NASA Engine Research Articles

TCN-GAWO: Genetic Algorithm Enhanced Weight Optimization for Temporal Convolutional Network

Abstract This article proposes a genetic algorithm (GA)-enhanced weight optimization method for temporal convolutional network (TCN-GAWO). TCN-GAWO combines the evolutionary process of the genetic algorithm with the gradient-based training and can achieve higher predication/fitting accuracy than traditional temporal convolutional network (TCN). Performances of TCN-GAWO are also more stable. In TCN-GAWO, multiple TCNs are generated with random initial weights first, then these TCNs are trained individually for given epochs, next the selection-crossover-mutation procedure is applied among TCNs to get the evolved offspring. Gradient-based training and selection-crossover-mutation are taken in turns until convergence. The TCN with the optimal performance is then selected. Performances of TCN-GAWO are thoroughly evaluated using realistic engineering data, including C-MAPSS dataset provided by NASA and jet engine lubrication oil dataset provided by airlines. Experimental results show that TCN-GAWO outperforms existing methods for both datasets, demonstrating the effectiveness and the wide range applicability of the proposed method in solving time series problems.

Semi-supervised Constrained Hidden Markov Model Using Multiple Sensors for Remaining Useful Life Prediction and Optimal Predictive Maintenance

Remaining Useful Life (RUL) estimation is critical in many engineering systems where proper predictive maintenance is needed to increase a unit's effectiveness and reduce time and cost of repairing. Typically for such systems, multiple sensors are normally used to monitor performance, which create difficulties for system state identification. In this paper, we develop a semi-supervised left-to-right constrained Hidden Markov Model (HMM) model, which is effective in estimating the RUL, while capturing the jumps among states in condition dynamics. In addition, based on the HMM model learned from multiple sensors, we build a Partial Observable Markov Decision Process (POMDP) to demonstrate how such RUL estimation can be effectively used for optimal preventative maintenance decision making. We apply this technique to the NASA Engine degradation data and demonstrate the effectiveness of the proposed method.

Auralization of Hybrid Wing–Body Aircraft Flyover Noise from System Noise Predictions

System noise assessments of a state-of-the-art reference aircraft (similar to a Boeing 777-200ER with GE90-like turbofan engines) and several hybrid wing–body aircraft configurations were recently performed using NASA engine and aircraft system analysis tools. The hybrid wing–body aircraft were sized to an equivalent mission as the reference aircraft and assessments were performed using measurements of airframe shielding from a series of propulsion airframe aeroacoustic experiments. The focus of this work is to auralize flyover noise from the reference aircraft and the best hybrid wing–body configuration using source noise predictions and shielding data based largely on the earlier assessments. Here, auralization refers to the process by which numerical predictions are converted into audible pressure time histories. It entails synthesis of the source noise and propagation of that noise to a receiver on the ground. For each aircraft, three flyover conditions are auralized. These correspond to approach, sideline, and cutback operating states, but flown in straight and level flight trajectories. The auralizations are performed using synthesis and simulation tools developed at NASA. Audio and visual presentations are provided to allow the reader to experience the flyover from the perspective of a listener in the simulated environment.

Hybrid Wing Body Aircraft System Noise Assessment with Propulsion Airframe Aeroacoustic Experiments

A system noise assessment of a hybrid wing body configuration was performed using NASA's best available aircraft models, engine model, and system noise assessment method. A propulsion airframe aeroacoustic effects experimental database for key noise sources and interaction effects was used to provide data directly in the noise assessment where prediction methods are inadequate. NASA engine and aircraft system models were created to define the hybrid wing body aircraft concept as a twin engine aircraft with a 7500 nautical mile mission. The engines were modeled as existing technology, in production, bypass ratio seven turbofans. The baseline hybrid wing body aircraft was assessed at 26.4 dB cumulative below the FAA Stage 4 certification level. To determine the potential for noise reduction with relatively near term technologies, seven other configurations were assessed beginning with moving the engines two fan nozzle diameters upstream of the trailing edge and then adding technologies for reduction of the highest noise sources. Aft radiated noise was expected to be the most challenging to reduce and, therefore, the experimental database focused on jet nozzle and pylon configurations that could reduce jet noise through a combination of source reduction and shielding effectiveness. The best configuration for reduction of jet noise used state-of-the-art technology chevrons with a pylon above the engine in the crown position. This configuration resulted in jet source noise reduction, favorable azimuthal directivity, and noise source relocation upstream where it is more effectively shielded by the limited airframe surface, and additional fan noise attenuation from acoustic liner on the crown pylon internal surfaces. Vertical and elevon surfaces were also assessed to add shielding effectiveness. The elevon deflection above the trailing edge showed some small additional noise reduction whereas vertical surfaces resulted in a slight noise increase. With the effects of the configurations from the database included, the best available noise reduction was 41.5 dB cumulative. Projected effects from additional technologies were assessed for an advanced noise reduction configuration including landing gear fairings and advanced pylon and chevron nozzles. Incorporating the three additional technology improvements, an aircraft noise is projected of 42.9 dB cumulative below the Stage 4 level.

Optimization for Aircraft Engines with Regression and Neural-Network Analysis Approximators

The NASA Engine Performance Program (NEPP) can configure and analyze almost any type of gas turbine engine that can be generated through the interconnection of a set of standard physical components. In addition, the code can optimize engine performance by changing adjustable variables under a set of constraints. However, for engine cycle problems at certain operating points, the NEPP code can encounter difficulties: nonconvergence in the currently implemented Powell's optimization algorithm and deficiencies in the Newton-Raphson solver during engine balancing. A project was undertaken to correct these deficiencies. Nonconvergence was avoided through a cascade optimization strategy, and deficiencies associated with engine balancing were eliminated through neural network and linear regression methods. An approximation-interspersed cascade strategy was used to optimize the engine's operation over its flight envelope. Replacement of Powell's algorithm by the cascade strategy improved the optimization segment of the NEPP code. The performance of the linear regression and neural network methods as alternative engine analyzers was found to be satisfactory. This report considers two examples-a supersonic mixed-flow turbofan engine and a subsonic waverotor-topped engine-to illustrate the results, and it discusses insights gained from the improved version of the NEPP code.

Optimization of air-breathing propulsion engine concept

The design optimization of air-breathing propulsion engine concepts has been accomplished by soft-coupling the NASA Engine Performance Program (NEPP) analyser with the NASA Lewis multidisciplinary optimization tool COMETBOARDS. Engine problems, with their associated design variables and constraints, were cast as non-linear optimization problems with thrust as the merit function. Because of the large number of mission points in the flight envelope, the diversity of constraint types, and the overall distortion of the design space, the most reliable optimization algorithm available in COMETBOARDS, when used by itself, could not produce satisfactory, feasible, optimum solutions. However, COMETBOARDS' unique features–which include a cascade strategy, variable and constraint formulations, and scaling devised especially for difficult multidisciplinary applications–successfully optimized the performance of subsonic and supersonic engine concepts. Even when started from different design points, the combined COMETBOARDS and NEPP results converged to the same global optimum solution. This reliable and robust design tool eliminates manual intervention in the design of air-breathing propulsion engines and eases the cycle analysis procedures. It is also much easier to use than other codes, which is an added benefit. This paper describes COMETBOARDS and its cascade strategy and illustrates the capabilities of the combined design tool through the optimization of a high-bypass-turbofan wave-rotor-topped subsonic engine and a mixed-flow-turbofan supersonic engine. ©1997 John Wiley & Sons, Ltd.

Cascade Optimization Strategy for Aircraft and Air-Breathing Propulsion System Concepts

Design optimization for subsonic and supersonic aircraft and for air-breathing propulsion engine concepts has been accomplished by soft-coupling the Flight Optimization System (FLOPS) and the NASA Engine Performance Program analyzer (NEPP), to the NASA Lewis multidisciplinary optimization tool COMETBOARDS. Aircraft and engine design problems, with their associated constraints and design variables, were cast as nonlinear optimization problems with aircraft weight and engine thrust as the respective merit functions. Because of the diversity of constraint types and the overall distortion of the design space, the most reliable single optimization algorithm available in COMETBOARDS could not produce a satisfactory feasible optimum solution. Some of COMETBOARDS' unique features, which include a cascade strategy, variable and constraint formulations, and scaling devised especially for difficult multidisciplinary applications, successfully optimized the performance of both aircraft and engines. The cascade method has two principal steps: In the first, the solution initiates from a user-specified design and optimizer, in the second, the optimum design obtained in the first step with some random perturbation is used to begin the next specified optimizer. The second step is repeated for a specified sequence of optimizers or until a successful solution of the problem is achieved. A successful solution should satisfy the specified convergence criteria and have several active constraints but no violated constraints. The cascade strategy available in the combined COMETBOARDS, FLOPS, and NEPP design tool converges to the same global optimum solution even when it starts from different design points. This reliable and robust design tool eliminates manual intervention in the design of aircraft and of air-breathing propulsion engines where it eases the cycle analysis procedures. The combined code is also much easier to use, which is an added benefit. This paper describes COMETBOARDS and its cascade strategy and illustrates the capability of the combined design tool through the optimization of a subsonic aircraft and a high-bypass-turbofan wave-rotor-topped engine.

NNEPEQ—Chemical Equilibrium Version of the Navy/NASA Engine Program

The Navy NASA Engine Program, NNEP, developed in 1975, currently is in use at a large number of government agencies, commercial companies, and universities. This computer code has been used extensively to calculate the design and off-design (matched) performance of a broad range of turbine engines, ranging from subsonic turboprops to variable cycle engines for supersonic transports. Recently, there has been increased interest in applications that NNEP was not capable of simulating, namely, high Mach applications, alternate fuels including cryogenics, and cycles such as the gas generator air-turbo-rocket (ATR). In addition, there is interest in cycles employing ejectors such as for military fighters. New engine component models had to be created for incorporation into NNEP, and it was also found necessary to include chemical dissociation effects of high-temperature gases. This paper discusses the incorporation of these extended capabilities of NNEP and illustrates some of the effects of these changes.

The Feasibility of Water Injection Into the Turbine Coolant to Permit Gas Turbine Contingency Power for Helicopter Application

A system which would allow a substantially increased output from a turboshaft engine for brief periods in emergency situations with little or no loss of turbine stress rupture life is proposed and studied analytically. The increased engine output is obtained by turbine overtemperature; however, the temperature of the compressor bleed air used for hot section cooling is lowered by injecting and evaporating water. This decrease in cooling air temperature can offset the effect of increased gas temperature and increased shaft speed and thus keep turbine blade stress rupture life constant. The analysis utilized the Navy NASA Engine Program or NNEP computer code to model the turboshaft engine in both design and off-design modes. This report is concerned with the effect of the proposed method of power augmentation on the engine cycle and turbine components. A simple cycle turboshaft engine with a 16:1 pressure ratio and a 1533 K (2760° R) turbine inlet temperature operating at sea level static conditions was studied to determine the possible power increase and the effect on turbine stress rupture life that could be expected using the proposed emergency cooling scheme. The analysis showed a 54 percent increase in output power can be achieved with no loss in gas generator turbine stress rupture life. A 231 K (415° F) rise in turbine inlet temperature is required for this level of augmentation. The required water flow rate was found to be 0.0109 kg water per kg of engine air flow. For a 4.474 MW (6000 shp) engine this would require 32.26 kg (71.13 lbm) of water for a 2.5 min transient. At this power level, approximately 25 percent of the uncooled power turbine life is used up in a 2 1/2-min transient. If the power turbine were cooled, this loss of stress-rupture life could be reduced to zero. Also presented in this report are the results of an analysis used to determine the length of time a ceramic thermal barrier coating would delay the temperature rise in hot parts during operation at elevated temperatures. It was hoped that the thermal barrier could be used as a scheme to allow increased engine output while maintaining the life of hot section parts during short overtemperature transients. The thermal barrier coating was shown to be ineffective in reducing blade metal temperature rise during a 2.5-min overtemperature.