Method and system for estimating a quantity of particles emitted in the exhaust gas of a diesel engine for a motor vehicle
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G01M-017/00
G06F-007/00
G06F-015/18
F01N-003/00
G05B-013/02
G06E-001/00
G06E-003/00
G06G-007/00
출원번호
US-0580004
(2004-11-09)
등록번호
US-7409247
(2008-08-05)
우선권정보
FR-03 13549(2003-11-19)
국제출원번호
PCT/FR04/050574
(2004-11-09)
§371/§102 date
20061220
(20061220)
국제공개번호
WO05/052332
(2005-06-09)
발명자
/ 주소
Daneau,Marc
Netter,Caroline
출원인 / 주소
Renault s.a.s.
대리인 / 주소
Oblon, Spivak, McClelland, Maier & Neustadt, P.C.
인용정보
피인용 횟수 :
1인용 특허 :
3
초록▼
The inventive system for estimating quantities of pollution compounds emitted in the exhaust gas of a diesel engine for a motor vehicle comprises means for regenerating a solid particle filter and an electronic control unit which manages the engine operation and is provided with one or several data
The inventive system for estimating quantities of pollution compounds emitted in the exhaust gas of a diesel engine for a motor vehicle comprises means for regenerating a solid particle filter and an electronic control unit which manages the engine operation and is provided with one or several data memories. Said system also comprises one or several neurone networks (1) and networks (2) of input data representative for the engine operation and possibly for the vehicle motion, said data is available in the electronic control unit for managing the engine operation without an additional sensor. Said system also comprises means (4) for cumulating estimated quantities.
대표청구항▼
The invention claimed is: 1. A system for estimating quantities of pollutant compounds emitted in exhaust gases of a diesel engine of a motor vehicle, comprising means for regenerating a solid particulate filter, an electronic control unit for managing a engine operation comprising data memories, a
The invention claimed is: 1. A system for estimating quantities of pollutant compounds emitted in exhaust gases of a diesel engine of a motor vehicle, comprising means for regenerating a solid particulate filter, an electronic control unit for managing a engine operation comprising data memories, and the system further comprising: one or more neural networks; input data representative of the engine operation and, optionally, of vehicle movement, said data being available in the electronic control unit for managing the engine operation without adding a sensor; means for cumulating the estimated quantities; and 10 to 15 neurons. 2. The system as claimed in claim 1, further comprising training databases of the one or more neural networks, said databases being vehicle drive sequences of at least a few minutes. 3. The system as claimed in claim 1, wherein data used at an input of the one or more neural networks comprise at least one of the following parameters: an engine speed at two consecutive times t and t-Δt; a fuel flow rate at three consecutive times t, t-Δt and t-2Δt; an engine coolant temperature; and a vehicle speed at time t; where Δt is the preset time interval between two consecutive measurement times and further comprising means for estimating at least the cumulative quantity of soot in the exhaust gases which will be retained by the particulate filter. 4. The system as claimed in claim 1, wherein data used at an input of the one or more neural networks comprise at least one of the following parameters: an engine speed at two consecutive times t and t-Δt; a fuel flow rate at three consecutive times t, t-Δt and t-2Δt; an engine coolant temperature; and a fuel-air ratio of a mixture at time t; where Δt is the preset time interval between two consecutive measurement times and further comprising means for estimating at least the cumulative quantity of soot in the exhaust gases which will be retained by a particulate filter. 5. The system as claimed in claim 1, adapted to an engine with common rail injection, wherein a data used at an input of the one or more neural networks at time t comprise at least one of the following parameters: a fuel preinjection rate in the engine; a main fuel injection rate in the engine; a relative displacement of a piston with respect to top dead center from a time when a last fuel injection in a piston cylinder started; the relative displacement of a piston with respect to top dead center from a time when a last main fuel injection in a piston cylinder started; an engine coolant temperature; an engine air feed rate; a pressure inside the common rail; and an engine speed; and wherein the estimated quantities of pollutant compounds comprise at least one of the following quantities: the cumulative quantity of soot in the exhaust gases that will be retained by a particulate filter; the cumulative quantity of nitrogen oxides in the exhaust gases; the cumulative quantity of carbon oxides in the exhaust gases; and the cumulative quantity of hydrocarbons in the exhaust gases. 6. The system as claimed in claim 1, further comprising means for resetting the estimated quantities of particulates, independently of each other. 7. A method of calibrating engine control strategies comprising a step of estimating engine emissions over a vehicle drive cycle, wherein said estimating step is performed with the system as defined in claim 6. 8. A system for estimating quantities of pollutant compounds emitted in exhaust gases of a diesel engine of a motor vehicle, comprising means for regenerating a solid particulate filter, an electronic control unit for managing the engine operation comprising data memories, and further comprising: one or more neural networks; input data representative of the engine operation and, optionally, of vehicle movement, said data being available in the electronic control unit for managing the engine operation without adding a sensor; and means for cumulating the estimated quantities, wherein no output from the system is looped to an input of the system to avoid any problem of stability. 9. A method of controlling the means for regenerating the solid particulate filter of either claims 5 and 8, the method comprising the step of comparing an estimated quantity of cumulative soot with a memorized threshold value. 10. A method for evaluating a system for estimating quantities of pollutant compounds emitted in exhaust gases of a diesel engine of a motor vehicle, comprising means for regenerating a solid particulate filter, an electronic control unit for managing the engine operation comprising data memories, and further comprising: one or more neural networks; input data representative of the engine operation and, optionally, of vehicle movement, said data being available in the electronic control unit for managing the engine operation without adding a sensor; and means for cumulating the estimated quantities, said method comprising the step of: evaluating a best configuration of the one or more neural networks by calculating an error on output quantities by cumulation on a sliding window. 11. The method as claimed in claim 10, comprising the step of determining the sliding window so that its size is minimal while allowing an estimation error lower than a preset value. 12. The method as claimed in claim 11, wherein the size of the window corresponding to a vehicle movement varies between 0.5 km and 1.5 km to allow an estimation error of not more than 5 g of solid particulates emitted per 135 km traveled by the vehicle. 13. The method as claimed in claim 10, comprising the step of discarding part of the input data, reserved for training the one or more neural networks, to perform a validation without the input data being used.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (3)
Puskorius Gintaras V. (Redford MI) Feldkamp Lee A. (Plymouth MI), Catalyst monitor with direct prediction of hydrocarbon conversion efficiency by dynamic neural networks.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.