Development of a fuzzy-nets-based in-process surface roughness adaptive control system in turning operations

This paper discusses the development of an in-process surface roughness adaptive control system for a CNC turning operation, using fuzzy-nets modeling and tool vibrations measured with an accelerometer. The goal of this system is to predict the surface roughness of a surface being turned, determine if the surface roughness being generated is higher than the desired specification, and if so to adapt the feed rate of the turning operation in order to obtain a surface roughness no higher than that specified. Fuzzy-nets models for prediction of surface roughness and adapted feed rate were trained using feed rate, spindle speed, tangential vibration and measured surface roughness data collected during experimental runs. A series of validation runs indicated that the system could successfully meet its goal both in detecting out-of-spec surface roughness conditions, and adapting the machine tool to obtain a final surface roughness at or slightly below the desired surface roughness.     

Condition monitoring of CNC machining using adaptive control

In this work, an adaptive control constraint system has been developed for computer numerical control (CNC) turning based on the feedback control and adaptive control/self-tuning control. In an adaptive controlled system, the signals from the online measurement have to be processed and fed back to the machine tool controller to adjust the cutting parameters so that the machining can be stopped once a certain threshold is crossed. The main focus of the present work is to develop a reliable adaptive control system, and the objective of the control system is to control the cutting parameters and maintain the displacement and tool flank wear under constraint valves for a particular workpiece and tool combination as per ISO standard. Using Matlab Simulink, the digital adaption of the cutting parameters for experiment has confirmed the efficiency of the adaptively controlled condition monitoring system, which is reflected in different machining processes at varying machining conditions. This work describes the state of the art of the adaptive control constraint (ACC) machining systems for turning. AISI4140 steel of 150 BHN hardness is used as the workpiece material, and carbide inserts are used as cutting tool material throughout the experiment. With the developed approach, it is possible to predict the tool condition pretty accurately, if the feed and surface roughness are measured at identical conditions. As part of the present research work, the relationship between displacement due to vibration, cutting force, flank wear, and surface roughness has been examined.     

Prediction of surface roughness in ball-end milling process by utilizing dynamic cutting force ratio

The aim of this research is to propose the practical model to predict the in-process surface roughness during the ball-end milling process by utilizing the dynamic cutting force ratio. The proposed model is developed based on the experimentally obtained results by employing the exponential function with five factors of the spindle speed, the feed rate, the tool diameter, the depth of cut, and the dynamic cutting force ratio. The experimentally obtained results showed that the frequency of the dynamic cutting force corresponds with the frequency of the surface roughness profile in the frequency domain. Hence, the dimensionless dynamic cutting force ratio is proposed regardless of the cutting conditions to predict the in-process surface roughness by taking the ratio of the area of the dynamic cutting force in X axis to that in Z axis. The multiple regression analysis is adopted to calculate the regression coefficients at 95 % confident level. The experimentally obtained model has been verified by using the new cutting conditions. It is understood that the developed surface roughness model can be used to predict the in-process surface roughness with the high accuracy of 92.82 % for the average surface roughness and 91.54 % for the surface roughness.     

Modeling and adaptive force control of milling by using artificial techniques

The contribution discusses the use of combining the methods of neural networks, fuzzy logic and PSO evolutionary strategy in modeling and adaptively controlling the process of ball-end milling. On the basis of the hybrid process modeling, off-line optimization and feed-forward neural control scheme (UNKS) the combined system for off-line optimization and adaptive adjustment of cutting parameters is built. This is an adaptive control system controlling the cutting force and maintaining constant roughness of the surface being milled by digital adaptation of cutting parameters. In this way it compensates all disturbances during the cutting process: tool wear, non-homogeneity of the workpiece material, vibrations, chatter, etc. The basic control principle is based on the control scheme (UNKS) consisting of two neural identifiers of the process dynamics and primary regulator. An overall procedure of hybrid modeling of cutting process used for creating the CNC milling simulator has been prepared. The experimental results show that not only does the milling system with the design controller have high robustness, and global stability, but also the machining efficiency of the milling system with the adaptive controller is 27% higher than for traditional CNC milling system.     

Support vector machines models for surface roughness prediction in CNC turning of AISI 304 austenitic stainless steel

In the present investigation, three different type of support vector machines (SVMs) tools such as least square SVM (LS-SVM), Spider SVM and SVM-KM and an artificial neural network (ANN) model were developed to estimate the surface roughness values of AISI 304 austenitic stainless steel in CNC turning operation. In the development of predictive models, turning parameters of cutting speed, feed rate and depth of cut were considered as model variables. For this purpose, a three-level full factorial design of experiments (DOE) method was used to collect surface roughness values. A feedforward neural network based on backpropagation algorithm was a multilayered architecture made up of 15 hidden neurons placed between input and output layers. The prediction results showed that the all used SVMs results were better than ANN with high correlations between the prediction and experimentally measured values.     

Neural control strategy of constant cutting force system in end milling

This paper discusses the application of neural adaptive control strategy to the problem of cutting force control in high speed end milling operations. The research is concerned with integrating adaptive control and a standard computer numerical controller (CNC) for optimizing a metal-cutting process. It is designed to adaptively maximize the feed rate subject to allowable cutting force on the tool, which is very beneficial for a time consuming complex shape machining. The purpose is to present a reliable, robust neural controller aimed at adaptively adjusting feed rate to prevent excessive tool wear, tool breakage and maintain a high chip removal rate. Numerous simulations and experiments are conducted to confirm the efficiency of this architecture.     

In-process regressions and adaptive multicriteria neural networks for monitoring and supervising machining operations

The authors develop a monitoring and supervising system for machining operations using in-process regressions (for monitoring) and adaptive feedforward artificial neural networks (for supervising). The system is designed for: (1) in-process tool life measurement and prediction; (2) supervision of machining operations in terms of the best machining setup; and (3) catastrophic tool failure monitoring. The monitoring system predicts tool life by using different sensors for gathering information based on a regression model that allows for the variations between tools and different machine setups. The regression model makes its prediction by using the history of other tools and combining it with the information obtained about the tool under consideration. The supervision system identifies the best parameters for the machine setup problem within the framework of multiple criteria decision making. The decision maker (operator) considers several criteria, such as cutting quality, production rate and tool life. To make the optimal decision with several criteria, an adaptive feedforward artificial neural network is used to assess the decision maker's preferences. The authors' neural network approach learns from the decision maker's complex behavior and hence, in automatic mode, can make decisions for the decision maker. The approach is not computationally demanding, and experiments demonstrate that its predictions are accurate.     

Estimation of cutting forces and surface roughness for hard turning using neural networks

Metal cutting mechanics is quite complicated and it is very difficult to develop a comprehensive model which involves all cutting parameters affecting machining variables. In this study, machining variables such as cutting forces and surface roughness are measured during turning at different cutting parameters such as approaching angle, speed, feed and depth of cut. The data obtained by experimentation is analyzed and used to construct model using neural networks. The model obtained is then tested with the experimental data and results are indicated.     

Tool condition monitoring in metal cutting: A neural network approach

This paper discusses the application of neural network-based pattern recognition techniques for monitoring the metal-cutting process. The specific application considered is in-process monitoring of the condition of the cutting tool. Tool condition monitoring is an important prerequisite for successful automation of the metal cutting process. In this paper, we demonstrate the application of supervised and unsupervised neural network paradigms to pattern recognition of sensor signal features. The supervised technique used is backpropagation and the unsupervised technique used is adaptive resonance theory (ART). The results support the premise that, despite excellent classification accuracy by both networks, the unsupervised system holds greater promise in a real world setting. The advantages are discussed and a framework for exploiting them in tool condition monitoring systems is presented.This work was completed as part of graduate research at University of California, Berkeley, Department of Mechanical Engineering.     

MACHINED SURFACE ROUGHNESS PREDICTION USING ADAPTIVE NEUROFUZZY INFERENCE SYSTEM

This work considers the effect of the depth of cut, feed, and number of revolutions on the roughness of the machined surface. The results obtained by experimentally investigating the workpiece “diving manifold” were used to model the input/output data plan for the adaptive neurofuzzy inference system (ANFIS). Those data were used to generate a fuzzy inference system that made it possible to predict the output (surface roughness) based on the given inputs (feed, number of revolutions, and depth of cut). The surface roughness results obtained by the fuzzy inference system (FIS) were compared with the surface roughness results obtained by neural networks, moving linear least square method and moving linear least absolute deviation method on the same set of experimental data. These methods and systems for prediction of surface roughness are helpful when solving practical technological problems in a manufacturing process, first by determining the cutting parameter values that will add to the demanded quality of a product, and later when optimizing the technological process.     

Udwadia-Kalaba Equation Based Adaptive Robust Control for Two-wheeled Inverted Pendulum System: Underactuation and Uncertainty

A new adaptive robust control method based on Udwadia-Kalaba(U-K) approach which can be applied to the underactuated system is designed and used to a two-wheeled inverted pendulum system in this paper. We separate this typical underactuated system into two subsystems(forward subsystem and yaw subsystem), which are fully underactuated and actuated. For these different subsystems, we use different control methods. We apply an adaptive robust control method which has been proved many times to the fully actuated subsystem. Based on this adaptive robust method, a new control strategy can be redesigned and applied to the underactuated subsystem by modifying the adaptive law and other things. This adaptive robust control with a leakage-type adaptive law could guarantee the uniform boundedness and uniform ultimate boundedness of the system. Finally, the simulation is executed to demonstrate the advantage and simplicity of the proposed method.

     

Surface roughness prediction in turning using artificial neural network

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.     

Adaptive dynamic programming-based adaptive-gain sliding mode tracking control for fixed-wing unmanned aerial vehicle with disturbances

This article proposes an adaptive dynamic programming-based adaptive-gain sliding mode control (ADP-ASMC) scheme for a fixed-wing unmanned aerial vehicle (UAV) with matched and unmatched disturbances. Starting from the dynamic of fixed-wing UAV, the control-oriented model composed of attitude subsystem and airspeed subsystem is established. According to the different issues in two subsystems, two novel adaptive-gain generalized super-twisting (AGST) algorithms are developed to eliminate the effects of disturbances in two subsystems and make the system trajectories tend to the designed integral sliding manifolds in finite time. Then, based on the expected equivalent sliding-mode dynamics, the modified adaptive dynamic programming approach with actor-critic structure is utilized to generate the nearly optimal control laws and achieve the nearly optimal performance of the sliding-mode dynamics. Furthermore, through the Lyapunov stability theorem, the tracking errors and the weight estimation errors of two neural networks are all uniformly ultimately bounded. Finally, comparative simulations demonstrate the superior performance of the proposed control scheme for the fixed-wing UAV.     

Prediction of stable cutting depths in turning operation using soft computing methods

This article suggests soft computing methods to predict stable cutting depths in turning operations without chatter vibrations. Chatter vibrations cause poor surface finish. Therefore, preventing these vibrations is an important area of research. Predicting stable cutting depths is vital to determine the stable cutting region. In this study, a set of cutting experiments has been used and the stable cutting depths are predicted as a function of cutting, modal and tool-working material parameters. Regression analyses, artificial neural networks (ANN) decision trees and heuristic optimization models are used to develop the generalization models. The purpose of the models is to estimate stable cutting depths with minimum error. ANN produces better results compared to the other models. This study helps operators and engineers to perform turning operations in an appropriate cutting region without chatter vibrations. It also helps to take precautions against chatter.     

Effect of tool vibrations on surface roughness during lathe dry turning process

Choice of optimized cutting parameters is very important to control the required surface quality. In fact, the difference between the real and theoretical surface roughness can be attributed to the influence of physical and dynamic phenomena such as: built-up edge, friction of cut surface against tool point and vibrations. The focus of this study is the collection and analysis of surface roughness and tool vibration data generated by lathe dry turning of mild carbon steel samples at different levels of speed, feed, depth of cut, tool nose radius, tool length and work piece length. A full factorial experimental design (288 experiments ) that allows to consider the three-level interactions between the independant variables has been conducted. Vibration analysis has revealed that the dynamic force, related to the chip-thickness variation acting on the tool, is related to the amplitude of tool vibration at resonance and to the variation of the tool's natural frequency while cutting. The analogy of the effect of cutting parameters between tool dynamic forces and surface roughness is also investigated. The results show that second order interactions between cutting speed and tool nose radius, along with third-order interaction between feed rate, cutting speed and depth of cut are the factors with the greatest influence on surface roughness and tool dynamic forces in this type of operation and parameter levels studied. The analysis of variance revealed that the best surface roughness condition is achieved at a low feed rate (less than 0.35 mnt/rev), a large tool nose radius (1.59 mm) and a high cutting speed (265 m/min and above). The results also show that the depth of cut has not a significant effect on surface roughness, except when operating within the built-up edge range. It is shown that a correlation between surface roughness and tool dynamic force exist only when operating in the built-up edge range. In these cases, built-u edge formation deteriorates surface roughness and increases dynamic forces acting on the tool. The effect of built-up edge formation on surface roughness can be minimized by increasing depth of cut and increasing tool vibration. Key words:design of experiments, lathe dry turning operation, full factorial design, surface roughness, measurements, cutting parameters, tool vibrations.     

Design of neural network-based estimator for tool wear modeling in hard turning

Hard turning with cubic boron nitride (CBN) tools has been proven to be more effective and efficient than traditional grinding operations in machining hardened steels. However, rapid tool wear is still one of the major hurdles affecting the wide implementation of hard turning in industry. Better prediction of the CBN tool wear progression helps to optimize cutting conditions and/or tool geometry to reduce tool wear, which further helps to make hard turning a viable technology. The objective of this study is to design a novel but simple neural network-based generalized optimal estimator for CBN tool wear prediction in hard turning. The proposed estimator is based on a fully forward connected neural network with cutting conditions and machining time as the inputs and tool flank wear as the output. Extended Kalman filter algorithm is utilized as the network training algorithm to speed up the learning convergence. Network neuron connection is optimized using a destructive optimization algorithm. Besides performance comparisons with the CBN tool wear measurements in hard turning, the proposed tool wear estimator is also evaluated against a multilayer perceptron neural network modeling approach and/or an analytical modeling approach, and it has been proven to be faster, more accurate, and more robust. Although this neural network-based estimator is designed for CBN tool wear modeling in this study, it is expected to be applicable to other tool wear modeling applications.     

Optimization of cutting conditions during cutting by using neural networks

Optimum selection of cutting conditions importantly contribute to the increase of productivity and the reduction of costs, therefore utmost attention is paid to this problem in this contribution. In this paper, a neural network-based approach to complex optimization of cutting parameters is proposed. It describes the multi-objective technique of optimization of cutting conditions by means of the neural networks taking into consideration the technological, economic and organizational limitations. To reach higher precision of the predicted results, a neural optimization algorithm is developed and presented to ensure simple, fast and efficient optimization of all important turning parameters. The approach is suitable for fast determination of optimum cutting parameters during machining, where there is not enough time for deep analysis. To demonstrate the procedure and performance of the neural network approach, an illustrative example is discussed in detail.     

A knowledge-based system for the prediction of surface roughness in turning process

In the present work, a knowledge-based system is developed for the prediction of surface roughness in turning process. Neural networks and fuzzy set theory are used for this purpose. Knowledge acquired from the shop floor is used to train the neural network. The trained network provides a number of data sets, which are fed to a fuzzy-set-based rule generation module. A large number of IF–THEN rules are generated, which can be reduced to a smaller set of rules by using Boolean operations. The developed rule base may be used for predicting surface roughness for given process variables as well as for the prediction of process variables for a given surface roughness. The concise set of rules helps the user in understanding the behavior of the cutting process and to assess the effectiveness of the model. The performance of the developed knowledge-based system is studied with the experimental data of dry and wet turning of mild steel with HSS and carbide tools.     

Online tool wear prediction system in the turning process using an adaptive neuro-fuzzy inference system

Tool wear is a detrimental factor that affects the quality and tolerance of machined parts. Having an accurate prediction of tool wear is important for machining industries to maintain the machined surface quality and can consequently reduce inspection costs and increase productivity. Online and real-time tool wear prediction is possible due to developments in sensor technology. Recently, various sensors and methods have been proposed for the development of tool wear monitoring systems. In this study, an online tool wear monitoring system was proposed using a strain gauge-type sensor due to its simplicity and low cost. A model, based on the adaptive network-based fuzzy inference system (ANFIS), and a new statistical signal analysis method, the I-kaz method, were used to predict tool wear during a turning process. In order to develop the ANFIS model, the cutting speed, depth of cut, feed rate and I-kaz coefficient from the signals of each turning process were taken as inputs, and the flank wear value for the cutting edge was an output of the model. It was found that the prediction usually accurate if the correlation of coefficients and the average errors were in the range of 0.989–0.995 and 2.30–5.08% respectively for the developed model. The proposed model is efficient and low-cost which can be used in the machining industry for online prediction of the cutting tool wear progression, but the accuracy of the model depends upon the training and testing data.     

Adaptive neural decentralized control for strict feedback nonlinear interconnected systems via backstepping

An approximation based adaptive neural decentralized output tracking control scheme for a class of large-scale unknown nonlinear systems with strict-feedback interconnected subsystems with unknown nonlinear interconnections is developed in this paper. Within this scheme, radial basis function RBF neural networks are used to approximate the unknown nonlinear functions of the subsystems. An adaptive neural controller is designed based on the recursive backstepping procedure and the minimal learning parameter technique. The proposed decentralized control scheme has the following features. First, the controller singularity problem in some of the existing adaptive control schemes with feedback linearization is avoided. Second, the numbers of adaptive parameters required for each subsystem are not more than the order of this subsystem. Lyapunov stability method is used to prove that the proposed adaptive neural control scheme guarantees that all signals in the closed-loop system are uniformly ultimately bounded, while tracking errors converge to a small neighborhood of the origin. The simulation example of a two-spring interconnected inverted pendulum is presented to verify the effectiveness of the proposed scheme.