Four classes of second order sliding mode controllers (2-SMC) have been successfully applied to regulate the liquid level in the second tank of a coupled tanks system. The robustness of these classes of 2-SMC is investigated and their performances are compared with a first order controller to show the merits of these controllers. The effectiveness of these controllers is verified through computer simulations. Comparison between the controllers is based on the time domain performance measures such as rise time, settling time, and the integral absolute error. Results showed that controllers are able to regulate the liquid level with small differences in their performance.

Optimizing flexible routing in flexible manufacturing systems is one of the aspects that increase the efficiency of flexible manufacturing systems especially in dynamic environment systems. This article presents a multistage approach to solve flexible routing problem in flexible manufacturing systems. Multistage approach includes three stages; the first stage is a production simulation system to find the fitness of the flexible manufacturing systems corresponding to different products' routes' groups. The second stage proposes an artificial neural network approach to predict the products' routes' group in flexible manufacturing systems. The last stage combines genetic algorithms and artificial neural network to optimize proper routes for all product types in flexible manufacturing systems. Multistage approach proposed in this study aims to reduce the computational time required to obtain and optimize the flexible routes in flexible manufacturing systems. The results of this study show that the artificial neural network can be used efficiently to predict the flexible routes in flexible manufacturing systems and it reduces the computational time for routes' optimization required with production simulation system. This characteristic improves the flexibility of flexible manufacturing systems since it can be adapted frequently against any change in production ratios.

The proper positioning of machine tools in flexible manufacturing system is one of the factors that lead to increase in production efficiency. Choosing the optimum position of machine tools curtails the total part handling cost between machine tools within the flexible manufacturing system. In this article, a two-stage approach is presented to investigate the best locations of the machine tools in flexible manufacturing system. The location of each machine tool is selected from the available specific and fixed locations in such a way that it will result in best throughput of the flexible manufacturing system. In the first stage of the two-stage approach, the throughput of randomly selected locations of the machine tool in flexible manufacturing system is computed by proposing a production simulation system. The production simulation system utilizes genetic algorithms to find the locations of the machine tools in flexible manufacturing system that achieve the maximum throughput of the flexible manufacturing system. In the second stage, the generated locations are fed into artificial neural network to find a relation between a machine tool's location and the throughput that can be used to predict the throughput for any other set of locations. Artificial neural network will result in mitigating the computational time.

No abstract

This paper addresses the use of the kriging‏ approach to predict the springback in the air bending process. The materials and the geometrical parameters, which significantly affect the springback, were considered as inputs, and the springback angle was considered as the response. A verified nonlinear finite element model was used to generate the training data required to create the kriging‏ metamodel. The training examples were selected based on computer-generated D-optimal designs. A comparison between the kriging approaches and the response surface methodology is conducted and discussed. The results showed that kriging accurately predicts the finite element springback results. Comparing the accuracy of kriging with a response surface methodology shows that kriging with a 2nd degree polynomial and exponential correlation function predicts the springback more accurately than the response surface methodology.