Indian Journal of Pure and Applied Physics

Open Access Open Access  Restricted Access Subscription Access

Investigation on the Classification Accuracy of Harmonic Signal Detection by Artificial Neural Network


Affiliations
1 Department of Applied Sciences, Gauhati University, Guwahati, Assam 781 014, India
 

Harmonic signals are produced by many natural sources as well as man-made sources. The detection of the harmonic signal can reveal a lot about the physical system. Various Fourier harmonic analysis based numerical methods are commonly used to detect such signals. However, recently there has been considerable interest in other non-Fourier-based methods as well, to determine the harmonics. In the present work we have studied the application of artificial neural network based machine learning in frequency identification of sinusoidal signals. We considered training sets comprising harmonic signals with randomised phase or randomised amplitude or combination of the both. Based on such training sets the trained network is then applied to detect the frequency of unknown harmonics. Here we performed aninvestigation on the relative advantages of the network trained using sets of harmonic signals with different features.

Keywords

Artificial neural network (ANN); Harmonic signals; Detection accuracy 1 Introduction Many signals associated with real life problems exhibit periodic components that repeat at fixed frequencyor at an integral multiple of the main frequency, called the fundamental, throughout the signal duration. On the other hand, a function of time, say π‘“αˆΊπ‘‘αˆ», corresponding to any arbitrary signal data, with a given periodic variation, can in general be expressed as a weighted sum of periodic sinusoidal components written as π‘“αˆΊπ‘‘αˆ»ΰ΅Œπ‘Žΰ¬΄ΰ΅…βˆ‘ 𝐴௜sinαˆΊπœ”ΰ―œπ‘‘ΰ΅…πœ–ΰ―œ ሻ ΰ―‡ ΰ―œΰ­€ΰ¬΅ … (1) This is also known as the Fourier series expansion of the signal 1 . Here π‘Žΰ¬΄is the mean co-efficient, 𝑁is the total number of constituents, 𝐴௜ , ௜ and πœ–ΰ―œ are the amplitude, angular frequency and phase, respectively, of the i-th constituent. Each of these Nsinusoidals can b
User
Notifications
Font Size

  • Chatfield C, The analysis of time series: an introduction, CRC press, 2016.

  • Bruce A, Papa M A & Schutz B F, Phys Rev D, 66 (2002) 102003.

  • Covas P B & Sintes A M, Phys Rev D, 99 (2019) 124019.

  • Piper J E, Reese S S & Reese W G, Oceans, (2012) 1.

  • Marino C S & Chau P M, IEEE Trans Instr Meas, 61 (2012) 2413.

  • Filatrella, Giovanni & Pierro V, Phys Rev E, 82 (2010) 046712.

  • MaoilΓ©idigh, DΓ‘ibhid Γ“ & Hudspeth A J, Phys D: Nonlinear Phenomena, 378 (2018) 33.

  • Haykin S S, et al., Simon Haykin, New York, Prentice Hall, 2009.

  • Gu W, Valavanis K P, Rutherford M J & Rizzo A, J Intel Robotic Syst, 100 (2020) 1469.

  • Storrie-Lombardi M C, Lahav O, Sodre L & StorrieLombardi L J, Month Not Royal Astronom Soc, 259 (1992) 8P.

  • Bora A, Gupta R, Singh H P, Murthy J, Mohan R & Duorah K, Month Not Royal Astronom Soc, 384 (2008) 827.

  • Bora A, Gupta R, Singh H P & Duorah K, New Astronomy, 14 (2009) 649.

  • Gulati R K, Gupta R, Gothoskar P & Khobragade S, The Astrophys J, 426 (1994) 340.

  • Gulati R K, Gupta R & Rao N K, Astron Astrophys, 322 (1997) 933.

  • Malinov S, Sha W & McKeown J J, Computat Materials Sci, 21 (2001) 375.

  • Lisboa P J & Taktak A F G, Neural Networks, 19 (2006) 408.

  • Meireles M R G, Almeida P E M & Simoes M G, IEEE Trans Indus Electron, 50 (2003) 585.


Abstract Views: 81

PDF Views: 71




  • Investigation on the Classification Accuracy of Harmonic Signal Detection by Artificial Neural Network

Abstract Views: 81  |  PDF Views: 71

Authors

Archana Bora
Department of Applied Sciences, Gauhati University, Guwahati, Assam 781 014, India

Abstract


Harmonic signals are produced by many natural sources as well as man-made sources. The detection of the harmonic signal can reveal a lot about the physical system. Various Fourier harmonic analysis based numerical methods are commonly used to detect such signals. However, recently there has been considerable interest in other non-Fourier-based methods as well, to determine the harmonics. In the present work we have studied the application of artificial neural network based machine learning in frequency identification of sinusoidal signals. We considered training sets comprising harmonic signals with randomised phase or randomised amplitude or combination of the both. Based on such training sets the trained network is then applied to detect the frequency of unknown harmonics. Here we performed aninvestigation on the relative advantages of the network trained using sets of harmonic signals with different features.

Keywords


Artificial neural network (ANN); Harmonic signals; Detection accuracy 1 Introduction Many signals associated with real life problems exhibit periodic components that repeat at fixed frequencyor at an integral multiple of the main frequency, called the fundamental, throughout the signal duration. On the other hand, a function of time, say π‘“αˆΊπ‘‘αˆ», corresponding to any arbitrary signal data, with a given periodic variation, can in general be expressed as a weighted sum of periodic sinusoidal components written as π‘“αˆΊπ‘‘αˆ»ΰ΅Œπ‘Žΰ¬΄ΰ΅…βˆ‘ 𝐴௜sinαˆΊπœ”ΰ―œπ‘‘ΰ΅…πœ–ΰ―œ ሻ ΰ―‡ ΰ―œΰ­€ΰ¬΅ … (1) This is also known as the Fourier series expansion of the signal 1 . Here π‘Žΰ¬΄is the mean co-efficient, 𝑁is the total number of constituents, 𝐴௜ , ௜ and πœ–ΰ―œ are the amplitude, angular frequency and phase, respectively, of the i-th constituent. Each of these Nsinusoidals can b

References