Figure - available from: International Journal of RF and Microwave Computer-Aided Engineering
This content is subject to copyright. Terms and conditions apply.
Source publication
This paper deals with the development of a virtual instrument for fault diagnosis in fractal antenna array using Lab‐VIEW software. Faults in antenna array are considered on the basis of the radiation pattern. In this study, theta and gain values of radiation patterns for each fault are used in Lab‐VIEW for curve fitting. An artificial neural netwo...
Citations
... In [27] MLP was for finding the number of targets present in a range-velocity cell of automotive radar and achieved classification performance comparable to the Generalized Likelihood Ratio Test. ANNs have also been used for array synthesis [28], determination of performance parameters of microstrip antenna [29], optimization and design of antenna array [30][31], calculation of antenna phases for radiation pattern synthesis [32], and development of virtual instruments for diagnosing faults in a fractal antenna array [33]. Array antennas suitable for body area networks have been described in [34][35] Sidelobes, especially the first sidelobe, contribute a major part in introducing interferences in the system. ...
With an ever-increasing need to remotely monitor human health and activities, there has been an increase in the number of activity and health tracking devices. In this scenario, Internet-of-things technology plays a very important role by uploading the data to the cloud and enabling analysis of the data. As these devices need to connect to a wireless base station for Internet access, the smart antenna plays an indispensable role. These systems use antenna arrays to enhance the gain and processors running adaptive algorithms for beamforming and beam-steering. The learning and estimating capabilities of artificial neural networks have proven to be unparalleled in modeling systems that would have otherwise required lengthy calculations. Thus, in this paper, we propose a neuro-computational model based on a multilayer perceptron model to model and predict how the gain and the beamwidth depend upon the number of antenna elements in a smart antenna system and the distance between them. We found that the neuro-computational model was able to achieve the objective to a very high degree of accuracy. The gains predicted for 50 elements with 0.5λ and 0.6λ spacing were 16.86 dB and 16.5 dB, respectively, and the beamwidths were 10 degrees and 6.7 degrees, respectively. The predicted values were found to be very close to that of the computed values.
... This inevitably pushes antenna design for 5G devices to fit the ever-increasing requirements for greater bandwidth, more frequency bands, and superior interference immunity [17,18]. Furthermore, fault detection in antenna arrays and inverse scatteringbased non-linear problems need sophisticated yet cost-effective solutions, where Machine Learning (ML) can provide an edge over other techniques [19,20]. ...
As an integral part of the electromagnetic system, antennas are becoming more advanced and versatile than ever before, thus making it necessary to adopt new techniques to enhance their performance. Machine Learning (ML), a branch of artificial intelligence, is a method of data analysis that automates analytical model building with minimal human intervention. The potential for ML to solve unpredictable and non-linear complex challenges is attracting researchers in the field of electromagnetics (EM), especially in antenna and antenna-based systems. Numerous antenna simulations, synthesis, and pattern recognition of radiations as well as non-linear inverse scattering-based object identifications are now leveraging ML techniques. Although the accuracy of ML algorithms depends on the availability of sufficient data and expert handling of the model and hyperparameters, it is gradually becoming the desired solution when researchers are aiming for a cost-effective solution without excessive time consumption. In this context, this paper aims to present an overview of machine learning, and its applications in Electromagnetics, including communication, radar, and sensing. It extensively discusses recent research progress in the development and use of intelligent algorithms for antenna design, synthesis and analysis, electromagnetic inverse scattering, synthetic aperture radar target recognition, and fault detection systems. It also provides limitations of this emerging field of study. The unique aspect of this work is that it surveys the state-of the art and recent advances in ML techniques as applied to EM.
Three different faults, namely, element fault, feed point fault, and feed network fault of antenna array are addressed. The ensemble ML detects the type of fault and location to diagnose a failure in an antenna array and also provides visualization. The machine learning (ML) algorithms, viz, Decision tree, Random forest, K-nearest neighbors, and Naïve Bayes, proven to be efficient in many other applications, are tried for fault detection of 4 × 4 planar antenna array. The 4 × 4 planar antenna array with fault scenarios is simulated using Ansys HFSS tool. The design center frequency of the array is 3.5 GHz. Ensemble of optimized ML algorithms enhances the performance in terms of accuracy and generalization. The proposed tuned stacking ensemble learning (TSEL) model outperforms the individual ML models, including the Support vector machine and tuned majority voting ensemble learning (TMVEL). The TSEL model provides 2% more accuracy than the TMVEL model. The accuracy attained for a single type of fault as well as three types of fault is 97% using 199 and 574 test samples, respectively. The visualisation of the detected fault(s) also is presented.
In this research paper an antenna array consisting of fractal based circular shape elements is projected with a corporate network to achieve better performance. A curve fit concept has been applied for optimization of desired parameters at various feed position values of designed antenna array configuration. FA and PSO algorithms have been employed to achieve the best feed position of proposed antenna array. A cost function has developed for feed position optimization with specified values of gain and VSWR. The cost function has evaluated and best feed position of antenna array has determined which reveals that optimized feed position with PSO is closely matched with simulated and experimental values as compared to that optimized with FA algorithm.
Computer networks, as one of the indispensable infrastructures in today’s world, play an extremely important role in industrial production and daily life. This paper revolves around the intelligent diagnosis of computer network data faults using machine learning methods. Firstly, the support vector machine network fault minimization principle is proposed based on the machine learning model, which leads to under-learning or over-learning when the samples are limited, or there is noise. Then, a loss function is introduced for the under-learning or over-learning problem to ensure that the support vector machine can accurately achieve fault diagnosis. Finally, the evaluation index of computational network fault diagnosis is constructed for the experimental purpose, and four algorithms are selected as the experimental control group to analyze the data. It is obtained that SVM and ANN models have high DR and low FAR. Their DR is 87.9% and 84.5%, respectively, while their FAR is only 5.4%. This further validates the superiority of SVM in computer network data fault detection. This study possesses low training time complexity and can overcome the problem of uneven distribution of the number of faulty and normal samples in network fault diagnosis to some extent.
The rise of smart antennas made it imperative to use adaptive beam forming, but single-element failure in array antenna disturbs the radiation pattern. Hence, to achieve adaptive beam forming,
detecting and locating faults in an antenna array is a must for correction in the radiation pattern. The presented work in this paper provides real-time monitoring and alert for fault occurrence in antenna arrays. Fault detection is performed by an optimized Convolutional Neural Network (CNN), and the Thingspeak web service is utilized to store fault detection information on the cloud to get the visualization of faults. Voice over Internet Protocol (VoIP) Application programming interface (API) provides an alert in real-time once the fault is detected. The filter kernel parameters, number of convolutional layers, and dense layers of the fully connected neural network are tuned to minimize the mean square error (MSE). 16 element (4×4) planar microstrip array antenna is simulated on Ansys HFSS, and by introducing discontinuity, i.e. one type of defect in the corporate feed network, a training
and testing set of 374 samples considering single element fault are used to train the CNN Model with a 0.3 validation split. Further performance of the same model by changing the last layer of a
fully connected layer is evaluated to check the effectiveness of model when two elements are faulty.
With an increase in demand of wireless services and wireless mobile devices, there are some challenges, such as effective utilization of spectrum and high energy consumption, not provided by the fourth generation. The fifth-generation wireless systems are able to provide high data rates and mobility that are required by wireless system designers. These systems are expected to be deployed beyond 2020. The main work of the fifth generation is to provide a wireless world that is free from hindrance and limitations of the fourth generation. So, as a need of effective 5G wireless communication system, an efficient channel estimation technique is required. In general, the received signal is distorted because of channel characteristics. So, to recover the transmitted data, a channel has to be effectively estimated, and, in the receiver, it is compensated. Effective estimation of channel has become one of the major research challenges in massive multiple-input and multiple-output (mMIMO)-based fifth-generation wireless communication systems. So, this paper deals with the study and analyzation of existing channel estimation techniques and its limitations. The parameters that are mainly focused in this paper are bit error rate and symbol error rate with respect to signal-to-noise ratio.
This book presents the latest techniques for the design of antenna, focusing specifically on the microstrip antenna. The authors discuss antenna structure, defected ground, MIMO, and fractal design. The book provides the design of microstrip antenna in terms of latest applications and uses in areas like IoT and device-to-device communication. The book also provides the current methods and techniques used for the enhancement of the performance parameters of the microstrip antenna. Chapters enhance the knowledge and skills of students and researchers in the latest in the communications world like IoT, D2D, satellite, wearable devices etc. The authors discuss applications such as microwave imaging, medical implants, hyperthermia treatments, and wireless wellness monitoring and how a decrease in size of antenna help facilitate application potential.
Provides the latest techniques used for the design of antenna in terms of its structure, defected ground, MIMO and fractal design;
Outlines steps to resolve issues with designing antenna, including the latest design and design parameters for microstrip antenna;
Presents the design of conformal and miniaturized antenna structures for various applications.
This paper presents the parameter estimation of the fractal antenna array with the virtual instrument model designed in laboratory virtual instrument engineering workbench software. In this work resonant frequency, gain and voltage standing wave ratio have been used as an output parameter with the change in three input parameters such as radius of a circular patch, height of substrate, and dielectric constant of the material. Measured output parameters have been compared with neural network outputs and error has been represented in a graphical way for each output parameter of the antenna array. Along with output parameter estimation, a designing parameter such as radius of the circular patch has also been estimated with virtual instrument model and absolute error for radius has been shown in the display window of the designed model. The proposed antenna array has been fabricated and simulated results have been validated with measured results.
