Luis Pérez-Lombard

Decision system based on neural networks to optimize the energy efficiency of a petrochemical plant

Highlights? We developed a decision system to optimize the energy efficiency of a petrochemical plant. ? The decision system has been developed through a data mining process. ? The decision system is based on an algorithm and a kernel of neural networks. ? We have tested the system and obtained a save of 7%. ? The system has been integrated in a pilot software. The energy efficiency of industrial plants is an important issue in any type of business but particularly in the chemical industry. Not only is it important in order to reduce costs, but also it is necessary even more as a means of reducing the amount of fuel that gets wasted, thereby improving productivity, ensuring better product quality, and generally increasing profits. This article describes a decision system developed for optimizing the energy efficiency of a petrochemical plant. The system has been developed after a data mining process of the parameters registered in the past. The designed system carries out an optimization process of the energy efficiency of the plant based on a combined algorithm that uses the following for obtaining a solution: On the one hand, the energy efficiency of the operation points occurred in the past and, on the other hand, a module of two neural networks to obtain new interpolated operation points. Besides, the work includes a previous discriminant analysis of the variables of the plant in order to select the parameters most important in the plant and to study the behavior of the energy efficiency index. This study also helped ensure an optimal training of the neural networks. The robustness of the system as well as its satisfactory results in the testing process (an average rise in the energy efficiency of around 7%, reaching, in some cases, up to 45%) have encouraged a consulting company (ALIATIS) to implement and to integrate the decision system as a pilot software in an SCADA.

Improving direct solar shading calculations within building energy simulation tools

The calculation of the shadows that building environment, building elements or shading devices may cast on the building envelope, plays a key role in load calculations and building energy simulation. Algorithms for solar shading calculations have direct repercussions on the accuracy of the results and the computational times of building simulation tools. This paper presents an improved method for direct solar shading calculations based on the projection of every polygon on a unique receiving surface and incorporates recent and high efficient algorithms to solve polygon intersections. Firstly, the method is shortly described. Secondly, it is validated by comparisons with other methods, experimental results and European standards. Then, a comparison test between the proposed and conventional methods is presented to assess computational speed improvement. Finally, the main advantages of the proposed method are discussed.

A Decision Support System for consumption optimization in a naphtha reforming plant

Abstract In a naphtha distillation process, the natural objective is to perform an entire process maximization of the production rate while meeting required product qualities by searching for an optimal operating condition by manipulating the operating variables. The objective of this paper includes performing an energy process optimization. Not only is an adequate production rate met with the required product qualities but the operating cost is also minimized through a data mining approach. The study of the influence of all process attributes in the defined Energy Efficient Indicator (EEI) allows the construction of a multivariate linear model to aid human experts in the recovery of energy losses. A canonical discriminant function carried out the data prediction step. The quality of the Decision Support System framework is illustrated by a case study considering a real database. Also, a commercial software supported by this mining framework is presented.

Fitting conduction transfer function method to low Fourier numbers: application to ground-coupled floors

This paper proposes a practical solution to the problems arising when the conduction transfer function (CTF) method is applied to solve the 1D transient component of heat transfer in the internal zone of ground-coupled floors. The lower boundary condition for these problems must be imposed at a depth of several metres. The proposed method is based on the division of the ground domain into a number of layers that allows calculation of transfer function coefficients while keeping the first cross coefficient negligible. A mathematical expression is proposed for the proper layer thickness that assures the applicability of the CTF method to thick ground domains. A numerical validation for a slab-on-grade configuration has been carried out showing maximum errors of 0.09°C (0.42%) and 0.73 W/m2 (2.24%) for temperature and heat flow rates on the floor surface, respectively.