A neural network-based scheme for predicting critical unmeasurable parameters of a free piston Stirling oscillator

Shourangiz-Haghighi, Alireza; Tavakolpour-Saleh, A.R.

doi:10.1016/j.enconman.2019.06.035

Cited by 21 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper focuses on extracting feature information and predicting energy performance according to critical design and operation parameters of the centrifugal pump during the first stage only, with the goal of shortening the development period and reducing research costs. Current methods of centrifugal pump performance prediction (CPPP) mainly include the hydraulic loss method (HLM) [2][3][4][5], the computational fluid dynamic (CFD) [6][7][8] numerical simulation method, and the artificial neural network (ANN) method [9][10][11][12].…”

Section: Introductionmentioning

confidence: 99%

A Novel Energy Performance Prediction Approach towards Parametric Modeling of a Centrifugal Pump in the Design Process

Nan

Wang

Chen

et al. 2023

Water

View full text Add to dashboard Cite

Traditional centrifugal pump performance prediction (CPPP) employs the semi-theoretical and semi-empirical approaches; however, it can lead to many prediction errors. Considering the superiority of deep learning when applied to nonlinear systems, in this paper, a method combining hydraulic loss and convolutional neural network (HLCNN) is applied to CPPP. Head and efficiency were selected as two variables for demonstrating the energy performance of the centrifugal pump in order to reflect the prediction ability of the proposed model. The evaluation results indicate that the predicted head and efficiency are accurate, compared with the experimental results. Furthermore, the HLCNN prediction model was compared against machine learning methods and the computational fluid dynamic method. The proposed HLCNN model obtained a better AREmean, root mean square error, sum of squares due to error, and mean absolute error for centrifugal pump energy performance. The research revealed that the HLCNN model achieves accurate energy performance prediction in the design of centrifugal pumps, reducing the development time and costs.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Energy Performance Prediction Approach towards Parametric Modeling of a Centrifugal Pump in the Design Process

Nan

Wang

Chen

et al. 2023

Water

View full text Add to dashboard Cite

show abstract

“…However, in the present work, data related to a given output are never measured, and probably are unmeasurable. Unmeasurable variables have been recently considered by the scientific community, with several application in the engineering field [5]. In [5], the authors used physical modeling and simulation to complement datadriven approach with the missing unmeasurable data, however, there was no data-driven correction methodology to update these unmeasurable data.…”

Section: Introduction and Related Workmentioning

confidence: 99%

“…Unmeasurable variables have been recently considered by the scientific community, with several application in the engineering field [5]. In [5], the authors used physical modeling and simulation to complement datadriven approach with the missing unmeasurable data, however, there was no data-driven correction methodology to update these unmeasurable data. In [6], the authors aimed to build the most suitable differential equation of a physical domain, through using a pool of multiple linear and non-linear operators.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Data-Completion and Model Correction by Means of Evanescent Regularization

Ghnatios,

Jiang,

Tourbier

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

System components are often regarded as part of a whole system, especially when it comes to data-driven modeling. Thus, subsystem modeling is disregarded in general when building a data-driven response, especially since multiple subsystem outputs are never measured in real applications. However, subsystem knowledge and accurate modeling are of utmost importance when aiming to repair, tune or troubleshoot a system. This work proposes a holistic modeling of subsystems in an embedded system setting. A hybrid modeling starting from the physics-based model is proposed in this work, correcting or enhancing the model, and predicting output variables, even when a measurement is never available for some of those variables. The process relies on the variables’ history, and employs an adjoint-free neural ordinary differential equation technique, along with evanescent regularization to enhance the convergence on the unmeasurable variables. The updated model converges to the exact measurements, for both the measurable and the unmeasurable variables. Multiple examples are presented using synthetic data, to allow an easy evaluation of the hidden or unmeasurable variables. The relative error offered by the updated model is around 0.001% for the measurable quantities and 0.1% for the unmeasurable ones.

show abstract

An improved design of power-cycling hydrodynamic mechanical transmission

Liu

Sun

2020

J Mech Sci Technol

View full text Add to dashboard Cite

A neural network-based scheme for predicting critical unmeasurable parameters of a free piston Stirling oscillator

Cited by 21 publications

References 40 publications

A Novel Energy Performance Prediction Approach towards Parametric Modeling of a Centrifugal Pump in the Design Process

A Novel Energy Performance Prediction Approach towards Parametric Modeling of a Centrifugal Pump in the Design Process

Data-Completion and Model Correction by Means of Evanescent Regularization

An improved design of power-cycling hydrodynamic mechanical transmission

Contact Info

Product

Resources

About