Efficient Neural Network Approach for 2d Doa Estimation Based on Antenna Array Measurements

Agatonovic, Marija; Stankovic, Zoran; Milovanović, Ivan; Dončov, Nebojša; Sit, Leen; Zwick, Thomas; Milovanovic, and Bratislav

doi:10.2528/pier13012114

Cited by 42 publications

(35 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to bypass the difficulties of inverting a numerical model to estimate these parameters starting from EC data [18], a model-free estimation technique based on the use of an ANN is considered. This kind of approach has been proven to be efficient in various modeling and estimation problems in the electromagnetic domain [19,20]. In this study, a feed-forward neural network (FFNN) is implemented to estimate the conductivity variations [21].…”

Section: Evaluation Of Conductivity Variation Of Aluminum and Solder mentioning

confidence: 99%

“…In the same manner, Figure 5 illustrates the influence of the solder layer conductivity, σ solder (with α solder = [3, 5, 7, 9, 11]) on the variations of ΔZ n (f ), the aluminum conductivity is fixed at initial state (α al = 1). Finally, Figure 6 shows the influence of both conductivity variations on ΔZ n (f ) for (α al , α solder ) taking values such as (3, 3); (7, 5); (11, 7); (15, 9); and (19,11). These graphs point out that there exists a relevant frequency band which enhances the sensitivity of the EC sensor to the conductivity changes.…”

Section: Ec Data For the Estimation Of Ageingmentioning

confidence: 99%

“…Figure 4 illustrates the influence of the aluminum conductivity (σ al ) on the variations of ΔZ n (f ), the aluminum layer is successively altered by six attenuation values α al = [3,5,7,9,13,19], while the solder conductivity is fixed at initial state (α al = 1). In the same manner, Figure 5 illustrates the influence of the solder layer conductivity, σ solder (with α solder = [3, 5, 7, 9, 11]) on the variations of ΔZ n (f ), the aluminum conductivity is fixed at initial state (α al = 1).…”

Section: Ec Data For the Estimation Of Ageingmentioning

confidence: 99%

See 2 more Smart Citations

Estimation of the Ageing of Metallic Layers in Power Semiconductor Modules Using the Eddy Current Method and Artificial Neural Networks

Nguyen¹,

Joubert²,

Lefebvre³

2014

PIER M

View full text Add to dashboard Cite

Abstract-In high power operations, the ageing of power semiconductor modules has been often observed by several failures due to high temperature cycling. The main failures may be metallization reconstruction, solder delaminations, bond wire lift-offs or bond wire heel crackings, conchoidal breaking of ceramics. The paper focuses on the non-contact monitoring of the ageing of the aluminum metallization top layer and of the solder bottom layer of a power die, using the eddy current method. The ageing is assumed to induce a decrease of these layers conductivity. The evaluation of both layers conductivity changes are estimated using artificial neural networks starting from eddy current data provided by finite element computations carried out in the case of several aged die configurations. The error of estimation is less than a few percent in the considered cases and it demonstrates the relevance of the eddy current method to monitor the ageing state of power modules. The proposed approach provides relevant results which will be validated on experimental data in future works.

show abstract

Section: Evaluation Of Conductivity Variation Of Aluminum and Solder mentioning

confidence: 99%

Section: Ec Data For the Estimation Of Ageingmentioning

confidence: 99%

Section: Ec Data For the Estimation Of Ageingmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of the Ageing of Metallic Layers in Power Semiconductor Modules Using the Eddy Current Method and Artificial Neural Networks

Nguyen¹,

Joubert²,

Lefebvre³

2014

PIER M

View full text Add to dashboard Cite

show abstract

“…Neural Network approaches have also been used in beamforming [33][34][35][36][37][38][39]. Zaman et al utilized a GA hybridized with a pattern search for DOA analysis [40].…”

Section: Beamformingmentioning

confidence: 99%

Radar Angle of Arrival System Design Optimization Using a Genetic Algorithm

2017

View full text Add to dashboard Cite

An approach for using a Genetic Algorithm (GA) to select radar design parameters related to beamforming and angle of arrival estimation is presented in this article. This was accomplished by first developing a simulator that could evaluate the localization performance with a given set of design parameters. The simulator output was utilized as part of the GA objective function that searched the solution space for an optimal set of design parameters. Using this approach, the authors were able to more than halve the mean squared error in degrees of the localization algorithm versus a radar design using human-selected design parameters. The results of this study indicate that this kind of approach can be used to aid in the development of an actual radar design.

show abstract

“…Radiometer profiling during dynamic weather conditions is discussed and shows that the accuracy of radiometer retrievals is similar to radiosonde soundings when used for numerical weather prediction [19]. The method of artificial neural network is used in various fields [20][21][22][23][24]. Artificial neural network is increasingly used for its more accurate estimation of the atmospheric parameters in the case of strong nonlinearities [25][26][27][28][29][30][31][32].…”

Section: Introductionmentioning

confidence: 99%

A Dual-Frequency Method of Eliminating Liquid Water Radiation to Remotely Sense Cloudy Atmosphere by Ground-Based Microwave Radiometer

Li¹,

Guo²,

Lin³

et al. 2013

PIER

View full text Add to dashboard Cite

Abstract-Ground-based microwave radiometer is the main device to remotely sense atmosphere passively which can detect the water vapor density, temperature, integral water vapor, etc. Because of the influence of cloud liquid water on the brightness temperature measured by microwave radiometer, the cloud needs to be modeled to retrieve the parameters of cloudy atmosphere. However, the difference between the cloud model and actual cloud may bring on some error in retrieval. Based on the relation between absorption coefficient of liquid water and frequency, a dual-frequency method of eliminating liquid water radiation which is not based on modeling cloud is put forward to retrieve the parameters of cloudy atmosphere. Historical radiosonde data are employed in the calculation of retrieval coefficients to profile the water vapor of cloudy atmosphere. The simulation and experiment results show that the dual-frequency method can eliminate the radiation of liquid water effectively and has a higher precision than conventional method. The integral water vapor in cloudy atmosphere is also retrieved by the dual-frequency method, and the precision is comparable with the method of modeling cloud.

show abstract

Efficient Neural Network Approach for 2d Doa Estimation Based on Antenna Array Measurements

Cited by 42 publications

References 39 publications

Estimation of the Ageing of Metallic Layers in Power Semiconductor Modules Using the Eddy Current Method and Artificial Neural Networks

Estimation of the Ageing of Metallic Layers in Power Semiconductor Modules Using the Eddy Current Method and Artificial Neural Networks

Radar Angle of Arrival System Design Optimization Using a Genetic Algorithm

A Dual-Frequency Method of Eliminating Liquid Water Radiation to Remotely Sense Cloudy Atmosphere by Ground-Based Microwave Radiometer

Contact Info

Product

Resources

About