The recent development of a new generation of automated radionuclide assay equipment in our facility requires embedded software at each machine for the scheduling of sample assay tasks. The execution time requirements of real-time embedded software limit the complexity of the schedular software. By representing the scheduling problem properly, a simple backpropagation neural network performs the scheduling function within the imposed requirements. Operational tests have demonstrated that the neural network schedular has met all development goals and is superior to the previous approaches. This paper describes the design and development of the neural network task scheduler. In addition, several aspects of the practical application of neural networks to real-world problems are discussed.
展开▼