Optimizing power consumption and position control in an electro-hydraulic system with cylinder bypass and NN-MPC.

This study introduces an innovative approach to enhance the energy efficiency and position control performance of electro-hydraulic systems, employing a comprehensive comparative analysis. It presents and evaluates three control techniques: Proportional-Integral-Derivative (PID) control, Model Predictive Control (MPC), and Neural Network Model Predictive Control (NN-MPC). These methods are systematically assessed across varying load conditions. Notably, our research unequivocally establishes the exceptional performance of the NN-MPC approach, even when confronted with load variations. Furthermore, the study conducts an exhaustive examination of energy consumption by comparing a conventional system, where a flow control valve is not utilized as a hydraulic cylinder bypass, with a proposed system that employs a fully open Flow Control Valve (FCV). The results underscore the remarkable energy savings achieved, reaching up to 9% at high load levels.

An Improved Approach for Grasp Force Sensing and Control of Upper Limb Soft Robotic Prosthetics.

The following research proposes a closed loop force control system, which is implemented on a soft robotic prosthetic hand. The proposed system uses a force sensing approach that does not require any sensing elements to be embedded in the prosthetic's fingers, therefore maintaining their monolithic structural integrity, and subsequently decreasing the cost and manufacturing complexity. This is achieved by embedding an aluminum test specimen with a full bridge strain gauge circuit directly inside the actuator's housing rather than in the finger. The location of the test specimen is precisely at the location of the critical section of the bending moment on the actuator housing due to the tension in the driving tendon. Therefore, the resulting loadcell can acquire a signal proportional to the prosthetic's grasping force. A PI controller is implemented and tested using this force sensing approach. The experiment design includes a flexible test object, which serves to visually demonstrate the force controller's performance through the deformation that the test object experiences. Setpoints corresponding to "light", "medium", and "hard" grasps were tested with pinch, tripod, and full grasps and the results of these tests are documented in this manuscript. The developed controller was found to have an accuracy of ±2%. Additionally, the deformation of the test object increased proportionally with the given grasp force setpoint, with almost no deformation during the light grasp test, slight deformation during the medium grasp test, and relatively large deformation of the test object during the hard grasp test.

Hardware-in-the-loop testing of simple and intelligent MPPT control algorithm for an electric vehicle charging power by photovoltaic system.

In this paper, an electric vehicle (EV) charging station powered by a photovoltaic (PV) system has been created to charge EVs. Furthermore, the maximum available power from the PV system was extracted using a new algorithm called the simplified universal intelligent PID (SUIPID) controller, which has the advantages of simplicity in design and intelligence. The SUIPID controller was compared to the artificial neural networks (ANNs), the fuzzy logic controller (FLC) based on linear membership functions, and the FLC based on particle swarm optimization (PSO) to optimize its parameters under various conditions. The system simulation was first performed using MATLAB software, then an experimental set up was conducted to confirm the theoretical work. The proposed SUIPID responds 28.5%, 44.4%, and 61.5% faster than the PSO-FLC, ANN, and FLC, respectively, whereas the ITAE error was reduced by 27.3%, 52.9%, and 65.2%, respectively. Also, the charging procedure of the EV battery is precisely steady under different atmospheric conditions. The SUIPID controller has several advantages over other intelligent algorithms, most notably its ease of design and implementation.

Design of a Data Glove for Assessment of Hand Performance Using Supervised Machine Learning.

The large number of poststroke recovery patients poses a burden on rehabilitation centers, hospitals, and physiotherapists. The advent of rehabilitation robotics and automated assessment systems can ease this burden by assisting in the rehabilitation of patients with a high level of recovery. This assistance will enable medical professionals to either better provide for patients with severe injuries or treat more patients. It also translates into financial assistance as well in the long run. This paper demonstrated an automated assessment system for in-home rehabilitation utilizing a data glove, a mobile application, and machine learning algorithms. The system can be used by poststroke patients with a high level of recovery to assess their performance. Furthermore, this assessment can be sent to a medical professional for supervision. Additionally, a comparison between two machine learning classifiers was performed on their assessment of physical exercises. The proposed system has an accuracy of 85% (±5.1%) with careful feature and classifier selection.

Soft Finger Modelling and Co-Simulation Control towards Assistive Exoskeleton Hand Glove.

The soft pneumatic actuators of an assistive exoskeleton hand glove are here designed. The design of the actuators focuses on allowing the actuator to perform the required bending and to restrict elongation or twisting of the actuator. The actuator is then modeled using ABAQUS/CAE, a finite element modeling software, and the open loop response of the model is obtained. The parameters of the actuator are then optimized to reach the optimal parameters corresponding to the best performance. Design of experiment (DOE) techniques are then approached to study the robustness of the system. Software-in-the-loop (SiL) is then approached to control the model variables via a proportional-integral-derivative (PID) control generated by FORTRAN code. The link between the two programs is to be achieved by the user subroutine that is written, where the subroutine receives values from ABAQUS/CAE, performs calculations, and passes values back to the software. The controller's parameters are tuned and then the closed loop response of the model is obtained by setting the desired bending angle and running the model. Furthermore, a concentrated force at the tip of the actuator is added to observe the actuator's response to external disturbance.

A proposed soft pneumatic actuator control based on angle estimation from data-driven model.

This article proposes a bending angle controller for soft pneumatic actuators, which could be implemented in soft robotic rehabilitation gloves to assist patients with hand impairment, such as stroke survivors. A data-driven model is used to estimate the angle as pneumatic pressure is applied to the actuator. Furthermore, a finite element model was used to manually optimize the dimensions of the actuator. An embedded flex sensor, which together with a custom testing rig, was used to gather input data for the data-driven model. This rig contains a pneumatic pressure control circuit as well as a camera for image acquisition. Collected data were fed into a linear regression model to predict the data-driven model. Experiments were carried out to validate model's accuracy as well as modified proportional-integral-derivative controller angle controller performance. The latter controller is designed to mitigate the non-linear response of solenoid valves at different pressures of the actuator. The data-driven model along with the used controller allows more accurate estimation and quicker response.