Using Neural Network Model Predictive Control for Controlling Shape Memory Alloy-Based Manipulator

Nikdel, Nazila; Nikdel, Parisa; Badamchizadeh, Mohammad Ali; Hassanzadeh, Iraj

doi:10.1109/tie.2013.2258292

Cited by 83 publications

(51 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The preparation of stockpile needs to anticipate the degree of uncertainty conditions. It leads to obtaining poor customer services, miss-production schedules, incorrect capacity plans, inefficient shipping, and be a high cost for the manufacturers (Nikdel et al, 2014). Many companies have observed the lack of information on the bullwhip effect.…”

Section: Introductionmentioning

confidence: 99%

Reducing the bullwhip effect from signal demand of hybrid artificial neural network models of supply chain in Indonesia

Fradinata

2017

Int. j. adv. appl. sci.

View full text Add to dashboard Cite

The bullwhip effect becomes a problem for the factory to manage the inventory policy in the warehouse. This study proposes to reduce the bullwhip effect through signal demand forecast from hybrid artificial neural network (ANN) models. The original ANN is combined with analytical hierarchy process (AHP), Monte Carlo simulation (MC), and geometric random distribution at the parts of the input weight and input bias from the ANN. The variation of forecast signal demands from the hybrid models are used to reduce the variance from the signal customer demands. The results from this study, AHPiwANNb has the smallest mean square error (MSE) from signal demands, it implys that the variance signal demands should reduce the bullwhip effect (BWE) in the supply chain. It can be concluded that the small variance signal demand should reduce the bullwhip effect in the supply chain.

show abstract

Section: Introductionmentioning

confidence: 99%

Reducing the bullwhip effect from signal demand of hybrid artificial neural network models of supply chain in Indonesia

Fradinata

2017

Int. j. adv. appl. sci.

View full text Add to dashboard Cite

show abstract

“…A controller-based local planning scheme using model predictive control [13]- [15], [46] was proposed in [11]. In [11], an identical control scheme was used for the planner to generate a trajectory by forward simulation and for robot tracking control.…”

Section: Introductionmentioning

confidence: 99%

Kinodynamic Planner Dual-Tree RRT (DT-RRT) for Two-Wheeled Mobile Robots Using the Rapidly Exploring Random Tree

Moon

Chung

2015

IEEE Trans. Ind. Electron.

127

View full text Add to dashboard Cite

We propose a new trajectory generation scheme called dual-tree rapidly exploring random tree (DT-RRT), which is designed on the basis of a rapidly exploring random tree (RRT) method. The DT-RRT is suitable for high-speed navigation of a two-wheeled differential mobile robot. The proposed dual tree is composed of a workspace tree and a state tree. The workspace tree finds near sets in the target workspace without considering robot kinematics. Robot trajectories are generated by the extension of the state tree under the consideration of kinematic and dynamic constraints. The proposed scheme allows for different topological structures between the workspace tree and the state tree. Owing to the different structures between two trees, flexible node extensions can be achieved. As a result, the success rate of the node extension can be increased, while the computational cost can be saved. In order to improve the quality of the trajectory, we propose a reconnect-tree scheme that can modify the generated tree structure. The advantage of the reconnect-tree scheme is that the repropagation of the conventional RRT structure is not required. From simulations, the superior performance of DT-RRT was clarified in terms of computing time and success rate. The experimental result supported high quality of the generated trajectory with fast and smooth motion of the robot.Index Terms-Kinodynamic planning, mobile robots, nonholonomic motion planning, rapidly exploring random tree (RRT).

show abstract

“…In practice, many batch processes are nonlinear with A c c e p t e d M a n u s c r i p t 5 non-repetitive dynamics and unknown disturbances, which pose great challenge and difficulty for ILC. Recently, model predictive control (MPC) has also been proposed to improve control performance [22][23][24]. However, there is still space for further design methods to improve control performance under model/plant mismatch and partial actuator failure [25].…”

Section: Introductionmentioning

confidence: 99%

Improved infinite horizon LQ tracking control for injection molding process against partial actuator failures

Zhang

Gao

2015

Computers & Chemical Engineering

View full text Add to dashboard Cite

Using Neural Network Model Predictive Control for Controlling Shape Memory Alloy-Based Manipulator

Cited by 83 publications

References 21 publications

Reducing the bullwhip effect from signal demand of hybrid artificial neural network models of supply chain in Indonesia

Reducing the bullwhip effect from signal demand of hybrid artificial neural network models of supply chain in Indonesia

Kinodynamic Planner Dual-Tree RRT (DT-RRT) for Two-Wheeled Mobile Robots Using the Rapidly Exploring Random Tree

Improved infinite horizon LQ tracking control for injection molding process against partial actuator failures

Contact Info

Product

Resources

About