Research on fault location technology based on BP neural network in DWDM optical network

Liao, Xiaomin; Zhang, Yinfa; Yang, Shu-Qing; Lin, Changxing

doi:10.1007/s11801-008-8086-3

Cited by 3 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because of this, the BP neural network is not the best choice for analysing the warning signal. So, this dissertation tries to fill in the gaps by adding to the study that was done in Reference [25]. The channel-based network model is used to figure out what's wrong with the optical transport network.…”

Section: Related Workmentioning

confidence: 99%

Fault Identification in Optical Transport Network Using CNN

Ravindra L. Pardhi

2024

jes

View full text Add to dashboard Cite

The growing diversity Regarding the provision of information and services transmitted Using optical technology transport networks (OTN) has made network survival a crucial issue in current study. Fault detection refers to the process of identifying faults that arise from various issues such as packet loss, disconnection, and others in the OTN. The determination of the fault location in an OTN is highly significant in the analysis of the resilience of optical networks. This study presents a fault diagnosis system that utilises a Convolutional Neural Network (CNN), focusing primarily on distinguishing between hard faults (HF) and soft faults (SF). The CNN is implemented in where the fault is situated domain of OTN to determine the presence or absence of potential fault locations. The notion An F-Measure is implemented in order to quantify the impact of positioning.utilising Location, time, mean squared error (MSE), and F-measure. The scientific investigation demonstrates that the suggested CNN neural network achieves the highest performance. The suggested CNN has a reduced localization time and achieves an F1-score of 0.98 after 85 iterations. This level of accuracy and real-time performance fulfils the requirements for fault identification. Hence, there is significant potential and practical utility in incorporating neural networks in the field of identifying and locating faults in optical transport networks.

show abstract

Section: Related Workmentioning

confidence: 99%

Fault Identification in Optical Transport Network Using CNN

Ravindra L. Pardhi

2024

jes

View full text Add to dashboard Cite

show abstract

“…Forecasting of the state of OD is carried out on the same principle as the formation of a training sample (Wang and Hong, 2000;Pu and Xu, 2001;Liao et al, 2008;Wu and Feng, 2017;Yamada, 2010). There are two possibilities: onestep and multi-step forecasting (Yousif et al, 2015).…”

Section: Asmentioning

confidence: 99%

NEUROIDENTIFICATION WITH NEURO-SELF Tuning TO ENSURE THE OPERATION OF THE CURRENT LOOP OF THE ELECTRIC DRIVE WITH THE DESIRED STATIC ANDDYNAMIC CHARACTERISTICS

Buyankin¹

2018

PTQ

View full text Add to dashboard Cite

The synthesis of neural regulators for control systems of electric drives is considered in the article. The stable work and features of the application of neural regulators in closed circuits are analyzed. Neuroregulators self-adjust when changing the parameters of the control object. Information on the change in the parameters of the control object is compared with the optimal desired characteristics of the reference model, training signals are generated for the neuroregulators, which provide the necessary optimal static and dynamic characteristics of electric drive.

show abstract

“…The connection weight matrixes of 1 , 2 , 3 , and 4 can be updated according to the gradient descent method, which can be expressed as follows [29,30]:…”

Section: Improved Elman Neuralmentioning

confidence: 99%

A Cooperative Control Method for Fully Mechanized Mining Machines Based on Fuzzy Logic Theory and Neural Networks

Tan

Zhou³

et al. 2014

Advances in Mechanical Engineering

View full text Add to dashboard Cite

In a fully mechanized mining face, the coordinated control of coal mining machines has a significant promoting effect to perfect the mining environment and improve the efficiency of coal production and has become a research focus all over the world. In this paper, a cooperative control method based on the integration of fuzzy logic theory and neural networks was proposed. The improved Elman neural network (ENN) through a threshold strategy was presented to predict the running parameters of coal mining machines. On the basis of coupling analysis of coal mining machines, the expert knowledge base of scraper conveyor was established based on fuzzy logic theory. Furthermore, the probabilistic neural network (PNN) was applied to evaluate the running status of scraper conveyor, and the cooperative control flow was designed and analyzed. Finally, a simulation example was provided and the comparison results illustrated that the proposed method was feasible and superior to the manual control.

show abstract

Research on fault location technology based on BP neural network in DWDM optical network

Cited by 3 publications

References 1 publication

Fault Identification in Optical Transport Network Using CNN

Fault Identification in Optical Transport Network Using CNN

NEUROIDENTIFICATION WITH NEURO-SELF Tuning TO ENSURE THE OPERATION OF THE CURRENT LOOP OF THE ELECTRIC DRIVE WITH THE DESIRED STATIC ANDDYNAMIC CHARACTERISTICS

A Cooperative Control Method for Fully Mechanized Mining Machines Based on Fuzzy Logic Theory and Neural Networks

Contact Info

Product

Resources

About