GPR Signal processing in frequency domain using Artificial Neural Network for water content prediction in unsaturated subgrade

2010 ◽  
Author(s):  
Fabrizio D Amico ◽  
Claudia Guattari ◽  
Andrea Benedetto
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Signal Processing ◽  
Water Content ◽  
Frequency Domain ◽  
Artificial Neural

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 Feasibility of Acoustic Print Head Monitoring for Binder Jetting Processes with Artificial Neural Networks

2021 ◽  
Vol 11 (22) ◽  
pp. 10672
Author(s):  
Philipp Lechner ◽  
Philipp Heinle ◽  
Christoph Hartmann ◽  
Constantin Bauer ◽  
Benedikt Kirchebner ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Frequency Domain ◽  
Typical Problem ◽  
Print Head ◽  
Acoustic Data ◽  
Artificial Neural ◽  
Binder Jetting

The clogging of piezoelectric nozzles is a typical problem in various additive binder jetting processes, such as the manufacturing of casting molds. This work aims at print head monitoring in these binder jetting processes. The structure-born noise of piezoelectric print modules is analyzed with an Artificial Neural Network to classify whether the nozzles are functional or clogged. The acoustic data are studied in the frequency domain and utilized as input for an Artificial Neural Network. We found that it is possible to successfully classify individual nozzles well enough to implement a print head monitoring, which automatically determines whether the print head needs maintenance.

Damage detection of structures using signal processing and artificial neural networks

2019 ◽  
Vol 23 (5) ◽  
pp. 884-897 ◽  
Author(s):  
Seyed Bahram Beheshti Aval ◽  
Vahid Ahmadian ◽  
Mohammad Maldar ◽  
Ehsan Darvishan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Signal Processing ◽  
Damage Detection ◽  
Empirical Mode Decomposition ◽  
Degree Of Freedom ◽  
Benchmark Problem ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Artificial Neural

This article presents a signal-based seismic structural health monitoring technique for damage detection and evaluating damage severity of a multi-story frame subjected to an earthquake event. As a case study, this article is focused on IASC–ASCE benchmark problem to provide the possibility for side-by-side comparison. First, three signal processing techniques including empirical mode decomposition, Hilbert vibration decomposition, and local mean decomposition, categorized as instantaneous time–frequency methods, have been compared to find a method with the best resolution in extracting frequency responses. Time-varying single degree of freedom and multiple degree of freedom models are used since real vibration signals are nonstationary and nonlinear in nature. Based on the results, empirical mode decomposition has proved to outperform than the others. Second, empirical mode decomposition is used to extract the acceleration response of the sensors. Next, a two-stage artificial neural network is used to classify damage patterns. The first artificial neural network identifies location and severity of damage and the second one calculates the severity of damage for the entire structure. IASC–ASCE benchmark problem is used to validate the proposed procedure. By taking advantage of signal processing and artificial intelligence techniques, damage detection of structures was successfully carried out in three levels including damage occurrence, damage severity, and the location of damage.

scholarly journals Comparison of Pattern Recognition, Artificial Neural Network and Pedotransfer Functions for Estimation of Soil Water Parameters

2010 ◽  
Vol 2 (3) ◽  
pp. 114-120 ◽  
Author(s):  
Amir LAKZIAN ◽  
Mohammad BANNAYAN AVAL ◽  
Nasrin GORBANZADEH
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Artificial Neural Network ◽  
Water Content ◽  
Soil Water ◽  
Solid Phase ◽  
Soil Water Potential ◽  
Pedotransfer Functions ◽  
Mean Square ◽  
Artificial Neural

This paper presents the comparison of three different approaches to estimate soil water content at defined values of soil water potential based on selected parameters of soil solid phase. Forty different sampling locations in northeast of Iran were selected and undisturbed samples were taken to measure the water content at field capacity (FC), -33 kPa, and permanent wilting point (PWP), -1500 kPa. At each location solid particle of each sample including the percentage of sand, silt and clay were measured. Organic carbon percentage and soil texture were also determined for each soil sample at each location. Three different techniques including pattern recognition approach (k nearest neighbour, k-NN), Artificial Neural Network (ANN) and pedotransfer functions (PTF) were used to predict the soil water at each sampling location. Mean square deviation (MSD) and its components, index of agreement (d), root mean square difference (RMSD) and normalized RMSD (RMSDr) were used to evaluate the performance of all the three approaches. Our results showed that k-NN and PTF performed better than ANN in prediction of water content at both FC and PWP matric potential. Various statistics criteria for simulation performance also indicated that between kNN and PTF, the former, predicted water content at PWP more accurate than PTF, however both approach showed a similar accuracy to predict water content at FC.

scholarly journals Artificial neural network for Gaussian and non-Gaussian random fatigue loading analysis

2019 ◽  
Vol 233 (23-24) ◽  
pp. 7525-7544
Author(s):  
JF Durodola
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Frequency Domain ◽  
Fatigue Loading ◽  
Neural Network Approach ◽  
Frequency Domain Methods ◽  
Artificial Neural ◽  
Non Gaussian ◽  
Random Fatigue ◽  
Loading Analysis

There has been a lot of work done on the analysis of Gaussian loading analysis perhaps because its occurrence is more common than non-Gaussian loading problems. It is nevertheless known that non-Gaussian load occurs in many instances especially in various forms of transport, land, sea and space. Part of the challenge with non-Gaussian loading analysis is the increased number of variables that are needed to model the loading adequately. Artificial neural network approach provides a versatile means to develop models that may require many input variables in order to achieve applicable predictive generalisation capabilities. Artificial neural network has been shown to perform much better than existing frequency domain methods for random fatigue loading under stationary Gaussian load forms especially when mean stress effects are included. This paper presents an artificial neural network model with greater predictive capability than existing frequency domain methods for both Gaussian and non-Gaussian loading analysis. Both platykurtic and leptokurtic non-Gaussian loading cases were considered to demonstrate the scope of application. The model was also validated with available SAE experimental data, even though the skewness and kurtosis of the signal in this case were mild.

Sign in / Sign up

Export Citation Format

Share Document