Tool condition monitoring framework for predictive maintenance: a case study on milling process

Traini, Emiliano; Bruno, Giulia; Lombardi, Franco

doi:10.1080/00207543.2020.1836419

Cited by 46 publications

(8 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, it is desirable to have a methodology that can automatically filter the signal of interest. Traini et al [12] recently utilized the change point detection approach to select the stationary window in which the machining process has been taken. However, the methodology proposed in this study is complex and accuracy dependent on a threshold parameter, α.…”

Section: Data Filtering and Outlier Removalmentioning

confidence: 99%

“…Health indicators [5] TD: Mean FD: Mean TFD: Wavelet packet energy [6] TD: Root mean square, Variance, Skewness, Kurtosis, Peak, Peak-to-Peak FD: Peak-to-Peak, Spectral skewness, Spectral kurtosis TFD: Wavelet packet energy [12] TD: Max, Mean, RMS, Standard deviation, Skewness, Kurtosis, Peak-to-Peak, Crest factor FD: Max, Sum, Mean, Standard deviation, Skewness, Kurtosis, Relative spectral peak per band [11] TD: RMS, Kurtosis, Peak, Peak-to-Peak, Crest factor Pr(wear…”

Section: Referencesmentioning

confidence: 99%

“…The proposed TEKELM overcomes the shortcomings of KELM for preselecting the kernel function and its hyperparameter. Traini et al [12] extracted various time-domain, frequency-domain and polynomial regression coefficients based HIs for tool wear monitoring. Among extracted HIs, best HIs were selected using a few criterions such as (a) removing HIs with low coefficient of variation, (b) removing the HIs with low correlation coefficients, (c) hypothesis testing and (d) removing HIs with low prognosability and monotonicity.…”

Section: Introductionmentioning

confidence: 99%

“…An inverse hyperbolic cosine function was fitted to enveloped signal for sensitivity enhancement, and later the obtained signal was used for HI construction. Using the obtained HI, the existing machine learning (ML) models such as artificial neural network (ANN) [13,14], kernel extreme learning machine (KELM) [5,15], convolution neural network (CNN) [4,16], random forest regression (RFR) [12], recurrent neural network (RNN) [11], long short term memory (LSTM) [6,11,16,17], deep belief network [13], transfer learning [18,19], etc. can be used for tool wear prediction.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A novel current sensor indicator enabled WAFTR model for tool wear prediction under variable operating conditions

Kundu

Luo

Qin

et al. 2022

Journal of Manufacturing Processes

View full text Add to dashboard Cite

Section: Data Filtering and Outlier Removalmentioning

confidence: 99%

Section: Referencesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A novel current sensor indicator enabled WAFTR model for tool wear prediction under variable operating conditions

Kundu

Luo

Qin

et al. 2022

Journal of Manufacturing Processes

View full text Add to dashboard Cite

“…e data-driven methodology for evaluating tool wear status and predicting tool RUL has been explained through the use of real-time sensor data analysis combined with a machine-learning algorithm [23]. e reliability and availability analysis of the Uncaser system of the beer manufacturing process in the brewery production plant has investigated and analyzed the entire subsystems using MBDP and MATLAB software to predict the most critical subsystems in the brewery production plant [24].…”

Section: Review Of Literaturementioning

confidence: 99%

Availability Analysis of the Critical Production System in SMEs Using the Markov Decision Model

Velmurugan

Saravanasankar

Venkumar³

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Small and medium-sized enterprises (SMEs) in today’s world have numerous issues in ensuring the availability and safety of critical machines and their components in the working environment. As a result, SMEs considered planning and scheduling maintenance tasks to be a significant threat. The goal of this research is to identify the critical subsystem of the automobile spare parts production plant in the southern region of Tamil Nadu, India, and then to prioritize the maintenance activity and set up an architecture for autonomous preventive maintenance (PM) in SMEs that includes an optimal decision support system. The transition state diagram of the individual and simultaneous production system has been developed with the application of the Markov decision model approach. It was used to analyze the present variables of the production systems and forecast the optimal maintenance parameters such as the failure rate and the repair rate, through the production system’s availability analysis. This availability analysis reveals that system B (Piercing) is classified as the most critical because of the abrupt availability variation compared to all other production systems, concerning the corresponding maintenance parameters such as a failure rate of 0.0371, a repair rate of 0.7094, and the availability of the piercing system of 0.5056. Finally, the use of an autonomous PM management system and the most effective maintenance workforce has enhanced productivity and customer satisfaction in SMEs. The predictive maintenance management system has been further investigated to determine the real-time remaining useful life (RUL) of critical systems in the automobile spare parts manufacturing plant in the southern region of Tamil Nadu, India.

show abstract

A security‐enhanced equipment predictive maintenance solution for the ETO manufacturing

Cao,

Jing,

Zhao

et al. 2024

Int J Network Mgmt

View full text Add to dashboard Cite

SummaryWith the rapid advancement of intelligent manufacturing, ensuring equipment safety has become a crucial prerequisite for enterprise production. In the engineer‐to‐order (ETO) production mode, characterized by diverse equipment types and frequent adjustments in production lines, equipment maintenance has become increasingly complex. Traditional maintenance plans are no longer adequate to meet the evolving demands of equipment maintenance. This paper proposes a security‐enhanced predictive maintenance scheme specifically designed for ETO‐type production equipment. The scheme utilizes industrial Internet of Things (IIoT) technology to monitor machines and equipment, constructs prediction models using machine learning methods, and reinforces the security of the prediction system through adoption of a decentralized architecture with blockchain distributed storage. In this experiment, six supervised learning models were compared, and it was found that the model based on the random forest algorithm achieved an outstanding accuracy rate of 98.88%. Furthermore, the average total response time for generating predictions within the system is 2.0 s, demonstrating a performance suitable for practical equipment maintenance applications.

show abstract

Tool condition monitoring framework for predictive maintenance: a case study on milling process

Cited by 46 publications

References 48 publications

A novel current sensor indicator enabled WAFTR model for tool wear prediction under variable operating conditions

A novel current sensor indicator enabled WAFTR model for tool wear prediction under variable operating conditions

Availability Analysis of the Critical Production System in SMEs Using the Markov Decision Model

A security‐enhanced equipment predictive maintenance solution for the ETO manufacturing

Contact Info

Product

Resources

About