This webinar will comprise the two presentations below, each with a question and answer session.
Advanced Process Control in fertiliser production
Knut Wiig Mathisen, Advanced Process Control program manager, Yara Digital Production, Yara International ASA
Advanced Process Control (APC) is a supervisory process control method based on the model predictive control algorithm. Yara International ASA, www.yara.com, has implemented APC in ammonia, nitric acid, urea and finished fertiliser plants since 2004 and currently has 20 applications in operation. 17 applications are using IPCOS, www.ipcos.com, software whereas three are using Honeywell, www.honeywell.com, technology.
This paper describes the approach, project phases and procedures we are using when implementing APC together with the external software technology supplier. Key APC signals, strategy and benefits in four different fertiliser processes, ammonia, nitric acid, urea solution and granulation plants, are described without disclosing confidential or sensitive information. The importance of a well-working regulatory control system including controller tunings and advanced regulatory control functions for e.g. input flow ratio control is emphasised. The main APC projects risks including organisational challenges, process control system changes and plant modifications are presented. Finally, current challenges and future trends including integration with real-time, non-linear optimisation and increased use of online analysers and soft-sensors are discussed.
Application of Clustering to study fluorine losses in the phosphate industry
Houda Ariba, Prayon Technologies
This work presents an application of clustering in the phosphate industry. It focuses on the identification of fluorine losses in a phosphoric acid concentration unit. A clustering method using different algorithms was applied to group the data according to the importance of fluorine losses. As a result, the Gaussian mixture model was selected as the best method for this study.
Consequently, two important clusters of data were identified. The first one is comprised of data showing high losses and the second one is comprised of data showing low losses. In addition, a ratio R was calculated to quantify the losses. This Ratio enabled the detection and measurement of the level of fluorine losses in a phosphoric acid concentration unit.