Residual-based fault detection using soft computing techniques for condition monitoring at rolling mills

Serdio, Francisco; Lughofer, Edwin; Pichler, Kurt; Buchegger, Thomas; Efendic, Hajrudin

doi:10.1016/j.ins.2013.06.045

Cited by 76 publications

(40 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For most faults, NSC-NPE can detect the faults with notably higher detection rate. In particular, a great improvement has been made on T 2 statistic for faults that are difficult to detect (faults 1, 10,11,12,15). That is because by virtue of the nonlocal information, NSC-NPE is more capable of capturing much accurate and complete process characteristics.…”

Section: Case Study Of Semiconductor Etch Processmentioning

confidence: 99%

“…In such case, dimensionality reduction is necessary to be performed to obtain the desired properties of the correlated process data. MSPC-based methods typically employ dimensionality reduction to discover the reduced space where the underlying low-dimensional data structure is well preserved and perform monitoring in the reduced space as well as its complementary residual space to detect the variations both inside and outside the model [10,11]. Thus, the dimensionality reduction performance of those methods will directly influence the reliability of the extracted features, and the monitoring performance could also be influenced [11][12][13][14].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Nonlocal structure constrained neighborhood preserving embedding model and its application for fault detection

Miao

Song

et al. 2015

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

Section: Case Study Of Semiconductor Etch Processmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Nonlocal structure constrained neighborhood preserving embedding model and its application for fault detection

Miao

Song

et al. 2015

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

“…One example includes the learning of one-class SVM, which requires non-labeled data [18,19]. Other studies also utilized the method of non-labeled data, hence being able to operate in a fully unsupervised manner [20,21]. Fuzzy analytical hierarchy process was used to select unstable slicing machines to control wafer slicing quality, where the results of exponentially weighted moving average control chart demonstrated the feasibility of the proposed algorithm in effectively selecting the evaluation outcomes and evaluating the precision of the worst performing machines [22].…”

Section: Literature Reviewmentioning

confidence: 99%

E-quality control: A support vector machines approach

Tseng

Aleti

et al. 2015

Journal of Computational Design and Engineering

View full text Add to dashboard Cite

James) Kwon, E-quality control: A support vector machines approach, Journal of Computational Design and Engineering, http://dx. AbstractThe automated part quality inspection poses many challenges to the engineers, especially when the part features to be inspected become complicated. A large quantity of part inspection at a faster rate should be relied upon computerized, automated inspection methods, which requires advanced quality control approaches. In this context, this work uses innovative methods in remote part tracking and quality control with the aid of the modern equipment and application of support vector machine (SVM) learning approach to predict the outcome of the quality control process. The classifier equations are built on the data obtained from the experiments and analyzed with different kernel functions. From the analysis, detailed outcome is presented for six different cases. The results indicate the robustness of support vector classification for the experimental data with two output classes.

show abstract

“…Initially WSN was developed for military and civilian purposes, for example, a large quantity of sensor nodes could be deployed over a battlefield to detect enemy intrusions instead of using landmines. Nowadays it is extended to wide range of applications such as disaster management and habitat monitoring (Akyildiz et al 2002), target tracking and security management , medical and health care (El-said and Hassanien 2013), home automation and traffic control (Culler et al 2004;Akyildiz et al 2002;Estrin et al 2002;Ye et al 2002), machine failure diagnosis and energy management (Wood et al 2008), rolling mills for steel plate production (Serdio et al 2014), rescue mis- Fig. 1 Architecture of a smart sensor node sions, climate change, earthquake warning, and monitoring the enemy territory.…”

Section: Introductionmentioning

confidence: 99%

Optimized hierarchical routing technique for wireless sensors networks

2015

View full text Add to dashboard Cite

Wireless sensor networks are battery-powered ad hoc networks in which sensor nodes that are scattered over a region connect to each other and form multi-hop networks. Since these networks consist of sensors that are battery operated, care has to be taken so that these sensors use energy efficiently. This paper proposes an optimized hierarchical routing technique which aims to reduce the energy consumption and prolong network lifetime. In this technique, the selection of optimal cluster head (CHs) locations is based on artificial fish swarm algorithm that applies various behaviors such as preying, swarming, and following to the formulated clusters and then uses a fitness function to compare the outputs of these behaviors to select the best CHs locations. To prove the efficiency of the proposed technique, its performance is analyzed and compared to two other well-known energy efficient routing techniques: low-energy adaptive clustering hierarchy (LEACH) technique and particle swarm optimized (PSO) routing technique. Simulation results show the stability and efficiency of the proposed technique. Simulation results show that the proposed method Communicated by V. Loia. Egypt outperforms both LEACH and PSO in terms of energy consumption, number of alive nodes, first node die, network lifetime, and total data packets received by the base station. This may be due to considering residual energies of nodes and their distance from base station , and alternating the CH role among cluster's members. Alternating the CH role balances energy consumption and saves more energy in nodes.

show abstract

Residual-based fault detection using soft computing techniques for condition monitoring at rolling mills

Cited by 76 publications

References 25 publications

Nonlocal structure constrained neighborhood preserving embedding model and its application for fault detection

Nonlocal structure constrained neighborhood preserving embedding model and its application for fault detection

E-quality control: A support vector machines approach

Optimized hierarchical routing technique for wireless sensors networks

Contact Info

Product

Resources

About