Systems, apparatuses and methods for systematically executing a diagnosis and fault isolation of a failure condition for an engine during a cranking test of the engine. Examples of the failure condition include, but are not limited to, cylinder-by-cylinder compression conditions, excessive blow-by conditions, valve failures, leaks, and/or obstructions of the intake, exhausts, crankcase ventilation, and/or exhaust gas recirculation systems.

Methods and systems are provided for an EGR system reverse hose diagnostic. In one example, a method includes executing the reverse hose diagnostic in response to an EGR flowrate exceeding a threshold flow rate.

A method for calculating the mass of an overlap gaseous flow (M.sub.OVL), wherein the exhaust pressure is higher than the intake pressure, or in the case of scavenging (SCAV), wherein the intake pressure is higher than the exhaust pressure. The overlap gaseous flow (M.sub.OVL) is the flow which flows, in overlap conditions, through the intake valve and the exhaust valve of a cylinder of an internal combustion engine. At least one intake valve is driven so as to vary the lift (H) of the intake valve in controlled manner. The overlap condition is a condition in which the intake valve and the exhaust valve are both at least partially open. The method comprises calculating the mass of the gaseous flow (M.sub.OVL) which flows through the intake valve and the exhaust valve on the basis of the relation:

M.sub.OVL=PERM*β(P/P.sub.0,n)*P.sub.0/P.sub.0_REF*(T.sub.0_REF/T.sub.0).sup.1/2/n.

Methods and systems are provided for an EGR system reverse hose diagnostic. In one example, a method includes executing the reverse hose diagnostic in response to an EGR flowrate exceeding a threshold flow rate.

Methods and systems for fault identification and mitigation in an engine system. A state observer obtains current state information from the engine system, and a feature calculator uses data obtained from the state observer to calculate one or more feature indicators, which are monitored by a health estimator for the occurrence of a change using one or more change probability models. When the health estimator identifies a change, a fault isolator determines a component of the engine system that is subject to fault or health deterioration.

A control device includes a controller configured to: obtain a driving condition and an actual value of a controlled amount of an engine; use a transformed engine model to calculate an estimate value of a future controlled amount, from the obtained driving condition and a candidate value of an operation amount for controlling the controlled amount, the transformed engine model in which an activation function of each neuron is transformed using a linear inequality function having a binary variable, the transformed engine model for which a weight coefficient, bias, and upper and lower limits of an input/output variable of the each neuron are set based on an engine model that has a multilayer neural structure and the activation function of a ReLU structure, receives the driving condition and operation amount as input, and predicts dynamic characteristics of the engine; determine a value of the operation amount, based on error between the calculated estimate value and a target value of the controlled amount identified from the driving condition.

A control device includes a controller configured to: obtain a driving condition and an actual value of a controlled amount of an engine; use a transformed engine model to calculate an estimate value of a future controlled amount, from the obtained driving condition and a candidate value of an operation amount for controlling the controlled amount, the transformed engine model in which an activation function of each neuron is transformed using a linear inequality function having a binary variable, the transformed engine model for which a weight coefficient, bias, and upper and lower limits of an input/output variable of the each neuron are set based on an engine model that has a multilayer neural structure and the activation function of a ReLU structure, receives the driving condition and operation amount as input, and predicts dynamic characteristics of the engine; determine a value of the operation amount, based on error between the calculated estimate value and a target value of the controlled amount identified from the driving condition.

A method to determine the mass of air trapped in each cylinder of an internal combustion engine, which comprises determining, based on a model using measured and/or estimated physical quantities, a value for a first group of reference quantities; determining, based on the model, the actual inner volume of each cylinder as a function of the speed of rotation of the internal combustion engine and of the closing delay angle of the intake valve; and calculating the mass of air trapped in each cylinder as a function of the first group of reference quantities and of the actual inner volume of each cylinder.

A control unit configured to control an electric turbocharger and an EGR valve. While an internal combustion engine is stopped, an oxygen-free period, which is a period during which oxygen surrounding an exhaust gas purifier used for an oxidation reaction runs out, is estimated based on a temperature of the exhaust gas purifier. Before entering the oxygen-free period, the EGR valve is opened and the electric turbocharger is driven. Air surrounding the exhaust gas purifier is replaced with fresh air. After replacement with the fresh air has been completed, the electric turbocharger is stopped.

New and/or alternative approaches to determine mass flow using a flow measurement device in a pulsatile flow context. The flow measurement device is configured to generate a delta-pressure measurement. A semi-physical valve model is generated for the flow measurement device, and the delta-pressure measurement is then is isolated using the model. A discharge coefficient map is determined for the flow measurement device by testing using sets of operating parameters for a system. The operating parameters of the system are then used to determine the discharge coefficient for use in estimating mass flow with the semi-physical valve model. The resultant estimated mass flow can be used to control the system, and a Factor of Effective Area estimate generated using the valve model can be used to determine the status of the flow measurement device and identify or predict a need for maintenance.