scholarly journals Real Time Predictions of VGF-GaAs Growth Dynamics by LSTM Neural Networks

Crystals ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 138
Author(s):  
Natasha Dropka ◽  
Stefan Ecklebe ◽  
Martin Holena
Keyword(s):  
Neural Networks ◽  
Real Time ◽  
Network Performance ◽  
Short Term Memory ◽  
Predictive Accuracy ◽  
Growth Dynamics ◽  
Vertical Gradient ◽  
Performance Criteria ◽  
Interface Position ◽  
Vertical Gradient Freeze

The aim of this study was to assess the aptitude of the recurrent Long Short-Term Memory (LSTM) neural networks for fast and accurate predictions of process dynamics in vertical-gradient-freeze growth of gallium arsenide crystals (VGF-GaAs) using datasets generated by numerical transient simulations. Real time predictions of the temperatures and solid–liquid interface position in GaAs are crucial for control applications and for process visualization, i.e., for generation of digital twins. In the reported study, an LSTM network was trained on 1950 datasets with 2 external inputs and 6 outputs. Based on network performance criteria and training results, LSTMs showed the very accurate predictions of the VGF-GaAs growth process with median root-mean-square-error (RMSE) values of 2 × 10−3. This deep learning method achieved a superior predictive accuracy and timeliness compared with more traditional Nonlinear AutoRegressive eXogenous (NARX) recurrent networks.

scholarly journals Short-Term Net Load Forecasting with Singular Spectrum Analysis and LSTM Neural Networks

Energies ◽  
2021 ◽  
Vol 14 (14) ◽  
pp. 4107
Author(s):  
Akylas Stratigakos ◽  
Athanasios Bachoumis ◽  
Vasiliki Vita ◽  
Elias Zafiropoulos
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Spectrum Analysis ◽  
Short Term Memory ◽  
Predictive Accuracy ◽  
Singular Spectrum Analysis ◽  
Hybrid Approach ◽  
Load Forecasting ◽  
Short Term ◽  
Singular Spectrum

Short-term electricity load forecasting is key to the safe, reliable, and economical operation of power systems. An important challenge that arises with high-frequency load series, e.g., hourly load, is how to deal with the complex seasonal patterns that are present. Standard approaches suggest either removing seasonality prior to modeling or applying time series decomposition. This work proposes a hybrid approach that combines Singular Spectrum Analysis (SSA)-based decomposition and Artificial Neural Networks (ANNs) for day-ahead hourly load forecasting. First, the trajectory matrix of the time series is constructed and decomposed into trend, oscillating, and noise components. Next, the extracted components are employed as exogenous regressors in a global forecasting model, comprising either a Multilayer Perceptron (MLP) or a Long Short-Term Memory (LSTM) predictive layer. The model is further extended to include exogenous features, e.g., weather forecasts, transformed via parallel dense layers. The predictive performance is evaluated on two real-world datasets, controlling for the effect of exogenous features on predictive accuracy. The results showcase that the decomposition step improves the relative performance for ANN models, with the combination of LSTM and SAA providing the best overall performance.

scholarly journals Towards real-time respiratory motion prediction based on long short-term memory neural networks

2019 ◽  
Vol 64 (8) ◽  
pp. 085010 ◽  
Author(s):  
Hui Lin ◽  
Chengyu Shi ◽  
Brian Wang ◽  
Maria F Chan ◽  
Xiaoli Tang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Real Time ◽  
Respiratory Motion ◽  
Short Term Memory ◽  
Motion Prediction ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

scholarly journals Real-Time State of Charge Estimation for Each Cell of Lithium Battery Pack Using Neural Networks

2020 ◽  
Vol 10 (23) ◽  
pp. 8644
Author(s):  
JaeHyung Park ◽  
JongHyun Lee ◽  
SiJin Kim ◽  
InSoo Lee
Keyword(s):  
Neural Networks ◽  
Real Time ◽  
Alternative Energy ◽  
Lithium Battery ◽  
Short Term Memory ◽  
Discharge Rate ◽  
State Of Charge ◽  
Battery Pack ◽  
Storage Device ◽  
The Difference

With the emergence of problems on environmental pollutions, lithium batteries have attracted considerable attention as an efficient and nature-friendly alternative energy storage device owing to their advantages, such as high power density, low self-discharge rate, and long life cycle. They are widely used in numerous applications, from everyday items, such as smartphones, wireless vacuum cleaners, and wireless power tools, to transportation means, such as electric vehicles and bicycles. In this paper, the state of charge (SOC) of each cell of the lithium battery pack was estimated in real time using two types of neural networks: Multi-layer Neural Network (MNN) and Long Short-Term Memory (LSTM). To determine the difference in the SOC estimation performance under various conditions, the input values were compared using 2, 6, and 8 input values, and the difference according to the use of temperature variable data was compared, and finally, the MNN and LSTM. The differences were compared. Real-time SOC was estimated using the method with the lowest error rate.

scholarly journals Monitoring Mixing Processes Using Ultrasonic Sensors and Machine Learning

Sensors ◽  
2020 ◽  
Vol 20 (7) ◽  
pp. 1813 ◽  
Author(s):  
Alexander L. Bowler ◽  
Serafim Bakalis ◽  
Nicholas J. Watson
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Real Time ◽  
Short Term Memory ◽  
Support Vector ◽  
Learning Approaches ◽  
Learning Models ◽  
Ultrasonic Sensors ◽  
Multisensor Data Fusion ◽  
Machine Learning Models

Mixing is one of the most common processes across food, chemical, and pharmaceutical manufacturing. Real-time, in-line sensors are required for monitoring, and subsequently optimising, essential processes such as mixing. Ultrasonic sensors are low-cost, real-time, in-line, and applicable to characterise opaque systems. In this study, a non-invasive, reflection-mode ultrasonic measurement technique was used to monitor two model mixing systems. The two systems studied were honey-water blending and flour-water batter mixing. Classification machine learning models were developed to predict if materials were mixed or not mixed. Regression machine learning models were developed to predict the time remaining until mixing completion. Artificial neural networks, support vector machines, long short-term memory neural networks, and convolutional neural networks were tested, along with different methods for engineering features from ultrasonic waveforms in both the time and frequency domain. Comparisons between using a single sensor and performing multisensor data fusion between two sensors were made. Classification accuracies of up to 96.3% for honey-water blending and 92.5% for flour-water batter mixing were achieved, along with R2 values for the regression models of up to 0.977 for honey-water blending and 0.968 for flour-water batter mixing. Each prediction task produced optimal performance with different algorithms and feature engineering methods, vindicating the extensive comparison between different machine learning approaches.

scholarly journals APPLICATION OF ARTIFICIAL INTELLIGENCE TO BITCOIN COURSE MODELLING

2020 ◽  
pp. 14-20
Author(s):  
O. Liashenko ◽  
T. Kravets ◽  
Y. Repetskiyi
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Network Performance ◽  
Short Term Memory ◽  
Back Propagation ◽  
Absolute Deviation ◽  
Artificial Intelligence Algorithm ◽  
The Mean ◽  
Long Short Term Memory ◽  
Learning Machine

Artificial neural networks are modern methods suitable for solving the problem of nonlinear dependency approximation, which is successfully applied in many fields. This paper compares the predictive capabilities of Back Propagation, Radial Basis Function, Extreme Learning Machine, and Long-Short Term Memory neural networks to determine which artificial intelligence algorithm is best for modeling the price of Bitcoin opening. The criterion for comparing network performance was the standard deviation, the mean absolute deviation, and the accuracy of predicting the direction of change of course. At the same time, in the study of time series, it is recommended to perform a comprehensive data analysis using appropriate networks, depending on the length of the series and the specificity of the database.

scholarly journals Layer-Wise Relevance Propagation for Interpreting LSTM-RNN Decisions in Predictive Maintenance

2021 ◽  
Author(s):  
Haiyue Wu ◽  
Aihua Huang ◽  
John W. Sutherland
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Short Term Memory ◽  
Predictive Accuracy ◽  
Predictive Maintenance ◽  
Data Driven ◽  
Sensor Data ◽  
Neural Network Models ◽  
Advanced Technique

Abstract Predictive maintenance (PdM) is an advanced technique to predict the time to failure (TTF) of a system. PdM collects sensor data on the health of a system, processes the information using data analytics, and then establishes data-driven models that can forecast system failure. Deep neural networks are increasingly being used as these data-driven models owing to their high predictive accuracy and efficiency. However, deep neural networks are often criticized as being “black boxes,” which owing to their multi-layered and non-linear structure provide little insight into the underlying physics of the system being monitored, and that are nontransparent and untraceable in their predictions. In order to address this issue, the layer-wise relevance propagation (LRP) technique is applied to analyze a long short-term memory (LSTM) recurrent neural network (RNN) model. The proposed method is demonstrated and validated for a bearing health monitoring study based on vibration data. The obtained LRP results provide insights into how the model “learns” from the input data and demonstrate the distribution of contribution/relevance to the neural network classification in the input space. In addition, comparisons are made with gradient-based sensitivity analysis to show the power of LRP in interpreting RNN models. The LRP is proved to have promising potential in interpreting deep neural network models and improving model accuracy and efficiency for PdM.

Sign in / Sign up

Export Citation Format

Share Document