NARX Technique to Predict Torque in Internal Combustion Engines

نویسندگان

چکیده

To carry out increasingly sophisticated checks, which comply with international regulations and stringent constraints, on-board computational systems are called upon to manipulate a growing number of variables, provided by an ever-increasing real virtual sensors. The optimization phase ICE passes through the control these numerous often exhibit rapidly changing trends over time. On one hand, amount data be processed, narrow cyclical frequencies, entails ever more powerful equipment. other strategies techniques required allow actuation times that useful for timely optimized control. In automotive industry, ‘machine learning’ approach is becoming most used approaches perform forecasting activities reduced effort, due both its cost-effectiveness simple compact structure. present work, nonlinear dynamic system we address related torque estimation autoregressive exogenous inputs (NARX) approach. Preliminary were performed optimize neural network in terms neurons, hidden layers, input parameters assessed. A Shapley sensitivity analysis allowed quantification impact each variable on target prediction, therefore, reduction processed architecture. all cases analyzed, structure was able achieve average percentage errors prediction always lower than critical threshold 10%. particular, when dataset augmented or analyzed merged, architecture achieved about 1%, highlighting remarkable ability reproduce fidelity.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Real-time brake torque estimation for internal combustion engines

Presented is a real-time engine brake torque estimation model where the instantaneous measured engine speed serves as the model input. The model is comprised of notch filters executed in the crank-angle domain to extract mean engine speed and the nth frequency component from the instantaneous engine speed signal in real-time. Here n denotes the number of engine cylinders. Moreover, the engine b...

متن کامل

Ethanol Internal Combustion Engines

Ethanol Internal Combustion Engines HIGHLIGHTS PROCESS AND TECHNOLOGY STATUS – The use of biofuels (e.g. bio-ethanol and biodiesel) in the transport sector can save significant amounts of fossil fuels and greenhouse gas (GHG) emissions. Internal combustion engines (ICEs) can run on bio-ethanol manufactured from biomass or waste through biochemical processes. Agricultural feedstock such as sugar...

متن کامل

Transient combustion control of internal combustion engines

This thesis addresses the problem of combustion control for automotive engines. A method is proposed to complement existing controllers, which use lookup tables based on steady-state operation. During transients, the new control method adjusts fast control variables (ignition or injection time) to compensate for deviations in the cylinder initial conditions from their optimal values due to the ...

متن کامل

Heat Transfer in Internal Combustion Engines

A heat transfer model has been developed that uses quasi-steady heat flux relations to calculate the heat transfer from combustion gases through the cylinder wall to the coolant in an internal combustion engine. The treatment of convective heat transfer accounts for the physical problems of rotating and impinging axial flow inside the engine cylinder. The radiative heat transfer includes gas ra...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Information

سال: 2023

ISSN: ['2078-2489']

DOI: https://doi.org/10.3390/info14070417