Improved neural component analysis for monitoring nonlinear and Non-Gaussian processes

Lou, Zhijiang; Li, Zedong; Wang, Youqing; Lu, Shan

doi:10.1016/j.measurement.2022.111164

Cited by 5 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The window size is the most important hyperparameter in the model structure, as it determines the range of data considered for calculating distance patterns. Figure 19 shows the variation in 1.00 IDV (7) 1.00 IDV (8) 0.975 IDV (9) 0.00 IDV (10) 0.278 IDV (11) 0.987 IDV (12) 1.0 IDV (13) 0.937 IDV (14) 1.00 IDV (15) 0.00 IDV (16) 0.329 IDV (17) 0.924 IDV (18) 0.924 IDV (19) 0.089 IDV( 20 develop with slower dynamics and benefit from larger window sizes. In this specific case study, the optimal window size can be determined by selecting the minimum size that achieves the best performance.…”

Section: Example 2 − Simulated Cstrmentioning

confidence: 99%

“…6 Due to these limitations, several works that suggest modifications of the original PCA model have been proposed in the last 30 years. Common examples of data behavior addressed by these extensions are dynamics, 7 nonlinearity, 8 non-Gaussianity, 9 and multimodality. 10 A trend in recent years is the proposition of techniques that are less constrained by model structures and more focused on exploring the intrinsic patterns of the data itself.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Distance Matrix Patterns for Visual and Interpretable Process Data Analytics

Melo,

Fadel,

Câmara

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

A novel methodology for visual process data analytics based on distance matrices is proposed. A distance matrix is a two-dimensional representation that reflects intrinsic data patterns and is not constrained by a specific model structure. It is shown for the first time that fundamental patterns of process data, such as steps, drifts, and oscillations, can be clearly identified in distance matrices, allowing their use in process monitoring pipelines and as tools to aid process understanding and interpretation. The proposed approach has been applied to the context of visual exploratory data analysis and the formulation of an adaptive fault detection algorithm based on matrix dissimilarity. The effectiveness of the proposed methodology is illustrated through simulation cases, which involve a CSTR reactor and the Tennessee Eastman Process benchmark.

show abstract

Section: Example 2 − Simulated Cstrmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Distance Matrix Patterns for Visual and Interpretable Process Data Analytics

Melo,

Fadel,

Câmara

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…As such, NCA provides a new idea for solving the nonlinear monitoring issue, which can be transplanted to other algorithms. For example, Chen et al applied the NCA structure in the description of canonical correlation analysis and proposed artificial neural correlation analysis, and Lou et al applied the NCA structure in a non-Gaussian process and proposed improved NCA …”

Section: Introductionmentioning

confidence: 99%

“…For example, Chen et al applied the NCA structure in the description of canonical correlation analysis 32 and proposed artificial neural correlation analysis, 33 and Lou et al applied the NCA structure in a non-Gaussian process and proposed improved NCA. 34 In this article, NCA is combined with PLS, as NCA-PLS, to address the KPI monitoring issue. By introducing a new loss function and a new PC selection mechanism, all principles of PLS are realized by the NCA network structure.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neural Component Analysis for Key Performance Indicator Monitoring

Wang

Hou

et al. 2022

ACS Omega

View full text Add to dashboard Cite

The partial least squares (PLS) algorithm is a commonly used key performance indicator (KPI)-related performance monitoring method. To address nonlinear features in the process, this paper proposes neural component analysis (NCA)-PLS, which combines PLS with NCA. (NCA)-PLS realizes all the principles of PLS by introducing a new loss function and a new principal component selection mechanism to NCA. Then, the gradient descent formulas for network training are rederived. NCA-PLS can extract components with large correlations with KPI variables and adopt them for data reconstruction. Simulation tests using a mathematical model and the Tennessee Eastman process show that NCA-PLS can successfully handle nonlinear relationships in process data and that it performs much better than PLS, KPLS, and NCA.

show abstract

Incipient fault detection based on ensemble learning and distribution dissimilarity analysis in multi-feature processes

Liu,

Kong,

Luo

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Timely and accurate detection of incipient faults has attracted considerable attention and research interest in recent years, due to its potential for the prevention of serious safety incidents and for supporting preventive maintenance. However, most existing methods use single detection model, neglecting the coexistence of multiple features and the local data distribution information found in industrial scenes. To overcome this problem, an incipient fault detection method named multiple model ensemble and distribution dissimilarity analysis (MME-DISSIM) is proposed. First, various multivariate statistical analysis methods are employed as basic detectors to comprehensively capture the feature information hidden in the process data. Second, distribution dissimilarity analysis is performed to evaluate the dissimilarity between the current sliding window and each training subset. This evaluation allows for the calculation of weighting factors for each basic detector, which helps to preserve the local distribution information of the current sliding window. Third, ensemble learning is utilized to integrate the statistics from all basic detectors into two detection indices to determine the operation status of the system. In addition, two measurement metrics are defined to quantitatively analyze the fault level of incipient faults. Finally, several experiments on a numerical case, Tennessee Eastman process, and actual PROcess NeTwork Optimization are presented to verify the efficacy and superiority of the proposed method.

show abstract

Improved neural component analysis for monitoring nonlinear and Non-Gaussian processes

Cited by 5 publications

References 26 publications

Distance Matrix Patterns for Visual and Interpretable Process Data Analytics

Distance Matrix Patterns for Visual and Interpretable Process Data Analytics

Neural Component Analysis for Key Performance Indicator Monitoring

Incipient fault detection based on ensemble learning and distribution dissimilarity analysis in multi-feature processes

Contact Info

Product

Resources

About