Garrett Transportation I Inc.

Honeywell International Inc.

Honeywell Spol, S.r.o.

Daniel Pachner

Jaroslav Pekar

Vladimir Havlena

Michael Robert Uchanski

Gregory Edward Stewart

Ondrej Santin

Lubomir Baramov

Dejan Kihas

Gregory Stewart

Radek Beno

Adrian Matias Fuxman

Pavel Trnka

Greg Stewart

David Joachim Germann

Yuejiang Liu

Ondrej Basus

Pavel Otta

François-Xavier Brulhart

Lukas Lansky

Lucas Lansky

David Germann

During each of a plurality of iterations, a policy of a controller is updated and at least part of a process is controlled using the updated policy. The updated policy is associated with a performance level of the controller. For each iteration, the updated policy is determined using the associations generated during one or more previous iterations between the policies and the corresponding performance levels of the controller in controlling the at least part of the process, such that the updated policy is optimized to have a highest likelihood of producing a positive change in the performance level of the controller in controlling the at least part of the process rather than optimized to have a highest likelihood of producing a largest positive magnitude of change in the performance level of the controller in controlling the at least part of the process relative to the previous iteration.

Method and apparatus for tuning a regulatory controller

An approach for auto tuning a PID controller that may incorporate determining set-points for controlled variables, obtaining controlled variables from a controlled process module, taking a difference between the set-points and the controlled variable as inputs to a proportional, integral and derivative (PID) controller, calculating a loss or reward from the difference between the controlled variables and the set-points, and achieving set-point tracking. The loss or reward needs to be an increasing or decreasing function of a control error value. Also incorporated may be adding loss or reward components based on controlled variables time difference or control action time difference, which may effect a self-tuned performance of the PID controller.

PID controller autotuner using machine learning approaches

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.

Approach for aftertreatment system modeling and model identification

An engine and one or more aftertreatment subsystems integrated into one system for optimization and control. At least one controller may be connected to the engine and the one or more aftertreatment subsystems. The controller may contain and execute a program for the optimization and control of the one system. Controller may receive information pertinent to the engine and the one or more aftertreatment subsystems for the program. The controller may prescribe setpoints and constraints for measured variables and positions of actuators according to the program to aid in effecting the optimization and control of the one system.

Integrated optimization and control of an engine and aftertreatment system

An engine system incorporating an engine, one or more sensors, and a controller. The controller may be connected to the one or more sensors and the engine. The one or more sensors may be configured to sense one or more parameters related to operation of the engine. The controller may incorporate an air-path state estimator configured to estimate one or more air-path state parameters in the engine based on values of one or more parameters sensed by the sensors. The controller may have an on-line and an off-line portion, where the on-line portion may incorporate the air-path state estimator and the off-line portion may configure and/or calibrate a model for the air-path state estimator.

Engine system with inferential sensor

Systems and methods for pre-distortion pattern recognition are provided. In certain embodiments, the system includes an electronic device that provides an output signal, wherein the electronic device applies distortion to the output signal. The system also includes a pre-distorter that provides an input signal to the electronic device, wherein the pre-distorter applies a pre-distortion to the input signal before the electronic device receives the input signal. Further, the system includes a pre-distorter design block that identifies the distortion from an association between the output signal and a finite set of symbols and updates the pre-distortion based on the association.

Pre-distortion pattern recognition

A system and an approach for determining various flows in an internal combustion engine, such as an amount of recirculation exhaust gas flow through a controlled valve and a fresh air mass flow to an intake of an engine. Also, among the sensors accommodated in the system, is an inexpensive but slow-responding lambda sensor in the exhaust stream.

Inferential flow sensor

An engine system incorporating an intake manifold, a compressor, and a controller. The compressor may provide air to the intake manifold and the controller may be connected to the intake manifold and the compressor. The controller may receive a control signal and control air flow from the compressor to the intake manifold based on the received control signal. The controller may control the air flow from the compressor to the intake manifold based on a first equation when a value related to the control signal is on a first side of a threshold and according to a second equation when the value is on a second side of the threshold. The controller may control the air flow between the compressor and intake manifold according to the second equation to prevent the compressor from operating at a surge condition when controlling the air flow according to the first equation.

Compressor override control

The speed of a turbocharger may be estimated using data from sensors that are readily available in most engine management systems. In some cases, a pressure measurement from a MAP sensor may be used, in combination with one or more computational models, to provide an efficient, lower cost estimate of turbo speed that can be used to control operation of the engine and/or the turbocharger.

System and method for estimating turbo speed of an engine

A system for reducing environmentally harmful emissions from an internal combustion engine. The system may incorporate an exhaust after-treatment device. The exhaust after-treatment device may use selective catalytic reduction to remove certain emissions from the exhaust of the engine. Urea solution may be inserted into the exhaust emissions, which is decomposed to ammonia to become a reduction agent for reduction of NOx in the emissions. The engine may be managed by a controller and the exhaust after-treatment device may be managed by another controller. These controllers may be cascaded, or be managed by a third controller that provides hierarchical or coordinated control of engine performance and emissions reduction. The engine and the exhaust after-treatment device may be modeled to aid in designing and building a system for coordinated control of an actual engine and a selective catalytic reduction after-treatment device. The controllers may be predictive model controllers.

Coordinated engine and emissions control system

A system and an approach for determining various pressures or flows in an internal combustion engine, such as a pressure adjacent a recirculation exhaust gas flow through a controlled valve of an engine. Also, among the sensors accommodated in the system, is a pressure sensor sensing a pressure in an intake manifold of the engine.

Growing community of inventors

Prague, Czechia

Daniel Pachner