Methods and systems for real-time dosing of additives into a fuel supply unit. A method disclosed herein includes capturing at least one real-time operating condition of the equipment. The method further includes determining dosage of the at least one additive to be dosed into the fuel supply unit of the equipment, based on the captured at least one operating condition of the equipment. The method further includes enabling an additive dispensing device to dose the determined dosage of the at least one additive into the fuel supply unit of the equipment.

A control device of an internal combustion engine includes a parameter acquisition unit that acquires a plurality of input parameters, a calculation unit that calculates at least one output parameter using a neural network model, and a controller that controls the internal combustion engine. The neural network model includes a plurality of neural network units and an output layer. Each of the neural network units includes one input layer and at least one intermediate layer. The neural network model inputs different combinations of input parameters selected from the input parameters to each of the input layers of the neural network units such that a total number of input parameters to be input to the neural network units is larger than the number of the input parameters.

A control system includes a controller. The controller counts the number of driving times of a high pressure fuel pump, which is the number of reciprocating motions of a plunger based on a crank counter. The controller estimates a high pressure system fuel pressure based on the calculated number of driving times, a fuel temperature detected by a fuel temperature sensor, and a low pressure system fuel pressure detected by a low pressure system fuel pressure sensor when the high pressure system fuel pressure is not able to be acquired from a high pressure system fuel pressure sensor. The controller sets an opening period of an in-cylinder fuel injection valve based on the estimated high pressure system fuel pressure and to perform an engine start by an in-cylinder fuel injection when the high pressure system fuel pressure is not able to be acquired from the high pressure system fuel pressure sensor.

An engine controlling method is provided, which includes, during motoring of the engine, outputting, by an in-cylinder pressure sensor, to a controller a signal indicative of a reference pressure corresponding to a pressure change after an intake valve of a cylinder of the engine is closed when not performing fuel injection, and then injecting, by an injector, fuel for analysis into the cylinder at a specific timing after the intake valve is closed. The method includes, by the controller, acquiring a crank angle period from the intake valve close timing, through the fuel injection, to a timing of the in-cylinder pressure reaching the reference pressure based on signals from the in-cylinder pressure sensor and a crank angle sensor, and determining a property of the injected fuel by comparing the acquired crank angle period with that of a standard fuel based on stored information on a property of the standard fuel.

Provided is an internal combustion engine control device capable of reducing a control error of the ignition timing as compared with the conventional technique. The internal combustion engine control device of the present disclosure includes a neural network model that receives three or more variables including at least a rotation speed, a load, and another specific variable of an internal combustion engine as inputs and outputs a control amount of the internal combustion engine. The neural network model includes a first neural network model having a reference value of the specific variable as an input and a second neural network model having a current value of the specific variable as an input. The internal combustion engine control device of the present disclosure corrects a reference value of the control amount calculated based on the rotation speed and the load using a difference or a ratio between the output of the first neural network model and the output of the second neural network model as a correction amount.

An engine model construction method includes generating test patterns in which a plurality of manipulated variables used for an engine test are changed with time, correcting the test patterns based on first coverage of a first space of manipulated variables are allowed to take and second coverage of a second space of change rate values of the manipulated variables are allowed to take, acquiring pieces of time series data of operation amounts of the manipulated variables and controlled amounts with respect to the manipulated variables by performing an engine test using the corrected test patterns, and constructing a first engine model by performing machine learning on training data in which the corrected test patterns are adopted as input and the pieces of time series data are adopted as correct answers, by a processor.

Systems, devices and methods for diagnosing malfunctioning in a crankcase ventilation (CCV) system are provided. A controller includes a processor and a memory storing instructions that cause the processor to: receive a plurality of pressure values including (i) a first pressure value indicative of a pressure of fluid flowing from a crankcase to a breather assembly of a system, (ii) a second pressure value indicative of a pressure of fluid flowing through a first tube coupled to the breather assembly, and (iii) a third pressure value indicative of a pressure of fluid flowing through a second tube coupled to the breather assembly; determine a pair of pressure differences based on the first pressure value, the second pressure value, and the third pressure value; and detect a malfunctioning in the CCV system based on the pair of pressure differences.

A method of generating an ROI profile for a fuel injector using machine learning and a constrained/limited training data set is disclosed. The method includes receiving a first plurality of measurement sets for a fuel injector when operating at a first target set point. Preferably, at least two measurement sets of the first plurality of measurement sets are selected to generate a first averaged ROI profile for the first target condition. The at least two selected measurement sets are then used to train a machine learning model that can output a predicted ROI profile for a fuel injector based on a desired pressure value and/or desired mass flow rate value. Training of the machine learning model preferably includes a predetermined number of iterations that induces overfitting within the model/neural network.

An abnormality diagnosis system is applied to a fuel supply system including a fuel pump that pumps fuel from a fuel tank and a fuel pipe in which fuel discharged from the fuel pump flows. The abnormality diagnosis system stores a minimum fuel pressure in the fuel pipe in one trip after a main switch of the fuel supply system is turned on and until the main switch is turned off and data indicating a state when the minimum fuel pressure was recorded as diagnosis data in a storage device. In the abnormality diagnosis system, an execution device determines a failure spot associated with a decrease in fuel pressure in the fuel pipe using the diagnosis data stored in the storage device and diagnoses an abnormality of the fuel supply system.

Systems, devices and methods for diagnosing malfunctioning in a crankcase ventilation (CCV) system can include a controller receiving a plurality of pressure values. The plurality of pressure values include a first pressure value indicative of pressure of gases flowing between a crankcase and a breather assembly, a second pressure value indicative of pressure of gases flowing through a CCV tube from the breather assembly, and a third pressure value representing pressure of gases in a tube connected to the CCV tube. The controller can calculate a pair of pressure differences including a first pressure difference between the first pressure value and the second pressure value and a second pressure difference between the first pressure value and the third pressure value. The controller can detect a malfunctioning or defect in the CCV system based on the pair of pressure differences falling within a predefined clustering region.