Monitoring of Multimode Processes Based on Subspace Decomposition

Ли, Шуай; Zhou, Xiaofeng; Shi, Haibo; Qiao, Zhi; Zheng, Zeyu

doi:10.1021/ie504730x

Cited by 18 publications

(31 citation statements)

References 37 publications

(79 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each

Φ true({boldx}_{i} true)

J_{i}

denotes the neighbours of

Φ true({boldx}_{i} true)

and

{boldW}^{0}

denotes the weight matrix without hierarchical multimode information. The geometrical interpretations based on the marginal perspective are applied . For each clustering scheme, the weights

{boldW}_{i j}^{i n}

in the same mode and

{boldW}_{i j}^{b e t w e e n}

between different modes in the proposed method are defined as:

true{\begin{matrix} left \\ center {boldW}_{i j}^{i n} = 1, i f j \in J_{i}, L true({boldx}_{i} true) = L true({boldx}_{j} true) \\ center {boldW}_{i j}^{b e t w e e n} = - 1, i f j \in J_{i}, L true({boldx}_{i} true) \neq L true({boldx}_{j} true) \\ center {boldW}_{i j}^{i n} = {boldW}_{i j}^{b e t w e e n} = 0, e l s e \end{matrix}

where

L true({boldx}_{i} true)

is hierarchical mode information.…”

Section: Methodsmentioning

confidence: 99%

“…Process monitoring has a wide range of applications for modern industrial production processes as it can ensure stable production safety, maintain quality stabilization, and optimize production profit . The operating conditions often vary with raw materials, manufacturing parameters, production specifications, etc., which causes various operation modes . Different modes have their similar, respective specific characteristics and duration times in which one mode is the long duration process with similar statistical characteristics .…”

Section: Introductionmentioning

confidence: 99%

“…Multivariate statistical process monitoring methods, such as principal component analysis (PCA), partial least squares (PLS), etc., have attracted increasing attention on process monitoring . However, it is noted that industrial processes have dynamic and multimode characteristics and the variable trajectories measured over the duration are nonlinear, which cannot be directly monitored by traditional MSPM methods . Therefore, monitoring methods for multimode processes should be well developed.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, considering multimode information, a new subspace decomposition method was developed in which each mode could have unequal mode length. Nevertheless, it needs to achieve mode division for multimode processes, which could not overcome the missing a priori knowledge in most practical industrial processes . A mode division method based on the warped K‐means clustering algorithm was developed for multimode process monitoring .…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Multimode processes monitoring based on hierarchical mode division and subspace decomposition

Zhou

Shi

et al. 2018

Can J Chem Eng

Self Cite

View full text Add to dashboard Cite

To handle multimodal uncertainty and dynamics which are common in actual industrial processes, this paper proposes a multimode process monitoring method based on hierarchical mode division and subspace decomposition. First, hierarchical mode division is presented to achieve hierarchical mode information for multimode process modelling, which can improve the adaptability of industrial processes with multimodal uncertainty. Then, hierarchical subspace decomposition is presented to decompose multimode processes into multiple global subspaces and multiple local subspaces for monitoring. Lastly, the most similar mode with various hierarchical modes at the current sampling point is dynamically determined for monitoring, which considers multimodal dynamics. The simulation tests of the penicillin fermentation processes are developed to show feasibility and superiority of the proposed method.

show abstract

“…For each

Φ true({boldx}_{i} true)

J_{i}

denotes the neighbours of

Φ true({boldx}_{i} true)

and

{boldW}^{0}

denotes the weight matrix without hierarchical multimode information. The geometrical interpretations based on the marginal perspective are applied . For each clustering scheme, the weights

{boldW}_{i j}^{i n}

in the same mode and

{boldW}_{i j}^{b e t w e e n}

between different modes in the proposed method are defined as:

true{\begin{matrix} left \\ center {boldW}_{i j}^{i n} = 1, i f j \in J_{i}, L true({boldx}_{i} true) = L true({boldx}_{j} true) \\ center {boldW}_{i j}^{b e t w e e n} = - 1, i f j \in J_{i}, L true({boldx}_{i} true) \neq L true({boldx}_{j} true) \\ center {boldW}_{i j}^{i n} = {boldW}_{i j}^{b e t w e e n} = 0, e l s e \end{matrix}

where

L true({boldx}_{i} true)

is hierarchical mode information.…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multimode processes monitoring based on hierarchical mode division and subspace decomposition

Zhou

Shi

et al. 2018

Can J Chem Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…Nowadays, the size and complexity of modern industrial production processes are increasing (He, Zuo, Zhang, & Megahed, 2016;Li, Zhou, Shi, Qiao, & Zheng, 2015;Zhang, Li, & Hu, 2012). A huge amount of data including useful information can be collected (Huang & Yan, 2016b;Yan, Chen, Yao, & Huang, 2016).…”

Section: Introductionmentioning

confidence: 99%

Correlated and weakly correlated fault detection based on variable division and ICA

Zhou

Pan

et al. 2017

Computers & Industrial Engineering

Self Cite

View full text Add to dashboard Cite

Synthesis of dual‐stimuli‐responsive polyurethane shape memory nanocomposites incorporating isocyanate‐functionalized Fe₃O₄ nanoparticles

Babaie

Rezaei

Razzaghi

et al. 2022

J of Applied Polymer Sci

View full text Add to dashboard Cite

Thermally and magnetically stimulated shape memory polyurethane (PU) nanocomposites were synthesized for intravascular stent applications.For this end, Fe 3 O 4 magnetic nanoparticles (MNPs) were modified with octadecyl isocyanate (OD) to increase their affinity with the PU matrix by formation of the covalent urea linkages. The results showed that the OD-grafted MNPs were replaced instead of carbonyl groups of polycaprolactone (PCL) soft segments in hydrogen bond formation with the urethane linkages. This led to higher phase separation degrees among the soft and hard phases, thereby PCL chains could reveal higher crystallization potential. Mechanical studies showed that the nanocomposites had high mechanical strength, Young's modulus, and elongation at break, which improve their practical applications. The nanocomposites showed thermo-responsive shape memory behavior with a high shape recovery and shape fixity ratios due to the presence of the crystallizable PCL segments. The nanocomposite containing 10 wt% of the OD-grafted MNPs could recover its original shape (during 90s) in a relatively weak alternating magnetic field (350 kHz and 12.9 kA/m). These results indicated that the prepared nanocomposites could be used to normalize the narrowed blood vessels through the remotely and magnetically-controllable restricted shape recovery process.

show abstract

Monitoring of Multimode Processes Based on Subspace Decomposition

Cited by 18 publications

References 37 publications

Multimode processes monitoring based on hierarchical mode division and subspace decomposition

Multimode processes monitoring based on hierarchical mode division and subspace decomposition

Correlated and weakly correlated fault detection based on variable division and ICA

Synthesis of dual‐stimuli‐responsive polyurethane shape memory nanocomposites incorporating isocyanate‐functionalized Fe₃O₄ nanoparticles

Contact Info

Product

Resources

About

Monitoring of Multimode Processes Based on Subspace Decomposition

Cited by 18 publications

References 37 publications

Multimode processes monitoring based on hierarchical mode division and subspace decomposition

Multimode processes monitoring based on hierarchical mode division and subspace decomposition

Correlated and weakly correlated fault detection based on variable division and ICA

Synthesis of dual‐stimuli‐responsive polyurethane shape memory nanocomposites incorporating isocyanate‐functionalized Fe3O4 nanoparticles

Contact Info

Product

Resources

About

Synthesis of dual‐stimuli‐responsive polyurethane shape memory nanocomposites incorporating isocyanate‐functionalized Fe₃O₄ nanoparticles