The Data Driven Surrogate Model Based Dynamic Design of Aero-Engine Fan Systems

Abstract The permeability of fractures, including natural and hydraulic, are essential parameters for the modeling of fluid flow in conventional and unconventional fractured reservoirs. However, traditional analytical cubic law (CL-based) models used to estimate fracture permeability show unsatisfactory performance when dealing with different dynamic complexities of fractures. This work presents a data-driven, physics-included model based on machine learning as an alternative to traditional methods. The workflow for the development of the data-driven model includes four steps. Step 1: Identify uncertain parameters and perform Latin Hypercube Sampling (LHS). We first identify the uncertain parameters which affect the fracture permeability. We then generate training samples using LHS. Step 2: Perform training simulations and collect inputs and outputs. In this step, high-resolution simulations with parallel computing for the Navier-Stokes equations (NSEs) are run for each of the training samples. We then collect the inputs and outputs from the simulations. Step 3: Construct an optimized data-driven surrogate model. A data-driven model based on machine learning is then built to model the nonlinear mapping between the inputs and outputs collected from Step 2. Herein, Artificial Neural Network (ANN) coupling with Bayesian optimization algorithm is implemented to obtain the optimized surrogate model. Step 4: Validate the proposed data-driven model. In this step, we conduct blind validation on the proposed model with high-fidelity simulations. We further test the developed surrogate model with newly generated fracture cases with a broad range of roughness and tortuosity under different Reynolds numbers. We then compare its performance to the reference NSEs solutions. Results show that the developed data-driven model delivers good accuracy exceeding 90% for all training, validation, and test samples. This work introduces an integrated workflow for developing a data-driven, physics-included model using machine learning to estimate fracture permeability under complex physics (e.g., inertial effect). To our knowledge, this technique is introduced for the first time for the upscaling of rock fractures. The proposed model offers an efficient and accurate alternative to the traditional upscaling methods that can be readily implemented in reservoir characterization and modeling workflows.

Download Full-text

CO2 Leakage Rate Forecasting Using Optimized Deep Learning

10.2118/206222-ms ◽

2021 ◽

Author(s):

Xupeng He ◽

Weiwei Zhu ◽

Ryan Santoso ◽

Marwa Alsinan ◽

Hyung Kwak ◽

...

Keyword(s):

Deep Learning ◽

Real Time ◽

Surrogate Model ◽

Network Architecture ◽

Leakage Rate ◽

Bayesian Optimization ◽

Data Driven ◽

Co2 Leakage ◽

Model Based ◽

Uncertainty Parameters

Abstract Geologic CO2 Sequestration (GCS) is a promising engineering technology to reduce global greenhouse emissions. Real-time forecasting of CO2 leakage rates is an essential aspect of large-scale GCS deployment. This work introduces a data-driven, physics-featuring surrogate model based on deep-learning technique for CO2 leakage rate forecasting. The workflow for the development of data-driven, physics-featuring surrogate model includes three steps: 1) Datasets Generation: We first identify uncertainty parameters that affect the objective of interests (i.e., CO2 leakage rates). For the identified uncertainty parameters, various realizations are then generated based on Latin Hypercube Sampling (LHS). High-fidelity simulations based on a two-phase black-oil solver within MRST are performed to generate the objective functions. Datasets including inputs (i.e., the uncertainty parameters) and outputs (CO2 leakage rates) are collected. 2) Surrogate Development: In this step, a time-series surrogate model using long short-term memory (LSTM) is constructed to map the nonlinear relationship between these uncertainty parameters as inputs and CO2 leakage rates as outputs. We perform Bayesian optimization to automate the tuning of hyperparameters and network architecture instead of the traditional trial-error tuning process. 3) Uncertainty Analysis: This step aims to perform Monte Carlo (MC) simulations using the successfully trained surrogate model to explore uncertainty propagation. The sampled realizations are collected in the form of distributions from which the probabilistic forecast of percentiles, P10, P50, and P50, are evaluated. We propose a data-driven, physics-featuring surrogate model based on LSTM for CO2 leakage rate forecasting. We demonstrate its performance in terms of accuracy and efficiency by comparing it with ground-truth solutions. The proposed deep-learning workflow shows promising potential and could be readily implemented in commercial-scale GCS for real-time monitoring applications.

Download Full-text

The Data Driven Surrogate Model Based Dynamic Design of Aero-Engine Fan Systems

Journal of Engineering for Gas Turbines and Power ◽

10.1115/1.4049504 ◽

2021 ◽

Author(s):

Yunpeng Zhu ◽

Jie Yuan ◽

Zi-Qiang Lang ◽

Christoph W. Schwingshackl ◽

Loic Salles ◽

...

Keyword(s):

Surrogate Model ◽

System Analysis ◽

Data Driven ◽

Design Parameters ◽

Contact Friction ◽

Test Case ◽

Arx Model ◽

Analysis And Design ◽

Aero Engine ◽

Aero Engines

Abstract High cycle fatigue failures of fan blade systems due to vibrational loads are of great concern in the design of aero engines, where energy dissipation by the relative frictional motion in the dovetail joints provides the main damping to mitigate the vibrations. The performance of such a frictional damping can be enhanced by suitable coatings. However, the analysis and design of coated joint roots of gas turbine fan blades are computationally expensive due to strong contact friction nonlinearities and also complex physics involved in the dovetail. In this study, a data driven surrogate model, known as the Nonlinear in Parameter AutoRegressive with eXegenous input (NP-ARX) model, is introduced to circumvent the difficulties in the analysis and design of fan systems. The NP-ARX model is a linear input-output model, where the model coefficients are nonlinear functions of the design parameters of interest, such that the Frequency Response Function (FRF) can be directly obtained and used in the system analysis and design. A simplified fan bladed disc system is considered as the test case. The results show that by using the data driven surrogate model, an efficient and accurate design of aero-engine fan systems can be achieved. The approach is expected to be extended to solve the analysis and design problems of many other complex systems.

Download Full-text

The Data Driven Surrogate Model Based Dynamic Design of Aero-Engine Fan Systems

Volume 10B: Structures and Dynamics ◽

10.1115/gt2020-14272 ◽

2020 ◽

Author(s):

Yun-Peng Zhu ◽

Jie Yuan ◽

Z. Q. Lang ◽

C. W. Schwingshackl ◽

Loic Salles ◽

...

Keyword(s):

Surrogate Model ◽

System Analysis ◽

Data Driven ◽

Design Parameters ◽

Contact Friction ◽

Test Case ◽

Arx Model ◽

Analysis And Design ◽

Aero Engine ◽

Aero Engines

Abstract High cycle fatigue failures of fan blade systems due to vibrational loads are of great concern in the design of aero engines, where energy dissipation by the relative frictional motion in the dovetail joints provides the main damping to mitigate the vibrations. The performance of such a frictional damping can be enhanced by suitable coatings. However, the analysis and design of coated joint roots of gas turbine fan blades are computationally expensive due to strong contact friction nonlinearities and also complex physics involved in the dovetail. In this study, a data driven surrogate model, known as the Nonlinear in Parameter AutoRegressive with eXegenous input (NP-ARX) model, is introduced to circumvent the difficulties in the analysis and design of fan systems. The NP-ARX model is a linear input-output model, where the model coefficients are nonlinear functions of the design parameters of interest, such that the Frequency Response Function (FRF) can be directly obtained and used in the system analysis and design. A simplified fan bladed disc system is considered as the test case. The results show that by using the data driven surrogate model, an efficient and accurate design of aero-engine fan systems can be achieved. The approach is expected to be extended to solve the analysis and design problems of many other complex systems.

Download Full-text

The New Trend of State Estimation: From Model-Driven to Hybrid-Driven Methods

Sensors ◽

10.3390/s21062085 ◽

2021 ◽

Vol 21 (6) ◽

pp. 2085

Author(s):

Xue-Bo Jin ◽

Ruben Jonhson Robert RobertJeremiah ◽

Ting-Li Su ◽

Yu-Ting Bai ◽

Jian-Lei Kong

Keyword(s):

Kalman Filter ◽

State Estimation ◽

Future Development ◽

Data Driven ◽

Estimation Methods ◽

Multiple Model ◽

Development Trends ◽

Research Results ◽

Model Driven ◽

Model Based

State estimation is widely used in various automated systems, including IoT systems, unmanned systems, robots, etc. In traditional state estimation, measurement data are instantaneous and processed in real time. With modern systems’ development, sensors can obtain more and more signals and store them. Therefore, how to use these measurement big data to improve the performance of state estimation has become a hot research issue in this field. This paper reviews the development of state estimation and future development trends. First, we review the model-based state estimation methods, including the Kalman filter, such as the extended Kalman filter (EKF), unscented Kalman filter (UKF), cubature Kalman filter (CKF), etc. Particle filters and Gaussian mixture filters that can handle mixed Gaussian noise are discussed, too. These methods have high requirements for models, while it is not easy to obtain accurate system models in practice. The emergence of robust filters, the interacting multiple model (IMM), and adaptive filters are also mentioned here. Secondly, the current research status of data-driven state estimation methods is introduced based on network learning. Finally, the main research results for hybrid filters obtained in recent years are summarized and discussed, which combine model-based methods and data-driven methods. This paper is based on state estimation research results and provides a more detailed overview of model-driven, data-driven, and hybrid-driven approaches. The main algorithm of each method is provided so that beginners can have a clearer understanding. Additionally, it discusses the future development trends for researchers in state estimation.

Download Full-text