scholarly journals An MLP-ANN-based approach for assessing nitrate contamination

2019 ◽  
Vol 19 (7) ◽  
pp. 1911-1917 ◽  
Author(s):  
Maria Laura Foddis ◽  
Augusto Montisci ◽  
Fatma Trabelsi ◽  
Gabriele Uras
Keyword(s):  
Neural Networks ◽  
Electrical Conductivity ◽  
Laboratory Tests ◽  
Nitrate Concentration ◽  
Nitrate Contamination ◽  
Multi Layer Perceptron ◽  
Indirect Measurements ◽  
Direct Measurements ◽  
Ann Models ◽  
Cost Efficient

Abstract This paper investigates the feasibility of predicting nitrate contamination from agricultural sources using multi-layer perceptron artificial neural networks (MLP-ANNs). The approach consists in training an MLP-ANN to predict nitrate concentrations based on a set of indirect measurements, such as pH, electrical conductivity, temperature and groundwater level. These are simpler and more economical than direct measurements, and they can be continuously collected on-site, rather than by performing laboratory tests. The approach has been validated in the nitrate vulnerable zone of the Arborea plain (central western Sardinia, Italy) by comparing the results obtained with different MLP-ANN models in order to find the most efficient model. The results show that the MLP-ANN-based model is a time- and cost-efficient method for predicting nitrate concentration.

scholarly journals Mapping the Pollution Plume Using the Self-Potential Geophysical Method: Case of Oum Azza Landfill, Rabat, Morocco

Water ◽  
2021 ◽  
Vol 13 (7) ◽  
pp. 961
Author(s):  
Meryem Touzani ◽  
Ismail Mohsine ◽  
Jamila Ouardi ◽  
Ilias Kacimi ◽  
Moad Morarech ◽  
...  
Keyword(s):  
Electrical Conductivity ◽  
Water Table ◽  
Soil Surface ◽  
The Self ◽  
Drainage Network ◽  
Geophysical Method ◽  
Direct Measurements ◽  
Sandy Material ◽  
The City ◽  
Self Potential

The main landfill in the city of Rabat (Morocco) is based on sandy material containing the shallow Mio-Pliocene aquifer. The presence of a pollution plume is likely, but its extent is not known. Measurements of spontaneous potential (SP) from the soil surface were cross-referenced with direct measurements of the water table and leachates (pH, redox potential, electrical conductivity) according to the available accesses, as well as with an analysis of the landscape and the water table flows. With a few precautions during data acquisition on this resistive terrain, the results made it possible to separate the electrokinetic (~30%) and electrochemical (~70%) components responsible for the range of potentials observed (70 mV). The plume is detected in the hydrogeological downstream of the discharge, but is captured by the natural drainage network and does not extend further under the hills.

Direct and Indirect Vibro-Acoustic Measurements for Road Noise NVH Predictions

2005 ◽  
Author(s):  
Alessandro Zanarini ◽  
Filip De Coninck ◽  
Krzysztof Mendrok ◽  
Paul Sas
Keyword(s):  
Complex Structure ◽  
Indirect Measurement ◽  
Acoustic Measurements ◽  
Road Noise ◽  
Indirect Measurements ◽  
Direct Measurements ◽  
Path Direction ◽  
Vehicle Technologies ◽  
Structure Measurement ◽  
Reverse Path

This paper describes vibro-acoustic direct and indirect measurements for road noise NVH predictions from a complete car. Attention is devoted to the dynamic response of the structure and interior pressure field toward tire patch displacement inputs. The direct measurements exploited the Team Corporation CUBE™ high frequency 6 degree-of-freedom (DOF) shaker recently installed at the KULeuven Vehicle Technologies Laboratory; the input was provided directly at the tire contact patch, while the responses were measured as accelerations and pressures on the structure. In the indirect measurements a low-mid frequency volume velocity source (LMFVVS) was used to acoustically excite the structure in the reverse path direction from the inside of the interior car cavity, while accelerations on the car and forces/torques where acquired by a 6-DOF dynamometer at the tire patch. From both types of excitations Frequency Response Functions (FRF) were calculated in the frequency range [0–500 Hz]. The non-linearity of the full car system was investigated with different direct and indirect measurement tests, in order to assess the feasibility of the reciprocity principle in such a complex structure. Measurement set-ups, results and comparisons are described and discussed in detail.

Electrical conductivity identification of a carbon fiber composite material plate using a rotating magnetic field and multi-coil eddy current sensor

2018 ◽  
Vol 83 (2) ◽  
pp. 20901 ◽  
Author(s):  
Ahmed Chaouki Lahrech ◽  
Bachir Abdelhadi ◽  
Mouloud Feliachi ◽  
Abdelhalim Zaoui ◽  
Mohammed Naїdjate
Keyword(s):  
Magnetic Field ◽  
Neural Networks ◽  
Electrical Conductivity ◽  
Composite Material ◽  
Carbon Fiber ◽  
Fiber Composite ◽  
Rotating Magnetic Field ◽  
Current Sensor ◽  
Carbon Fiber Composite ◽  
Fiber Composite Material

This paper proposes a contactless method for the identification of the electrical conductivity tensor of a carbon fiber composite materials plate using a rotating magnetic field and multi-coil eddy current sensor. This sensor consists of identical rectangular multi-coil, excited by two-phase sinusoidal current source in order to generate a rotating magnetic field and to avoid the mechanical rotation of the sensor. The fibers orientations, the longitudinal and transverse conductivities in each ply of carbon fiber composite material plate were directly determined with analysis of the impedance variation of each coil as function of its angular position. The inversion process is based on the use of artificial neural networks. The direct calculation associated with artificial neural networks makes use of 3D time-harmonic finite element method based on the A, V–A formulation.

scholarly journals Applicability of Artificial Neural Networks to Predict Mechanical and Permeability Properties of Volcanic Scoria-Based Concrete

2018 ◽  
Vol 2018 ◽  
pp. 1-16 ◽  
Author(s):  
Aref M. al-Swaidani ◽  
Waed T. Khwies
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Network Architecture ◽  
Supplementary Cementitious Material ◽  
Natural Pozzolans ◽  
Long Time ◽  
Ann Models ◽  
Artificial Neural ◽  
And Performance ◽  
And Training

Numerous volcanic scoria (VS) cones are found in many places worldwide. Many of them have not yet been investigated, although few of which have been used as a supplementary cementitious material (SCM) for a long time. The use of natural pozzolans as cement replacement could be considered as a common practice in the construction industry due to the related economic, ecologic, and performance benefits. In the current paper, the effect of VS on the properties of concrete was investigated. Twenty-one concrete mixes with three w/b ratios (0.5, 0.6, and 0.7) and seven replacement levels of VS (0%, 10%, 15%, 20%, 25%, 30%, and 35%) were produced. The investigated concrete properties were the compressive strength, the water permeability, and the concrete porosity. Artificial neural networks (ANNs) were used for prediction of the investigated properties. Feed-forward backpropagation neural networks have been used. The ANN models have been established by incorporation of the laboratory experimental data and by properly choosing the network architecture and training processes. This study shows that the use of ANN models provided a more accurate tool to capture the effects of five parameters (cement content, volcanic scoria content, water content, superplasticizer content, and curing time) on the investigated properties. This prediction makes it possible to design VS-based concretes for a desired strength, water impermeability, and porosity at any given age and replacement level. Some correlations between the investigated properties were derived from the analysed data. Furthermore, the sensitivity analysis showed that all studied parameters have a strong effect on the investigated properties. The modification of the microstructure of VS-based cement paste has been observed, as well.

Sign in / Sign up

Export Citation Format

Share Document