Fast Dual Purpose Algorithm Based on Novel Unified Cost Function

Dong, Haidi; Gao, Yingbin; He, Bing; Liu, Gang

doi:10.1109/access.2018.2808951

Cited by 4 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of adaptive process monitoring schemes, it is necessary to recursively calculate this matrix to track both the PCS and the RS, which is prohibitively expensive. The dual-purpose algorithms can perform tracking of these subspaces by switching the sign of one algorithm . FDPM is one of the dual-purpose algorithms with lower computational complexity; hence, a lower hardware cost is required in real industrial applications .…”

Section: Basic Theory and Problem Formulationmentioning

confidence: 99%

“…Many researchers have proposed alternative algorithms requiring fewer operations. Assuming that the dimension of the tracked subspace is τ and τ ≪ m , these algorithms with regard to the computational complexity are classified into three categories: high-complexity algorithms requiring O ( m 2 ) or O ( m 2 τ) operations such as first-order perturbation (FOP) analysis, rank-one modifications, and Lanczos tridiagonalizations; medium-complexity algorithms with O ( m τ 2 ) operations such as DPM and fast dual-purpose algorithms; and low-complexity algorithms requiring only O ( m τ) such as FRANS, HFRANS, FOOJA, YAST and MYAST, , and FDPM . The last category of algorithms is considered as the fast subspace tracking algorithms and the most important one from the viewpoint of real-time implementation.…”

Section: Introductionmentioning

confidence: 99%

“…In general, seeking fast subspace tracking schemes is an ongoing research topic not only in the field of fault detection but also in other applications such as signal processing, pattern recognition, machine learning, and face recognition. 37 Recursive computation of singular value decomposition (SVD) of a covariance matrix is a crucial step in adaptive process monitoring methods, which requires a high computational load. This computation cost is usually quantified by counting f lops, which is a floating-point addition, subtraction, multiplication, or division.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Simultaneous Fault Detection and Diagnosis Using Adaptive Principal Component Analysis and Multivariate Contribution Analysis

Elshenawy

Mahmoud

Chakour

2020

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Detecting and diagnosing faults without a priori knowledge are important requirements in monitoring practical industrial processes. Principal component analysis (PCA) and multivariate contribution analysis (MCA) methods belong to this category of unsupervised monitoring methods. Because the processes' operation conditions and parameters may vary with time, there is a need to online update the monitoring statistics. This paper presents an adaptive approach for fault detection and diagnosis depending on an orthogonal iteration method, i.e., the fast data projection method (FDPM), which is known as the lowest complexity one among all known subspace tracking methods. The faults are first detected using four adaptive indices of PCA, i.e., Hotelling's T 2 , Hawkins' T H 2 , SPE, and a combined index ψ. Second, adaptive diagnosis methods based on multivariate contribution analysis (MCA) are used to diagnose faults in time-varying processes. The diagnosability of the adaptive diagnosis methods is investigated, and a comparison of the adaptive diagnosis methods for the four indices is conducted. The effectiveness of the adaptive PCA-and MCA-based diagnosis methods is demonstrated by three simulation studies: a numerical example, the continuous stirred-tank reactor (CSTR) chemical process, and the Tennessee Eastman process.

show abstract

Section: Basic Theory and Problem Formulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Simultaneous Fault Detection and Diagnosis Using Adaptive Principal Component Analysis and Multivariate Contribution Analysis

Elshenawy

Mahmoud

Chakour

2020

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…Remark: The DDT system of the proposed algorithm has a computation complexity of n 2 + 4n flops per update, which is the same as n 2 + 4n of the Chen algorithm's DDT system [14], and is cheaper than n 2 + 8n of the Hasan algorithm's DDT system in [15] and n 2 +5n the projection approximation subspace tracking with deflation (PASTd) algorithm's DDT system in [16]. In addition, the operations involved in (4) are simple matrix addition and multiplication, which are easy for the systolic array implementation.…”

Section: B Dynamic Properties Of the Mca Algorithmmentioning

confidence: 99%

Novel Dual-Purpose Algorithm for Principal and Minor Component Analysis

2020

Self Cite

View full text Add to dashboard Cite

A dual-purpose algorithm is capable of estimating the principal component and minor component from input signals by simply switching the sign of some terms in the same learning rule. Compared with single-purpose algorithms, a dual-purpose algorithm has many advantages. In this paper, a novel dual-purpose algorithm is proposed based on the study of some existing algorithms. The dynamic behavior of this dual-purpose algorithm is investigated by the deterministic discrete time method. Some constraint conditions, which provide a way to choose the initial weight vector and learning factor, are also derived to guarantee its convergence. Numerical simulation results not only demonstrate the fast convergence of the proposed algorithm but also demonstrate the correctness of the convergence conditions. INDEX TERMS Dual-purpose algorithm, principal component analysis, minor component analysis, dynamic behavior analysis.

show abstract

“…The cost coefficient to enlarge or reduce the generalized cost is introduced [51]. The reliability cost can be distributed to different units.…”

Section: Rational Investment For a Better User Experience A Reliamentioning

confidence: 99%

Online Car-Hailing System Performance Analysis Based on Bayesian Network

2019

View full text Add to dashboard Cite

The concept of the sharing economy has attracted wide attention due to its huge impact on transforming traditional industries. Online car-hailing, combining the sharing economy and ICT technologies, shapes a new landscape, which can greatly shorten the traveler's waiting time and reduce the emptyrun rate of cars (such as Uber and DiDi). However, a few comprehensive studies have been conducted on the sustainable development of online car-hailing considering both the user experience and the operational cost. To address this issue, this paper systematically studies the influencing factors, their relations, and their impacts on online car-hailing in an empirical way. First, an index system in four key aspects, namely service, price, safety, and traveling time, is established to evaluate the user experience. Second, the Bayesian network theory is employed to model the complexity of each factor and the extent of its influence on the online car-hailing system with expert scores. The two most important influence paths affecting the passengers' choices of online car-hailing are determined. Third, we further construct an investment allocation model with the aim of minimizing the economic cost of the online car-hailing system while maintaining the system performance, considering the limiting factors, such as the complexity and cost. Finally, we perform a simulation experiment, which generates some practical suggestions for improving the online car-hailing system.

show abstract

Fast Dual Purpose Algorithm Based on Novel Unified Cost Function

Cited by 4 publications

References 16 publications

Simultaneous Fault Detection and Diagnosis Using Adaptive Principal Component Analysis and Multivariate Contribution Analysis

Simultaneous Fault Detection and Diagnosis Using Adaptive Principal Component Analysis and Multivariate Contribution Analysis

Novel Dual-Purpose Algorithm for Principal and Minor Component Analysis

Online Car-Hailing System Performance Analysis Based on Bayesian Network

Contact Info

Product

Resources

About