Detecting Outliers in Electric Arc Furnace under the Condition of Unlabeled, Imbalanced, Non-stationary and Noisy Data

Wang, Biao; Mao, Zhizhong

doi:10.1177/0020294018771097

Cited by 10 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the implementation of data scaling, we propose to detect if there are some abnormal samples (outliers) in the training set before using them to train base models. It has been underlined in many researches that the presence of outliers is detrimental to most data models [49,50]. As we have introduced in Section 3.3, we would use a clustering algorithm (K-means) to determine the region of competence during the training phase.…”

Section: A Datasets and Preprocessingmentioning

confidence: 99%

Molten Steel Temperature Prediction in Ladle Furnace Using a Dynamic Ensemble for Regression

Qiao

Wang

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

The accurate prediction of molten steel temperature is of great significance to the control of tapping temperature in ladle furnace. The more accurate the prediction is the better performance the controller will attain. In order to further improve the accuracy of existing data-driven predictive models, we propose a dynamic ensemble for regression to predict molten steel temperature. In contrast to existing ensemble models, we only select one base model with the highest competence from the pool for each test pattern, rather than fusing all base models. We can thus alleviate the effect of weak base models on the ensemble. Specifically, the operation of dynamic selection can be implemented by estimating the competence of all base models in the region of competence. In addition, the proposed ensemble generation method has taken into account the diversity and accuracy, which are crucial factors of deriving better ensembles. In order to investigate the effectiveness of our predictor, we compare it with several competitors proposed in literature on a real-world dataset. The experimental result has approved the superiority of our predictor.

show abstract

Section: A Datasets and Preprocessingmentioning

confidence: 99%

Molten Steel Temperature Prediction in Ladle Furnace Using a Dynamic Ensemble for Regression

Qiao

Wang

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Then it heavily depends on the predictive model, and the detection performance will deteriorate much when the predictions are biased. In Wang and Mao, 12 a clustering-based ensemble detector is proposed for EAF control system. In this method, a clustering algorithm is used first to separate the training set into several subsets, in each of which a single detector is established.…”

Section: Related Work and Preliminariesmentioning

confidence: 99%

“…Clustering-based SVDD (C-SVDD) proposed in Wang and Mao. 12 In this detection model, clustering technique is used to develop a parallel ensemble model.…”

Section: Experiments and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Using a dynamically selective support vector data description model to discover novelties in the control system of electric arc furnace

Zhang

Wang

et al. 2020

Measurement and Control

Self Cite

View full text Add to dashboard Cite

As increasing data-driven control strategies are applied in electric arc furnace systems, the problem of novelty detection has drawn more attentions than before. The presence of outliers should be the main obstacle in practical applications for these advanced control techniques. To this end, this paper proposes a dynamically selective support vector data description model to discover novelties in electric arc furnace. In this model, support vector data description plays the role of base detector. Artificial outliers are generated with two objectives, one is to assist the dynamic selection, and the other is to optimize two parameters of support vector data description. Then clustering technique is used to determine the validation set for each test point. Finally, a probabilistic method is used to compute the competence of base detectors. In contrast to other novelty ensembles that have parallel structures, our ensemble model has a dynamic selection mechanism that could facilitate the mining of the potential of base detectors. Three synthetic and three real-world datasets are used to validate the effectiveness of the proposed detection model. Experimental results have approved our method by comparing it with several competitors.

show abstract

“…Examples of typical clustering algorithms include the fuzzy C-means clustering, 7 k -means clustering, 8 density-based clustering, 9 and consensus clustering. 10 Yang et al 11 proposed the k -shape clustering algorithm based on load shape, which is to detect different levels of building energy consumption patterns, and further use the clustering results to improve the accuracy of the prediction model. Xiang et al 12 proposed a shape clustering method based on the segmented slope to solve the problem that the Euclidean distance as a measure of similarity is not enough to reflect the shape similarity of the load curve.…”

Section: Introductionmentioning

confidence: 99%

Hierarchical classification method of electricity consumption industries through TNPE and Bayes

Lang

et al. 2021

Measurement and Control

View full text Add to dashboard Cite

As the multi-daily electricity consumption behaviors have the strong characteristics of dynamicity, nonlinearity and locality caused by temporal manifold structure, the existing methods are difficult to fine-grained and accurately classify it. To solve this problem, this paper proposes a hierarchical classification method based on the temporal extension of the neighborhood preserving embedding algorithm (TNPE) and Bayes. The input data are multi daily-load curves of a single consumer, including power-hour-day three dimensions, which contains the full information of the user’s consumption behaviors not only in hours, but also in days. Firstly, electricity consumption behaviors are divided into routine and non-routine types by k-means clustering algorithm. Secondly, the load feature mapping matrix of different industries is extracted through the TNPE, and each TNPE model can regard as one binary classifier, so the multi-classifier is constructed through multiple TNPE models. Finally, by converting the feature similarity between samples into probabilities, a Bayesian model is established to realize which the power consumption type belongs to. The case results show that this method can effectively recognize the local dynamic features in the temporal load data, and obtain a higher classification accuracy through a smaller number of training samples.

show abstract

Detecting Outliers in Electric Arc Furnace under the Condition of Unlabeled, Imbalanced, Non-stationary and Noisy Data

Cited by 10 publications

References 14 publications

Molten Steel Temperature Prediction in Ladle Furnace Using a Dynamic Ensemble for Regression

Molten Steel Temperature Prediction in Ladle Furnace Using a Dynamic Ensemble for Regression

Using a dynamically selective support vector data description model to discover novelties in the control system of electric arc furnace

Hierarchical classification method of electricity consumption industries through TNPE and Bayes

Contact Info

Product

Resources

About