Abstract:

Gantt charts are a common technique for representing the phases and activities of a project or a process work breakdown structure (WBS), so that they can be understood by a wide audience. Because the horizontal bars of a Gantt chart have a fixed height, they can misrepresent the time-phased workload (resource requirements) of a project, which may cause confusion especially in large projects.This paper shows a new approach of rendering the graph point series called Gantts. In our application, Gantts are placed in the two dimensional graph which contains the information about available production sources in the real manufacturing process. To provide a comfortable appearance, Gantts are accompanied with the description text giving detailed information about each Gantt such as name, required amount of item, etc. All Gantt descriptions must be displayed without any overlapping with each other. We applied the modified version of the RBF (Radial Basic Function) neural network with biases to optimize this task. With respect to the similarity to the RBF structure, the new type of neural network was named RBF 2. We also offer the idea of positive and negative attributes of the solution based on the neural network architecture.