faults across different conditions.
Bayesian Recurrent Neural Networks improve fault detection and identification in manufacturing.
problem Detect and identify faults in chemical processes to ensure optimal operations.
method Bayesian Recurrent Neural Networks (BRNNs) with variational dropout.
result BRNNs provide uncertainty estimates for fault detection and identification.
Few-shot learning improves bearing fault diagnosis with limited data.
problem Challenges in collecting sufficient fault data for robust classifier training.
method Model-Agnostic Meta-Learning (MAML) for few-shot learning.
result Framework achieves up to 25% higher accuracy than Siamese network.
CNN improves fault location in power grids with high accuracy.
problem Challenges in real-time fault location due to diverse fault types and fast reclosures.
method Convolutional Neural Network (CNN) classifier using bus voltages.
result CNN-based localization tool outperforms other machine learning methods.
This paper proposes a novel Gaussian process approach to fault removal in time-series data. Fault removal does not delete the faulty signal data but, instead, massages the fault from the data. We assume that only one fault occurs at any one time and model the signal by two separate non-parametric Gaussian process model…
Study on how SEU affects neural networks and proposes remedies.
problem Impact of SEU on neural networks' robustness.
method Defined fault models of SEU, defined sensitivity to SIPP, analytically explored network weaknesses, proposed remedies.
result Proposed remedies can mitigate accuracy degradation from 28% to 0.27%.
A stealthy framework injects faults into DNNs to misclassify images without affecting overall accuracy.
problem Vulnerability of deep neural networks to misclassification attacks.
method Fault sneaking attack using ADMM optimization with constraints on maintaining model accuracy and minimizing parameter modifications.
result The framework can inject multiple sneaking faults into DNNs without reducing overall accuracy.
Domain-Adversarial Neural Networks improve fault diagnosis models across different machines.
problem Improving fault diagnosis models on new machines with limited labeled data.
method Domain-Adversarial Neural Networks (DANN) and other methods for domain adaptation.
result Unified experimental protocol for fair comparison of domain adaptation methods.
Deep RL improves cellular network fault management and performance.
problem Fault management and radio performance improvement in outdoor cellular networks.
method Deep Q-Learning for self-organizing networks fault management.
result The proposed algorithm learns to clear alarms and improve radio performance better than existing methods.
Paper proposes methods to train RBF networks under faults.
problem Training RBF networks with fault tolerance.
method Two novel ADMM-based algorithms using MCP and l0-norm.
result Both methods globally converge to a unique limit point.
TensorFI injects faults in TensorFlow programs to assess their reliability.
problem Ensuring reliability of machine learning systems in safety-critical domains.
method TensorFI is a flexible fault injection framework for TensorFlow applications.
result TensorFI evaluates the resilience of 12 ML programs, including autonomous vehicle DNNs.
New PCA method detects faults using occupation kernels.
problem Fault detection in dynamical systems.
method Occupation kernel PCA for irregularly sampled data.
result Validation of reconstruction error approach for fault detection.
Paper addresses fault-tolerance in distributed machine learning with stochastic gradient descent.
problem Fault-tolerance in distributed stochastic gradient descent (D-SGD) for machine learning.
method Proposes norm-based comparative gradient elimination (CGE) to robustify D-SGD against Byzantine faulty agents.
result CGE guarantees fault-tolerance against a bounded fraction of Byzantine agents under standard stochastic assumptions.
Survey of ML and DL for bearing fault diagnostics.
problem Fault detection and categorization in bearings.
method Review of conventional ML methods and analysis of DL algorithms.
result DL methods outperform conventional ML in fault feature extraction and classification.
Prototype for early fault warnings in large electric grids.
problem Early detection and classification of faults in complex electric grids.
method Multi-stage approach with anomaly detection, feature mapping, classification, and clustering.
result Random forest method offers the most accurate fault classification.
Fault diagnosis method for refrigerant leaks using scaling law.
problem Difficulty in improving fault-detection model generalization due to complex system configuration and insufficient data.
method Derive a scaling law based on physical modeling and control mechanism, apply to other systems without modification.
result Scaling exponents of different air-conditioning systems are equivalent, indicating the proposed method's applicability.
Enhances fault tolerance of neural networks for security-critical applications.
problem Fault tolerance of neural networks is biased and can lead to severe consequences in security-critical scenarios.
method Proposes a revised implementation that significantly enhances the fault tolerance property of neural networks with detailed mathematical analysis.
result Significantly increased fault tolerance of neural networks for security-critical applications.
Fault-tolerant neural networks inspired by biological error correction codes.
problem Achieving reliable computation with unreliable neurons.
method Using biological error correction codes from grid cells in the mammalian cortex to develop a fault-tolerant neural network.
result Noisy biological neurons operate below a fault-tolerance threshold, suggesting a mechanism for reliable computation in the brain.
A method uses ITD and XGBoost for precise power transformer fault diagnosis.
problem Fault diagnosis of power transformers using DGA data.
method Ranking DGA parameters by skewness, extracting ITD features, and using an XGBoost classifier.
result The method achieves over 95% accuracy in classification.
We adopted an approach based on an LSTM neural network to monitor and detect faults in industrial multivariate time series data. To validate the approach we created a Modelica model of part of a real gasoil plant. By introducing hacks into the logic of the Modelica model, we were able to generate both the roots and cau…
Paper tackles fault classification in time series data with deep neural networks.
problem Fault classification over a future horizon in multidimensional time series data with class imbalances.
method Proposes a multi-label recurrent neural network with a new cost function to address class imbalances.
result The proposed algorithm outperforms state-of-the-art techniques in F1-score, precision, and recall.
A new method improves fault diagnostics and prognostics for class-imbalanced data.
problem Class imbalance in industrial fault diagnostics and prognostics.
method EWMOTE: EM-based Weighted Minority Oversampling TEchnique.
result EWMOTE achieves better performance on binary and multi-class imbalance learning tasks.