Unsupervised Monitoring of Flocculation Processes based on Recurrence Theory

Abstract Continuous monitoring of abnormal conditions during operation is an important requirement to increase the quality, and efficiency of chemical processes, and to optimize operating costs. In this study, fault diagnosis of abnormal conditions is considered for flocculation processes, which due to the complexity of these processes requires more attention. To this end, an unsupervised learning method is developed to diagnose the faults in chemical processes based on recurrence analysis. This method consists of two stages of pre-processing and clustering. The pre-processing stage is carried out by transferring the time series from time space to state space and converting the data into a two-dimensional recurrence plot. Quantitative parameters of recurrence analysis can be extracted from this plot. Then, in the clustering stage, the density-based spatial clustering of applications with noise (DBSCAN) method was used for clustering different operating conditions and diagnosing faults. By comparing the results with conventional methods, such as independent component analysis (ICA) and Kernel ICA (KICA) it was found that the developed method is more powerful and shows the best performance. Application of this method was illustrated throughout a laboratory scale flocculation of silica particles in water. An on-line non-invasive sampling method was used for monitoring the size distribution of particles with a dynamic image analysis sensor.

[1]  Seyed Soheil Mansouri,et al.  Data-Driven Fault Diagnosis of Chemical Processes Based on Recurrence Plots , 2021 .

[2]  Wahiba Bounoua,et al.  Fault detection and diagnosis of nonlinear dynamical processes through correlation dimension and fractal analysis based dynamic kernel PCA , 2021 .

[3]  X. Liang,et al.  Centrifugal Compressor Diagnosis Using Kernel PCA and Fuzzy Clustering , 2018, Lecture Notes in Mechanical Engineering.

[4]  L. Hubert,et al.  Comparing partitions , 1985 .

[5]  Jinsong Zhao,et al.  A new unsupervised data mining method based on the stacked autoencoder for chemical process fault diagnosis , 2020, Comput. Chem. Eng..

[6]  Jürgen Kurths,et al.  Recurrence plots for the analysis of complex systems , 2009 .

[7]  N. Mostoufi,et al.  Recognition of Particle Size Changes in Fluidized Beds by Recurrence and Cross Recurrence Quantification Analyses , 2018, Industrial & Engineering Chemistry Research.

[8]  Sylvain Verron,et al.  Bridging data-driven and model-based approaches for process fault diagnosis and health monitoring: A review of researches and future challenges , 2016, Annu. Rev. Control..

[9]  D. Ruelle,et al.  Recurrence Plots of Dynamical Systems , 1987 .

[10]  N. Mostoufi,et al.  Investigation of hydrodynamics of gas-solid fluidized beds using cross recurrence quantification analysis , 2017 .

[11]  Chin-Teng Lin,et al.  A review of clustering techniques and developments , 2017, Neurocomputing.

[12]  Xue Z. Wang,et al.  Knowledge discovery from process operational data using PCA and fuzzy clustering , 2001 .

[13]  Krist V. Gernaey,et al.  Integration of Computational Chemistry and Artificial Intelligence for Multi-scale Modeling of Bioprocesses , 2020, Computer Aided Chemical Engineering.

[14]  Yingjie Tian,et al.  A Comprehensive Survey of Clustering Algorithms , 2015, Annals of Data Science.

[15]  D. Seborg,et al.  Clustering multivariate time‐series data , 2005 .

[16]  Krist V. Gernaey,et al.  Hybrid machine learning assisted modelling framework for particle processes , 2020, Comput. Chem. Eng..