Analysis and Detection of Outliers and Systematic Errors in Industrial Plant Data

Abstract

This article describes the analysis of industrial process data to detect outliers and systematic errors. Data reconciliation is an important step in adjusting mathematical models to plant data. The quality of the data directly affects the quality of adjustment of the model for modeling, simulation, and optimization purposes. To detect these errors in a multivariable system is not an easy task. If the origin of the abnormal values is known, these values can be immediately discarded. On the other hand, if an error or an extreme observation is not clearly justified, the decision whether or not to discard these values must be based on statistical analysis. In this work, in addition to process knowledge, the methodology employed involves an approach based on statistical analysis, first-principle equations, neural network models, and a composite of these. The neural network based approach was used to represent the process in order to classify similar inputs and outputs, i.e., to identify clusters. The elimination of gross errors was performed by the similarity principle or by hypothesis testing for means. The system studied is the Isoprene Production Unit of BRASKEM, the largest Brazilian petrochemical plant. The analysis of the process was undertaken by using a one-year database. The frequency of the data collection of the monitoring variables was 15 minutes.

Data-based Design of Inferential Sensors for Petrochemical Industry

“…The detection of a certain class of systematic errors can be carried out through visual inspection in time series plots (Alves and Nascimento, 2007).…”

“…Subsequently, the data quality is affected by the amount of systematic and random errors (Su et al, 2009). There are several methods dealing with the pre-treatment methods for industrial data (Alves and Nascimento, 2007). The group of well-known and popular multivariate data treatment methods includes Hotelling's T 2 distance (Hotelling, 1931), k-means clustering (Forgy, 1965), or minimum covariance determinant (MCD) technique (Rousseeuw, 1984).…”

Designing and Testing a Chemical Demulsifier Dosage Controller in a Crude Oil Desalting Plant: An Artificial Intelligence‐Based Network Approach

“…The process data used in the present study was collected from 17 GSOP. The recorded data were pretreated to detect outliers in the observations using typical influential observation methods [21,22] and visual inspection of the data set. The outliers detected in the original data set represented approximately 1 % of the total data points collected for the analysis [23].…”