Design of deaerator storage tank level control system at industrial steam power plant with comparison of Neural Network (NN) and Extreme Learning Machine (ELM) method

This paper has proposed a prototype of a control system in deaerator storage tank level at Industrial Steam Power Plant based on artificial intelligence (AI). There are two kind methods of AI which are implemented in this research, first is Back Propagation Neural Network (BP-NN) and the second is Extreme Learning Machine (ELM). The proposed method is aimed to improve the performance of an existing Proportional Integral (PI) control method. The input variables are error level and load condition. The output variables are control valve percentage and indicator value. From the experiment, the result proved that ELM is fast superior to BP-NN according to the time of training process and error tolerance. Prototype-based on ELM is also working properly with an error tolerance of 0.15 %.

[1]  Adi Soeprijanto,et al.  Real-time unbalanced load flow development using direct-ZBR method and modified lambda iteration for on-line monitoring and control , 2013 .

[2]  Adi Soeprijanto,et al.  Comparison methods of Fuzzy Logic Control and Feed Forward Neural Network in automatic operating temperature and humidity control system (Oyster Mushroom Farm House) using microcontroller , 2016, 2016 International Symposium on Electronics and Smart Devices (ISESD).

[3]  Adi Soeprijanto,et al.  Optimal Placement and Sizing of Distributed Generation for Minimize Losses in Unbalance Radial Distribution Systems Using Quantum Genetic Algorithm , 2014 .

[4]  Adi Soeprijanto,et al.  Smart-Meter based on current transient signal signature and constructive backpropagation method , 2014, 2014 The 1st International Conference on Information Technology, Computer, and Electrical Engineering.

[5]  Adi Soeprijanto.  Neural Network Optimal Power Flow(NN-OPF) based on IPSO with Developed Load Cluster Method , 2010 .

[6]  Adi Soeprijanto,et al.  Incremental Particle Swarm Optimizer with local search for Optimal Power Flow Subjected to Digital GCC based on Neural Network , 2012 .

[7]  Adi Soeprijanto,et al.  Rotor bars fault detection by DFT spectral analysis and Extreme Learning Machine , 2016, 2016 International Symposium on Electronics and Smart Devices (ISESD).

[8]  Dong Peng,et al.  Decoupling control based on PID neural network for deaerator and condenser water level control system , 2015, 2015 34th Chinese Control Conference (CCC).

[9]  Peng Wang,et al.  PID neural network decoupling control of deaerator pressure and water level control system , 2014, 2014 IEEE International Conference on Robotics and Biomimetics (ROBIO 2014).

[10]  Adi Soeprijanto,et al.  Digital Generator Capability Curve for Improving Optimal Power Flow based on IPSO , 2013 .

[11]  Kuo Lung Lian,et al.  Microgrid power flow using Homotopic and Runge-Kutta Method , 2015, 2015 IEEE 2nd International Future Energy Electronics Conference (IFEEC).

[12]  Tsai-Hsiang Chen,et al.  A distribution power flow using particle swarm optimization , 2012, PES 2012.

[13]  Lei Jinli.  Adaptive Fuzzy PID Control for Boiler Deaerator , 2012, 2012 International Conference on Industrial Control and Electronics Engineering.

[14]  Kuo Lung Lian,et al.  Improved Robustness of Sequential Three Phase Power Flow Using Homotopic Method , 2013 .

[15]  Geng Liang.  A class of model reference adaptive decouple control based on RBF neural network in deaerator system , 2008, 2008 3rd IEEE Conference on Industrial Electronics and Applications.

[16]  Xia Liu,et al.  Is Extreme Learning Machine Feasible? A Theoretical Assessment (Part I) , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[17]  C. L. Liu,et al.  Robust microgrid power flow using particle swarm optimization , 2013, International School on Nonsinusoidal Currents and Compensation 2013 (ISNCC 2013).