Optimization and design of machine learning computational technique for prediction of physical separation process

A data driven machine learning approach for predicting and optimizing sulfur compound adsorption on metal organic frameworks

This study employed some machine learning (ML) techniques with Python programming to forecast the adsorption capacity of MOF adsorbents for thiophenic compounds namely benzothiophene (BT), dibenzothiophene (DBT), and 4,6-dimethyl dibenzothiophene (4,6-DMDBT). Five ML models were developed with the help of a dataset containing 676 rows to correlate the adsorbent features, adsorption conditions, and adsorbate characteristics to the MOF sample's sulfur adsorption capability. Among the ML approaches, MLP model achieved the best performance with a low mean squared error (MSE) of 0.0032 on the test set and 0.0021 on the training set and mean relative error (MRE) of 15.26% on the test set. Also, Random Forest model yielded a higher test MSE of 0.0045 and MRE of 17.83%. Feature importance analysis was performed by utilizing MLP model and shapely additive plan (SHAP) method, and the findings revealed that "initial concentration of sulfur" (SHAP value 0.51) and "contact time" (SHAP value 0.37) were the crucial factors influenced desulfurization process efficiency. Additionally, a comparative analysis of the features utilizing the MLP network classified the factors into three primary categories: process conditions, adsorbent characteristics, and adsorbate characteristics. Consequently, the process condition was identified as the most significant group compared to others. Finally, the desulfurization process optimization indicated the maximum DBT adsorption of 161.6 mg/g for Zr-based MOF could be achieved when the features including BET, TPV, pore size, oil/adsorbent ration, and temperature were tuned around 756 m2/g, 0.955 cm3/g, 5.96 nm, 449.85 g/g, 20.1 °C, respectively.

A Novel Method for Full-Section Assessment of High-Speed Railway Subgrade Compaction Quality Based on ML-Interval Prediction Theory

The high-speed railway subgrade compaction quality is controlled by the compaction degree (K), with the maximum dry density (ρdmax) serving as a crucial indicator for its calculation. The current mechanisms and methods for determining the ρdmax still suffer from uncertainties, inefficiencies, and lack of intelligence. These deficiencies can lead to insufficient assessments for the high-speed railway subgrade compaction quality, further impacting the operational safety of high-speed railways. In this paper, a novel method for full-section assessment of high-speed railway subgrade compaction quality based on ML-interval prediction theory is proposed. Firstly, based on indoor vibration compaction tests, a method for determining the ρdmax based on the dynamic stiffness Krb turning point is proposed. Secondly, the Pso-OptimalML-Adaboost (POA) model for predicting ρdmax is determined based on three typical machine learning (ML) algorithms, which are back propagation neural network (BPNN), support vector regression (SVR), and random forest (RF). Thirdly, the interval prediction theory is introduced to quantify the uncertainty in ρdmax prediction. Finally, based on the Bootstrap-POA-ANN interval prediction model and spatial interpolation algorithms, the interval distribution of ρdmax across the full-section can be determined, and a model for full-section assessment of compaction quality is developed based on the compaction standard (95%). Moreover, the proposed method is applied to determine the optimal compaction thicknesses (H0), within the station subgrade test section in the southwest region. The results indicate that: (1) The PSO-BPNN-AdaBoost model performs better in the accuracy and error metrics, which is selected as the POA model for predicting ρdmax. (2) The Bootstrap-POA-ANN interval prediction model for ρdmax can construct clear and reliable prediction intervals. (3) The model for full-section assessment of compaction quality can provide the full-section distribution interval for K. Comparing the H0 of 50~60 cm and 60~70 cm, the compaction quality is better with the H0 of 40~50 cm. The research findings can provide effective techniques for assessing the compaction quality of high-speed railway subgrades.