Intelligent computation modeling and analysis of a gripper for advanced manufacturing application

This paper is aimed to provide a new design modeling of the gripper via using the intelligent computing model. The gripper is designed to get benefit of a symmetric structure and compliant mechanism that can manipulate the objects with a stable force. The numerically experimental samples for the gripper are built and the finite element simulations are implemented. The displacement of left hand is collected. An intelligent computing model is formulated via a hybridization of the teaching learning optimization and feed forward neural network. The teaching learning optimization algorithm is embedded into neural network to enhance the training process. The results determined that the mean square error values of the entire model, the training, the testing, and validating are about 6.04e-07, 6.11e-07, 6.50e-08, and 1.10e-06, respectively. Furthermore, the coefficient of determination value of the entire model, the training, the testing, and validating are 0.9975, 0.9970, 0.9998, and 0.9677, accordingly. In addition, the proposed intelligent predictor is outperformed other regression methods such as linear regression, full 2nd order polynomial regression, and traditional artificial neural network. Moreover, the errors among the estimated from the proposed intelligent method and the prediction errors are less than 3%. It revealed that the proposed intelligent methodology is a well-suitable predictor for modeling the behaviors of gripper. The gripper is capable of providing a displacement amplification ratio of 2.85 and a max grasping force of 145.96 N. The gripper is potential for many practical applications such as robotics and manipulators in agricultural and electrics engineering.