A machine-learning approach to predicting the energy conversion performance of centrifugal pump impeller influenced by blade profile

2021 ◽  
pp. 095440622110282
Author(s):  
Yanzhao Wu ◽  
Ran Tao ◽  
Di Zhu ◽  
Zhifeng Yao ◽  
Ruofu Xiao
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Energy Conversion ◽  
Centrifugal Pump ◽  
Mechanical Energy ◽  
Traditional Theory ◽  
Pump Efficiency ◽  
Blade Profile ◽  
Blade Angle ◽  
Conversion Performance

Centrifugal pump is a kind of energy conversion machine for fluid delivering. It transfers the mechanical energy of impeller to the potential and kinetic energy of fluid. As a key factor in influencing the energy conversion performance of centrifugal pump, blade profile design is crucial. Traditional design concepts have ideal assumptions. To have a better design guidance, machine-learning based on neural network is used in this study. A typical centrifugal pump with simplified blade profile is numerically studied with experimental validation for a better discussion. Statistical results show that, for the high dimensional nonlinear relationship between blade angle and performance of centrifugal pump, neural network can adapt to this complex correlation better. The blade installation angle at leading-edge ( βLE′) and trailing-edge ( βTE′) and the wrap angle (Δ θ′) has significant correlation with the performance including pump head H, pump efficiency η, impeller head Himp, impeller efficiency ηimp and volute loss Δ Hvol. The influence level of blade angle follows the high-to-low order of Δ θ′, βLE′ and βTE′. Determination of blade profile can be done for improving the energy conversion efficiency. Optimal blade profiles have higher βLE′ and Δ θ′ with better flow-control ability. Compared with the blade parameters of the initial pump, the blade profile with the best centrifugal pump efficiency is the best βLE′ increased by 1.926°, Δ θ′ increased by 9.858°, Optimization of impeller efficiency βLE′ increased by 1.855°, Δ θ′ increased by 9.421°. Computational fluid dynamics indicate the elimination of vortex in impeller after optimal selection. Then, βTE′ and Δ θ′ are found influential in aggravating the circumferential flow component in this special circular-volute with generating higher loss. βTE′ has a positive correlation with impeller head which suits traditional theory. In general, the machine-learning using neural network is effective in determining blade profiles for enhancing the performance of centrifugal pump.

scholarly journals Performance Characteristics in Runner of an Impulse Water Turbine with Splitter Blade

Processes ◽  
2021 ◽  
Vol 9 (2) ◽  
pp. 303
Author(s):  
Lingdi Tang ◽  
Shouqi Yuan ◽  
Yue Tang ◽  
Zhijun Gao
Keyword(s):  
Energy Conversion ◽  
Flow Direction ◽  
Mechanical Energy ◽  
Experimental Tests ◽  
High Energy ◽  
Negative Energy ◽  
Water Turbine ◽  
Conversion Performance ◽  
Water Turbines ◽  
Current Energy

The impulse water turbine is a promising energy conversion device that can be used as mechanical power or a micro hydro generator, and its application can effectively ease the current energy crisis. This paper aims to clarify the mechanism of liquid acting on runner blades, the hydraulic performance, and energy conversion characteristics in the runner domain of an impulse water turbine with a splitter blade by using experimental tests and numerical simulations. The runner was divided into seven areas along the flow direction, and the power variation in the runner domain was analyzed to reflect its energy conversion characteristics. The obtained results indicate that the critical area of the runner for doing the work is in the front half of the blades, while the rear area of the blades does relatively little work and even consumes the mechanical energy of the runner to produce negative work. The high energy area is concentrated in the flow passage facing the nozzle. The energy is gradually evenly distributed from the runner inlet to the runner outlet, and the negative energy caused by flow separation with high probability is gradually reduced. The clarification of the energy conversion performance is of great significance to improve the design of impulse water turbines.

scholarly journals Fault Diagnosis in Centrifugal Pump using Support Vector Machine and Artificial Neural Network

2021 ◽  
Author(s):  
Nagendra Singh Ranawat ◽  
◽  
Pavan Kumar Kankar ◽  
Ankur Miglani ◽  
◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Centrifugal Pump ◽  
Support Vector ◽  
Feature Ranking ◽  
Chi Square ◽  
Artificial Neural

Centrifugal pumps are commonly utilized in thermo-fluidic systems in the industry. Being a rotating machinery, they are prone to vibrations and their premature failure may affect the system predictability and reliability. To avoid their premature breakdown during operation, it is necessary to diagnose the faults in a pump at their initial stage. This study presents the methodology to diagnose fault of a cent rifugal pump using two distinct machine learning techniques, namely, Support vector machine (SVM) and Artificial neural network (ANN). Different statistical features are extracted in the time and the frequency domain of the vibration signal for different working conditions of the pump. Furthermore, to decrease the dimensionality of the obtained features different feature ranking (FR) methods, namely, Chi-square, ReliefF and XGBoost are employed. ANN technique is found to be more efficient in classifying faults in a centrifugal pump as compared to the SVM, and Chi-square and XGBoost ranking techniques are better than ReliefF at sorting more relevant features. The results presented in thus study demonstrate that an ANN based machine learning approach with Chi-square and XGBoost feature ranking techniques can be used effectively for the fault diagnosis of a centrifugal pump.

scholarly journals Methods to Improve Energy Conversion Efficiency of Dielectric Elastomer Generators

2019 ◽  
Vol 804 ◽  
pp. 63-67
Author(s):  
Heng Tong Cheng ◽  
Zhen Qiang Song ◽  
Shijie Zhu ◽  
Kazuhiro Ohyama
Keyword(s):  
Energy Conversion ◽  
Conversion Efficiency ◽  
Mechanical Energy ◽  
Electrical Energy ◽  
Input Voltage ◽  
Energy Conversion Efficiency ◽  
Stretch Ratio ◽  
Dielectric Elastomer ◽  
Conversion Performance ◽  
Ratio Range

Dielectric elastomer generators (DEGs) are based on the electromechanical response of the dielectric elastomer film sandwiched between the compliant electrodes on each side, which are capable of converting mechanical energy from diverse sources (e.g, ocean wave) into electrical energy. In essence, DEG is a voltage up-converter using mechanical energy to increase the electrical energy of the charge on a soft capacitor. We evaluated the effect of input voltage and the pre-stretch ratios on energy conversion efficiency of DEG. With a power supply of 2.2kV and pre-stretch ratio of 2, the maximum net electrical energy density and energy conversion efficiency in a single harvesting cycle were measured to be 413 J/kg and 15.8%, respectively. The experimental results showed that, with the higher input voltage and the larger stretch ratio range, higher the energy conversion performance of DEG can be achieved.

Adsorption Isotherm Predictions for Multiple Molecules in MOFs Using the Same Deep Learning Model

2019 ◽  
Author(s):  
Ryther Anderson ◽  
Achay Biong ◽  
Diego Gómez-Gualdrón
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Molecular Simulation ◽  
Large Scale ◽  
Learning Model ◽  
Operating Conditions ◽  
Small Subset ◽  
Screening Methods ◽  
Large Set ◽  
Metal Organic

<div>Tailoring the structure and chemistry of metal-organic frameworks (MOFs) enables the manipulation of their adsorption properties to suit specific energy and environmental applications. As there are millions of possible MOFs (with tens of thousands already synthesized), molecular simulation, such as grand canonical Monte Carlo (GCMC), has frequently been used to rapidly evaluate the adsorption performance of a large set of MOFs. This allows subsequent experiments to focus only on a small subset of the most promising MOFs. In many instances, however, even molecular simulation becomes prohibitively time consuming, underscoring the need for alternative screening methods, such as machine learning, to precede molecular simulation efforts. In this study, as a proof of concept, we trained a neural network as the first example of a machine learning model capable of predicting full adsorption isotherms of different molecules not included in the training of the model. To achieve this, we trained our neural network only on alchemical species, represented only by their geometry and force field parameters, and used this neural network to predict the loadings of real adsorbates. We focused on predicting room temperature adsorption of small (one- and two-atom) molecules relevant to chemical separations. Namely, argon, krypton, xenon, methane, ethane, and nitrogen. However, we also observed surprisingly promising predictions for more complex molecules, whose properties are outside the range spanned by the alchemical adsorbates. Prediction accuracies suitable for large-scale screening were achieved using simple MOF (e.g. geometric properties and chemical moieties), and adsorbate (e.g. forcefield parameters and geometry) descriptors. Our results illustrate a new philosophy of training that opens the path towards development of machine learning models that can predict the adsorption loading of any new adsorbate at any new operating conditions in any new MOF.</div>

Artificial neural network models for coronary artery disease

2020 ◽  
Vol 15 ◽  
Author(s):  
Elham Shamsara ◽  
Sara Saffar Soflaei ◽  
Mohammad Tajfard ◽  
Ivan Yamshchikov ◽  
Habibollah Esmaili ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Coronary Artery Disease ◽  
Pattern Recognition ◽  
Artificial Neural Network ◽  
Coronary Artery ◽  
Diagnostic Model ◽  
Early Prediction ◽  
Artificial Neural ◽  
Artery Disease

Background: Coronary artery disease (CAD) is an important cause of mortality and morbidity globally. Objective : The early prediction of the CAD would be valuable in identifying individuals at risk, and in focusing resources on its prevention. In this paper, we aimed to establish a diagnostic model to predict CAD by using three approaches of ANN (pattern recognition-ANN, LVQ-ANN, and competitive ANN). Methods: One promising method for early prediction of disease based on risk factors is machine learning. Among different machine learning algorithms, the artificial neural network (ANN) algo-rithms have been applied widely in medicine and a variety of real-world classifications. ANN is a non-linear computational model, that is inspired by the human brain to analyze and process complex datasets. Results: Different methods of ANN that are investigated in this paper indicates in both pattern recognition ANN and LVQ-ANN methods, the predictions of Angiography+ class have high accuracy. Moreover, in CNN the correlations between the individuals in cluster ”c” with the class of Angiography+ is strongly high. This accuracy indicates the significant difference among some of the input features in Angiography+ class and the other two output classes. A comparison among the chosen weights in these three methods in separating control class and Angiography+ shows that hs-CRP, FSG, and WBC are the most substantial excitatory weights in recognizing the Angiography+ individuals although, HDL-C and MCH are determined as inhibitory weights. Furthermore, the effect of decomposition of a multi-class problem to a set of binary classes and random sampling on the accuracy of the diagnostic model is investigated. Conclusion : This study confirms that pattern recognition-ANN had the most accuracy of performance among different methods of ANN. That’s due to the back-propagation procedure of the process in which the network classify input variables based on labeled classes. The results of binarization show that decomposition of the multi-class set to binary sets could achieve higher accuracy.

Using artificial neural network condensation to facilitate adaption of machine learning in medical settings by reducing computational burden (Preprint)

2020 ◽  
Author(s):  
Dianbo Liu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Third World ◽  
Mortality Prediction ◽  
Neural Net ◽  
Medical Settings ◽  
Hidden Layer ◽  
Applications Of Machine Learning ◽  
Computational Resources ◽  
Developed Nations

BACKGROUND Applications of machine learning (ML) on health care can have a great impact on people’s lives. At the same time, medical data is usually big, requiring a significant amount of computational resources. Although it might not be a problem for wide-adoption of ML tools in developed nations, availability of computational resource can very well be limited in third-world nations and on mobile devices. This can prevent many people from benefiting of the advancement in ML applications for healthcare. OBJECTIVE In this paper we explored three methods to increase computational efficiency of either recurrent neural net-work(RNN) or feedforward (deep) neural network (DNN) while not compromising its accuracy. We used in-patient mortality prediction as our case analysis upon intensive care dataset. METHODS We reduced the size of RNN and DNN by applying pruning of “unused” neurons. Additionally, we modified the RNN structure by adding a hidden-layer to the RNN cell but reduce the total number of recurrent layers to accomplish a reduction of total parameters in the network. Finally, we implemented quantization on DNN—forcing the weights to be 8-bits instead of 32-bits. RESULTS We found that all methods increased implementation efficiency–including training speed, memory size and inference speed–without reducing the accuracy of mortality prediction. CONCLUSIONS This improvements allow the implementation of sophisticated NN algorithms on devices with lower computational resources.

scholarly journals Discretization and machine learning approximation of BSDEs with a constraint on the Gains-process

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Idris Kharroubi ◽  
Thomas Lim ◽  
Xavier Warin
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Differential Equations ◽  
Numerical Experiments ◽  
Optimization Problem ◽  
Learning Approach ◽  
The Neural Network ◽  
Machine Learning Approach ◽  
Mesh Grid

AbstractWe study the approximation of backward stochastic differential equations (BSDEs for short) with a constraint on the gains process. We first discretize the constraint by applying a so-called facelift operator at times of a grid. We show that this discretely constrained BSDE converges to the continuously constrained one as the mesh grid converges to zero. We then focus on the approximation of the discretely constrained BSDE. For that we adopt a machine learning approach. We show that the facelift can be approximated by an optimization problem over a class of neural networks under constraints on the neural network and its derivative. We then derive an algorithm converging to the discretely constrained BSDE as the number of neurons goes to infinity. We end by numerical experiments.

scholarly journals A review of infant cry analysis and classification

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Chunyan Ji ◽  
Thosini Bamunu Mudiyanselage ◽  
Yutong Gao ◽  
Yi Pan
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Signal Analysis ◽  
Future Research ◽  
Prosodic Features ◽  
Infant Cry ◽  
Machine Learning Classification ◽  
Machine Learning Classifiers ◽  
Learning Classifiers ◽  
Processing Techniques

AbstractThis paper reviews recent research works in infant cry signal analysis and classification tasks. A broad range of literatures are reviewed mainly from the aspects of data acquisition, cross domain signal processing techniques, and machine learning classification methods. We introduce pre-processing approaches and describe a diversity of features such as MFCC, spectrogram, and fundamental frequency, etc. Both acoustic features and prosodic features extracted from different domains can discriminate frame-based signals from one another and can be used to train machine learning classifiers. Together with traditional machine learning classifiers such as KNN, SVM, and GMM, newly developed neural network architectures such as CNN and RNN are applied in infant cry research. We present some significant experimental results on pathological cry identification, cry reason classification, and cry sound detection with some typical databases. This survey systematically studies the previous research in all relevant areas of infant cry and provides an insight on the current cutting-edge works in infant cry signal analysis and classification. We also propose future research directions in data processing, feature extraction, and neural network classification fields to better understand, interpret, and process infant cry signals.

Sign in / Sign up

Export Citation Format

Share Document