Stochastic Bayesian optimization for predicting borderline knock

2021 ◽  
pp. 146808742110652
Author(s):  
Jian Tang ◽  
Anuj Pal ◽  
Wen Dai ◽  
Chad Archer ◽  
James Yi ◽  
...  
Keyword(s):  
Fuel Economy ◽  
Learning Algorithm ◽  
Feedforward Control ◽  
Model Development ◽  
Kriging Model ◽  
Optimization Method ◽  
Surrogate Models ◽  
Bayesian Optimization ◽  
Control Parameters ◽  
Operation Conditions

Engine knock is an undesirable combustion that could damage the engine mechanically. On the other hand, it is often desired to operate the engine close to its borderline knock limit to optimize combustion efficiency. Traditionally, borderline knock limit is detected by sweeping tests of related control parameters for the worst knock, which is expensive and time consuming, and also, the detected borderline knock limit is often used as a feedforward control without considering its stochastic characteristics without compensating current engine operational condition and type of fuel used. In this paper, stochastic Bayesian optimization method is used to obtain a tradeoff between stochastic knock intensity and fuel economy. The log-nominal distribution of knock intensity signal is converted to Gaussian one using a proposed map to satisfy the assumption for Kriging model development. Both deterministic and stochastic Kriging surrogate models are developed based on test data using the Bayesian iterative optimization process. This study focuses on optimizing two competing objectives, knock intensity and indicated specific fuel consumption using two control parameters: spark and intake valve timings. Test results at two different operation conditions show that the proposed learning algorithm not only reduces required time and cost for predicting knock borderline but also provides control parameters, based on trained surrogate models and the corresponding Pareto front, with the best fuel economy possible.

scholarly journals CFD Optimization Process of a Lateral Inlet/Outlet Diffusion Part of a Pumped Hydroelectric Storage Based on Optimal Surrogate Models

Processes ◽  
2019 ◽  
Vol 7 (4) ◽  
pp. 204 ◽  
Author(s):  
Gao ◽  
Zhu ◽  
Zhang ◽  
Sun ◽  
Qin ◽  
...  
Keyword(s):  
Velocity Distribution ◽  
Critical Role ◽  
Kriging Model ◽  
Optimization Method ◽  
Surrogate Models ◽  
Distribution Coefficients ◽  
Head Loss ◽  
Optimization Process ◽  
Gaussian Kernel ◽  
Cfd Optimization

The lateral inlet/outlet plays a critical role in the connecting tunnels of a water delivery system in a pumped hydroelectric storage (PHES). Therefore, the shape of the inlet/outlet was improved through computational fluid dynamics (CFD) optimization based on optimal surrogate models. The CFD method applied in this paper was validated by a physical experiment that was carefully designed to meet bidirectional flow requirements. To determine a good compromise between the generation and pump mode, reasonable weights were defined to better evaluate the overall performance. In order to find suitable surrogate models to improve the optimization process, the best suited surrogate models were identified by an optimal model selection method. The optimal configurations of the surrogate model for the head loss and the velocity distribution coefficient were the Kriging model with a Gaussian kernel and the Kriging model with an Exponential kernel, respectively. Finally, a multi-objective surrogate-based optimization method was used to determine the optimum design. The overall head loss coefficient and velocity distribution coefficients were 0.248 and 1.416. Compared with the original shape, the coefficients decrease by 6.42% and 40.28%, respectively. The methods and findings of this work may provide practical guidelines for designers and researchers.

scholarly journals An Integrated Approach of Mechanistic-Modeling and Machine-Learning for Thickness Optimization of Frozen Microwaveable Foods

Foods ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 763
Author(s):  
Ran Yang ◽  
Zhenbo Wang ◽  
Jiajia Chen
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Food Product ◽  
Integrated Approach ◽  
Mechanistic Modeling ◽  
Bayesian Optimization ◽  
Initial Training ◽  
Thickness Optimization ◽  
Heating Uniformity ◽  
Food Design

Mechanistic-modeling has been a useful tool to help food scientists in understanding complicated microwave-food interactions, but it cannot be directly used by the food developers for food design due to its resource-intensive characteristic. This study developed and validated an integrated approach that coupled mechanistic-modeling and machine-learning to achieve efficient food product design (thickness optimization) with better heating uniformity. The mechanistic-modeling that incorporated electromagnetics and heat transfer was previously developed and validated extensively and was used directly in this study. A Bayesian optimization machine-learning algorithm was developed and integrated with the mechanistic-modeling. The integrated approach was validated by comparing the optimization performance with a parametric sweep approach, which is solely based on mechanistic-modeling. The results showed that the integrated approach had the capability and robustness to optimize the thickness of different-shape products using different initial training datasets with higher efficiency (45.9% to 62.1% improvement) than the parametric sweep approach. Three rectangular-shape trays with one optimized thickness (1.56 cm) and two non-optimized thicknesses (1.20 and 2.00 cm) were 3-D printed and used in microwave heating experiments, which confirmed the feasibility of the integrated approach in thickness optimization. The integrated approach can be further developed and extended as a platform to efficiently design complicated microwavable foods with multiple-parameter optimization.

Development of a machine learning algorithm for fault detection in a cantilever beam

2021 ◽  
pp. 095745652110004
Author(s):  
Amit Kumar Gorai ◽  
Tarapada Roy ◽  
Sumeet Mishra
Keyword(s):  
Mechanical Properties ◽  
Fault Detection ◽  
Cantilever Beam ◽  
Learning Algorithm ◽  
Model Development ◽  
Vibration Signal ◽  
Beam Specimen ◽  
Discrete Wavelet ◽  
Feed Forward Network ◽  
Model Training

The mechanical properties of a component change with any type of damage such as crack development, generation of holes, bend, excessive wear, and tear. The change in mechanical properties causes the material to behave differently in terms of noise and vibration under different loading conditions. Thus, the present study aims to develop an artificial neural network model using vibration signal data for early fault detection in a cantilever beam. The discrete wavelet transform coefficients of de-noised vibration signals were used for model development. The vibration signal was recorded using the OROS OR35 module for different fault conditions (no fault, notch fault, and hole fault) of a cantilever beam. A feed-forward network was trained using backpropagation to map the input features to output. A total of 603 training datasets (201 datasets for three types of cantilever beam—no fault, notch fault, and hole fault) were used for training, and 201 datasets were used for testing of the model. The testing dataset was recorded for a hole fault cantilever beam specimen. The results indicated that the proposed model predicted the test samples with 78.6% accuracy. To increase the accuracy of prediction, more data need to be used in the model training.

scholarly journals Application of Artificial Intelligence (AI) for Sustainable Highway and Road System

Symmetry ◽  
2020 ◽  
Vol 13 (1) ◽  
pp. 60
Author(s):  
Md Arifuzzaman ◽  
Muhammad Aniq Gul ◽  
Kaffayatullah Khan ◽  
S. M. Zakir Hossain
Keyword(s):  
Experimental Data ◽  
High Performance ◽  
Adhesion Force ◽  
Model Development ◽  
Real Life ◽  
Bayesian Optimization ◽  
Support Vector ◽  
Adhesive Properties ◽  
Bayesian Optimization Algorithm ◽  
The Mean

There are several environmental factors such as temperature differential, moisture, oxidation, etc. that affect the extended life of the modified asphalt influencing its desired adhesive properties. Knowledge of the properties of asphalt adhesives can help to provide a more resilient and durable asphalt surface. In this study, a hybrid of Bayesian optimization algorithm and support vector regression approach is recommended to predict the adhesion force of asphalt. The effects of three important variables viz., conditions (fresh, wet and aged), binder types (base, 4% SB, 5% SB, 4% SBS and 5% SBS), and Carbon Nano Tube doses (0.5%, 1.0% and 1.5%) on adhesive force are taken into consideration. Real-life experimental data (405 specimens) are considered for model development. Using atomic force microscopy, the adhesive strength of nanoscales of test specimens is determined according to functional groups on the asphalt. It is found that the model predictions overlap with the experimental data with a high R2 of 90.5% and relative deviation are scattered around zero line. Besides, the mean, median and standard deviations of experimental and the predicted values are very close. In addition, the mean absolute Error, root mean square error and fractional bias values were found to be low, indicating the high performance of the developed model.

scholarly journals A New Hyper-Parameter Optimization Method for Power Load Forecast Based on Recurrent Neural Networks

Algorithms ◽  
2021 ◽  
Vol 14 (6) ◽  
pp. 163
Author(s):  
Yaru Li ◽  
Yulai Zhang ◽  
Yongping Cai
Keyword(s):  
Neural Networks ◽  
Parameter Optimization ◽  
Recurrent Neural Networks ◽  
Critical Role ◽  
Optimization Method ◽  
Bayesian Optimization ◽  
Power Load ◽  
Gradient Calculation ◽  
Truncated Newton ◽  
Selection Of

The selection of the hyper-parameters plays a critical role in the task of prediction based on the recurrent neural networks (RNN). Traditionally, the hyper-parameters of the machine learning models are selected by simulations as well as human experiences. In recent years, multiple algorithms based on Bayesian optimization (BO) are developed to determine the optimal values of the hyper-parameters. In most of these methods, gradients are required to be calculated. In this work, the particle swarm optimization (PSO) is used under the BO framework to develop a new method for hyper-parameter optimization. The proposed algorithm (BO-PSO) is free of gradient calculation and the particles can be optimized in parallel naturally. So the computational complexity can be effectively reduced which means better hyper-parameters can be obtained under the same amount of calculation. Experiments are done on real world power load data,where the proposed method outperforms the existing state-of-the-art algorithms,BO with limit-BFGS-bound (BO-L-BFGS-B) and BO with truncated-newton (BO-TNC),in terms of the prediction accuracy. The errors of the prediction result in different models show that BO-PSO is an effective hyper-parameter optimization method.

scholarly journals A Kriging-Assisted Multi-Objective Constrained Global Optimization Method for Expensive Black-Box Functions

Mathematics ◽  
2021 ◽  
Vol 9 (2) ◽  
pp. 149
Author(s):  
Yaohui Li ◽  
Jingfang Shen ◽  
Ziliang Cai ◽  
Yizhong Wu ◽  
Shuting Wang
Keyword(s):  
Global Optimization ◽  
Pareto Frontier ◽  
Kriging Model ◽  
Optimization Method ◽  
Function Evaluation ◽  
Sampling Point ◽  
Constrained Global Optimization ◽  
Multi Objective ◽  
Sample Data ◽  
Sampling Points

The kriging optimization method that can only obtain one sampling point per cycle has encountered a bottleneck in practical engineering applications. How to find a suitable optimization method to generate multiple sampling points at a time while improving the accuracy of convergence and reducing the number of expensive evaluations has been a wide concern. For this reason, a kriging-assisted multi-objective constrained global optimization (KMCGO) method has been proposed. The sample data obtained from the expensive function evaluation is first used to construct or update the kriging model in each cycle. Then, kriging-based estimated target, RMSE (root mean square error), and feasibility probability are used to form three objectives, which are optimized to generate the Pareto frontier set through multi-objective optimization. Finally, the sample data from the Pareto frontier set is further screened to obtain more promising and valuable sampling points. The test results of five benchmark functions, four design problems, and a fuel economy simulation optimization prove the effectiveness of the proposed algorithm.

scholarly journals Vestas V90-3MW Wind Turbine Gearbox Health Assessment Using a Vibration-Based Condition Monitoring System

2016 ◽  
Vol 2016 ◽  
pp. 1-18 ◽  
Author(s):  
A. Romero ◽  
Y. Lage ◽  
S. Soua ◽  
B. Wang ◽  
T.-H. Gan
Keyword(s):  
Fault Diagnosis ◽  
Wind Turbine ◽  
Condition Monitoring ◽  
Learning Algorithm ◽  
Health Assessment ◽  
Field Trials ◽  
Health Condition ◽  
Normal Operation ◽  
Wind Turbine Gearbox ◽  
Operation Conditions

Reliable monitoring for the early fault diagnosis of gearbox faults is of great concern for the wind industry. This paper presents a novel approach for health condition monitoring (CM) and fault diagnosis in wind turbine gearboxes using vibration analysis. This methodology is based on a machine learning algorithm that generates a baseline for the identification of deviations from the normal operation conditions of the turbine and the intrinsic characteristic-scale decomposition (ICD) method for fault type recognition. Outliers picked up during the baseline stage are decomposed by the ICD method to obtain the product components which reveal the fault information. The new methodology proposed for gear and bearing defect identification was validated by laboratory and field trials, comparing well with the methods reviewed in the literature.

Extended validation of a ground-based three-axis spacecraft simulator model

2020 ◽  
pp. 095441002093896
Author(s):  
H Sh Ousaloo ◽  
Gh Sharifi ◽  
B Akbarinia
Keyword(s):  
Mathematical Model ◽  
Attitude Control ◽  
Aerodynamic Drag ◽  
Center Of Mass ◽  
Model Development ◽  
Optimization Method ◽  
Experimental Results ◽  
Spacecraft Dynamics ◽  
Detailed Model ◽  
Mass Properties

The ground-based spacecraft dynamics simulator plays an important role in the implementation and validation of attitude control scenarios before a mission. The development of a comprehensive mathematical model of the platform is one of the indispensable and challenging steps during the control design process. A precise mathematical model should include mass properties, disturbances forces, mathematical models of actuators and uncertainties. This paper presents an approach for synthesizing a set of trajectories scenarios to estimate the platform inertia tensor, center of mass and aerodynamic drag coefficients. Reaction wheel drag torque is also estimated for having better performance. In order to verify the estimation techniques, a dynamics model of the satellite simulator using MATLAB software was developed, and the problem reduces to a parameter estimation problem to match the experimental results obtained from the simulator using a classical Lenevnberg-Marquardt optimization method. The process of parameter identification and mathematical model development has implemented on a three-axis spherical satellite simulator using air bearing, and several experiments are performed to validate the results. For validation of the simulator model, the model and experimental results must be carefully matched. The experimental results demonstrate that step-by-step implementation of this scenario leads to a detailed model of the platform which can be employed to design and develop control algorithms.

scholarly journals ASAMS: An Adaptive Sequential Sampling and Automatic Model Selection for Artificial Intelligence Surrogate Modeling

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5332
Author(s):  
Carlos A. Duchanoy ◽  
Hiram Calvo ◽  
Marco A. Moreno-Armendáriz
Keyword(s):  
Artificial Intelligence ◽  
Model Selection ◽  
Adaptive Sampling ◽  
Search Algorithm ◽  
Sequential Sampling ◽  
Surrogate Modeling ◽  
Kriging Model ◽  
Surrogate Models ◽  
Physical Experiments ◽  
Leave One Out

Surrogate Modeling (SM) is often used to reduce the computational burden of time-consuming system simulations. However, continuous advances in Artificial Intelligence (AI) and the spread of embedded sensors have led to the creation of Digital Twins (DT), Design Mining (DM), and Soft Sensors (SS). These methodologies represent a new challenge for the generation of surrogate models since they require the implementation of elaborated artificial intelligence algorithms and minimize the number of physical experiments measured. To reduce the assessment of a physical system, several existing adaptive sequential sampling methodologies have been developed; however, they are limited in most part to the Kriging models and Kriging-model-based Monte Carlo Simulation. In this paper, we integrate a distinct adaptive sampling methodology to an automated machine learning methodology (AutoML) to help in the process of model selection while minimizing the system evaluation and maximizing the system performance for surrogate models based on artificial intelligence algorithms. In each iteration, this framework uses a grid search algorithm to determine the best candidate models and perform a leave-one-out cross-validation to calculate the performance of each sampled point. A Voronoi diagram is applied to partition the sampling region into some local cells, and the Voronoi vertexes are considered as new candidate points. The performance of the sample points is used to estimate the accuracy of the model for a set of candidate points to select those that will improve more the model’s accuracy. Then, the number of candidate models is reduced. Finally, the performance of the framework is tested using two examples to demonstrate the applicability of the proposed method.

scholarly journals Deep kernel learning approach to engine emissions modeling

2020 ◽  
Vol 1 ◽  
Author(s):  
Changmin Yu ◽  
Marko Seslija ◽  
George Brownbridge ◽  
Sebastian Mosbach ◽  
Markus Kraft ◽  
...  
Keyword(s):  
Network Architecture ◽  
Mean Squared Error ◽  
Computational Cost ◽  
Optimization Method ◽  
Surrogate Models ◽  
Kernel Learning ◽  
High Dimensional Model Representation ◽  
Compression Ignition ◽  
Compression Ignition Engine ◽  
Engine Emissions

Abstract We apply deep kernel learning (DKL), which can be viewed as a combination of a Gaussian process (GP) and a deep neural network (DNN), to compression ignition engine emissions and compare its performance to a selection of other surrogate models on the same dataset. Surrogate models are a class of computationally cheaper alternatives to physics-based models. High-dimensional model representation (HDMR) is also briefly discussed and acts as a benchmark model for comparison. We apply the considered methods to a dataset, which was obtained from a compression ignition engine and includes as outputs soot and NO x emissions as functions of 14 engine operating condition variables. We combine a quasi-random global search with a conventional grid-optimization method in order to identify suitable values for several DKL hyperparameters, which include network architecture, kernel, and learning parameters. The performance of DKL, HDMR, plain GPs, and plain DNNs is compared in terms of the root mean squared error (RMSE) of the predictions as well as computational expense of training and evaluation. It is shown that DKL performs best in terms of RMSE in the predictions whilst maintaining the computational cost at a reasonable level, and DKL predictions are in good agreement with the experimental emissions data.

Sign in / Sign up

Export Citation Format

Share Document