Article

Multi-expression programming for structure optimization algorithm on FNT in the application of process object modeling

Authors:
If you want to read the PDF, try requesting it from the authors.

Abstract

According to characteristics of massive data, high dimension, strong coupling, inconsistency as well as data type of diversity, multi-mode in production control object of flow process, there are some modeling methods for process object modeling at present. This paper which bases on the production process of decomposition furnace builds a relationship network model by Flexible Neural Tree. The structure and parameters of flexible neural tree are optimized by Multi-Expression Programming and simulation annealing respectively. The results show that the important features by constructing the FNT model were formulated in accordance with the procedure mentioned in the previous research and this method has a high accuracy.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

Article
This paper which bases on the overall cement production process and eighteen parameters of cement process were obtained. Their relationship network model was built by Flexible Neural Tree. The structure and parameters of flexible neural tree are optimized by Multi-expression Programming and simulation annealing respectively. The results show that the built overall model can reflect and affect important parameters for f-CaO of cement clinker very well and has a certain accuracy.
Article
The purpose of this paper is to present our experience from the design of an air conditioner control mechanism, and the implications for the design of integrating technologies from different fields in smart house applications. We investigate the application of digital imaging technology to detect the number and location of interior parties. Combined with a simulated annealing algorithm, we implemented an intelligent air conditioning system, which can adjust itself automatically to the most appropriate configuration in different contexts and load demands. The identification result is used by the simulated annealing algorithm. Together with the size and the temperature of the room, one can achieve a more humane and intelligent control.
Article
This paper has proposed an approach based on ACO-SA algorithm for the multi-objective Distribution Feeder Reconfiguration. The simulation results have shown that global or close to global optimum solutions for the system losses, the voltage deviation was attained. Also, the proposed approach minimizes the number of switching operations. The proposed method is independent on the initial status of network switches. The ACO-SA is a combination of two powerful optimization algorithms: Ant Colony Optimization and Simulated Optimization.
Article
Classification and rule induction are two important tasks to extract knowledge from data. In rule induction, the representation of knowledge is defined as IF-THEN rules which are easily understandable and applicable by problem-domain experts. In this paper, a new chromosome representation and solution technique based on Multi-Expression Programming (MEP) which is named as MEPAR-miner (Multi-Expression Programming for Association Rule Mining) for rule induction is proposed. Multi-Expression Programming (MEP) is a relatively new technique in evolutionary programming that is first introduced in 2002 by Oltean and Dumitrescu. MEP uses linear chromosome structure. In MEP, multiple logical expressions which have different sizes are used to represent different logical rules. MEP expressions can be encoded and implemented in a flexible and efficient manner. MEP is generally applied to prediction problems; in this paper a new algorithm is presented which enables MEP to discover classification rules. The performance of the developed algorithm is tested on nine publicly available binary and n-ary classification data sets. Extensive experiments are performed to demonstrate that MEPAR-miner can discover effective classification rules that are as good as (or better than) the ones obtained by the traditional rule induction methods. It is also shown that effective gene encoding structure directly improves the predictive accuracy of logical IF-THEN rules.
Article
This paper describes the development and application of neural networks for analysis and optimization of industrial production data. Artificial neural networks based on a feedforward architecture and trained by the backpropagation technique were applied to analysis and improvement of a separation process. Various neural network topologies have been tested and compared. The Powell method was used to train the network by minimizing the sum of squares of residuals as well as the generalized delta rule (GDR) algorithm. The performance of the network have been analyzed. The obtained results show the applicability the neural networks structure with and without hidden layers. These results illustrate the feasibility of using a neural network as a data analyzer and as an optimization tool.
Article
In this study, gene expression programming (GEP), a novel genetic algorithm, is used to develop quantitative model as potential screening mechanism for mineral crystal lattice energy for the first time. Eight descriptors, including ionic radius, charges, effective nuclear charges and principal quantum number, are selected to establish this model. A nonlinear quantitative structure-property relationship (QSPR) model based on GEP has been built and its predicted coefficient (R2) is 0.9912. This study has provided a new and effective method for the research of mineral crystal lattice energy.