Open Access. Powered by Scholars. Published by Universities.®
- Discipline
Articles 1 - 13 of 13
Full-Text Articles in Mechanical Engineering
Neural Network Approach For Obstacle Avoidance In 3-D Environments For Uavs, Vivek Yadav, Xiaohua Wang, S. N. Balakrishnan
Neural Network Approach For Obstacle Avoidance In 3-D Environments For Uavs, Vivek Yadav, Xiaohua Wang, S. N. Balakrishnan
Mechanical and Aerospace Engineering Faculty Research & Creative Works
In this paper a controller design is proposed to get obstacle free trajectories in a three dimensional urban environment for unmanned air vehicles (UAVs). The controller has a two-layer architecture. In the upper layer, vision-inspired Grossberg neural network is proposed to get the shortest distance paths. In the bottom layer, a model predictive control (MPC) based controller is used to obtain dynamically feasible trajectories. Simulation results are presented for to demonstrate the potential of the approach.
Development And Analysis Of A Feedback Treatment Strategy For Parturient Paresis Of Cows, Radhakant Padhi, S. N. Balakrishnan
Development And Analysis Of A Feedback Treatment Strategy For Parturient Paresis Of Cows, Radhakant Padhi, S. N. Balakrishnan
Mechanical and Aerospace Engineering Faculty Research & Creative Works
An intelligent on-line feedback treatment strategy based on nonlinear optimal control theory is presented for the parturient paresis of cows. A limitation in the development of an existing nonlinear mathematical model for the homogeneous system is addressed and further modified to incorporate a control input. A neural network based optimal feedback controller is synthesized for the treatment of the disease. Detailed studies are used to analyze the effectiveness of a feedback medication strategy and it is compared with the current "impulse" strategy. The results show that while the current practice may fail in some cases, especially if it is carried …
State-Constrained Agile Missile Control With Adaptive-Critic-Based Neural Networks, Dongchen Han, S. N. Balakrishnan
State-Constrained Agile Missile Control With Adaptive-Critic-Based Neural Networks, Dongchen Han, S. N. Balakrishnan
Mechanical and Aerospace Engineering Faculty Research & Creative Works
In this study, we develop an adaptive-critic-based controller to steer an agile missile that has a constraint on the minimum flight Mach number from various initial Mach numbers to a given final Mach number in minimum time while completely reversing its flightpath angle. This class of bounded state space, free final time problems is very difficult to solve due to discontinuities in costates at the constraint boundaries. We use a two-neural-network structure called "adaptive critic" in this study to carry out the optimization process. This structure obtains an optimal controller through solving optimal control-related equations resulting from a Hamiltonian formulation. …
Proper Orthogonal Decomposition Based Feedback Optimal Control Synthesis Of Distributed Parameter Systems Using Neural Networks, Radhakant Padhi, S. N. Balakrishnan
Proper Orthogonal Decomposition Based Feedback Optimal Control Synthesis Of Distributed Parameter Systems Using Neural Networks, Radhakant Padhi, S. N. Balakrishnan
Mechanical and Aerospace Engineering Faculty Research & Creative Works
A new method for optimal control design of distributed parameter systems is presented in this paper. The concept of proper orthogonal decomposition is used for the model reduction of distributed parameter systems to form a reduced order lumped parameter problem. The optimal control problem is then solved in the time domain, in a state feedback sense, following the philosophy of ''adaptive critic'' neural networks. The control solution is then mapped back to the spatial domain using the same basis functions. Numerical simulation results are presented for a linear and nonlinear one-dimensional heat equation problem in an infinite time regulator framework.
Adaptive Critic Based Neuro-Observer, Xin Liu, S. N. Balakrishnan
Adaptive Critic Based Neuro-Observer, Xin Liu, S. N. Balakrishnan
Mechanical and Aerospace Engineering Faculty Research & Creative Works
A new Neural Network (NN) based observer design method for nonlinear systems represented by nonlinear dynamics and linear/nonlinear measurement is proposed in this paper. In this new approach, as the first step, the observer design problem is changed into a "controller" design problem by establishing the error dynamics, and then the Adaptive Critic (AC) based approach is applied on this error dynamics to design a 'controller', such that the errors are driven to zero. The resulting observer has inherent robustness from the AC based design approach. Some simulations are presented to illustrate the effectiveness of this approach.
An Optimal Control Based Treatment Strategy For Parturient Paresis Using Neural Networks, Radhakant Padhi, S. N. Balakrishnan
An Optimal Control Based Treatment Strategy For Parturient Paresis Using Neural Networks, Radhakant Padhi, S. N. Balakrishnan
Mechanical and Aerospace Engineering Faculty Research & Creative Works
An optimal online feedback treatment strategy is developed for the parturient paresis of cows, based on nonlinear optimal control theory. A limitation in the development of an existing mathematical model for calcium homeostasis is addressed and the model is extended to incorporate control inputs. An optimal feedback controller is synthesized for the nonlinear system using neural networks. Though the main aim of this paper is to solve the biomedical control problem, the methodology presented in this paper is a general computational tool, which can be applied to solve a fairly general class nonlinear optimal control problems.
Use Of Time Varying Dynamics In Neural Network To Solve Multi-Target Classification, S. N. Balakrishnan, J. Rainwater
Use Of Time Varying Dynamics In Neural Network To Solve Multi-Target Classification, S. N. Balakrishnan, J. Rainwater
Mechanical and Aerospace Engineering Faculty Research & Creative Works
Several types of solutions exist for multiple target tracking. These techniques are computation-intensive and in some cases very difficult to operate online. The authors report on a backpropagation neural network which has been successfully used to identify multiple moving targets using kinematic data (time, range, range-rate and azimuth angle) from sensors to train the network. Preliminary results from simulated scenarios show that neural networks are capable of learning target identification for three targets during the time period used during training and a time period shortly after. This effective classification period can be extended by the use of networks in coordination …
Moving Object Recognition And Guidance Of Robots Using Neural Networks, Abhijit Neogy, S. N. Balakrishnan, Cihan H. Dagli
Moving Object Recognition And Guidance Of Robots Using Neural Networks, Abhijit Neogy, S. N. Balakrishnan, Cihan H. Dagli
Mechanical and Aerospace Engineering Faculty Research & Creative Works
The design of a robust guidance system for a robot is discussed. The two major tasks for this guidance system are the online recognition of a moving object invariant to rotation and translation, and tracking the moving object using a neural-network-driven vision system. This system included computer software ported to the IBM PC and interfaced with an IBM 7535 robot. The operation of this guidance system involved recognition of a moving object and the ability to track it till the robot and effector was in close proximity of the object. It was found that the robot was able to track …
Planning And Control Of A Robotic Manipulator Using Neural Networks, Xavier J. R. Avula, Heng Ma, Anil Malkani, Jay-Shinn Tsai, Luis C. Rabelo
Planning And Control Of A Robotic Manipulator Using Neural Networks, Xavier J. R. Avula, Heng Ma, Anil Malkani, Jay-Shinn Tsai, Luis C. Rabelo
Chemical and Biochemical Engineering Faculty Research & Creative Works
An architecture which utilizes two artificial neural systems for planning and control of a robotic arm is presented. The first neural network system participates in the trajectory planning and the motion decision-making process. The second neural network system provides the correct sequence of control actions with a high accuracy due to the utilization of an unsupervised/supervised neural network scheme. The utilization of a hybrid hierarchical/distributed organization, supervised/unsupervised learning models, and forward modeling yielded an architecture with capabilities of high level functionality.
Hierarchical Neurocontroller Architecture For Robotic Manipulation, Xavier J. R. Avula, Luis C. Rabelo
Hierarchical Neurocontroller Architecture For Robotic Manipulation, Xavier J. R. Avula, Luis C. Rabelo
Chemical and Biochemical Engineering Faculty Research & Creative Works
A hierarchical neurocontroller architecture consisting of two artificial neural network systems for the manipulation of a robotic arm is presented. The higher-level network system participates in the delineation of the robot arm workspace and coordinates transformation and the motion decision-making process. The lower-level network provides the correct sequence of control actions. A straightforward example illustrates the architecture''s capabilities, including speed, adaptability, and computational efficiency
Hierarchical Neurocontroller Architecture For Intelligent Robotic Manipulation, Xavier J. R. Avula, Luis C. Rabelo
Hierarchical Neurocontroller Architecture For Intelligent Robotic Manipulation, Xavier J. R. Avula, Luis C. Rabelo
Mechanical and Aerospace Engineering Faculty Research & Creative Works
A hierarchical neurocontroller architecture consisting of two artificial neural network systems for the manipulation of a robotic arm is presented. The higher-level neural system participates in the delineation of the robot arm workspace and coordinates transformation and the motion decision-making process. The lower one provides the correct sequence of control actions. The capabilities, including speed, adaptability, and computational efficiency, of the developed architecture are illustrated by an example.
Intelligent Control Of A Robotic Arm Using Hierarchical Neural Network Systems, Xavier J. R. Avula, Luis C. Rabelo
Intelligent Control Of A Robotic Arm Using Hierarchical Neural Network Systems, Xavier J. R. Avula, Luis C. Rabelo
Chemical and Biochemical Engineering Faculty Research & Creative Works
Two artificial neural network systems are considered in a hierarchical fashion to plan the trajectory and control of a robotic arm. At the higher level of the hierarchy the neural system consists of four networks: a restricted Coulomb energy network to delineate the robot arm workspace; two standard backpropagation (BP) networks for coordinates transformation; and a fourth network which also uses BP and participates in the trajectory planning by cooperating with other knowledge sources. The control emulation process which is developed using a second neural system at a lower hierarchical level provides the correct sequence of control actions. An example …
Parallel Implementation Of A Recursive Least Squares Neural Network Training Method On The Intel Ipsc/2, James Edward Steck, Bruce M. Mcmillin, K. Krishnamurthy, M. Reza Ashouri, Gary G. Leininger
Parallel Implementation Of A Recursive Least Squares Neural Network Training Method On The Intel Ipsc/2, James Edward Steck, Bruce M. Mcmillin, K. Krishnamurthy, M. Reza Ashouri, Gary G. Leininger
Computer Science Faculty Research & Creative Works
An algorithm based on the Marquardt-Levenberg least-square optimization method has been shown by S. Kollias and D. Anastassiou (IEEE Trans. on Circuits Syst. vol.36, no.8, p.1092-101, Aug. 1989) to be a much more efficient training method than gradient descent, when applied to some small feedforward neural networks. Yet, for many applications, the increase in computational complexity of the method outweighs any gain in learning rate obtained over current training methods. However, the least-squares method can be more efficiently implemented on parallel architectures than standard methods. This is demonstrated by comparing computation times and learning rates for the least-squares method implemented …