Bio-inspirované výpočty

Duong Ngoc Hieu

Doctoral thesis

Bio-inspired Computing

Abstract:

The main objective of this thesis is to investigate and tackle urgent practical problems involving Vietnamese agriculture. In Vietnam, agriculture is one of the major industries and contributes significantly to the national Gross Domestic Product (GDP). Thus it is necessary to drastically improve Vietnamese agriculture in many aspects, such as national policies, advanced agriculture technologies, applications of computer science and so on. Two problems that are investigated in this thesis are river runoff prediction and boiler efficiency optimization. Since neural networks have proven to be effective methods for modeling, characterizing and predicting several types of sophisticated data, they are chosen as key methods in this thesis. For the first problem, we investigate some appropriate methods for predicting river runoff. The Srepok River is chosen as a case study. The task of prediction is divided into two cases: long-term and short-term prediction. To deal with the task of long-term prediction, three methods are utilized, such as recurrent fuzzy neural networks (RFNN), a hybrid of RFNN and genetic algorithms, and a physical-based method called SWAT. The experimental results show that the hybrid of RFNN and genetic algorithm is the most effective method. To predict short-term river runoff, we propose a hybrid of chaotic expressions, RFNN and clustering algorithms consisting of K-means and DBSCAN. Chaotic expressions are used to transform the river runoff data into new data, called phase space, containing much temporal information. Whereas the combination of RFNN and clustering algorithms, which is based on the principle of mixture of experts, is trained and tested with the phase space. The experimental results are conducted with many combinations of RFNN, K-means, DBSCAN, Eulid distance, and Dynamic Time Warping (DTW). The experimental results indicate that the combination of RFNN, DBSCAN and DTW is superior to others. For the second problem, RFNN and clustering algorithms are used to simulate boiler efficiency. The module of boiler simulation is an important component of a sophisticated soft sensor, namely BEO, which has been deployed at Phu My Fertilizer Plant since 2013. Then the boiler efficiency is forecasted multi-step-ahead and real-time. This task is tackled by using three methods including RFNN, a hybrid of RFNN and stochastic exploration, and RFNN improved by a reinforcement learning algorithm. The experimental results show that BEO is effective and can bring increased benefits to the plant.

Abstract:

The main objective of this thesis is to investigate and tackle urgent practical problems involving Vietnamese agriculture. In Vietnam, agriculture is one of the major industries and contributes significantly to the national Gross Domestic Product (GDP). Thus it is necessary to drastically improve Vietnamese agriculture in many aspects, such as national policies, advanced agriculture technologies, applications of computer science and so on. Two problems that are investigated in this thesis are river runoff prediction and boiler efficiency optimization. Since neural networks have proven to be effective methods for modeling, characterizing and predicting several types of sophisticated data, they are chosen as key methods in this thesis. For the first problem, we investigate some appropriate methods for predicting river runoff. The Srepok River is chosen as a case study. The task of prediction is divided into two cases: long-term and short-term prediction. To deal with the task of long-term prediction, three methods are utilized, such as recurrent fuzzy neural networks (RFNN), a hybrid of RFNN and genetic algorithms, and a physical-based method called SWAT. The experimental results show that the hybrid of RFNN and genetic algorithm is the most effective method. To predict short-term river runoff, we propose a hybrid of chaotic expressions, RFNN and clustering algorithms consisting of K-means and DBSCAN. Chaotic expressions are used to transform the river runoff data into new data, called phase space, containing much temporal information. Whereas the combination of RFNN and clustering algorithms, which is based on the principle of mixture of experts, is trained and tested with the phase space. The experimental results are conducted with many combinations of RFNN, K-means, DBSCAN, Eulid distance, and Dynamic Time Warping (DTW). The experimental results indicate that the combination of RFNN, DBSCAN and DTW is superior to others. For the second problem, RFNN and clustering algorithms are used to simulate boiler efficiency. The module of boiler simulation is an important component of a sophisticated soft sensor, namely BEO, which has been deployed at Phu My Fertilizer Plant since 2013. Then the boiler efficiency is forecasted multi-step-ahead and real-time. This task is tackled by using three methods including RFNN, a hybrid of RFNN and stochastic exploration, and RFNN improved by a reinforcement learning algorithm. The experimental results show that BEO is effective and can bring increased benefits to the plant.

Keywords

Neural networks, clustering algorithms, genetic algorithms, mixture of experts, river runoff prediction, soft sensors, boiler efficiency optimization.

Keywords

Neural networks, clustering algorithms, genetic algorithms, mixture of experts, river runoff prediction, soft sensors, boiler efficiency optimization.

Language used: Czech

Date on which the thesis was submitted / produced: 1. 9. 2016

Thesis defence

• Date of defence: 2. 11. 2016
• Supervisor: Václav Snášel
• Reader: Pavel Krömer, Roman Šenkeřík, Martin Radvanský

VŠB - Technical University of Ostrava

Fakulta elektrotechniky a informatiky

Doctoral programme / field:
Informatika, komunikační technologie a aplikovaná matematika / Informatika