Apoyo a la toma de decisión en una red de evaporadores industriales

Abstract

<p>La planificación de la producción y tareas de mantenimiento en una red de equipos es una tarea cuya complejidad aumenta exponencialmente con el número de productos, equipos y tareas. Encontrar soluciones óptimas económicas o de eficiencia de recursos) se hace especialmente difícil para un planificador humano, más aún cuando se requiere tomar decisiones en breves periodos de tiempo. Este trabajo aborda el problema de distribución de carga en tiempo real y programación de limpiezas en una red de evaporadores industriales mediante herramientas de ayuda a la decisión basadas en optimización mixta entera con modelos. Las herramientas propuestas tienen en cuenta las preferencias de visualización de los operarios y están integradas con el sistema de supervisión de la planta. Además de proporcionar recomendaciones para la operación óptima de la red, se incluye un sistema semiautomático de actualización de modelos basado en datos históricos de operación.</p>

Modelling and real-time optimisation of an industrial cooling-water network

“…1), which also affects the overall specific steam consumption. Fouling in the heating line is out of this work, for details on how to deal with it see [8].…”

“…The complete evaporation system in Lenzing A.G. can be mainly described by two networks of equipment. The first one concerns the evaporation plants where decisions on load allocation need to be taken [8]. The second one refers to the cooling systems attached to each plant, feed by a water distribution network, where decisions on water flows to plants need to be taken, i.e the problem addressed in this work.…”

“…Currently, independent optimisation setups are already developed for each network. However, both systems are coupled by the spinbath loads EC e and the outlet water temperatures T out,e in the cooling systems, so that the decisions on the load allocation influence the cooling-water distribution and vice versa (see the formulation of the optimisation in [8] and compare with the one in Section IV-A). If both problems are solved independently, by treating these shared variables as "a priori" fixed data for each problem, the overall optimisation becomes an iterative procedure with no global optimality guarantees.…”

A Systematic Grey-Box Modeling Methodology via Data Reconciliation and SOS Constrained Regression

“…Consequently, many people in the process control community have been devoting efforts during the last decade to develop efficient and reliable models to support operators and managers in their decisions [9,10]. The preferred option is building models that combine as much physical information as possible/acceptable with relationships obtained from experimental data collected from the plant [11].…”

Optimal distributed load allocation and resource utilisation in evaporation plants

“…Then, the absolute steam consumption (ASC) in each plant is computed by ASC = SSC • EC. Plant surrogate models were developed to estimate the SSC in Kalliski et al (2019), which, after straightforward manipulations, is found to depend on EC and on the cooling capacity of the surface condenser C pow , as shown in (1). The cooling system performance is also modelled experimentally: the outlet cooling-water temperature of the condensers T out is estimated by a polynomial function up to degree 3 on the cooling-water flow F w and affine in its inlet temperature T in , as proposed in (Marcos et al, 2018):…”