Toward Blind Nonlinearity Estimation in Back-Propagation Algorithm for Coherent Optical Transmission Systems

Jiang, Lin; Yan, Lianshan; Yi, Anlin; Pan, Yan; Ge, Jun; Dai, Liangliang; Pan, Wei; Luo, Bin

doi:10.1364/ofc.2017.w1g.3

Cited by 7 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The performance of ELM is compared with two other stateof-the-art machine learning algorithms, Support Vector Regression (SVR) [17] and Back-Propagation (BP) [18]. The number of hidden neurons and support vectors were selected using similar constructive-destructive procedures [20].…”

Section: Performance Resultsmentioning

confidence: 99%

Dynamic Positioning Reliability Index (DP-RI) and Offline Forecasting of DP-RI During Complex Marine Operations

Fernandez

Kumar

Woo

et al. 2018

Volume 1: Offshore Technology

View full text Add to dashboard Cite

The Dynamic Positioning (DP) System is a complex system with significant levels of integration between many sub-systems to perform diverse control functions. The extent of information managed by each sub-system is enormous. The complex level of integration between sub-systems creates more possible failure scenarios. A systematic analysis of all failure scenarios is tedious and for an operator to handle any such catastrophic situation is breath taking. There are many accidents where a failure in a DP system has resulted in fatalities and environmental pollution. Therefore, reliability assessment of a DP system is critical for safe and efficient operation of marine and offshore vessels. Traditionally, the reliability of a DP system is assessed during the design stage by methodologies such as Failure Mode Effects and Analysis (FMEA), Proving Trials, Hardware In-the Loop (HIL) testing, Site-Specific Risk Analysis, DP capability Analysis and during operation by annual trials to verify functionality. All these methods are time consuming, involving a lot of human effort and notably no analysis of previous accidents are indicated in the reliability assessment. This imposes in-built uncertainty and risk in DP system during operation. In this paper, a new concept of Dynamic Positioning Reliability Index (DP-RI) is introduced and a state-of-the-art advisory decision making tool is proposed. This tool is developed based on information from various sources including Offshore Reliability Data (OREDA), International Marine Contractors Association (IMCA) Accident database, DP vendor equipment failure databases, DP System supplier’s manuals, previous system level FMEA and HIL testing results, Site specific risk analysis documents, Project design specification and Operator’s operational experiences. Thus, DP-RI addresses the pitfalls of existing reliability assessment methods and will be an efficient tool in reducing the number of DP-related accidents.

show abstract

Section: Performance Resultsmentioning

confidence: 99%

Dynamic Positioning Reliability Index (DP-RI) and Offline Forecasting of DP-RI During Complex Marine Operations

Fernandez

Kumar

Woo

et al. 2018

Volume 1: Offshore Technology

View full text Add to dashboard Cite

show abstract

“…GRU–RNN architecture has updating and resetting gates to prevent error flow vanishing by a long time for back-propagation (Jiang et al , 2017). To update the weights W and U in the RNN, the BPTT algorithm (Mikolov et al , 2014) is used through the time.…”

Section: Our Proposed Methods For the Prediction Of Nssmentioning

confidence: 99%

A new method for the prediction of network security situations based on recurrent neural network with gated recurrent unit

Feng

Fan

2018

IJICC

View full text Add to dashboard Cite

Purpose The purpose of this paper is to solve the shortage of the existing methods for the prediction of network security situations (NSS). Because the conventional methods for the prediction of NSS, such as support vector machine, particle swarm optimization, etc., lack accuracy, robustness and efficiency, in this study, the authors propose a new method for the prediction of NSS based on recurrent neural network (RNN) with gated recurrent unit. Design/methodology/approach This method extracts internal and external information features from the original time-series network data for the first time. Then, the extracted features are applied to the deep RNN model for training and validation. After iteration and optimization, the accuracy of predictions of NSS will be obtained by the well-trained model, and the model is robust for the unstable network data. Findings Experiments on bench marked data set show that the proposed method obtains more accurate and robust prediction results than conventional models. Although the deep RNN models need more time consumption for training, they guarantee the accuracy and robustness of prediction in return for validation. Originality/value In the prediction of NSS time-series data, the proposed internal and external information features are well described the original data, and the employment of deep RNN model will outperform the state-of-the-arts models.

show abstract

“…Under this background, various adaptive DBP methods have been proposed without knowing the exact channel parameters. Based on the phase variance or Godard's error as the cost function (CF), adaptive DBP (ADBP) algorithms based on gradient descent algorithm have been proposed to estimate the nonlinear coefficient γ 4,5 . Based on the genetic algorithm to estimate the signal power of each span, an ADBP algorithm is proposed to minimize the Kerr nonlinearity noise 6 .…”

Section: Introductionmentioning

confidence: 99%

Data reduction adaptive digital back propagation algorithm

Jiang,

Zhang,

Xin

et al. 2023

Fourteenth International Conference on Information Optics and Photonics (CIOP 2023)

View full text Add to dashboard Cite

Toward Blind Nonlinearity Estimation in Back-Propagation Algorithm for Coherent Optical Transmission Systems

Cited by 7 publications

References 6 publications

Dynamic Positioning Reliability Index (DP-RI) and Offline Forecasting of DP-RI During Complex Marine Operations

Dynamic Positioning Reliability Index (DP-RI) and Offline Forecasting of DP-RI During Complex Marine Operations

A new method for the prediction of network security situations based on recurrent neural network with gated recurrent unit

Data reduction adaptive digital back propagation algorithm

Contact Info

Product

Resources

About