Tula Technology, Inc.

Cummins Inc.

Elliott A Ortiz-Soto

Shikui Kevin Chen

Matthew Aaron Younkins

Louis Joseph Serrano

Li-Chun Chien

Aditya Mandal

Vijay Srinivasan

Shahaboddin Owlia

Yongyan Cao

Engine controllers and control schemes are provided for managing engine state transitions requiring increased compressor pressure ratios in turbocharged engines. In some circumstances, turbo lag can be mitigated by initially transitioning the engine to an intermediate engine state that directly or indirectly increases airflow through the engine and turbocharger relative to what would be possible if the engine were immediately commanded to operate at the target engine state. After reaching a point where the desired torque is actually generated at the intermediate engine state, the operational settings are gradually reduced to the target effective firing density while increasing the operational compressor pressure ratio to the target compressor ratio.

Fast torque response for boosted engines

A system and method for controlling an internal combustion engine involving (1) cylinder trapping strategies where one of several pneumatic spring types are dynamically selected for cylinders based at least partially on a predicted number of upcoming skips for each of the cylinders respectively and/or (2) staggering various valvetrain dependent operational engine strategies as operating conditions permit as the internal combustion engine warms up following a cold start.

Cylinder charge trapping strategies based on predictive number of skips and staggered implementation of valvetrain dependent operational strategies for internal combustion engines

Using machine learning for cylinder misfire detection in a dynamic firing level modulation controlled internal combustion engine is described. In a classification embodiment, cylinder misfires are differentiated from intentional skips based on a measured exhaust manifold pressure. In a regressive model embodiment, the measured exhaust manifold pressure is compared to a predicted exhaust manifold pressure generated by neural network in response to one or more inputs indicative of the operation of the vehicle. Based on the comparison, a prediction is made if a misfire has occurred or not. In yet other alternative embodiment, angular crank acceleration is used as well for misfire detection.

Machine learning for misfire detection in a dynamic firing level modulation controlled engine of a vehicle

Engine controllers and control schemes are provided for managing engine state transitions requiring increased compressor pressure ratios in turbocharged engines operating in a cylinder output level modulation mode (e.g., skip fire, multi-level skip fire, or firing level modulation modes). In some circumstances, turbo lag can be mitigated by initially transitioning the engine to an intermediate effective firing density that is higher than both the initial and target effective firing density to increase the flow of gases through the engine and the turbocharger while maintaining a compressor ratio the same as or close to the initial compressor pressure ratio. After reaching a point where the desired torque is actually generated at the intermediate effective firing density, the operational effective firing density is gradually reduced to the target effective firing density while increasing the operational compressor pressure ratio to the target compressor ratio.

A variety of engine controllers and methods are described for controlling engines operating in a cylinder output level modulation mode. In one aspect transitions between different effective firing fractions are managed by gradually ramping an effective firing density. In another, when an engine transitions to a multi-level skip fire firing density that has more than one possible high/low/skip sequence, the phase of the high/low pattern is set relative to the phase of the firing pattern to ensure that a preferred high/low/skip sequence is generated. In another aspect, rapid large torque changes can be implemented in part by immediately changing the operational high/low fraction in response to a command to increase or reduce the desired engine torque.

Engine cylinder output level modulation

Methods, devices, controllers, and algorithms are described for operating an internal combustion engine wherein at least some firing opportunities utilize low temperature gasoline combustion (LTGC). Other firing opportunities may be skipped or utilize some other type of combustion, such as spark ignition. The nature of any particular firing opportunity is dynamically determined during engine operation, often on a firing opportunity by firing opportunity basis. Firings that utilize LTGC produce little, if any, nitrous oxides in the exhaust stream and thus, in some implementations, may require no aftertreatment system to remove them from the exhaust stream.

Dynamic charge compression ignition engine with multiple aftertreatment systems

Using machine learning for misfire detection in a Dynamic firing level modulation controlled internal combustion engine is described. A neural network is used to calculate expected crank acceleration from various inputs, including the dynamically defined cylinder skip fire sequence. The output of the neural network is then compared to a signal indicative of the measured crank acceleration. Based the comparison, a prediction is made if a misfire has occurred or not. In alternative embodiment, the neural network is expanded to include the measured crank acceleration as an additional input. With the latter embodiment, the neural network is arranged to directly predict misfire events.

Growing community of inventors

San Jose, CA, United States of America

Elliott A Ortiz-Soto