This work aims at the efficient control of a mobile robot using optimised PID controller. The two DC motors are controlled precisely which in turn regulate the movement of the robot. Numerous techniques have been deve...
This work aims at the efficient control of a mobile robot using optimised PID controller. The two DC motors are controlled precisely which in turn regulate the movement of the robot. Numerous techniques have been developed to enhance the PID control strategy applied to linear and non-linear systems. In this work, first the actuator model of the mobile robot is simulated and then the optimal computation techniques i.e., Simulated Annealing (SA), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) are considered to tune the gains of PID controller. ITAE is considered as the objective function for optimization. The comparative study reveals that PSO tuned PID provides the least ITAE and is thus used for the mobile robot. The velocity plots are analysed for various positions of wheels. The motion characteristics for different paths are also analysed which justify the effectiveness of the PSO-PID controller over the other considered techniques.
Budding Micro, Small and Medium Enterprises (MSMEs) dealing with solar PV manufacturing, installation, and maintenance need a way to test their outsourced and inhouse PV modules. To keep up with the required power gen...
详细信息
PID controllers have been in use for numerous decades. Many researchers have developed and discussed their tuning methods. In this presented work, we discuss different types of tuning methods for Proportional Integral...
详细信息
This paper involves the modeling and prediction of non linear systems. The modelling of a nonlinear system will be accomplished using deep learning techniques. The dataset that is considered in this case is of time se...
详细信息
This paper presents the active realization of a voltage mode fractional-order biquad filter which is capable of generating inverting low-pass, non-inverting band-pass along with a high-pass response. This filter has b...
详细信息
The primary objective of this work is to present a detailed performance analysis of various 2×2 solar photovoltaic (SPV) array configurations, i.e., series (S), parallel (P), series-parallel (SP), and total-cross...
详细信息
This paper focuses on finding the shortest and correct path for the robots without any collision with the objects in its environment. Generally global (static) and local environments are used for path planning of mobi...
详细信息
Water is important for survival. With increasing cases of water quality deterioration, it is need of the hour to use brimming machine learning technologies which can aid in water quality prediction and further classif...
详细信息
Long Short-Term Memory (LSTM) is a Recurrent Neural Network (RNN) that overcomes typical neural network constraints. Because of its ability to record temporal dependencies and solve nonlinear equations, long-term data...
Long Short-Term Memory (LSTM) is a Recurrent Neural Network (RNN) that overcomes typical neural network constraints. Because of its ability to record temporal dependencies and solve nonlinear equations, long-term data can be simply managed. LSTM is intended to alleviate the problems of RNN's vanishing gradient and exploding gradient difficulties. In this paper, we used LSTM to solve nonlinear plant equations with a gradient descent-based back propagation approach and retrieved the plant's output as well as other performance measures including Average Mean Square Error (AMSE) and Total Mean Average Error (TMAE). When the output of an LSTM is compared to that of a feed-forward Neural Network (FFNN), the LSTM outshines the FFNN. All the parameters of both models, such as iteration count and learning rate are kept constant.
A Double Internal Loop Recurrent Neural Network (DILRNN) model is proposed for Multiple Input Multiple Output (MIMO) system to obtain improved output using Gradient Descent based Back Propagation Algorithm. In the mod...
A Double Internal Loop Recurrent Neural Network (DILRNN) model is proposed for Multiple Input Multiple Output (MIMO) system to obtain improved output using Gradient Descent based Back Propagation Algorithm. In the modelling of DILRNN, three feedback loops are taken i.e., the first feedback is taken from the unit delay of the output to the hidden layer, the second feedback is taken from the previous value of hidden layer to itself and the last feedback is taken from the previous value of output to output. The weight is updated with the help of the algorithm after every iteration. The output of the proposed DILRNN model reduces error significantly vis-à-vis other Recurrent Neural Network (RNN) models for constant value of iterations and epochs. The statistical parameters such as RMSE and TMAE for the proposed model are greatly in comparison to other models and thereby enhances the accuracy of the model.
暂无评论