Application of Artificial Neural Networks for Misfiring Detection in an Annular Pulsed Detonation Combustor Mockup

2016 ◽  
Author(s):  
Sascha Wolff ◽  
Jan-Simon Schäpel ◽  
Rudibert King
Keyword(s):  
Neural Network ◽  
Initial Conditions ◽  
Environmental Parameters ◽  
Data Driven ◽  
Learning Approach ◽  
Physical Knowledge ◽  
Pulsed Detonation ◽  
Machine Learning Approach ◽  
Set Up ◽  
The Given

An annular pulsed detonation combustor basically consists of a number of detonation tubes which are firing in a predetermined sequence into a common downstream annular plenum. Fluctuating initial conditions and fluctuating environmental parameters strongly affect the detonation. Operating such a set-up without misfiring is delicate. Misfiring of individual combustion tubes will significantly lower performance or even stop the engine. Hence, an operation of such an engine requires a misfiring detection. Here, a supervised data driven machine learning approach is used for the misfiring detection. The features used as inputs for the classifier are extracted from measurements incorporating physical knowledge about the given set-up. To this end, a neural network is trained based on labeled data which is then used for classification purposes, i.e., misfiring detection. A surrogate, non-reacting experimental set-up is considered in order to develop and test these methods.

Application of Artificial Neural Networks for Misfiring Detection in an Annular Pulsed Detonation Combustor Mockup

2016 ◽  
Vol 139 (4) ◽  
Author(s):  
Sascha Wolff ◽  
Jan-Simon Schäpel ◽  
Rudibert King
Keyword(s):  
Neural Network ◽  
Initial Conditions ◽  
Environmental Parameters ◽  
Data Driven ◽  
Learning Approach ◽  
Experimental Setup ◽  
Physical Knowledge ◽  
Pulsed Detonation ◽  
Machine Learning Approach ◽  
The Given

An annular pulsed detonation combustor (PDC) basically consists of a number of detonation tubes which are firing in a predetermined sequence into a common downstream annular plenum. Fluctuating initial conditions and fluctuating environmental parameters strongly affect the detonation. Operating such a setup without misfiring is delicate. Misfiring of individual combustion tubes will significantly lower performance or even stop the engine. Hence, an operation of such an engine requires a misfiring detection. Here, a supervised data driven machine learning approach is used for the misfiring detection. The features used as inputs for the classifier are extracted from measurements incorporating physical knowledge about the given setup. To this end, a neural network is trained based on labeled data which is then used for classification purposes, i.e., misfiring detection. A surrogate, nonreacting experimental setup is considered in order to develop and test these methods.

scholarly journals A Data-Driven Machine Learning Approach for Corrosion Risk Assessment—A Comparative Study

2019 ◽  
Vol 3 (2) ◽  
pp. 28 ◽  
Author(s):  
Chinedu I. Ossai
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Data Driven ◽  
Gradient Boosting ◽  
Learning Approach ◽  
Inspection Planning ◽  
Defect Depth ◽  
Corrosion Defect ◽  
Machine Learning Approach ◽  
Corrosion Risk

Understanding the corrosion risk of a pipeline is vital for maintaining health, safety and the environment. This study implemented a data-driven machine learning approach that relied on Principal Component Analysis (PCA), Particle Swarm Optimization (PSO), Feed-Forward Artificial Neural Network (FFANN), Gradient Boosting Machine (GBM), Random Forest (RF) and Deep Neural Network (DNN) to estimate the corrosion defect depth growth of aged pipelines. By modifying the hyperparameters of the FFANN algorithm with PSO and using PCA to transform the operating variables of the pipelines, different Machine Learning (ML) models were developed and tested for the X52 grade of pipeline. A comparative analysis of the computational accuracy of the corrosion defect growth was estimated for the PCA transformed and non-transformed parametric values of the training data to know the influence of the PCA transformation on the accuracy of the models. The result of the analysis showed that the ML modelling with PCA transformed data has an accuracy that is 3.52 to 5.32 times better than those carried out without PCA transformation. Again, the PCA transformed GBM model was found to have the best modeling accuracy amongst the tested algorithms; hence, it was used for computing the future corrosion defect depth growth of the pipelines. This helped to compute the corrosion risks using the failure probabilities at different lifecycle phases of the asset. The excerpts from the results of this study indicate that my technique is vital for the prognostic health monitoring of pipelines because it will provide information for maintenance and inspection planning.

scholarly journals A Nonlinear Five-Term System: Symmetry, Chaos, and Prediction

Symmetry ◽  
2020 ◽  
Vol 12 (5) ◽  
pp. 865
Author(s):  
Vo Phu Thoai ◽  
Maryam Shahriari Kahkeshi ◽  
Van Van Huynh ◽  
Adel Ouannas ◽  
Viet-Thanh Pham
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Lyapunov Exponents ◽  
Chaotic Systems ◽  
Initial Conditions ◽  
Phase Portraits ◽  
Learning Approach ◽  
Bifurcation Diagrams ◽  
Machine Learning Approach ◽  
Simple Systems

Chaotic systems have attracted considerable attention and been applied in various applications. Investigating simple systems and counterexamples with chaotic behaviors is still an important topic. The purpose of this work was to study a simple symmetrical system including only five nonlinear terms. We discovered the system’s rich behavior such as chaos through phase portraits, bifurcation diagrams, Lyapunov exponents, and entropy. Interestingly, multi-stability was observed when changing system’s initial conditions. Chaos of such a system was predicted by applying a machine learning approach based on a neural network.

An Annular Pulsed Detonation Combustor Mockup: System Identification and Misfiring Detection

2015 ◽  
Author(s):  
Sascha Wolff ◽  
Rudibert King
Keyword(s):  
Kalman Filter ◽  
System Identification ◽  
Initial Conditions ◽  
Environmental Parameters ◽  
Modal Identification ◽  
Lower Performance ◽  
Model Based ◽  
Pulsed Detonation ◽  
Identification Technique ◽  
Set Up

An annular pulsed detonation combustor basically consists of a number of detonation tubes which are firing in a predetermined sequence into a common downstream annular plenum. Fluctuating initial conditions and fluctuating environmental parameters strongly affect the detonation. Operating such a set-up without misfiring is delicate. Misfiring of individual combustion tubes will significantly lower performance or even stop the engine. Hence, an operation of such an engine requires a misfiring detection. Here, a model-based approach is used which exploits the innovation sequence calculated by a Kalman filter. The model necessary for the Kalman filter is determined based on a modal identification technique. A surrogate, nonreacting experimental set-up is considered in order to develop and test these methods.

scholarly journals Discretization and machine learning approximation of BSDEs with a constraint on the Gains-process

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Idris Kharroubi ◽  
Thomas Lim ◽  
Xavier Warin
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Differential Equations ◽  
Numerical Experiments ◽  
Optimization Problem ◽  
Learning Approach ◽  
The Neural Network ◽  
Machine Learning Approach ◽  
Mesh Grid

AbstractWe study the approximation of backward stochastic differential equations (BSDEs for short) with a constraint on the gains process. We first discretize the constraint by applying a so-called facelift operator at times of a grid. We show that this discretely constrained BSDE converges to the continuously constrained one as the mesh grid converges to zero. We then focus on the approximation of the discretely constrained BSDE. For that we adopt a machine learning approach. We show that the facelift can be approximated by an optimization problem over a class of neural networks under constraints on the neural network and its derivative. We then derive an algorithm converging to the discretely constrained BSDE as the number of neurons goes to infinity. We end by numerical experiments.

Sign in / Sign up

Export Citation Format

Share Document