Explainable IAOA-CNN-CBAM-SVR model for predicting air consumption of auxiliary nozzles with limited sample size

Min Shen, Yongbo Cao, Xiaoshuang Xiong, Zhen Wang, Lianqing Yu, Xuezheng Yang, Yongfa Lv · 2026

Read Explainable IAOA-CNN-CBAM-SVR model for predicting air consumption of auxiliary nozzles with limited sample size by Min Shen, Yongbo Cao, Xiaoshuang Xiong, Zhen Wang, Lianqing Yu, Xuezheng Yang, Yongfa Lv (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0351109.txt.

Description

Min Shen and colleagues built an explainable model to predict air use by helper nozzles on air jet looms, machines that weave with blasts of air. Helper nozzles burn nearly four fifths of a looms air, yet data to train models are scarce. Their hybrid joins image style networks, attention, and a classic regressor, tuned by an improved search algorithm.

The hybrid beat all simpler rivals, explaining over ninety nine percent of variation in air use on tests. Explanation plots ranked which nozzle shape traits drive air use most. Loom makers can cut energy bills at the drawing board by reshaping the greediest traits first, with the model showing its reasoning.

Catalog record

CREATORMin Shen, Yongbo Cao, Xiaoshuang Xiong, Zhen Wang, Lianqing Yu, Xuezheng Yang, Yongfa Lv
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE61519
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0351109

Browse the full library · About the Tower of Babel