Honeywell (India)

Abstract This paper presents a comprehensive study on the implementation of an artificial intelligence and machine learning (AI/ML) based flare management system in oil and gas operations. The research focuses on the utilization of Honeywell's Flare Intelligence system at ADNOC's Northeast Bab (NEB) facilities, specifically at Rumaitha site. The study demonstrates how AI-driven automation can transform traditional manual flare categorization processes and root-cause analysis into intelligent, real-time monitoring systems that enhance proactive operational actions, improve regulatory compliance, and enable proactive flare management. The system successfully categorizes flaring events into routine, non-routine, and safety categories while providing automated root cause analysis for abnormal flares. The methodology combines historical data analysis, near real-time monitoring, and predictive analytics to create a comprehensive flare management system. This research contributes to the growing body of knowledge on digital transformation in the energy and emissions sector and provides practical insights for implementing AI-driven sustainability solutions in industrial operations.

Abstract Computational modeling of hot streak migration in gas turbines is challenging due to multi-scale physics and dynamic interaction between the combustor and the high-pressure turbine (HPT) first stage. The standard practice for modeling such interactions has been performing a 1-way transfer of boundary conditions from the combustor exit to the turbine inlet. This approach is simple but not ideal for capturing the intricate flow perturbations that travel across the components and, hence, not suitable for accurately predicting hot streak migration. An improvement on the standard practice is to conduct separate component simulations and use a 2-way boundary-condition exchange process, which we call co-simulation. In co-simulations, the information between the combustor and the HPT is exchanged in an iterative loop until convergence is achieved. The co-simulations are performed on the hot section of a Honeywell turbofan engine using Stress Blended Eddy Simulation (SBES) in the reversed flow annular combustor and Reynolds Averaged Navier Strokes (RANS) in the HPT. However, the most accurate combustor-turbine interactions are modeled using joint simulation in which the combustor and the HPT stage are in the same computational domain. Therefore, the joint simulation process excludes the need for any boundary condition exchange. The SBES turbulence model, Flamelet combustion model, and discrete phase-based spray model are applied to the entire domain. Inherent to joint simulations, the transient HPT calculations require the time scale to be that of HPT, which is generally one order of magnitude lower than the combustor time-scale. As a result, joint simulations are computationally very costly (in most situations, prohibitive) compared to co-simulations. In this paper, the computational viability of joint simulations, as a better alternative to co-simulations, is explored using a mixing-plane interface in the HPT. Such an approach ameliorates the disparity in time-scale between the combustor and rotor, which is observed in calculations of joint simulations. As the calculations in joint simulations are performed at combustor time-scale, the overall process hence becomes computationally faster than co-simulations. The hot streak migration in the HPT is modeled by using a separate simulation of the HPT with sliding mesh (advanced at rotor time-scale). The aero-thermal flow solution and hot-streak migration in the HPT stage are compared between the 1-way transfer, co-simulation, and joint simulation. The distribution of near-wall blade temperatures (instantaneous, period-averaged, maximum, and minimum) is analyzed.

Abstract Advances in technology have made it easy to integrate multiple modern systems to form complex system‐of‐systems (SoS) to achieve unparalleled levels of functionality that are otherwise not achievable by the constituent systems in isolation. In fact, with the recent explosion of machine learning techniques to build autonomous systems such as drones and self‐driving cars, there is a pressing need to ensure that they collaboratively and safely operate in an SoS context. However, in general, the characteristic emergent behaviors of complex SoS – that directly impact its operational measures of success or Measures of Effectiveness (MOEs) – is very difficult, if not impossible, to manually explore, anticipate, and arbitrate just from knowledge of its underlying systems. Further, there are multiple scenarios of evolution in such complex SoS, including evolution in the emergent behavior of the SoS. The continuous, continual, and evolving nature of the SoS and constituent system environment's state and possible actions, adds further complexity. In this paper, we present a novel approach that leverages Reinforcement Learning, a machine learning approach, to inculcate adaptable intelligence in constituent systems to adapt their behaviors in tandem with the evolution of emergent behavior at the SoS level. By augmenting the reward mechanism of RL by leveraging SoS‐Constituent System MOE Relationship, that relates and ranks System MOEs vs. SoS MOEs, we inculcate an Intelligent‐Behavior Evolution Agent, with the necessary constraints to learn to maximize the SoS and system‐level MOEs, while adapting itself to the evolution in SoS. We illustrate our approach and demonstrate its feasibility and potential by applying it to a power grid SoS case example. The effectiveness and performance of the approach are quantified.

The Air-breathing Hypersonic Vehicle can fulfil futuristic ambitions of rapid global travel on Earth and in space in the near future. This paper presents the linear control design for the linear dynamic 6DOF model with the decoupled dynamics. The analysis and simulation of the 6DOF linear model is performed at trimmed flight condition at Mach number, <tex>$M=5$</tex> and height, <tex>$h=35000ft$</tex> for the level and straight flight. The dynamic stability of the model is analyzed using classical control technique and state feedback control using pole placement, and comparison with PI, PD and PID is shown.

Abstract The aerodynamic performance of a compressor rotor is known to deteriorate due to surface roughness. It is important to understand this deterioration as it impacts the overall performance of the engine. This paper, therefore, aims to numerically investigate the impact of roughness on the performance of an axial compressor rotor at different rotational speeds. In this numerical study, the simulations are carried out for NASA Rotor37 at 100%, 80%, and 60% of its design speed. with and without roughness on the blade surface. These speeds are chosen because they represent different flow regimes. The front stages of a multistage compressor usually have a supersonic or transonic regime whereas the middle and aft stages have a subsonic regime. Thus, these performance characteristics can give an estimate of the impact on the performance of a multistage compressor. At 100% speed (design speed), the relative flow is supersonic, at 80% of design speed, the relative flow is transonic and at 60% of design speed, the relative flow is subsonic. Detailed flow field investigations are carried out to understand the underlying flow physics. The results indicate that, for the same amount of roughness, the degradation in the performance is maximum at 100% speed where the rotor is supersonic, while the impact is minimum at 60% speed where the rotor is subsonic. Thus, the rotor shock system plays an important role in determining the performance loss due to roughness. It is also observed that the loss increases with increased span for 100% and 80% speeds, but for 60% speed, the loss is almost constant from the hub to the shroud. This is because, with the increased span, the shock strength increases for 100% and 80% speeds, whereas at 60% speed flow is subsonic.