Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: Mean Value Engine Model

Sortuj według:

Ogranicz wyniki do:

Analysis of the possibilities of using modern process working marine diesel engine

Cuper-Przybylska D.

Journal of KONES

2016

Vol. 23, No. 2

81--88

Increasing public awareness of environmental protection, it has caused a lot of emphasis on the marine industry to create reciprocating diesel environmentally friendly. Conducting research on real objects in the laboratory gives us the solution to the problem. However, such studies generate large financial resources, especially for marine engines also take a lot of time. Creating a simulation on a computer allows for the limited financial resources and also speeding up work on the piston marine engine. Computer simulations allow the creation of more complex physical models, which can describe the process of operating a marine diesel engine. However, the complication models cause a problem of the future understanding of the model and the possibility of subsequent use of it, for example for control of the engine. The more it established the need to simplify complex models of engines for better understand the processes occurring in the engine. The article is a description of the Mean Value Engine Model (MVEM), which were analysed individual blocks of the model together with the modifications related to the environment in which the engine will run. Modular model allows better modifying it and adding new blocks. This model is based mainly designed for application control. Because of the simple structure easy to adjust for different types of engines. This is particularly good for use in motor drivers. It allows better matching engine operating parameters to reduce emissions of harmful substances into the environment and also achieve better efficiency of marine engine.

Robust predictive control of lambda in internal combustion engines using neural networks

Sardarmehni T., Keighobadi J., Menhaj M. B., Rahmani H.

Archives of Civil and Mechanical Engineering

2013

Vol. 13, no. 4

432--443

Stoichiometric air-to-fuel ratio (lambda) control plays a significant role on the performance of three way catalysts in the reduction of exhaust pollutants of Internal Combustion Engines (ICEs). The classic controllers, such as PI systems, could not result in robust control of lambda against exogenous disturbances and modeling uncertainties. Therefore, a Model Predictive Control (MPC) system is designed for robust control of lambda. As an accurate and control oriented model, a mean value model of a Spark Ignition (SI) engine is developed to generate simulation data of the engine's subsystems. Based on the simulation data, two neural networks models of the engine are generated. The identified Multi-Layer Perceptron (MLP) neural network model yields small verification error compared with that of the adaptive Radial Base Function (RBF) neural network model. Consequently, based on the MLP engine's model, the MPC system is performed through a nonlinear constrained optimization within gradient descent algorithm. The performance of the MPC system is compared with that of a first order Sliding Mode Control (SMC) system. According to simulation results, the tracking accuracy of lambda by the MPC system is close to that of the SMC system. However, the MPC system results in considerably smoother injected fuel signal.