A CPU substitutes a difference between a crank-side speed that is a rotation speed of a crankshaft and a downstream-side speed that is a speed of a portion, opposite from the crankshaft, in a damper into a differential speed. The CPU calculates a torsion speed component that is a speed component of the crankshaft due to torsion of the damper based on a physical model of which an input is the differential speed, and calculates a time that is a variable indicating a speed of the crankshaft, used to determine a misfire, based on the torsion speed component. The CPU delays acquisition time of the downstream-side speed used to calculate the differential speed, with respect to acquisition time of the crank-side speed according to the rotation speed of the crankshaft.

A misfire detection device for an internal combustion engine includes a storage device and processing circuitry. The storage device stores mapping data. The mapping data is data specifying a mapping that outputs a misfire variable using a rotation waveform variable as an input. The misfire variable is a variable related to a probability that a misfire has occurred in the internal combustion engine. The rotation waveform variable is a variable based on an instantaneous speed variable corresponding to each of discontinuous rotational angle intervals selected from multiple continuous rotational angle intervals.

Methods and systems are provided for detection of cylinder misfire in an engine. In one example, a system may comprise a first cylinder and second cylinder of the engine having exhaust flows combined together in an exhaust system before being combined with other cylinders of the engine. The first cylinder and second cylinder may share an exhaust gas sensor mounted in the exhaust in a position to sense exhaust from the first cylinder and second cylinder, and being positioned before exhaust from other cylinders is combined with sensed exhaust from the first cylinder and second cylinder. The system may further include a control system with instructions stored therein to indicate detected misfire in one or more of the first and second sensors based on an output from the exhaust gas sensor.

A determination device for an internal combustion engine executes a partial fuel cut-off process. The determination device determines that exhaust gas characteristics have deteriorated when the misfire rate of the internal combustion engine is greater than or equal to a determination threshold. The determination device sets the determination threshold to a first determination threshold when the calculated misfire rate is a misfire rate in a period of non-execution of the partial fuel cut-off process. Also, the determination device sets the determination threshold to a second determination threshold, which is less than the first determination threshold, when the calculated misfire rate is a misfire rate in a period of execution of the partial fuel cut-off process.

An internal combustion engine of a vehicle is equipped with a plurality of cylinders, and ignition devices provided for the cylinders respectively. The vehicle is mounted with an ECU. The ECU performs an ignition timing decision process for deciding a basic ignition timing of the ignition devices in accordance with a load of the internal combustion engine. The ECU performs a misfire determination process for determining that a misfire has occurred on a condition that the torque has decreased below a threshold set in advance. The ECU performs a retardation process for controlling an ignition timing toward a retardation side from the basic ignition timing when a state of the vehicle satisfies a condition determined in advance. A determination on the occurrence of a misfire based on a relationship in magnitude between the torque and the threshold is not made during the retardation process, in the misfire determination process.

The present disclosure relates to a method for detecting and distinguishing a cause of at least one combustion misfire of an internal combustion engine. The internal combustion engine has several cylinders, at least one exhaust gas tract, and an exhaust gas sensor which is arranged in the exhaust gas tract. The method includes the following steps: acquisition of a measurement signal with the exhaust gas sensor over a certain first period of time gas tract; subdivision of the measurement signal into measurement signal sections; assignment of the measurement signal sections to the corresponding cylinders, whereby cylinder-selective measurement signal profiles are produced that are characteristic of the respective oxygen content downstream of the respective cylinders over the determined first period of time of time; and evaluation of the cylinder-selective measurement signal profiles to detect at least one combustion misfire of the internal combustion engine.

A method for the diagnosis of engine misfires in an internal combustion engine having at least one cylinder, and includes the steps of: Determining exhaust back pressure values of the individual cylinders over at least two working cycles, correlating the exhaust back pressure values with the camshaft position and/or the working cycle, determining the exhaust back pressure maxima and/or exhaust back pressure minima per working cycle, comparing the exhaust back pressure maxima and/or exhaust back pressure minima between the individual cylinders—in the case of multiple cylinders—and/or to maximum and/or minimum values from previous working cycles and determining the deviations, comparing the deviations to a predetermined threshold value. The invention also relates to a control device for carrying out the method and a motor vehicle including such a control device.

A two-stroke combustion engine comprising a user-operated throttle control, an adjustable valve arranged to control one or more air intakes of the combustion engine, and a control unit arranged to control a state of the adjustable valve, wherein the combustion engine is arranged to operate in a first idle mode at an idle engine speed below a clutch engagement engine speed when the user-operated throttle control is not engaged, wherein the combustion engine is arranged to operate in a second idle mode at a target engine speed above the clutch engagement engine speed when the user-operated throttle control is engaged and when the engine is not subject to an external load, the control unit being arranged to control the state of the adjustable valve to maintain engine speed at the target engine speed when the engine operates in the second idle mode.

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.

A CPU calculates probability models by inputting input variables to a neural network. Next, the CPU determines whether a maximum value among the calculated probability models is larger than an upper limit value of a permissible range. When the maximum value is larger than the upper limit value of the permissible range, the CPU calculates a difference between the maximum value and a first reference value within the permissible range, and subtracts the difference from all the probability models. Then, the CPU calculates a probability of misfire in each cylinder by inputting each of the calculated probability models to a softmax function of mapping.