Artificial Neural Networks for loudspeaker modelling and fault detection

This thesis is the result of a collaborative project between Cardiff University and Harman/Becker Automotive Systems. It investigates the application of Artificial Neural Networks to loudspeaker fault detection and modelling of the loudspeaker transfer function. The aim was to utilise the ability of artificial neural networks to model high order nonlinear systems to generate a model of the loudspeaker transfer function which could be used in a linearisation scheme to reduce distortion in loudspeaker output. This thesis investigates a practical approach to transfer function modelling through the use of musical excitation signals. This would allow data to be collected during normal operation of the loudspeaker and, as the transfer function changes over time due to time dependent nonlinearities, would facilitate regular updating of the neural network model to incorporate these nonlinearities. It was determined that although very accurate models could be produced over long training periods, a significant compromise in ANN training set size and number of training epochs were required to reduce the ANN training duration to the required time period, which ultimately resulted in a decline in performance. The aim in the case of fault detection was to improve on current end of production line testing for loudspeaker distortion. Neural networks were trained with harmonic distortion data in order to emulate the end of line test result. Excellent classification accuracy was achieved when neural network classification results were compared to the end of line test results. An investigation was also conducted to determine if neural networks could be trained to recognise specific loudspeaker faults. In a development of the end of line test, a system of neural networks were trained to produce an output vector that described which of five frequency regions the loudspeaker distortion levels were above the limits, thus giving an indication of the possible fault.

[1]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[2]  Chester W. Rice,et al.  Notes on the Development of a New Type of Hornless Loud Speaker , 1925, Transactions of the American Institute of Electrical Engineers.

[3]  Richard H. Small.  Vented-Box Loudspeaker Systems-Part 4: Appendices , 1973 .

[4]  G. J. Adams.  Adaptive Control of Loudspeaker Frequency Response at Low Frequencies , 1983 .

[5]  Richard H. Small.  Closed-Box Loudspeaker Systems-Part 1: Analysis , 1972 .

[6]  Po-Rong Chang,et al.  Inverse filtering of a loudspeaker and room acoustics using time‐delay neural networks , 1994 .

[7]  Duc Truong Pham,et al.  Neural Networks for Identification, Prediction and Control , 1995 .

[8]  Malcolm J. Hawksford,et al.  Efficient filter design for loudspeaker equalization , 1991 .

[9]  Stéphane Lecoeuche,et al.  Unsupervised and auto-adaptive neural architecture for on-line monitoring. Application to a hydraulic process , 2003 .

[10]  W. Martin Snelgrove,et al.  Adaptive linearization of a loudspeaker , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[11]  Richard H. Small.  Vented-Box Loudspeaker Systems-Part 2: Large-Signal Analysis , 1973 .

[12]  Benjamin David Hutt.  Evolving artificial neural network controllers for robots using species-based methods , 2002 .

[13]  Alex Waibel,et al.  Learning the architecture of neural networks for speech recognition , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[14]  Dianhui Wang,et al.  Enhancing the estimation of plant Jacobian for adaptive neural inverse control , 2000, Neurocomputing.

[15]  A. Sideris,et al.  A multilayered neural network controller , 1988, IEEE Control Systems Magazine.

[16]  Wolfgang Klippel.  The Mirror Filter-A New Basis for Reducing Nonlinear Distortion and Equalizing Response in Woofer Systems , 1992 .

[17]  Duc Truong Pham,et al.  Neural Classifiers for Automated Visual Inspection , 1994 .

[18]  J Watton,et al.  Simulation of fluid power circuits using artificial network models: Part 1: Selection of component models , 1997 .

[19]  Brian C. J. Moore,et al.  The Effect of Nonlinear Distortion on the Perceived Quality of Music and Speech Signals , 2003 .

[20]  Marco Saerens,et al.  Neural controller based on back-propagation algorithm , 1991 .

[21]  Malcolm J. Hawksford,et al.  Distortion Reduction in Moving-Coil Loudspeaker Systems Using Current-Drive Technology , 1989 .

[22]  Francis Rumsey,et al.  Verbal and non-verbal elicitation techniques in the subjective assessment of spatial sound reproduction , 2001 .

[23]  B. A. Harvey,et al.  Neural network-based EKG pattern recognition , 2002 .

[24]  B. Widrow,et al.  Neural networks for self-learning control systems , 1990, IEEE Control Systems Magazine.