A Real-Time and Closed-Loop Control Algorithm for Cascaded Multilevel Inverter Based on Artificial Neural Network

In order to control the cascaded H-bridges (CHB) converter with staircase modulation strategy in a real-time manner, a real-time and closed-loop control algorithm based on artificial neural network (ANN) for three-phase CHB converter is proposed in this paper. It costs little computation time and memory. It has two steps. In the first step, hierarchical particle swarm optimizer with time-varying acceleration coefficient (HPSO-TVAC) algorithm is employed to minimize the total harmonic distortion (THD) and generate the optimal switching angles offline. In the second step, part of optimal switching angles are used to train an ANN and the well-designed ANN can generate optimal switching angles in a real-time manner. Compared with previous real-time algorithm, the proposed algorithm is suitable for a wider range of modulation index and results in a smaller THD and a lower calculation time. Furthermore, the well-designed ANN is embedded into a closed-loop control algorithm for CHB converter with variable direct voltage (DC) sources. Simulation results demonstrate that the proposed closed-loop control algorithm is able to quickly stabilize load voltage and minimize the line current’s THD (<5%) when subjecting the DC sources disturbance or load disturbance. In real design stage, a switching angle pulse generation scheme is proposed and experiment results verify its correctness.

Download Full-text

Closed-loop control of product geometry by using an artificial neural network in incremental sheet forming with active medium

International Journal of Material Forming ◽

10.1007/s12289-020-01598-1 ◽

2020 ◽

Author(s):

S. Thiery ◽

M. Zein El Abdine ◽

J. Heger ◽

N. Ben Khalifa

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Active Medium ◽

Closed Loop ◽

Sheet Forming ◽

Incremental Sheet Forming ◽

Closed Loop Control ◽

Loop Control ◽

Geometrical Accuracy ◽

Artificial Neural

AbstractA strategy to adjust the product geometry autonomously through an online control of the manufacturing process in incremental sheet forming with active medium is presented. An axial force sensor and a laser distance sensor are integrated into the process setup to measure the forming force and the product height, respectively. Experiments are conducted to estimate the bulging behavior for different pre-determined tool paths. An artificial neural network is consequently trained based on the experimental data to continuously predict the pressure levels required to control the final product height. The predicted pressure is part of a closed-loop control to improve the geometrical accuracy of formed parts. Finally, experiments were conducted to verify the results, where truncated cones with different dimensions were formed with and without the closed-loop control. The results indicate that this strategy enhances the geometrical accuracy of the parts and can potentially be expanded to be implemented for different types of material and geometries.

Download Full-text

Real-Time Closed Loop system controlled by an Artificial Neural Network for Estimation of the Optimal Load Shedding

12th IET International Conference on Developments in Power System Protection (DPSP 2014) ◽

10.1049/cp.2014.0056 ◽

2014 ◽

Author(s):

A.Q. Santos ◽

R.M. Monaro ◽

D.V. Coury ◽

M. Oleskovicz

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Real Time ◽

Closed Loop ◽

Loop System ◽

Load Shedding ◽

Closed Loop System ◽

Optimal Load ◽

Artificial Neural

Download Full-text

Modeling and Closed-Loop Control of Stretch Bending of Aluminum Rectangular Tubes

Journal of Manufacturing Science and Engineering ◽

10.1115/1.1536659 ◽

2003 ◽

Vol 125 (1) ◽

pp. 113-119 ◽

Cited By ~ 13

Author(s):

Hong Zhu ◽

Kim A. Stelson

Keyword(s):

Experimental Data ◽

Real Time ◽

Control Algorithm ◽

Closed Loop ◽

Strain History ◽

Closed Loop Control ◽

Loop Control ◽

Stretch Bending ◽

Rectangular Tube ◽

Rectangular Tubes

During stretch bending, considerable springback will occur after a tube has been plastically bent. To predict the springback, a simplified two-flange model for stretch bending of a rectangular tube has been developed in which the strain history has been considered. A comparison has been made between the springback predicted by this model and experimental data, which shows rough agreement. Based on this model, a real time closed-loop control algorithm is developed.

Download Full-text