4
350
5
300
3
2
1
250
1
3
4
200
150
5
100
50
2
0
0.00
50.00 100.00 150.00 200.00 250.00
Cold-side bulk temperature (˚C)
Pinch
Figure 5 Temperature-enthalpy diagram and the Grand Composite Curve of the crude preheat train in case study with an approach temperature of 20°C
Collaboration and scaling : The final phase focuses on knowledge transfer and organisational engagement. Cross-functional teams from operations, engineering, and finance are trained to interpret and utilise the SmartPM dashboards and results pushed to the data historian effectively. This collaborative effort ensures that insights from the digital twin are integrated into daily decision-making. Additionally, the implementation can be scaled to cover other heat exchanger network sections, such as combined crude distillation unit (CDU)/vacuum distillation unit (VDU) systems, amplifying the overall impact on plant performance and sustainability. Conclusion SmartPM integrates industry-proven modelling and analysis techniques with AI, digital twins, and advanced analytics. By combining thermal modelling with plant data, it delivers a practical approach to optimising process performance.
validate the fidelity of the digital twin, ensuring the simulation accurately represents the physical system and its thermal-hydraulic behaviour. Data integration : SmartPM is connected directly to the plant’s data historian systems. This enables reconciliation and continuous updating of critical process variables, such as temperatures, pressures, and flow rates. With this connection, the digital twin maintains alignment with actual plant conditions for precise monitoring and early detection of deviations or performance losses. Baseline assessment : With the digital twin operational and monitoring data feeding the model, an initial assessment is conducted. This step involves running simulations to evaluate current exchanger performance, identifying bottlenecks, inefficiencies, and fouling trends. The baseline provides a clear picture of the existing operational challenges and serves as a reference point for measuring future improvements. Scenario optimisation: After the baseline is established, SmartPM enables the simulation of various operational and maintenance scenarios. These include the generation of cleaning schedules under operational and economic constraints, adjustments in flow rates, or equipment revamp options. Each scenario is analysed for its cost-effectiveness, impact on fuel consumption, and potential to reduce greenhouse gas emissions. This data-driven approach allows plant managers to make more informed decisions that balance operational reliability with economic and environmental goals.
VIEW REFERENCES
Edward Ishiyama edward.ishiyama@htri.net James Kennedy james.kennedy@htri.net Simon Pugh simon.pugh@htri.net
Refining India
37
Powered by FlippingBook