Abstract: An exhaust aftertreatment system including a selective catalytic reduction device (SCR), a NOx sensor and a reductant injection system is described. A method for controlling the reductant injection system to inject reductant into the exhaust gas feedstream upstream relative to the SCR includes monitoring engine operation, and determining an initial reductant dosing rate responsive to the engine operation. A dosing perturbation is induced in the reductant dosing rate. The exhaust gas feedstream is monitored via the NOx sensor, and a reductant dosing correction term is determined based upon the monitoring. A final dosing rate for controlling the reductant injection system is determined based upon the initial reductant dosing rate, the dosing perturbation, and the reductant dosing correction term.

Abstract: An exhaust aftertreatment system including a selective catalytic reduction device (SCR), a NOx sensor and a reductant injection system is described. A method for controlling the reductant injection system to inject reductant into the exhaust gas feedstream upstream relative to the SCR includes monitoring engine operation, and determining an initial reductant dosing rate responsive to the engine operation. A dosing perturbation is induced in the reductant dosing rate. The exhaust gas feedstream is monitored via the NOx sensor, and a reductant dosing correction term is determined based upon the monitoring.

Abstract: A system according to the principles of the present disclosure includes an engine air sensor, an engine air prediction module, and an engine actuator module. The engine air sensor measures an engine air parameter at a first rate. The engine air parameter includes at least one of a mass flow rate of air flowing into an intake manifold of an engine, a pressure within the intake manifold, and a mass of air within a cylinder of the engine. The engine air prediction module predicts the engine air parameter at a second rate that is greater than the first rate. The engine actuator module controls an actuator of the engine based on at least one of the measured engine air parameter and the predicted engine air parameter.

Abstract: A method of estimating soot loading in a diesel particulate filter (DPF) in a vehicle exhaust system includes estimating an engine-out soot rate using a first neural network that has a first set of vehicle operating conditions as inputs. The method further includes estimating DPF soot loading using a second neural network that has the estimated engine-out soot rate from the first neural network and a second set of vehicle operating conditions as inputs. Estimating the engine-out soot rate and estimating the DPF soot loading are performed by an electronic controller that executes the first and the second neural networks. The method also provides for training the first and second neural networks both offline (for initial settings of the neural networks in the vehicle), and online (when the vehicle is being used by a vehicle operator). An exhaust system has a controller that implements the method.

Abstract: A system according to the principles of the present disclosure includes an engine air sensor, an engine air prediction module, and an engine actuator module. The engine air sensor measures an engine air parameter at a first rate. The engine air parameter includes at least one of a mass flow rate of air flowing into an intake manifold of an engine, a pressure within the intake manifold, and a mass of air within a cylinder of the engine. The engine air prediction module predicts the engine air parameter at a second rate that is greater than the first rate. The engine actuator module controls an actuator of the engine based on at least one of the measured engine air parameter and the predicted engine air parameter.

Abstract: A method of estimating soot loading in a diesel particulate filter (DPF) in a vehicle exhaust system includes determining engine operating conditions of an engine in exhaust flow communication with the diesel particulate filter, and monitoring a pressure differential of the exhaust flow across the diesel particulate filter. The method includes estimating soot loading in the diesel particulate filter according to a pressure-based model using the monitored pressure differential when the engine operating conditions are within a predetermined first set of engine operating conditions, and estimating soot loading in the diesel particulate filter according to an engine-out soot model and a DPF soot loading model when the engine operating conditions are within a predetermined second set of operating conditions. The method includes updating the engine-out soot model based in part on a difference in estimated soot loading between the pressure-based model and the DPF soot loading model.

Abstract: A method of estimating soot loading in a diesel particulate filter (DPF) in a vehicle exhaust system includes estimating an engine-out soot rate using a first neural network that has a first set of vehicle operating conditions as inputs. The method further includes estimating DPF soot loading using a second neural network that has the estimated engine-out soot rate from the first neural network and a second set of vehicle operating conditions as inputs. Estimating the engine-out soot rate and estimating the DPF soot loading are performed by an electronic controller that executes the first and the second neural networks. The method also provides for training the first and second neural networks both offline (for initial settings of the neural networks in the vehicle), and online (when the vehicle is being used by a vehicle operator). An exhaust system has a controller that implements the method.