Optimization of the Robot's Position Base Point by Using the Proper Algorithm and Iterative Pseudo Inverse Jacobian Neural Network Matrix Method
In the robotized production one of the more important think is to choose the optimal solution to use the robots with respect an objective function which represents, for example, minimum time of motion during a application, or minimum consumption of energy, or maximum precision, or combination of these. Some objective functions could results from the specificity of the application like is the case of casting of forging, where the minimum of the accumulation of heat could be one of the optimization criteria. In the controlling of the space movement of the end effecter and the robot’s joints of the all robots from the applications, one of the most important think is to know, with the extreme precision, the joints relative displacements of all robots. One of the most precise method to solve the inverse kinematics problem in the robots with redundant chain is the complex coupled method of the neural network with Iterative Pseudo Inverse Jacobian Matrix Method. In this paper was used the proper coupled method Iterative Pseudo Inverse Jacobian Matrix Method (IPIJMM) with Sigmoid Bipolar Hyperbolic Tangent Neural Network with Time Delay and Recurrent Links (SBHTNN-TDRL) to establish the optimal position of the application point of the robot's base with respect simultaneously two objective functions: the extreme precision and the minimum of the movements time. The paper shown how can be changed the multi robots application in to one application with parallel robot structure with three independent robots, all of them with optimal location point with respect the obiective function. The presented method and the virtual instrumentations (VI) are generally and they can be used in all other robots application and for all other conventional and unconventional space curves.
Prof. Adrian Olaru
A. Olaru et al., "Optimization of the Robot's Position Base Point by Using the Proper Algorithm and Iterative Pseudo Inverse Jacobian Neural Network Matrix Method", Applied Mechanics and Materials, Vol. 859, pp. 153-160, 2017