scholarly journals Enhancing Machine Learning Models With Prior Physical Knowledge to Aid in VIV Response Prediction

2021 ◽  
Author(s):  
Leixin Ma ◽  
Themistocles L. Resvanis ◽  
J. Kim Vandiver
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Reynolds Number ◽  
Prediction Error ◽  
Prediction Models ◽  
Response Prediction ◽  
Vibration Response ◽  
Response Amplitude ◽  
Physical Knowledge ◽  
Input Parameters

Abstract Practical engineering prediction models for flow-induced vibration are needed in the design of structures in the ocean. Research has shown that structural vibration response may be influenced by a large number of physical input parameters, such as damping and Reynolds number. Practical response prediction tools used in design are inevitably a compromise between complexity and simplicity of use. Modern machine learning tools may be used to identify which input parameters are most important. Standard machine learning techniques enable the researcher to compile a list of the most important input parameters, ranked or ordered by the effect of each on the prediction error of the model. When all inputs are treated as equals, blind application of machine learning may lead to predictions that are inconsistent with prior physical knowledge. To address this problem, we conducted a parameter selection process using a prior knowledge-based, trend-informed neural network architecture. This approach was used to identify features important to the prediction of the cross-flow vibration response amplitude of long flexible cylinders, given the known prior effect of Reynolds number and damping. The model balances the usual goal of minimizing the model prediction error, but doing so in a manner that closely follows the extensive knowledge we have of the influence of Reynolds number and damping parameter on response. The resulting neural network model was able to reveal additional insights, including the role of mode number shifting, mode dominance and travelling waves in the regulation of VIV response amplitude.

scholarly journals Using Machine Learning to Identify Important Parameters for Flow-Induced Vibration

2020 ◽  
Author(s):  
Leixin Ma ◽  
Themistocles L. Resvanis ◽  
J. Kim Vandiver
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Reynolds Number ◽  
Feature Selection ◽  
Prediction Error ◽  
Vibration Amplitude ◽  
Response Amplitude ◽  
Paper Machine ◽  
Damping Parameter ◽  
Input Parameters

Abstract Vortex-induced vibration (VIV) of long flexible cylinders in deep water involves a large number of physical variables, such as Strouhal number, Reynolds number, mass ratio, damping parameter etc. Among all the variables, it is essential to identify the most important parameters for robust VIV response prediction. In this paper, machine learning techniques were applied to iteratively reduce the dimension of VIV related parameters. The crossflow vibration amplitude was chosen as the prediction target. A neural network was used to build nonlinear mappings between a set of up to seventeen input parameters and the predicted crossflow vibration amplitude. The data used in this study came from 38-meter-long bare cylinders of 30 and 80 mm diameters, which were tested in uniform and sheared flows at Marintek in 2011. A baseline prediction using the full set of seventeen parameters gave a prediction error of 12%. The objective was then to determine the minimum number of input parameters that would yield approximately the same level of prediction accuracy as the baseline prediction. Feature selection techniques including both forward greedy feature selection and combinatorial search were implemented in a neural network model with two hidden layers. A prediction error of 13% was achieved using only six of the original seventeen input parameters. The results provide insight as to those parameters which are truly important in the prediction of the VIV of flexible cylinders. It was also shown that the coupling between inline and crossflow vibration has significant influence. It was also confirmed that Reynolds number and the damping parameter, c*, are important for predicting the crossflow response amplitude of long flexible cylinders. While shear parameter was not helpful for response amplitude prediction.

scholarly journals Dynamic Modulus Prediction of a High-Modulus Asphalt Mixture

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Chaohui Wang ◽  
Songyuan Tan ◽  
Qian Chen ◽  
Jiguo Han ◽  
Liang Song ◽  
...  
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Multiple Regression ◽  
Dynamic Modulus ◽  
Prediction Error ◽  
Prediction Models ◽  
Asphalt Mixture ◽  
High Modulus ◽  
Output Stability ◽  
Svm Model

Dynamic modulus is a key evaluation index of the high-modulus asphalt mixture, but it is relatively difficult to test and collect its data. The purpose is to achieve the accurate prediction of the dynamic modulus of the high-modulus asphalt mixture and further optimize the design process of the high-modulus asphalt mixture. Five high-temperature performance indexes of high-modulus asphalt and its mixture were selected. The correlation between the above five indexes and the dynamic modulus of the high-modulus asphalt mixture was analyzed. On this basis, the dynamic modulus prediction models of the high-modulus asphalt mixture based on small sample data were established by multiple regression, general regression neural network (GRNN), and support vector machine (SVM) neural network. According to parameter adjustment and cross-validation, the output stability and accuracy of different prediction models were compared and evaluated. The most effective prediction model was recommended. The results show that the SVM model has more significant prediction accuracy and output stability than the multiple regression model and the GRNN model. Its prediction error was 0.98–9.71%. Compared with the other two models, the prediction error of the SVM model declined by 0.50–11.96% and 3.76–13.44%. The SVM neural network was recommended as the dynamic modulus prediction model of the high-modulus asphalt mixture.

scholarly journals Harmonic Distortion Prediction Model of a Grid-Tie Photovoltaic Inverter Using an Artificial Neural Network

Energies ◽  
2019 ◽  
Vol 12 (5) ◽  
pp. 790 ◽  
Author(s):  
Matej Žnidarec ◽  
Zvonimir Klaić ◽  
Damir Šljivac ◽  
Boris Dumnić
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Power Quality ◽  
Prediction Models ◽  
Harmonic Distortion ◽  
Pv System ◽  
Current Harmonics ◽  
Pv Systems ◽  
Input Parameters ◽  
Artificial Neural

Expanding the number of photovoltaic (PV) systems integrated into a grid raises many concerns regarding protection, system safety, and power quality. In order to monitor the effects of the current harmonics generated by PV systems, this paper presents long-term current harmonic distortion prediction models. The proposed models use a multilayer perceptron neural network, a type of artificial neural network (ANN), with input parameters that are easy to measure in order to predict current harmonics. The models were trained with one-year worth of measurements of power quality at the point of common coupling of the PV system with the distribution network and the meteorological parameters measured at the test site. A total of six different models were developed, tested, and validated regarding a number of hidden layers and input parameters. The results show that the model with three input parameters and two hidden layers generates the best prediction performance.

Improving Tourist Arrival Prediction: A Big Data and Artificial Neural Network Approach

2020 ◽  
pp. 004728752092124 ◽  
Author(s):  
Wolfram Höpken ◽  
Tobias Eberle ◽  
Matthias Fuchs ◽  
Maria Lexhagen
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Big Data ◽  
Web Search ◽  
Prediction Models ◽  
Arima Models ◽  
Study Results ◽  
Artificial Neural ◽  
Prediction Approach

Because of high fluctuations of tourism demand, accurate predictions of tourist arrivals are of high importance for tourism organizations. The study at hand presents an approach to enhance autoregressive prediction models by including travelers’ web search traffic as external input attribute for tourist arrival prediction. The study proposes a novel method to identify relevant search terms and to aggregate them into a compound web-search index, used as additional input of an autoregressive prediction approach. As methods to predict tourism arrivals, the study compares autoregressive integrated moving average (ARIMA) models with the machine learning–based technique artificial neural network (ANN). Study results show that (1) Google Trends data, mirroring traveler’s online search behavior (i.e., big data information source), significantly increase the performance of tourist arrival prediction compared to autoregressive approaches using past arrivals alone, and (2) the machine learning technique ANN has the capacity to outperform ARIMA models.

Investigating Transfer Learning for Characterization and Performance Prediction in Unconventional Reservoirs

2021 ◽  
Author(s):  
Jodel Cornelio ◽  
Syamil Mohd Razak ◽  
Atefeh Jahandideh ◽  
Behnam Jafarpour ◽  
Young Cho ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Transfer Learning ◽  
Method Development ◽  
Simulated Data ◽  
Production Performance ◽  
Unconventional Reservoirs ◽  
Eagle Ford ◽  
Input Parameters

Abstract Transfer learning is a machine learning concept whereby the knowledge gained (e.g., a model developed) in one task can be transferred (applied) to solve a different but related task. In the context of unconventional reservoirs, the concept can be used to transfer a machine learning model that is learned from data in one field (or shale play) to another, thereby significantly reducing the data needs and efforts to build a new model from scratch. In this work, we study the feasibility of developing deep learning models that can capture and transfer common features in a rich dataset pertaining to a mature unconventional play to enable production prediction in a new unconventional play with limited available data. The focus in this work is on method development using simulated data that correspond to the Bakken and Eagle Ford Shale Plays as two different unconventional plays in the US. We use formation and completion parameter ranges that correspond to the Bakken play with their simulated production responses to explore different approaches for training neural network models that enable transfer learning to predict production responses of input parameters corresponding to the Eagle Ford play (previously unseen input parameters). We explore different schemes by accessing the internal components of the model to extrapolate and categorize salient features that are represented in the trained neural network. Ultimately, our goal is to use these new mechanisms to enable effective sharing and reuse of discovered features from one unconventional well to another. To extract salient trends from formation and completion input parameters and their corresponding simulated production responses, we use deep learning architectures that consist of convolutional encoder-decoder networks. The architecture is then trained with rich simulated data from one field to generate a robust mapping between the input and the output feature spaces. The "learned" parameters from this network can then be "transferred" to develop a different predictive model for another field that may lack sufficient historical data. The results show that using standard training approaches, a neural network model that is trained with sufficiently large data samples from Bakken could produce reliable prediction models for typical wells that may be found in that field. The same neural network, however, could not produce reliable predictions for a typical Eagle Ford well. Furthermore, we observe that a neural network trained with insufficient data samples from Eagle Ford produces a poor prediction model for typical wells that may be found in Eagle Ford. However, when extrapolated feature components of the Bakken neural network were integrated into the training process of the Eagle Ford neural network, the resulting predictions for typical Eagle Ford wells improved significantly. Moreover, we observe that the ability to transfer learning can improve when specialized training strategies are adopted to enable transfer learning. Using several numerical experiments, the paper presents and assesses various transfer learning strategies to predict the production performance of unconventional wells in a new area with limited information by integrating knowledge from more mature plays.

scholarly journals MIMO LS-SVR-Based Multi-Point Vibration Response Prediction in the Frequency Domain

2020 ◽  
Vol 10 (24) ◽  
pp. 8784
Author(s):  
Cheng Wang ◽  
Delei Chen ◽  
Haiyang Huang ◽  
Wei Zhan ◽  
Xiongming Lai ◽  
...  
Keyword(s):  
Neural Network ◽  
Transfer Function ◽  
Linear Regression ◽  
Frequency Domain ◽  
Matrix Method ◽  
Response Prediction ◽  
Vibration Response ◽  
Data Driven ◽  
Training Dataset ◽  
Network Method

To predict the multi-point vibration response in the frequency domain when the uncorrelated multi-source loads are unknown, a data-driven and multi-input multi-output least squares support vector regression (MIMO LS-SVR)-based method in the frequency domain is proposed. Firstly, the relationship between the measured multi-point vibration response and unmeasured multi-point vibration response is formulated using the transfer function in the frequency domain. Secondly, the data-driven multiple regression analysis problem of multi-point vibration response prediction in the frequency domain is described formally, and its mathematical model is established. With the measured multi-point vibration response as the input and the unmeasured multi-point vibration response as the output, the vibration response history data are assembled as a MIMO training dataset at each frequency. Thirdly, using the MIMO LS-SVR algorithm and MIMO history training dataset, the multi-point vibration response prediction model is built at each frequency point. By comparing the transmissibility matrix method, multiple linear regression model-based method, and MIMO neural network method, the application scope of the proposed method and its advantages are analyzed. The experimental results for acoustic and vibration experiment on a cylindrical shell verified that the MIMO LS-SVR-based method predicts the multi-point vibration response effectively when the loads are unknown, and has higher precision than the transfer function method, multiple linear regression method, MIMO neural network method, and transmissibility matrix method.

Prediction Method of NOx from Power Station Boilers Based on Neural Network

2020 ◽  
pp. 2150097
Author(s):  
Yuzuo Zhang ◽  
Yuanhao Li ◽  
Xinyan Zhang ◽  
Shijue Zheng
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Prediction Error ◽  
Learning Algorithms ◽  
Operating Conditions ◽  
Machine Learning Algorithms ◽  
Features Selection ◽  
Power Station ◽  
Data Set ◽  
Prediction Ability

In the coal-fired power generation system, it is necessary to predict the NOx emissions of power station boilers when it comes to the step to spray ammonia to ensure that NOx emissions do not exceed national standards. Using traditional machine learning algorithms in the modeling of power station boilers will require features selection and steady-state extraction, which is not suitable for practical applications. In order to reduce the NOx prediction error rate under variable operating conditions, a multi-model fusion algorithm S3LX combined with linear regression, XGBoost, and long-short-term memory recurrent neural network is proposed to model the NOx emission prediction of power station boilers. The preprocessing data scheme suitable for power station boiler data sets is proposed and implemented in this paper, which can perform numerical processing, data cleaning and data standardization for boiler’s data and features. A 7-day historical operating data set of a unit in Guangzhou Shajiao C Power Plant was used as the training set and test set and was used to build the NOx emission prediction model after data preprocessing. Results show that compared with traditional machine learning algorithms, S3LX has good prediction ability under varying conditions with an average error of 4.28%. Compared with the average prediction error of the multi-layer perceptron 9.16%, SVM 7.37%, S3LX makes the error significantly reduced and satisfies the actual engineering demand.

scholarly journals Low-Order Spherical Harmonic HRTF Restoration Using a Neural Network Approach

2020 ◽  
Vol 10 (17) ◽  
pp. 5764
Author(s):  
Benjamin Tsui ◽  
William A. P. Smith ◽  
Gavin Kearney
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Spherical Harmonic ◽  
High Frequency ◽  
Prediction Models ◽  
Machine Learning Algorithms ◽  
Network Approach ◽  
Spectral Difference ◽  
Neural Network Approach ◽  
Head Related Transfer Function

Spherical harmonic (SH) interpolation is a commonly used method to spatially up-sample sparse head related transfer function (HRTF) datasets to denser HRTF datasets. However, depending on the number of sparse HRTF measurements and SH order, this process can introduce distortions into high frequency representations of the HRTFs. This paper investigates whether it is possible to restore some of the distorted high frequency HRTF components using machine learning algorithms. A combination of convolutional auto-encoder (CAE) and denoising auto-encoder (DAE) models is proposed to restore the high frequency distortion in SH-interpolated HRTFs. Results were evaluated using both perceptual spectral difference (PSD) and localisation prediction models, both of which demonstrated significant improvement after the restoration process.

scholarly journals Comparison of Machine Learning With Logistic Regression for Prediction of Chronic Kidney Disease in the Thai Adult Population

2021 ◽  
Vol 44 (4) ◽  
pp. 1-12
Author(s):  
Ratchainant Thammasudjarit ◽  
Punnathorn Ingsathit ◽  
Sigit Ari Saputro ◽  
Atiporn Ingsathit ◽  
Ammarin Thakkinstian
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Chronic Kidney Disease ◽  
Logistic Regression ◽  
Random Forest ◽  
Kidney Disease ◽  
Decision Tree ◽  
Prediction Model ◽  
Prediction Models ◽  
The Neural Network

Background: Chronic kidney disease (CKD) takes huge amounts of resources for treatments. Early detection of patients by risk prediction model should be useful in identifying risk patients and providing early treatments. Objective: To compare the performance of traditional logistic regression with machine learning (ML) in predicting the risk of CKD in Thai population. Methods: This study used Thai Screening and Early Evaluation of Kidney Disease (SEEK) data. Seventeen features were firstly considered in constructing prediction models using logistic regression and 4 MLs (Random Forest, Naïve Bayes, Decision Tree, and Neural Network). Data were split into train and test data with a ratio of 70:30. Performances of the model were assessed by estimating recall, C statistics, accuracy, F1, and precision. Results: Seven out of 17 features were included in the prediction models. A logistic regression model could well discriminate CKD from non-CKD patients with the C statistics of 0.79 and 0.78 in the train and test data. The Neural Network performed best among ML followed by a Random Forest, Naïve Bayes, and a Decision Tree with the corresponding C statistics of 0.82, 0.80, 0.78, and 0.77 in training data set. Performance of these corresponding models in testing data decreased about 5%, 3%, 1%, and 2% relative to the logistic model by 2%. Conclusions: Risk prediction model of CKD constructed by the logit equation may yield better discrimination and lower tendency to get overfitting relative to ML models including the Neural Network and Random Forest.  

Sign in / Sign up

Export Citation Format

Share Document