Implementation of deep learning methods in prediction of adsorption processes

Skrobek, Dorian; Krzywański, Jarosław; Sosnowski, Marcin; Kulakowska, Anna; Żyłka, Anna; Grabowska, Karolina; Ciesielska, Katarzyna; Nowak, W.

doi:10.1016/j.advengsoft.2022.103190

Cited by 53 publications

(15 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the increased thermal diffusivities of the prepared modified adsorption beds, the addition of CNTs to SG resulted in a decrease in the sorption capacity. Another interesting option is the use of fluidization adsorption beds [79][80][81][82][83][84][85]. This is a new concept, in which fluidized adsorption beds replace packed beds in conventional adsorption chillers.…”

Section: Technological Advancements In Adsorption Refrigeration: Impr...mentioning

confidence: 99%

Review of Micro- and Nanobubble Technologies: Advancements in Theory and Applications and Perspectives on Adsorption Cooling and Desalination Systems

Lasek,

Krzywanski,

Skrobek

et al. 2023

Energies

Self Cite

View full text Add to dashboard Cite

Adsorption refrigerators are a compelling ecological alternative to compressor refrigerators; global warming forces us to constantly look for alternative sources of energy and cold. Cold production in adsorption chillers is based on the use of heat generated by other processes running in the company. Waste heat from production processes, which has, until now, been irretrievably lost, is a potential source of energy for generating cold via an adsorption unit producing chilled water. Cooling optimizes the use of the heating network in summer and can lead to increased electricity production while reducing heat supply losses. Thus far, attempts to implement adsorption refrigerators for widespread use have not been successful as a result of the low efficiency of these devices; this is directly related to the poor heat and mass transfer conditions in the beds and heat exchangers of adsorption refrigerators. The solutions used so far, such as new working pairs, glued beds or modifications to the structure or cycle length, are still not strong enough for these devices. Therefore, it is necessary to look for new solutions. Using micro- and nanobubbles as media to increase mass and heat transfer in refrigerators is an innovative and pioneering solution. Thus, this document describes the most important features of micro- and nanobubble technology applications in adsorption refrigerators. This article is an introduction and a basis for the implementation of further research, consolidating the existing literature as a review.

show abstract

Section: Technological Advancements In Adsorption Refrigeration: Impr...mentioning

confidence: 99%

Review of Micro- and Nanobubble Technologies: Advancements in Theory and Applications and Perspectives on Adsorption Cooling and Desalination Systems

Lasek,

Krzywanski,

Skrobek

et al. 2023

Energies

Self Cite

View full text Add to dashboard Cite

show abstract

“…The efficiency of cooling-desalination systems depends on several parameters, mainly on the sorption processes in the adsorbent bed [12][13][14] and the operating conditions, that is, the temperature and mass flow rates of cooling, hot and chilled water. [15][16][17] The evaporation of the refrigerant in the evaporator is the main stage of the adsorption chiller's operating cycle. The harnessing of heat from the water flowing through the heat exchanger enables the production of so-called chilled water.…”

Section: Introduction 1| Adsorption Cooling and Desalination Systemsmentioning

confidence: 99%

“…21 The possibility of improving the chiller performance using a multistage cycle was numerically shown in Ali et al 22 Artificial intelligence (AI) methods were employed to optimize adsorption processes. 16,17 The Adaptive Neuro-Fuzzy Inference System (ANFIS) was used to study the effect of the evaporator's thermal conductivity and adsorption bed on the AC performance. Simulations in ANSYS Fluent software confirmed the possibility of improving the heat transport conditions in the bonded sorbent bed.…”

Section: Introduction 1| Adsorption Cooling and Desalination Systemsmentioning

confidence: 99%

See 1 more Smart Citation

AutoML‐based predictive framework for predictive analysis in adsorption cooling and desalination systems

Krzywanski,

Sztekler,

Skrobek

et al. 2024

Energy Science & Engineering

Self Cite

View full text Add to dashboard Cite

Adsorption cooling and desalination systems have a distinct advantage over other systems that use low‐grade waste heat near ambient temperature. Since improving their performance, including reliability and failure prediction, is challenging, developing an efficient diagnostic system is of great practical significance. The paper introduces artificial intelligence (AI) and an automated machine learning approach (AutoML) in a real‐life application for a computational diagnostic system of existing adsorption cooling and desalination facilities. A total of 1769 simulated data points containing data indicating a failure status are applied to develop a comprehensive AI‐based Diagnostic (AID) system covering a wide range of 42 input parameters. The paper introduces a conditional monitoring system for adsorption cooling and desalination systems. The novelty of the presented study mainly consists of two aspects. First, the intelligent system predicts the health or failure states of various components in a complex three‐bed adsorption chiller installation using the extensive input data sets of 42 different operating parameters. The developed AID expert tool, based on selecting the best from 42 models generated by the DataRobot platform, was validated on the complex, existing three‐bed adsorption chiller. The AID system correctly identified healthy and failure states in various installation components. The developed expert system is very efficient (AUC = 0.988, RMSE = 0.20, LogLoss = 0.14) in predicting emergency states. The proposed method constitutes a quick and easy technique for failure prediction and represents a complementary tool compared to the other condition monitoring methods.

show abstract

“…An LSTM-based deep learning approach has been used to predict the vapor mass quantity in the adsorption bed [28]. Other machine learning mechanisms based on LSTM, Bidirectional Long Short-Term Memory (BiLSTM), and Gated Recurrent Unit (GRU) have been employed to improve the efficiency of adsorption cooling systems [29].…”

Section: Introductionmentioning

confidence: 99%

Real-time measurement-driven reinforcement learning control approach for uncertain nonlinear systems

Abouheaf

Boase

Gueaieb

et al. 2023

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Implementation of deep learning methods in prediction of adsorption processes

Cited by 53 publications

References 31 publications

Review of Micro- and Nanobubble Technologies: Advancements in Theory and Applications and Perspectives on Adsorption Cooling and Desalination Systems

Review of Micro- and Nanobubble Technologies: Advancements in Theory and Applications and Perspectives on Adsorption Cooling and Desalination Systems

AutoML‐based predictive framework for predictive analysis in adsorption cooling and desalination systems

Real-time measurement-driven reinforcement learning control approach for uncertain nonlinear systems

Contact Info

Product

Resources

About