Abstract:
An arrangement for controlling a system (S) according to the deviation (ERR) between the value measured on the system (VR) and the value (VS) estimated by means of a model of the controlled system (S) of at least one control parameter. The arrangement comprises a neural network (12), which generates the estimation (VS) of the control parameter according to a set of characteristic parameters (I, Q, T) of the controlled system (S) and of respective configuration parameters (W, B). The neural network (12) has associated thereto a training module (11), which can train said neural network (12) by modifying said configuration parameters (W, B) according to a set of updating data (I t , T t , Q t , V t ). An acquisition module (21, 221) acquires the actual value, as measured on the controlled system (S), of a set of sensing parameters comprising at least one from among said control parameter (VR) and said characteristic parameters (I, Q, T) of the controlled system. A variation module (22) is sensitive to the variation of said control parameter (V k , a ; V k , m ) and generates an update-enable signal (EU) when the control parameter falls outside a pre-set tolerance range (228). The acquisition module (21, 221) being sensitive to said update-enable signal (EU) for transferring to the training module (11), as updating-data set, said set of sensing parameters (V t , Q t , I t , T t ). A preferential application is for the control of fuel-cell stacks.
Abstract:
An injection control method for controlling a "common rail" (CR) fuel injection system in a Diesel engine is described. The method comprises the following steps: a. an initialising step for acquiring engine control parameters; and b. a main adjustment cycle for adjusting operational variables of the engine. Advantageously according to the invention, the injection control method further comprises the following steps: c. an interrupting step for adjusting an injection procedure proper of the injection system by variation of all the characteristic parameters of the injection procedure. Also described is an injection control system for a Diesel engine based on the above method.
Abstract:
A method is described for controlling fuel injection in an spontaneous ignition engine (1) equipped with an electronically controlled fuel injection system (2) and with an electronic control unit (4) receiving engine quantities comprising the pressure ( P ) in the combustion changer of the engine (1) and closed-loop controlling the fuel injection system (2) on the basis of the pressure ( P ) in the combustion chamber, in which the pressure ( P ) in the combustion chamber is determined as a function of engine kinematic quantities such as the engine speed and the crank angle ( rpm , θ) and of the fuel injection law, which is defined by the quantity of fuel injected ( m c ) and by the crank angle at the start of injection ( SOI ).
Abstract:
An injection control method for controlling a "common rail" (CR) fuel injection system in a Diesel engine is described. The method comprises the following steps:
a. an initialising step for acquiring engine control parameters; and b. a main adjustment cycle for adjusting operational variables of the engine. Advantageously according to the invention, the injection control method further comprises the following steps:
c. an interrupting step for adjusting an injection procedure proper of the injection system by variation of all the characteristic parameters of the injection procedure.
Also described is an injection control system for a Diesel engine based on the above method.
Abstract:
The invention relates to a novel neuro-fuzzy integrated architecture which permits of on-line self-training. The architecture comprises at least one microcontroller (11) of the fuzzy type (fuzzyfier/defuzzyfier), dedicated to fuzzy rules computing and integrated monolythically on a semiconductor together with a non-volatile memory (9). Also provided within the same integrated circuit, are a microprocessor (5), a volatile memory unit (2), and an arbiter block (3) which is linked to a bus (4) interconnecting the fuzzy microcontroller (11), the microprocessor (5) and said volatile memory unit (2); the arbiter block (3) acts to control access to the memory unit (2) by the microprocessor (5) or the fuzzy microcontroller (11). An additional fuzzy co-processor (6) is connected between the fuzzy microcontroller (11) and the microprocessor (5) for handling the fuzzy logic operations.
Abstract:
An injection control method for controlling a "common rail" (CR) fuel injection system in a Diesel engine is described. The method comprises the following steps: a. an initialising step for acquiring engine control parameters; and b. a main adjustment cycle for adjusting operational variables of the engine. Advantageously according to the invention, the injection control method further comprises the following steps: c. an interrupting step for adjusting an injection procedure proper of the injection system by variation of all the characteristic parameters of the injection procedure. Also described is an injection control system for a Diesel engine based on the above method.
Abstract:
A PET decoder for ATM network has a modular architecture composed of a processing unit ( PU ) having RO M and SRAM memory means and a processing pipeline ( build _ A , LU _ dec , find _ Y , find _ X ) for constructing from a block of m data of a certain number of bits, a square matrix A based on a vector D of relative points over the Galois field (GF[p]), decomposing by triangular factorization the square matrix A and solving the subsystem of equations by simple substitution, and a control unit ( CU ) interfacing with the ATM network, a programmable parallel processor, a random access memory ( RAM ) and said processing unit ( PU ).
Abstract:
The invention describes a virtual pressure sensor for a Common Rail injection system of an endothermic engine (1), the injection system comprising at least one fuel pressure accumulating tank, of the rail type, having an input in fluid communication with a high-pressure pump and a plurality of outputs for feeding corresponding injectors (4) by using pressure regulating means connected and depending on an electronic control unit (9). Advantageously in the invention, the virtual pressure sensor includes a fluid-dynamic model of the accumulating tank (2) suitable to estimate and to obtain fluid pressure values used by the electronic control unit (9) for driving the injection means of the Common Rail injection system.