A nature inspired optimal control of pneumatic-driven parallel robot platform

Abstract

Woodworking industry is increasingly characterized by processing complex spatial forms with high accuracy and high speeds. The use of parallel robot platforms with six degrees of freedom gains more significance. Due to stricter requirements regarding energy consumption, easy maintenance and environmental safety, parallel platforms with pneumatic drives become more and more interesting. However, the high precision tracking control of such systems represents a serious challenge for designers. The reason is found in complex dynamics of the mechanical system and strong nonlinearity of the pneumatic system. This paper presents an optimal control design for a pneumatically driven parallel robot platform. The Proportional-Integral-Derivative (PID) algorithm with feedback linearization is used for control. The parameter search method is based on a firefly algorithm due to the empirical evidence of its superiority in solving various nonconvex problems. The simulation results show that the proposed optimal tuned cascade control is effective and efficient. These results clearly demonstrate that the proposed control techniques exhibit significant performance improvement over classical and widely used control techniques.

Machine learning for multi-dimensional optimisation and predictive visualisation of laser machining

“…In traditional optimisation tasks, many complex algorithms are employed (Desiré et al 1978) such as ones inspired (Pršić et al 2017;. However, once trained, interrogating the neural network (to retrieve crown height and dimple depth predictions) only took 0.77 ms per parameter combination, and hence a detailed parameter scan, of 50*50*50 125,000 predictions, took less than 100 s. While this method is quick and effective it will not find a true optimum, only the best out of the sampled positions.…”

NSGA-II as feature selection technique and AdaBoost classifier for COVID-19 prediction using patient’s symptoms

“…To this end, GA is used to select the optimal combination of hyper-parameters. In fact, this technique has been commonly used in different areas [27][28][29] which provide outstanding results in maximizing the results. It also has revealed to be more efficient compared to other techniques in searching parameters [26].…”

Improved Beetle Antennae Search Algorithm-Based Lévy Flight for Tuning of PID Controller in Force Control System

“…Zhang et al [36] used a differential evolution algorithm to design a PID controller in the pneumatic rotary actuator position servo system. Pršić et al [37] applied the firefly algorithm to tune three PID parameters in the parallel robot platforms with six degrees of freedom gains. e literature [38] proposed a PID controller based on the selfgrowing Lévy flight salp swarm algorithm in hydraulic systems.…”