This application claims priority to and the benefit of German Patent Application No. 102018213620.3, filed on Aug. 13, 2018, the entire contents of which are incorporated herein by reference.
The disclosure relates to a method and apparatus for correction of pressure wave effected fuel injection of fuel injection actuators of a fuel injection system.
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
Combustion engines can use fuel injection systems to meet targets on performance, emission, noise and fuel efficiency. However, conventional storage accumulator injection systems are faced with pressure disturbances or pressure waves that have an impact on the fuel injection accuracy for a following injection in a negative way. These pressure disturbances reduce the engine performance of the combustion engine and reduce the emission noise and fuel efficiency of the combustion engine.
In a conventional combustion engine, the pressure disturbances and their effects on the fuel injection accuracy of the fuel injection system are compensated by control programs using correction algorithms which are based on the measurements of the pressure wave impact on fuel injection accuracy.
The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art.
The present disclosure provides a method and a system which provides precise correction of pressure wave affected fuel injection in a fully autonomous way.
In one form of the present disclosure, a fuel injection system of a combustion engine includes at least one fuel injection actuator, a high pressure fuel supply system, and a control logic device. The at least one fuel injection actuator is adapted to inject fuel into a cylinder of the combustion engine. The high pressure fuel supply system is adapted to supply the fuel injection actuators with fuel. The control logic device includes an artificial neural network adapted to calculate pressure correction data used to correct pressure waves generated by at least one actuator of the fuel injection system.
The fuel injection system according to the first aspect of the present disclosure has the advantage that it is fully self-adaptive and does not require pre-working by an engineer if there are changes in the system, in particular in the high pressure fuel supply system and/or the used combustion engine.
A further advantage of the fuel injection system according to the first aspect of the present disclosure is in that it improves the accuracy of pressure wave correction of pressure waves generated by actuators, in particular pressure waves generated by a high pressure pump and/or by a pressure control valve of the high pressure fuel supply system.
In one form, the present disclosure provides a method for correction of pressure wave affected fuel injection by fuel injection actuators of a fuel injection system.
The method for correction of pressure wave affected fuel injection by fuel injection actuators of a fuel injection system comprises the steps of:
In one form, the artificial neural network comprises a deep neural network having an input layer to receive input variables, at least one hidden layer, and an output layer to provide output variables.
In a further possible form of the fuel injection system, the artificial neural network is trained with training data sets provided for varying parameters of the fuel injection system and/or combustion engine.
In a still further possible form of the fuel injection system in the first aspect of the present disclosure, the high pressure fuel supply system comprises a high pressure pump adapted to pump fuel from a fuel reservoir into a common high pressure fuel rail adapted to supply the fuel injection actuators with high pressure fuel.
In a still further possible form of the fuel injection system in the first aspect of the present disclosure, the high pressure pump forms an actuator of said high pressure fuel supply system and generates pressure waves at each compression stroke of the high pressure pump.
In other form of the fuel injection system, the high pressure fuel supply system comprises a pressure control valve adapted to regulate a fuel pressure in the common high pressure fuel rail, wherein the pressure control valve forms an actuator of the high pressure fuel supply system and generates pressure waves when actuated.
In a still further possible form of the fuel injection system, the high pressure fuel supply system comprises at least one pressure sensor adapted to measure the pressure within the high pressure fuel supply system to provide pressure data supplied as input variables to the artificial neural network of the control logic device.
In a still further possible form of the fuel injection system, load point information data is supplied as input variables to the artificial neural network of the control logic device.
In a still further possible form of the fuel injection system, the artificial neural network is adapted to calculate pressure correction data as an output variable on the basis of the pressure data received from the at least one pressure sensor and on the basis of the received load point information data.
In a further possible form of the fuel injection system, pressure wave affected fuel injection is corrected according to the pressure correction data calculated by the artificial neural network of the control logic device by adjusting an energizing time and/or an energizing amplitude of each fuel injection actuator.
In a still further possible form of the fuel injection system, the fuel injection actuator is adapted to inject fuel into its associated cylinder of the combustion engine during a main injection and during one or more pilot injections preceding the main injection.
In a still further possible form of the fuel injection system, pressure wave affected fuel injection is corrected according to the pressure correction data calculated by the artificial neural network of the control logic device by controlling the energizing time and/or energizing amplitude of the main injection and/or pilot injections of the fuel injection actuators.
The present disclosure further provides a control logic device for a fuel injection system including an artificial neural network and a control unit. The artificial neural network is adapted to calculate pressure correction data used to correct pressure waves generated by at least one actuator of the fuel injection system. The control unit is adapted to generate control signals for the fuel injection actuators of the fuel injection system depending on the calculated pressure correction data.
Further areas of applicability will become apparent from the description provided herein. It should be understood that the description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure.
In order that the disclosure may be well understood, there will now be described various forms thereof, given by way of example, reference being made to the accompanying drawings, in which:
The drawings described herein are for illustration purposes only and are not intended to limit the scope of the present disclosure in any way.
The following description is merely exemplary in nature and is not intended to limit the present disclosure, application, or uses. It should be understood that throughout the drawings, corresponding reference numerals indicate like or corresponding parts and features.
As can be seen in the block diagram of
The high pressure fuel supply system further comprises at least one pressure sensor 10 adapted to measure the current pressure within the high pressure fuel supply system at a position within the high pressure fuel supply to provide pressure data supplied via a signal line 11 as in input variable “x” to an artificial neural network 12A of a control logic device 12 as shown in
The high pressure pump 5 of the fuel supply system forms an actuator which generates unwanted pressure waves PW at each compression stroke of the high pressure pump 5. Also the pressure control valve 9 forms an actuator of the high pressure fuel supply system which generates unwanted pressure waves PW when actuated. Also each fuel injection actuator 3-i can generate pressure waves PW when actuated. The pressure waves PW propagate through the pipes and affect the fuel injection by the fuel injection actuators 3-i negatively. A system pressure can be measured at a position in the high pressure fuel supply. The system pressure can be anything between a maximum pressure and a minimum pressure depending on engine and/or pump speed as well as the fuel amount and depending on several other impacting factors. The ideal information which is desired is the precise pressure at each fuel injection actuator 3-i in order to calculate the correct actuation of the respective fuel injection actuator 3-1 since the injected fuel quantity depends on the pressure at the location of the fuel injection actuator 3-i and the opening duration of the respective fuel injection actuator 3-i. However, this pressure information for each individual fuel injection actuator 3-i is not existing as a measurement signal. Only a calculation of this pressure information is possible and is performed by the control logic device 12 of the system 1. The pressure sensor 10 is adapted to measure the system pressure within the high pressure fuel supply system and supplies the pressure data as one of a plurality of input variables x to the artificial neural network 12A of the control logic device 12 as shown in
Further, input variables x supplied as load point information data to the artificial neural network 12A can comprise also parameters concerning the status of correction functions, in particular whether the pilot corrections and/or main corrections are active or not. In another form, the load point information data supplied as input variables x to the artificial neural network 12A can further comprise data concerning fuel properties of the fuel, in particular fuel temperature and/or fuel type (physical properties of the fuel).
In one form of the fuel injection system 1, the supplied input variables x can also include data concerning the hardware set-up of the fuel supply system and/or combustion engine. The supplied variables x can comprise information about the implemented hardware of the system such as length of the supply pipes, the pump type of the high pressure pump 5, the injector type of the used fuel injection actuators 3, volume of the common high pressure fuel rail 4, and information about the pressure control valve 9. These kind of information data is normally constant after implementation of the system, i.e., the fuel supply system and/or the combustion engine. However, the use of these input variables allows to use the control logic device 12 also for different types of combustion engines and/or fuel supply systems. Accordingly, the artificial neural network 12A can be trained for not only a single type of combustion engine or vehicle type, but for different types or variants of a combustion engine and/or motors.
The artificial neural network 12A calculates pressure correction data pcd as an output variable y supplied to the control unit 12B as shown in
The artificial neural network 12A implemented in the control logic device 12 can comprise several layers wherein each layer can comprise a plurality of calculating nodes. In another form, the artificial neural network 12A is a deep neural network DNN comprising an input layer IL, one or more hidden layers HL and an output layer OL. In a possible implementation, the artificial neural network 12A comprises an input layer IL, three hidden layers HL and an output layer OL.
The common rail fuel system can stabilize the rail pressure within a relative small margin to a nominal value. The high pressure pump 5 provides a high rail pressure and continuously delivers fuel F to the high pressure fuel rail 4. The pressure is monitored by the pressure sensor 10 and pressure data of the current pressure is supplied to the artificial neural network 12A. The common rail fuel supply system has the advantage that the fuel pressure is independent of the engine speed and load conditions. This allows for flexibility in controlling both, the fuel injection quantity and injection timing, and provides better spray penetration in mixing even at low combustion engine speeds and loads. Further, the common rail system provides for lower fuel pump peak torque requirements and improved noise quality of the engine.
As illustrated in
In a first step S1 pressure correction data pcd are calculated by an artificial neural network ANN on the basis of pressure data provided by at least one pressure sensor and on the basis of received load point information data.
In a further step S2 fuel injection actuators of the fuel injection system are controlled in response to the pressure correction data calculated by the artificial neural network ANN.
The correction of the negative effects of pressure waves PW on the fuel injection is performed by adjusting the energizing time ET and/or the energizing amplitude EA of the respective injection. Depending on when the injection is released, the energizing time ET is set to an appropriate value. The control logic device 12 of the fuel injection system 1 provides for a precise elimination of pressure waves PW generated by actuators of the system, in particular generated by the high pressure pump 5 and the high pressure control valve 9.
A fuel injection system 1 according to the present disclosure as illustrated for instance in
The fuel injection actuators 3-i are electrically activated by the control unit 12B. A hydraulic valve (consisting of a nozzle and plunger) can be mechanically or hydraulically opened and the fuel F is sprayed into the associated cylinder 2-i (i=1, 2, 3, 4) at the desired pressure. Since the fuel pressure energy is stored remotely and the fuel injection actuators 3-i are electrically actuated in response to the control signals CRTL received from the control unit 12B, the injection pressure at a start and at the end of injection is close to the pressure within the accumulator, i.e. at the high pressure fuel rail 4. According to the dimension of the accumulator, pump and plumbing, the injection pressure and rate can be almost the same for each of the multiple injection events.
The artificial neural network (ANN) 12A, the control unit 12B, the control logic device 12, the controller CONT, and the high pressure analyzing unit HDA may be realized as at least one microprocessor operated by a predetermined program, and the predetermined program may include a set of instruction to perform the above-described functions.
While this present disclosure has been described in connection with what is presently considered to be practical exemplary forms, it is to be understood that the present disclosure is not limited to the disclosed forms, but, on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the present disclosure.
Number | Date | Country | Kind |
---|---|---|---|
102018213620.3 | Aug 2018 | DE | national |