A time-specified zeroing neural network for quadratic programming with its redundant manipulator application

To solve time-varying quadratic programming with equation constraint, a new time-specified zeroing neural network (TSZNN) is proposed and analyzed. Unlike the existing methods such as Zhang neural network (ZNN) with different activation functions (AFs) and finite time neural network (FTNN), TSZNN model is incorporated into a terminal attractor and the convergent error can be guaranteed to reduce to zero in advance (instead of finite-time property). The greatest advantage of the TSZNN model is independent to the initial state of the systematic dynamics, which is much astonishing to the finite convergence relied on the initial conditions and comprehensively modifies the convergent performance. Mathematical analyses substantiate the pre-specified convergence of the TSZNN model and high convergent precision under the situation of various convergent time setting. Pre-specified convergence of the TSZNN model for a quadratic programming problem has been mathematically proved under different convergent constant setting. In addition, simulation applications conducted on a repeatable trajectory planning of redundant manipulator are studied to demonstrate the validity of the proposed TSZNN model.