Ensemble Methods for APS In-Flight Particle Temperature and Velocity Prediction Considering Torch Electrodes Ageing

2021 ◽  
Author(s):  
K.R. Yu ◽  
C.V. Cojocaru ◽  
F. Ilinca ◽  
E. Irissou
Keyword(s):  
Powder Particle ◽  
Process Parameters ◽  
Particle Temperature ◽  
Ensemble Methods ◽  
Machine Learning Algorithms ◽  
Atmospheric Plasma ◽  
Gradient Boosting ◽  
Input Process ◽  
Process Data ◽  
Particle Characteristics

Abstract In an atmospheric plasma spray (APS) process; in-flight powder particle characteristics; such as the particle velocity and temperature; have significant influence on the coating formation. The nonlinear relationship between the input process parameters and in-flight particle characteristics is thus of paramount importance for coating properties design and quality control. It is also known that the ageing of torch electrodes affects this relationship. In recent years; machine learning algorithms have proven to be able to take into account such complex nonlinear interactions. This work illustrates the application of ensemble methods based on decision tree algorithms to evaluate and to predict in-flight particle temperature and velocity during an APS process considering torch electrodes ageing. Experiments were performed to record simultaneously the input process parameters; the in-flight powder particle characteristics and the electrodes usage time. Various spray durations were considered to emulate industrial coating spray production settings. Random forest and gradient boosting algorithms were used to rank and select the features for the APS process data recorded as the electrodes aged and the corresponding predictive models were compared. The time series aspect of the data will be examined.

scholarly journals Comparison of Ensemble Machine Learning Methods for Soil Erosion Pin Measurements

2021 ◽  
Vol 10 (1) ◽  
pp. 42
Author(s):  
Kieu Anh Nguyen ◽  
Walter Chen ◽  
Bor-Shiun Lin ◽  
Uma Seeboonruang
Keyword(s):  
Machine Learning ◽  
Soil Erosion ◽  
Ensemble Methods ◽  
Machine Learning Algorithms ◽  
Multivariate Adaptive Regression Splines ◽  
Gradient Boosting ◽  
Support Vector ◽  
Ensemble Machine Learning ◽  
Boosting Method ◽  
Bagging Method

Although machine learning has been extensively used in various fields, it has only recently been applied to soil erosion pin modeling. To improve upon previous methods of quantifying soil erosion based on erosion pin measurements, this study explored the possible application of ensemble machine learning algorithms to the Shihmen Reservoir watershed in northern Taiwan. Three categories of ensemble methods were considered in this study: (a) Bagging, (b) boosting, and (c) stacking. The bagging method in this study refers to bagged multivariate adaptive regression splines (bagged MARS) and random forest (RF), and the boosting method includes Cubist and gradient boosting machine (GBM). Finally, the stacking method is an ensemble method that uses a meta-model to combine the predictions of base models. This study used RF and GBM as the meta-models, decision tree, linear regression, artificial neural network, and support vector machine as the base models. The dataset used in this study was sampled using stratified random sampling to achieve a 70/30 split for the training and test data, and the process was repeated three times. The performance of six ensemble methods in three categories was analyzed based on the average of three attempts. It was found that GBM performed the best among the ensemble models with the lowest root-mean-square error (RMSE = 1.72 mm/year), the highest Nash-Sutcliffe efficiency (NSE = 0.54), and the highest index of agreement (d = 0.81). This result was confirmed by the spatial comparison of the absolute differences (errors) between model predictions and observations using GBM and RF in the study area. In summary, the results show that as a group, the bagging method and the boosting method performed equally well, and the stacking method was third for the erosion pin dataset considered in this study.

Artificial Intelligence Based Approach for Predicting Fatigue Strength Using Composition and Process Parameters

2020 ◽  
Author(s):  
Arvind Keprate ◽  
R. M. Chandima Ratnayake
Keyword(s):  
Artificial Intelligence ◽  
Fatigue Strength ◽  
Process Parameters ◽  
Fatigue Testing ◽  
Simulated Data ◽  
Machine Learning Algorithms ◽  
Coefficient Of Determination ◽  
Gradient Boosting ◽  
Data Set ◽  
Strength Based

Abstract Accurate prediction of the fatigue strength of steels is vital, due to the extremely high cost (and time) of fatigue testing and the often fatal consequences of fatigue failures. The work presented in this paper is an extension of the previous paper submitted to OMAE 2019. The main objective of this manuscript is to utilize Artificial Intelligence (AI) to predict fatigue strength, based on composition and process parameters, using the fatigue dataset for carbon and low alloy steel available from the National Institute of Material Science (NIMS) database, MatNavi. A deep learning framework Keras is used to build a Neural Network (NN), which is trained and tested on the data set obtained from MatNavi. The fatigue strength values estimated using NN are compared to the values predicted by the gradient boosting algorithm, which was the most accurate model in the OMAE 2019 paper. The comparison is done using metrics such as root mean square error (RMSE), Mean Absolute Error (MAE), Coefficient of Determination (R2) and Explained Variance Score (EVS). Thereafter, the trained NN model is used to make predictions of fatigue strength for the simulated data (1 million samples) of input parameters, which is then used to generate conditional probability tables for the Bayesian Network (BN). The main advantage of using BN over previously used machine learning algorithms is that BN can be used to make both forward and backward propagation during the Bayesian inference. A case study illustrating the applicability of the proposed approach is also presented. Furthermore, a dashboard is developed using PowerBI, which can be used by practicing engineers to estimate fatigue strength based on composition and process parameters.

scholarly journals Using Reinforcement Learning for Generating Polynomial Models to Explain Complex Data

2021 ◽  
Vol 2 (2) ◽  
Author(s):  
Niclas Ståhl ◽  
Gunnar Mathiason ◽  
Dellainey Alcacoas
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Process Parameters ◽  
Machine Learning Algorithms ◽  
Complex Data ◽  
Low Carbon ◽  
Learning To Learn ◽  
Process Data ◽  
Operator Experience ◽  
Prediction Systems

AbstractBasic oxygen steel making is a complex chemical and physical industrial process that reduces a mix of pig iron and recycled scrap into low-carbon steel. Good understanding of the process and the ability to predict how it will evolve requires long operator experience, but this can be augmented with process target prediction systems. Such systems may use machine learning to learn a model of the process based on a long process history, and have an advantage in that they can make use of vastly more process parameters than operators can comprehend. While it has become less of a challenge to build such prediction systems using machine learning algorithms, actual production implementations are rare. The hidden reasoning of complex prediction model and lack of transparency prevents operator trust, even for models that show high accuracy predictions. To express model behaviour and thereby increasing transparency we develop a reinforcement learning (RL) based agent approach, which task is to generate short polynomials that can explain the model of the process from what it has learnt from process data. The RL agent is rewarded on how well it generates polynomials that can predict the process from a smaller subset of the process parameters. Agent training is done with the REINFORCE algorithm, which enables the sampling of multiple concurrently plausible polynomials. Having multiple polynomials, process developers can evaluate several alternative and plausible explanations, as observed in the historic process data. The presented approach gives both a trained generative model and a set of polynomials that can explain the process. The performance of the polynomials is as good as or better than more complex and less interpretable models. Further, the relative simplicity of the resulting polynomials allows good generalisation to fit new instances of data. The best of the resulting polynomials in our evaluation achieves a better $$R^2$$ R 2 score on the test set in comparison to the other machine learning models evaluated.

scholarly journals Analysis of Heart Disease Using Parallel and Sequential Ensemble Methods With Feature Selection Techniques

2021 ◽  
Vol 6 (1) ◽  
pp. 40-56
Author(s):  
Dhyan Chandra Yadav ◽  
Saurabh Pal
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Random Forest ◽  
Decision Tree ◽  
Classification Accuracy ◽  
Ensemble Methods ◽  
Machine Learning Algorithms ◽  
Ensemble Method ◽  
Gradient Boosting ◽  
High Classification Accuracy

This paper has organized a heart disease-related dataset from UCI repository. The organized dataset describes variables correlations with class-level target variables. This experiment has analyzed the variables by different machine learning algorithms. The authors have considered prediction-based previous work and finds some machine learning algorithms did not properly work or do not cover 100% classification accuracy with overfitting, underfitting, noisy data, residual errors on base level decision tree. This research has used Pearson correlation and chi-square features selection-based algorithms for heart disease attributes correlation strength. The main objective of this research to achieved highest classification accuracy with fewer errors. So, the authors have used parallel and sequential ensemble methods to reduce above drawback in prediction. The parallel and serial ensemble methods were organized by J48 algorithm, reduced error pruning, and decision stump algorithm decision tree-based algorithms. This paper has used random forest ensemble method for parallel randomly selection in prediction and various sequential ensemble methods such as AdaBoost, Gradient Boosting, and XGBoost Meta classifiers. In this paper, the experiment divides into two parts: The first part deals with J48, reduced error pruning and decision stump and generated a random forest ensemble method. This parallel ensemble method calculated high classification accuracy 100% with low error. The second part of the experiment deals with J48, reduced error pruning, and decision stump with three sequential ensemble methods, namely AdaBoostM1, XG Boost, and Gradient Boosting. The XG Boost ensemble method calculated better results or high classification accuracy and low error compare to AdaBoostM1 and Gradient Boosting ensemble methods. The XG Boost ensemble method calculated 98.05% classification accuracy, but random forest ensemble method calculated high classification accuracy 100% with low error.

Prediction of residual stress in electron beam welding of stainless steel from process parameters and natural frequency of vibrations using machine-learning algorithms

2020 ◽  
pp. 095440622095034
Author(s):  
Debasish Das ◽  
Amit Kr Das ◽  
DK Pratihar ◽  
GG Roy
Keyword(s):  
Machine Learning ◽  
Residual Stress ◽  
Stainless Steel ◽  
Electron Beam ◽  
Process Parameters ◽  
Electron Beam Welding ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Input Process

In the present study, machine learning algorithms have been used to predict residual stress during electron beam welding of stainless steel using the information of input process parameters and natural frequency of vibrations. Accelerating voltage, beam current and welding speed have been considered as input process parameters. Both residual stress and natural frequencies of vibration of the weld obtained using each set of the input parameters are measured experimentally. A number of machine learning algorithms, namely M5 algorithm-based Model Trees Regression, Random forest, Support Vector Regression, Reduced Error Pruning Tree, Multi-layer perceptron, Instance-based k-nearest neighbor algorithm, and Locally weighted learning have been used for the said purpose. Support vector regression and Locally weighted learning are found to perform consistently good and bad, respectively. The predicted welding residual stresses have been validated experimentally through X-ray diffraction (XRD) and good agreements are obtained. In addition, statistical tests are conducted, and the estimated reliability values of the employed models are analyzed through Monte-Carlo simulations.

scholarly journals Monitoring and control of polymer production line based on machine learning

2021 ◽  
Vol 2119 (1) ◽  
pp. 012159
Author(s):  
S Abdurakipov
Keyword(s):  
Machine Learning ◽  
Process Parameters ◽  
Learning Model ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Real Problem ◽  
Monitoring And Control ◽  
Machine Learning Model ◽  
Statistical Relationships ◽  
And Control

Abstract The work is devoted to the development of an application for monitoring and controlling the state of equipment (extruder) for the petrochemical industry based on sensor readings using a machine learning model. The statistical relationships of the technological process parameters are analyzed, the most significant parameters influencing the occurrence of failures are determined using SHAP values. The hypotheses regarding the effectiveness of various machine learning algorithms in relation to the real problem of predicting the technical state of the extruder are tested. A gradient boosting model has been developed to predict the probability of extruder shutdown due to the formation of polypropylene agglomerates. The developed application allows interpreting the results of the model, which makes it possible to select the most important process parameters that have the greatest impact on the probability of extruder failure, and also proposing a prototype of an extruder monitoring system based on sensor readings using a machine learning model.

Forecasting US movies box office performances in Turkey using machine learning algorithms

2020 ◽  
Vol 39 (5) ◽  
pp. 6579-6590
Author(s):  
Sandy Çağlıyor ◽  
Başar Öztayşi ◽  
Selime Sezgin
Keyword(s):  
Machine Learning ◽  
Global Economy ◽  
Learning Algorithms ◽  
Forecast Model ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
High Stakes ◽  
Box Office ◽  
Industry Forecast ◽  
The Impact

The motion picture industry is one of the largest industries worldwide and has significant importance in the global economy. Considering the high stakes and high risks in the industry, forecast models and decision support systems are gaining importance. Several attempts have been made to estimate the theatrical performance of a movie before or at the early stages of its release. Nevertheless, these models are mostly used for predicting domestic performances and the industry still struggles to predict box office performances in overseas markets. In this study, the aim is to design a forecast model using different machine learning algorithms to estimate the theatrical success of US movies in Turkey. From various sources, a dataset of 1559 movies is constructed. Firstly, independent variables are grouped as pre-release, distributor type, and international distribution based on their characteristic. The number of attendances is discretized into three classes. Four popular machine learning algorithms, artificial neural networks, decision tree regression and gradient boosting tree and random forest are employed, and the impact of each group is observed by compared by the performance models. Then the number of target classes is increased into five and eight and results are compared with the previously developed models in the literature.

Predicting Undesired Treatment Outcome in Mental Healthcare: Machine Learning Study (Preprint)

2019 ◽  
Author(s):  
Kasper Van Mens ◽  
Joran Lokkerbol ◽  
Richard Janssen ◽  
Robert de Lange ◽  
Bea Tiemens
Keyword(s):  
Machine Learning ◽  
Treatment Outcome ◽  
Mental Health Treatment ◽  
Mental Healthcare ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Trade Off ◽  
Trade Offs ◽  
Outcome Monitoring ◽  
Extreme Gradient Boosting

BACKGROUND It remains a challenge to predict which treatment will work for which patient in mental healthcare. OBJECTIVE In this study we compare machine algorithms to predict during treatment which patients will not benefit from brief mental health treatment and present trade-offs that must be considered before an algorithm can be used in clinical practice. METHODS Using an anonymized dataset containing routine outcome monitoring data from a mental healthcare organization in the Netherlands (n = 2,655), we applied three machine learning algorithms to predict treatment outcome. The algorithms were internally validated with cross-validation on a training sample (n = 1,860) and externally validated on an unseen test sample (n = 795). RESULTS The performance of the three algorithms did not significantly differ on the test set. With a default classification cut-off at 0.5 predicted probability, the extreme gradient boosting algorithm showed the highest positive predictive value (ppv) of 0.71(0.61 – 0.77) with a sensitivity of 0.35 (0.29 – 0.41) and area under the curve of 0.78. A trade-off can be made between ppv and sensitivity by choosing different cut-off probabilities. With a cut-off at 0.63, the ppv increased to 0.87 and the sensitivity dropped to 0.17. With a cut-off of at 0.38, the ppv decreased to 0.61 and the sensitivity increased to 0.57. CONCLUSIONS Machine learning can be used to predict treatment outcomes based on routine monitoring data.This allows practitioners to choose their own trade-off between being selective and more certain versus inclusive and less certain.

scholarly journals Feasibility of Machine Learning Algorithms for Predicting the Deformation of Anodic Titanium Films by Modulating Anodization Processes

Materials ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 1089
Author(s):  
Sung-Hee Kim ◽  
Chanyoung Jeong
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Multiclass Classification ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Smart Manufacturing ◽  
Gradient Boosting ◽  
Experimental Conditions ◽  
Learning Techniques ◽  
Tio2 Nanostructures

This study aims to demonstrate the feasibility of applying eight machine learning algorithms to predict the classification of the surface characteristics of titanium oxide (TiO2) nanostructures with different anodization processes. We produced a total of 100 samples, and we assessed changes in TiO2 nanostructures’ thicknesses by performing anodization. We successfully grew TiO2 films with different thicknesses by one-step anodization in ethylene glycol containing NH4F and H2O at applied voltage differences ranging from 10 V to 100 V at various anodization durations. We found that the thicknesses of TiO2 nanostructures are dependent on anodization voltages under time differences. Therefore, we tested the feasibility of applying machine learning algorithms to predict the deformation of TiO2. As the characteristics of TiO2 changed based on the different experimental conditions, we classified its surface pore structure into two categories and four groups. For the classification based on granularity, we assessed layer creation, roughness, pore creation, and pore height. We applied eight machine learning techniques to predict classification for binary and multiclass classification. For binary classification, random forest and gradient boosting algorithm had relatively high performance. However, all eight algorithms had scores higher than 0.93, which signifies high prediction on estimating the presence of pore. In contrast, decision tree and three ensemble methods had a relatively higher performance for multiclass classification, with an accuracy rate greater than 0.79. The weakest algorithm used was k-nearest neighbors for both binary and multiclass classifications. We believe that these results show that we can apply machine learning techniques to predict surface quality improvement, leading to smart manufacturing technology to better control color appearance, super-hydrophobicity, super-hydrophilicity or batter efficiency.

Sign in / Sign up

Export Citation Format

Share Document