A weighted hidden Markov model approach for continuous-state tool wear monitoring and tool life prediction

Yu, Jing; Liang, Shuang; Tang, Diyin; Liu, Hao

doi:10.1007/s00170-016-9711-0

Cited by 85 publications

(35 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cutting force, which is originated by the shearing of the material, friction between the chip and the cutter and so on, can convey key information on the conditions of machining processes. The cutting forces can reflect the machinability of the material [ 1 , 2 ] or used to identify machining malfunctions, such as machining vibrations [ 3 , 4 ] or tool wear [ 5 ]. Therefore, measuring cutting forces in the machining process is fundamental for condition monitoring and process optimization [ 6 , 7 ].…”

Section: Introductionmentioning

confidence: 99%

Cutting Forces Measurement for Milling Process by Using Working Tables with Integrated PVDF Thin-Film Sensors

Luo

Chong

Liu

2018

Sensors

View full text Add to dashboard Cite

In the milling process, cutting forces contain key information about the machining process status in terms of workpiece quality and tool condition. On-line cutting force measurement is key for machining condition monitoring and machined surface quality assurance. This paper presents a novel instrumented working table with integrated polyvinylidene fluoride (PVDF) thin-film sensors, thus enabling the dynamic milling force measurement with compact structures. To achieve this, PVDF thin-film sensors are integrated into the working table to sense forces in different directions and the dedicated cutting force decoupling model is derived. A prototype instrumented working table is developed and validated. The validation demonstrates that profiles of the forces measured from the developed instrumented working table prototype and the dynamometer match well. Furthermore, the milling experiment results convey that the instrumented working table prototype could also identify the tool runout due to tool manufacturing or assembly errors, and the force signal spectrum analysis indicates that the developed working table can capture the tool passing frequency correctly, therefore, is suitable for the milling force measurement.

show abstract

Section: Introductionmentioning

confidence: 99%

Cutting Forces Measurement for Milling Process by Using Working Tables with Integrated PVDF Thin-Film Sensors

Luo

Chong

Liu

2018

Sensors

View full text Add to dashboard Cite

show abstract

“…Many studies have applied ANNs and HMMs to TCM in milling processes with outstanding results [33], [51], [52]. Deep neural networks such as CNNs [53], [54] and RNNs [55], [56] have also been applied with considerable success.…”

Section: B Monitoring Modelmentioning

confidence: 99%

Tool Wear Condition Monitoring in Milling Process Based on Current Sensors

Zhou

Sun

2020

IEEE Access

View full text Add to dashboard Cite

Accurate tool condition monitoring (TCM) is essential for the development of fully automated milling processes. This is typically accomplished using indirect TCM methods that synthesize the information collected from one or more sensors to estimate tool condition based on machine learning approaches. Among the many sensor types available for conducting TCM, motor current sensors offer numerous advantages, in that they are inexpensive, easily installed, and have no effect on the milling process. Accordingly, this study proposes a new TCM method employing a few appropriate current sensor signal features based on the time, frequency, and time − frequency domains of the signals and an advanced monitoring model based on an improved kernel extreme learning machine (KELM). The selected multidomain features are strongly correlated with tool wear condition and overcome the loss of useful information related to tool condition when employing a single domain. The improved KELM employs a two-layer network structure and an angle kernel function that includes no hyperparameter, which overcome the drawbacks of KELM in terms of the difficulty of learning the features of complex nonlinear data and avoiding the need for preselecting the kernel function and its hyperparameter. The performance of the proposed method is verified by its application to the benchmark NASA milling dataset and separate TCM experiments in comparison with existing TCM methods. The results indicate that the proposed TCM method achieves excellent monitoring performance using only a few key signal features of current sensors. INDEX TERMS Tool condition monitoring (TCM), milling process, current sensor, kernel extreme learning machine (KELM), angle kernel.

show abstract

“…As mentioned above, the mean wear depth is necessary to determine the intensity of the Markov process as equation (21). In the above section, the average wear depth is calculated by an estimate of the 50th percentile of the measured growth rate distribution.…”

Section: Wear Depth Growth Rate Distributionmentioning

confidence: 99%

Markov stochastic process modeling for evolution of wear depth in steam generator tubes

Wei

et al. 2019

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Reliability of steam generator is a serious concern in the operation of nuclear power plants, especially for steam generator tubes that experience a variety of degradation mechanisms including wear damage. It is necessary to develop a model to accurately predict wear depth of tubes for the assessment and management of steam generator aging. In this article, a non-homogeneous Markov process model of wear is proposed to assess the evaluation of wear depth in steam generator tubes. Based on the analytical solutions of the system of Kolmogorov's forward equations, the transition probability functions are computed to estimate the future wear depth distribution. The parameters are estimated under the assumption that the mean wear depths in the proposed Markov stochastic model are equal to the average of measured depths. The time evolution of wear depth distribution can be predicted. The proposed Markov stochastic model was tested with the in-service inspection records from steam generator tube inspection report, and the results showed a good agreement with future wear depth distribution.

show abstract

A weighted hidden Markov model approach for continuous-state tool wear monitoring and tool life prediction

Cited by 85 publications

References 26 publications

Cutting Forces Measurement for Milling Process by Using Working Tables with Integrated PVDF Thin-Film Sensors

Cutting Forces Measurement for Milling Process by Using Working Tables with Integrated PVDF Thin-Film Sensors

Tool Wear Condition Monitoring in Milling Process Based on Current Sensors

Markov stochastic process modeling for evolution of wear depth in steam generator tubes

Contact Info

Product

Resources

About