Patrick J. Connally

  • Citations Per Year
Learn More
Nonlinear identification using a novel neural network paradigm, namely enggenes, is investigated. A set of MATLAB functions for the training and simulation of eng-genes based neural models are described. These functions are then used to investigate the effectiveness of the technique applied to two nonlinear dynamical systems. Experimental data from a pH(More)
The ‘eng-genes’ concept, in which system-related nonlinearities are used as hidden-layer activation functions, has proven effective in the context of nonlinear systems modelling. This concept is now extended to control applications. An eng-genes network is integrated into a nonlinear adaptive controller and applied to a simulation of the Continuous Stirred(More)
  • 1