Hamed Dehghan Banadaki

Bio: Hamed Dehghan Banadaki is an academic researcher from Islamic Azad University. The author has contributed to research in topics: Fault detection and isolation & Multilayer perceptron. The author has an hindex of 5, co-authored 8 publications receiving 140 citations. Previous affiliations of Hamed Dehghan Banadaki include Islamic Azad University, Science and Research Branch, Tehran.

Prediction of Urmia Lake Water-Level Fluctuations by Using Analytical, Linear Statistic and Intelligent Methods

Abstract: Undoubtedly, the most significant factor with wise decision making and designing hydrological structures along the lake coasts is an accurate model of lake level changes. This issue becomes more and more important as recent global climate changes have completely reformed the behavior of traditional lake level fluctuations. Subsequently, estimating lake levels becomes more important and at the same time more difficult. This paper deals with modeling lake level changes of Lake Urmia located in north-west of Iran, in terms of both simulator and predictor models. According to this, two traditional simulator models based on water budget are developed which benefit from most effective components on water budget namely precipitation, evaporation, inflow and the lake level antecedents, as model inputs. Most famous linear modeling tools, Autoregressive with exogenous input (ARX) and Box-Jenkins (BJ) models are employed with the same mentioned inputs for prediction purpose. In addition, two other methods that are, Multi-Layer Perceptron (MLP) neural network and also Local Linear Neuro-Fuzzy (LLNF) are applied to investigate capability of intelligent nonlinear methods for lake level changes prediction. All models performances are indicated using both graph and numerical illustrations and results are discussed. Comparative results reveal that the intelligent methods are superior to traditional models for modeling lake level behavior as complex hydrological phenomena.

Intelligent non-linear modelling of an industrial winding process using recurrent local linear neuro-fuzzy networks

Abstract: This study deals with the neuro-fuzzy (NF) modelling of a real industrial winding process in which the acquired NF model can be exploited to improve control performance and achieve a robust fault-tolerant system. A new simulator model is proposed for a winding process using non-linear identification based on a recurrent local linear neuro-fuzzy (RLLNF) network trained by local linear model tree (LOLIMOT), which is an incremental tree-based learning algorithm. The proposed NF models are compared with other known intelligent identifiers, namely multilayer perceptron (MLP) and radial basis function (RBF). Comparison of our proposed non-linear models and associated models obtained through the least square error (LSE) technique (the optimal modelling method for linear systems) confirms that the winding process is a non-linear system. Experimental results show the effectiveness of our proposed NF modelling approach.

Model-based Fault Detection and Isolation Using Neural Networks: An Industrial Gas Turbine Case Study

Abstract: This study proposed a model based fault detection and isolation (FDI) method using multi-layer perceptron (MLP) neural network. Detection and isolation of realistic faults of an industrial gas turbine engine in steady-state conditions is mainly centered. A bank of MLP models which are obtained by nonlinear dynamic system identification is used to generate the residuals, and also simple thresholding is used for the intend of fault detection while another MLP neural network is employed to isolate the faults. The proposed FDI method was tested on a single-shaft industrial gas turbine prototype and it have been evaluated using non-linear simulations based on the real gas turbine data. A brief comparative study with other related works in the literature on this gas turbine benchmark is also provided to show the benefits of proposed FDI method.

Implementation of a hybrid MLP-FFA model for water level prediction of Lake Egirdir, Turkey

Abstract: The predictive ability of a hybrid model integrating the Firefly Algorithm (FFA), as a heuristic optimization tool with the Multilayer Perceptron (MLP-FFA) algorithm for the prediction of water level in Lake Egirdir, Turkey, is investigated. The accuracy of the hybrid MLP-FFA model is then evaluated against the standalone MLP-based model developed with the Levenberg–Marquadt optimization scheme applied for in the backpropagation-based learning process. To develop and investigate the veracity of the proposed hybrid MLP-FFA model, monthly time scale water level data for 56 years (1961–2016) are applied to train and test the hybrid model. The input combinations of the standalone and the hybrid predictive models are determined in accordance with the Average Mutual Information computed from the historical water level (training) data; generating four statistically significant lagged combinations of historical data to be adopted for the 1-month forecasting of lake water level. The proposed hybrid MLP-FFA model is evaluated with statistical score metrics: Nash–Sutcliffe efficiency, root mean square and mean absolute error, Wilmott’s Index and Taylor diagram developed in the testing phase. The analysis of the results showed that the hybrid MLP–FFA4 model (where 4 months of lagged combinations of lake water level data are utilized) performed more accurately than the standalone MLP4 model. For the fully optimized hybrid (MLP-FFA4) model evaluated in the testing phase, the Willmott’s Index was approximately 0.999 relative to 0.988 (MLP 4) and the root mean square error was approximately 0.029 m and compared to 0.102 m. Moreover, the inter-comparison of the forecasted and the observed data with various other performance metrics (including the Taylor diagram) verified the robustness of the proposed hybrid MLP-FFA4 model over the standalone MLP4 model applied in the problem of forecasting lake water level prediction in the current semi-arid region in Turkey.

Lake water quality assessment: a case study of Shahu Lake in the semiarid loess area of northwest China

Abstract: A comprehensive assessment on lake water quality was carried out in Shahu Lake, northwest China, to provide valuable information about present lake water quality for decision making. Major ions, general parameters, bacteriological parameters, organics and trace metals monitored monthly in 2014 were considered. Monitored parameters were compared with quality criteria for surface water of China, and overall water quality assessment was carried out using an entropy weighted water quality index (EWQI) based on 20 selected parameters. Lake water quality was also assessed for irrigation purpose. The results show that the lake water is of Cl·SO4–Na facies with high salinity and COD. The geochemistry of the lake water is regulated by intense evaporation and human activities. TP, TN and F− are major inorganic contaminants, with over 50% of the water samples polluted by them. Oil, mainly attributed by leaky motor tourist boats, is the major organic pollutants in the lake water, with 10 samples (37.04%) showing higher oil content than the permissible limit. The concentrations of other inorganic and organic contaminants as well as trace metals are well below the permissible limits. The present study indicates that inorganic contamination in the lake water is more severe than organic pollution. The overall lake water quality, assessed by EWQI, is poor and very poor with SO4 2−, TDS, TH and Cl− being the dominant contributing factors. The lake water is suitable for irrigation in terms of alkalinity, but is unsuitable for irrigation from the salinity point of view. Accelerating the circulation and replenishment of the lake water is an important way of reducing contaminant concentrations. This study is important in providing comprehensive information on lake water quality for decision makers and valuable reference for international lake water researchers.