Accurate modeling and prediction of surface roughness by computer vision in turning operations using an adaptive neuro-fuzzy inference system

Ho, Shinn‐Ying; Lee, Kuang Chyi; Chen, Shih Shin

doi:10.1016/s0890-6955(02)00078-0

Cited by 111 publications

(44 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For micro and macro milling operations different modeling techniques have been applied for tool wear or part quality estimation and they include response surfaces [8,[22][23][24][25], and Artificial Intelligence (AI) models such as Artificial Neural Networks (ANN) [8, 11-13, 15, 23-27], Adaptive Neuro Fuzzy Inference Systems (ANFIS) [28,29], Fuzzy Systems [12,30,31], Hidden Markov Models (HMM) [24], Bayesian Networks (BN) [32,33] and Least Squares Support Vector Machines (LS-SVM) [34][35][36]. Comprehensive reviews about modeling techniques applied in machining can be found in [19,37,38].…”

Section: Estimation Modulementioning

confidence: 99%

Adaptive control optimization in micro-milling of hardened steels—evaluation of optimization approaches

Coppel

Abellán-Nebot

Siller

et al. 2015

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Nowadays, the miniaturization of many consumer products is extending the use of micro-milling operations with high quality requirements. However, the impacts of cutting-tool wear on part dimensions, form and surface integrity are not negligible and part quality assurance for a minimum production cost is a challenging task. In fact, industrial practices usually set conservative cutting parameters and early cutting replacement policies in order to minimize the impact of cutting-tool wear on part quality. Although these practices may ensure part integrity, the production cost is far away to be minimized, especially in highly tool-consuming operations like mold and die micromanufacturing. In this paper, an Adaptive Control Optimization (ACO) system is proposed to estimate cutting-tool wear in terms of part quality and adapt the cutting conditions accordingly in order to minimize the production cost, ensuring quality specifications in hardened steel micro-parts. The ACO system is based on: i) a monitoring sensor system composed of a dynamometer; ii) an estimation module with Artificial Neural Networks models; iii) an optimization module with evolutionary optimization algorithms; and iv) a CNC interface module. In order to operate in a nearly real time basis and facilitate the implementation of the ACO system, different evolutionary optimization algorithms are evaluated such as Particle Swarm Optimization (PSO), Genetic Algorithms (GA) and Simulated Annealing (SA) in terms of accuracy, precision and robustness. The results for a given micro-milling operation showed that PSO algorithm performs better than GA and SA algorithms under computing time constraints. Furthermore, the implementation of the final ACO system reported a decrease in the production cost of 12.3% and 29% in comparison with conservative and high production strategies, respectively.

show abstract

Section: Estimation Modulementioning

confidence: 99%

Adaptive control optimization in micro-milling of hardened steels—evaluation of optimization approaches

Coppel

Abellán-Nebot

Siller

et al. 2015

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…The network is composed of a number of functional nodes which are self-configured to form an optimal network hierarchy by using a predicted square error criterion. Ho et al [17] proposed a method to establish the relationship between the features of surface image and the actual surface roughness using an adaptive neuro-fuzzy inference system (ANFIS). It can consequently predict surface roughness using cutting parameters such as speed, feed, and depth of cut and gray level of the surface image.…”

Section: Literature Surveymentioning

confidence: 99%

Surface roughness prediction in turning using artificial neural network

Pal

Chakraborty

2005

Neural Comput & Applic

View full text Add to dashboard Cite

In this work, a back propagation neural network model has been developed for the prediction of surface roughness in turning operation. A large number of experiments were performed on mild steel work-pieces using high speed steel as the cutting tool. Process parametric conditions including speed, feed, depth of cut, and the measured parameters such as feed and the cutting forces are used as inputs to the neural network model. Roughness of the machined surface corresponding to these conditions is the output of the neural network. The convergence of the mean square error both in training and testing came out very well. The performance of the trained neural network has been tested with experimental data, and found to be in good agreement.

show abstract

“…An adaptive control with the on-line surface roughness prediction model could be capable of controlling the surface roughness in real time [11]. Some systems with designed mechanism to control the surface roughness have been developed for turning operations [12,13], with only a few for milling operations [14].…”

Section: Introductionmentioning

confidence: 99%

Simulation and Visual Control of Chip Size for Constant Surface Roughness

Zuperl¹,

Cus²

2015

Int. j. simul. model.

View full text Add to dashboard Cite

A visual cutting chip control system is designed to automatically adjust feed rate in order to maintain constant surface roughness in ball-end milling. The proposed visual control system has a modular structure, consisting of an optical vision system (OVS), an adaptive cutting chip size-control loop for a feed servo and a surface roughness in-process prediction model. The OVS is employed to acquire the cutting chip sizes form the camera. A division controller is used to control the chip size by modifying the feed rate and consequently maintaining surface roughness constant. Surface roughness is predicted based on the detected chip size. The efficiency of the chip control strategy is tested by series of simulation with various step changes in the cutter/workpiece contact area. For simulation purposes an experimentally validated milling plant simulator with an adopted feed servo drive model and a cutting chip size model is employed. An adaptive neural inference system (ANFIS) is established to effectively simulate the cutting chip size in ball end-milling. In simulation, the reference chip size and consequently the reference surface roughness are well maintained when the cutting-depth profile of a workpiece is varying step-wise or continuously.

show abstract

Accurate modeling and prediction of surface roughness by computer vision in turning operations using an adaptive neuro-fuzzy inference system

Cited by 111 publications

References 10 publications

Adaptive control optimization in micro-milling of hardened steels—evaluation of optimization approaches

Adaptive control optimization in micro-milling of hardened steels—evaluation of optimization approaches

Surface roughness prediction in turning using artificial neural network

Simulation and Visual Control of Chip Size for Constant Surface Roughness

Contact Info

Product

Resources

About