Software platform for high-fidelity-data-based artificial neural network modeling and process optimization in chemical engineering

Moon, Jiyoung; Gbadago, Dela Quarme; Hwang, Gang Uk; Lee, Dongjun; Hwang, Sungwon

doi:10.1016/j.compchemeng.2021.107637

Cited by 8 publications

(6 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The grid search method [37] was employed to enhance the accuracy of the models, thereby eliminating the possibility of obtaining suboptimal models generally obtained via the conventional trial-and-error approach to model netuning [23,24]. The grid search methodology represents a fundamental algorithmic approach for hyperparameter tuning [38].…”

Section: Hyperparameter Optimizationmentioning

confidence: 99%

Deep Learning for Green Chemistry: An AI-Enabled Pathway for Biodegradability Prediction and Organic Material Discovery

Gbadago,

Hwang,

Lee

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

The increasing global demand for eco-friendly products is driving innovation in sustainable chemical synthesis, particularly the development of biodegradable substances. Herein, a novel method utilizing artificial intelligence (AI) to predict the biodegradability of organic compounds is presented, overcoming the limitations of traditional prediction methods that rely on laborious and costly density functional theory (DFT) calculations. We propose leveraging readily available molecular formulas and structures represented by simplified molecular-input line-entry system (SMILES) notation and molecular images to develop an effective AI-based prediction model using state-of-the-art machine learning techniques, including deep convolutional neural networks (CNN) and long-short term memory (LSTM) learning algorithms, capable of extracting meaningful molecular features and spatiotemporal relationships. The model is further enhanced with reinforcement learning (RL) to better predict and discover new biodegradable materials by rewarding the system for identifying unique and biodegradable compounds. The combined CNN-LSTM model achieved an 87.2% prediction accuracy, outperforming CNN- (75.4%) and LSTM-only (79.3%) models. The RL-assisted generator model produced approximately 60% valid SMILES structures, with over 80% being unique to the training dataset, demonstrating the model's capability to generate novel compounds with potential for practical application in sustainable chemistry. The model was extended to develop novel electrolytes with desired molecular weight distribution.

show abstract

Section: Hyperparameter Optimizationmentioning

confidence: 99%

Deep Learning for Green Chemistry: An AI-Enabled Pathway for Biodegradability Prediction and Organic Material Discovery

Gbadago,

Hwang,

Lee

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Also, 𝑡𝑡 𝑏𝑏 does not have any impact on the calculation of ℎ using Eqs. ( 5) to (7). Among 200 input data, 35% and 15% are chosen randomly for the training and validation, respectively.…”

Section: Motivation and Problem Descriptionmentioning

confidence: 99%

“…The neural network learns the input-output patterns from the training dataset, the trained performance is assessed using the validation dataset, and finally the accuracy of the network is evaluated using the testing dataset [6]. The output transferred from the 𝑘𝑘th neuron of the (𝑛𝑛 − 1)th layer to the 𝑗𝑗th neuron of the 𝑛𝑛th layer is described as follows [7]:…”

Section: Introductionmentioning

confidence: 99%

Prediction Accuracy of Artificial Neural Networks in Thermal Management Applications Subject to Neural Network Architectures

Randriambololona¹,

Shaeri²,

Sarabi³

2022

Proceedings of the 8th World Congress on Mechanical, Chemical, and Material Engineering

View full text Add to dashboard Cite

The present study investigates the dependency of prediction accuracy of an artificial neural network (ANN) on the network architecture using 65 different neural networks from seven architecture patterns. The accuracy of the ANNs is compared based on their capability to predict heat transfer coefficients of air-cooled heat sinks operating in laminar flow. Scattered input data is used for training the networks to make the modelling more realistic and closer to practical applications. The input variables for the neural network are heat sink width, channel height, channel length, number of channels, fin thickness, and Reynolds number. The output is heat transfer coefficient. The training process for all ANNs is performed using ReLU as the activation function. The accuracy of the neural networks is evaluated by the root mean square error. It is found that the prediction accuracy of an ANN is strongly dictated by the optimization of the network architecture, which corresponds to the proper number of hidden layers and the number of neurons at each layer. The most accurate architecture in the present study predicts heat transfer coefficients of 60% and 86% of heat sinks within ±10% and ±20% of the true values, respectively. However, an ANN with an unoptimized architecture results in a substantially reduced accuracy such that it predicts heat transfer coefficients of only 19% and 30% of heat sinks within ±10% and ±20% of the true values, respectively.

show abstract

“…As an alternative approach, machine learning (ML), an artificial intelligence (AI) method, can be used. By ML, the hidden trends and relationships in data can be discovered for solving complex problems . Machine learning methods can be divided into two broad categories: supervised learners and unsupervised learners.…”

Section: Introductionmentioning

confidence: 99%

“…By ML, the hidden trends and relationships in data can be discovered for solving complex problems. 24 Machine learning methods can be divided into two broad categories: supervised learners and unsupervised learners. Supervised learning develops a predictive model based on both input and output data by using training data with known labels.…”

Section: ■ Introductionmentioning

confidence: 99%

Enhanced Copolymer Characterization for Polyethers Using Gel Permeation Chromatography Combined with Artificial Neural Networks

et al. 2023

View full text Add to dashboard Cite

Gel permeation chromatography (GPC) is a generally applied method for the mass analysis of various polymers and copolymers, but it inherently fails to provide additional important information such as the composition of copolymers. However, we will show that GPC measurements using different solvents can yield not just the correct molecular weight but the composition of the copolymer. Accordingly, artificial neural networks (ANNs) have been developed to process the data of GPC measurements and determine the molecular weight and the chemical composition of the copolymers. The target values of the ANNs were obtained by matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) and nuclear magnetic resonance (NMR) spectroscopy. Our GPC–ANN method is demonstrated by the analysis of various poloxamers, i.e., poly(ethylene oxide) (PEO)–poly(propylene oxide) (PPO) block copolymers. Two ANNs were constructed. The first one (ANN_1) works in a wider mass range (from 900 to 12,500 dalton), while the second one (ANN_2) produces more output values. ANN_2 can thus predict seven characteristic copolymer parameters, namely, two average molecular weights, the average weight fraction of the EO unit, and four average numbers of the repeat units. The correlation between the experimentally obtained outputs and the predicted ones is high (r > 0.98). The accuracy of the ANNs is very convincing, and both ANNs predict the number-average molecular weight (M n) with an accuracy below 5%. Furthermore, this work is the first step for creating an open database and applications extending the use of the GPC–ANN method for the analysis of copolymers.

show abstract

Software platform for high-fidelity-data-based artificial neural network modeling and process optimization in chemical engineering

Cited by 8 publications

References 51 publications

Deep Learning for Green Chemistry: An AI-Enabled Pathway for Biodegradability Prediction and Organic Material Discovery

Deep Learning for Green Chemistry: An AI-Enabled Pathway for Biodegradability Prediction and Organic Material Discovery

Prediction Accuracy of Artificial Neural Networks in Thermal Management Applications Subject to Neural Network Architectures

Enhanced Copolymer Characterization for Polyethers Using Gel Permeation Chromatography Combined with Artificial Neural Networks

Contact Info

Product

Resources

About