Subsurface object recognition in a soil using UWB irradiation by Bow-Tie antenna and artificial neural network

Visnyk of V.N. Karazin Kharkiv National University, series “Radio Physics and Electronics” ◽

10.26565/2311-0872-2018-29-04 ◽

2018 ◽

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Fdtd Method ◽

Antenna System ◽

Modern World ◽

Field Energy ◽

Important Place ◽

Transient Electromagnetic ◽

Artificial Neural ◽

Bow Tie

Background: Subsurface radiolocation problems have an important place in the modern world, such as in geology, building, and humanitarian demining. A complex problem that impedes the widespread use of subsurface radars is the processing and interpretation of the parameters of the reflected electromagnetic field. Objectives: The main purpose of this work is to solve the problem of recognition of objects buried in a soil by bow-tie antenna and artificial neural network (ANN). Materials and methods: The problem of recognition an ideally conducting cylindrical object that is situated below the earth's surface is solved by an ANN. The air-ground interface is irradiated by a bow-tie antenna, which is excited by means of a nanosecond impulse current. The irradiation by nearly point-like source in contrast to plane transient electromagnetic wave incidence considered in our previous works is characterized by the significant decrease of field energy reached a hidden object, reflected, and received by antenna. Moreover, the descent of the field energy becomes more sensible proportionally to the distance from the object to the radar. The complications can call into question the possibility the application of the approach on the base of ANN. The electromagnetic problem is solved numerically by using the FDTD method. The time dependences of amplitudes of differently polarized electric field components, which were obtained in four points above the earth's surface were used as the initial data. The points form the shape of a square. The ANN was trained by the obtained data to determine the position of the object beneath the ground. Results: ANN recognition quality was tested by test data with the addition of Gaussian noise and data obtained when the receiving system is moved relative to the object by shift of the value that was absent in training set. Conclusion: Such type of antenna system in combination with the ANN shows good results for determining the distance to the object even in the presence of noise.

Download Full-text

Resistivity-depth imaging of airborne transient electromagnetic method based on an artificial neural network

10.5194/egusphere-egu2020-1729 ◽

2020 ◽

Author(s):

Jifeng Zhang ◽

Bing Feng ◽

Dong Li

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Bp Neural Network ◽

Apparent Resistivity ◽

Electromagnetic Method ◽

Electromagnetic Response ◽

Model Parameters ◽

Transient Electromagnetic Method ◽

Transient Electromagnetic ◽

Artificial Neural

<p>An artificial neural network, which is an important part of artificial intelligence, has been widely used to many fields such as information processing, automation and economy, and geophysical data processing as one of the efficient tools. However, the application in geophysical electromagnetic method is still relatively few. In this paper, BP neural network was combined with airborne transient electromagnetic method for imaging subsurface geological structures.</p><p>We developed an artificial neural network code to map the distribution of geologic conductivity in the subsurface for the airborne transient electromagnetic method. It avoids complex derivation of electromagnetic field formula and only requires input and transfer functions to obtain the quasi-resistivity image section. First, training sample set, which is airborne transient electromagnetic response of homogeneous half-space models with the different resistivity, is formed and network model parameters include the flight altitude and the time constant, which were taken as input variables of the network, and pseudo-resistivity are taken as output variables. Then, a double hidden layer BP neural network is established in accordance with the mapping relationship between quasi-resistivity and airborne transient electromagnetic response. By analyzing mean square error curve, the training&#160;termination criterion of BP neural network is presented. Next, the trained BP neural network is used to interpret the airborne transient electromagnetic responses of various typical layered geo-electric models, and it is compared with those of the all-time apparent resistivity algorithm. After a lot of tests, reasonable BP neural network parameters were selected, and the mapping from airborne TEM quasi-resistivity was realized. The results show that the resistivity imaging from BP neural network approach is much closer to the true resistivity of model, and the response to anomalous bodies is better than that of all-time apparent resistivity numerical method. Finally, this imaging technique was use to process the field data acquired by the airborne transient method from Huayangchuan area. Quasi-resistivity depth section calculated by BP neural network and all-time apparent resistivity is in good agreement with the actual geological situation, which further verifies the effectiveness and practicability of this algorithm.</p>

Download Full-text

Resistivity-depth Imaging with the Airborne Transient Electromagnetic Method Based on an Artificial Neural Network

Journal of Environmental and Engineering Geophysics ◽

10.32389/jeeg19-087 ◽

2020 ◽

Vol 25 (3) ◽

pp. 355-368

Author(s):

Bing Feng ◽

Ji-feng Zhang ◽

Dong Li ◽

Yang Bai

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Bp Neural Network ◽

Apparent Resistivity ◽

Electromagnetic Method ◽

Electromagnetic Response ◽

Model Parameters ◽

Transient Electromagnetic Method ◽

Transient Electromagnetic ◽

Artificial Neural

We developed an artificial neural network to map the distribution of geologic conductivity in the earth subsurface using the airborne transient electromagnetic method. The artificial neural network avoids the need for complex derivations of electromagnetic field formulas and requires only input and transfer functions to obtain a quasi-resistivity image. First, training sample set from the airborne transient electromagnetic response of homogeneous half-space models with different resistivities was formed, and network model parameters, including the flight altitude, time constant, and response amplitude, were determined. Then, a double-hidden-layer back-propagation (BP) neural network was established based on the mapping relationship between quasi-resistivity and airborne transient electromagnetic response. By analyzing the mean square error curve, the training termination criterion of the BP neural network was determined. Next, the trained BP neural network was used to interpret the airborne transient electromagnetic responses of various typical layered geo-electric models, and the results were compared with that from the all-time apparent resistivity algorithm. The comparison indicated that the resistivity imaging from the BP neural network approach was much closer to the true resistivity of the model, and the response to anomalous bodies was better than that from an all-time apparent resistivity. Finally, this imaging technique was used to process field data acquired by employing the airborne transient method from the HuaYin survey area. Quasi-resistivity depth sections calculated with the BP neural network and the actual geological situation were in good.

Download Full-text

Object classification using artificial neural network processing of data obtained by impulse GPR with 1 Tx + 4Rx antenna system

2020 IEEE Ukrainian Microwave Week (UkrMW) ◽

10.1109/ukrmw49653.2020.9252613 ◽

2020 ◽

Author(s):

Oleksandr Dumin ◽

Vadym Plakhtii ◽

Gennadiy Pochanin ◽

Dmytro Shyrokorad

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Object Classification ◽

Antenna System ◽

Artificial Neural ◽

Network Processing

Download Full-text

Modeling of Building Energy Consumption by Integrating Regression Analysis and Artificial Neural Network with Data Classification

Buildings ◽

10.3390/buildings10110198 ◽

2020 ◽

Vol 10 (11) ◽

pp. 198

Author(s):

Iffat Ridwana ◽

Nabil Nassif ◽

Wonchang Choi

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Energy Demand ◽

Regression Models ◽

Mean Squared Error ◽

Data Classification ◽

Building Energy ◽

Modern World ◽

Artificial Neural ◽

Conventional Regression

With the constant expansion of the building sector as a major energy consumer in the modern world, the significance of energy-efficient building systems cannot be more emphasized. Most of the buildings are now equipped with an electric dashboard to record consumption data which presents a significant scope of research by utilizing those data in energy modeling. This paper investigates conventional regression modeling in building energy estimation and proposes three models with data classifications to improve their performance. The proposed models are regression models and an artificial neural network model with data classification for predicting hourly or sub-hourly energy usage in four different buildings. Energy data is collected from a building energy simulation program and existing buildings to develop the models for detailed analysis. Data classification is recommended according to the system operating schedules of the buildings and models are tested for their performance in capturing the data trends resulting from those schedules. Proposed regression models and an ANN model with the recommended classification show very accurate results in estimating energy demand compared to conventional regression models. Correlation coefficient and root mean squared error values improve noticeably for the proposed models and they can potentially be utilized for energy conservation purposes and energy savings in the buildings.

Download Full-text

Artificial Neural Network

10.4018/978-1-7998-8561-0.ch006 ◽

2022 ◽

pp. 95-115

Author(s):

Anupama Kumari ◽

Mukund Madhaw ◽

C. B. Majumder ◽

Amit Arora

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Gas Hydrate ◽

Hydrate Formation ◽

Oil And Gas Industry ◽

Modern World ◽

Gas Industry ◽

Research Fields ◽

Gas Hydrate Formation ◽

Artificial Neural

The analysis and collection of data is an integral part of all research fields of the modern world. There is a need to perform forward mathematical modeling to improve the operations and calculations with modern technologies. Artificial neural network signifies the structure of the human brain. They can provide reasonable solutions quickly for the problems that classical programming cannot solve. An in-depth systematic study is presented in this chapter related to artificial neural network applications (ANN) for predicting the equilibrium conditions for gas hydrate formation, which can assist in designing future dissociation technology for gas hydrate so that this white gold can make world energy free for the future generation. This chapter can also help to develop a novel inhibitor for gas hydrate formation and save millions of dollars for the oil and gas industry.

Download Full-text