A Machine Learning Approach to Predict Radiation Effects in Microelectronic Components.

This paper presents an innovative technique, Advanced Predictor of Electrical Parameters, based on machine learning methods to predict the degradation of electronic components under the effects of radiation. The term degradation refers to the way in which electrical parameters of the electronic components vary with the irradiation dose. This method consists of two sequential steps defined as 'recognition of degradation patterns in the database' and 'degradation prediction of new samples without any kind of irradiation'. The technique can be used under two different approaches called 'pure data driven' and 'model based'. In this paper, the use of Advanced Predictor of Electrical Parameters is shown for bipolar transistors, but the methodology is sufficiently general to be applied to any other component.

Deep Learning-Based State-of-Health Estimation of Proton-Exchange Membrane Fuel Cells under Dynamic Operation Conditions.

Proton-exchange membrane fuel cells (PEMFCs) play a crucial role in the transition to sustainable energy systems. Accurately estimating the state of health (SOH) of PEMFCs under dynamic operating conditions is essential for ensuring their reliability and longevity. This study designed dynamic operating conditions for fuel cells and conducted durability tests using both crack-free fuel cells and fuel cells with uniform cracks. Utilizing deep learning methods, we estimated the SOH of PEMFCs under dynamic operating conditions and investigated the performance of long short-term memory networks (LSTM), gated recurrent units (GRU), temporal convolutional networks (TCN), and transformer models for SOH estimation tasks. We also explored the impact of different sampling intervals and training set proportions on the predictive performance of these models. The results indicated that shorter sampling intervals and higher training set proportions significantly improve prediction accuracy. The study also highlighted the challenges posed by the presence of cracks. Cracks cause more frequent and intense voltage fluctuations, making it more difficult for the models to accurately capture the dynamic behavior of PEMFCs, thereby increasing prediction errors. However, under crack-free conditions, due to more stable voltage output, all models showed improved predictive performance. Finally, this study underscores the effectiveness of deep learning models in estimating the SOH of PEMFCs and provides insights into optimizing sampling and training strategies to enhance prediction accuracy. The findings make a significant contribution to the development of more reliable and efficient PEMFC systems for sustainable energy applications.

Prediction of Contact Fatigue Performance Degradation Trends Based on Multi-Domain Features and Temporal Convolutional Networks.

Contact fatigue is one of the most common failure forms of typical basic components such as bearings and gears. Accurate prediction of contact fatigue performance degradation trends in components is conducive to the scientific formulation of maintenance strategies and health management of equipment, which is of great significance for industrial production. In this paper, to realize the performance degradation trend prediction accurately, a prediction method based on multi-domain features and temporal convolutional networks (TCNs) was proposed. Firstly, a multi-domain and high-dimensional feature set of vibration signals was constructed, and performance degradation indexes with good sensitivity and strong trends were initially screened using comprehensive evaluation indexes. Secondly, the kernel principal component analysis (KPCA) method was used to eliminate redundant information among multi-domain features and construct health indexes (HIs) based on a convolutional autoencoder (CAE) network. Then, the performance degradation trend prediction model based on TCN was constructed, and the degradation trend prediction for the monitored object was realized using direct multi-step prediction. On this basis, the effectiveness of the proposed method was verified using a bearing common-use data set, and it was successfully applied to performance degradation trend prediction for rolling contact fatigue specimens. The results show that using KPCA can reduce the feature set from 14 dimensions to 4 dimensions and retain 98.33% of the information in the original preferred feature set. The method of constructing the HI based on CAE is effective, and change processes versus time of the constructed HI can truly reflect the degradation process of rolling contact fatigue specimen performance; this method has obvious advantages over the two commonly used methods for constructing HIs including auto-encoding (AE) networks and gaussian mixture models (GMMs). The model based on TCN can accurately predict the performance degradation of rolling contact fatigue specimens. Compared with prediction models based on long short-term memory (LSTM) networks and gating recurrent units (GRUs), the model based on TCN has better performance and higher prediction accuracy. The RMS error and average absolute error for a prediction step of 3 are 0.0146 and 0.0105, respectively. Overall, the proposed method has universal significance and can be applied to predict the performance degradation trend of other mechanical equipment/parts.

Unsupervised Learning-Guided Accelerated Discovery of Alkaline Anion Exchange Membranes for Fuel Cells.

Without insight into the correlation between the structure and properties, anion exchange membranes (AEMs) for fuel cells are developed usually using the empirical trial and error method or simulation methods. Here, a virtual module compound enumeration screening (V-MCES) approach, which does not require the establishment of expensive training databases and can search the chemical space containing more than 4.2×105 candidates was proposed. The accuracy of the V-MCES model was considerably improved when the model was combined with supervised learning for the feature selection of molecular descriptors. Techniques from V-MCES, correlating the molecular structures of the AEMs with the predicted chemical stability, generated a ranking list of potential high stability AEMs. Under the guidance of V-MCES, highly stable AEMs were synthesized. With understanding of AEM structure and performance by machine learning, AEM science may enter a new era of unprecedented levels of architectural design.

Performance Degradation Prediction Using LSTM with Optimized Parameters.

Predicting the degradation of mechanical components, such as rolling bearings is critical to the proper monitoring of the condition of mechanical equipment. A new method, based on a long short-term memory network (LSTM) algorithm, has been developed to improve the accuracy of degradation prediction. The model parameters are optimized via improved particle swarm optimization (IPSO). Regarding how this applies to the rolling bearings, firstly, multi-dimension feature parameters are extracted from the bearing's vibration signals and fused into responsive features by using the kernel joint approximate diagonalization of eigen-matrices (KJADE) method. Then, the between-class and within-class scatter (SS) are calculated to develop performance degradation indicators. Since network model parameters influence the predictive accuracy of the LSTM model, an IPSO algorithm is used to obtain the optimal prediction model via the LSTM model parameters' optimization. Finally, the LSTM model, with said optimal parameters, was used to predict the degradation trend of the bearing's performance. The experiment's results show that the proposed method can effectively identify the trends of degradation and performance. Moreover, the predictive accuracy of this proposed method is greater than that of the extreme learning machine (ELM) and support vector regression (SVR), which are the algorithms conventionally used in degradation modeling.

A Hybrid Prognostic Method for Proton-Exchange-Membrane Fuel Cell with Decomposition Forecasting Framework Based on AEKF and LSTM.

Durability and reliability are the major bottlenecks of the proton-exchange-membrane fuel cell (PEMFC) for large-scale commercial deployment. With the help of prognostic approaches, we can reduce its maintenance cost and maximize its lifetime. This paper proposes a hybrid prognostic method for PEMFCs based on a decomposition forecasting framework. Firstly, the original voltage data is decomposed into the calendar aging part and the reversible aging part based on locally weighted regression (LOESS). Then, we apply an adaptive extended Kalman filter (AEKF) and long short-term memory (LSTM) neural network to predict those two components, respectively. Three-dimensional aging factors are introduced in the physical aging model to capture the overall aging trend better. We utilize the automatic machine-learning method based on the genetic algorithm to train the LSTM model more efficiently and improve prediction accuracy. The aging voltage is derived from the sum of the two predicted voltage components, and we can further realize the remaining useful life estimation. Experimental results show that the proposed hybrid prognostic method can realize an accurate long-term voltage-degradation prediction and outperform the single model-based method or data-based method.

The Best of Both Worlds: A Framework for Combining Degradation Prediction with High Performance Super-Resolution Networks.

To date, the best-performing blind super-resolution (SR) techniques follow one of two paradigms: (A) train standard SR networks on synthetic low-resolution-high-resolution (LR-HR) pairs or (B) predict the degradations of an LR image and then use these to inform a customised SR network. Despite significant progress, subscribers to the former miss out on useful degradation information and followers of the latter rely on weaker SR networks, which are significantly outperformed by the latest architectural advancements. In this work, we present a framework for combining any blind SR prediction mechanism with any deep SR network. We show that a single lightweight metadata insertion block together with a degradation prediction mechanism can allow non-blind SR architectures to rival or outperform state-of-the-art dedicated blind SR networks. We implement various contrastive and iterative degradation prediction schemes and show they are readily compatible with high-performance SR networks such as RCAN and HAN within our framework. Furthermore, we demonstrate our framework's robustness by successfully performing blind SR on images degraded with blurring, noise and compression. This represents the first explicit combined blind prediction and SR of images degraded with such a complex pipeline, acting as a baseline for further advancements.

Prediction Models for Railway Track Geometry Degradation Using Machine Learning Methods: A Review.

Keeping railway tracks in good operational condition is one of the most important tasks for railway owners. As a result, railway companies have to conduct track inspections periodically, which is costly and time-consuming. Due to the rapid development in computer science, many prediction models using machine learning methods have been developed. It is possible to discover the degradation pattern and develop accurate prediction models. The paper reviews the existing prediction methods for railway track degradation, including traditional methods and prediction methods based on machine learning methods, including probabilistic methods, Artificial Neural Network (ANN), Support Vector Machine (SVM), and Grey Model (GM). The advantages, shortage, and applicability of methods are discussed, and recommendations for further research are provided.

Volumetric efficiency degradation prediction of axial piston pump based on friction and wear test.

The axial piston pump (APP) is being developed towards higher pressure and higher rotational speeds to enhance operational power density. The piston-cylinder friction pair is a critical component of the APP. Due to its lack of self-compensation capability, the leakage of the piston-cylinder friction pair escalates rapidly under increasingly severe wear conditions. An innovative method for predicting the performance degradation and lifespan of APPs based on friction and wear tests has been proposed. This method can effectively predict the performance degradation trends of APPs under different operating conditions. The actual contact force on the piston pair (PP) during operation is determined through dynamic analysis. Friction and wear tests were conducted on 38CrMoAl piston and ZCuPb15Sn8 cylinder materials under various conditions using a testing apparatus. Utilizing friction and wear theory, the volumetric efficiency of APP under various operating conditions was derived as a function of operational time. The reliability of the theoretical analysis was validated through leakage tests on the APP. The results indicate that volumetric efficiency decreases exponentially with increasing working pressure at rated speed. This research provides theoretical guidance and an experimental foundation for the failure prediction of volumetric efficiency degradation in APP.

Root Cause Analysis of Degradation in Protonic Ceramic Electrochemical Cell with Interfacial Electrical Sensors Using Data-Driven Machine Learning.

Protonic ceramic electrochemical cells (PCECs) offer promising paths for energy storage and conversion. Despite considerable achievements made, PCECs still face challenges such as physiochemical compatibility between componenets and suboptimal solid-solid contact at the interfaces between the electrolytes and electrodes. In this study, a novel approach is proposed that combines in situ electrochemical characterization of interfacial electrical sensor embedded PCECs and machine learning to quantify the contributions of different cell components to total degradation, as well as to predict the remaining useful life. The experimental results suggest that the overpotential induced by the oxygen electrode is 48% less than that of oxygen electrode/electrolyte interfacial contact for up to 1171 h. The data-driven machine learning simulation predicts the RUL of up to 2132 h. The root cause of degradation is overpotential increase induced by oxygen electrode, which accounts for 82.9% of total cell degradation. The success of the failure diagnostic model is demonstrated by its consistency with degradation modes that do not manifest in electrolysis fade during early real operations. This synergistic approach provides valuable insights into practical failure diagnosis of PCECs and has the potential to revolutionize their development by enabling improved performance prediction and material selection for enhanced durability and efficiency.

An Aging Small-Signal Model for Degradation Prediction of Microwave Heterojunction Bipolar Transistor S-Parameters Based on Prior Knowledge Neural Network.

In this paper, an aging small-signal model for degradation prediction of microwave heterojunction bipolar transistor (HBT) S-parameters based on prior knowledge neural networks (PKNNs) is explored. A dual-extreme learning machine (D-ELM) structure with an adaptive genetic algorithm (AGA) optimization process is used to simulate the fresh S-parameters of InP HBT devices and the degradation of S-parameters after accelerated aging, respectively. In addition to the reliability parametric inputs of the original aging problem, the S-parameter degradation trend obtained from the aging small-signal equivalent circuit is used as additional information to inject into the D-ELM structure. Good agreement was achieved between measured and predicted results of the degradation of S-parameters within a frequency range of 0.1 to 40 GHz.

A Hybrid Method for Performance Degradation Probability Prediction of Proton Exchange Membrane Fuel Cell.

The proton exchange membrane fuel cell (PEMFC) is a promising power source, but the short lifespan and high maintenance cost restrict its development and widespread application. Performance degradation prediction is an effective technique to extend the lifespan and reduce the maintenance cost of PEMFC. This paper proposed a novel hybrid method for the performance degradation prediction of PEMFC. Firstly, considering the randomness of PEMFC degradation, a Wiener process model is established to describe the degradation of the aging factor. Secondly, the unscented Kalman filter algorithm is used to estimate the degradation state of the aging factor from monitoring voltage. Then, in order to predict the degradation state of PEMFC, the transformer structure is used to capture the data characteristics and fluctuations of the aging factor. To quantify the uncertainty of the predicted results, we also add the Monte Carlo dropout technology to the transformer to obtain the confidence interval of the predicted result. Finally, the effectiveness and superiority of the proposed method are verified on the experimental datasets.