Differences in the Tensile Properties and Failure Mechanism of PP/PE Core/Sheath Bicomponent and PP Spunbond Fabrics in Uniaxial Conditions

Wang, Hong; Jin, Xiangyu; Mao, Ningtao; Russell, Stephen J.

doi:10.1177/0040517510369403

Cited by 13 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Common features include diagnoses (comorbidities), demographics (age, sex, race, and ethnicity), medications, and lab tests. A study evaluating the RNN model REverse Time AttentIoN model (RETAIN) over Cerner Health Facts© EMR shows that using all four features provides the best result, with an average AUC of 0.823 [4].…”

Section: Background and Related Workmentioning

confidence: 99%

FRISTS: Interpretable Time Series-Based Heart Failure Risk Prediction

Lin,

Dong,

Wang

2023

Preprint

View full text Add to dashboard Cite

Heart failure is an incurable medical condition that affects millions of people globally. Developing prediction models is crucial to prevent patients from progressing to heart failure. Current heart failure prediction models struggle with achieving interpretability, a mandatory trait that allows the model to be applied in healthcare, while possessing high real-world accuracy. We introduce FRISTS, a novel HF prediction approach leveraging sequential times series-based modeling, such as long short-term memory (LSTM) networks, and feature selection. Our study utilized an extensive electronic health record (EHR) database and found that FRISTS outperformed traditional AI models (e.g., Random Forest Classifier, Logistic Regression, and Decision Tree) and more complex machine learning techniques (e.g., XGBoost, LSTM), yielding an average F1 score of 0.805 and receiver operating characteristic area under the curve (ROC AUC) value of 0.990. Our SHAP-inspired permutation method enables interpretation of the feature ranking, enhancing the result transparency and paving the way for a new class of interpretable models. This approach holds promise in enhancing clinical decision-making and patient care in the context of heart failure prevention.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

FRISTS: Interpretable Time Series-Based Heart Failure Risk Prediction

Lin,

Dong,

Wang

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…When these two parameters function together, the interaction between them led it to be complex between the process parameters and the final product [4,5]. Although the relationship between the various process parameters and the product's properties can been obtained by the method of mathematical statistics to some extent [6,7], from the simplicity and dynamic adaptability to solve this problem in manufacturing processes, the neural network model has more obvious advantages [8]. In this paper, BP neural network predictive model had been established using part of experiment data as training samples and others as testing samples to check the model.…”

Section: Bp Neural Network Modelmentioning

confidence: 99%

Study on Spunlaced Nonwoven Fabric’s Moisture Absorption and Permeability Based on BP Network

Jiao

2011

AMR

View full text Add to dashboard Cite

Using BP neural network, a predictive model has been set up between the parameters of spunlaced nonwoven fabric and its two important performances which were the moisture permeability and absorption. The results showed the model was very ideal. Based on this, various parameters corresponding to the optimal values were obtained through computer simulation, that while the viscose content was 80% and the surface density was 58g/m2, the maximum permeability was 6627.3 g/m2. d and the horizontal moisture absorption also reached the maximum of 22.41cm. While the viscose content was100% and the surface density was 68g/m2, the vertical moisture absorption reached the maximum of 19.1429cm. In the end, the PCA was used to integrate the three properties into one target and the optimal parameters were also obtained, which viscose content was 80 % and surface density was 58g/m2 .Besides, according to the method of the computer simulation, a variety of different spunlaced nonwovens also can be obtained to meet different needs, which could be a reference in the future production and experiments.

show abstract

Uniaxial tensile investigation of a porous compound nonwoven fabric

Tang

Hong-fei

et al. 2018

Polymers for Advanced Techs

View full text Add to dashboard Cite

Carbon fiber (CF) nonwoven fabric possesses excellent chemical resistance, remarkable electrical properties, and low density, but its mechanical strength must be enhanced to facilitate its application. Therefore, a flexible compound nonwoven fabric (CEF-NF) consisting of CF and a bicomponent polypropylene/polyethylene core/sheath fiber (known as ESF) was prepared using a 2-step wet papermaking/ thermal bonding process. Scanning electron microscopy observations indicated that the CEF-NF fibrous network could be strengthened without blocking its pores by using a heat-pressing temperature falling between the melting regions of the sheath polyethylene and core polypropylene. Additionally, uniaxial tensile experiments were conducted to investigate the failure mode and tensile properties of the CEF-NF by varying the thermal bonding and structural parameters. The results showed that 3 failure modes of fiber physical contact separation, thermal bond breakage, and ESF fracture emerged and could be defined based on the variation in the heat-pressing temperature. The tensile strength of the CEF-NF was improved with increasing thermal bonding and structural parameters. Under a set of process parameters, ie, 180°C heat-pressing temperature, 6-MPa heat-pressing pressure, 40 wt% ESF mass fraction, and 40-gsm areal density, the tensile strength of CEF-NF reached 5.7 MPa, which is much higher than that of pure CF nonwoven fabric.

show abstract

Differences in the Tensile Properties and Failure Mechanism of PP/PE Core/Sheath Bicomponent and PP Spunbond Fabrics in Uniaxial Conditions

Cited by 13 publications

References 15 publications

FRISTS: Interpretable Time Series-Based Heart Failure Risk Prediction

FRISTS: Interpretable Time Series-Based Heart Failure Risk Prediction

Study on Spunlaced Nonwoven Fabric’s Moisture Absorption and Permeability Based on BP Network

Uniaxial tensile investigation of a porous compound nonwoven fabric

Contact Info

Product

Resources

About