An exhaust purification system of an internal combustion engine includes a catalyst arranged in an exhaust passage of the internal combustion engine, a fuel supply device supplying fuel to the catalyst through the exhaust passage, and a control device configured to control the supply of fuel by the fuel supply device. The control device is configured to calculate a concentration in exhaust gas of fuel supplied to the exhaust passage by the fuel supply device and a saturation vapor pressure concentration of the fuel and supply fuel from the fuel supply device to the catalyst only when the concentration in the exhaust gas is higher than the saturation vapor pressure concentration.

A hydrocarbon injector deflector for a diesel exhaust system includes a base plate having a first end linearly extending to a second end to define a first side and a second side. The base plate is arcuately formed such that the first side extends arcuately to the second side. The first end is disposed upstream of the exhaust system relative to the second end. The hydrocarbon deflector further includes a frame connected to the second end of the base plate and extends therefrom at a first angle. The frame has an opening formed through the frame. The opening defines an outer wall having an inner side of the frame. The deflector further includes a tab extending from the inner side at a second angle.

In a method for avoiding a runaway condition of an internal combustion engine that includes a cylinder, an operational characteristic of the engine, presumed to be caused by an unrequested introduction of hydrocarbon into the cylinder, is detected and the engine is derated in dependence of the detection, and, while the engine is derated, a test procedure is performed to detect an unrequested introduction of hydrocarbon into the cylinder.

A machine learning system using a neural network to output an output value corresponding to values of operating parameters of the machine. When the value of an operating parameter of a machine is outside a preset range, the number of nodes of the hidden layer one layer before the output layer of the neural network is increased and training data obtained by actual measurement for a newly acquired value of an operating parameter of the machine is used to learn the weights of the neural network so that the difference between the output value changing in accordance with the values of the operating parameters of the machine and training data corresponding to the values of the operating parameters of the machine becomes smaller.

A system and approach for catalyst model parameter identification with modeling accomplished by an identification procedure that may incorporate a catalyst parameter identification procedure which may include determination of parameters for a catalyst device, specification of values for parameters and component level identification. Component level identification may be of a thermal model, adsorption and desorption, and chemistry. There may then be system level identification to get a final estimate of catalyst parameters.

Systems and methods of preventing thermal spikes at a catalyst in an exhaust system of an engine of a vehicle include detecting whether one of a fuel enrichment event and a fuel cutoff event has been initiated and in response, temporarily disabling the other of the fuel enrichment event and the fuel cutoff event from occurring to prevent an exhaust gas temperature thermal spike that could damage the catalyst, while the other of the fuel enrichment event and the fuel cutoff event is disabled, performing stoichiometric closed-loop fuel control using the one or more oxygen sensors to drive the exhaust gas fuel/air ratio to stoichiometry and an oxygen storage capacity of the catalyst to a balanced state, and when measurements from the one or more oxygen sensors indicate at least one lean-to-rich transition and one rich-to-lean transition in the exhaust gas oxygen level has occurred, re-enabling the other event.

A fuel content detection system is disclosed. The fuel content detection system may include an engine control module (ECM) to receive a measurement of a parameter. The parameter may correlate with an amount of a substance in a fuel that is being consumed in an engine. The ECM may determine an estimation of the parameter based on a model. The model may use a predetermined value associated with the amount of the substance, and the engine may be configured to consume a designated type of fuel that includes an amount of the substance that corresponds to the predetermined value. The ECM may determine, based on the estimation and the measurement not being within a threshold range, that the fuel is not the designated type of fuel and perform an action associated with the engine.

A vehicle includes an engine, a fueling system, an exhaust assembly, and a controller. The fueling system controls fuel to the engine. The exhaust assembly releases combustion gas from the engine and includes at least one sensor and a catalytic converter. The controller is configured to control the engine, the fueling system and the exhaust assembly. The controller evaluates engine state and an output from the at least one sensor and commands a fueling strategy to control an oxygen storage capacity of the catalytic converter based on the engine state and output from the at least one sensor.

Methods and systems for providing exhaust gas recirculation to a two stroke opposed piston diesel engine are described. In one example, high and low pressure exhaust gas recirculation systems may be activated or deactivated in response to exhaust gas hydrocarbon concentration and particulate matter flow rate from the engine. In addition, operation of the low and high pressure exhaust gas recirculation systems may be responsive to an operating state of a supercharger compressor.

A system and approach for catalyst model parameter identification with modeling accomplished by an identification procedure that may incorporate a catalyst parameter identification procedure which may include determination of parameters for a catalyst device, specification of values for parameters and component level identification. Component level identification may be of a thermal model, adsorption and desorption, and chemistry. There may then be system level identification to get a final estimate of catalyst parameters.