Farid A. Tolbah

Design and Implementation of a Flexible Manufacturing Control System Using Neural Network

Design and implementation of a sequential controller based on the concept of artificial neural networks for a flexible manufacturing system are presented. The recurrent neural network (RNN) type is used for such a purpose. Contrary to the programmable controller, an RNN-based sequential controller is based on a definite mathematical model rather than depending on experience and trial and error techniques. The proposed controller is also more flexible because it is not limited by the restrictions of the finite state automata theory. Adequate guidelines of how to construct an RNN-based sequential controller are presented. These guidelines are applied to different case studies. The proposed controller is tested by simulations and real-time experiments. These tests prove the successfulness of the proposed controller performances. Theoretical as well as experimental results are presented and discussed indicating that the proposed design procedure using Elmans RNN can be effective in designing a sequential controller for event-based type manufacturing systems. In addition, the simulation results assure the effectiveness of the proposed controller to outperform the effect of noisy inputs.

A recurrent neural network-based sequential controller for manufacturing automated systems

The objective of this paper is to propose a recurrent neural network (RNN)-based sequential controller to be used in an automated manufacturing system. Contrary to the programmable controller, an RNN-based sequential controller is based on a definite mathematical model rather than a trial and error technique. The proposed controller is also more flexible since it is not limited by the restrictions of finite state automata theory. A design procedure to use Elmans RNN-based sequential controller is presented, and applied to different case studies. The proposed controller is tested experimentally and proves successful. Theoretical results as well as experimental results are presented and discussed indicating that the proposed design procedure using Elmans RNN can be effective in designing a sequential controller for different types of manufacturing systems.

Lower limb gait activity recognition using Inertial Measurement Units for rehabilitation robotics

In this paper, The authors considered a human lower limb gait activity recognition algorithm, using an IMU sensory network consisting of 4 IMUs distributed to the lower limb. The proposed algorithm depends on Random Forest for classification and a Hybrid Mutual Information and Genetic Algorithm (HMIGA) as a features selection technique. HMIGA selects the most distinguishing features from Discrete Wavelet Coefficient (DWT) features and other statistical and physical (self designed) features. The proposed algorithm is compared with Support Vector Machine (SVM) to classify 5 activities and the results are presented on 6 subjects with 2% average error rate with 1.9% superiority on SVM. Moreover, HMIGA as a feature selector is compared to the traditional feature selectors and DWT as a feature also compared to statistical and physical features, showing their influence on the activity recognition process. Finally, the most important features selected by HMIGA are presented, proving the important role of the shanks sensor on the recognition process, where almost 50% of the selected features are from the shank sensor.

Metaheuristic optimization in path planning of autonomous vehicles under the ATOM framework

Autonomous transportation systems are embarking our lives at an increasing pace. Over the past few years, several commercially available vehicles are incorporated with increasing levels of autonomy. The Autonomous Transportation Operating Modules (ATOM) framework is proposed to organize and coordinate the development as well as testing of these autonomous systems. One of the most important modules is the path planning of the vehicle, and finding the optimal path between two points is of great importance as it is directly to power saving of the battery. Metaheuristic optimization techniques are widely used to solve complex problems in an acceptable time interval. In this study, three metaheuristic approaches; simulated annealing, particle swarm and ant colony optimization are investigated to find the optimal path between two points in a static environment. The results of the PSO outperformed the other two, opening the door for investigating its implementation on the embedded level for further demonstration and testing on real experimental platforms.

Proportional myoelectric prosthetic hand control using multi-regression model estimator with pattern classifier selector

Myoelectric hand prostheses using pattern recognition control scheme lack simultaneous motion, and perform robotic unnatural inter-pattern motion. Accordingly, the use of regression models for the estimation of hand kinematics proportionally to sEMG (surface electromyography) signals has proved more simultaneous and natural motion. The objective of this study is to introduce proportional speed control on robotic hand motion, where each finger has its own estimator model to achieve non-robotic performance of the hand. Each finger has four regression models to cover the motion of the finger over four patterns. A pattern recognition classifier is trained to classify four hand gestures, accordingly, the regression models of the fingers is to be altered according to the classifier decision. Commercial sEMG sensing armband was used in the acquisition of training data that can be used later in the development of the prosthetic control system. The reproduction of data for linear (least-square fitted model) and non-linear (ANN) regression models are investigated, where the ANN proved better reproducibility of finger speeds. The models also are trained on reduced RMS features, where the selected features are only the channels that are allocated over the active muscles during performing the patterns which resulted reproducibility of 89.27±1.92%. These results demonstrate the robustness of the multi-regression models system over wide range of motion.

Modeling and simulation of a new bioinspired muscle actuator

In this paper a new linear bioinspired actuator is developed. This actuator is made to mimic the biological muscles structure and function. Ionic polymer metal composites (IPMC) smart material is used to emulate the motion of the cross-bridges of biological muscle. A dynamic model of the proposed actuator is developed using the wave propagation technique. Modeling and simulation of the bioinspired actuator shows that one muscle unit actuator produces a maximum force of 0.12 N, axial displacement of 4 mm in each step, and a maximum axial displacement of about 30% of total muscle unit length. Sixteen IPMC sets are used; each set contains three IPMC segments connected in series. The length, width and height of each segment are 16mm, 10mm, 0.2 mm respectively. The total muscle unit length and diameter are 120 mm and 70 mm respectively.

A mechatronic vision system for inspection of garnished wall plates

Detecting drawn objects on reflective surfaces is a challenging process due to severe reflectivity of illumination even with the utilization of inclined light sources. Lens distortion, which is a common problem, could jeopardize the accuracy of metrics needed during assessment of ceramic plates to classify its quality. This paper proposes a complete mechatronic vision system covering all aspects of building a robust system for inspecting garnished wall plates.