PTQ Q3 2022 Issue

control technology, also known as an ‘end of pipe’ solu- tion. Two widely used are the selective catalytic reduction (SCR) process and the selective noncatalytic reduction (SNCR) process. SNCR and SCR technology should be considered only when the available low-NOx combustion technology pro- vides insufficient NOx reduction to comply with the emis - sion requirements. Furthermore, DeNOx technology cannot be installed easily in any system and relies on sufficient space, proper mixing with injectant, flue gas temperature, and residence time. Both SNCR and SCR processes reduce NOx to N₂ and H₂O using ammonia or ammonia-based reagents like urea. The residual unreacted ammonia leaves the reactor as ammonia slip. The emission of ammonia slip is another pol- lutant, which typically also has legislative limits. Q With the enormous potential for reducing the refin - ery carbon footprint by increasing direct fired heater efficiency, what successful cases provide an example of increased efficiency and reduced emissions? A Ron Beck and Gerardo Munoz, AspenTech For most refineries and bulk chemical sites, the opportunity is there to improve energy efficiency by 10-30%, with a significant amount of that through optimisation of opera - tions. A recent benchmark of European refineries shows that they lag significantly behind best-in-class global refin - ers in energy efficiency. Some examples of how digital solu - tions are achieving energy efficiencies and reduced carbon emissions include: • KNPC identifies opportunities across the refinery to save 57,890 tpy of CO₂ and reach an EII rating of 3.2 without sig - nificant investment through rigorous modelling of energy supply and demand in Aspen Performance engineering. Additionally, it identified opportunities with added CAPEX that allowed it to save 260 MBTU/hr with an EII of 6 • Sinopec decreased by 13% the total fuel gas to unit feed ratio using APC (Aspen DMC3) at an integrated refining petrochemical complex • An international bulk chemicals producer reduced its fuel gas consumption by 1.7 to 4.3 kg/hr per day per furnace in less than a month using multivariate statistical analysis with Aspen ProMV • Tupras reduced fuel consumption by 20% through heat integration and higher energy recovery • Probably the broadest existing case study is the 10% car - bon reduction Dow Chemical has reported to the investor community over the past 10 years through the combined use of APC and digital twin models online, both using AspenTech technology. A Hervé Lavieu, Heurtey Petrochem Solutions To increase the fuel efficiency of existing heaters, several options can be considered depending on the inlet tempera- ture of the process fluid and the temperature of the flue gas rejected to the atmosphere. The first solution is revamping the heater to increase the heat exchange surface of the coil; this solution has been

implemented on natural draft heaters and does not require the installation of additional equipment such as air and flue gas fans. The second option consists of the installation of an air preheating system (APH) to preheat the combustion air by recovery of heat on the flue gas going to the stack. And when the heater is already equipped with such an APH, the installation of a new generation APH allows the recovery of more heat from the flue gas. In this situation, we have installed an APH with an enhanced exchange surface but also utilising special coated or polymer-based tubes, oper- ating below the acid dew point (ADP) to reach low stack temperatures (<90°C/195°F). Q What do you see necessary for successful implemen- tation of plant-wide AI and machine learning (ML) in the refinery and petrochemical complex? Can AI/ML strate - gies provide additional benefits beyond APC? A Ron Beck and Gerardo Munoz, AspenTech AI and machine learning are positioned to create very sig - nificant benefits in operational excellence. In fact, some of the benefit areas will be significantly greater than those that may come from APC. One area we have already implemented is in applying AI/ ML to refinery and olefins planning. AI can augment the existing planning systems by helping planners sift through hundreds of complex plan alternatives to find those most likely to achieve lower carbon operations based on results from historical planning periods. Another area is achieving more accurate digital twin models by applying AI to data streams to improve results from rigorous models. These will help in crucial areas of energy efficiency, such as heat exchanger and process unit fouling. By being able to model the actual conditions, not the ideal ones, these AI-based hybrid models will have a big impact on optimising operations for energy efficiency. It is necessary to have technology that democratises the application of Industrial AI, making it possible for AI and ML to be used by engineers of different skill levels. Very often, process data is treated as company intellec - tual property. As a result, access can be on a need-to-know basis. There must be documented processes for people who need that access to be able to gain it. Likewise, it is necessary to have good data quality. There may be time periods requiring users to ‘condition’ data to be able to get the most out of it, for example, where: • The process is not steady (assuming you are calibrating a steady-state model) • The process measurement is bad (for example, outside the measurable range of the instrument) • The data does not close the material balance • The plant is operating in a regime that is out of the norm. There are many benefits to using AI/ML. Aspen hybrid models combining first principles and AI/ML allow engi - neers to: • Capture unknown or unmeasurable details of phenomena while recalibrating models to changing process conditions more easily with AI/ML

PTQ Q3 2022