Levenberg-marquardt algorithm to identify the fault analysis for industrial applications

Bhuvaneswari, P. T. V.; G.P, Ramesh

doi:10.14419/ijet.v7i1.2.9040

Cited by 4 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Delays with are assumed independent and uniformly distributed random variables between 0 and Ts. The soft decision receiver output can be express in the following: (8) where m(t) is correlated mask, its expression as: (9) Where The receiver estimates the bit according to all signals contribution: (10) where Zu , Zmui and Zn represent the useful signal, the MUI noise and thermal noise, respectively. For orthogonal and the best binary PPM modulation, we use ML decision rule (11)…”

Section: Ts =Tb /Nsmentioning

confidence: 99%

“…In training, the number of hidden layers, the number of the neurons in the hidden layers and Marquardt parameters were determined after trying various network structures, The network model used is a three-layer feed-forward network as illustrated in figure.4, two-layer feed-forward network with sigmoid hidden neurons and onelayer feed-forward network with linear output neurons, After a few experimental run, the number of neurons in the hidden layers was set to 20 neurons for each layer, [9][10]. The experimental data were to be separated into training, testing and validation data.…”

Section: Proposed Modelmentioning

confidence: 99%

See 1 more Smart Citation

Optimal PPM-Shift Based on Artificial Neural Network for 2PPM-TH-UWB systems

Maaref¹,

Elahmar²

2019

JESTR

View full text Add to dashboard Cite

The optimal value of the PPM-Shift related with the binary TH-PPM should be cautiously selected to make sure the finest performance of the PPM-TH-UWB system for a given pulse shape utilized in a specific submission. In addition, it has been demonstrated that the ideal choice of the PPM-Shift parameter denotes back to the autocorrelation characteristics of the pulse shape under examination. In this paper, artificial neural network (ANN) with Levenberg-Marquardt Learning Algorithm (LM) is proposed to optimize PPM-shift for the TH-UWB under Standard Gaussian Approximation (SGA) with multi-Rate system, this optimal PPM-Shift is a function of the data bit Rate (Rb) and Gaussian pulse and its derivatives. Theoretical analysis and simulation results show that our algorithm rapidly converges to the optimal PPM-Shift and has the advantages of low bit-error rate.

show abstract

Section: Ts =Tb /Nsmentioning

confidence: 99%

Section: Proposed Modelmentioning

confidence: 99%

Optimal PPM-Shift Based on Artificial Neural Network for 2PPM-TH-UWB systems

Maaref¹,

Elahmar²

2019

JESTR

View full text Add to dashboard Cite

show abstract

“…Then the cluster centroid of a particle is updated based on the velocity and position equation and repeated until maximum number of iteration is reached [11]. It tends to incorporate the small categorizes into larger clusters [12]. More optimal solution is considered by the fitness function.…”

Section: Introductionmentioning

confidence: 99%

Comparative Analysis of Distributive Optimized Clustering Techniques in Cognitive Radio Networks

Babu¹,

Amudha²

2018

IJET

View full text Add to dashboard Cite

In this paper we study and compare the performance of Distributed Firefly Optimized Clustering (DFOC) with Distributed Swarm Optimized Clustering (DSOC) optimization techniques used for the dynamic clustering. Proposed Distributed Firefly Optimized Clustering (DFOC) is an optimization algorithm based on the function of attractiveness of firefly behavior. All the cognitive nodes move towards the brighter firefly with random velocity to form an organized cluster with least computation time. In the existing DSOC method each particle's best position and velocity are evaluated according to the objective function until an optimum global best position is reached. The convergence rate of DSOC is similar to Genetic Algorithm (GA). The proposed DFOC, the SU power is reduced to 7.34% for 100 numbers of SUs.compared to DSOC.

show abstract

“…The Levenberg-Marquardt model can also be used as a process for improving a management. Although in general, this model is commonly used for a machine learning that has certain intelligence [9]. As it was done by Hossein Mirzaee [10] where the Levenberg-Marquardt had been implemented the learning algorithm with a neural network approach.…”

Section: Introductionmentioning

confidence: 99%

The Implementation of the Levenberg-Marquardt for Continuous Improvement of the Management System for BPK PENABUR Education Foundation in Jakarta

Kusuma¹,

Wibawa²,

Sitepu³

2018

IJET

View full text Add to dashboard Cite

Improving the quality of the management system for schools that have several branches requires a big commitment from executor to managerial. By using the Levenberg-Marquardt education system concept that belongs to 15 branches, it is divided into 5 subsystems and 3 layers. The subsystems are in the form of learning dynamics, organizational transformation, human development, knowledge management and technology applications. Layer 1 is the managerial rank in each branch, the second layer is the leader as the first validator to be forwarded to the third layer, which is the head office with the final decision at the top of BPK Penabur organization. The improvement of management system starts from the gap between each subsystem that has been agreed as the standard. All components covering the secretariat (administration), Principal, Deputy Principal (student, curriculum, Facility SBI), teachers, librarians and laboratory assistants were the subjects responsible for the improvement of the management performance. While the president director and organization leader are the last layer that determines the better changes that is run. After being done gradually and continuously, the gap occurred is decreasing. By reducing the gap, the performance of the management at BPK PENABUR school can become better

show abstract

Levenberg-marquardt algorithm to identify the fault analysis for industrial applications

Cited by 4 publications

References 12 publications

Optimal PPM-Shift Based on Artificial Neural Network for 2PPM-TH-UWB systems

Optimal PPM-Shift Based on Artificial Neural Network for 2PPM-TH-UWB systems

Comparative Analysis of Distributive Optimized Clustering Techniques in Cognitive Radio Networks

The Implementation of the Levenberg-Marquardt for Continuous Improvement of the Management System for BPK PENABUR Education Foundation in Jakarta

Contact Info

Product

Resources

About