Paper proposes a method to monitor industrial processes under closed-loop control.
problem Difficulty distinguishing between real process faults and normal operating conditions changes.
method Develops a distributed monitoring system by capturing static and dynamic characteristics of large-scale closed-loop industrial processes.
result The method effectively distinguishes between real process faults and normal operating conditions changes.
A new method uses active learning to monitor industrial processes more accurately.
problem Classifying process states (IC, OC) with limited labeled data.
method Stream-based active learning for partially hidden Markov models.
result Improved dynamic recognition of process states, especially unseen classes.
New method uses deep learning for better monitoring of industrial processes.
problem Monitoring high-dimensional, nonlinear profiles in industrial systems.
method Variational Autoencoders (VAEs) for modeling nonlinear manifolds.
result Deep probabilistic models outperform traditional methods in residual-space.
As the Industrial Internet of Things (IIoT) grows, systems are increasingly being monitored by arrays of sensors returning time-series data at ever-increasing 'volume, velocity and variety' (i.e. Industrial Big Data). An obvious use for these data is real-time systems condition monitoring and prognostic time to failure…
Automated feature extraction for bearing health monitoring.
problem Predicting mechanical faults in process industries to prevent shutdowns.
method Stacked autoencoder neural network and OSELM for automated feature extraction.
result 100% detection accuracy for bearing health states.
New method uses tensor decomposition to improve noise reduction in machine fault detection.
problem Noise in acoustic signals hinders fault detection in industrial machines.
method Non-negative Canonical Polyadic (CP) decomposition for denoising spectral data.
result Improvement in unsupervised anomaly detection for machine fault detection.
TSML tackles anomaly detection and pattern discovery in industrial time series data.
problem Extracting and exploiting information from large industrial data to reduce downtimes and manufacturing errors.
method TSML uses a pipeline of lightweight filters to process industrial time series data in parallel.
result TSML effectively detects anomalies and discovers patterns in industrial time series data.
Modified PCA algorithm with continual learning preserves features of previous modes for multimode process monitoring.
problem Catastrophic forgetting of previous modes in monitoring models for successive modes.
method Modified PCA algorithm with elastic weight consolidation (EWC) to preserve features of previous modes.
result PCA-EWC algorithm effectively monitors multimode processes without performance decrease.
Two methods monitor high-dimensional processes via manifold fitting or learning.
problem Monitoring high-dimensional, dynamic industrial processes.
method Manifold fitting and learning approaches for online SPC.
result Manifold-fitting approach achieves performance competitive with classical methods.
NMF identifies hidden component processes from thermal manufacturing data.
problem Thermal manufacturing processes with many interacting parameters are hard to diagnose.
method Non-negative matrix factorization guided by a knowledge-based initialization strategy.
result Identifies physical meaningful sources from temperature time series.
New method uses Markov chains for cost-optimal healthcare monitoring.
problem Optimizing healthcare monitoring protocols for patient health characteristics.
method Adapts Markov chain approach to account for random shift sizes, repairs, and time intervals.
result Optimal parameters can differ from traditional medical protocols, showing new insights.
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 dataset for industrial machine sounds to aid maintenance.
problem Lack of public datasets for industrial machine sounds.
method Recorded normal and anomalous sounds of industrial machines.
result Assists in automated facility maintenance development.
Semi-supervised method predicts faults in systems with multiple operation modes.
problem Fault detection in industrial systems with missing target data.
method Semi-supervised soft sensor modeling incorporating mode transition properties.
result Regression coefficients estimated under constraint conditions from mode transitions.
Enhances monitoring of industrial systems with limited data.
problem Early detection of rare faults in safety-critical systems with limited training data.
method Feature alignment techniques (variational encoder, adversarial training) to align features from different units.
result Feature alignment improves robustness of one-class classifier for health monitoring.
A new process model for machine learning applications with quality assurance.
problem Lack of standard process model for machine learning applications.
method Six-phase process model with quality assurance methodology.
result Proposes a new process model for machine learning applications.
Deep CNN monitors AM quality with high accuracy.
problem Quality control in AM processes.
method Deep Convolutional Neural Network (CNN) model trained and tested online.
result 94% accuracy and 96% specificity in classifying AM quality.
Anomaly detection aids in labeling fast-running processes for machine learning.
problem Manual labeling of fast-running processes for machine learning models.
method Anomaly detection to assist in labeling data, specific metrics for model validation.
result Possibility to manually classify data for training machine learning models.
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.
New online learning algorithms improve cyberattack detection in industrial control systems.
problem Detecting cyberattacks in industrial control systems with limited resources.
method Online learning algorithms to process continuous data streams and address class imbalance.
result Improved detection rate of cyberattacks in industrial control systems.
Study uses ML and statistical models to analyze climate impacts of industrial growth.
problem Understanding and predicting environmental impacts of industrial activities.
method Comparative analysis of ML and statistical models on time series data.
result ML models outperform statistical models in predicting environmental impacts.
A method to monitor probability predictions for calibration loss in image classification models.
problem Maintaining calibration in machine learning predictions over time.
method Cumulative sum-based approach with dynamic limits for early detection of miscalibration.
result Early detection of operational context changes impacting image classification performance.
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.
Amazon SageMaker Model Monitor detects drift in deployed ML models.
problem Ensuring high performance of ML models in production environments.
method Automatically detects data, concept, bias, and feature attribution drift in real-time.
result Maintains high quality models by providing alerts and corrective actions.
The paper adds explanation to predictive process monitoring.
problem Equipping predictive business process monitoring with explanation capabilities.
method Used game theory of Shapley Values to obtain robust explanations.
result First time explanations given in predictive business process monitoring.
This paper develops a federated approach to learn Granger causality in interdependent industrial clients.
problem Detecting and quantifying interdependencies in large, complex industrial data.
method Linear state space system framework, federated learning, differential privacy.
result Federated Granger causality learning addresses bandwidth and computational limitations.
Deep learning powers automotive innovations like self-driving cars.
problem Improving vehicle safety and functionality.
method Deployment of deep learning models in ADAS systems.
result Deep learning enhances performance and functionality of ADAS solutions.
Deep learning speeds up real-time emission monitoring.
problem Real-time greenhouse gas emission monitoring under transient conditions.
method Bayesian inference with deep learning surrogate of CFD outputs.
result Near-real-time predictions with orders-of-magnitude faster runtimes.
Adversarial attacks hide cyber-physical attacks in ICS.
problem Hiding cyber-physical attacks in industrial control systems.
method Modeling an attacker compromising sensors, manipulating data, and evaluating attacks on both continuous and mixed data.
result Successfully hides cyber-physical attacks with 2.87 out of 12 sensors compromised on average.
VSCOUT detects anomalies in high-dimensional data using a hybrid VAE approach.
problem Challenges in classical SPC for high-dimensional, non-Gaussian data.
method Hybrid VAE architecture with ARD prior, ensemble filtering, and changepoint detection.
result VSCOUT achieves superior sensitivity to special-cause structure and controlled false alarms.
Unsupervised methods detect faults in industrial systems with limited data.
problem Challenges in training data-driven fault detection models with scarce or unavailable data.
method Proposes five approaches: baseline, incremental learning, fleet comparison, and UFAN.
result UFAN outperforms other methods in detecting faults in dissimilar units.
Unlike other industries in which intellectual property is patentable, the financial industry relies on trade secrecy to protect its business processes and methods, which can obscure critical financial risk exposures from regulators and the public. We develop methods for sharing and aggregating such risk exposures that …
Adaptive activity monitoring framework for wearable sensors.
problem Efficiently monitor human activities with low power consumption.
method Switching Gaussian process model with block circulant embedding and FFT for inference.
result Optimized trade-off between sensor power consumption and prediction performance.
Framework detects anomalies in fleet-based machine monitoring.
problem Detecting faults in fleets of similar machines without large historical data.
method Unsupervised, generic anomaly detection using online fleet comparisons and user-defined measures.
result Framework detects anomalies in real-time with minimal historical data.
Transformer model predicts train axle vibrations for safer maintenance.
problem Prevent mechanical failures in railway axles.
method Integrates Deep Autoregressive solution with spectral methods and observation models.
result Transformer model (ShaftFormer) improves predictive maintenance for railway axles.
The paper introduces a framework for prescriptive process monitoring that generates alarms to prevent or mitigate undesired outcomes.
problem Existing predictive process monitoring techniques do not prescribe when and how to intervene to decrease undesired outcomes.
method The paper proposes a framework that extends predictive monitoring with the ability to generate alarms, incorporating a cost model to assess the trade-off between generating alarms and the cost of undesired outcomes.
result The net cost of undesired outcomes can be minimized by optimizing the generation of alarms based on the progress of the process instance and introducing delays for triggering alarms.
Method monitors neural networks using topological properties.
problem Detecting data shifts and out-of-distribution samples.
method Topological Uncertainty based on activation graphs.
result Validates network predictions without retraining.
This research tackles group fairness in predictive process monitoring by ensuring predictions are independent of sensitive group membership.
problem Predictive models using biased historical data can perpetuate unfair behavior in new cases.
method Investigates independence through metrics like ΔDP and a composite loss function balancing predictive performance and fairness.
result Proposes and validates a composite loss function for training models that balance fairness and performance.
A new method for efficient nonlinear process monitoring using random Bernoulli features.
problem High computational demands and real-time responsiveness in online monitoring systems.
method Random Bernoulli principal component analysis to capture nonlinear patterns efficiently.
result The proposed methods offer excellent scalability and reduced computational complexity.
Paper uses Gaussian Processes to monitor air quality in Kampala.
problem Monitoring air pollution in cities with limited sensor coverage.
method Gaussian Processes for nowcasting and forecasting air pollution.
result Demonstrates the effectiveness of Gaussian Processes in air quality monitoring.
We present a numerical scheme to calculate fluctuation identities for exponential Lévy processes in the continuous monitoring case. This includes the Spitzer identities for touching a single upper or lower barrier, and the more difficult case of the two-barriers exit problem. These identities are given in the Fourier-L…
Study monitors wind turbine drivetrain bearings using dictionary learning from vibration data.
problem Early detection of faults in wind turbine drivetrain bearings with minimal false positives.
method Unsupervised dictionary learning from 46 months of vibration data.
result Abnormal dictionary adaptation signals faults 6-12 months before bearing or gearbox replacement.
Predictive process monitoring is concerned with the analysis of events produced during the execution of a business process in order to predict as early as possible the final outcome of an ongoing case. Traditionally, predictive process monitoring methods are optimized with respect to accuracy. However, in environments …
Deep neural network detects anomalies in time series data.
problem Detecting anomalies in diverse time series data.
method End-to-end deep feedforward neural network without feature engineering.
result Effective anomaly detection for various time series types.
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…
This research develops efficient surrogate models for predicting crack growth in metal structures.
problem Accurately predicting crack growth in metal structures under uncertainty.
method Employing Gaussian Process (GP) regression models for latent variable modeling to create probabilistic surrogate models.
result Surrogate models successfully encode material and load-related uncertainties in stochastic crack growth processes.
Paper optimizes industrial refrigeration using adaptive exploration.
problem Challenges in optimizing real-time industrial processes with unknown characteristics and safety constraints.
method Adaptive and explorative real-time optimization framework with Gaussian process uncertainty quantification.
result Approach increases energy efficiency of refrigeration process, approximating complete information solutions.
This research tackles monitoring machine learning algorithms post-deployment, addressing performativity issues.
problem Monitoring machine learning algorithms after deployment, especially when they affect their own data-generating process.
method Uses causal inference techniques to navigate performativity and compares different monitoring criteria and data sources.
result Different monitoring systems have varying operating characteristics and implications for ML monitoring design.