首页|Chongqing University of Science and Technology Reports Findings in Machine Learn ing (Understanding of Wetting Mechanism Toward the Sticky Powder and Machine Lea rning in Predicting Granule Size Distribution Under High Shear Wet Granulation)
Chongqing University of Science and Technology Reports Findings in Machine Learn ing (Understanding of Wetting Mechanism Toward the Sticky Powder and Machine Lea rning in Predicting Granule Size Distribution Under High Shear Wet Granulation)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News-New research on Machine Learning is th e subject of a report. According to newsreporting originating from Chongqing, People's Republic of China, by NewsRx correspondents, researchstated, "The granu lation of traditional Chinese medicine (TCM) has attracted widespread attention, thereis limited research on the high shear wet granulation (HSWG) and wetting mechanisms of sticky TCMpowders, which profoundly impact the granule size distr ibution (GSD). Here we investigate the wettingmechanism of binders and the infl uence of various parameters on the GSD of HSWG and establish a GSDprediction mo del."Our news editors obtained a quote from the research from the Chongqing Universit y of Scienceand Technology, "Permeability and contact angle experiments combine d with molecular dynamics (MD)simulations were used to explore the wetting mech anism of hydroalcoholic solutions with TCM powder.Machine learning (ML) was emp loyed to build a GSD prediction model, feature importance explained theinfluenc e of features on the predictive performance of the model, and correlation analys is was used toassess the influence of various parameters on GSD. The results sh ow that water increases powder viscosity,forming high-viscosity aggregates, whi le ethanol primarily acted as a wetting agent. The contact angleof water on the powder bed was the largest and decreased with an increase in ethanol concentrat ion.Extreme Gradient Boosting (XGBoost) outperformed other models in overall pr ediction accuracy in GSDprediction, the binder had the greatest impact on the p redictions and GSD, adjusting the amount andconcentration of adhesive can contr ol the adhesion and growth of granules while the impeller speed hadthe least in fluence on granulation."
ChongqingPeople's Republic of ChinaA siaCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
