An assembly sequence-planning system for mechanical parts using neural network

Purpose - In this paper, an assembly sequence planning system, based on binary vector representations, is developed. The neural network approach has been employed for. analyzing optimum assembly sequence for assembly systems. Design/methodology/approach - The input to the assembly system is the assembly's connection graph that represents parts and relations between these parts. The output to the system is the optimum assembly sequence. In the constitution of assembly's connection graph, a different approach employing contact matrices and Boolean operators has been used. Moreover, the neural network approach is used in the determination of optimum assembly sequence. The inputs to the networks are the collection of assembly sequence data. This data is used to train the network using the back propagation (BP) algorithm. Findings - The proposed neural network model outperforms the available assembly sequence-planning model in predicting the optimum assembly sequence for mechanical parts. Due to the parallel structure and fast learning of neural network, this kind of algorithm will be utilized to model another types of assembly systems. Research limitations/implications - In the proposed neural approach, the back propagation algorithm is used. Various training algorithms can be employed. Practical implications - The simulation results suggest that the neural predictor would be used as a predictor for possible practical applications on modeling assembly sequence planning system. Originality/value - This paper discusses a new modelling scheme known as artificial neural networks. The neural network approach has been employed for analyzing feasible assembly sequences and optimum assembly sequence for assembly systems.