&lt;p&gt;A Multiple-Regression Model for Monitoring Tool Wear with a Dynamometer in
            Milling Operations&lt;/p&gt;

Chen, Jacob C.; Chen, Joseph C.

doi:10.21061/jots.v30i4.a.11

Cited by 19 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fisher‐Pry curve fitting is applied to the different sets of data collected. This is done by using the ordinary least squares (OLS) regression in MicrosoftExcel (Chen and Chen, 2004).…”

Section: Data Analysis and Research Modelmentioning

confidence: 99%

See 1 more Smart Citation

Time lag assessment between research funding and output in emerging technologies

et al. 2007

View full text Add to dashboard Cite

PurposeIn this paper, an analysis is presented of the research funding towards nanotechnology at the National Nanotechnology Initiative (NNI) and its relationship to the research output in Nanoscope, an application area of nanotechnology.Design/methodology/approachThe paper analyzes the data collected from 1997 till 2006 and derives a definitive time lag between the allocation of research funds and issued patents and published journals. This assessment is achieved by identifying growth trends in patents, funds and publications and doing a curve‐fit analysis using the Fisher‐Pry model. Linear regression analysis is used to show the correlation between the funding and research outputs. Alongside, non‐linear programming objective function optimization technique is used to derive the time lag in years for each of the research outputs from the year of funds granted.FindingsThis paper demonstrated that there is a strong correlation between research funding and different research outputs. The time lag between funding and patents issued is evident from the patent trend analysis and Bibliometric analysis. In the case of Nanoscope, the patent time lag was found to be approximately five to six years, for journal article it was approximately two to three years and conference presentations happened right after the funding. The research outputs showed similar trends and were found to be interdependent as evident from our mathematical analysis.Research limitations/implicationsWhile this study has shown that lag times exist within the chosen example of Nanoscope, and furthermore can be calculated to a precise degree, further data points in terms of additional emerging technologies would support the hypothesis in a more general term. A future study can look at developing technology roadmaps of the future based on the funding happening today.Originality/valueThe work takes bibliometric analysis to a further intelligence and establishes key linkages between these indicators.

show abstract

“…Fisher‐Pry curve fitting is applied to the different sets of data collected. This is done by using the ordinary least squares (OLS) regression in MicrosoftExcel (Chen and Chen, 2004).…”

Section: Data Analysis and Research Modelmentioning

confidence: 99%

“…In order to show that, we collect data for research funding and research publications and fit it to appropriate growth curve. The time lag is predicted through linear regression analysis and maximizing coefficients of determination (R‐Square) (Chen and Chen, 2004) after applying a time shift to align the curves.…”

Section: Introductionmentioning

confidence: 99%

Time lag assessment between research funding and output in emerging technologies

et al. 2007

View full text Add to dashboard Cite

show abstract

“…ML techniques and algorithms incorporate embedded techniques for diagnosing non-linear and irregular systematic failures with random cause failure events such as irregular wear loss, fatigue, cracks, and others [32] - [35]. ML techniques (e.g., supervised regression with kernel functions and unsupervised artificial neural networks) can adapt rapidly, compared to BN and DBD when predicting the integrity loss of critical railway rolling stock subsystems subjected to systematic failures with temporal random events [35], [44] - [48]. However, ML sometimes suffers from lack of accuracy, inconsistency, and discrepancies when multiple sources and different weights are considered simultaneously [29] - [31].…”

Section: Bayesian Network (Bn) and Dynamic Bayesian Discretisation (Dbd)mentioning

confidence: 99%

Composite Hybrid Framework for Through-Life Multi-Objective Failure Analysis and Optimisation

Appoh

Yunusa‐Kaltungo

2021

IEEE Access

View full text Add to dashboard Cite

Complex engineering systems include several subsystems that interact in a stochastic and multifaceted manner with multiple failure modes (FMs). The dynamic nature of FMs introduces uncertainties that negatively impact the reliability, risk, and maintenance of complex systems. Traditional approaches of adopting standalone techniques for managing FMs independently at various stages of the asset life cycle pose challenges related to utilisation, costs, availability, and in some cases, accidents. Therefore, this paper proposes a composite hybrid framework comprising four independent hybrid models for comprehensive through-life failure management and optimisation. The first hybrid model entails failure mode, effects, and criticality analysis (FMECA) and fault tree analysis (FTA) to identify critical FMs and overall subsystem failure rates. The second hybrid model analyses FMs caused by multiple subsystems using hybrid dynamic Bayesian discretisation. The third hybrid model adopts a hybrid Gaussian process regression machine learning technique to evaluate wear loss. The fourth hybrid model evaluates the overall risk using a Bayesian factorisation and elimination method based on multiple failure causes. Finally, a decision-making step is used to evaluate the results of the previous four steps to decide an appropriate maintenance strategy. The proposed method is verified through a case study of a UK-based train operator's pantograph system. The results show that the maintenance inspection intervals and strategy obtained using the proposed framework strike a good balance between safety and fleet availability.

show abstract

“…A major goal of the manufacturing industry is increasing the quality of the product. The quality of a product is strongly associated with the condition of the cutting tool that produces it [1].…”

Section: Introductionmentioning

confidence: 99%

Tool wear and tool life estimation based on linear regression learning

Karuppusamy

Lee

et al. 2015

2015 IEEE International Conference on Mechatronics and Automation (ICMA)

View full text Add to dashboard Cite

Tools have remained an integral part of the society without which stimulation of certain aspects of human evolution would not have been possible. In recent times the modern tools are used in the manufacturing of high precision components. We know that the accuracy and surface finish of these components can be achieved only by the usage of accurate tools. Sharp edged tools may loosen their sharpness due to repeated usage and machining parameters. Hence to address this issue we propose a system to monitor tool wear by using the captured image of cutting tool tip. We used vision system since it is the primitive method of predicting tool wear and two main machining parameters feed rate and depth of cut. The image of flank wear cutting edge at tool tip is captured by examining under profile projector. The system uses linear regression model to calculate tool wear which is mapped onto continuous 2-D coordinates with feed rate and depth of cut as axis from a captured digital image. Thus the proposed intelligent system uses profile projector and digital image processing methods to estimate tool wear continuously and predictively like humans rather than using strict rules. By estimating tool wear continuously the machine can better perform and machine components accurately by using the resultant values of feed rate and depth of cut as a threshold which are arrived as a result.

show abstract

<p>A Multiple-Regression Model for Monitoring Tool Wear with a Dynamometer in Milling Operations</p>

Cited by 19 publications

References 13 publications

Time lag assessment between research funding and output in emerging technologies

Time lag assessment between research funding and output in emerging technologies

Composite Hybrid Framework for Through-Life Multi-Objective Failure Analysis and Optimisation

Tool wear and tool life estimation based on linear regression learning

Contact Info

Product

Resources

About