The paper investigates the application of the Artificial Neural Network (ANN) in modeling of double-link flexible robotic manipulator (DLFRM). The system was categorized under multi-input multi-output. In this research, the dynamic models of DLFRM were separated into single-input single-output in the modeling stage. Thus, the characteristics of DLFRM were defined separately in each model and the coupling effect was assumed to be minimized. There are four discrete SISO model of double link flexible manipulator were developed from torque input to the hub angle and from torque input to the end point accelerations of each link. An experimental work was established to collect the input-output data pairs and used in developing the system model. Since the system is highly nonlinear, NARX model was chosen as the model structure because of its simplicity. The nonlinear characteristic of the system was estimated using the ANN whereby multi-layer perceptron (MLP) and ELMAN neural network (ENN) structure were utilized. The implementation of the ANN and its’ effectiveness in developing the model of DLFRM was emphasized. The performance of the MLP was compared to ENN based on the validation of the mean-squared error (MSE) and correlation tests of the developed models. The results indicated that the identification of the DLFRM system using the MLP outperformed the ENN with lower mean squared prediction error and unbiased results for all the models. Thus, the MLP provides a good approximation of the DLFRM dynamic model compared to the ENN.
Pipelines are essential tools for transporting water, oils, gases and sewer from one place to another. Pipelines are used to interconnect networks from one station to another that involved various diameter sizes and fittings to compensate intended directions. There are many issues that influenced performance of the pipelines namely aging, corrosion, cracks and use to clog up with debris, or sediments after long use. There are number of methods available to clean the inside of the closed pipeline namely traditional method like boiling, picking, alcohol and salt and cleaning kits, or tools kits such as wire and plunger or large-gauge snake. However, all the methods can over-stress older pipeline and cause leaks that make even more extensive repair procedures needed to fix the problem. Chemical fluid for pipe cleaning is also not suitable to all types of pipeline because the chemical can erode the pipe wall. Currently, service robot is the best solution that purposely developed to facilitate humans being activities including cleaning, inspection for cracks or repairing damage in pipeline. This paper intends to report about the development of cleaning device for in-pipe robot application. The development covers both software and hardware of the device. Significant experiment has been designed to validate the function of the device. It is proof that the device has successfully clean the soft and moderate clog. The success of the cleaning device can be attached to the in-pipe robot and the outcome is expected to assist pipeline cleaning operations. Thus, enable the pipelines to transport efficiently with minimum cost of operation
Stroke is one of the leading causes of disability in the world. The stroke patients need professional support for the rehabilitation activity. However, the number of therapist is considered inadequate to support an increasing numbers of stroke patients especially in the rural areas. Therefore, robot based device for rehabilitation is considered one of the solutions for the increasing numbers of stroke patients and to support the therapist. This research presents the development of upper limb rehabilitation device robot. The device is considered portable for home setting and allowed movement on vertical elbow flexion and shoulder/elbow horizontal flexion and extension. The device consists of scissors lift and armrest mechanism that allowed the patients to perform upper limb rehabilitation at X-X, X-Z, Y-Y and Y-Z axis direction. Two linear actuators, motor drivers and Arduino UNO board were used to drive the device.
19 June 2025 in Journal of the Brazilian Society of Mechanical Sciences and Engineering
The modelling and control of unmanned aerial vehicles (UAVs), especially quadrotors with significant position–orientation coupling, pose considerable challenges in practical applications, such as environmental monitoring in wind-affected mangrove forests. Traditional control methods, such as the PID controller, which are commonly used in simulations owing to their simplicity, often fail to perform optimally under real-world conditions because of their reliance on linear assumptions. This study addresses these challenges through three key innovations: (1) a hierarchical cascaded model predictive control (MPC) framework that decouples translational and rotational dynamics into computationally efficient subsystems, significantly reducing the computational load of conventional MPC implementations; (2) a control strategy explicitly optimized for turbulent mangrove ecosystems, where dense vegetation amplifies wind disturbances; and (3) experimental validation of the framework’s real-world applicability via simulations and hardware-in-the-loop flight tests using Pixhawk autopilots under realistic wind conditions. These tests demonstrated that the proposed controller significantly outperformed the conventional PID controller, particularly in terms of stability and disturbance rejection. These results highlight the potential of this control system for UAV applications in challenging environments bridging the gap between theoretical control design and field-ready robustness.
The paper investigates the development of intelligent hybrid collocated and non-collocated PID controller for hub motion and end point vibration suppression of double-link flexible robotic manipulator. The system was modeled using multi-layer perceptron neural network structure based on Nonlinear Autoregressive Exogenous (NARX) model. The hybrid controllers are incorporated with optimization algorithm that is ABC and PSO to find out the parameters of the PID controllers. Numerical simulation was carried out in MATLAB/Simulink to evaluate the system in term of tracking capability and vibration suppression for both links. Performance of the controllers are compared with the hybrid PID-PID Ziegler Nichols (ZN) controller in term of input tracking and vibration suppression. The results show that PSO revealed the superiority over ABC in controlling the system. The system managed to reach desired angle for both hub at lower overshoot using proposed method. Meanwhile, the vibration reduction shows great improvement for both link 1 and 2. This signifies that, the PSO algorithm is very effective in optimizing the PID parameters.
7 November 2024 in e-Prime - Advances in Electrical Engineering, Electronics and Energy