RVFLN-based online adaptive semi-supervised learning algorithm with application to product quality estimation of industrial processes

Dai, Wei; Hu, Jincheng; Cheng, Yuhu; Wang, Xuesong; Chai, Tianyou

doi:10.1007/s11771-019-4257-6

Cited by 8 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Random vector functional link network is a special type of single-layer feed-forward neural network (SLFN). 23,24 RVFLN has direct interlinks between input and output, and the weights in the enhancement layer of RVFLN are assigned randomly as shown in Figure 10. The major advantages of the RVFLN are a simple architecture, faster learning speed, and less computation time.…”

Section: Basic Rvfln Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Effective fault distance estimation and diagnosis in the PV based DC‐ring network using Hilbert Huang transform and weighted online sequential random vector functional network

Anjaiah

Dash

2021

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

This paper proposes a novel approach for fault detection, classification, and distance estimation of five kinds of faults (ie, cable and Arc faults) in the PV-based DC-ring microgrid. The proposed approach is based on the Hilbert Huang Transform (HHT) and online sequential random vector functional link network (OS-RVFLN). Initially, differential current signals are passed through empirical mode decomposition (EMD) to yield intrinsic mode functions (IMFs). Among the series of IMFs, more efficient IMFs are selected based on the threshold of maximum weighted kurtosis index (M-WKI) value for fault diagnosis. The selected IMFs are passed through Hilbert transform (HT) for determining the instantaneous frequency, magnitude spectrum, and Hilbert energy. Then, the Teager energy operator (TEO) is applied to the more effective IMF among the selected IMFs of each DC fault for fault detection. The most suitable target features are extracted from the selected efficient IMFs. This feature set data is initialized to the proposed HHT-OSRVFLN algorithm for five kinds of faults classification and its location estimation. The performance of the proposed algorithm in the proposed microgrid is proved in terms of low fault detection time, superior classification accuracy, and low relative error through different case studies by consuming minimum computation time in MATLAB/Simulink environment. Finally, the digital architecture of the proposed method is designed and simulated in Xilinx ISE 14.5 software environment to estimate the fault location. The Chip scope hardware debugging output proves the correctness, simplicity, feasibility, practicability, and robustness of the proposed method for online fault diagnosis.List of Symbols and Abbreviations: R f , fault resistance; Idc 1 , Idc 2 , DC currents; Vdc 1 , Vdc 2 , DC voltages; α 1 , α 2 , attenuation constants; ωd 1 , ωd 2 , damping frequencies; ω n1 , ω n2 , natural frequencies; I 3 , differential current; I avg , average current; SD (k), squared difference; M e (t), mean envelope; E [C(t)], Teager energy of the signal; ω(t), instantaneous frequency; θ(t), phase angle; I b , best IMF; H, hidden layers; β 0 , output weight matrix; Z, output of the signal; d pfd , predicted fault distance; d actl , actual fault distance; t c , computation time; CC, correlation coefficient; EMD, empirical mode decomposition; FPGA, field programmable gate array; HHT, Hilbert Haung transform; ICON, integrator controller; ILA, integrated logic analyzer; IMF, intrinsic mode functions; KI, Kurtosis index; MAC, multiply and accumulate unit; OS-RVFLN, online sequential random vector functional link; TEO, Teager energy operator; VHDL, hardware description language; WKI, weighted kurtosis index.

show abstract

Section: Basic Rvfln Algorithmmentioning

confidence: 99%

“…These techniques are susceptible to different volatility variations and loss of information due to kernel selection. 14,23,24 To overcome these drawbacks and to provide reliable as well as uninterrupted power to the customer, an efficient protection scheme is required for the DC ring network.…”

Section: Introductionmentioning

confidence: 99%

Effective fault distance estimation and diagnosis in the PV based DC‐ring network using Hilbert Huang transform and weighted online sequential random vector functional network

Anjaiah

Dash

2021

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

show abstract

“…Igelnik and Pao (1995) proved that RVFLN with random parameters chosen from the uniform distribution defined over a range can be a universal approximator with probability one for continuous functions. RVFLN has been applied to industrial processes for modeling (Guan & Cui, 2020) and estimation (Dai et al, 2019). At present, an advanced randomized neural network, named stochastic configuring networks (SCNs), was proposed in Wang and Li (2017).…”

Section: Introductionmentioning

confidence: 99%

Short‐term photovoltaic power forecasting with adaptive stochastic configuration network ensemble

Guo

Wang

et al. 2022

WIREs Data Min & Knowl

Self Cite

View full text Add to dashboard Cite

The volatility and intermittency of solar energy seriously restrict the development of the photovoltaic (PV) industry. Accurate forecast of short-term PV power generation is essential for the optimal balance and dispatch of power plants in the smart grid. This article presents a machine learning approach for analyzing the volt-ampere characteristics and influential factors on PV data. A correlation analysis is employed to discover some hidden characteristic variables. Then, an adaptive ensemble method with stochastic configuration networks as base models (AE-SCN) is proposed to construct the PV prediction model, which integrates bagging and adaptive weighted data fusion algorithms. Compared with the original SCN, SCN ensemble (SCNE) and random vector functional-link network (RVFLN), linear regression model, random forest model and autoregressive integrated moving average (ARMA) model, AE-SCN performs favorably in the terms of the prediction accuracy.

show abstract

Enhancing incremental deep learning for FCCU end-point quality prediction

Zhang

Zou

2020

Information Sciences

View full text Add to dashboard Cite

RVFLN-based online adaptive semi-supervised learning algorithm with application to product quality estimation of industrial processes

Cited by 8 publications

References 20 publications

Effective fault distance estimation and diagnosis in the PV based DC‐ring network using Hilbert Huang transform and weighted online sequential random vector functional network

Effective fault distance estimation and diagnosis in the PV based DC‐ring network using Hilbert Huang transform and weighted online sequential random vector functional network

Short‐term photovoltaic power forecasting with adaptive stochastic configuration network ensemble

Enhancing incremental deep learning for FCCU end-point quality prediction

Contact Info

Product

Resources

About