scholarly journals Simulation of Groundwater Quality Characteristics using Artificial Neural Network

2021 ◽  
Vol 40 (1) ◽  
pp. 161-167
Author(s):  
O.O. Fadipe ◽  
L.K. Abidoye ◽  
J.O. Adeosun ◽  
B.B. Oguntola ◽  
O. Adewusi ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Groundwater Quality ◽  
Water Samples ◽  
Ph Value ◽  
Water Sources ◽  
Total Hardness ◽  
Good Prediction ◽  
Microbiological Analysis ◽  
Artificial Neural

This paper reports the study of groundwater quality assessment in Boluwaduro community, Ofatedo in Osun State. In addition, it utilized the Artificial Neural Network (ANN) tool in MATLAB Software to simulate the water quality parameters/contaminants. Water samples were taken from 18 randomly selected dugwells and subjected to physico-chemicals and microbiological analysis. The mean concentrations of nitrate, nitrite, lead and iron are 20.12 mg/L, 0.78 mg/L, 0.159 mg/L and 0.35 mg/L respectively. Total plate counts range between 27 – 96 cfu/mL with growth in all the water samples. The ANN structure was trained in several rounds till satisfactory output was obtained with correlation value of R2 = 0.97. Simulation of the pH using ANN provides a good match at 10% increment of chloride, nitrate and iron and the pH value of the water sources increased with the corresponding increase in the concentrations of the parameters. The generated model for TDS gave a good prediction with total hardness and magnesium respectively. The concentrations of some metals in the wells are not safe for drinking; it could pose danger to users of the water sources. It is therefore recommended that the wells in the community should be subjected to routine monitoring and treatment of the contaminants should be enforced.

scholarly journals Prediction of Groundwater Quality Using Artificial Neural Network

2021 ◽  
Author(s):  
Rita Maria Joseph ◽  
Alna D Manjaly ◽  
Sreeram Unni ◽  
Able E C ◽  
Vinitha Sharon
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Artificial Neural Network ◽  
Groundwater Quality ◽  
Quality Criterion ◽  
Quality Parameters ◽  
Total Hardness ◽  
Target Values ◽  
Input Parameters ◽  
Artificial Neural

Assessment and prediction of water quality is a vital tool for the management of water resources systems. It is necessitous for human existence, agriculture and industry. This project delves into the prediction of groundwater quality parameters and groundwater quality criterion based on the Artificial Neural Network Modelling with the study area as Kerala, a state of India. Two models were developed. The first model employs the water quality parameters such as pH, electrical conductivity, total hardness as the input parameters and calcium, magnesium, chloride, fluoride, nitrate concentration as the output parameters. The second model was designed by giving input as, input values and the predicted output values of the first model, and groundwater quality criterion corresponding to each location as the target values. The output qualitative parameters were estimated and compared with the measured values, to evaluate the influence of key input parameters. The number of neurons to be given in the hidden layer was decided by the trial-and-error method. Data of 506 water samples from all over Kerala were collected for modelling.

scholarly journals Prediction of size distribution of iron ore granules and permeability of its bed

2011 ◽  
Vol 47 (2) ◽  
pp. 113-123 ◽  
Author(s):  
X. Lv ◽  
C. Bai ◽  
X. Huang ◽  
G. Qiu
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Water Content ◽  
Size Distribution ◽  
Mass Fraction ◽  
Raw Materials ◽  
Good Prediction ◽  
Moisture Capacity ◽  
Granulation Process ◽  
Artificial Neural

The granulation process, which is determined by many factors like properties of the mixture and the operating parameters, is of very importance for getting a good permeability of the burden in the sintering strand. The prediction of the size distribution of the granules and the permeability of its bed by the artificial neural network was studied in this paper. It was found by the experiments that the order of significance in the granulation process is water content added into the mixture, the mass fraction of the particles of 0.7-3 mm, and the moisture capacity. The water content added in the mixture and the mass fractions of the particles of 0.7-3 mm have the positive relation to the permeability of granulation, While, the moisture capacity has the negative relation to the permeability of granulation. Both the moisture capacity and the water content added were used as the inputs in the model of artificial neural network, which can give a good prediction on the permeability and mass fraction of the granules of 3-8 mm, as well as the tendency of the samples under instable raw materials conditions. These two models can be used for optimization the granulation.

scholarly journals Prediction and Analysis of Tensile Properties of Austenitic Stainless Steel Using Artificial Neural Network

Metals ◽  
2020 ◽  
Vol 10 (2) ◽  
pp. 234 ◽  
Author(s):  
Yuxuan Wang ◽  
Xuebang Wu ◽  
Xiangyan Li ◽  
Zhuoming Xie ◽  
Rui Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Stainless Steel ◽  
Austenitic Stainless Steel ◽  
Tensile Properties ◽  
Prediction Performance ◽  
Good Prediction ◽  
Relative Significance ◽  
Value Analysis ◽  
Artificial Neural

Predicting mechanical properties of metals from big data is of great importance to materials engineering. The present work aims at applying artificial neural network (ANN) models to predict the tensile properties including yield strength (YS) and ultimate tensile strength (UTS) on austenitic stainless steel as a function of chemical composition, heat treatment and test temperature. The developed models have good prediction performance for YS and UTS, with R values over 0.93. The models were also tested to verify the reliability and accuracy in the context of metallurgical principles and other data published in the literature. In addition, the mean impact value analysis was conducted to quantitatively examine the relative significance of each input variable for the improvement of prediction performance. The trained models can be used as a guideline for the preparation and development of new austenitic stainless steels with the required tensile properties.

Studying on the Fiber Diameter of Polypropylene (PP) Spunbonding Fabric by Means of Artificial Neural Network Model and Physical Model

2010 ◽  
Vol 426-427 ◽  
pp. 356-360
Author(s):  
Bo Zhao
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Physical Model ◽  
Network Model ◽  
Process Parameters ◽  
Neural Network Model ◽  
Artificial Neural Network Model ◽  
Fiber Diameter ◽  
Good Prediction ◽  
Artificial Neural

In this work, the artificial neural network model and physical model are established and utilized for predicting the fiber diameter of polypropylene(PP) spunbonding nonwovens from the process parameters. The artificial neural network model has good approximation capability and fast convergence rate, is used in this research. The results show the artificial neural network model can provide quantitative predictions of fiber diameter and yield more accurate and stable predictions than the physical model, which reveals that the artificial neural network model is based on the inherent principles, and it can yield reasonably good prediction results and provide insight into the relationship between process parameters and fiber diameter.

Water Quality Forecast Based on BP-Artificial Neural Network Model in Qiantang River

2014 ◽  
Vol 668-669 ◽  
pp. 994-998
Author(s):  
Jin Ting Ding ◽  
Jie He
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Artificial Neural Network ◽  
Ph Value ◽  
Back Propagation ◽  
Ammonia Nitrogen ◽  
Quality Parameters ◽  
Ann Model ◽  
Qiantang River ◽  
Artificial Neural

This study aims at providing a back propagation-artificial neural network (BP-ANN) model on forecasting the water quality change trend of Qiantang River basin. To achieve this goal, a three-layer (one input layer, one hidden layer, and one output layer) BP-ANN with the LM regularization training algorithm was used. Water quality variables such as pH value, dissolved oxygen, permanganate index and ammonia-nitrogen was selected as the input data to obtain the output of the neural network. The ANN structure with 17 hidden neurons obtained the best selection. The comparison between the original measured and forecast values of the ANN model shows that the relative errors, with a few exceptions, were lower than 9%. The results indicated that the BP neural network can be satisfactorily applied to forecast precise water quality parameters and is suitable for pre-alarm of water quality trend.

Sign in / Sign up

Export Citation Format

Share Document