Introduction to Predictive Models for Motor Dielectric Aging

With the evolution of fifth generation (5G) network technologies, network maintenance strategies have become increasingly complex, necessitating the use of predictive analysis enabled by Machine Learning (ML) algorithms. This paper emphasizes exploring how ML algorithms can further enhance predictive maintenance in 5G and future networks. It reviews the current literature on this interdisciplinary topic, identifying key ML models such as Decision Trees, Neural Networks, and Support Vector Machines, and discussing their benefits and limitations. Special attention is given to the methodologies in applying these models, handling of data stages, and the training process. Major challenges in implementing ML in the context of network maintenance, such as data privacy, data gathering, model training, and generalizability, are discussed. Furthermore, the research aims to go beyond predicting maintenance needs to introduce a proactive approach in improving overall network performance and pre-empting potential issues based on ML predictions. The paper also discusses possible future trends including advancements in ML algorithms, Automated Machine Learning (AutoML), Explainable AI, and others. The objective is to provide a comprehensive understanding of the current ML-based predictive maintenance field and outline possibilities for future research. The study finds that the application of ML algorithms continues to show promise in transforming the landscape of network management by improving predictive maintenance and proactive performance enhancement strategies. It remains a challenging yet important area in the context of 5G networks.

Offshore platforms are vital assets for the oil and gas industry, serving as the primary facilities for exploration, extraction, and processing. Maintenance logistics plays a crucial role in ensuring these platforms operate efficiently and safely. However, the remote and harsh environments of offshore platforms present significant challenges for maintenance activities. Traditional maintenance strategies often struggle to meet the demands of these environments, leading to inefficiencies, increased costs, and potential safety risks. This review discusses the application of Artificial Intelligence (AI) in optimizing maintenance logistics on offshore platforms. Current strategies involve a combination of preventive, predictive, and corrective maintenance approaches. Preventive maintenance schedules regular inspections and replacements based on predetermined intervals, while predictive maintenance utilizes data analytics to predict equipment failures and plan maintenance activities accordingly. Corrective maintenance addresses issues as they arise, often in response to unexpected failures. AI offers opportunities to enhance these strategies by leveraging advanced data analytics, machine learning, and optimization algorithms. AI-enabled predictive maintenance can analyze vast amounts of data from sensors, historical maintenance records, and environmental factors to forecast equipment failures with greater accuracy. This allows for proactive maintenance planning, minimizing downtime and reducing maintenance costs. Furthermore, AI can optimize maintenance logistics by improving resource allocation and scheduling. Through real-time monitoring and analysis, AI systems can prioritize maintenance tasks based on urgency, equipment criticality, and resource availability. This ensures that maintenance crews are deployed efficiently, reducing idle time and improving overall productivity. Future innovations in AI for maintenance logistics on offshore platforms include the integration of Internet of Things (IoT) devices and autonomous systems. IoT sensors can provide real-time data on equipment condition and environmental factors, enabling more precise predictive maintenance models. Autonomous maintenance robots equipped with AI algorithms can perform routine inspections and minor repairs, reducing the need for human intervention in hazardous environments. However, implementing AI in offshore maintenance logistics also poses challenges, including data quality, cybersecurity, and workforce readiness. Ensuring data accuracy and reliability is crucial for effective AI models, requiring robust data collection and management processes. Cybersecurity measures must be strengthened to protect AI systems from malicious attacks that could disrupt operations or compromise safety. Additionally, workforce training and education are essential to prepare personnel for working alongside AI systems and interpreting AI-generated insights. Optimizing maintenance logistics on offshore platforms with AI offers significant benefits in terms of efficiency, cost savings, and safety. By leveraging AI technologies, current maintenance strategies can be enhanced, and future innovations can revolutionize offshore maintenance practices, making operations more sustainable and resilient in the face of evolving challenges.

In recent years, the demand to provide best-estimate predictions with confident bounds is increasing for the nuclear reactor performance and safety analysis. The Organisation for Economic Co-operation and Development Nuclear Energy Agency has been developing an international benchmark of the light water reactor (LWR) uncertainty analysis in modeling (UAM) for the examination of uncertainty quantification and propagation methodologies with various modeling and simulation code systems. The objective of the present work is to develop an uncertainty propagation mechanism based on the stochastic sampling method by taking into account the uncertainties of both basic nuclear data and fuel modeling parameters in the simulation of pressurized water reactors (PWRs) that can be incorporated in the conventional LWR simulation approach. More specifically, the Three Mile Island Unit 1–related exercises from the LWR-UAM benchmark have been modeled using the coupled TRACE/PARCS code system in the three-dimensional core representation. The input uncertainties of the neutronics simulation include few-group cross sections and kinetics parameters generated using the Sampler/Polaris sequence of SCALE 6.2.1. Several heat transfer–related variables for the fuel modeling were considered as sources of input uncertainty of the thermal-hydraulics simulations, including the thermal conductivity of fuel and cladding, fuel heat capacity, and the gap conductance. Dakota was used to sample input parameters of the coupled code system and to perform the uncertainty analysis. Two types of simulations were conducted: steady-state calculation at hot full-power condition and transient scenario initiated by the spatially asymmetric rod ejection accident. Quantities of interest for the steady-state calculation, including core multiplication factor and power peaking factors, were calculated with associated uncertainties. For transient calculations, best-estimate plus uncertainty results of the time evolution of core reactivity, core power, and peak fuel temperature were generated and analyzed. The Wilks’ formula was used to determine the necessary sample size to achieve a 95% confidence of the 95% limit of output quantities of interest. Although the uncertainty propagation and quantification method presented in this paper was developed for PWRs, it could be in general applicable to the multiphysics uncertainty quantification of other types of LWR cores.

Machine learning (ML) approaches to predicting quantum mechanical (QM) properties have made great strides toward achieving the computational chemist's holy grail of structure-based property prediction. In contrast to direct ML methods, which encode a molecule with only structural information, in this work, we show that QM descriptors improve ML predictions of dimer interaction energy, both in terms of accuracy and data efficiency, by incorporating electronic information into the descriptor. We present the electron deformation density interaction energy machine learning (EDDIE-ML) model, which predicts the interaction energy as a function of Hartree-Fock electron deformation density. We compare its performance with leading direct ML schemes and modern DFT methods for the prediction of interaction energies for dimers of varying charge type, size, and intermolecular separation. Under a low-data regime, EDDIE-ML outperforms other direct ML schemes and is the only model readily transferrable to larger, more complex systems including base pair trimers and porous cages. The underlying physical connection between the density and interaction energy enables EDDIE-ML to reach an accuracy comparable to modern DFT functionals in fewer training data points compared to other ML methods.

Machine Learning and Sampling Scheme: An Empirical Study of Money Laundering Detection

Uncertainty quantification and propagation with probability boxes

SummaryAccurate prediction of the solubility of chemical substances in solvents remains a challenge. The sparsity of high-quality solubility data is recognized as the biggest hurdle in the development of robust data-driven methods for practical use. Nonetheless, the effects of the quality and quantity of data on aqueous solubility predictions have not yet been scrutinized. In this study, the roles of the size and the quality of data sets on the performances of the solubility prediction models are unraveled, and the concepts of actual and observed performances are introduced. In an effort to curtail the gap between actual and observed performances, a quality-oriented data selection method, which evaluates the quality of data and extracts the most accurate part of it through statistical validation, is designed. Applying this method on the largest publicly available solubility database and using a consensus machine learning approach, a top-performing solubility prediction model is achieved.

Tsunamis are unpredictable events and catastrophic in their potential for destruction of human lives and economy. The unpredictability of their occurrence poses a challenge to the tsunami community, as it is difficult to obtain from the tsunamigenic records estimates of recurrence rates and severity. Accurate and efficient mathematical/computational modeling is thus called upon to provide tsunami forecasts and hazard assessments. Compounding this challenge for warning centres is the physical nature of tsunamis, which can travel at extremely high speeds in the open ocean or be generated close to the shoreline. Thus, tsunami forecasts must be not only accurate but also delivered under severe time constraints. In the immediate aftermath of a tsunamigenic earthquake event, there are uncertainties in the source such as location, rupture geometry, depth, magnitude. Ideally, these uncertainties should be represented in a tsunami warning. However in practice, quantifying the uncertainties in the hazard intensity (i.e.,maximum tsunami amplitude) due to the uncertainties in the source is not feasible, since it requires a large number of high resolution simulations. We approximate the functionally complex and computationally expensive high resolution tsunami simulations with a simple and cheap statistical emulator. A workflow integrating the entire chain of components from the tsunami source to quantification of hazard uncertainties is developed here - quantification of uncertainties in tsunamigenic earthquake sources, high resolution simulation of tsunami scenarios using the GPU version of Volna-OP2 on a non-uniform mesh for an ensemble of sources, construction of an emulator using the simulations as training data, and prediction of hazard intensities with associated uncertainties using the emulator. Thus, using the massively parallelized finite volume tsunami code Volna-OP2 as the heart of the workflow, we use statistical emulation to compute uncertainties in hazard intensity at locations of interest. Such an integration also balances the trade-off between computationally expensive simulations and desired accuracy of uncertainties, within given time constraints. The developed workflow is fully generic and independent of the source (1945 Makran earthquake) studied here.

Optimizing aircraft engine longevity: A comparative framework for dynamically adaptive predictive maintenance using autoencoders, LSTMs, and Gaussian processes

As Internet worms become ever faster and more sophisticated, it is important to be able to extract worm signatures in an accurate and timely manner. In this paper, we apply machine learning to automatically fingerprint polymorphic worms, which are able to change their appearance across every instance. Using real Internet traces and synthetic polymorphic worms, we evaluated the performance of several advanced machine learning algorithms, including naive Bayes, decision-tree induction, rule learning (RIPPER) and support vector machines. The results are very promising. Compared with Polygraph, the state of the art in polymorphic worm fingerprinting, several machine learning algorithms are able to generate more accurate signatures, tolerate more noise in the training data and require much shorter training time. These results open the possibility of applying machine learning to build a fast and accurate online worm fingerprinting system.

Surrogate models are statistical or conceptual approximations for more complex simulation models. In this context, it is crucial to propagate the uncertainty induced by limited simulation budget and surrogate approximation error to predictions, inference, and subsequent decision-relevant quantities. However, quantifying and then propagating the uncertainty of surrogates is usually limited to special analytic cases or is otherwise computationally very expensive. In this paper, we propose a framework enabling a scalable, Bayesian approach to surrogate modeling with thorough uncertainty quantification, propagation, and validation. Specifically, we present three methods for Bayesian inference with surrogate models given measurement data. This is a task where the propagation of surrogate uncertainty is especially relevant, because failing to account for it may lead to biased and/or overconfident estimates of the parameters of interest. We showcase our approach in three detailed case studies for linear and nonlinear real-world modeling scenarios. Uncertainty propagation in surrogate models enables more reliable and safe approximation of expensive simulators and will therefore be useful in various fields of applications.

Electroless plating is a chemical process commonly used in semiconductor manufacturing that deposits a uniform metal coating onto a substrate through an auto-catalytic reduction reaction without using electricity. High quality deposition hinges on the precise control of bath composition and operating conditions, which in turn requires accurate and accessible monitoring of the bath chemical concentration. While chemical analyzers present an effective monitoring technique, they are generally limited by high costs, complexity, and maintenance. Time-delayed measurements also impose challenges on real-time operations, and any reduction to the monitoring lag would be highly beneficial. We introduce a data-driven machine learning (ML) approach able to achieve fast concentration predictions directly from operating conditions, and able to compute the prediction uncertainty that is valuable for subsequent robust control and optimization and for improving transparency and trustworthiness of ML tools in manufacturing settings. Notably, our ML procedure overcomes challenges of asynchronous time-series training data with missing values, and where available data are often noisy and sparse. Our ML approach begins with a data preprocessing step to handle asynchronous measurements and missing values by engineering features rooted in the underlying physical processes. Notably, a systematic feature selection is performed to down select features that are most correlated with the prediction target, thereby reduce model overfitting. We then compare a number of regression model architectures for capturing the sequential data relationships, including linear models, random forest, extreme gradient boosting, and fully connected, long short-term memory, and transformer neural networks. We quantify the model uncertainty by training them in a Bayesian manner using scalable Stein variational gradient descent, to compute the posterior probability distributions conditioned on the training data that reflect the uncertainty in the models induced by the quality and quantity of the available observations. We demonstrate the overall ML approach on a real-world dataset from a semiconductor manufacturing plant that exhibits the aforementioned data challenges. The best performing models exhibited 1, 5, 12% accuracy (defined as achieving within a 3% margin) improvements on predicting the metal ion, alkali, reductant concentrations, respectively, over a naive feature extraction technique. It also achieved 13, 10, 32% accuracy improvements over an autoregressive integrated moving average (ARIMA) baseline. These results show the approach’s effectiveness in providing reliable predictions with quantified uncertainty.

For many years, unplanned equipment downtime has wreaked havoc on productivity and is an expensive way to run an operational business; yet when we look at the manufacturing of today, virtually all industries are impacted. However, conventional maintenance approaches, like reactive and preventive, do not provide an effective solution for tackling these issues. Through predictive maintenance, it is possible to anticipate equipment failures as well as optimize maintenance schedules. This study will explore the integration of predictive maintenance capabilities within the QAD Enterprise Resource Planning (ERP) system, using machine learning algorithms to predict equipment failures. Our approach helps reduce unnecessary downtime and maximizes overall equipment effectiveness using real-time data from such Internet of Things (IoT) sensors and advanced predictive analytics. The methodology includes the collection of data from IoTs, data pre-processing, feature engineering, and employing Machine Learning models for predictive maintenance. The result of these key findings is that this predicts a substantial decrease in unplanned downtime and maintenance costs, which validates the ability to include predictive maintenance in QAD ERP. Finally, the study concludes by demonstrating the potential to create more resilient and efficient manufacturing operations by combining machine learning-powered predictive maintenance with enterprise resource planning (ERP) systems.

This paper proposes an uncertainty quantification (UQ)-incorporated design optimization technique that integrates UQ considering the statistical characteristics of sensing margin with machine learning (ML) for the design of bitline sense amplifiers (BLSAs) in dynamic random access memory (DRAM), including offset compensation operation. The increased offset due to process variation exacerbated by device scaling degrades the reliability of DRAM read operations, making quantitative analysis of process variation essential. Conventional Monte Carlo (MC)-based UQ analysis provides high accuracy but requires extensive simulation costs. Accordingly, this study systematically defines key input and output variables for conventional BLSA and two representative offset compensation BLSA structures, introduces Sobol sequence-based quasi-Monte Carlo (QMC) sampling to improve simulation efficiency, and generalizes the Standard UQ methodology to predict statistical distributions of circuit performance parameters under process variation. Furthermore, a 3-Stage UQ algorithm that sequentially learns nominal, mean, and standard deviation values is proposed to enhance the efficiency of ML model training. HSPICE simulation results based on the TSMC 65 nm process demonstrated that the proposed 3-Stage UQ method reduced the simulation time required for ML training data generation by an average of 43% compared to the Standard UQ method and achieved excellent prediction performance even in data-limited environments. Additionally, design optimization combined with Bayesian Optimization (BO) confirmed performance improvements across all circuit structures. The methodology presented in this study enables effective process variation-aware optimization for DRAM designs requiring high reliability and yield, and is expected to contribute to next-generation memory circuit design automation.

In this paper, we propose a hybrid methodology based on a combination of analytical, numerical and machine learning methods for performing dexterous, in-hand manipulation with simple, adaptive robot hands. A constrained optimization scheme utilizes analytical models that describe the kinematics of adaptive hands and classic conventions for modelling quasistatically the manipulation problem, providing intuition about the problem mechanics. A machine learning (ML) scheme is used in order to split the problem space, deriving task-specific models that account for difficult to model, dynamic phenomena (e.g., slipping). In this respect, the ML scheme: 1) employs the simulation module in order to explore the feasible manipulation paths for a specific hand-object system, 2) feeds the feasible paths to an experimental setup that collects manipulation data in an automated fashion, 3) uses clustering techniques in order to group together similar manipulation trajectories, 4) trains a set of task-specific manipulation models and 5) uses classification techniques in order to trigger a task-specific model based on the user provided task specifications. The efficacy of the proposed methodology is experimentally validated using various adaptive robot hands in 2D and 3D in-hand manipulation tasks.