scholarly journals Neural Nonlinear Autoregressive Model with Exogenous Input (NARX) for Turboshaft Aeroengine Fuel Control Unit Model

Aerospace ◽  
2021 ◽  
Vol 8 (8) ◽  
pp. 206
Author(s):  
Maria Grazia De Giorgi ◽  
Luciano Strafella ◽  
Antonio Ficarella
Keyword(s):  
Neural Networks ◽  
Control System ◽  
Fuel Consumption ◽  
Control Method ◽  
Engine Performance ◽  
Control Unit ◽  
Specific Fuel Consumption ◽  
Engine Fuel ◽  
State Variables ◽  
Nonlinear Autoregressive

One of the most important parts of a turboshaft engine, which has a direct impact on the performance of the engine and, as a result, on the performance of the propulsion system, is the engine fuel control system. The traditional engine control system is a sensor-based control method, which uses measurable parameters to control engine performance. In this context, engine component degradation leads to a change in the relationship between the measurable parameters and the engine performance parameters, and thus an increase of control errors. In this work, a nonlinear model predictive control method for turboshaft direct fuel control is implemented to improve engine response ability also in presence of degraded conditions. The control objective of the proposed model is the prediction of the specific fuel consumption directly instead of the measurable parameters. In this way is possible decentralize controller functions and realize an intelligent engine with the development of a distributed control system. Artificial Neural Networks (ANN) are widely used as data-driven models for modelling of complex systems such as aeroengine performance. In this paper, two Nonlinear Autoregressive Neural Networks have been trained to predict the specific fuel consumption for several transient flight maneuvers. The data used for the ANN predictions have been estimated through the Gas Turbine Simulation Program. In particular the first ANN predicts the state variables based on flight conditions and the second one predicts the performance parameter based on the previous predicted variables. The results show a good approximation of the studied variables also in degraded conditions.

scholarly journals Diesel engine performance modelling using neural networks

2005 ◽  
Author(s):  
◽  
Mark Steve Rawlins
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Diesel Engine ◽  
Fuel Consumption ◽  
Diesel Engines ◽  
Engine Performance ◽  
Specific Fuel Consumption ◽  
Engine Fuel ◽  
Modular Network ◽  
Feed Forward

The aim of this study is to develop, using neural networks, a model to aid the performance monitoring of operational diesel engines in industrial settings. Feed-forward and modular neural network-based models are created for the prediction of the specific fuel consumption on any normally aspirated direct injection four-stroke diesel engine. The predictive capability of each model is compared to that of a published quadratic method. Since engine performance maps are difficult and time consuming to develop, there is a general scarcity of these maps, thereby limiting the effectiveness of any engine monitoring program that aims to manage the fuel consumption of an operational engine. Current methods applied for engine consumption prediction are either too complex or fail to account for specific engine characteristics that could make engine fuel consumption monitoring simple and general in application. This study addresses these issues by providing a neural network-based predictive model that requires two measured operational parameters: the engine speed and torque, and five known engine parameters. The five parameters are: rated power, rated and minimum specific fuel consumption bore and stroke. The neural networks are trained using the performance maps of eight commercially available diesel engines, with one entire map being held out of sample for assessment of model generalisation performance and application validation. The model inputs are defined using the domain expertise approach to neural network input specification. This approach requires a thorough review of the operational and design parameters affecting engine fuel consumption performance and the development of specific parameters that both scale and normalize engine performance for comparative purposes. Network architecture and learning rate parameters are optimized using a genetic algorithm-based global search method together with a locally adaptive learning algorithm for weight optimization. Network training errors are statistically verified and the neural network test responses are validation tested using both white and black box validation principles. The validation tests are constructed to enable assessment of the confidence that can be associated with the model for its intended purpose. Comparison of the modular network with the feed-forward network indicates that they learn the underlying function differently, with the modular network displaying improved generalisation on the test data set. Both networks demonstrate improved predictive performance over the published quadratic method. The modular network is the only model accepted as verified and validated for application implementation. The significance of this work is that fuel consumption monitoring can be effectively applied to operational diesel engines using a neural network-based model, the consequence of which is improved long term energy efficiency. Further, a methodology is demonstrated for the development and validation testing of modular neural networks for diesel engine performance prediction.

scholarly journals Investigation of cycle skipping methods in an engine converted to positive ignition natural gas engine

2021 ◽  
Vol 13 (9) ◽  
pp. 168781402110454
Author(s):  
Erdal Tunçer ◽  
Tarkan Sandalcı ◽  
Yasin Karagöz
Keyword(s):  
Natural Gas ◽  
Fuel Consumption ◽  
Electronic Control Unit ◽  
Engine Performance ◽  
Control Unit ◽  
Operating Conditions ◽  
Spark Ignition Engine ◽  
Specific Fuel Consumption ◽  
Electronic Throttle ◽  
Operating Modes

In this study, a single cylinder of 1.16 L, naturally aspirated engine was converted to a spark ignition engine, which was a diesel engine operating with natural gas as fuel. By placing electronic throttle, electronic ignition module, gas fuel injectors and proximity sensors on the test engine, the engine has been turned into a positive ignition engine that can work with natural gas as fuel, thanks to the electronic control unit developed by our project team. Then, in the study performed, different cycle skipping strategies were experimentally investigated at a constant engine speed of 1565 rpm, in accordance with the generator operating conditions. Engine performance, emissions (CO, HC, and NOx), and combustion characteristics (cylinder pressure, rate of heat release, etc.) of cycle skipping strategies were experimentally investigated with natural gas as fuel in Normal, 3N1S, 2N1S, and 1N1S engine operating modes. According to the results obtained, specific fuel consumption, CO and HC values improved in all cycle skipping operating conditions, except for NOx, but the best results were obtained in 2N1S operating conditions; it was concluded that the specific fuel consumption, CO and HC values improved by 11.19%, 61.89%, and 65.60%, respectively.

Two-Stroke Marine Diesel Engine Variable Injection Timing System Performance Evaluation and Optimum Setting for Minimum Fuel Consumption at Acceptable NOx Levels

2014 ◽  
Author(s):  
Dimitrios T. Hountalas ◽  
Spiridon Raptotasios ◽  
Antonis Antonopoulos ◽  
Stavros Daniolos ◽  
Iosif Dolaptzis ◽  
...  
Keyword(s):  
Diesel Engine ◽  
Fuel Consumption ◽  
Engine Performance ◽  
Operating Conditions ◽  
Specific Fuel Consumption ◽  
Injection Timing ◽  
Nox Emissions ◽  
Pressure Measurements ◽  
Cylinder Pressure ◽  
Start Of Injection

Currently the most promising solution for marine propulsion is the two-stroke low-speed diesel engine. Start of Injection (SOI) is of significant importance for these engines due to its effect on firing pressure and specific fuel consumption. Therefore these engines are usually equipped with Variable Injection Timing (VIT) systems for variation of SOI with load. Proper operation of these systems is essential for both safe engine operation and performance since they are also used to control peak firing pressure. However, it is rather difficult to evaluate the operation of VIT system and determine the required rack settings for a specific SOI angle without using experimental techniques, which are extremely expensive and time consuming. For this reason in the present work it is examined the use of on-board monitoring and diagnosis techniques to overcome this difficulty. The application is conducted on a commercial vessel equipped with a two-stroke engine from which cylinder pressure measurements were acquired. From the processing of measurements acquired at various operating conditions it is determined the relation between VIT rack position and start of injection angle. This is used to evaluate the VIT system condition and determine the required settings to achieve the desired SOI angle. After VIT system tuning, new measurements were acquired from the processing of which results were derived for various operating parameters, i.e. brake power, specific fuel consumption, heat release rate, start of combustion etc. From the comparative evaluation of results before and after VIT adjustment it is revealed an improvement of specific fuel consumption while firing pressure remains within limits. It is thus revealed that the proposed method has the potential to overcome the disadvantages of purely experimental trial and error methods and that its use can result to fuel saving with minimum effort and time. To evaluate the corresponding effect on NOx emissions, as required by Marpol Annex-VI regulation a theoretical investigation is conducted using a multi-zone combustion model. Shop-test and NOx-file data are used to evaluate its ability to predict engine performance and NOx emissions before conducting the investigation. Moreover, the results derived from the on-board cylinder pressure measurements, after VIT system tuning, are used to evaluate the model’s ability to predict the effect of SOI variation on engine performance. Then the simulation model is applied to estimate the impact of SOI advance on NOx emissions. As revealed NOx emissions remain within limits despite the SOI variation (increase).

Characteristics of Water-in-Diesel Emulsions in a Single Cylinder Compression Ignition Engine

2014 ◽  
Author(s):  
Teja Gonguntla ◽  
Robert Raine ◽  
Leigh Ramsey ◽  
Thomas Houlihan
Keyword(s):  
Fuel Consumption ◽  
Direct Injection ◽  
Engine Performance ◽  
Operating Conditions ◽  
Specific Fuel Consumption ◽  
Brake Specific Fuel Consumption ◽  
Compression Ignition Engine ◽  
Oil Emulsion ◽  
Single Cylinder ◽  
Performance And Emission

The objective of this project was to develop both engine performance and emission profiles for two test fuels — a 6% water-in-diesel oil emulsion (DOE-6) fuel and a neat diesel (D100) fuel. The testing was performed on a single cylinder, direct-injection, water-cooled diesel engine coupled to an eddy current dynamometer. Output parameters of the engine were used to calculate Brake Specific Fuel Consumption (BSFC) and Engine Efficiency (η) for each test fuel. DOE-6 fuels generated a 24% reduction in NOX and a 42% reduction in Carbon Monoxide emissions over the tested operating conditions. DOE-6 fuels presented higher ignition delays — between 1°-4°, yielded 1%–12% lower peak cylinder pressures and produced up to 5.5% lower exhaust temperatures. Brake Specific Fuel consumption increased by 6.6% for the DOE-6 fuels as compared to the D100 fuels. This project is the first research done by a New Zealand academic institution on water-in-diesel emulsion fuels.

Optimization of Turbofan Propulsion Cycle Using a Genetic Algorithm

2010 ◽  
Author(s):  
Adel Ghenaiet
Keyword(s):  
Genetic Algorithm ◽  
Fuel Consumption ◽  
Pressure Ratio ◽  
Engine Performance ◽  
Optimization Procedure ◽  
Specific Fuel Consumption ◽  
High Mass ◽  
Design Parameters ◽  
Inlet Temperature ◽  
Simplifying Assumptions

This paper presents an evolutionary approach as the optimization framework to design for the optimal performance of a high-bypass unmixed turbofan to match with the power requirements of a commercial aircraft. The parametric analysis had the objective to highlight the effects of the principal design parameters on the propulsive performance in terms of specific fuel consumption and specific thrust. The design optimization procedure based on the genetic algorithm PIKAIA coupled to the developed engine performance analyzer (on-design and off-design) aimed at finding the propulsion cycle parameters minimizing the specific fuel consumption, while meeting the required thrusts in cruise and takeoff and the restrictions of temperatures limits, engine size and weight as well as pollutants emissions. This methodology does not use engine components’ maps and operates on simplifying assumptions which are satisfying the conceptual or early design stages. The predefined requirements and design constraints have resulted in an engine with high mass flow rate, bypass ratio and overall pressure ratio and a moderate turbine inlet temperature. In general, the optimized engine is fairly comparable with available engines of equivalent power range.

Combination of Neural Networks and State Vector Feedback Adaptive Control (SVFAC) Technique to Control the Gas Turbine Combustor

2006 ◽  
Author(s):  
Mahmood Lahroodi ◽  
A. A. Mozafari
Keyword(s):  
Neural Networks ◽  
Adaptive Control ◽  
Control System ◽  
Gas Turbine ◽  
Control Method ◽  
Control Performance ◽  
Gas Turbine Combustor ◽  
Model Network ◽  
Neural Network Controller ◽  
Nonlinear Plants

Neural networks have been applied very successfully in the identification and control of dynamic systems. When designing a control system to ensure the safe and automatic operation of the gas turbine combustor, it is necessary to be able to predict temperature and pressure levels and outlet flow rate throughout the gas turbine combustor to use them for selection of control parameters. This paper describes a nonlinear SVFAC controller scheme for gas turbine combustor. In order to achieve the satisfied control performance, we have to consider the affection of nonlinear factors contained in controller. The neural network controller learns to produce the input selected by the optimization process. The controller is adaptively trained to force the plant output to track a reference output. Proposed Adaptive control system configuration uses two neural networks: a controller network and a model network. The model network is used to predict the effect of controller changes on plant output, which allows the updating of controller parameters. This paper presents the new adaptive SFVC controller using neural networks with compensation for nonlinear plants. The control performance of designed controller is compared with inverse control method and results have shown that the proposed method has good performance for nonlinear plants such as gas turbine combustor.

scholarly journals Control of Exhaust Emissions Using Piston Coating on Two-StrokeSI Engines with Gasoline Blends

2021 ◽  
Vol 8 (1) ◽  
pp. H16-H20
Author(s):  
A.V.N.S. Kiran ◽  
B. Ramanjaneyulu ◽  
M. Lokanath M. ◽  
S. Nagendra ◽  
G.E. Balachander
Keyword(s):  
Fuel Consumption ◽  
Thermal Efficiency ◽  
Internal Combustion Engines ◽  
Fossil Fuels ◽  
Engine Performance ◽  
Exhaust Emissions ◽  
Specific Fuel Consumption ◽  
Thermal Barrier ◽  
Piston Crown ◽  
Barrier Coating

An increase in fuel utilization to internal combustion engines, variation in gasoline price, reduction of the fossil fuels and natural resources, needs less carbon content in fuel to find an alternative fuel. This paper presents a comparative study of various gasoline blends in a single-cylinder two-stroke SI engine. The present experimental investigation with gasoline blends of butanol and propanol and magnesium partially stabilized zirconium (Mg-PSZ) as thermal barrier coating on piston crown of 100 µm. The samples of gasoline blends were blended with petrol in 1:4 ratios: 20 % of butanol and 80 % of gasoline; 20 % of propanol and 80 % of gasoline. In this work, the following engine characteristics of brake thermal efficiency (BTH), specific fuel consumption (SFC), HC, and CO emissions were measured for both coated and non-coated pistons. Experiments have shown that the thermal efficiency is increased by 2.2 % at P20. The specific fuel consumption is minimized by 2.2 % at P20. Exhaust emissions are minimized by 2.0 % of HC and 2.4 % of CO at B20. The results strongly indicate that the combination of thermal barrier coatings and gasoline blends can improve engine performance and reduce exhaust emissions.

scholarly journals Rancang Bangun dan Pengujian Penghalang Heliks sebagai Pencampur Udara-Biogas pada Motor Otto

2021 ◽  
Vol 8 (3) ◽  
pp. 89-96
Author(s):  
Herbert Hasudungan Siahaan ◽  
Armansyah H Tambunan ◽  
Desrial ◽  
Soni Solistia Wirawan
Keyword(s):  
Fuel Consumption ◽  
Performance Test ◽  
Engine Performance ◽  
Fuel Mixture ◽  
Specific Fuel Consumption ◽  
Combustion Reaction ◽  
Otto Cycle ◽  
Direct Use ◽  
Engine Power

A helical barrier as air-biogas mixing device was designed and tested for direct use of biogas from digester in otto cycle generator set. Homogeneity of the air-fuel mixture can give better combustion reaction and increase engine power. The design was based on simulation, which shows that a 0.039 m length of helical barrier gave a 5% increase in power compared to non-helical barrier. Likewise, the simulations also showed that the helical barrier reduced specific fuel consumption (SFC) by 8%. Accordingly, the mixer with helical barrier was designed, and fabricated. Its performance test confirms the improvement resulted by using helical barriers as air-biogas mixer in the engine. The experiment showed that the power increased by 5% when using helical barrier, while SFC decreased by 4.5%. It is concluded that the helical barrier can increase the homogeneity of the mixture resulting in better engine performance. Besides, emissions produced from the engine using a helical barrier also decreased.

NEURAL ADAPTIVE CONTROL OF NONLINEAR MULTIVARIABLE SYSTEMS WITH APPLICATION TO A CLASS OF INVERTED PENDULUMS

2002 ◽  
Vol 12 (05) ◽  
pp. 411-424
Author(s):  
SHOULING HE
Keyword(s):  
Neural Networks ◽  
Control System ◽  
Control Algorithm ◽  
Learning Algorithm ◽  
Dimensional Space ◽  
Three Dimensional ◽  
Base Point ◽  
Upper Body ◽  
Model Parameters ◽  
State Variables

In this paper multilayer neural networks (MNNs) are used to control the balancing of a class of inverted pendulums. Unlike normal inverted pendulums, the pendulum discussed here has two degrees of rotational freedom and the base-point moves randomly in three-dimensional space. The goal is to apply control torques to keep the pendulum in a prescribed position in spite of the random movement at the base-point. Since the inclusion of the base-point motion leads to a non-autonomous dynamic system with time-varying parametric excitation, the design of the control system is a challenging task. A feedback control algorithm is proposed that utilizes a set of neural networks to compensate for the effect of the system's nonlinearities. The weight parameters of neural networks updated on-line, according to a learning algorithm that guarantees the Lyapunov stability of the control system. Furthermore, since the base-point movement is considered unmeasurable, a neural inverse model is employed to estimate it from only measured state variables. The estimate is then utilized within the main control algorithm to produce compensating control signals. The examination of the proposed control system, through simulations, demonstrates the promise of the methodology and exhibits positive aspects, which cannot be achieved by the previously developed techniques on the same problem. These aspects include fast, yet well-maintained damped responses with reasonable control torques and no requirement for knowledge of the model or the model parameters. The work presented here can benefit practical problems such as the study of stable locomotion of human upper body and bipedal robots.

Thermodynamics Cycle Analysis, Pressure Loss and Heat Transfer Assessment of a Recuperative System for Aero Engines

2014 ◽  
Author(s):  
A. Goulas ◽  
S. Donnerhack ◽  
M. Flouros ◽  
D. Misirlis ◽  
Z. Vlahostergios ◽  
...  
Keyword(s):  
Combustion Chamber ◽  
Fuel Consumption ◽  
Heat Exchangers ◽  
Engine Performance ◽  
Specific Fuel Consumption ◽  
Hot Gas ◽  
Research Activities ◽  
Aero Engine ◽  
Overall Efficiency ◽  
Aero Engines

Aiming in the direction of designing more efficient aero engines, various concepts have been developed in recent years, among which is the concept of an intercooled and recuperative aero engine. Particularly in the area of recuperation, MTU Aero Engines has been driving research activities in the last decade. This concept is based on the use of a system of heat exchangers mounted inside the hot-gas exhaust nozzle (recuperator). Through the operation of the system of heat exchangers, the heat from the exhaust gas, downstream the LP turbine of the jet engine is driven back to the combustion chamber. Thus, the preheated air enters the engine combustion chamber with increased enthalpy, providing improved combustion and by consequence, increased fuel economy and low-level emissions. If additionally an intercooler is placed between the compressor stages of the aero engine, the compressed air is then cooled by the intercooler thus, less compression work is required to reach the compressor target pressure. In this paper an overall assessment of the system is presented with particular focus on the recuperative system and the heat exchangers mounted into the aero engine’s exhaust nozzle. The herein presented results were based on the combined use of CFD computations, experimental measurements and thermodynamic cycle analysis. They focus on the effects of total pressure losses and heat exchanger efficiency on the aero engine performance especially the engine’s overall efficiency and the specific fuel consumption. More specifically, two different hot-gas exhaust nozzle configurations incorporating modifications in the system of heat exchangers are examined. The results show that significant improvements can be achieved in overall efficiency and specific fuel consumption hence contributing into the reduction of CO2 and NOx emissions. The design of a more sophisticated recuperation system can lead to further improvements in the aero engine efficiency in the reduction of fuel consumption. This work is part of the European funded research program LEMCOTEC (Low Emissions Core engine Technologies).

Sign in / Sign up

Export Citation Format

Share Document