Electro discharge machining (EDM) process need to be optimized when a new material invented or even if some process variables changed. This process has many variables and it is always difficult to get the optimum set of variables by chance. Therefore, an optimization process need to be conducted considering different combinations of machining parameters as well as other variables even if the process were optimized for a certain set of variables. Optimization of the EDM process for machining stainless steel 304 (SS304) (ASTM A240) was studied in this paper. Signal-to-noise ratio (S/N) was calculated for each performance measures, and multi response performance index (MRPI) was generated using fuzzy logic inference system. Optimal machining parameters for machining SS304 materials were identified, namely current 10, pulse on time 60 μ s, and pulse off time 35 μ s. Analyses of variances (ANOVA) method was used as well to see which machining parameter has significant effect on the performance measures. The result of ANOVA indicates that pulse off time and current are the most significant machining parameters in affecting the performance measures, with the pulse off time being the most significant parameter.

This paper describes the development and implementation of closed-loop control for oval stamp forming tooling using MATLAB ® ’s SIMULINK ® and the d SPACE ® CONTROLDESK ® . A traditional PID controller was used for the blank holder pressure and an advanced controller utilizing fuzzy logic combining a linear quadratic gauss controller and a bang–bang controller was used to control draw bead position. The draw beads were used to control local forces near the draw beads. The blank holder pressures were used to control both wrinkling and local forces during forming. It was shown that a complex, advanced controller could be modeled using MATLAB ’s SIMULINK and implemented in DSPACE CONTROLDESK . The resulting control systems for blank holder pressures and draw beads were used to control simultaneously local punch forces and wrinkling during the forming operation thereby resulting in a complex control strategy that could be used to improve the robustness of the stamp forming processes.

The property of high frequency in micro-EDM (electrical discharge machining) causes the discharge states to vary much faster than in conventional EDM, and discharge states of micro-EDM have the characteristics of nonstationarity, nonlinearity, and internal coupling, all of this makes it very difficult to carry out stable control. Thus empirical mode decomposition is adopted to conduct the prediction of the discharge states obtained through multisensor data fusion and fuzzy logic in micro-EDM. Combined with the autoregressive (AR) model identification and linear prediction, the mathematical model for EDM discharge state prediction using empirical mode decomposition is established and the corresponding prediction method is presented. Experiments demonstrate that the new prediction method with short identification data is highly accurate and operates quickly. Even using short model identification data, the accuracy of empirical mode decomposition prediction can stably reach a correlation of 74%, which satisfies statistical expectations. Additionally, the new process can also effectively eliminate the lag of conventional prediction methods to improve the efficiency of micro-EDM, and it provides a good basis to enhance the stability of the control system.

A microhole electrical discharge machining (EDM) system with adaptive fuzzy logic control and precision piezoelectric stage is developed in this study. A high-speed EDM monitoring system is implemented to measure the gap voltage, current, and ignition delay time, which are used to derive three input parameters—the average gap voltage, deviation in spark ratio, and change in the deviation in spark ratio—for the fuzzy logic control. Servo displacement and speed of the piezoelectric stage during each sampling duration are synthesized in real time by the adaptive fuzzy logic controller. Effects of the single and multiple input parameters, ignition delay threshold value, and maximum servo displacement and speed on the EDM drilling process are experimentally studied. Experimental results show that the fuzzy logic EDM control system yields a much more stable and efficient microhole EDM drilling process.

A neuro-fuzzy system is used to predict the condition of the tool in a milling process. Specifically the relationship between the sensor readings and tool wear state is first captured via a neural network and is subsequently reflected in linguistic form in terms of a fuzzy logic based diagnostic algorithm. In this approach, the neural network serves as an interpolative mechanism for the generation of data that is consistent with the behavior of the process, whereas fuzzy logic provides a transparent view of the relationship between the measured variables and the tool wear state. The methodology used in this paper incorporates an error-based, density-driven adaptation scheme in conjunction with a neural network based reference model to adapt the fuzzy membership functions associated with the tool condition monitoring algorithm to ensure that the rule set reflects the true nature of the inter-relationship between the sensor readings and the tool condition. Experimental results show that the proposed fuzzy mechanism correctly predicts the condition of the tool in 97 percent of the cases where it is applied.

The paper addresses the problem of picking up moving objects from a vibratory feeder with robotic hand-eye coordination. Since the dynamics of moving targets on the vibratory feeder are highly nonlinear and often impractical to model accurately, the problem has been formulated in the context of Prey Capture with the robot as a “pursuer” and a moving object as a passive “prey”. A vision-based intelligent controller has been developed and implemented in the Factory-of-the-Future Kitting Cell at Georgia Tech. The controller consists of two parts: The first part, based on the principle of fuzzy logic, guides the robot to search for an object of interest and then pursue it. The second part, an open-loop estimator built upon back-propagation neural network, predicts the target‘s position at which the robot executes the pickup task. The feasibility of the concept and the control strategies were verified by two experiments. The first experiment evaluated the performance of the fuzzy logic controller for following the highly nonlinear motion of a moving object. The second experiment demonstrated that the neural network provides a fairly accurate location estimation for part pick up once the target is within the vicinity of the gripper.

When machining conditions change significantly, applying parameter-adaptive control to the cutting system by varying the table feedrate allows a constant cutting force to be maintained. Although several controller schemes have been proposed, their cutting control performance is limited especially when the cutting conditions vary significantly. This paper presents an adaptive fuzzy logic control (FLC) developed for cutting processes under various cutting conditions. The controller adopts on-line scaling factors for cases with varied cutting parameters. In addition, a reliable self-learning (SL) algorithm is proposed to achieve even better cutting performance by modifying the adaptive FLC rule base according to properly weighted performance measurements. Both simulation and experimental results show that given a sufficient number of learning cases, the adaptive SL-FLC is effective for a wide range of applications. The successful implementation of the proposed adaptive SL-FLC algorithm on an industrial heavy-duty machining center indicates that the proposed adaptive SL-FLC is feasible for use in manufacturing industries.

This paper presents a systematic study of various monitoring methods suitable for automated monitoring of manufacturing processes. In general, monitoring is composed of two phases: learning and classification. In the learning phase, the key issue is to establish the relationship between monitoring indices (selected signature features) and the process conditions. Based on this relationship and the current sensor signals, the process condition is then estimated in the classification phase. The monitoring methods discussed in this paper include pattern recognition, fuzzy systems, decision trees, expert systems and neural networks. A brief review of signal processing techniques commonly used in monitoring, such as statistical analysis, spectral analysis, system modeling, bi-spectral analysis and time-frequency distribution, is also included.