Proportional, integral, and derivative (PID) controllers have been widely adopted for industrial applications. However, these controllers are not very efficient for non-linear systems. Artificial neural networks (ANN)...
Proportional, integral, and derivative (PID) controllers have been widely adopted for industrial applications. However, these controllers are not very efficient for non-linear systems. Artificial neural networks (ANN) based on the Group Method of Data Handling (GMDH) have great potential to replace the PID controllers due to their polynomial structure, allowing complex non-linear systems to be controlled. This work presents a hardware architecture of a GMDH network applied to speed control of a mobile robot platform. The proposed GMDH controller was implemented using a 16-bit floating-point arithmetic representation and was mapped on a Zynq7020 device. A hardware-in-the-loop based on the Universal Direct Memory Access methodology was developed to validate the proposed circuits, allowing for performance comparisons between a classical PID and the GMDH controllers for different simulated scenarios.
This paper introduces an initial investigation of a series elastic resistance mechanism for exercise and rehabilitation. The idea of Series Elastic Actuator is applied to a resistance mechanism that is designed to per...
详细信息
ISBN:
(纸本)9781509047192
This paper introduces an initial investigation of a series elastic resistance mechanism for exercise and rehabilitation. The idea of Series Elastic Actuator is applied to a resistance mechanism that is designed to perform stable force control under safe operation in a cost effective way. The mechanism can generate various resistance force considering the biomechanical characteristic of a human by actively controlling resistance during an exercise stroke. As an initial investment of a series elastic resistance mechanism, a prototype hardware has been developed. Bluetooth communication is used to connect the prototype with a smartphone which sets resistance levels and receives experimental data log. A PID feedback controller is implemented with the prototype hardware to provide a constant, non-inertial resistance force by maintaining a constant deflection of springs during an exercise stroke. Dynamic simulation and experimental results of the prototype are also presented.
Micro components of micro machines, such as mechanisms, gears, sensors and actuators which are almost invisible, have been made by recent advance of mechanical and electronic engineering. The production of micro machi...
详细信息
Micro components of micro machines, such as mechanisms, gears, sensors and actuators which are almost invisible, have been made by recent advance of mechanical and electronic engineering. The production of micro machines, however, requires new technologies for assembling micro parts into complete micro machines. Macro-micro teleoperation is one of the key technologies for constructing micro machines and will help human operators assemble micro parts with the skills they already have. First, we describe an experimental system for macro-micro teleoperation which we have developed. This system consists of a pair of prototype 2 DOF micro slave arms actuated by voice-coil motors to generate micro forces, and a pair of 2 DOF master arms actuated by the linear DD motors. Second, the basic characteristics of the system are introduced and the experimental results are presented.
In this paper, a radial basis function neural network-based (RBFNN) adaptive inverse controller for real-time position tracking control of a two phase hybrid stepper motor in microstep mode is presented. To ensure sys...
详细信息
In this paper, a radial basis function neural network-based (RBFNN) adaptive inverse controller for real-time position tracking control of a two phase hybrid stepper motor in microstep mode is presented. To ensure system's robustness and closed loop stability and to improve the performance of the controller, the RBF based adaptive inverse control is combined with a closed loop PID controller. Experimental results are provided for various types of trajectories, comparing the performance of the proposed controller to the same neuro-controller using feed forward back-propagation neural networks (FFBP) proposed previously by the authors. The results show the superior performance of RBFNN over FFBP neural networks. Also the comparison of neuro controllers with a conventional fixed gain stand-alone PID controller show the improvement of the controller performance from 80% up to 99.7% decrease in the mean squared error (MSE) for different trajectories. Trajectories were tracked with the maximum error of 0.02 up to 0.06 degrees. Also the robustness of the method is confirmed through experimental results comparing neuro-controllers and the conventional PID controller by varying the load's inertia and disturbance torques. For this purpose two methods were examined. First using the same neuro-controllers trained by the initial training data and in the second method, neuro-controllers were adapted by new training data according to the new working conditions.
This paper is concerned with the dynamic modeling and vibration measurement of a single or bundled power transmission line. The bundled power transmission line may consists of two or more electric lines, which are con...
详细信息
This research discusses the application of the hyperbolic tangent model for an outer bypass MR damper with a meandering valve, which was developed by one of the authors. The hyperbolic tangent model consists of six pa...
详细信息
ISBN:
(数字)9798350364750
ISBN:
(纸本)9798350364767
This research discusses the application of the hyperbolic tangent model for an outer bypass MR damper with a meandering valve, which was developed by one of the authors. The hyperbolic tangent model consists of six parameters. In this study, parameter reduction was carried out using local and global sensitivity analysis, and a parameter identification strategy based on Particle Swarm Optimization (PSO) was employed. The objective function is the relative error between the model's force and the force obtained from experiments with an outer bypass MR damper prototype featuring a meandering valve. The sensitivity analysis identifies an optimal hyperbolic tangent model with two sensitive parameters, while the remaining parameters are determined to be constant. The results show an improvement in accuracy, with the optimal hyperbolic tangent model reducing the error from 8.06 % to 7.1 %. This indicates that the optimal hyperbolic tangent model can be obtained by applying the sensitivity analysis method developed in this research.
Laser ablation is a novel non-mechanical wheel preparation method for optimizing the treatment costs of superabrasive tools. In this study the thermal effects of picosecond laser radiation on CBN superabrasive grindin...
详细信息
作者:
Lu, Y.Ye, L.Wang, D.Wang, X.Su, Z.
School of Aerospace Mechanical and Mechatronic Engineering University of Sydney NSW2006 Australia Urban Systems Program
CSIRO Sustainable Ecosystems Commonwealth Scientific and Industrial Research Organisation 37 Graham Road Highett MelbourneVIC3190 Australia Department of Mechanical Engineering
Hong Kong Polytechnic University Hong Kong Hong Kong
Identification of multiple notches in an aluminium plate was investigated with the aid of probability-based imaging evaluation of Lamb wave signals activated and captured by a piezoelectric sensor network. A signal pr...
详细信息
ISBN:
(纸本)9781605950075
Identification of multiple notches in an aluminium plate was investigated with the aid of probability-based imaging evaluation of Lamb wave signals activated and captured by a piezoelectric sensor network. A signal processing algorithm featuring signal synchronization and correlation is proposed to facilitate the extraction of damage-scattered waves, by the means of which the corresponding arrival times of the scattered waves are obtained. Using a virtually-meshed grid in the plate, an image with respect to the probability of the arrival time at individual nodes is achieved, indicating the location of damage as perceived by individual actuator-sensor paths. Compromised and conjunctive data fusion techniques are applied to aggregate the images for all engaged actuator-sensor paths, to provide a complete appraisal of the location of damage. The diagnostic results demonstrate that the proposed approach is capable of identifying multiple notches with good accuracy in terms of their position.
Knowledge-based planning (KBP) is an automated approach to radiation therapy treatment planning that involves predicting desirable treatment plans before they are then corrected to deliverable ones. We propose a gener...
详细信息
An autonomous walking aid is a type of Autonomous Mobile Robots (AMRs) designed to navigate and perform tasks independently. In this paper, we introduce an innovative obstacle avoidance approach for walking aids, with...
详细信息
ISBN:
(数字)9798331528263
ISBN:
(纸本)9798331528270
An autonomous walking aid is a type of Autonomous Mobile Robots (AMRs) designed to navigate and perform tasks independently. In this paper, we introduce an innovative obstacle avoidance approach for walking aids, with a particular emphasis on avoiding non-stereotypical obstacles such as water puddles. Traditional methods relying on LiDAR, depth sensors, or cameras often struggle with low-lying obstacles due to challenges in detecting reflective surfaces and interpreting complex visual data. To overcome these limitations, we developed two deep learning-based network architectures: the Single-Image Action Network (SIAN) and the Sequence-to-Action Network with Feedback Network (SAN-FN). The first architecture processes a single image to generate an action sequence for obstacle avoidance, while the second architecture takes an image sequence and feedback from wheel velocities to infer real-time action responses. In addition, we employed Gazebo to create a 3D simulation environment and gather training data for deep learning networks, significantly reducing the cost and effort associated with data collection. The first approach achieved a 100
%
success rate in simulated obstacle avoidance tests involving puddles, while the second approach demonstrated a 76% success rate. This study highlights the significant potential of deep learning in enhancing the obstacle avoidance capabilities of walking aids, particularly in the context of challenging obstacles like water puddles.
暂无评论