In the present study, multi-objective optimization of Forward-Curved (FC) blade centrifugal fans is performed in three steps. In the first step, Head rise (HR) and the Head loss (HL) in a set of FC centrifugal fan is numerically investigated using commercial software NUMECA. Two meta-models based on the evolved group method of data handling (GMDH) type neural networks are obtained, in the secon...

This article deals with the problem of determination of the model uncertainty during the system identification via application of the self-organising group method of data handling (GMDH) neural network. In particular, the contribution of the neural network structure errors and the parameter estimates inaccuracy to the model uncertainty were presented. Knowing these sources and applying the Oute...

A system identification method for nonlinear systems with unknown structure by means of short input-output data is proposed. This method introduces more general model structure for nonlinear systems. Moreover, based on gray-box idea and its salient feature with expanding NARMAX (Nonlinear Autoregressive, Moving Average eXogenous) modeling, this method integrates different system information. Th...

Linear regression is widely used in flood quantile study that consists of meteorological and physiographical variables. However, linear does not capture the complex nonlinear relationship between predictor target It rare to find a hydrological application using group method data handling (GMDH) model, artificial bee colony (ABC) algorithm, ensemble technique, precisely predicting ungauged sites...

Prediction of building energy consumption plays an important role in conservation, management, and planning. Continuously improving enhancing the performance forecasting models is key to ensuring sustainability systems. In this connection, current paper presented a new improved hybrid model machine learning application for cooling load (CL) heating (HL) residential buildings after studying anal...

Abstract Free overfalls are hydraulic structures used in flood control, water supply, irrigation, and flow measurements. The systems of free overfall depend on rectangular end shape. studies that dealt with triangular crest few almost non-existent. In this study, a end-shape design uses multiple linear regression (MLR) group method data handling (GMDH) methods for four models six sub-models. Th...

Characteristics of the existing neural networks GMDH with active neurons are given and their main advantages disadvantages analyzed. Two approaches increasing efficiency inductive construction complex system models from statistical data based on a new hybrid using methods computational intelligence proposed. The effectiveness these is compared classical to artificial modelling tasks (noisy line...

The focus of this research is to introduce the application polynomial neural network group method data handling (GMDH) for first time in regional area New South Wales state Australia. Within context, temperature are modeled assess its projected variation impacts on rainfall depth due climate change. study encompasses six local government areas within state’s Central West region. Stochastic meth...