An on-line SAX and HMM-based anomaly detection and visualization tool for early disturbance discovery in a dynamic industrial process

Abstract

a b s t r a c tIn order to achieve an optimum and successful operation of an industrial process, it is important firstly to detect upsets, equipment malfunctions or other abnormal events as early as possible and secondly to identify and remove the cause of those events. Univariate and multivariate statistical process control methods have been widely applied in process industries for early fault detection and localization.The primary objective of the proposed research is the design of an anomaly detection and visualization tool that is able to present to the shift operator -and to the various levels of plant operation and company management -an early, global, accurate and consolidated presentation of the operation of major subgroups or of the whole plant, aided by a graphical form.Piecewise Aggregate Approximation (PAA) and Symbolic Aggregate Approximation (SAX) are considered as two of the most popular representations for time series data mining, including clustering, classification, pattern discovery and visualization in time series datasets. However SAX is preferred since it is able to transform a time series into a set of discrete symbols, e.g. into alphabet letters, being thus far more appropriate for a graphical representation of the corresponding information, especially for the shift operator. The methods are applied on individual time records of each process variable, as well as on entire groups of time records of process variables in combination with Hidden Markov Models. In this way, the proposed visualization tool is not only associated with a process defect, but it allows also identifying which specific abnormal situation occurred and if this has also occurred in the past. Case studies based on the benchmark Tennessee Eastman process demonstrate the effectiveness of the proposed approach. The results indicate that the proposed visualization tool captures meaningful information hidden in the observations and shows superior monitoring performance.

Symbolic Important Point Perceptually and Hidden Markov Model Based Hydraulic Pump Fault Diagnosis Method

“…A lot of works have been carried out in time series compression. Christos Yiakopoulis et al utilize Piecewise Aggregate Approximation (PAA) for the analysis of signals, the original signal is divided into a number of equal subsequences, then each subsequence is substituted with its mean value, and a low dimension series is achieved [7]. G. Das et al propose a simple N/S conversion, a fixed length window is used to segment a time series into subsequences and the time series is then represented by the primitive shape patterns that are formed [8].…”

The Machine Learning Life Cycle in Chemical Operations – Status and Open Challenges

“…Model requirements definitions ''Machine Learning'' AND (Requirements OR Target OR Object OR Performance OR Quality) [49,50] Data collection ''machine learning'' AND ((''data collection'' OR ''data acquisition'' OR ''data gathering'' OR ''data sharing'' OR ''data browsing'' OR ''data augmentation'' OR ''data generation'') OR ''synthetic data'') [10,11,16,26,28,39,[51][52][53][54][55][56] -Cleaning ''data cleaning'' [15,29,38,46,[57][58][59][60] -Labelling ''data labelling'' OR ''data labeling'' OR ''semi-supervised'' OR ''weak supervision'' OR ''weakly supervised'' [8,20,21,30,37,[61][62][63][64][65][66][67] Feature engineering ''Machine Learning'' AND ''Feature Engineering'' OR ''Feature Selection'' [29,[68][69][70][71][72][73][74][75] Model training ''Machine Learning'' AND ''Model Training'' OR ''Modeling'' [5,35,…”

Operator's Experience-Level Classification Based on Micro-Assembly Steps for Smart Factories

“…Time series represent a collection of values obtained from sequential measurements over time. There are various type of researches on time series related to representation, visualization and forecasting [4,24,11]. Esling [5] presented the state of art related to time series in data mining.…”