Interpreting tree-based prediction models and their data in machining processes

Bustillo, Andrés; Grzenda, Maciej; Macukow, Bohdan

doi:10.3233/ica-160513

Cited by 16 publications

(11 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some complex manufacturing problems like laser polishing (Bustillo et al 2011b), maintenance planning of five-axis milling (Freiburg et al 2014), laser micromachining of cavities (Teixidor et al 2015), and deep drilling (Bustillo et al 2016) have been successfully modeled using regression trees. In all these cases, the decision trees create models that are as accurate as other standard machine-learning techniques, such as ANNs, and are suitable for both continuous and discrete outputs.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, the analysis of how these models can provide useful and immediate information for the process engineer is considered: in some cases, such as regression or decision trees, this information can be directly extracted from the model structure, but in other cases, such as ANN models, interpretation of the black-box structure is not easy and the development of 3D charts becomes necessary (Bustillo et al 2016). …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence for automatic prediction of required surface roughness by monitoring wear on face mill teeth

2017

View full text Add to dashboard Cite

Nowadays, face milling is one of the most widely used machining processes for the generation of flat surfaces. Following international standards, the quality of a machined surface is measured in terms of surface roughness, Ra, a parameter that will decrease with increased tool wear. So, cutting inserts of the milling tool have to be changed before a given surface quality threshold is exceeded. The use of artificial intelligence methods is suggested in this paper for real-time prediction of surface roughness deviations, depending on the main drive power, and taking tool wear, V B into account. This method ensures comprehensive use of the potential of modern CNC machines that are able to monitor the main drive power, N , in real-time. It can likewise estimate the three parameters -maximum tool wear, machining time, and cutting power-that are required to generate a given surface roughness, thereby making the most efficient use of the cutting tool. A series of artificial intelligence methods are tested: random forest (RF), standard Multilayer perceptrons (MLP), Regression Trees, and radial-based functions. Random forest was shown to have the highest model accuracy, followed by regression trees, displaying higher accuracy than the standard MLP and the radial-basis function. Moreover, RF techniques are easily tuned and generate visual information for direct use by the process engineer, such as the linear relationships between process parameters and roughness, and thresholds for avoiding rapid tool wear. All of this information can be directly extracted from the tree structure or by drawing 3D charts plotting two process inputs and the predicted roughness depending on workshop requirements. Keywords

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Artificial intelligence for automatic prediction of required surface roughness by monitoring wear on face mill teeth

2017

View full text Add to dashboard Cite

show abstract

“…The decision trees and regression methods are the approaches to establish predictive models [ 27 , 28 ]. In the literature [ 29 ], a prediction model of ore crushing plate lifetimes was proposed based on the decision trees and artificial neural networks.…”

Section: Methodsmentioning

confidence: 99%

Semi-Empirical Prediction of Residual Stress Distributions Introduced by Turning Inconel 718 Alloy Based on Lorentz Function

et al. 2020

View full text Add to dashboard Cite

The residual stress of machined surface has a crucial influence on the performance of parts. It results in large deviations in terms of the position accuracy, dimension accuracy and service life. The purpose of the present study is to provide a novel semi-empirical residual stress prediction approach for turning Inconel 718. In the method, the bimodal Lorentz function was originally applied to express the residual stress distribution. A statistical model between the coefficients of the bimodal Lorentz function and cutting parameters was established by the random forest regression, in order to predict the residual stress distribution along the depth direction. Finally, the turning experiments, electrolytic corrosion peeling, residual stress measurement and correlation analysis were carried out to verify the accuracy of predicted residual stress. The results show that the bimodal Lorentz function has a great fitting accuracy. The adjusted R2 (Ad-R2) are ranging from 95.4% to 99.4% and 94.7% to 99.6% in circumferential and axial directions, respectively. The maximum and minimum errors of the surface residual tensile stress (SRTS) are 124.564 MPa and 18.082 MPa, those of the peak residual compressive stress (PRCS) are 84.649 MPa and 3.009 MPa and those of the depth of the peak residual compressive stress (DPRCS) are 0.00875 mm and 0.00155 mm, comparing three key feature indicators of predicted and simulated residual stress. The predicted residual stress is highly correlated with the measured residual stress, with correlation coefficients greater than 0.8. In the range of experimental measurement error, the research in the present work provides a quite accurate method for predicting the residual stress in turning Inconel 718, and plays a vital role in controlling the machining deformation of parts.

show abstract

“…Bustillo et al proposed a visualization technique using knowledge of industrial engineering for representing conditional inference trees. This visualization demonstrates the prediction data and models during machining processes to support engineers' decisionmakings [17].…”

Section: Qualitative Assessments Of Tool-chainsmentioning

confidence: 99%

A domain-specific modeling approach supporting tool-chain development with Bayesian network models

Wang

Tao

et al. 2020

ICA

View full text Add to dashboard Cite

Constructing and evaluating a comprehensive tool-chain with commercial off-the-shelf and proprietary tools for the deployment of model-based systems engineering (MBSE) is a challenging and complex task. Specifically, the lack of early assessment during tool-chain development has led to increased research and development costs when unexpected features are developed or poor decisions are made. In this paper, a domain-specific modeling (DSM) approach is proposed to support decision-makings during tool-chain design and to facilitate quantitative assessment of tool-chain features at early-phases. Using this approach, different views of tool-chains are first formalized under a DSM framework. Then the DSM models are transformed to Bayesian network models for supporting the quantitative assessment of related tools in order to analyze the whole tool-chains' features. In the case study, the approach is verified by comparing two MBSE tool-chains for an auto-braking system design. The results indicate that the DSM approach enhances the understanding of tool-chain concepts, promotes the efficiency of MBSE tool-chain development, and verifies the tool-chain in early development phases using a quantitative approach.

show abstract

Interpreting tree-based prediction models and their data in machining processes

Cited by 16 publications

References 63 publications

Artificial intelligence for automatic prediction of required surface roughness by monitoring wear on face mill teeth

Artificial intelligence for automatic prediction of required surface roughness by monitoring wear on face mill teeth

Semi-Empirical Prediction of Residual Stress Distributions Introduced by Turning Inconel 718 Alloy Based on Lorentz Function

A domain-specific modeling approach supporting tool-chain development with Bayesian network models

Contact Info

Product

Resources

About