Nicolae Constantin

Learn More
This paper presents a fast and reliable method, for obtaining all the range of dispersion curves for wave propagation usually used in practice, by numerical simulation only, via common commercial finite element codes. Essentially, the method is based on a simple and robust approach, consisting in a few series of modal analyses for a representative part of(More)
This paper presents a combined strategy for tracking a non-holonomic mobile robot which works under certain operating conditions for system parameters and disturbances. The strategy includes kinematic steering and velocity dynamics learning of mobile robot system simultaneously. In the learning controller (neural network based controller) the velocity(More)
The paper presents the concept and implementation of an intelligent motion controller for a low power brushless servodrive. Fuzzy logic control and fuzzy reasoning tuning procedures are used for speed and current controllers respectively. A digital signal processor (DSP) based hardware set-up and a specialized software environment are used to laboratory(More)
Over the past decades has begun to increasingly pay attention to properties and structure of metals and alloys in liquid phase, the motivation being both scientifically and practically [1]. Particularly, especially in recent years, it has been demonstrated through the numerous studies, that the structural characteristics of different metallic melting might(More)
This paper presents a new algorithm for approximating a nonlinear function by means of local models. It is proposed a memory-based technique for selecting the best model configuration by comparing different alternatives. A recursive technique for local model identification and validation is presented, together with an enhanced statistical method for model(More)
In this paper a novel neural fuzzy inference network (NFIN) it is proposed. The NFIN represent a modified Takagi-Sugeno-Kang (TSK) type fuzzy rule based model with neural network learning ability. The rules in the NFIN are created and adapted in an on-line learning algorithm. The structure learning together with the parameter learning forms the learning(More)
  • 1