An adaptive robotic system has been developed to be used for hand rehabilitation. Previously developed exoskeletons are either very complex in terms of mechanism, hardware and software, or simple but have limited functionality only for a specific rehabilitation task. Some of these studies use simple position controllers considering only to improve the trajectory tracking performance of the exoskeleton which is inadequate in terms of safety and health of the patient. Some of them focus only on either passive or active rehabilitation, but not both together. Some others use EMG signals to assist the patient, but this time active rehabilitation is impossible unless different designs and control strategies are not developed. The proposed mechanical structure is extremely simple. The middle and the proximal phalanxes are used as a link of consecutively connected two 4-bar mechanisms, respectively. The PIP and MCP joints are actuated by a single electro mechanical cylinder to produce complex flexion and extension movements. It is simpler than similar ones from aspect with the mechanical structure and the biodynamic fit of the hand, making it practicable in terms of production and personal usage. Simple design lets to implement adaptive compliance controller for all active and passive rehabilitation tasks, instead of developing complex and different strategies for different rehabilitation tasks. Furthermore, using the Luenberger observer for unmeasured velocity state variable, an on-line estimation method is used to estimate the dynamic parameters of the system. This makes possible to estimate the force exerted by the patient as well, without a force sensor.

The selection of parameters affects the surface roughness in the additive manufacturing process. This study aims to determine the optimal combination of input parameters for predicting and minimising the surface roughness of samples produced by Fused Deposition Modelling on a 3D printer using a cascade-forward neural network (CFNN) and genetic algorithm. Box-Behnken Design with four independent printing parameters at three levels is used, and 25 parts are fabricated with a 3D printer. Roughness tests are performed on the fabricated parts. Models generated by the hybrid algorithm achieve the best results for predicting and optimising surface roughness in 3D-printed parts. The surface roughness prediction accuracy of the trained CFNN with optimised parameters is more accurate compared to previous random test results.

No abstract

No abstract

This study presents a position tracking control method, with reference to Data-Driven Predictive Controller (DDPC), for a Pneumatic Artificial Muscle (PAM) system. The design of predictive controller is created from the subspace identification matrices acquired by input/output data. The control scheme is entirely data-based without explicit use of a model in the control application that can rectify the nonlinearity and uncertainties of the PAM. Firstly, subspace matrices are developed employing the identification method as a predictor by using open-loop experiments. Secondly, the estimated subspace matrices are used to design the so-called DDPC. In this instance, the quadratic programming (QR) decomposition method is used to obtain the prediction matrices. Consequently, experiments are carried out by the PAM actuator with different testing and loading conditions. The real-time experimental results demonstrate the feasibility and efficiency of the suggested control approach for nonlinear systems.

This paper presents a deployment method of various test maneuver scenarios for 2 degree of freedom (2 DoF) vehicle simulator by using feature extraction and neural networks (NN). A prototype version has been set up for the 2 DoF vehicle simulator. Then, a hardware in the loop (HIL) model with 2 inputs (torque, τ 1 -τ 2 ) and 3 outputs (acceleration, a x -a y -a z ) is created. System identification is performed to obtain the training data of NNs to be used for the deployment of test maneuvers. In the system identification process, 2 arbitrary sinusoidal torque signals (τ 1 -τ 2 ) are generated by using the actuator specs of the 2 DoF vehicle simulator. By applying the generated torque signals to the actuators, acceleration (a x -a y -a z ) data are collected from the inertial measurement sensor (IMU) on the 2 DoF vehicle simulator. It is determined to create 3 different NN models for the obtained data. The 1st NN model is trained with 3 inputs (a x -a y -a z ) and 2 targets (τ 1 -τ 2 ) training data. The 2nd NN model is trained with 6 inputs (amplitudes and phases of a x -a y -a z ) and 2 targets (τ 1 -τ 2 ) training data. The input data features for the 2nd NN model is extracted by using the Fast Fourier Transform (FFT). The 3rd NN model is trained with 6 inputs (amplitudes and phases of a x -a y -a z ) and 4 targets (amplitudes and phases of τ 1 -τ 2 ) training data. For the 3rd NN model, the features of input and target data are extracted by using the FFT. The NN training process continues until acceptable performance criteria are reached. Then, 3 NN models are run and analyzed under various test scenarios such as Double Lane Change, Constant Radius, Increase Steer, Fish Hook, Sine with Dwell and Swept Sine. Only for the 3rd NN, the actuator signals (τ 1 -τ 2 ) are recomposed by applying an inverse FFT process to the 4 targets (amplitudes and phases of τ 1 -τ 2 ). Finally, the reference trajectory tracking performances are evaluated by comparing the NN models that are run under the test scenarios.

In this study, the focus is on an implant used in the treatment of early-onset scoliosis called magnetically controlled growing rods (MCGR). The primary goal of the study is to address and propose solutions for the mechanical problems reported in the literature concerning MCGR. The problems of the MCGR are mainly due to excessive stress and mechanical bearing problems. Therefore, an MCGR removed from a patient is teardown and geometrically modeled. Then, eleven design parameters are determined on the MCGR for the mechanical problems experienced and these are evaluated by mechanical analysis over 14 control points. In this study, analysis processes are carried out with L12 orthogonal array for eleven design parameters and 2 levels using Taguchi's experimental design method (DoE). With the obtained data by analyzing the experiments in L12, the fitness functions depending on the design parameters are created for 14 control points. Since the problem is multi-objective, a non-dominated sorting genetic algorithm (NSGA II) and multi-objective particle swarm optimization (MOPSO) are used to minimize stress and displacement in existing mechanical problems using fitness functions. The obtained design models from NSGA II and MOPSO are analyzed and evaluated in comparison with the existing mechanical model obtained through preoptimization teardown study of MCGR.

No abstract