Description:Complete Specification:
The following specification describes and ascertains the nature of this invention and the manner in which it is to be performed.

Field of the invention:
[0001] The present invention relates to a device and method to determine injection mass deviation in a Hydrogen Gas Injector (HGI).

Background of the invention:
[0002] In current practice the fuel flows from storage tank to combustion chamber. The hydrogen fuel is stored in high pressure in the storage tank which is passed to the combustion chamber by regulating the pressure using Hydrogen injection pressure regulator and accumulating the gas in Hydrogen rail with reduced pressure and injected into the combustion chamber via Hydrogen gas injector for accurate injection which helps for proper combustion. However, the injected mass of hydrogen gas into the combustion chamber is not always equal to the setpoint mass due to which the expected behavior of the system is slightly affected. It is difficult to calculate the exact amount of hydrogen gas injected into the combustion chamber using a hardware / measuring device which is due to the temperature constraints inside combustion chamber. Therefore, there is a strong motivation to determine injection mass deviation in the Hydrogen gas injector.

[0003] According to a prior art US2018100449, an apparatus for operating a gaseous fuel injector in an internal combustion engine. The apparatus comprises a mass flow sensor that generates a signal representative of the mass flow rate of the gaseous fuel in a supply conduit in the engine. A controller is connected with the injector and the mass flow sensor is programmed to actuate the injector to introduce gaseous fuel into the engine which determines the actual mass flow rate of the gaseous fuel on the signal representative of the mass flow rate. It also calculates a difference between the actual mass flow and a desired mass flow rate. Based on that, at least one of on-time of the gaseous fuel injector and a magnitude of an injector activation signal by respective amounts based on the difference when the absolute value of the difference is greater than a predetermined value.

[0004] Brief description of the accompanying drawings:
[0005] An embodiment of the disclosure is described with reference to the following accompanying drawings,
[0006] Fig. 1 illustrates a block diagram of a device to determine injection mass deviation in a Hydrogen Gas Injector (HGI), according to an embodiment of the present invention;
[0007] Fig. 2 illustrates a flow diagram of a method for determining injection mass deviation in a hydrogen gas injector (HGI), according to the present invention, and
[0008] Fig. 3 illustrates a graph illustrating a relation between the hydrogen rail pressure and injector energization, according to the present invention.

Detailed description of the embodiments:
[0009] Fig. 1 illustrates a block diagram of a device comprises of a controller 100 to determine injection mass/quantity deviation in a Hydrogen Gas Injector (HGI) 110, according to an embodiment of the present invention. The HGI 110 is shown to be part of a vehicle but not limited to the same. The vehicle comprises a hydrogen gas tank 102 integrated with a temperature sensor which stores the hydrogen gas at a high pressure. From the hydrogen gas tank 102, the hydrogen gas reaches to a hydrogen rail 106 via a hydrogen injector pressure regulator 104. The gas flow path between the hydrogen gas tank 102 and the hydrogen injector pressure regulator 104 comprises different filters and sensors for regulating the pressure of hydrogen gas, however these filters and sensors are not shown in the diagram as they are not relevant for the explanation of present invention and also are state of the art. The hydrogen injector pressure regulator 104 comprises of a pressure regulator, a pressure sensor which regulates the pressure of hydrogen gas. From the hydrogen injector pressure regulator 104, the hydrogen gas enters a hydrogen rail 106 integrated with a pressure sensor 114 and finally via hydrogen gas injector 110, it enters the combustion chamber 112 of an engine of the vehicle.

[0010] According to the embodiment of the present invention, the gas accumulated/stored in the hydrogen rail 106 is at high pressure as compared to the atmospheric pressure. The pressure at the hydrogen rail 106 is measured by the integrated pressure sensor 114. However, the pressure in the hydrogen rail 106 drops once the gas is injected into the combustion chamber 112 and the pressure drop is used as one of the parameters to calculate the hydrogen gas injected into the combustion chamber 112 using an offline trained machine learning model 108. The machine learning model 108 is trained on engine speed, rail pressure before hydrogen injection, drop in the rail pressure due to the injections, hydrogen rail 106 temperature, injector energizing duration, engine torque and mass flow through hydrogen injector pressure regulator 104 and the like. However, these parameters are independent to achieve certain vehicle speed based on the driver demand as the injector energization varies on that.

[0011] According to the embodiment of the present invention, data is collected from the engine or test bench to reproduce/present an injection scenario. The machine learning model 108 is trained offline using the collected data and ported in an Engine Control Unit (ECU) or in a cloud. In a real scenario, once a vehicle runs on a road, the trained machine learning model 108 reads the rail pressure across injections and engine speed, uses injector energizing duration, engine torque and mass flow through hydrogen injector pressure regulator 104 to estimate the actual fuel mass injected into the combustion chamber 112.

[0012] According to the embodiment of the present invention, the delta mass is determined by calculating the difference between the estimated hydrogen mass injected in the combustion chamber 112 from the machine learning model and a set point mass as per the operating condition of the engine. The determined delta mass of the hydrogen gas is compared with the predefined thresholds to decide the drift or deviation in the injection mass through the hydrogen gas injector 110. The delta mass is a drift or error used for further actions like corrective functions in the software or replacement of hydrogen gas injector 110 and the like.

[0013] According to the embodiment of the present invention, the delta mass value is compared with a threshold value and based on the comparison if the delta mass in a permissible range, the ECU corrects the HGI 110 tolerance. If the delta mass is beyond permissible range, then correction is not possible and the hydrogen gas injector 110 needs replacement. For e.g., in a scenario where the delta mass of the hydrogen gas is above the 80 percent of the threshold value permissible range, it is an indication to change the hydrogen gas injector 110. In another scenario, where the delta mass of the hydrogen gas is within a limit of 80 percent of the permissible threshold range, the hydrogen gas injector 110 can be corrected.

[0014] According to the embodiment of the present invention, either the HGI 110 needs replacement or correction is shared with the end user or service providers, so that it is easy to make decision quickly and further damages are avoided. The determined injection mass deviation of the HGI 110 is communicated over the cloud to update the status of the HGI 110. From the cloud, the updated information is used by OEM or end users, so that end users and OEM are in same understanding regarding the component status.

[0015] According to an embodiment of the present invention, the controller 100 is at least one chosen from a group of devices comprising a smartphone, a computer and, a cloud. The controller 100 is the one which comprises input interface, output interfaces having pins or ports, the memory element such as Random Access Memory (RAM) and/or Read Only Memory (ROM), Analog-to-Digital Converter (ADC) and a Digital-to-Analog Convertor (DAC), clocks, timers, counters and at least one processor (capable of implementing machine learning) connected with each other and to other components through communication bus channels. The memory element (not shown) is pre-stored with logics or instructions or programs or applications or modules/models and/or threshold values/ranges, reference values, predefined/predetermined criteria/conditions, lists, knowledge sources which is/are accessed by the at least one processor as per the defined routines. The internal components of the controller 100 are not explained for being state of the art, and the same must not be understood in a limiting manner. The controller 100 may also comprise communication units such as transceivers to communicate through wireless or wired means such as Global System for Mobile Communications (GSM), 3G, 4G, 5G, Wi-Fi, Bluetooth, Ethernet, serial networks, and the like. The controller 100 is implementable in the form of System-in-Package (SiP) or System-on-Chip (SOC) or any other known types. Examples of controller 100 comprises but not limited to, microcontroller, microprocessor, microcomputer, Electronic Control Units (ECUs), etc.

[0016] According to the present invention, the working of the controller 100 is envisaged. The controller 100 estimates a hydrogen mass (A) injected in the combustion chamber 112 using the trained machine learning mode 108. To calculate the hydrogen mass injected, the pressure drop in the hydrogen rail 106 is used by the controller 100. Using the hydrogen mass A injected, the controller 100 calculates the delta mass C as the difference between the estimated injected hydrogen mass A and a set point mass B as per the operating condition of the engine. Finally, deviation in the hydrogen mass injected D of HGI 110 is determined by comparing the delta mass C with the threshold value E. Once D is determined, it is communicated over the cloud to update the status of HGI 110 and based on the updated information, decision can be taken accordingly.

[0017] Fig. 2 illustrates a flow diagram of a method for determining injection mass deviation in a hydrogen gas injector (HGI), according to the present invention. The method comprises plurality of steps of which a step 202 comprises measuring, by the controller, the real time hydrogen pressure in the hydrogen rail 106 before injection and after injection which is fluidly connected to the hydrogen gas injector 110. A step 204 comprises calculating, by the controller, the pressure drop in the hydrogen rail 106 and by using the calculated pressure drop, estimating the hydrogen mass injected in the combustion chamber 112 using the trained machine learning model 108. A step 206 comprises determining, by the controller, delta mass using difference between the estimated hydrogen mass and the set point mass as per the operating conditions of the engine of the vehicle. A step 208 comprises determining, by the controller, injection mass deviation based on the comparison between the determined delta mass and the threshold value.

[0018] According to the method, the step 204 further comprises estimating injected hydrogen mass using a trained machine learning model 108, wherein the machine learning model 108 is trained using parameters comprising an engine speed, the fuel rail pressure before injection, the fuel rail pressure drops due to injection, the fuel rail temperature, the injector energizing, the engine torque, and the mass flow through hydrogen injector pressure regulator 104. Once the machine learning model 108 is trained, it is deployed in the ECU or the cloud. While the vehicle is running on road, the trained model read rail pressure across injections and engine speed, uses injector energizing duration, engine torque and mass flow through hydrogen injector pressure regulator 104 to calculate the actual hydrogen mass injected into the combustion chamber 112.

[0019] Fig. 3 illustrates a graph illustrating a relation between the hydrogen rail pressure and injector energization, according to the present invention. the figure 3 explains the rail pressure drop (P1 to P2) once the hydrogen gas is injected in the combustion chamber 112. Here, P1 and P2 are pressure measured before and after the energization of the hydrogen gas injector 110. Once the curve of hydrogen gas injector 110 energizing goes up (rises), the curve of the hydrogen rail 110 pressure goes down and there is a pressure difference (P1-P2). The pressure difference (P1-P2) gives the amount of hydrogen gas injected in the combustion chamber 112. However, the temperature dynamics affects this calculation and hence, the amount of the hydrogen gas injected is determined using the trained machine learning model 108 where it uses all the relevant parameters such as engine speed, injector energizing duration, engine torque and mass flow through hydrogen injector pressure regulator 104.

[0020] According to the present invention, the controller and method to determine injection mass deviation in a HGI 110 is disclosed. By determining the deviation of injected mass, rectification of the HGI is done. The determined deviation is communicated over the could update the status of HGI 110. From the cloud, the updated information is used by OEM or end users, so that end users and OEM are in same understanding regarding the component status. This information helps to take timely decision.

[0021] It should be understood that the embodiments explained in the description above are only illustrative and do not limit the scope of this invention. Many such embodiments and other modifications and changes in the embodiment explained in the description are envisaged. The scope of the invention is only limited by the scope of the claims.
, Claims:We claim:
1. A device to determine injection mass deviation in a Hydrogen Gas Injector (HGI) (110), said device comprises a controller (100), said controller (100) configured to:
a. Measure a real time hydrogen pressure in a hydrogen rail (106), said hydrogen rail (106) is fluidly connected to said HGI (110) and said hydrogen pressure is measured before injection and after injection into a combustion chamber (112) of an engine, characterized in that:
b. Calculate a pressure drop in said hydrogen rail (106), and by using said calculated pressure drop, estimate a hydrogen mass injected using a trained machine learning model (108);
c. Determine a delta mass by calculating a difference between said estimated hydrogen mass and a set point mass as per the operating condition of said engine, and
d. Determine an injection mass deviation of said HGI (110) by comparing said delta mass with a threshold value.

2. The device as claimed in claim 1, wherein said machine learning model (108) is trained using parameters comprising an engine speed, a fuel rail pressure before injection, a fuel rail pressure drops due to injections, a fuel rail temperature, an injector energizing duration, an engine torque, and a mass flow through Hydrogen injector pressure regulator (104).

3. The device as claimed in claim 1, wherein determined deviation is compared with the permissible range and based on that rectification of HGI (110) is done.

4. The device as claimed in claim 1, wherein the determined deviation of the HGI (110) is communicated over cloud to update the HGI (110) status.

5. The device as claimed in claim 1 is at least one chosen from a group of devices comprising a smartphone, a computer, an ECU, and a cloud.

6. A method for determining injection mass deviation in a Hydrogen Gas Injector (HGI) (110), said method comprising the steps of:
a. Measuring a real time hydrogen pressure in a hydrogen rail (106), said hydrogen rail (106) is fluidly connected to said HGI (110) and the hydrogen pressure is measured before injection and after injection into a combustion chamber (112) of an engine, characterized by:
b. Calculating a pressure drop in the hydrogen rail (106) and by using the calculated pressure drop estimate a hydrogen mass injected using a trained machine learning model (108);
c. Determining a delta mass by calculating a difference between the estimated hydrogen mass and a set point mass as per the operating condition of said engine, and
d. Determining said injection quantity deviation of said HGI (110) by comparing said delta mass and a threshold value.

7. The method as claimed in claim 6, wherein said machine learning model 108 is trained using parameters comprising an engine speed, a fuel rail pressure before injection, a fuel rail pressure drops due to injections, a fuel rail temperature, an injector energizing, an engine torque, and a mass flow through Hydrogen injector pressure regulator (104).

8. The method as claimed in claim 6 comprises correcting the operation of said HGI (110) when said determined injection mass deviation is within a permissible range.

9. The method as claimed in claim 6 comprises communicating the determined injection mass deviation of said HGI (110) to a cloud and updating a status of said HGI (110).

10. The method as claimed in claim 6 is performed by a controller (100), wherein said controller (100) is at least one chosen from a group of devices comprising a smartphone, a computer, an ECU, and a cloud.