Hybrid of ANN with genetic algorithm for optimization of frictional vibration joining process of plastics

Complex shapes of plastics can be realized by joining techniques. Newer method of joining of plastics is necessitated by the industries due to the requirement such as reduced processing time and improved strength. Frictional vibration joining of plastics is a newer method where the heat generated by the third body at the interface of joining members is utilized for joining. The present study attempts to use the Taguchi method for frictional vibration joining of plastic plates. The effectiveness of the Taguchi method lies in clarifying the factor that dominates complex interactions in frictional vibration welding. The factors are (1) frequency of tool vibrating across the work piece, (2) feed of the work piece against the tool, and (3) clamping force at the joint interface. This study describes a new method of selection of process parameters for obtaining optimal weld tensile strength. Genetic algorithm was used to optimize the parameters for the process. Artificial neural network (ANN) was used to establish the relationship between the input/output parameters of the process. The established ANN is then suitably integrated with the optimization technique. This hybrid technique of ANN and genetic algorithm is effectively used to obtain optimal joint strength.