Data Extraction from Historian

In the industry, steam is measured in mass flow, fuel in volumetric flow, and electricity in electrical current. To compare them on the same basis, all the energy 

Steam generation Product fractionator bottom steam gen 16.50  

Enei export Condensate return to boiler house 129.4  

Condensate lost MP steam goes to steam header 50.0 -10.0  

nei y entering Into the process Enei y exporting outside the process 3147.0 188.6 50.0 129.4 337.1 

---

Variability assessment starts with a simple statistical analysis of operating data. For example, the operating data for Cs% in the debutanizer column overhead product under normal conditions can be extracted from the historian as shown in Figure 4.5a with specification limit provided. To understand the variability, data in Figure 4.5a are converted to a normal distribution curve, which represents frequency of observations as shown in Figure 4.5b. In many cases, the operating data mimic the normal distributions. 

Data Collection During the data collection step, the required data are collected and analysed to determine if there are any obvious problems with the data set, such as missing data, faulty sensors, faulty values, or multiple operating modes. The framework presented in Fig. 6.3 assumes that a separate experiment will be designed in order to obtain the data required for system identification. In industry, the ability to perform such experiments can be limited due to various factors, including safety, economic, or reluctance on the part of the plant operators. Instead, historical data from the data historian are extracted and preprocessed to determine their usefulness for the given problem. 

---