scholarly journals Inverse Method of Centrifugal Pump Blade Based on Gaussian Process Regression

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Renhui Zhang ◽  
Xutao Zhao
Keyword(s):  
Inverse Problem ◽  
Gaussian Process ◽  
Centrifugal Pump ◽  
Cross Validation ◽  
Gaussian Process Regression ◽  
Inverse Methods ◽  
Shape Parameters ◽  
Problem Model ◽  
Blade Shape ◽  
Mean Square Errors

The inverse problem is always one of the important issues in the field of fluid machinery for the complex relationship among the blade shape, the hydraulic performance, and the inner flow structure. Based on Bayesian theory of posterior probability obtained from known prior probability, the inverse methods for the centrifugal pump blade based on the single-output Gaussian process regression (SOGPR) and the multioutput Gaussian process regression (MOGPR) were proposed, respectively. The training sample set consists of the blade shape parameters and the distribution of flow parameters. The hyperparameters in the inverse problem models were trained by using the maximum likelihood estimation and the gradient descent algorithm. The blade shape corresponding to the objective blade load can be achieved by the trained inverse problem models. The MH48-12.5 low specific speed centrifugal pump was selected to verify the proposed inverse methods. The reliability and accuracy of both inverse problem models were confirmed and compared by implementing leave-one-out (LOO) cross-validation and extrapolation characteristic analysis. The results show that the blade shapes within the sample space can be reconstructed exactly by both models. The root mean square errors of the MOGPR inverse problem model for the pump blade are generally lower than those of the SOGPR inverse problem model in the LOO cross-validation. The extrapolation characteristic of the MOGPR inverse problem model is better than that of the SOGPR inverse problem model for the correlation between the blade shape parameters can be fully considered by the correlation matrix of the MOGPR model. The proposed inverse methods can efficiently solve the inverse problem of centrifugal pump blade with sufficient accuracy.

scholarly journals Monitoring Cropland Phenology on Google Earth Engine Using Gaussian Process Regression

2021 ◽  
Vol 14 (1) ◽  
pp. 146
Author(s):  
Matías Salinero-Delgado ◽  
José Estévez ◽  
Luca Pipia ◽  
Santiago Belda ◽  
Katja Berger ◽  
...  
Keyword(s):  
Time Series ◽  
Gaussian Process ◽  
Satellite Data ◽  
Gaussian Process Regression ◽  
Google Earth ◽  
Gap Filling ◽  
Area Index ◽  
Filling Time ◽  
Google Earth Engine ◽  
Mean Square Errors

Monitoring cropland phenology from optical satellite data remains a challenging task due to the influence of clouds and atmospheric artifacts. Therefore, measures need to be taken to overcome these challenges and gain better knowledge of crop dynamics. The arrival of cloud computing platforms such as Google Earth Engine (GEE) has enabled us to propose a Sentinel-2 (S2) phenology end-to-end processing chain. To achieve this, the following pipeline was implemented: (1) the building of hybrid Gaussian Process Regression (GPR) retrieval models of crop traits optimized with active learning, (2) implementation of these models on GEE (3) generation of spatiotemporally continuous maps and time series of these crop traits with the use of gap-filling through GPR fitting, and finally, (4) calculation of land surface phenology (LSP) metrics such as the start of season (SOS) or end of season (EOS). Overall, from good to high performance was achieved, in particular for the estimation of canopy-level traits such as leaf area index (LAI) and canopy chlorophyll content, with normalized root mean square errors (NRMSE) of 9% and 10%, respectively. By means of the GPR gap-filling time series of S2, entire tiles were reconstructed, and resulting maps were demonstrated over an agricultural area in Castile and Leon, Spain, where crop calendar data were available to assess the validity of LSP metrics derived from crop traits. In addition, phenology derived from the normalized difference vegetation index (NDVI) was used as reference. NDVI not only proved to be a robust indicator for the calculation of LSP metrics, but also served to demonstrate the good phenology quality of the quantitative trait products. Thanks to the GEE framework, the proposed workflow can be realized anywhere in the world and for any time window, thus representing a shift in the satellite data processing paradigm. We anticipate that the produced LSP metrics can provide meaningful insights into crop seasonal patterns in a changing environment that demands adaptive agricultural production.

A comparative study of Gaussian process regression with other three machine learning approaches in the performance prediction of centrifugal pump

2021 ◽  
pp. 095440622110505
Author(s):  
Xutao Zhao ◽  
Desheng Zhang ◽  
Renhui Zhang ◽  
Bin Xu
Keyword(s):  
Machine Learning ◽  
Gaussian Process ◽  
Centrifugal Pump ◽  
Kernel Function ◽  
Performance Prediction ◽  
Optimization Design ◽  
Gaussian Process Regression ◽  
Kernel Functions ◽  
Performance Indices ◽  
Pump Performance

Accurate prediction of performance indices using impeller parameters is of great importance for the initial and optimal design of centrifugal pump. In this study, a kernel-based non-parametric machine learning method named with Gaussian process regression (GPR) was proposed, with the purpose of predicting the performance of centrifugal pump with less effort based on available impeller parameters. Nine impeller parameters were defined as model inputs, and the pump performance indices, that is, the head and efficiency, were determined as model outputs. The applicability of three widely used nonlinear kernel functions of GPR including squared exponential (SE), rational quadratic (RQ) and Matern5/2 was investigated, and it was found by comparing with the experimental data that the SE kernel function is more suitable to capture the relationship between impeller parameters and performance indices because of the highest R square and the lowest values of max absolute relative error (MARE), mean absolute proportional error (MAPE), and root mean square error (RMSE). In addition, the results predicted by GPR with SE kernel function were compared with the results given by other three machine learning models. The comparison shows that the GPR with SE kernel function is more accurate and robust than other models in centrifugal pump performance prediction, and its prediction errors and uncertainties are both acceptable in terms of engineering applications. The GPR method is less costly in the performance prediction of centrifugal pump with sufficient accuracy, which can be further used to effectively assist the design and manufacture of centrifugal pump and to speed up the optimization design process of impeller coupled with stochastic optimization methods.

Adjoint-Based Inverse Design of Axial Compressor Airfoils

2021 ◽  
Author(s):  
Christophe Geuens ◽  
Tom Verstraete
Keyword(s):  
Inverse Problem ◽  
Inverse Method ◽  
Axial Compressor ◽  
Direct Methods ◽  
Velocity Profiles ◽  
Inverse Methods ◽  
Design Methods ◽  
Operating Conditions ◽  
Inverse Design ◽  
Blade Shape

Abstract Design methodologies for axial compressor airfoils have undergone significant changes over the past decades. While inverse design methods have played a significant historical role, today they are mostly replaced by direct methods. Inverse methods do impose either the desired pressure or velocity distribution and search for the corresponding blade profile, in contrast to direct methods which modify directly the blade shape to reduce losses. Inverse methods therefore require the designer to know pressure or velocity profiles which provide low losses, and are as such mostly effective only in the hands of an experienced designer. Inverse methods, however, pose some advantages: through setting velocity profiles which feature good off-design performance, the computational cost for the design of profiles can be significantly reduced compared to direct methods, which require to simulate multiple operating points. Additionally, inverse methods offer a way to adapt blades for experimental testing if the wind tunnel imposes restrictions on e.g. Mach number, allowing for similar boundary layer conditions. Finally, inverse methods can be used to deduce the blade geometry from measured or published velocity distributions. Within this article, we aim to verify the use of inverse methods by applying more recent optimisation techniques to the inverse problem. Specifically, we test the performance of an inverse method that uses a gradient based technique to solve the inverse problem. The merits of the inverse method are investigated for different use cases. It is found that conventional, direct design methods are preferred for design improvement, although more expensive. The inverse method is, however, well-suited for adapting existing profiles to altered operating conditions, and for reproducing the blade shape based on published data.

scholarly journals An Experimental and Statistical Study on Rebar Corrosion Considering the Temperature Effect Using Gaussian Process Regression

2020 ◽  
Vol 10 (17) ◽  
pp. 5937
Author(s):  
Byeong Hun Woo ◽  
In Kyu Jeon ◽  
Seong Soo Kim ◽  
Jeong Bae Lee ◽  
Jae-Suk Ryou
Keyword(s):  
Gaussian Process ◽  
Temperature Effect ◽  
Precise Measurement ◽  
Statistical Study ◽  
Corrosion Potential ◽  
High Reliability ◽  
Gaussian Process Regression ◽  
Corrosion Rates ◽  
Rebar Corrosion ◽  
Mean Square Errors

Temperature is an important factor that affects corrosion potential in rebars. The temperature effect must be removed from the corrosion potential for precise measurement of corrosion rates. To separate the temperature effect from the corrosion potential, in this study rebar specimens were not embedded in concrete but, instead, were placed in an uncontrolled air environment. Gaussian process regression (GPR) was applied to the temperature and the non-corrosion potential data in order to remove the temperature effect from the corrosion potential. The results indicated that the corrosion potential was affected by the temperature. Furthermore, the GPR models of all the experimental cases showed high coefficients of determination (R2 > 0.90) and low root mean square errors (RMSE < 0.08), meaning that these models had high reliability. The fitted GPR models were used to successfully remove the temperature effect from the corrosion potential. This demonstrates that the GPR method can be appropriately used to assess the temperature effect on rebar corrosion.

Exchange Spin Coupling from Gaussian Process Regression

2020 ◽  
Author(s):  
Marc Philipp Bahlke ◽  
Natnael Mogos ◽  
Jonny Proppe ◽  
Carmen Herrmann
Keyword(s):  
Machine Learning ◽  
Gaussian Process ◽  
Gaussian Process Regression ◽  
Molecular Magnets ◽  
Molecular Structures ◽  
Spin Coupling ◽  
Structure Property ◽  
Data Set ◽  
Uncertainty Estimates

Heisenberg exchange spin coupling between metal centers is essential for describing and understanding the electronic structure of many molecular catalysts, metalloenzymes, and molecular magnets for potential application in information technology. We explore the machine-learnability of exchange spin coupling, which has not been studied yet. We employ Gaussian process regression since it can potentially deal with small training sets (as likely associated with the rather complex molecular structures required for exploring spin coupling) and since it provides uncertainty estimates (“error bars”) along with predicted values. We compare a range of descriptors and kernels for 257 small dicopper complexes and find that a simple descriptor based on chemical intuition, consisting only of copper-bridge angles and copper-copper distances, clearly outperforms several more sophisticated descriptors when it comes to extrapolating towards larger experimentally relevant complexes. Exchange spin coupling is similarly easy to learn as the polarizability, while learning dipole moments is much harder. The strength of the sophisticated descriptors lies in their ability to linearize structure-property relationships, to the point that a simple linear ridge regression performs just as well as the kernel-based machine-learning model for our small dicopper data set. The superior extrapolation performance of the simple descriptor is unique to exchange spin coupling, reinforcing the crucial role of choosing a suitable descriptor, and highlighting the interesting question of the role of chemical intuition vs. systematic or automated selection of features for machine learning in chemistry and material science.

SAMPL6 Challenge Results from pKa Predictions Based on a General Gaussian Process Model

2018 ◽  
Author(s):  
Caitlin C. Bannan ◽  
David Mobley ◽  
A. Geoff Skillman
Keyword(s):  
Gaussian Process ◽  
Process Model ◽  
Molecular Graph ◽  
Gaussian Process Regression ◽  
Ionization State ◽  
Training Set ◽  
Physiochemical Properties ◽  
Quantile Plots ◽  
Physical And Chemical ◽  
Good Agreement

<div>A variety of fields would benefit from accurate pK<sub>a</sub> predictions, especially drug design due to the affect a change in ionization state can have on a molecules physiochemical properties.</div><div>Participants in the recent SAMPL6 blind challenge were asked to submit predictions for microscopic and macroscopic pK<sub>a</sub>s of 24 drug like small molecules.</div><div>We recently built a general model for predicting pK<sub>a</sub>s using a Gaussian process regression trained using physical and chemical features of each ionizable group.</div><div>Our pipeline takes a molecular graph and uses the OpenEye Toolkits to calculate features describing the removal of a proton.</div><div>These features are fed into a Scikit-learn Gaussian process to predict microscopic pK<sub>a</sub>s which are then used to analytically determine macroscopic pK<sub>a</sub>s.</div><div>Our Gaussian process is trained on a set of 2,700 macroscopic pK<sub>a</sub>s from monoprotic and select diprotic molecules.</div><div>Here, we share our results for microscopic and macroscopic predictions in the SAMPL6 challenge.</div><div>Overall, we ranked in the middle of the pack compared to other participants, but our fairly good agreement with experiment is still promising considering the challenge molecules are chemically diverse and often polyprotic while our training set is predominately monoprotic.</div><div>Of particular importance to us when building this model was to include an uncertainty estimate based on the chemistry of the molecule that would reflect the likely accuracy of our prediction. </div><div>Our model reports large uncertainties for the molecules that appear to have chemistry outside our domain of applicability, along with good agreement in quantile-quantile plots, indicating it can predict its own accuracy.</div><div>The challenge highlighted a variety of means to improve our model, including adding more polyprotic molecules to our training set and more carefully considering what functional groups we do or do not identify as ionizable. </div>

Sign in / Sign up

Export Citation Format

Share Document