An integrated approach to process planning and scheduling using genetic algorithms
This thesis presents a new integrated approach to process planning aad job-shop scheduling. The relationship between planning and scheduling is reassessed and the line between the two tasks is made significantly more blurred than in the usual treatment. Scheduling is traditionally seen as the task of finding an optimal way of interleaving a number of fixed plans which are to be executed concurrently and which must share resources. The implicit assumption is that once planning has finished scheduling takes over. In fact there are often many possible choices for the sub-operations in the plans. Very often the real optimisation problem is to simultaaeously optimise all the individual plans alzd the overall schedule. This thesis describes how manufa.cturing planning has been recast to allow solutions to the simultaneous plan and schedule optimisation problem, a problem traditionally considered too hard to tackle at all. A model based on simulated coevolution is developed and it is shown how complex interactions are handled in an emergent way. Results from various implementations are reported. Underlying this new approach is a feature based process planning system that is used to generate the space of all possible legal process plans for a given component. This space is then searched, in parallel with spaces for all other components, using an advanced form of genetic algorithm. The thesis describes the development of the ideas behind this technique and presents in detail the constituent parts of the whole system.