A neural-network model has been developed to predict the value of a critica
l strength parameter (internal bond) in a particleboard manufacturing proce
ss, based on process operating parameters and conditions. A genetic algorit
hm was then applied to the trained neural network model to determine the pr
ocess parameter values that would result in desired levels of the strength
parameter for given operating conditions. The integrated NN-GA system was s
uccessful in determining the process parameter values needed under differen
t conditions, and at various stages in the process, to provide the desired
level of internal bond. The NN-GA tool allows a manufacturer to quickly det
ermine the values of critical process parameters needed to achieve acceptab
le levels of board strength, based on current operating conditions and the
stage of manufacturing. (C) 2000 Elsevier Science Ltd. All rights reserved.