TBM performance prediction with Bayesian optimization and automated machine learning

2020 ◽  
Vol 103 ◽  
pp. 103493 ◽  
Author(s):  
Qianli Zhang ◽  
Weifei Hu ◽  
Zhenyu Liu ◽  
Jianrong Tan
Keyword(s):  
Machine Learning ◽  
Performance Prediction ◽  
Bayesian Optimization ◽  
Tbm Performance ◽  
Automated Machine Learning

scholarly journals Bayesian Optimization for Categorical and Category-Specific Continuous Inputs

2020 ◽  
Vol 34 (04) ◽  
pp. 5256-5263 ◽  
Author(s):  
Dang Nguyen ◽  
Sunil Gupta ◽  
Santu Rana ◽  
Alistair Shilton ◽  
Svetha Venkatesh
Keyword(s):  
Machine Learning ◽  
Parameter Tuning ◽  
Bayesian Optimization ◽  
Parallel Optimization ◽  
Continuous Variables ◽  
Unified Framework ◽  
Multiple Resources ◽  
Thompson Sampling ◽  
Machine Learning Model ◽  
Automated Machine Learning

Many real-world functions are defined over both categorical and category-specific continuous variables and thus cannot be optimized by traditional Bayesian optimization (BO) methods. To optimize such functions, we propose a new method that formulates the problem as a multi-armed bandit problem, wherein each category corresponds to an arm with its reward distribution centered around the optimum of the objective function in continuous variables. Our goal is to identify the best arm and the maximizer of the corresponding continuous function simultaneously. Our algorithm uses a Thompson sampling scheme that helps connecting both multi-arm bandit and BO in a unified framework. We extend our method to batch BO to allow parallel optimization when multiple resources are available. We theoretically analyze our method for convergence and prove sub-linear regret bounds. We perform a variety of experiments: optimization of several benchmark functions, hyper-parameter tuning of a neural network, and automatic selection of the best machine learning model along with its optimal hyper-parameters (a.k.a automated machine learning). Comparisons with other methods demonstrate the effectiveness of our proposed method.

Bandit-Based Automated Machine Learning

2018 ◽  
Author(s):  
Silvia Cristina Nunes das Dores ◽  
Carlos Soares ◽  
Duncan Ruiz
Keyword(s):  
Machine Learning ◽  
Automated Machine Learning

scholarly journals From Exploratory Tunnel to Base Tunnel: Hard Rock TBM Performance Prediction by Means of a Stochastic Approach

2020 ◽  
Vol 53 (12) ◽  
pp. 5473-5487 ◽  
Author(s):  
Andrea Rispoli ◽  
Anna Maria Ferrero ◽  
Marilena Cardu
Keyword(s):  
Performance Prediction ◽  
Early Stage ◽  
Tunnel Boring Machine ◽  
Stochastic Approach ◽  
Critical Issue ◽  
Utilization Factor ◽  
Tbm Performance ◽  
Factors Affecting ◽  
Tunnel Section ◽  
Input Variables

AbstractTunnel boring machine (TBM) performance prediction is often a critical issue in the early stage of a tunnelling project, mainly due to the unpredictable nature of some important factors affecting the machine performance. In this regard, deterministic approaches are normally employed, providing results in terms of average values expected for the TBM performance. Stochastic approaches would offer improvement over deterministic methods, taking into account the parameter variability; however, their use is limited, since the level of information required is often not available. In this study, the data provided by the excavation of the Maddalena exploratory tunnel were used to predict the net and overall TBM performance for a 2.96 km section of the Mont Cenis base tunnel by using a stochastic approach. The preliminary design of the TBM cutterhead was carried out. A prediction model based on field penetration index, machine operating level and utilization factor was adopted. The variability of the parameters involved was analysed. A procedure to take into account the correlation between the input variables was described. The probability of occurrence of the outcomes was evaluated, and the total excavation time expected for the tunnel section analysed was calculated.

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.

scholarly journals Machine Learning–enabled Scalable Performance Prediction of Scientific Codes

2021 ◽  
Vol 31 (2) ◽  
pp. 1-28
Author(s):  
Gopinath Chennupati ◽  
Nandakishore Santhi ◽  
Phill Romero ◽  
Stephan Eidenbenz
Keyword(s):  
Machine Learning ◽  
Performance Prediction ◽  
Prediction Models ◽  
Radiation Transport ◽  
Discrete Event ◽  
Basic Block ◽  
Distribution Models ◽  
Scientific Application ◽  
High Level ◽  
Access Patterns

Hardware architectures become increasingly complex as the compute capabilities grow to exascale. We present the Analytical Memory Model with Pipelines (AMMP) of the Performance Prediction Toolkit (PPT). PPT-AMMP takes high-level source code and hardware architecture parameters as input and predicts runtime of that code on the target hardware platform, which is defined in the input parameters. PPT-AMMP transforms the code to an (architecture-independent) intermediate representation, then (i) analyzes the basic block structure of the code, (ii) processes architecture-independent virtual memory access patterns that it uses to build memory reuse distance distribution models for each basic block, and (iii) runs detailed basic-block level simulations to determine hardware pipeline usage. PPT-AMMP uses machine learning and regression techniques to build the prediction models based on small instances of the input code, then integrates into a higher-order discrete-event simulation model of PPT running on Simian PDES engine. We validate PPT-AMMP on four standard computational physics benchmarks and present a use case of hardware parameter sensitivity analysis to identify bottleneck hardware resources on different code inputs. We further extend PPT-AMMP to predict the performance of a scientific application code, namely, the radiation transport mini-app SNAP. To this end, we analyze multi-variate regression models that accurately predict the reuse profiles and the basic block counts. We validate predicted SNAP runtimes against actual measured times.

Sign in / Sign up

Export Citation Format

Share Document