Amâncio Santos

Global optimization of energy and production in process industries: a genetic algorithm application

Abstract The process industries exhibit an increasing need for efficient management of all the factors that can reduce their operating costs, leading to the necessity for a global multi-objective optimization methodology that will enable the generation of optimum strategies, fulfilling the required restrictions. In this paper, a genetic algorithm is developed and applied for the optimal assignment of all the production sections in a particular mill in the kraft pulp and paper industry, in order to optimize energy the costs and production rate changes. This system is intended to implement all programmed or forced maintenance shutdowns, as well as all the reductions imposed in production rates.

Simulation platform for Wireless Sensor Networks based on the TrueTime toolbox

Research on wireless sensor networks (WSN) has received considerable attention in the last few years due to their unique characteristics, including, flexibility, self-organization, easy deployment, which make them an ideal candidate for low-cost monitoring. In order to help WSN planning and to enable the design of new protocols and applications and assess their performance, several existent simulation platforms have been extended to include simulation frameworks for WSN. In this paper, a higher level simulation platform for WSN is proposed based on the truetime toolbox. Relevant features include graphical representation of communication components, wireless communication and battery-driven operation. Special attention was paid to the 3D graphical interface, simulator interactivity and its extendibility. Simulation results demonstrate the applicability and usability of the proposed simulation platform.

Constrained GA applied to production and energy management of a pulp and paper mill

Optimization tasks issued from real industrial problems are often characterized by being multicriteria, mixed, nonconvex, large scale, ill-defined [2][9][26]. In this work such a problem is obtained from the optimization of production scheduling and energy management in industrial complexes (in the case of a kraft pulp and paper mill). Consider two criteria, one of real variables issued from the energy optimization, and another of integer (logical) variables issued from production scheduling optimization, submitted to a high number of equality and inequality constraints [19][20]. To solve this problem it is proposed a strategy based on genetic algorithms. Computational results are presented to support discussion of the several developed techniques, namely selection methods, crossover and mutation operators, and diversification techniques. Results about the industrial relevance of the method are also presented, showing that genetic algorithms can solve important industrial problems although they need yet powerful computers to get answers in an interactive way. ∗Partially financed by JNICT/PRAXIS XXI program. Industrial data given by Eng. J. Amaral, Portucel, Viana do Castelo, Portugal.

Multi-Agent Platform in WSAN Applications: A Time Synchronization Perspective

Abstract Research on wireless sensor and actuator networks has attracted considerable attention in the past few years. When dealing with monitoring and control over these infrastructures in industrial environments, distributed artificial intelligence techniques, under the form of agents, can be used to improve performance, in terms of autonomy, adaptability and robustness. In this context, synchronization of nodes’ clocks is critical for the overall system performance. The paper focuses on developing a wireless sensor network multi-agent based architecture. A particular topology is proposed and general features and requirements for mobile agents described, namely, tasks and services, as well as communication and coordination mechanisms. In order to cope with offset and skew of nodes’ internal clocks a solution is proposed based on message transmissions between two nodes.

Bayes information criterion for Tikhonov regularization with linear constraints: application to spectral data estimation

Spectral data estimation is an ill-posed problem, since it is difficult to collect sufficient linear independent data and, due to the integral nature of solid-state light sensors, camera outputs do not depend continuously on input signals. To solve these problems, most methods rely on exact a priori knowledge to reduce the problems complexity (solution space). In this paper a new algorithm is introduced which does not require a priori information. The method is build upon a new extension of the Bayes information criterion for ill-posed estimation problems, that is able to extract this information from the input data. The proposed solution is quite general and can readily be applied to other ill-posed problems, which are common in computer vision and image processing.

Learning spectral calibration parameters for color inspection

Light sensor spectral calibration is an ill-defined problem. For the identification problem one needs a priori knowledge of the characteristics of the sensor which is difficult to get in most situations. A new methodology is presented in this paper that does not rely on any a priori knowledge of the sensors characteristics. The method uses an extended generalized cross-validation function to measure predictability of the identified sensors spectral behavior. The prediction error is minimized with a hybrid genetic algorithm. Further an extended image formation model is introduced to model changes in additive and multiplicative errors. The calibration problem is formulated to be independent of these changes by previously identifying and removing them from the images.

Global Optimization of Energy and Production in Basic Industries: A Genetic Algorithm Application

Abstract The basic industries exhibit an increasing need for efficient management of all factors reducing the operation costs, leading to the necessity of a global multi-objective optimization methodology enabling the generation of optimum strategies fulfilling the required restrictions. In this paper a genetic algorithm is developed and applied for the optimal assignment of all the production sections in a particular mill of the Kraft pulp and paper industry in order to optimize energy costs and the production rate changes. This system is intended to fulfill all programmed or forced tnaintenance shutdowns as well as all the imposed reductions in production rates.

On the estimation of spectral data: a genetic algorithm approach

Spectral data estimation from image data is an ill-posed problem since (i) due to the integral nature of solid-state light sensors, the same output can be obtained from an infinity of input signals and (ii) color signals are spectrally smooth in nature and therefore limit the number of linear independent equations that can be formulated for the identification problem. To enable the solution of these problems most methods rely on exact a priori knowledge, such as smoothness and modality, to formulate hard constraints. A new method based on an extended generalized cross-validation measure is introduced for this type of problems. The solution is obtained with a genetic algorithm that maximizes its prediction ability. The method does not require exact a priori knowledge on the solution, since it is able to extract this information from the input data.

Multi-agent Topologies over WSANs in the Context of Fault Tolerant Supervision

Wireless Sensor and Actuator Networks can be used to detect and classify ephemeral distributed events, where different process components with different behaviours are involved. Agents implementing Distributed Artificial Intelligence techniques are a key value in improving the overall system’s performance. This paper proposes a general WSAN Multi-Agent based architecture for robust supervision and fault tolerant control.

Recovering imaging device sensitivities: a data-driven approach

Recovering spectral sensitivities of imaging devices with indirect methods, as well as spectral stimuli estimation from device responses are ill-posed problems. All known methods have to rely on a priori information to constrain the solution space, which, in most situations, is difficult or even impossible to obtain. In this paper we introduce a simple and fully data-driven approach for indirect spectral sensitivity estimation, which does not rely on explicit a priori information. The method is built upon an extension of our previous work on generalized cross-validation for constraint Tikhonov problems and utilizes a linear combination of band-limited basis functions.