4.4 Article

Stacking ensemble transfer learning based thermal displacement prediction system

Related references

Note: Only part of the references are listed.
Article Engineering, Multidisciplinary

Using LSTM neural network to predict remaining useful life of electrolytic capacitors in dynamic operating conditions

Ameneh Forouzandeh Shahraki et al.

Summary: This paper proposes a RUL prediction method for aluminum electrolytic capacitors based on deep learning. The method uses original condition monitoring and operating condition data, avoiding the need to assume a particular degradation process, while ensuring high prediction performance.

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART O-JOURNAL OF RISK AND RELIABILITY (2023)

Article Computer Science, Information Systems

Multiarea Inertia Estimation Using Convolutional Neural Networks and Federated Learning

Abodh Poudyal et al.

Summary: This article introduces a client-server-based federated learning framework to estimate power system inertia in multiarea systems. By utilizing local frequency measurements and training with CNN, the inertia constant for each area can be accurately estimated, outperforming conventional neural network-based estimation techniques.

IEEE SYSTEMS JOURNAL (2022)

Article Engineering, Mechanical

Prediction of frictional braking noise based on brake dynamometer test and artificial intelligent algorithms

Shuwen Wang et al.

Summary: This study quantitatively analyzed and predicted frictional braking noise using brake noise dynamometer test data and artificial intelligent algorithms. A prediction method for frictional braking noise was proposed, validated for feasibility, and shown to save time for brake system development and testing.

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING (2022)

Article Computer Science, Information Systems

Transfer Learning for Autonomous Cell Activation Based on Relational Reinforcement Learning With Adaptive Reward

Guolin Sun et al.

Summary: The article proposes an energy consumption optimization strategy based on DRL and TL techniques, using adaptive reward to balance user QoS requirements and system energy consumption. The cell activation problem is formulated as an MDP, and a relational DRL model is introduced to meet user QoS requirements.

IEEE SYSTEMS JOURNAL (2022)

Article Engineering, Multidisciplinary

A multiple-point monitoring model for concrete dam displacements based on correlated multiple-output support vector regression

Qiubing Ren et al.

Summary: This study proposed a dam multiple-point displacement monitoring model based on the SVR algorithm, which can analyze and predict displacements at multiple measurement points simultaneously. By introducing weight vectors to separate common and individual information and considering spatiotemporal correlations, the CMOSVR-based model showed better monitoring performance and higher adaptability to various scenarios compared to conventional single-point monitoring models.

STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL (2022)

Article Computer Science, Information Systems

CapsGaNet: Deep Neural Network Based on Capsule and GRU for Human Activity Recognition

Xiaojie Sun et al.

Summary: CapsGaNet, a novel framework for spatiotemporal multi-feature extraction, effectively improves the accuracy of human activity recognition. The construction of the DAAD dataset and the proposed threshold-based approach for aggressive activity detection meet the requirements of high real-time and low computational complexity in smart prison scenarios.

IEEE SYSTEMS JOURNAL (2022)

Article Engineering, Electrical & Electronic

MEMS enabled suspended silicon waveguide platform for long-wave infrared modulation applications

Xinmiao Liu et al.

Summary: This paper presents a MEMS tunable directional coupler operating in the long-wave infrared wavelength range, with a focus on the miniaturization of the device through membrane transfer technology. The experimental results show that the device has excellent optical performance and response time, and its application in computational spectroscopy has been validated.

INTERNATIONAL JOURNAL OF OPTOMECHATRONICS (2022)

Article Computer Science, Information Systems

Data-Adaptive Censoring for Short-Term Wind Speed Predictors Based on MLP, RNN, and SVM

Ali Ogun Sarp et al.

Summary: This study introduces novel short-term wind speed predictors based on MLP, RNN, and SVM with the DAC strategy. The DAC strategy, based on the LMS algorithm, iteratively selects informative wind data for training and reduces the training costs without significantly affecting the prediction performances. Simulation results on real-life large-scale data confirm the attractive features of the proposed predictors.

IEEE SYSTEMS JOURNAL (2022)

Article Engineering, Multidisciplinary

An iterative method for leakage zone identification in water distribution networks based on machine learning

Jingyu Chen et al.

Summary: An iterative method combining k-means clustering with the random forest classifier is proposed for leakage identification in water distribution networks to improve the accuracy of the classifier model. The method effectively identifies simultaneous leakages in different scenarios, demonstrating its effectiveness in leak detection.

STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL (2021)

Article Computer Science, Information Systems

Boosting Grid Efficiency and Resiliency by Releasing V2G Potentiality Through a Novel Rolling Prediction-Decision Framework and Deep-LSTM Algorithm

Shuangqi Li et al.

Summary: This article proposes a novel V2G scheduling approach that considers predicted V2G capacity, which can significantly enhance the efficiency and resiliency of the grid. The design of a brand-new rolling prediction-decision framework bridges the gap between optimization and forecasting phases, allowing for more reasonable utilization of predicted information.

IEEE SYSTEMS JOURNAL (2021)

Article Engineering, Electrical & Electronic

A Novel Quench Detection Method Based on CNN-LSTM Model

Xiao Zhou et al.

Summary: The proposed quench detection method based on the CNN-LSTM model can achieve real-time and accurate detection of quench, balancing sensitivity and accuracy by adjusting the probability threshold. Experimental results demonstrate that this method is more advanced compared to the traditional voltage threshold method.

IEEE TRANSACTIONS ON APPLIED SUPERCONDUCTIVITY (2021)

Article Computer Science, Information Systems

Toward Deep Transfer Learning in Industrial Internet of Things

Xing Liu et al.

Summary: This article proposes a general framework to adopt transfer learning in Industrial IoT (IIoT) systems, categorizing the application of transfer learning into four common scenarios based on dataset size and distribution. Design workflows are created for each scenario based on their characteristics.

IEEE INTERNET OF THINGS JOURNAL (2021)

Article Engineering, Electrical & Electronic

Mechanism of peripheral nerve modulation and recent applications

Heejae Shin et al.

Summary: Neuromodulation is an interdisciplinary field involving neuroscience, neural engineering, and medicine, which has attracted increasing interest due to promising applications like bionic limbs. The review covers the basic mechanisms, methods, and applications of peripheral neuromodulation, including the structure and functions of the human nervous system, neurophysiology, electrical and optogenetic approaches, and closed-loop systems integrated with sensors and controllers. Advanced applications combining neuromodulation with sensor technology are exemplified through bionic limb systems.

INTERNATIONAL JOURNAL OF OPTOMECHATRONICS (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Predictive Maintenance of Relative Humidity Using Random Forest Method

Aji Teguh Prihatno et al.

Summary: This paper discusses the implementation of predicting Relative Humidity in a smart factory environment using the Random Forest method, achieving an accuracy of 82.49%. The research goal may contribute to lowering costs and increasing maintenance efficiency in the manufacturing industry.

3RD INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE IN INFORMATION AND COMMUNICATION (IEEE ICAIIC 2021) (2021)

Article Computer Science, Information Systems

A Transfer and Deep Learning-Based Method for Online Frequency Stability Assessment and Control

Jian Xie et al.

Summary: The proposed deep learning model combining CNN and LSTM networks shows superior performance in predicting power system frequency control. The use of transfer learning to address challenges of insufficient data and changes in operating conditions has been validated, demonstrating the effectiveness of the model.

IEEE ACCESS (2021)

Article Engineering, Electrical & Electronic

MEMS gratings and their applications

Guangcan Zhou et al.

Summary: The integration of MEMS technology with diffraction grating provides an efficient way to miniaturize optical systems, particularly in the directions of MEMS scanning gratings and MEMS tunable gratings. Grating scanners, with their dispersive properties, are attractive in wavelength sensing applications and play a significant role in scanning systems; while tunable gratings employ MEMS actuators to dynamically change diffraction properties for specific applications.

INTERNATIONAL JOURNAL OF OPTOMECHATRONICS (2021)

Article Engineering, Electrical & Electronic

Feedback motion control of a spatial double pendulum manipulator relying on swept laser based pose estimation

Roland R. Zana et al.

Summary: The development of spatial pose estimation devices for mobile and cable-suspended robots, particularly with the use of the HTC Vive sensor, has been of interest to researchers. Experiments with a double pendulum robot equipped with the HTC Vive Tracker demonstrated the effectiveness of a linear feedback controller. The study showed that the HTC Vive's accuracy is sufficient for feedback position control of indoor mobile robots.

INTERNATIONAL JOURNAL OF OPTOMECHATRONICS (2021)

Article Energy & Fuels

Preventive control for power system transient security based on XGBoost and DCOPF with consideration of model interpretability

Songtao Zhang et al.

Summary: This paper proposes a new approach for online power system transient security assessment and preventive control based on XGBoost and DC optimal power flow. It utilizes XGBoost and local feature importance evaluation, applies SMOTE+ENN for data rebalancing, trains XGBoost model with time domain simulations, and implements generation rescheduling with the differential evolution algorithm. The feasibility and effectiveness of the proposed approach are demonstrated on test systems and operational models.

CSEE JOURNAL OF POWER AND ENERGY SYSTEMS (2021)

Article Engineering, Electrical & Electronic

Correlation of accommodation and lens location with higher-order aberrations and axial length elongation during orthokeratology lens wear

Jy-Been Liang et al.

Summary: Overnight orthokeratology has effects on higher-order wavefront aberrations, axial length elongation, and accommodation. The study found a strong correlation between spherical aberration and changes in corneal thickness and curvature, as well as a correlation between axial length elongation and coma and spherical aberration.

INTERNATIONAL JOURNAL OF OPTOMECHATRONICS (2021)

Article Computer Science, Artificial Intelligence

Reliable Accuracy Estimates from k-Fold Cross Validation

Tzu-Tsung Wong et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2020)

Article Engineering, Manufacturing

Adaptive thermal displacement compensation method based on deep learning

Makoto Fujishima et al.

CIRP JOURNAL OF MANUFACTURING SCIENCE AND TECHNOLOGY (2019)

Article Computer Science, Information Systems

Short-Term Non-Residential Load Forecasting Based on Multiple Sequences LSTM Recurrent Neural Network

Runhai Jiao et al.

IEEE ACCESS (2018)