Cutting tool remaining useful life prediction based on robust empirical mode decomposition and Capsule-BiLSTM network

Sun, Liangshi; Zhao, Chengying; Huang, Xianzhen; Ding, Pengfei; Li, Yuxiong

doi:10.1177/09544062221142197

Cited by 6 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By incorporating gated attention mechanism and Bayesian layer, Zhao et al [204] further improved the prediction performance of CapsNet and quantified the uncertainty. In addition, [205][206][207] also combined CapsNet with LSTM to enhance the ability to capture long-term dependencies between features.…”

Section: Cutting-edge Methods In DLmentioning

confidence: 99%

A comprehensive survey of machine remaining useful life prediction approaches based on pattern recognition: taxonomy and challenges

Zhou,

Yang,

Qian

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Predictive maintenance (PdM) is currently the most cost-effective maintenance method for industrial equipment, offering improved safety and availability of mechanical assets. A crucial component of PdM is the remaining useful life (RUL) prediction for machines, which has garnered increasing attention. With the rapid advancements in industrial Internet of Things (IoT) and artificial intelligence (AI) technologies, RUL prediction methods, particularly those based on pattern recognition (PR) technology, have made significant progress. However, a comprehensive review that systematically analyzes and summarizes these state-of-the-art PR-based prognostic methods is currently lacking. To address this gap, this paper presents a comprehensive review of PR-based RUL prediction methods. Firstly, it summarizes commonly used evaluation indicators based on accuracy metrics, prediction confidence metrics, and prediction stability metrics. Secondly, it provides a comprehensive analysis of typical machine learning methods and deep learning networks employed in RUL prediction. Furthermore, it delves into cutting-edge techniques, including advanced network models and frontier learning theories in RUL prediction. Finally, the paper concludes by discussing the current main challenges and prospects in the field. The intended audience of this article includes practitioners and researchers involved in machinery PdM, aiming to provide them with essential foundational knowledge and a technical overview of the subject matter.

show abstract

Section: Cutting-edge Methods In DLmentioning

confidence: 99%

A comprehensive survey of machine remaining useful life prediction approaches based on pattern recognition: taxonomy and challenges

Zhou,

Yang,

Qian

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Different from traditional neural networks, which rely on neurons for information transmission, capsule network utilizes vectorized capsules as fundamental units, offering distinct advantages [34]. This design empowers capsule networks to efficiently extract crucial information by leveraging vector representation to preserve spatial relationships among features.…”

Section: Capsnetmentioning

confidence: 99%

A multi-scale spatial–temporal capsule network based on sequence encoding for bearing fault diagnosis

Wang,

Chen

2024

Complex Intell. Syst.

View full text Add to dashboard Cite

The Capsule Network (CapsNet) has been shown to have significant advantages in improving the accuracy of bearing fault identification. Nevertheless, the CapsNet faces challenges in identifying the type of bearing fault under nonstationary and noisy conditions. These challenges arise from the distinctive nature of its dynamic routing algorithm and the use of fixed single-scale kernels. To address these challenges, a multi-scale spatial–temporal capsule network (MSCN) based on sequence encoding is proposed for bearing fault identification under nonstationary and noisy environments. A spatial–temporal sequence encoding module focuses on feature correlations at various times and positions. Dilated convolution-based multiscale capsule layer (MCaps) is designed to capture spatial–temporal features at different scales. MCaps establishes connections between various layers, enhancing the comprehension and interpretation of spatial–temporal features. Furthermore, the Bhattacharyya coefficient is introduced into the dynamic routing to compare the similarity between capsules. The validity of the model is verified through comparative experiments, and the results show that MSCN has significant advantages over traditional methods.

show abstract

“…Pendekatan ini dapat membantu siswa memahami penerapan praktis sains dan memotivasi mereka untuk belajar lebih banyak. Selain itu, teknik berbasis pembelajaran mendalam telah diterapkan pada prediksi sisa masa manfaat (RUL) pada peralatan kompleks, seperti sistem penerbangan dan ruang angkasa (Sun et al, 2022;Sun et al, 2023). Kemajuan ilmu pengetahuan dan teknologi ini berkontribusi pada pengembangan peralatan yang lebih andal, aman, dan stabil, sehingga memberikan manfaat bagi berbagai industri dan sektor.…”

Section: Gambar 4 Respon Terhadap Aspek Kelancaranunclassified

Implementasi Pembelajaran Berbasis Sikap Ilmiah dan Keterampilan Proses Sains: Bagaimana Respon Mahasiswa Rumpun Non-Sains?

Syazali,

Erfan

2023

JIPP

View full text Add to dashboard Cite

Learning based on scientific attitudes and scientific process skills is common among science students. However, this learning is almost never applied to non-science students, especially Primary School Teacher Education (PGSD) students at Mataram University. The aim of this research is to describe student responses to the implementation of learning based on these two aspects of science. This descriptive research using the survey method was carried out on PGSD students who were taking Basic Natural Sciences (IKD) courses in the odd semester of the 2021-2022 Academic Year. The sample consisted of 167 students who were determined using the purposive sampling method. Response data on learning implementation was measured using a questionnaire instrument which was distributed to respondents via a link in the Google Form application. Based on the survey results, we found that 53.3% of students stated that they had studied science through the research process, and the results were written in the form of scientific papers. As for the impression, the response from all students was positive. The details were 17.4% felt very happy, 53.3% were happy, and the remaining 29.3% answered quite happy. This is encouraged because they benefit from learning based on process skills and scientific attitudes. However, there are still 15.6% of students who experience difficulties in the process. The cause is the obstacles experienced by most of them (87.4%), and there are also students (6%) who feel that the time given is not enough. Some of the difficulties experienced by students include finding research problems (25.1%), formulating titles (26.9%), designing research activities (18%), and collecting data (29.9%). When writing scientific papers, the greatest difficulty lies in writing results and discussion (63.5%), followed by writing research methods (19.8), and the rest is in writing the abstract, introduction, conclusion and bibliography. The sample paper media used can help students in writing papers, but as many as 95.2% of students need additional facilities to practice their writing skills.

show abstract

Cutting tool remaining useful life prediction based on robust empirical mode decomposition and Capsule-BiLSTM network

Cited by 6 publications

References 37 publications

A comprehensive survey of machine remaining useful life prediction approaches based on pattern recognition: taxonomy and challenges

A comprehensive survey of machine remaining useful life prediction approaches based on pattern recognition: taxonomy and challenges

A multi-scale spatial–temporal capsule network based on sequence encoding for bearing fault diagnosis

Implementasi Pembelajaran Berbasis Sikap Ilmiah dan Keterampilan Proses Sains: Bagaimana Respon Mahasiswa Rumpun Non-Sains?

Contact Info

Product

Resources

About