This paper addresses the issue of direct inverse control for two types of nonlinear transducer systems characterised by:
piecewise linear input-output transfer function;
hysteresis occurring in the input-output transfer function;
with the aim of establishing whether some relationship exists between the severity of different nonlinearities and the complexity of the network required to control such nonlinearities in static/low-frequency sensor applications.
The compensation is performed using an artificial neural networks approach. The networks chosen were a static MLP and if tap-delayed line MLP, both trained by an improved BKP method which included a form of dynamic learning management.
|Title of host publication||Artificial Neural Nets and Genetic Algorithms|
|Subtitle of host publication||Proceedings of the International Conference in Portorož, Slovenia, 1999|
|Editors||Andrej Dobnikar, Nigel C. Steele, David W. Pearson, Rudolf F. Albrecht|
|Publisher||Springer, Springer Nature|
|Number of pages||6|
|ISBN (Print)||3211833641, 9783211833643|
|Publication status||Published - 1999|
|Event||International Conference on Artificial Neural Networks and Genetic Algorithms (ICANNGA 99) - PORTOROZ, Slovenia|
Duration: 6 Apr 1999 → 9 Apr 1999
|Conference||International Conference on Artificial Neural Networks and Genetic Algorithms (ICANNGA 99)|
|Period||6/04/99 → 9/04/99|