José R. Alique

Toward intelligent machining: hierarchical fuzzy control for the end milling process

The difficulties in implementing adaptive and other advanced control schemes in industrial machining processes have encouraged researchers to combine the utilization of one hierarchical level, a fuzzy control algorithm, and robust sensing systems. The main idea of this paper deals with self-regulating controllers (SRCs). The control signals scaling factor (output scaling factor) is self-regulated during the control process, and it can assure the optimum gain setting for the hierarchical fuzzy controller. An important role in this strategy is performed by a robust sensing system based on current sensors. For comparison, the CNC-PLCs own control loops, a hierarchical fuzzy controller based on look-up tables, and the hierarchical fuzzy controller with a self-regulating output scaling factor GC are studied. The performances of these controllers are compared. The results indicate that the hierarchical fuzzy controller with a self-regulating output scaling factor yields the best performances among them. The index known as the metal removal rate is increased, and the in-process time is reduced by 50%. Thus, higher production rates are obtained. The hierarchical fuzzy controller is equipped with three basic requirements: flexibility, low cost, and compatibility with any CNC manufacturer.

A Bayesian network model for surface roughness prediction in the machining process

The literature reports many scientific works on the use of artificial intelligence techniques such as neural networks or fuzzy logic to predict surface roughness. This article aims at introducing Bayesian network-based classifiers to predict surface roughness (Ra) in high-speed machining. These models are appropriate as prediction techniques because the non-linearity of the machining process demands robust and reliable algorithms to deal with all the invisible trends present when a work piece is machining. The experimental test obtained from a high-speed milling contouring process analysed the indicator of goodness using the Naïve Bayes and the Tree-Augmented Network algorithms. Up to 81.2% accuracy was achieved in the Ra classification results. Therefore, we envisage that Bayesian network-based classifiers may become a powerful and flexible tool in high-speed machining.

Fuzzy Logic-Based Torque Control System for Milling Process Optimization

This paper focuses on the design and implementation of a fuzzy-logic-based torque control system, embedded in an open-architecture computer numerical control (CNC), in order to provide an optimization function for the material removal rate. The control system adjusts the feed rate and spindle speed simultaneously as needed, to regulate the cutting torque using the CNCs own resources without requiring additional hardware overheads. The control system consists of two inputs (i.e., torque error and change of error), two outputs (i.e., the feed rate and spindle speed increment) fuzzy controller, and a self-tuning mechanism, all of which are embedded within the kernel of a standard open control. The self-tuning strategy is based on the measured peaks in the torque error signal of the closed-loop system response. The self-tuning fuzzy controller is applied to the milling process in a production environment in order to demonstrate the improvements in performance and effectiveness. Two approaches are tested, and their performance is assessed using several performance measurements. These approaches are the two-input/two-output for the fuzzy controller and a single-output fuzzy controller (i.e., only feed-rate modification), with and without the self-tuning mechanism. The results demonstrate that the proposed control strategy provides better transient performance, accuracy, and machining cycle time than the others, thus, increasing the metal removal rate.

A Transductive Neuro-Fuzzy Controller: Application to a Drilling Process

Recently, new neuro-fuzzy inference algorithms have been developed to deal with the time-varying behavior and uncertainty of many complex systems. This paper presents the design and application of a novel transductive neuro-fuzzy inference method to control force in a high-performance drilling process. The main goal is to study, analyze, and verify the behavior of a transductive neuro-fuzzy inference system for controlling this complex process, specifically addressing the dynamic modeling, computational efficiency, and viability of the real-time application of this algorithm as well as assessing the topology of the neuro-fuzzy system (e.g., number of clusters, number of rules). A transductive reasoning method is used to create local neuro-fuzzy models for each input/output data set in a case study. The direct and inverse dynamics of a complex process are modeled using this strategy. The synergies among fuzzy, neural, and transductive strategies are then exploited to deal with process complexity and uncertainty through the application of the neuro-fuzzy models within an internal model control (IMC) scheme. A comparative study is made of the adaptive neuro-fuzzy inference system (ANFIS) and the suggested method inspired in a transductive neuro-fuzzy inference strategy. The two neuro-fuzzy strategies are evaluated in a real drilling force control problem. The experimental results demonstrated that the transductive neuro-fuzzy control system provides a good transient response (without overshoot) and better error-based performance indices than the ANFIS-based control system. In particular, the IMC system based on a transductive neuro-fuzzy inference approach reduces the influence of the increase in cutting force that occurs as the drill depth increases, reducing the risk of rapid tool wear and catastrophic tool breakage.

Embedded fuzzy-control system for machining processes results of a case study

In this paper a fuzzy-control system has been designed, implemented and embedded in an open CNC. The integration process, design steps and results of applying an embedded fuzzy-control system are shown through the example of real machining operations. The controller uses internal CNC signals (i.e. spindle-motor current) that are gathered and mathematically processed by means of an integrated application. The results show that, at least in rough milling operations, internal CNC signals can double as an intelligent, sensorless control system. Actual industrial tests show a higher machining efficiency (i.e. in-process time is reduced by 10% and total estimated savings the system would provide are about 78%).

Fuzzy supervisory control of end milling process

Abstract The necessity of raising the efficiency of the milling process in a vertical (end) milling machine determines the implementation of a supervisory control system, which should manipulate the cutting process variables, in order to keep constant a high level of the cutting force. Modeling and control of this process using conventional techniques are quite difficult due to its complexity and nonlinearity. Therefore, a fuzzy control approach is undertaken. The algorithm used for the resulting MIMO controller has classic structure, partitions, and rule base, with IF…THEN rules. Also, the classic “sup-min” compositional operator and center of gravity for the defuzzification strategy are employed. A precalculated look-up table is the actual kernel of the implemented control algorithm. The system hierarchical structure has two levels: the lower one includes the CNC loops, and the higher one the fuzzy controller of the cutting force, acting over the cutting variables set points, and based on a PC. The necessary high- and low-level software as well as the complementary hardware were created. The results are evaluated as very satisfactory, especially concerning the increase of the metal removal rate and the suitable transient response, also compared with linear controllers.

Transductive-Weighted Neuro-Fuzzy Inference System for Tool Wear Prediction in a Turning Process

This paper presents the application to the modeling of a novel technique of artificial intelligence. Through a transductive learning process, a neuro-fuzzy inference system enables to create a different model for each input to the system at issue. The model was created from a given number of known data with similar features to data input. The sum of these individual models yields greater accuracy to the general model because it takes into account the particularities of each input. To demonstrate the benefits of this kind of modeling, this system is applied to the tool wear modeling for turning process.

Intelligent monitoring and decision control system for peripheral milling process

The aeronautic and automotive industries demand high quality products. Different aluminium alloys are used to produce them exploiting high speed machining (HSM) systems. HSM needs intelligent features such as monitoring and decision control. A framework that consists of four modules: data acquisition system, cutting tool monitoring, surface roughness prediction and intelligent planning module is presented. The planning module exploits genetic algorithms and Markov decision processes. This module supports and guides the operator in the operation of the CNC. Early results validate the benefits of this system in peripheral milling process, with a decrease between 18 % and 60 % in the operation costs.

Using simulated annealing for optimal tuning of a PID controller for time-delay systems: an application to a high-performance drilling process

This paper shows a strategy based on simulated annealing for the optimal tuning of a PID controller to deal with time-varying delay. The main goal is to minimize the integral time absolute error (ITAE) performance index and the overshoot for a drilling-force control system. The proposed strategy is compared with other classic tuning rules (the Ziegler-Nichols and Cohen-Coon tuning formulas). Other tuning laws derived from genetic algorithms and the Simplex search algorithm for unconstrained optimization are also included in the comparative study. The results demonstrate that simulated annealing provides an optimal tuning of the PID controller, which means better transient response (less overshoot) and less ITAE than with other methods.

Controlling a complex electromechanical process on the basis of a neurofuzzy approach

This paper shows the viability of implementing a control strategy based on the internal-model control paradigm, which is a useful synergy of a dynamic ANN trained from real-life data and used to predict process output and a fuzzy-logic control (FLC) that enhances the control systems overall performance. A force control problem involving a complex electromechanical system, represented here by the machining process, is considered as a case study. The main goal is to control a single-output variable, cutting force, by changing a single-input variable, feed rate. The proposed neurofuzzy-control (NFC) scheme consists of a dynamic model using ANNs to estimate process output, and a fuzzy-logic controller (FLC) with the same static gain as the inverse model to determine the control inputs (feed rate) necessary to keep the cutting force constant. Four approaches, the fuzzy-logic controller (FLC), the direct inverse controller based on ANNs (DIC-NN), the internal-model controller (IMC-NN) and a neurofuzzy controller (NFC), are simulated and their performances are assessed in terms of several performance measurements. The results demonstrate that the NFC strategy provides better disturbance rejection than the IMC-NN and the FLC for the cases analyzed.