Rotary Inverted Pendulum Identification for Control by Paraconsistent Neural Network

Abstract

Artificial neural networks (ANNs) have been used over the last few decades to perform tasks by learning with comparisons. Fitting input-output models, system identification, control, and pattern recognition are some fields for ANN applications. However, problems involving uncertain situations could be challenging for them. The family of paraconsistent logics (PL) is a powerful tool that can deal with uncertainty and contradictory information, so getting attention from researchers for its implications and applications in artificial intelligence. This investigation describes a novel activation function reasoned on the paraconsistent annotated logic by two-value annotations (PAL2v) rules, a variation of PL, allowing the design of a new paraconsistent neural net (PNN), applied in model identification for control (I4C) of a closed-loop rotary inverted pendulum (RIP) system.

Thiết kế bộ điều khiển con lắc ngược quay sử dụng bộ điều khiển trượt mờ Mamdani loại 2

“…Một số phương pháp truyền thống trong điều khiển như PI [2], PD và PID [3] được sử dụng. Ngoài ra, các phương pháp điều khiển hiện đại như trượt thích nghi [4], điều khiển mờ [5], mạng neural [6], tối ưu hóa bầy đàn (PSO) [6] và giải thuật di truyền (GA) [7] cũng đã được áp dụng để giải quyết vấn đề này.…”

Computing of LQR Technique for Nonlinear System Using Local Approximation

“…RIP is the underactuated mechanical system with lesser control inputs than the degree of freedom. The control of such a system is a more challenging task, and the system becomes a classical benchmark for designing, testing, estimating, and comparing different control techniques [1][2][3][4][5]. The RIP controller design is a crucial problem with the inherent instability feature.…”

Combining Passivity-Based Control and Linear Quadratic Regulator to Control a Rotary Inverted Pendulum

“…A number of control strategies have been applied for RIP such as optimizing time of swing-up to control of RIP [2], safe manual control strategy for RIP [3], virtual holonomic constraint for stabilization control [4], research of limit cycle elimination in RIP and pendubot [5], nonlinear sliding mode control methodology [6], memory output-feedback integral sliding mode control [7], a research related to Bayesian Optimization [8]. Apart from that research has been completed on the use of intelligence control which are paraconsistent neural network for RIP identification [9], deep neural network [10]- [12], [65], fuzzy logic control (FLC) [13], [14]. Besides, soft computation such as genetic algorithm (GA) [13], [14], [16]- [18], practical swarm optimization [15], gravitational search algorithm (GSA) [16], seeker optimization algorithm (SOA) [16], Teachinglearning based optimization (TLBO) [16].…”