Jan Pitel

Model-based Evolution of a Fast Hybrid Fuzzy Adaptive Controller for a Pneumatic Muscle Actuator

Pneumatic artificial muscle-based robotic systems usually necessitate the use of various nonlinear control techniques in order to improve their performance. Their robustness to parameter variation, which is generally difficult to predict, should also be tested. Here a fast hybrid adaptive control is proposed, where a conventional PD controller is placed into the feedforward branch and a fuzzy controller is placed into the adaptation branch. The fuzzy controller compensates for the actions of the PD controller under conditions of inertia moment variation. The fuzzy controller of Takagi-Sugeno type is evolved through a genetic algorithm using the dynamic model of a pneumatic muscle actuator. The results confirm the capability of the designed system to provide robust performance under the conditions of varying inertia.

Simulation of actuator dynamics based on geometric model of pneumatic artificial muscle

Dynamic simulation model of the actuator with two pneumatic artificial muscles in antagonistic connection was designed and built in Matlab Simulink environment. The basis for this simulation model was dynamic model of the pneumatic actuator based on advanced geometric muscle model. The main dynamics characteristics of such actuator were obtained by model simulation, as for example muscle force change, pressure change in muscle, arm position of the actuator. Simulation results will be used in design of control system of such actuator using model reference adaptive controller.

Cost Effective Biomass Combustion Process Control

Abstract The new control algorithms were implemented into control systems of boilers for woodchips combustion with aim to reach the complete combustion with minimum excess of combustion air. The main selection criterion for carbon monoxide and oxygen sensors was an achievement of required technical parameters under minimal costs for possibility of using the designed algorithms also in control systems of the small-scale boilers. So far obtained data from monitored control systems of two types of boilers for woodchips combustion confirm the right approach to design and realization of automatic biomass combustion process control system.

Smart 3D pointing device based on MEMS sensor and bluetooth low energy

The paper deals with the development of a new type of wireless pointing device based on 3D MEMS sensor as measuring component. Currently available pointing devices based on MEMS sensors (AIR mouse or AIR presenter) use proprietary wireless solution and their dimensions are copied from standard mouse. The new approach of our pointing device is based on standardized Bluetooth Low Energy protocol with minimal dimension and 3D way of control. This device can be used like a standard mouse in 2D with computer equipped by Bluetooth 4. The third measured dimension can be used to switch X or Y axis to Z plane, because we can control pointer without flat surface. The change of 2D pointing plane from XY to YZ or XZ can be switched intelligent by detection of acceleration activity in third axis. The device in full 3D mode will be used for control of rehabilitation arm in teaching mode by patient or therapist.

Simulation of fuzzy adaptive position controllers for pneumatic muscle actuator

Pneumatic muscle actuators usually use various non-linear control techniques in order to improve their performance. Therefore a hybrid adaptive control scheme with reference model was designed where a conventional PD controller in the feedforward branch and a fuzzy controller in the adaptation branch were used. In the paper two types of fuzzy adaptive position controllers (type Mamdani and type Sugeno) are tested for comparison and simulation results of their using in the pneumatic muscle actuator hybrid adaptive control system are presented.

Simulation of Hybrid Fuzzy Adaptive Control of Pneumatic Muscle Actuator

The pneumatic muscle actuator is highly nonlinear system and it is difficult to control it using only a linear controller with fixed gains. The hybrid fuzzy adaptive control scheme with reference model was designed to control such actuator. It uses a multiplicative signal adaptation with a linear controller in the feedforward and a fuzzy controller in the adaptive feedback loop. In the paper there are presented some simulation results of this control. The nonlinear dynamic model of one-DOF actuator based on the advanced geometric muscle model was used in simulation.

Improved modeling of pneumatic muscle actuator using recurrent neural network

Derivation of models of complex nonlinear systems usually incorporates a number of simplifications in modeled phenomena with the level of these simplifications being dictated primarily by its intended purpose. If the overall model accuracy is insufficient, it might be helpful to use the powerful approximation capabilities of universal approximators like neural networks which are capable of approximating certain types of functions to arbitrary degree of accuracy. On the other hand, using black-box modeling techniques can impair the resulting extrapolation qualities of the model as well as eliminate its physical interpretation. Here an improved dynamic modeling of one-DOF pneumatic muscle actuator using recurrent neural network is proposed. The proposed method preserves the physical meaning of the model while improving its accuracy compared to the original analytic model. System and model responses are compared in closed-loop (using conventional PD controller) and all unmodeled dynamics is treated as disturbance which is identified using Elman neural network It is shown that the resulting model is applicable for model-based control system design with greater precision.

Feature selection via competitive levy flights

Evolutionary meta-heuristics are designed for optimization using population with selection and mutation operators. Novelty of our approach is based on competition of various operators from mutation portfolio. Resulting meta-heuristic is successfully tested on the feature selection task: searching for a sparse sub-model having the best possible value by means of information criteria. Beginning with such statistical formulation we obtain an NP-hard optimization task which can be efficiently solved via meta-heuristic approach. We demonstrate how meta-heuristic optimization combined with statistics can enhance machine learning models and therefore is useful in Computational Intelligence in general.

Application of neural networks to evaluate experimental data of galvanic zincing

In order to improve corrosion resistance of alloy S355 EN 1025, the relationship between the thickness of zinc coating created during the process of acidic galvanic zincing and factors that influence this process were investigated. Influence of individual factors on thickness of zinc coating for sample area with surface current density of 3 A·dm-2 was determined by planned experiment which uses central composite plan. The obtained experimental data were evaluated based on neural network theory using cubic neural unit with Levenberg-Marquardt iterative adaptive algorithm. The influence of number of training data on the reliability of the obtained computational model has been studied. Furthermore, relationship between the amount of training data and reliability of prediction for the thickness of created zinc layer was observed. The relationship between input factors and thickness of layer coating with 88.37% reliability was reached.

Application of Artificial Neural Network for Identification of Bearing Stiffness Characteristics in Rotor Dynamics Analysis

In this article the implementation of the mathematical model for rotor oscillations on non-linear bearing supports for the multistage centrifugal compressor is considered by using the computer program “Critical frequencies of the rotor”. It realized the finite element mathematical model, which allows taking into account the non-linear dependence of bearing stiffness on the rotor speed, as well as gyroscopic moments of inertia of impellers and shell-type parts. The artificial neural network “Virtual Gene Developer” software is proposed for evaluating the operating parameters of the approximating curve “bearing stiffness – rotor speed” by the dataset of numerical simulation results in the abovementioned software. Actual parameters of non-linear bearing stiffness are obtained by the results of the experimental research of rotor critical frequencies for the multistage centrifugal compressor 295GC2-190/44-100M on the experimental accelerating-balancing stand “Schenck”. The main advantages of the proposed approach and methodology for application of Artificial Neural Networks are stated.