Design of fuzzy system-fuzzy neural network-backstepping control for complex robot system

Fully Scalable Fuzzy Neural Network for Data Processing

The primary objective of the research presented in this article is to introduce an artificial neural network that demands less computational power than a conventional deep neural network. The development of this ANN was achieved through the application of Ordered Fuzzy Numbers (OFNs). In the context of Industry 4.0, there are numerous applications where this solution could be utilized for data processing. It allows the deployment of Artificial Intelligence at the network edge on small devices, eliminating the need to transfer large amounts of data to a cloud server for analysis. Such networks will be easier to implement in small-scale solutions, like those for the Internet of Things, in the future. This paper presents test results where a real system was monitored, and anomalies were detected and predicted.

Entropy-Weighted Numerical Gradient Optimization Spiking Neural System for Biped Robot Control

The optimization of robot controller parameters is a crucial task for enhancing robot performance, yet it often presents challenges due to the complexity of multi-objective, multi-dimensional multi-parameter optimization. This paper introduces a novel approach aimed at efficiently optimizing robot controller parameters to enhance its motion performance. While spiking neural P systems have shown great potential in addressing optimization problems, there has been limited research and validation concerning their application in continuous numerical, multi-objective, and multi-dimensional multi-parameter contexts. To address this research gap, our paper proposes the Entropy-Weighted Numerical Gradient Optimization Spiking Neural P System, which combines the strengths of entropy weighting and spiking neural P systems. First, the introduction of entropy weighting eliminates the subjectivity of weight selection, enhancing the objectivity and reproducibility of the optimization process. Second, our approach employs parallel gradient descent to achieve efficient multi-dimensional multi-parameter optimization searches. In conclusion, validation results on a biped robot simulation model show that our method markedly enhances walking performance compared to traditional approaches and other optimization algorithms. We achieved a velocity mean absolute error at least 35% lower than other methods, with a displacement error two orders of magnitude smaller. This research provides an effective new avenue for performance optimization in the field of robotics.

Robust tracking control of a flexible manipulator with limited control input based on backstepping and the Nussbaum function

A flexible manipulator is a versatile automated device with a wide range of applications, capable of performing various tasks. However, these manipulators are often vulnerable to external disturbances and face limitations in their ability to control actuators. These factors significantly impact the precision of tracking control in such systems. This study delves into the problem of attitude tracking control for a flexible manipulator under the constraints of control input limitations and the influence of external disturbances. To address these challenges effectively, we first introduce the backstepping method, aiming to achieve precise state tracking and tackle the issue of external disturbances. Additionally, recognizing the constraints posed by control input limitations in the flexible manipulator's actuator control system, we employ a design approach based on the Nussbaum function. This method is designed to overcome these limitations, allowing for more robust control. To validate the effectiveness and disturbance rejection capabilities of the proposed control strategy, we conduct comparative numerical simulations using MATLAB/Simulink. These simulations provide further evidence of the robustness and reliability of the control strategy, even in the presence of external disturbances and control input limitations.

Synchronization of discrete-time fractional fuzzy neural networks with delays via quantized control

In this paper, synchronization issue of discrete-time fractional fuzzy neural networks (DFFNNs) with delays is solved via quantized control, and is applied in image encryption. Firstly, a novel fractional-order h-difference inequality which makes Lyapunov method more flexible and practical is strictly proved based on the properties of convex functions and theory of discrete fractional calculus. Secondly, by using compression mapping theorem and mathematical induction, we obtain two sufficient conditions to ensure the existence and uniqueness of solutions for DFFNNs. Whereafter, we design a suitable quantized controller, which not only saves channel resources but also reduces control costs. By utilizing our inequality and some analytical techniques, several conservative synchronization criteria for DFFNNs are acquired. Finally, two examples are arranged to illustrate the validity and practicability of our results.

Trajectory Tracking Control Method for Omnidirectional Mobile Robot Based on Self-Organizing Fuzzy Neural Network and Preview Strategy

This paper proposes a new trajectory tracking control scheme for the four mecanums wheel omnidirectional mobile robot (FM-OMR). Considering the influence of uncertainty on tracking accuracy, a self-organizing fuzzy neural network approximator (SOT1FNNA) is proposed to estimate the uncertainty. In particular, since the structure of traditional approximation network is preset, it will cause problems such as input constraints and rule redundancy, resulting in low adaptability of the controller. Therefore, a self-organizing algorithm including rule growth and local access is designed according to the tracking control requirements of omnidirectional mobile robots. In addition, a preview strategy (PS) based on Bezier curve trajectory re-planning is proposed to solve the problem of tracking curve instability caused by the lag of tracking starting point. Finally, the simulation verifies the effectiveness of this method in tracking and trajectory starting point optimization.

Observer-based finite-time adaptive fuzzy back-stepping control for MIMO coupled nonlinear systems

An attempt is made in this paper to devise a finite-time adaptive fuzzy back-stepping control scheme for a class of multi-input and multi-output (MIMO) coupled nonlinear systems with immeasurable states. In view of the uncertainty of the system, adaptive fuzzy logic systems (AFLSs) are used to approach the uncertainty of the system, and the unmeasured states of the system are estimated by the finite-time extend state observers (FT-ESOs), where the state of the observer is a sphere around the state of the system. The accuracy and efficiency of the control effect are ensured by combining the back-stepping and finite-time theory. It is proved that all the states of the closed-loop adaptive control system are semi-global practical finite-time stability (SGPFS) by the finite-time Lyapunov stability theorem, and the tracking errors of the system states converge to a tiny neighborhood of the origin in a finite time. The validity of this scheme is demonstrated by a simulation.

Logistics Distribution Route Optimization Model Based on Recursive Fuzzy Neural Network Algorithm

In recent years, more and more attention has been paid to the utilization of data and information in the logistics distribution path optimization system of e-commerce, but it is difficult to have scientific guarantee in the process of determining the optimal distribution path scheme of e-commerce. How to realize the optimization and adaptive setting of distribution path by using intelligent algorithm has become a hot spot. To battle these issues, this paper studies the logistics distribution path optimization model based on recursive fuzzy neural network algorithm. This paper analyses the research status of logistics distribution path determination scheme and applies the recursive fuzzy neural network algorithm in the selection of e-commerce logistics distribution path scheme. The experimental results show that the recursive fuzzy neural network algorithm can realize the optimization of e-commerce logistics distribution path, and the best distribution route can be made according to the characteristic difference of logistics distribution route, and its distribution accuracy can reach more than 97%.

Automatic Detection Method of Technical and Tactical Indicators for Table Tennis Based on Trajectory Prediction Using Compensation Fuzzy Neural Network

In the system design of table tennis robot, the important influencing factors of automatic detection of technical and tactical indicators for table tennis are table tennis rotation state, trajectory, and rebound force. But the general prediction algorithm cannot process the time series data and give the corresponding rotation state. Therefore, this paper studies the automatic detection method of technical and tactical indicators for table tennis based on the trajectory prediction using the compensation fuzzy neural network. In this paper, the compensation fuzzy neural network algorithm which combines the compensation fuzzy algorithm and recurrent neural network is selected to construct the automatic detection of technical and tactical indicators for table tennis. The experimental results show that the convergence time of the compensation fuzzy neural network is shorter, the training time is shortened, and the prediction accuracy is improved. At the same time, in terms of performance testing, the model can accurately distinguish the influence of table tennis rotation state and rebound on table tennis motion estimation, so as to improve the accuracy of motion trajectory prediction. In addition, the accuracy of trajectory prediction will be improved with the increase of input data. When the number of data reaches 30, the trajectory prediction error is within the actual acceptable error range.

Stabilization and Synchronization of a Complex Hidden Attractor Chaotic System by Backstepping Technique

In this paper, the stabilization and synchronization of a complex hidden chaotic attractor is shown. This article begins with the dynamic analysis of a complex Lorenz chaotic system considering the vector field properties of the analyzed system in the Cn domain. Then, considering first the original domain of attraction of the complex Lorenz chaotic system in the equilibrium point, by using the required set topology of this domain of attraction, one hidden chaotic attractor is found by finding the intersection of two sets in which two of the parameters, r and b, can be varied in order to find hidden chaotic attractors. Then, a backstepping controller is derived by selecting extra state variables and establishing the required Lyapunov functionals in a recursive methodology. For the control synchronization law, a similar procedure is implemented, but this time, taking into consideration the error variable which comprise the difference of the response system and drive system, to synchronize the response system with the original drive system which is the original complex Lorenz system.