Mohammad Hamiruce Marhaban

Artificial neural network-based kinematics Jacobian solution for serial manipulator passing through singular configurations

Singularities and uncertainties in arm configurations are the main problems in kinematics robot control resulting from applying robot model, a solution based on using Artificial Neural Network (ANN) is proposed here. The main idea of this approach is the use of an ANN to learn the robot system characteristics rather than having to specify an explicit robot system model. Despite the fact that this is very difficult in practice, training data were recorded experimentally from sensors fixed on each joint for a six Degrees of Freedom (DOF) industrial robot. The network was designed to have one hidden layer, where the input were the Cartesian positions along the X, Y and Z coordinates, the orientation according to the RPY representation and the linear velocity of the end-effector while the output were the angular position and velocities for each joint, In a free-of-obstacles workspace, off-line smooth geometric paths in the joint space of the manipulator are obtained. The resulting network was tested for a new set of data that has never been introduced to the network before these data were recorded in the singular configurations, in order to show the generality and efficiency of the proposed approach, and then testing results were verified experimentally.

FPGA-Based Fuzzy Logic: Design and Applications – a Review

— A large numbers of fuzzy control applications with the physical systems require a real-time operation to interface high speed constraints; higher density programmable logic devices such as field programmable gate array (FPGA) can be used to integrate large amounts of logic in a single IC. This paper reviews the state of the art of FPGA with the focus on FPGA-based fuzzy logic controller. The paper starts with an overview of FPGA in order to get an idea about FPGA architecture, and followed by an explanation on the hardware implementation with both type analogue and digital implementation, a comparison between fuzzy and conventional controller also provided in this paper. A survey on fuzzy logic controller structure is highlighted in this article with the focus on FPGA-based design of fuzzy logic controller with different applications. Finally, we provided the simulation and experimental results form the literature and concluded the main differences between software-based systems with respect to FPGA-based systems, and the main features for FPGA technology and its real-time applications.

Modelling and Optimisation of a Traffic Intersection Based on Queue Theory and Markov Decision Control Methods

Traffic models play an important role in both todays traffic research and in many traffic applications such as traffic flow prediction, incident detection and traffic control. Modelling traffic dynamics and optimising the control signal are two interrelated problems. Modelling provides fundamental understanding of traffic dynamics and behaviour. In this paper, traffic signal is modelled as a M/M/l queueing theory. The validation of a simulation model (M/M/l queue) with different arrival rates is presented. From the result, a traffic light model was developed by applying M/M/l queue theory for single intersection. In the optimisation strategy, the Markov decision control is applied to minimize queue length and waiting time. Simulation results show the excellent potential of this approach

A genetically trained simplified ANFIS Controller to control nonlinear MIMO systems

This paper presents a simplified ANFIS (Adaptive Neuro-Fuzzy Inference System) structure acting as a PID-like feedback controller to control nonlinear multi-input multi-output (MIMO) systems. Only few rules have been utilized in the rule base of this controller to provide the control actions, instead of the full combination of all possible rules. As a result, the proposed controller has several advantages over the conventional ANFIS structure particularly the reduction in execution time without sacrificing the controller performance, and hence, it is more suitable for real time control. In addition, the real-coded genetic algorithm (GA) has been utilized to train this MIMO ANFIS controller, instead of the hybrid learning methods that are widely used in the literature. Consequently, the necessity for the teaching signal required by other techniques has been eliminated. Moreover, the GA was used to find the optimal settings for the input and output scaling factors for this controller, instead of the widely used trial and error method. To demonstrate the accuracy and the generalization ability of the proposed controller, two nonlinear MIMO systems have been selected to be controlled by this controller. In addition, this controller robustness to output disturbances has been also evaluated and the results clearly showed the remarkable performance of this MIMO controller.

Non-linear modelling and control of a conveyor-belt grain dryer utilizing neuro-fuzzy systems

The grain drying process is characterized by its complex and non-linear nature. As a result, conventional control system design cannot handle this process appropriately. This work presents an intelligent control system for the grain drying process, utilizing the capabilities of the adaptive neuro-fuzzy inference system (ANFIS) to model and control this process. In this context, a laboratory-scale conveyor-belt grain dryer was specifically designed and constructed for this study. Utilizing this dryer, a real-time experiment was conducted to dry paddy (rough rice) grains. Then, the input–output data collected from this experiment were presented to an ANFIS network to develop a control-oriented dryer model. As the main controller, a simplified proportional–integral–derivative (PID)-like ANFIS controller is utilized to control the drying process. A real-coded genetic algorithm (GA) is used to train this controller and to find its scaling factors. From the robustness tests and a comparative study with a genetically tuned conventional PID controller, the simplified ANFIS controller has proved its remarkable ability in controlling the grain drying process represented by the developed ANFIS model.

Artificial neural network based maximum power point tracking controller for photovoltaic standalone system

ABSTRACT This article presents a two-stage maximum power point tracking (MPPT) controller using artificial neural network (ANN) for photovoltaic (PV) standalone system, under varying weather conditions of solar irradiation and module temperature. At the first-stage, the ANN algorithm locates the maximum power point (MPP) associated to solar irradiation and module temperature. Then, a simple controller at the second-step, by changing the duty cycle of a DC–DC boost converter, tracks the MPP. In this method, in addition to experimental data collection for training the ANN, a circuit is designed in MATLAB-Simulink to acquire data for whole ranges of weather condition. The whole system is simulated in Simulink. Simulation results show small transient response time, and low power oscillation in steady-state. Furthermore, dynamic response verifies that this method is very fast and precise at tracking the MPP under rapidly changing irradiation, and has very low power oscillation under slowly changing irradiation. Experimental results are provided to verify the simulation results as well.

Electromagnetic Design and FEM Analysis of a Novel Dual-Air-Gap Reluctance Machine

The electro-magnetic torque production in the reluctance machine is highly in∞uenced by the magnetic linkages in the air-gap area. The conventional machines derive the drawback of reduction in the air-gap area to a minimal due to in∞uence of mechanical unbalancing thereby restricting the efiective energy conversion area. In order to increase the magnetic linkage area, the dual-air-gap structure is introduced. The dual-air-gap structure is realised through the division of the magnetic circuit area into two air-gaps while still maintaining the net air-gap length value. A double-rotor with single- stator structure is used to attribute the above concept. The electro- magnetic analysis of such a structure is developed and investigated through numerical analysis. In order to validate the proposed structure the electro-magnetic characteristics are compared with that of the conventional structure at similar operating conditions. The maximum torque generated by the selected dual-air-gap structure is 1.7549Nm and for conventional structure is 1.2723Nm. The evaluation of the proposed machine is done at the same operating conditions and it is found that the dual-air-gap structure exhibit 65% increase in average torque value in comparison with that of the conventional single-air-gap structure.

Mobile robot safe navigation in unknown environment

This paper provides a mobile robot navigation strategy using fuzzy logic is developed for a two wheeled mobile robot in a static environment. The information about the target and the low-range sensory information are used by the controller to produce the commands that gives a favorable direction in terms of reaching to the target within the collision detection. Furthermore, the mobile robot does not suffer from typical u-shape environment by a planned local minimum trapping algorithm and also designed controller is easy to understand, simple, and not sensitive to the system model parameters. The resulting path, connecting a start point to a target position where in this method there is no information about the environment. Due to its ability and effortlessness for real-time implementation, fuzzy controller has been used for the proposed navigation strategy. The resulting navigation system is implemented on the e-puck robot in Webots software, and tested in several environments. Simulation results are presented which show the effectiveness of the proposed fuzzy controller and local minimum algorithm to safely navigate the mobile robot in various dead end trap environment.

FASTA-ELM

Extreme learning machine (ELM) is an interesting algorithm for learning the hidden layer of single layer feed forward neural networks. However, one of the main shortcomings restricting further improvement of ELM is the complexity of singular value decomposition (SVD) for computing the Moore-Penrose generalized inverse of the hidden layer matrix. This paper presents a new algorithm named fast adaptive shrinkage/thresholding algorithm ELM (FASTA-ELM) which uses an extension of forward-backward splitting (FBS) to compute the smallest norm of the output weights in ELM. The proposed FASTA-ELM algorithm is evaluated on face gender recognition problem using 5 benchmarked datasets. The results indicate that FASTA-ELM provides efficient performance and outperforms the standard ELM and two other variants of ELM in terms of generalization ability and computational time. Furthermore, the recognition performance of FASTA-ELM is comparable to other state-of-the-art face gender recognition methods.

Application of Statistical and Intelligent Techniques for Modeling of Metallurgical Performance of a Batch Flotation Process

Froth flotation is one of the most frequently used processes for separation of valuable from gangue minerals. Modeling and simulation of the flotation process is a difficult task because of nonlinear and dynamic nature of the process. In this contribution, the relationship between the process variables (i.e., gas flow rate, slurry solids%, frother/collector dosages, and pH) and the metallurgical parameters (i.e., copper/mass/water recoveries and concentrate grade) in the batch flotation of a copper sulfide ore is discussed and modeled. Statistical (i.e., nonlinear regression) and intelligent (i.e., neural network and adaptive neuro-fuzzy) techniques are applied to model the process behavior at different conditions. The results indicate that intelligent approaches are more efficient tools for modeling of the complicated process like flotation, which are of central importance for development of the model-based control systems.