Established prediction models of thermal conductivity of hybrid nanofluids based on artificial neural network (ANN) models in waste heat system

In this study, three artificial neural network (ANN) models are developed with back propagation (BP) optimization algorithms to predict various lightning damage modes in carbon/epoxy laminates. The proposed ANN models use three input variables associated with lightning waveform parameters (i.e., the peak current amplitude, rising time, and decaying time) to predict fiber damage, matrix damage, and through-thickness damage in the composites. The data used for training and testing the networks was actual lightning damage data collected from peer-reviewed published literature. Various BP training algorithms and network architecture configurations (i.e., data splitting, the number of neurons in a hidden layer, and the number of hidden layers) have been tested to improve the performance of the neural networks. Among the various BP algorithms considered, the Bayesian regularization back propagation (BRBP) showed the overall best performance in lightning damage prediction. When using the BRBP algorithm, as expected, the greater the fraction of the collected data that is allocated to the training dataset, the better the network is trained. In addition, the optimal ANN architecture was found to have a single hidden layer with 20 neurons. The ANN models proposed in this work may prove useful in preliminary assessments of lightning damage and reduce the number of expensive experimental lightning tests.

Download Full-text

Prediction of the Density & Thermal Conductivity of Light Bricks on the Effect of Aluminium Elements Using Artificial Neural Network (ANN)

Materials Science Forum ◽

10.4028/www.scientific.net/msf.964.270 ◽

2019 ◽

Vol 964 ◽

pp. 270-279

Author(s):

Zulkifli ◽

Gede Panji

Keyword(s):

Neural Network ◽

Thermal Conductivity ◽

Artificial Neural Network ◽

Raw Materials ◽

Simulation Method ◽

Acoustic Properties ◽

Main Element ◽

Artificial Neural ◽

Artificial Neural Network Ann ◽

Element Variation

Indonesia with abundant limestone raw materials, lightweight brick is the most important component in building construction, so it needs a light brick product that qualifies in thermal, mechanical and acoustic properties. In this paper raised the lightweight brick domains that qualify on the properties of thermal conductivity as building wall components.The advantage of low light density brick (500-650 kg/m3), more economical, suitable for high rise building can reduce the weight of 30-40% in compared to conventional brick (clay brick). To obtain AAC type lightweight brick product that qualifies for low thermal and density properties to the effect of Aluminum (Al) additive element variation using artificial neural network (ANN). The composition of the main elements of lightweight brick O (29-45 % wt), Si (25-35% wt) and Ca (20-40 % wt). Mixing ratio of the main element of light brick (Ca, O and Si) with Aluminum additive element (Al), is done by simulation method of artificial neural network (ANN), Al additive element as a porosity regulator is formed. The simulation of thermal conductivity to the influence of main element variation: Ca (22-32 % wt), Si (12-33 % wt). Simulation of thermal conductivity to effect of additive Al variation (1-7 % wt). Simulation of thermal conductivity to density variation (500-1200 kg/m3). The simulated results of four AAC brick samples showed the thermal conductivity (0.145-0.192 W/m.K) to the influence of qualified Aluminum additives (2.10-6.75 % wt). Additive Al the higher the lower density value (higher porosity) additive Al smaller than 2.10 % wt does not meet the requirements in the simulation.Thermal conductivity of AAC light brick sample (0.184 W/m.K) the influence of the main elements that qualify Ca (20.32-30.35 % wt) and Si (26.57 % wt). Simulation of artificial neural network (ANN) of light brick shows that maximum allowable Si content of 26.57 % wt, Ca content is in the range 20.32-30.35 % wt, and the minimum content of aluminum in brick is light at 2.10 % wt. ANN tests performed to predict the thermal conductivity of light brick samples obtained results of the average AAC light brick thermal conductivity of 0.151 W/m.K. The best performance with Artificial Neural Network (ANN) characteristics has a validation MSE of 0.002252.

Download Full-text

An investigation on the mortars containing blended cement subjected to elevated temperatures using Artificial Neural Network (ANN) models

Computers and Concrete ◽

10.12989/cac.2012.10.6.649 ◽

2012 ◽

Vol 10 (6) ◽

pp. 649-662

Author(s):

A.A. Ramezanianpour ◽

M.E. Kamel ◽

A. Kazemian ◽

E. Ghiasvand ◽

H. Shokrani ◽

...

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Elevated Temperatures ◽

Blended Cement ◽

Ann Models ◽

Artificial Neural ◽

Artificial Neural Network Ann

Download Full-text

Length of Hospital Stay Prediction at the Admission Stage for Cardiology Patients Using Artificial Neural Network

Journal of Healthcare Engineering ◽

10.1155/2016/7035463 ◽

2016 ◽

Vol 2016 ◽

pp. 1-11 ◽

Cited By ~ 24

Author(s):

Pei-Fang (Jennifer) Tsai ◽

Po-Chia Chen ◽

Yen-You Chen ◽

Hao-Yuan Song ◽

Hsiu-Mei Lin ◽

...

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Coronary Atherosclerosis ◽

Inpatient Care ◽

Length Of Hospital Stay ◽

Ann Models ◽

Artificial Neural ◽

Artificial Neural Network Ann ◽

Christian Hospital

For hospitals’ admission management, the ability to predict length of stay (LOS) as early as in the preadmission stage might be helpful to monitor the quality of inpatient care. This study is to develop artificial neural network (ANN) models to predict LOS for inpatients with one of the three primary diagnoses: coronary atherosclerosis (CAS), heart failure (HF), and acute myocardial infarction (AMI) in a cardiovascular unit in a Christian hospital in Taipei, Taiwan. A total of 2,377 cardiology patients discharged between October 1, 2010, and December 31, 2011, were analyzed. Using ANN or linear regression model was able to predict correctly for 88.07% to 89.95% CAS patients at the predischarge stage and for 88.31% to 91.53% at the preadmission stage. For AMI or HF patients, the accuracy ranged from 64.12% to 66.78% at the predischarge stage and 63.69% to 67.47% at the preadmission stage when a tolerance of 2 days was allowed.

Download Full-text

A Modified Kennard-Stone Algorithm for Optimal Division of Data for Developing Artificial Neural Network Models

Chemical Product and Process Modeling ◽

10.1515/1934-2659.1645 ◽

2012 ◽

Vol 7 (1) ◽

Cited By ~ 33

Author(s):

Agus Saptoro ◽

Moses O. Tadé ◽

Hari Vuthaluru

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Network Models ◽

Data Representation ◽

Data Splitting ◽

Neural Network Models ◽

Data Division ◽

Ann Models ◽

Artificial Neural ◽

Artificial Neural Network Ann

Abstract This paper proposes a method, namely MDKS (Kennard-Stone algorithm based on Mahalanobis distance), to divide the data into training and testing subsets for developing artificial neural network (ANN) models. This method is a modified version of the Kennard-Stone (KS) algorithm. With this method, better data splitting, in terms of data representation and enhanced performance of developed ANN models, can be achieved. Compared with standard KS algorithm and another improved KS algorithm (data division based on joint x - y distances (SPXY) method), the proposed method has also shown a better performance. Therefore, the proposed technique can be used as an advantageous alternative to other existing methods of data splitting for developing ANN models. Care should be taken when dealing with large amount of dataset since they may increase the computational load for MDKS due to its variance-covariance matrix calculations.

Download Full-text