This paper presents a new method for designing adaptive neuro-fuzzy inference systems (ANFIS). Improvements are made by introducing specially developed orthogonal functions into the very structure of ANFIS, specifically, into the layer that imitates Sugeno stile defuzzification. These functions are specially tailored for analysis and synthesis of dynamic systems and they also contain an adaptive measure of the variability of the systems operating in a real environment, which can be implemented inside the ANFIS as hormonal effect.

In this article, a new intelligent hybrid controller is proposed. The controller is based on the combination of the orthogonal endocrine neural network (OENN) and orthogonal endocrine ANFIS (OEANFIS). The orthogonal part of the controller consists of Chebyshev orthogonal functions, which are used because of their recursive property, computational simplicity, and accuracy in nonlinear approximations. Artificial endocrine influence on the controller is achieved by introducing excitatory and inhibitory glands to the OENN part of the structure, in the form of postsynaptic potentials. These potentials provide a network with the capability of additional self-regulation in the presence of external disturbances. The intelligent structure is trained using a developed learning algorithm, which consists of both offline and online learning procedures: online learning for fitting OENN substructure and offline learning for adjusting OEANFIS parameters. The learning process is expanded by introducing the learning rate adaptation algorithm, which bases its calculations on the sign of the error difference. Finally, the proposed intelligent controller was experimentally tested for control of a nonlinear multiple-input-multiple-output two rotor aerodynamical system. During the test phase, an additional four related intelligent control logics and default PID-based controllers were used, and tracking performance comparisons were performed. The proposed controller showed notably better online results in comparison to other control algorithms. The major deficiencies of the structure are complexity and noticeably large training computation time, but these drawbacks can be neglected if tracking performances of a dynamical system are of the highest importance.

Currently, artificial intelligence and intelligent algorithms for the control of dynamic systems are the main focus for building Industry 4.0 services and developing novel, innovative industrial solutions. This paper proposes a novel intelligent control structure specifically tailored for treating environmental stimuli and disturbances in operational environments of dynamic systems. The structure is based on the Orthogonal Endocrine Neural Network (OENN) and Artificial Orthogonal Glands (AOGs). The operational mechanism of each AOG acquires and processes environmental stimuli and generates artificial hormone concentration values at the gland output. These values are introduced to the appropriate OENN layer to provoke the network with collected environmental insights. To verify the applicability of the proposed structure on a complex dynamical nonlinear system, it was tested in a laboratory environment on the laboratory magnetic levitation system (MLS). The main experimental goal was to test the tracking performance of a levitation object when the new control logic was applied. The results were compared with two additional intelligent algorithms and a default linear quadratic (LQ) control logic. OENN + AOG structure showed improved tracking performances compared with traditional LQ control and better adaptability to environmental conditions compared with similar existing solutions.

This paper presents a new type of endocrine neural network (ENN). ENN utilizes artificial glands which enable the network to be adaptive to external disturbances. Sensitivity is controlled by the hormone decay rate and the value of the sensitivity parameter. The network presented in this paper is improved by making the sensitivity parameter self-tuning and implementing orthogonal activation functions inside the network structure. Automatic tuning is performed on the basis of the biological principle of postsynaptic potentials by implementing inhibitory and excitatory glands inside the standard backpropagation learning algorithm of developed orthogonal ENN. These additional network functionalities enable extra sensitivity to external conditions and an additional network feature of activation sharpening. The network was tested on real-time series of experimental data with a purpose to forecast exchange rate of the three widely used international currencies.

Hammerstein-Wiener systems present a structure consisting of three serial cascade blocks. Two are static nonlinearities, which can be described with nonlinear functions. The third block represents a linear dynamic component placed between the first two blocks. Some of the common linear model structures include a rational-type transfer function, orthogonal rational functions (ORF), finite impulse response (FIR), autoregressive with extra input (ARX), autoregressive moving average with exogenous inputs model (ARMAX), and output-error (O-E) model structure. This paper presents a new structure, and a new improvement is proposed, which is consisted of the basic structure of Hammerstein-Wiener models with an improved orthogonal function of Müntz-Legendre type. We present an extension of generalised Malmquist polynomials that represent Müntz polynomials. Also, a detailed mathematical background for performing improved almost orthogonal polynomials, in combination with Hammerstein-Wiener models, is proposed. The proposed approach is used to identify the strongly nonlinear hydraulic system via the transfer function. To compare the results obtained, well-known orthogonal functions of the Legendre, Chebyshev, and Laguerre types are exploited.