Dynamic modelling of induced draft cooling towers with parallel heat exchangers, pumps and cooling water network

Viljoen, Johannes Henning; Muller, Cornelius Jacobus; Craig, I.K.

doi:10.1016/j.jprocont.2018.04.005

Cited by 18 publications

(24 citation statements)

References 34 publications

(74 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An induced draft cooling tower is an essential part of the overall ECS that provides opportunities to build effective control. A white-box model for the induced draft cooling tower based on first principles is proposed in [6]. A comparison of this white-box model and a black-box model based on an adaptive neuro-fuzzy interference system (i.e., a neural network trained with an interference system based on fuzzy rules) in [13] shows that white-box models are superior for identifying basin temperature in the induced draft cooling tower.…”

Section: B Evaporative Cooling System (Ecs)mentioning

confidence: 99%

“…We particularly present a methodology for neural networks to follow a first order differential equation that describes the physical process. As an exemplary use case, we focus on an induced draft cooling tower [6]. Specifically, we devise and evaluate two state-of-the-art grey-box models, applied to the induced draft cooling tower: physics informed neural networks (PhyNN) and physics informed long-short term memory networks (PhyLSTM).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Physics-Informed LSTM Network for Flexibility Identification in Evaporative Cooling System

Lahariya

Karami

Develder

et al. 2023

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

In energy intensive industrial systems, an evaporative cooling process may introduce operational flexibility. Such flexibility refers to a system's ability to deviate from its scheduled energy consumption. Identifying the flexibility, and therefore, designing control that ensures efficient and reliable operation presents a great challenge due to the inherently complex dynamics of industrial systems. Recently, machine learning models have attracted attention for identifying flexibility, due to their ability to model complex nonlinear behavior. This research presents machine learning based methods that integrate system dynamics into the machine learning models (e.g., Neural Networks) for better adherence to physical constraints. We define and evaluate physics informed long-short term memory networks (PhyLSTM) and physics informed neural networks (PhyNN) for the identification of flexibility in the evaporative cooling process. These physics informed networks approximate the time-dependent relationship between control input and system response while enforcing the dynamics of the process in the neural network architecture. Our proposed PhyLSTM provides less than 2% system response estimation error, converges in less than half iterations compared to a baseline Neural Network (NN), and accurately estimates the defined flexibility metrics. We include a detailed analysis of the impact of training data size on the performance and optimization of our proposed models.

show abstract

Section: B Evaporative Cooling System (Ecs)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Physics-Informed LSTM Network for Flexibility Identification in Evaporative Cooling System

Lahariya

Karami

Develder

et al. 2023

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

show abstract

“…The performance of this measure relies on the affinity laws for the fans. The automatic air flow adjustment is described by Equation 7 [22]. Moreover, the change on the power of the fans is described by Equation 8…”

Section: Vsd In the Cooling Tower Fansmentioning

confidence: 99%

Water and Energy Efficiency Improvement of Steel Wire Manufacturing by Circuit Modelling and Optimisation

et al. 2019

View full text Add to dashboard Cite

Industrial water circuits (IWC) are frequently neglected as they are auxiliary circuits of industrial processes, leading to a missing awareness of their energy- and water-saving potential. Industrial sectors such as steel, chemicals, paper and food processing are notable in their water-related energy requirements. Improvement of energy efficiency in industrial processes saves resources and reduces manufacturing costs. The paper presents a cooling IWC of a steel wire processing plant in which steel billets are transformed into wire. The circuit was built in object-oriented language in OpenModelica and validated with real plant data. Several improvement measures have been identified and an optimisation methodology has been proposed. A techno-economic analysis has been carried out to estimate the energy savings and payback time for the proposed improvement measures. The suggested measures allow energy savings up to 29% in less than 3 years’ payback time and water consumption savings of approximately 7.5%.

show abstract

“…As a result, the water falling down in the basin underneath has dropped in temperature and can be recirculated through the process. For a more detailed description of an induced draft evaporative cooling system, we refer to [5]. The models created in this work are based on and verified by the data from an industrial cooling system as available at a chemical industrial site of INEOS in Belgium.…”

Section: Evaporative Cooling Systemmentioning

confidence: 99%

“…In this case, all the models predict practically identical water outlet temperatures [15]. In [5], Viljoen et al investigated the dynamic modelling of an induced draft cooling tower including the heat exchangers, pumps and fans. They also made initial assumptions regarding the cooling tower model.…”

Section: White Boxmentioning

confidence: 99%

Thermal Performance Evaluation of an Induced Draft Evaporative Cooling System through Adaptive Neuro-Fuzzy Interference System (ANFIS) Model and Mathematical Model

et al. 2019

View full text Add to dashboard Cite

The shift from fossil fuel to more renewable electricity generation will require the broader implementation of Demand Side Response (DSR) into the grid. Utility processes in industry are suited for this, having a large thermal time constant or buffer, and large electricity consumption. A widespread utility system in industry is an induced draft evaporative cooling tower. Considering the safety aspect, such a process needs to maintain cooling water temperature within predefined safe boundaries. Therefore, in this paper, two modelling methods for the prediction of the basin temperature of an induced draft evaporative cooling tower are proposed. Both a white box and a black box methodology are presented, based on the physical principles of fluid dynamics and adaptive neuro-fuzzy interference system (ANFIS) modelling, respectively. By analysing the accuracy of both models with a focus to cooling tower fan state changes, i.e., DSR purposes, it is shown that the white box model performs best. Fostering the idea of using such a system for DSR purposes, the concept of design for flexibility is also touched upon, discussing the thermal mass. Pre-cooling, where the temperature of the cooling water basin is lowered before a fan switch off period, was simulated with the white box model. It was shown that beneficial pre-cooling (to lower the temperature peak) is limited in time.

show abstract

Dynamic modelling of induced draft cooling towers with parallel heat exchangers, pumps and cooling water network

Cited by 18 publications

References 34 publications

Physics-Informed LSTM Network for Flexibility Identification in Evaporative Cooling System

Physics-Informed LSTM Network for Flexibility Identification in Evaporative Cooling System

Water and Energy Efficiency Improvement of Steel Wire Manufacturing by Circuit Modelling and Optimisation

Thermal Performance Evaluation of an Induced Draft Evaporative Cooling System through Adaptive Neuro-Fuzzy Interference System (ANFIS) Model and Mathematical Model

Contact Info

Product

Resources

About