<i>k</i>‐Means Clustering for Prediction of Tensile Properties in Carbon Fiber‐Reinforced Polymer Composites

Kurita, Hiroki; Suganuma, Masanori; Wang, Yinli; Narita, Fumio

doi:10.1002/adem.202101072

Cited by 13 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kurita et al 119 applied k‐means method to predict the Young's modulus and ultimate tensile strength of carbon‐fiber‐reinforced polymers with different porosities and carbon fiber orientation. And the comparison with test results shows its effectiveness on prediction of mechanical and physical properties without any material tests.…”

Section: Ml‐based Methods For Fatigue Life Prediction Of Am Metalsmentioning

confidence: 99%

Recent developments and future trends in fatigue life assessment of additively manufactured metals with particular emphasis on machine learning modeling

Zhan,

He,

Tang

et al. 2023

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

Additive manufacturing (AM) has emerged as a very promising technology for producing complex metallic components with enhanced design flexibility. However, the mechanical properties and fatigue behavior of AM metals differ significantly from conventionally manufactured materials, thereby presenting challenges in accurately predicting their fatigue life. This study provides a comprehensive overview of recent developments and future trends in fatigue life prediction of AM metals, with a particular emphasis on machine learning (ML) modeling techniques. This review recalls recent developments and achievements in fatigue characteristics of AM metals, ML‐based approaches for fatigue life prediction of AM metals, and non‐ML‐based methodologies for the same purpose. In particular, some commonly used regression and classification techniques for fatigue evaluation of AM metals are summarized and elaborated. The study intends to furnish researchers, engineers, and practitioners in the field of AM with a guidance for the accurate and efficient prediction of fatigue life in AM metal components.

show abstract

Section: Ml‐based Methods For Fatigue Life Prediction Of Am Metalsmentioning

confidence: 99%

Recent developments and future trends in fatigue life assessment of additively manufactured metals with particular emphasis on machine learning modeling

Zhan,

He,

Tang

et al. 2023

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

show abstract

“…The K-means algorithm has a relatively simple principle and usually obtains stable clustering results, which has good applications in biological research [13], material analysis [14], etc. However, the method also has an obvious drawback: its initial center value is generated randomly, which cannot guarantee that the final result can converge to the globally optimal solution; therefore, in order to improve the effect of the K-means algorithm in power equipment fault data analysis, it needs to be improved.…”

Section: K-means Algorithmmentioning

confidence: 99%

Study on the Analysis of Fault Data During Intelligent Operation of Power Equipment With Cluster Analysis

2023

IJOMAM

View full text Add to dashboard Cite

Many fault-related data are generated in the intelligent operation of power equipment, and analyzing these data can help understand the operating condition of the equipment. This paper studied the clustering analysis methods and introduced K-means, kernel C-means (KCM), and fuzzy kernel C-means (FKCM) methods. The gray wolf optimization (GWO) algorithm was used to optimize the initial clustering center and kernel parameters of the FKCM algorithm to obtain the GWO-FKCM algorithm. Experiments were conducted taking transformer data as an example. It was found that the GWO-FKCM algorithm obtained the optimal clustering results at the 763rd iteration, and its accuracy rates for different fault types were all above 90%, with an average value of 92.92%, which was higher than the other clustering analysis methods. The results prove the reliability of the GWO-FKCM algorithm for equipment fault data analysis. This algorithm can be promoted and applied in actual power equipment.

show abstract

“…With the discovery of many novel 2D crystals, traditional numerical simulations to predict their properties have some drawbacks. Hence, it will be necessary to conduct integrated research in computer sciences, [116,117] which will become the dominant means for modelling and predicting the properties of small and lightweight structures in the near future. In addition, as mentioned earlier, wearable sensors will become smaller and smaller, however such small devices will face the problem of [108] Copyright 2020, Wiley-VCH.…”

Section: Prospectivementioning

confidence: 99%

Self‐Powered Wearable Piezoelectric Monitoring of Human Motion and Physiological Signals for the Postpandemic Era: A Review

Wang

Wei

et al. 2022

Adv Materials Technologies

Self Cite

View full text Add to dashboard Cite

populations. Moreover, with the advent of the novel coronavirus disease (COVID-19), significant investment in medical resources is required. Under the umbrella of the global COVID-19 pandemic, the use of biosensors in healthcare and online medical care are becoming ubiquitous, which represent methods that can be used to detect signs from the human body for further health analysis. Furthermore, the internet of things (IoT) technology in healthcare is a method by which biosensorembedded objects can be worn on the human body in everyday life that continuously measure and digitize health information without any burden to the wearer. [1] Recently, various biometric technologies have been developed, wearable devices such as smart watches, invasive biodevices, and devices that sense the everyday surrounding environment of the wearer. Medical data can be collected using such devices, which can then be further analyzed by artificial intelligence (AI). These data can then be used for health promotion, prevention of disease, and early disease diagnosis. Moreover, with the advent of COVID-19, healthcare IoT (HIoT) technology has become extremely important. [2] In terms of the individual, when a mask is constantly worn it may cause lung damage to the user. Therefore, the HIoT would make a significant contribution in this case to offer forewarning about the situations of the lungs As society advances, the shift from passive medical care to health management and preventive medical care has become an important issue, with the realization of wearable monitors becoming desirable. In light of the COVID-19 pandemic, the number of patients who are in urgent need of the monitoring of biological information is increasing. This review focuses on piezoelectric materials and composites that convert kinetic energy into electrical energy to realize self-powered wearable monitoring sensors, outlining the recent research activity on sensors for use in healthcare monitoring. First, a general description of the principles of piezoelectric monitoring sensors is given. Next, the development status of piezoelectric materials and composites aimed at the application of detecting tiny motions of the human body is introduced, and then the research trends on the detection of larger human body movements are highlighted. Finally, after presenting the performance of current piezoelectric sensors and future research guidelines for developing multifunctional systems in the post COVID-19 era, the achievements are summarized. Overall, this review will provide guidance to researchers who are seeking to design and develop highly sensitive self-powered piezoelectric sensors that monitor human motion and physiological signals.The ORCID identification number(s) for the author(s) of this article can be found under https://doi.org/10.1002/admt.202200318.

show abstract

k‐Means Clustering for Prediction of Tensile Properties in Carbon Fiber‐Reinforced Polymer Composites

Cited by 13 publications

References 23 publications

Recent developments and future trends in fatigue life assessment of additively manufactured metals with particular emphasis on machine learning modeling

Recent developments and future trends in fatigue life assessment of additively manufactured metals with particular emphasis on machine learning modeling

Study on the Analysis of Fault Data During Intelligent Operation of Power Equipment With Cluster Analysis

Self‐Powered Wearable Piezoelectric Monitoring of Human Motion and Physiological Signals for the Postpandemic Era: A Review

Contact Info

Product

Resources

About