Intelligent prediction model of ammonia solubility in designable green solvents based on microstructure group contribution

Liu, Tianxiong; Chu, Xiaojun; Fan, Dingchao; Ma, Zhaoyuan; Dai, Yasen; Zhu, Zhaoyou; Wang, Yinglong; Gao, Jun

doi:10.1080/00268976.2022.2124203

Cited by 7 publications

(6 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI techniques for STLF have grown in popularity in the last several years. For instance, machine learning-based approaches have been employed, including Support Vector Machines (SVM) [20,21], Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) [22]; artificial neural networks (ANN), BP neural networks [23,24], the deep neural network (DNN) algorithm [25] and deep learning-based methods are also used, including the Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and improved models by various scholars, etc. These methods show broad application prospects in short-term load forecasting.…”

Section: Related Workmentioning

confidence: 99%

An Improved WOA (Whale Optimization Algorithm)-Based CNN-BIGRU-CBAM Model and Its Application to Short-Term Power Load Forecasting

Dai,

Wang

2024

Energies

View full text Add to dashboard Cite

The accuracy requirements for short-term power load forecasting have been increasing due to the rapid development of the electric power industry. Nevertheless, the short-term load exhibits both elasticity and instability characteristics, posing challenges for accurate load forecasting. Meanwhile, the traditional prediction model suffers from the issues of inadequate precision and inefficient training. In this work, a proposed model called IWOA-CNN-BIGRU-CBAM is introduced. To solve the problem of the Squeeze-and-Excitation (SE) attention mechanism’s inability to collect information in the spatial dimension effectively, the Convolutional Block Attention Module (CBAM) is firstly introduced as a replacement. This change aims to enhance the ability to capture location attributes. Subsequently, we propose an improved Whale Optimization Algorithm (IWOA) that addresses its limitations, such as heavy reliance on the initial solution and susceptibility to local optimum solutions. The proposed IWOA is also applied for the hyperparameter optimization of the Convolutional Neural Network–Bidirectional Gated Recurrent Unit–Convolutional Block Attention Module (CNN-BiGRU-CBAM) to improve the precision of predictions. Ultimately, applying the proposed model to forecast short-term power demand yields results that show that the CBAM effectively addresses the problem of the SE attention mechanism’s inability to capture spatial characteristics fully. The proposed IWOA exhibits a homogeneous dispersion of the initial population and an effective capability to identify the optimal solution. Compared to other models, the proposed model improves R2 by 0.00224, reduces the RMSE by 18.5781, and reduces MAE by 25.8940, and the model’s applicability and superiority are validated.

show abstract

Section: Related Workmentioning

confidence: 99%

An Improved WOA (Whale Optimization Algorithm)-Based CNN-BIGRU-CBAM Model and Its Application to Short-Term Power Load Forecasting

Dai,

Wang

2024

Energies

View full text Add to dashboard Cite

show abstract

“…In the manufacture of fertilizers and chemical materials, the poisonous and reactive gas known as NH 3 is an important starting material. Consequently, the removal of NH 3 from the atmosphere to safeguard the ecosystem and restore resources is paramount . A novel IL/MOF composite was created by Liu et al to extract NH 3 from humid and dry air.…”

Section: Il/mof Composites For Adsorptionmentioning

confidence: 99%

“…Consequently, the removal of NH 3 from the atmosphere to safeguard the ecosystem and restore resources is paramount. 260 A novel IL/MOF composite was created by Liu et al 261 to extract NH 3 from humid and dry air. The NH 3 uptake of [BOHMIM][Zn 2 Cl 5 ]/MIL-101(Cr) (540.29 cm 3 /g) was two times that of MIL-101(Cr) (199.81 cm 3 /g).…”

Section: Incorporated [Bmim][bf 4 ] Intomentioning

confidence: 99%

Ionic Liquids Functionalized MOFs for Adsorption

et al. 2023

View full text Add to dashboard Cite

Metal–organic frameworks (MOFs) and ionic liquids (ILs) represent promising materials for adsorption separation. ILs incorporated into MOF materials (denoted as IL/MOF composites) have been developed, and IL/MOF composites combine the advantages of MOFs and ILs to achieve enhanced performance in the adsorption-based separation of fluid mixtures. The designed different ILs are introduced into the various MOFs to tailor their functional properties, which affect the optimal adsorptive separation performance. In this Perspective, the rational fabrication of IL/MOF composites is presented, and their functional properties are demonstrated. This paper provides a critical overview of an emergent class of materials termed IL/MOF composites as well as the recent advances in the applications of IL/MOF composites as adsorbents or membranes in fluid separation. Furthermore, the applications of IL/MOF in adsorptive gas separations (CO2 capture from flue gas, natural gas purification, separation of acetylene and ethylene, indoor pollutants removal) and liquid separations (separation of bioactive components, organic-contaminant removal, adsorptive desulfurization, radionuclide removal) are discussed. Finally, the existing challenges of IL/MOF are highlighted, and an appropriate design strategy direction for the effective exploration of new IL/MOF adsorptive materials is proposed.

show abstract

“…Most ML methods expect learning examples to be described by vectors of numbers or nominal values. Quantitative structure–activity relationship models are an efficient representation of this approach 18–20 . For example, many models had been reported to predict the refractive index, viscosity, and conductivity of ILs 21,22 .…”

Section: Introductionmentioning

confidence: 99%

Prediction of CO₂ solubility in ionic liquids via convolutional autoencoder based on molecular structure encoding

et al. 2023

Self Cite

View full text Add to dashboard Cite

In this study, novel molecular structure encoding descriptors composed of feature encoding and one‐hot encoding was developed and then convolutional autoencoder was used to denoise based on the structure of ionic liquids (ILs). It could be used to predict the CO2 solubility in ILs at different temperatures and pressures, when combined with three different machine learning algorithms (multilayer perceptron [MLP], random forest [RF], and support vector machine [SVM]). Statistics of the prediction results show that the newly proposed molecular structure‐based coding has better regression prediction performance than the conventional molecular cheminformatics descriptors. SE‐MLP model with R2 of 0.9873 and mean square error of 0.0007 has the best performance in predicting the CO2 solubility in ILs. In addition, the relationship between features and dissolved CO2 capacity was analyzed through model interpretation to retrieve physical insights for the underlying system. This work provided a new predictive tool for enriching and refining data on CO2 solubility in ILs and for solving phase equilibrium problems.

show abstract

Intelligent prediction model of ammonia solubility in designable green solvents based on microstructure group contribution

Cited by 7 publications

References 46 publications

An Improved WOA (Whale Optimization Algorithm)-Based CNN-BIGRU-CBAM Model and Its Application to Short-Term Power Load Forecasting

An Improved WOA (Whale Optimization Algorithm)-Based CNN-BIGRU-CBAM Model and Its Application to Short-Term Power Load Forecasting

Ionic Liquids Functionalized MOFs for Adsorption

Prediction of CO₂ solubility in ionic liquids via convolutional autoencoder based on molecular structure encoding

Contact Info

Product

Resources

About

Intelligent prediction model of ammonia solubility in designable green solvents based on microstructure group contribution

Cited by 7 publications

References 46 publications

An Improved WOA (Whale Optimization Algorithm)-Based CNN-BIGRU-CBAM Model and Its Application to Short-Term Power Load Forecasting

An Improved WOA (Whale Optimization Algorithm)-Based CNN-BIGRU-CBAM Model and Its Application to Short-Term Power Load Forecasting

Ionic Liquids Functionalized MOFs for Adsorption

Prediction of CO2 solubility in ionic liquids via convolutional autoencoder based on molecular structure encoding

Contact Info

Product

Resources

About

Prediction of CO₂ solubility in ionic liquids via convolutional autoencoder based on molecular structure encoding