Steel plates fault diagnosis on the basis of support vector machines

Tian, Yu‐Ping; Fu, Mengyu; Wu, Fang

doi:10.1016/j.neucom.2014.09.036

Cited by 52 publications

(25 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supposing the classification for y n is binary, the standard SVC training is constrained by an optimization problem expressed as [37] min w;ξ n 1 2 w T w þ C…”

Section: Support Vector Fusion For Enhancing the Multimodal Grbmsmentioning

confidence: 99%

Multimodal deep support vector classification with homologous features and its application to gearbox fault diagnosis

et al. 2015

View full text Add to dashboard Cite

“…Supposing the classification for y n is binary, the standard SVC training is constrained by an optimization problem expressed as [37] min w;ξ n 1 2 w T w þ C…”

Section: Support Vector Fusion For Enhancing the Multimodal Grbmsmentioning

confidence: 99%

Multimodal deep support vector classification with homologous features and its application to gearbox fault diagnosis

et al. 2015

View full text Add to dashboard Cite

“…For regression problems, the functions of the kernel are often to be used to predict resulting outcome, such as radial basis function (RBF), two neural networks, polynomial, sigmoid and linear, exponential radial basis function (ERBF) [55,56]. In recent years, SVM has been applied in many fields as well as publications, therefore, the details of the SVM are not presented in this study but can be found in [57][58][59][60][61][62][63].…”

Section: Svmmentioning

confidence: 99%

A Comparative Study of Different Machine Learning Algorithms in Predicting the Content of Ilmenite in Titanium Placer

Bui

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

In this study, the ilmenite content in beach placer sand was estimated using seven soft computing techniques, namely random forest (RF), artificial neural network (ANN), k-nearest neighbors (kNN), cubist, support vector machine (SVM), stochastic gradient boosting (SGB), and classification and regression tree (CART). The 405 beach placer borehole samples were collected from Southern Suoi Nhum deposit, Binh Thuan province, Vietnam, to test the feasibility of these soft computing techniques in estimating ilmenite content. Heavy mineral analysis indicated that valuable minerals in the placer sand are zircon, ilmenite, leucoxene, rutile, anatase, and monazite. In this study, five materials, namely rutile, anatase, leucoxene, zircon, and monazite, were used as the input variables to estimate ilmenite content based on the above mentioned soft computing models. Of the whole dataset, 325 samples were used to build the regarded soft computing models; 80 remaining samples were used for the models’ verification. Root-mean-squared error (RMSE), determination coefficient (R2), a simple ranking method, and residuals analysis technique were used as the statistical criteria for assessing the model performances. The numerical experiments revealed that soft computing techniques are capable of estimating the content of ilmenite with high accuracy. The residuals analysis also indicated that the SGB model was the most suitable for determining the ilmenite content in the context of this research.

show abstract

“…It has been proved that the larger the distance between states and the hyperplane is, the more accurately the sample can be classified. 42 Therefore, the overall objective is to find the optimal hyperplane that can maximize the minimal geometric margin. It can be presented as a standard quadratic programming (QP) optimization:…”

Section: Training Of a Svm Modelmentioning

confidence: 99%

An adaptive SVM-based real-time scheduling mechanism and simulation for multiple-load carriers in automobile assembly lines

Zhou

2017

Int. J. Model. Simul. Sci. Comput.

View full text Add to dashboard Cite

Multiple-load carriers are widely introduced for material delivery in manufacturing systems. The real-time scheduling of multiple-load carriers is so complex that it deserves attention to pursue higher productivity and better system performance. In this paper, a support vector machine (SVM)-based real-time scheduling mechanism was proposed to tackle the scheduling problem of parts replenishment with multiple-load carriers in automobile assembly plants under dynamic environment. The SVM-based scheduling mechanism was trained first and then used to make the optimal real-time decisions between "wait" and "deliver" on the basis of real-time system states. An objective function considering throughput and delivery distances was established to evaluate the system performance. Moreover, a simulation model in eM-Plant software was developed to validate and compare the proposed SVM-based scheduling mechanism with the classic minimum batch size (MBS) heuristic. It simulated both the steady and dynamic environments which are characterized by the uncertainty of demands or scheduling criteria. The simulation results demonstrated that the SVM-based scheduling mechanism could dynamically make optimal real-time decisions for multiple-load carriers and outperform the MBS heuristic as well.

show abstract

Steel plates fault diagnosis on the basis of support vector machines

Cited by 52 publications

References 28 publications

Multimodal deep support vector classification with homologous features and its application to gearbox fault diagnosis

Multimodal deep support vector classification with homologous features and its application to gearbox fault diagnosis

A Comparative Study of Different Machine Learning Algorithms in Predicting the Content of Ilmenite in Titanium Placer

An adaptive SVM-based real-time scheduling mechanism and simulation for multiple-load carriers in automobile assembly lines

Contact Info

Product

Resources

About