A Study on the RNN Algorithm for Metal Detection Based on MI Sensor

2021 ◽  
Vol 26 (2) ◽  
pp. 103-111
Author(s):  
Sungjae Ha ◽  
Dongwoo Lee ◽  
Hoijun Kim ◽  
Eung-Jo Kim ◽  
Soonchul Kwon ◽  
...  
Keyword(s):  
Metal Detection

scholarly journals Fiber optic sensor based on fluorescence quenching for heavy metal detection

2020 ◽  
Author(s):  
Yadira A. Fuentes-Rubio ◽  
Rene F. Dominguez-Cruz ◽  
Oscar Baldovino-Pantaleon ◽  
Carlos Ruiz-Zamarreno ◽  
Francisco J. Arregui
Keyword(s):  
Heavy Metal ◽  
Fluorescence Quenching ◽  
Fiber Optic ◽  
Fiber Optic Sensor ◽  
Heavy Metal Detection ◽  
Optic Sensor ◽  
Metal Detection

scholarly journals Anodic Stripping Voltammetry with the Hanging Mercury Drop Electrode for Trace Metal Detection in Soil Samples

Chemosensors ◽  
2021 ◽  
Vol 9 (5) ◽  
pp. 107
Author(s):  
Kequan Xu ◽  
Clara Pérez-Ràfols ◽  
Amine Marchoud ◽  
María Cuartero ◽  
Gastón A. Crespo
Keyword(s):  
Metal Ions ◽  
Limit Of Detection ◽  
Anodic Stripping Voltammetry ◽  
Stripping Voltammetry ◽  
Hanging Mercury Drop Electrode ◽  
Mercury Drop Electrode ◽  
Redox Active ◽  
Active Metal ◽  
Metal Detection ◽  
Trace Metal Detection

The widely spread use of the hanging mercury drop electrode (HMDE) for multi-ion analysis is primarily ascribed to the following reasons: (i) excellent reproducibility owing to the easy renewal of the electrode surface avoiding any hysteresis effect (i.e., a new identical drop is generated for each measurement to be accomplished); (ii) a wide cathodic potential window originating from the passive hydrogen evolution and solvent electrolysis; (iii) the ability to form amalgams with many redox-active metal ions; and (iv) the achievement of (sub)nanomolar limits of detection. On the other hand, the main controversy of the HMDE usage is the high toxicity level of mercury, which has motivated the scientific community to question whether the HMDE deserves to continue being used despite its unique capability for multi-metal detection. In this work, the simultaneous determination of Zn2+, Cd2+, Pb2+, and Cu2+ using the HMDE is investigated as a model system to evaluate the main features of the technique. The analytical benefits of the HMDE in terms of linear range of response, reproducibility, limit of detection, proximity to ideal redox behavior of metal ions and analysis time are herein demonstrated and compared to other electrodes proposed in the literature as less-toxic alternatives to the HMDE. The results have revealed that the HMDE is largely superior to other reported methods in several aspects and, moreover, it displays excellent accuracy when simultaneously analyzing Zn2+, Cd2+, Pb2+, and Cu2+ in such a complex matrix as digested soils. Yet, more efforts are required towards the definitive replacement of the HMDE in the electroanalysis field, despite the elegant approaches already reported in the literature.

scholarly journals Neural Network for Metal Detection Based on Magnetic Impedance Sensor

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4456
Author(s):  
Sungjae Ha ◽  
Dongwoo Lee ◽  
Hoijun Kim ◽  
Soonchul Kwon ◽  
EungJo Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Magnetic Field ◽  
Deep Learning ◽  
Short Term Memory ◽  
Magnetic Impedance ◽  
Detection Technology ◽  
Metal Detection ◽  
Long Short Term Memory ◽  
Impedance Sensor ◽  
The Magnetic Field

The efficiency of the metal detection method using deep learning with data obtained from multiple magnetic impedance (MI) sensors was investigated. The MI sensor is a passive sensor that detects metal objects and magnetic field changes. However, when detecting a metal object, the amount of change in the magnetic field caused by the metal is small and unstable with noise. Consequently, there is a limit to the detectable distance. To effectively detect and analyze this distance, a method using deep learning was applied. The detection performances of a convolutional neural network (CNN) and a recurrent neural network (RNN) were compared from the data extracted from a self-impedance sensor. The RNN model showed better performance than the CNN model. However, in the shallow stage, the CNN model was superior compared to the RNN model. The performance of a deep-learning-based (DLB) metal detection network using multiple MI sensors was compared and analyzed. The network was detected using long short-term memory and CNN. The performance was compared according to the number of layers and the size of the metal sheet. The results are expected to contribute to sensor-based DLB detection technology.

scholarly journals An Initial Value Estimation Method for the Kalman and Extended Kalman Filters in Underground Metal Detection

2019 ◽  
Vol 9 (19) ◽  
pp. 4113 ◽  
Author(s):  
Yadong Wan ◽  
Zhen Wang ◽  
Peng Wang ◽  
Zhiyang Liu ◽  
Na Li ◽  
...  
Keyword(s):  
Kalman Filter ◽  
Estimation Method ◽  
Detection Methods ◽  
Polarizability Tensor ◽  
Filter Method ◽  
Excellent Performance ◽  
Initial Value ◽  
Initial State ◽  
Metal Detection ◽  
Value Estimation

As an underground metal detection technology, the electromagnetic induction (EMI) method is widely used in many cases. Therefore, the EMI detection algorithms with excellent performance are worth studying. One of the EMI detection methods in the underground metal detection is the filter method, which first obtains the secondary magnetic field data and then uses the Kalman filter (KF) and the extended Kalman filter (EKF) to estimate the parameters of metal targets. However, the traditional KF methods used in the underground metal detection have an unsatisfactory performance of the convergence as the algorithms are given a random or a fixed initial value. Here, an initial state estimation algorithm for the underground metal detection is proposed. The initial state of the target’s horizontal position is estimated by the first order central moments of the secondary field strength map. In addition, the initial state of the target’s depth is estimated by the full width at half maximum (FWHM) method. In addition, the initial state of the magnetic polarizability tensor is estimated by the least squares method. Then, these initial states are used as the initial values for KF and EKF. Finally, the position, posture and polarizability of the target are recursively calculated. A simulation platform for the underground metal detection is built in this paper. The simulation results show that the initial value estimation method proposed for the filtering algorithm has an excellent performance in the underground metal detection.

Microfabricated electrochemical analysis system for heavy metal detection

1996 ◽  
Vol 34 (1-3) ◽  
pp. 450-455 ◽  
Author(s):  
Richard J. Reay ◽  
Anthony F. Flannery ◽  
Christopher W. Storment ◽  
Samuel P. Kounaves ◽  
Gregory T.A. Kovacs
Keyword(s):  
Heavy Metal ◽  
Electrochemical Analysis ◽  
Heavy Metal Detection ◽  
Metal Detection ◽  
Analysis System

METAL DETECTION TESTING PROVIDES PROTECTION

Sensor Review ◽  
1991 ◽  
Vol 11 (1) ◽  
pp. 10-14
Author(s):  
Trevor Butler
Keyword(s):  
Metal Detection

scholarly journals Desorption of metals from Cetraria islandica (L.) Ach. Lichen using solutions simulating acid rain

2014 ◽  
Vol 66 (1) ◽  
pp. 273-284 ◽  
Author(s):  
Ana Cuculovic ◽  
Mirjana Pavlovic ◽  
Jelena Savovic ◽  
D.S. Veselinovic
Keyword(s):  
Detection Limit ◽  
Acid Rain ◽  
Metal Content ◽  
Strong Link ◽  
Ph Values ◽  
Metal Detection ◽  
Logarithmic Dependence ◽  
Solution Volume

Desorption of metals K, Al, Ca, Mg, Fe, Ba, Zn, Mn, Cu and Sr from Cetraria islandica (L.) with solutions whose composition was similar to that of acid rain, was investigated. Desorption of metals from the lichen was performed by five successive desorption processes. Solution mixtures containing H2SO4, HNO3 and H2SO4-HNO3 were used for desorption. Each solution had three different pH values: 4.61, 5.15 and 5.75, so that the desorptions were performed with nine different solutions successively five times, always using the same solution volume. The investigated metals can be divided into two groups. One group was comprised of K, Ca and Mg, which were desorbed in each of the five desorption processes at all pH values used. The second group included Al, Fe, Zn, Ba, Mn and Sr; these were not desorbed in each individual desorption and not at all pH values, whereas Cu was not desorbed at all under any circumstances. Using the logarithmic dependence of the metal content as a function of the desorption number, it was found that potassium builds two types of links and is connected with weaker links in lichen. Potassium is completely desorbed, 80% in the first desorption, and then gradually in the following desorptions. Other metals are linked with one weaker link (desorption 1-38%) and with one very strong link (desorption below the metal detection limit).

Sign in / Sign up

Export Citation Format

Share Document