scholarly journals A hybrid modeling combining the proper generalized decomposition approach to data-driven model learners, with application to nonlinear biphasic materials

2021 ◽  
Vol 349 (2) ◽  
pp. 259-273
Author(s):  
Chady Ghnatios
Keyword(s):  
Hybrid Modeling ◽  
Data Driven ◽  
Proper Generalized Decomposition ◽  
Decomposition Approach ◽  
Biphasic Materials

Operation Optimization Approaches of Thermal Power Units with Big Data-Driven Hybrid Modeling

2014 ◽  
Vol 631-632 ◽  
pp. 362-366
Author(s):  
Ning Ling Wang ◽  
Yong Zhang ◽  
Long Fei Zhu ◽  
Zhi Ping Yang
Keyword(s):  
Energy Consumption ◽  
Thermal Power ◽  
Hybrid Modeling ◽  
Data Driven ◽  
Fuzzy Rough Set ◽  
Operation Optimization ◽  
Operation Conditions ◽  
Energy Consumption Model ◽  
Practical Guidelines ◽  
Data Driven Modeling

An accurate and reliable energy-consumption model is the key to operation optimization and energy-saving diagnosis of thermal power units especially under different operation conditions and boundaries. Conventional mathematical and data-driven modeling methods were overviewed and compared in this paper. A hybrid modeling based on thermodynamic theory and fuzzy rough set (FRS) method was proposed to process the great volume of operation data and describe the energy-consumption behavior of thermal power units. On this basis, the operation optimization was performed with intelligent computation methods to derive the realizable benchmark state with the whole set of operation parameters. The resultant optimum operation state reflects the exterior factors and system behavior, taking practical guidelines for the modeling and optimization of large thermal power units.

scholarly journals A Multidimensional Data-Driven Sparse Identification Technique: The Sparse Proper Generalized Decomposition

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Rubén Ibáñez ◽  
Emmanuelle Abisset-Chavanne ◽  
Amine Ammar ◽  
David González ◽  
Elías Cueto ◽  
...  
Keyword(s):  
Dimensional Space ◽  
Model Identification ◽  
Curse Of Dimensionality ◽  
Data Driven ◽  
Multidimensional Data ◽  
High Dimensional ◽  
Proper Generalized Decomposition ◽  
High Dimensional Space ◽  
Sparse Model ◽  
Identification Technique

Sparse model identification by means of data is especially cumbersome if the sought dynamics live in a high dimensional space. This usually involves the need for large amount of data, unfeasible in such a high dimensional settings. This well-known phenomenon, coined as the curse of dimensionality, is here overcome by means of the use of separate representations. We present a technique based on the same principles of the Proper Generalized Decomposition that enables the identification of complex laws in the low-data limit. We provide examples on the performance of the technique in up to ten dimensions.

Hybrid Modeling Approach for Melt Pool Prediction in Laser Powder Bed Fusion Additive Manufacturing

2020 ◽  
Author(s):  
Tesfaye Moges ◽  
Zhuo Yang ◽  
Kevontrez Jones ◽  
Shaw Feng ◽  
Paul Witherell ◽  
...  
Keyword(s):  
Additive Manufacturing ◽  
Hybrid Model ◽  
Hybrid Models ◽  
Hybrid Modeling ◽  
Data Driven ◽  
Powder Bed Fusion ◽  
Cfd Model ◽  
Laser Powder Bed Fusion ◽  
Powder Bed ◽  
Melt Pool

Abstract Multi-scale, multi-physics, computational models are a promising tool to provide detailed insights to understand the process-structure-property-performance relationships in additive manufacturing (AM) processes. To take advantage of the strengths of both physics-based and data-driven models, we propose a novel, hybrid modeling framework for laser powder bed fusion (L-PBF) processes. Our unbiased, model integration method combines physics-based data and measurement data for approaching more accurate prediction of melt-pool width. Both a high-fidelity computational fluid dynamics (CFD) model and experiments utilizing optical images are used to generate a combined dataset of melt-pool widths. From this aggregated dataset, a hybrid model is developed using data-driven modeling techniques, including polynomial regression and Kriging methods. The performance of the hybrid model is evaluated by computing the average relative error and comparing it with the results of the simulations and surrogate models constructed from the original CFD model and experimental measurements. It is found that the proposed hybrid model performs better in terms of prediction accuracy and computational time. Future work includes a conceptual introduction on the use of an AM ontology to support improved model and data selection when constructing hybrid models. This study can be viewed as a significant step towards the use of hybrid models as predictive models with improved accuracy and without the sacrifice of speed.

An Automated Approach to Enhance Multiscale Signal Monitoring of Manufacturing Processes

2015 ◽  
Vol 138 (5) ◽  
Author(s):  
Marco Grasso ◽  
Bianca Maria Colosimo
Keyword(s):  
Kernel Estimation ◽  
Optimal Number ◽  
Signal Decomposition ◽  
Data Driven ◽  
Manufacturing Processes ◽  
Density Functions ◽  
Decomposition Approach ◽  
Mode Decomposition ◽  
Manufacturing Applications ◽  
Original Information

Multiscale signal decomposition represents an important step to enhance process monitoring results in many manufacturing applications. Empirical mode decomposition (EMD) is a data driven technique that gained an increasing interest in this framework. However, it usually yields an-over decomposition of the signal, leading to the generation of spurious and meaningless modes and the possible mixing of embedded modes. This study proposes an enhanced signal decomposition approach that synthetizes the original information content into a minimal number of relevant modes via a data-driven and automated procedure. A criterion based on the kernel estimation of density functions is proposed to estimate the dissimilarities between the intrinsic modes generated by the EMD, together with a methodology to automatically determine the optimal number of final modes. The performances of the method are demonstrated by means of simulated signals and real industrial data from a waterjet cutting application.

scholarly journals Functional-Hybrid Modeling through automated adaptive symbolic regression for interpretable mathematical expressions

2021 ◽  
Author(s):  
Harini Narayanan ◽  
M. Nicolas Cruz Bournazou ◽  
Gonzalo Guillen-Gosalbez ◽  
Alessandro Butte
Keyword(s):  
Hybrid Model ◽  
Dynamic Models ◽  
Learning Algorithm ◽  
Symbolic Regression ◽  
Hybrid Modeling ◽  
Data Driven ◽  
Support Vector ◽  
Successful Implementation ◽  
Modeling Framework ◽  
Improved Performance

Mathematical models used for the representation of (bio)-chemical processes can be grouped into two broad paradigms: white-box or mechanistic models, completely based on knowledge or black-box data-driven models based on patterns observed in data. However, in the past two-decade, hybrid modeling that explores the synergy between the two paradigms has emerged as a pragmatic compromise. The data-driven part of these have been largely based on conventional machine learning algorithm (e.g., artificial neural network, support vector regression), which prevents interpretability of the finally learnt model by the domain-experts. In this work we present a novel hybrid modeling framework, the Functional-Hybrid model, that uses the ranked domain-specific functional beliefs together with symbolic regression to develop dynamic models. We demonstrate the successful implementation of these hybrid models for four benchmark systems and a microbial fermentation reactor, all of which are systems of (bio)chemical relevance. We also demonstrate that compared to a similar implementation with the conventional ANN, the performance of Functional-Hybrid model is at least two times better in interpolation and extrapolation. Additionally, the proposed framework can learn the dynamics in 50% lower number of experiments. This improved performance can be attributed to the structure imposed by the functional transformations introduced in the Functional-Hybrid model.

scholarly journals A Bibliometric Analysis of Physics-Based and Data-Driven Hybrid Modeling

Procedia CIRP ◽  
2021 ◽  
Vol 103 ◽  
pp. 49-54
Author(s):  
Sathish Kasilingam ◽  
Makenzie Keepers ◽  
Thorsten Wuest
Keyword(s):  
Bibliometric Analysis ◽  
Hybrid Modeling ◽  
Data Driven

Hybrid Physics-Based and Data-Driven Modeling for Improved Standpipe Pressure Prediction

2021 ◽  
Author(s):  
Oney Erge ◽  
Eric van Oort
Keyword(s):  
Machine Learning ◽  
Markov Model ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Hybrid Modeling ◽  
Data Driven ◽  
Learning Models ◽  
Drilling Data ◽  
Drilling Operations ◽  
Pump Pressure

Abstract During drilling operations, it is common to see pump pressure spikes when flow is initiated, including after a connection or after a prolonged break in drilling operations. It is important to be able to predict the magnitude of such pressure spikes to avoid compromising wellbore integrity. This study shows how a hybrid approach using data-driven machine learning coupled with physics-based modeling can be used to accurately predict the magnitude of pressure spikes. To model standpipe pressure behavior, machine learning techniques were combined with physics-based models via a rule-based, stochastic decision-making algorithm. To start, neural networks and deep learning models were trained using time-series drilling data. From there, physics-based equations that model the pressure required to break the mud's gel strength as well as the flow of non-Newtonian fluids through the entire circulation system were used to simulate standpipe pressure. Then, these two highly different methods for predicting/modeling standpipe pressure were combined by a hidden Markov model using a set of rules and transition probabilities. By combining machine learning and physics-based approaches, the best features of each model are leveraged by the hidden Markov model, yielding a more accurate and robust prediction of pressure. A similar result is not achievable with a purely data-driven black-box model, because it lacks a connection to the underlying physics. Our study highlights how drilling data analysis can be optimally leveraged. The overarching conclusion: hybrid modeling can more accurately predict pump pressure spikes and capture the transient events at flow initiation when compared to physics-based or machine learning models used in isolation. Moreover, the approach is not limited to pressure behavior but can be applied to a wide range of well construction operations. The proposed approach is easy to implement and the details of implementation are presented in this study. Being able to accurately model and manage the pressure response during drilling operations is essential, especially for wells drilled in narrow-margin environments. Pressure can be more accurately predicted through our proposed hybrid modeling, leading to safer, more optimized operations.

scholarly journals Model order reduction in hyperelasticity: a proper generalized decomposition approach

2013 ◽  
Vol 96 (3) ◽  
pp. 129-149 ◽  
Author(s):  
Siamak Niroomandi ◽  
Icíar Alfaro ◽  
David González ◽  
Elías Cueto ◽  
Francisco Chinesta
Keyword(s):  
Model Order Reduction ◽  
Order Reduction ◽  
Proper Generalized Decomposition ◽  
Model Order ◽  
Decomposition Approach
Sign in / Sign up

Export Citation Format

Share Document