Abstract: A method for operating an industrial automation system may include receiving, via a first module of a plurality of modules in a control system, a plurality of datasets via at least a portion of the plurality of modules. The plurality datasets may include raw values without context regarding the plurality datasets. The method may then include identifying a subset of the plurality of datasets that influences a value of a target variable by analyzing the data without regard to the context, modeling a behavior of the target variable over time based on the subset of the plurality of datasets, and adjusting one or more operations of an automation device based on the model.

Abstract: The present disclosure provides a method and system for training an unmanned aerial vehicle control model based on artificial intelligence. The method comprises: obtaining training data by using sensor data and target state information of the unmanned aerial vehicle and state information of the unmanned aerial vehicle under action of control information output by a deep neural network; training the deep neural network with the training data to obtain an unmanned aerial vehicle control model, the unmanned aerial vehicle control model being used to obtain the control information of the unmanned aerial vehicle according to the senor data and target state information of the unmanned aerial vehicle.

Abstract: A Wiebe function parameter identification method, the method includes: acquiring, by a computer, operation data when an internal-combustion engine is in operation; and identifying values of a plurality of parameters included in a combination of at least two Wiebe functions including a first Wiebe function and a second Wiebe function based on the operation data and a first difference between values of a same parameter of the first Wiebe function and the second Wiebe function.

Abstract: A control device of an internal combustion engine includes: a parameter value acquiring part acquiring values of input parameters; a computing part utilizing a model using a neural network to calculate a value of an output parameter, and a control part controlling operation of the engine. The model outputs the value of the output parameter from an output layer node if the values of the input parameters are input to the input layer nodes. When an abnormality occurs at values of part of the input parameters among the input parameters, the computing part uses the corrected model to calculate the value of the output parameter, the corrected model being provided by correcting the model so that a value changing in accordance with a value of an abnormal input parameter is not input from a input layer node corresponding to the abnormal input parameter to a hidden layer node.

Abstract: Embodiments for predicting large data flushes in a data replication system collecting usage data for assets in the system; analyzing the data using machine learning processes on the basis of each asset and the system as a whole to determine usage trends with respect to the data flush operations; predicting a next large data flush using a time-series model; obtaining a capacity of a journal storage space used for write operations to a storage device in the system; and determining if a size of the predicted next flush size is too large relative to this capacity, and if so, invoking a fast forward mode to not retain I/O history information for undo operations during a replication in order to save resources in the system.

Abstract: Provided is a control device of a hybrid vehicle powered by an internal-combustion engine and a motor, wherein a catalyst that purifies exhaust gas is located in an exhaust passage of the internal-combustion engine, and the control device comprises: a learning unit configured to, during operation of the internal-combustion engine, learn a parameter for controlling a rotation speed of the internal-combustion engine so that a rotation speed of the internal-combustion engine during idling operation is equal to a target rotation speed; and a controller configured to stop the internal-combustion engine when a state where a correction amount of the parameter to cause the rotation speed during idling operation to be equal to the target rotation speed is equal to or greater than a predetermined value continues for equal to or greater than a predetermined time period, the correction amount being obtained by learning by the learning unit.

Abstract: Methods and apparatus are provided for controlling an autonomous vehicle. A sensor fusion system with a sensor system for providing environment condition information and a convolutional neural network (CNN) is provided. The CNN includes a receiving interface configured to receive the environment condition information from the sensor system, a common convolutional layer configured to extract traffic information from the received environment condition information, and a plurality of fully connected layers configured to detect objects belonging to different object classes based on the extracted traffic information, wherein the object classes include at least one of a road feature class, a static object class, and a dynamic object class.

Abstract: A system and method is provided for determining a position of an end of a traffic jam using traffic measurement data received from a plurality of vehicle and at least one sigmoid function. A system server configured to execute the method includes a computer unit, a memory, a receiving unit for receiving a plurality of measured data, each having one position data indication of a vehicle.

Abstract: Methods and systems for operating an engine that includes a low pressure EGR passage and a selective reduction catalyst are disclosed. In one example, an actuator is adjusted in response to a NOx mass flow rate in the low pressure EGR passage.

Abstract: An internal combustion engine includes an air charging system. A method to control the air charging system includes providing a desired operating target command for the air charging system, and monitoring operating parameters of the air charging system. An error between the desired operating target command for the air charging system and the corresponding one of said operating parameters of the air charging system is determined, and scheduled PID gains are determined based on the error utilizing a PID controller. An adaptive algorithm is applied to modify the scheduled PID gains, and a system control command for the air charging system is determined based upon the modified scheduled PID gains. The air charging system is controlled based upon the system control command for the air charging system.

Abstract: A method includes determining a stored injection relationship that includes a number of fuel performance parameters. In one form the fuel performance parameters are related to a particular shape, and may be related to a particular operating condition. The method includes determining a fuel performance outcome during a fuel injection event, and updating the stored injection relationship in response to the fuel performance outcome. The fuel performance outcome can be an injected fuel quantity.

Abstract: Methods and systems for use in indicating and/or determining fuel properties. One or more physical properties of a fuel are determined and indicated using taggants that are added to the fuel, such as by encoding the properties in the taggants or by encoding an identifier in the taggants and associating the properties with the identifier. The taggants are detected by a taggant sensor, and the physical properties are determined based on the detected taggants. A concentration of the taggants in the fuel may also be determined.

Abstract: A genset system that includes a genset assembly, an electronic fuel injection (EFI) system and an alcohol sensor and a method of controlling air-to-fuel ratio using the genset system are described. The genset assembly includes a genset engine that (1) is capable of running on at least one of gasoline and alcohol, (2) is an air-cooled engine, and (3) operates at a rich air-to-fuel ratio (AFR). The EFI system includes an electronic control unit that is configured to determine a requested AFR based on the data from the alcohol sensor and the data from the air flow sensor, and based on the determined requested relative AFR, the electronic control unit is configured to actuate the fuel injector such that the fuel in an amount sufficient for obtaining an air/fuel mixture that is at the determined requested relative AFR is injected into the intake system.

Abstract: A controller for a plant that controls a controlled variable for the plant in accordance with estimated values, allowing to reduce any error in the estimated values that is caused by solid variation or aging of the plant. A controller for an exhaust emission control system has an estimated Inert-EGR value calculation section (711) to calculate the estimated value IEGRHAT for the Inert-EGR amount on the basis of an input vector U through a neural network, an estimated LAF sensor output value calculation section (712) to calculate the estimated value ?HAT for an exhaust air-fuel ratio correlating with the Inert-EGR amount on the basis of the input vector U through the neural network, an LAF sensor (34) to detect the exhaust air-fuel ratio, and a nonlinear adaptive corrector (713) to calculate the adaptive input UVNS such that the estimated error EHAT between the detected value ?ACT from the LAF sensor (34) and the estimated output value ?HAT of the LAF sensor (34) is minimized.

Abstract: A method for adapting a mixture for a pilot control process for setting a fuel/air mixture for operating an internal combustion engine. The method includes determining a current measuring point from an air and fuel quantity in which a predefined lambda is achieved, determining a current operating range in which the measuring point lies, determining a deviation of the measuring point from the operating point lying in the current operating range, determining a corrected operating point between the operating point and the measuring point, and determining corrected parameters of a parameterized relationship from the corrected operating point and the operating points and parameter values of the preceding adaptation step not lying in the current operating range, and permits adaptation of a mixture without separation of load/rotational speed ranges for adaptation of the offset and of the factor of the linear relationship of air quantity and fuel quantity.

Abstract: Methods and systems for engine control optimization are provided. A first and a second operating condition of a vehicle engine are detected. An initial value is identified for a first and a second engine control parameter corresponding to a combination of the detected operating conditions according to a first and a second engine map look-up table. The initial values for the engine control parameters are adjusted based on a detected engine performance variable to cause the engine performance variable to approach a target value. A first and a second sensitivity of the engine performance variable are determined in response to changes in the engine control parameters. The first engine map look-up table is adjusted when the first sensitivity is greater than a threshold, and the second engine map look-up table is adjusted when the second sensitivity is greater than a threshold.

Abstract: An engine control system which may be used in automotive vehicles includes first correlation data representing correlations between performance parameters associated with different types of performances of a combustion engine and uncorrelated common factors existing among the performance parameters and second correlation data representing correlations between the common factors and combustion parameters associated with combustion states of fuel in the combustion engine. The engine control system determines target values of the common factors using the first correlation data and also determines target values of the combustion parameters using the second correlation data. The engine control system determines command values as a function of the target values of the combustion parameter and outputs them to actuators which control combustion states of fuel in the engine for achieving desired levels of the performances of the combustion engine.

Abstract: A method includes: generating an indicator of present operating conditions of an engine; determining a first amount of noise based on vibration measured during a first plurality of combustion events of a cylinder; storing the first amount of noise and a first value of the indicator in a mapping based on a first engine speed and a first engine load; determining the first value of the indicator from the mapping based on a second engine speed and a second engine load; generating a trigger signal when the first value is different than a second value of the indicator; and, when the trigger signal is generated: determining a second amount of noise based on vibration measured during a second plurality of combustion events of the cylinder; and replacing the first amount of noise and the first value in the mapping with the second amount of noise and the second value.

Abstract: An engine control system includes a torque request control module to determine a first engine torque request. An artificial neural network (ANN) torque request module determines a second engine torque request using an ANN model. A torque security check module that selectively generates a malfunction signal based on the difference between the first engine torque request and the second engine torque request.

Abstract: An engine control apparatus works to determine a target value of each of performance parameters associated with different types of performances of a combustion engine based on operating conditions of the combustion engine, determine target values of combustion parameters associated with combustion states of fuel in the combustion engine based on the target values of the performance parameters using first correlation data representing correlations between the performance parameters and the combustion parameters, and calculate command values of controlled parameters for actuators as a function of the target values of the combustion parameters. When actual values of the performance parameters are in coincidence with the target values, the system changes or corrects the target value of a selected one of the performance parameters so as to enhance the level of a corresponding one of the performances of the engine based on the other performance parameters.

Abstract: A bicycle suspension control apparatus includes a user operating device and a control device. The control device is operatively coupled to the user operating device to selectively control a front bicycle suspension between a plurality of operating states and a rear bicycle suspension between a plurality of operating states. The control device is configured to selectively change the operating states of both the front and rear bicycle suspensions to different ones of the operating states in response to a single operation of the user operating device. The control device controls the front and rear bicycle suspensions such that a first operating state change operation of one of the front and rear bicycle suspensions occurs later than a second operating state change operation of the other of the front and rear bicycle suspensions.

Abstract: A system and method for real-time, self-learning characterization of fuel injector performance during engine operation. The system includes an algorithm for an engine controller which allows the controller to learn the correlation between the fuel mass and pulse width for each injector in the engine in real time while the engine is running. The controller progressively perceives those pulse widths that achieve the desired fuel mass, while it can continuously adapt what it has learned based on various input variations, such as temperature and fuel rail pressure. The controller then uses the learned actual performance of each injector to command the pulse width required to achieve the desired quantity of fuel for each cylinder on each cycle.

Abstract: A vehicle drive motor control system is provided, which, when a vehicle drive motor is in a locked state, may urge a driver to make a switch from actuation of an accelerator to actuation of a brake, thereby preventing thermal damage to coils inside the motor. The vehicle drive motor control system is capable of, when a vehicle drive motor is in a locked state as a result of actuating an accelerator, making the vehicle slowly move backward (or providing other stimulus to the driver) by decreasing a maximum drive torque value. This may effectively cause the driver to make the switch from actuation of the accelerator to actuation of the brake.

Abstract: A method to control an exhaust gas recirculation and a manifold air pressure in an engine includes utilizing a decoupling matrix within a multiple input and multiple output controller to determine an exhaust gas recirculation command and a manifold air pressure command, wherein the decoupling matrix is configured based upon a diagonally dominant model of the engine compensated by the determined exhaust gas recirculation command and the manifold air pressure command. The exhaust gas recirculation and manifold air pressure are controlled based upon the determined exhaust gas recirculation command and the determined manifold air pressure command.

Abstract: According to some embodiments, a method is provided for simulating an analog and mixed-signal circuit design comprising an analog circuit segment connected to a digital circuit segment at a connection point, the method comprising: inserting a bi-directional interface element at the connection point, wherein the analog circuit segment connects to an analog port of the bi-directional interface element and the digital circuit segment connects to a digital port of the bi-directional interface element; and operating the bi-directional interface element such that the bi-directional interface element detects a signal direction and, according to the signal direction, either converts a first analog signal received from the analog port to a first digital signal for the digital port while maintaining a first signal strength of the first analog signal, or converts a second digital signal received from the digital port to a second analog signal for the analog port while maintaining a second signal strength of the second d

Abstract: With the use of a model expression (FIG. 9C), of which inputs include a desired value of an in-cylinder air amount that is a controlled object of a system and predetermined parameters, such as engine speed (ne), a desired throttle opening degree (?ref) required to control the in-cylinder air amount to the desired value is calculated. In this model expression, parameters, such as the engine speed (ne), that oscillate at a relatively high frequency are excluded from subjects of differentiation, and the desired in-cylinder air amount value only is included in the subjects of differentiation.

Abstract: A logical sensor method is provided for internal combustion engines (Compression Ignited or Spark Ignited) based on a software algorithm (SBS). This algorithm identifies the mixture diesel/bio-diesel present in a vehicle's fuel tank and adapts the engine control strategy as a function of the fraction of FAME (Fatty Acid Methyl Esters) vegetal-based oil or oil produced from organic waste blended into a crude oil based diesel fuel (average chemical formula C12H23).

Abstract: A computer-implemented method is used to correct deviations between a predicted gas excess air ratio and a calculated excess air ratio in a dual fuel engine or other gas fueled compression ignition engine. The method includes determining gas excess air ratio for the engine based at least in part on at least one detected current operating parameter and calculating a predicted exhaust gas oxygen concentration engine based on the predicted gas excess air ratio. A time based filtered predicted exhaust gas oxygen concentration value may then be calculated and compared to a time-based filtered measured exhaust gas oxygen concentration value. The resultant oxygen concentration deviation value may be used to generate a corrected predicted gas excess air ratio.

Abstract: A robust optimization-based decision support tool for reservoir development planning can comprise a source of input data, an optimization model, a high fidelity model for simulating the reservoir, and one or more solution routines interfacing with the optimization model. The optimization model can consider unknown parameters having uncertainties directly within the optimization model. The model can systematically address uncertain data, for example, comprehensively or even taking all uncertain data into account. Accordingly, the optimization model can provide flexible or robust optimization solutions that remain feasible over an uncertainty space. Once the reservoir model is optimized, final development plans may be generated.

Abstract: The present invention provides a process for reducing abnormal combustion within a combustion chamber of the engine. The process can include simulation of the piston-driven internal combustion engine with oil droplets from the crankcase entering into the combustion chamber. In addition, the oil drops entering into the combustion chamber can be simulated as hot spots, as can simulation of fuel combustion within the combustion chamber. A probability of pre-ignition for at least a portion of the simulated hot spots as a function of the simulated fuel combustion and the simulated hot spots within the combustion chamber can be calculated and based on the calculation a combustion chamber parameter can be altered such that pre-ignition within the combustion chamber is reduced.

Abstract: A device for controlling the exhaust-gas turbocharging of an internal combustion engine having an exhaust-gas turbocharging device, has an estimated value unit for determining a mass flow through a turbine system, a regulating unit for determining a regulating exhaust-gas back pressure as a function of a nominal charge pressure and an actual charge pressure, and also a unit for generating at least one actuating signal for at least one actuator of the turbine system as a function of the regulating exhaust-gas back pressure and of the mass flow through the turbine system, wherein the estimated value unit has a turbine system model for determining an estimated overall efficiency of the turbine system and a model for determining an estimated overall efficiency of a compressor system having at least two compressors, and wherein the regulating unit is set up to determine the regulating exhaust-gas back pressure using the estimated overall efficiencies

Abstract: A method for controlling an internal combustion engine includes monitoring engine operation including a parameter descriptive of NOx generation within the engine, determining a fast transient NOx estimate with a dynamic model based upon the monitored engine operation, and during a fast transient engine operation including an increase in an operating state of the engine and a substantial closing of an exhaust gas recirculation valve, controlling an engine system based upon the fast transient NOx estimate.

Abstract: an intake system control device includes: an acquisition section that acquires an operation condition of an engine; a steady-state value determination section that determines input and output steady-state values for an intake system of the engine based on the acquired operation condition; a gain determination section that determines a gain for a state space model; and a first input calculation section that calculates the intake system input from the acquired operation condition, the input steady-state value, the output steady-state value, and an intake system output by using the state space model having the determined gain.

Abstract: An apparatus includes a parallel computation unit including an input port and an output port and a one-dimensional computational fluid dynamics model. The input port is configured to sample at a time t1 a boundary condition signal for the one-dimensional computational fluid dynamics model and the output port is configured to provide an output signal before the boundary condition signal is sampled at a time t2.

Abstract: Upon satisfaction of an idle learning condition, the internal combustion engine system of the invention successively performs learning of an idle control amount and learning of a most delayed angle control amount in this sequence. Upon satisfaction of a most delayed angle learning condition, on the other hand, the internal combustion engine system successively performs learning of the most delayed angle control amount and learning of the idle control amount in this sequence. This arrangement effectively reduces the total time required for completion of learning both the idle control amount and the most delayed angle control amount, compared with the conventional procedure of individually learning only one control amount corresponding to the satisfied learning condition.

Abstract: When the internal combustion engine is in an injection-free operating mode, a selected injector is open for injecting a small fuel amount, whereby at least one working cycle with injector control follows or precedes one cycle without control, a differential of two subsequent segment times of the cylinder associated with the selected injector or another variable, that reproduces a temporal crankshaft angle speed modification, is determined as a measurement value respectively for the cycle with and without control, and a relation is formed between the values of the cycles with or without control and used to correct the injection characteristic curve. The engine operates with active ignition and the value for the cycle with control is tested by taking into account ignition faults and the relation is only used to correct the curve if the value in the cycle with control significantly deviates from the one without control.

Abstract: A method for calibrating an engine control module includes sampling a first signal from a first oxygen sensor located upstream from a catalyst. The first signal indicates an oxygen content of exhaust gas produced by an engine. The method further includes predicting a response of a second oxygen sensor located downstream from the catalyst using a model of the catalyst and the first signal and sampling a second signal from the second oxygen sensor. The method further includes determining a component of the second signal based on a difference between samples of the second signal and the predicted response. The component is due to gases other than oxygen. Additionally, the method includes calibrating the engine control module based on the component of the second signal. The engine control module controls an amount of fuel injected into the engine.

Abstract: A Method for estimating NOx creation in a combustion process of a four-stroke internal combustion engine includes monitoring engine sensor inputs, modeling parameters descriptive of said combustion process based upon said engine sensor inputs, and estimating NOx creation with an artificial neural network based upon said parameters.

Abstract: Data indicating a sudden change in a bulk modulus of fuel and data indicating a usage state and a usage environment of an injector as of occurrence of an injection abnormality are stored in EEPROM mounted in the injector. Thus, it can be analyzed whether a cause of a defect such as the injection abnormality is use of inferior fuel based on the data related to the bulk modulus. In addition, it can be analyzed whether the cause of the defect such as the injection abnormality is a severe usage state and a severe usage environment based on the data related to the usage state and the usage environment. Thus, the data useful for analyzing the cause of the defect related to the fuel injection can be provided.

Abstract: An apparatus includes a parallel computation unit including an input port and an output port and a one-dimensional computational fluid dynamics model. The input port is configured to sample at a time t1 a boundary condition signal for the one-dimensional computational fluid dynamics model and the output port is configured to provide an output signal before the boundary condition signal is sampled at a time t2.

Abstract: The invention relates to a method for operating a heating element in a motor vehicle by pulse width modulation, wherein fluctuations in the supply voltage are compensated for by adapting the duty cycle so as to achieve a desired heating output. According to the invention, during a voltage pulse the voltage that is present at the heating element and/or the current flowing through the heating element are measured at specified intervals, and the measured values or values determined therefrom are added to calculate a sum value, which rises with the energy that is fed into the heating element by the voltage pulse, and the voltage pulse is ended at the latest when the sum value has reached a target value. The invention furthermore relates to a glow plug controller for carrying out the method according to the invention.

Abstract: A sensor system includes a plurality of sensor units which transmit any one of a pressure detection signal and a temperature detection signal as a detection signal, a processing unit which transmits a switching command signal to the sensor unit and receives a detection signal from the sensor unit, communication lines through which the switching command signal is transmitted from the processing unit to each of the sensor units, and signal lines through which the detection signal is transmitted in a form of analog signal from the sensor unit to the processing unit. The sensor units are grouped into a first group and a second group. A plurality of communication lines of the first group are branched from one first base line connected to a first communication port of the processing unit.

Abstract: A power output apparatus for outputting power to a drive shaft includes a control unit that controls an internal combustion engine to perform an idle operation at a predetermined rotation speed, executes idle control amount learning, in which an idle control amount serving as a control amount obtained during the control is learned in accordance with establishment of a predetermined learning condition, within a range in which a rotation speed of the drive shaft is lower than a first speed, when the idle control amount learning is incomplete, and executes again the idle control amount learning within a range in which the rotation speed of the drive shaft is lower than a second speed, which is lower than the first speed, when the idle control amount learning is complete.

Abstract: When a specified learning executing condition is established, a command furl injection quantity ratio (CFIQ-ratio) between two fuel injectors is compulsorily changed and a fuel injection quantity error of each fuel injector is learned respectively based on the CFIQ-ratio and an air-fuel-ratio feedback correction value. Based on the learning value of fuel injection quantity error, a fuel injection period of each fuel injector is respectively corrected, whereby each fuel injection quantity error of two fuel injectors is respectively corrected with respect to each cylinder. Thereby, a ratio of fuel injection quantity between two fuel injectors is accurately controlled.

Abstract: An apparatus includes a parallel computation unit including an input port and an output port and a one-dimensional computational fluid dynamics model. The input port is configured to sample at a time t1 a boundary condition signal for the one-dimensional computational fluid dynamics model and the output port is configured to provide an output signal before the boundary condition signal is sampled at a time t2.

Abstract: An efficient control wave form is utilized to actuate the solenoids of a fuel system to reduce boost power/energy consumption. The solenoid is initially energized by applying a boost voltage from an electronic controller across a solenoid coil circuit. The electronic controller monitors the current level in the solenoid coil circuit, and changes to a reduced battery voltage when the current level in the solenoid coil circuit reaches a predetermined trigger current. The controller then maintains a pull-in current based upon battery voltage for a pull-in duration that initiates movement of the solenoid armature from an initial air gap position toward a final air gap position. After the pull-in duration, the current level is dropped to a hold in level for the remaining duration of the actuation event. The solenoid may be used for fuel injector control and/or pump control, such as to control fuel injection and pumping events respectively.

Abstract: The method for generating an integrated guidance law for aerodynamic missiles uses a strength Pareto evolutionary algorithm (SPEA)-based approach for generating an integrated fuzzy guidance law, which includes three separate fuzzy controllers. Each of these fuzzy controllers is activated in a unique region of missile interception. The distribution of membership functions and the associated rules are obtained by solving a nonlinear constrained multi-objective optimization problem in which final time, energy consumption, and miss distance are treated as competing objectives. A Tabu search is utilized to build a library of initial feasible solutions for the multi-objective optimization algorithm. Additionally, a hierarchical clustering technique is utilized to provide the decision maker with a representative and manageable Pareto-optimal set without destroying the characteristics of the trade-off front. A fuzzy-based system is employed to extract the best compromise solution over the trade-off curve.

Abstract: The present invention relates to a method and apparatus for three dimensional calibration of an on-board diagnostics system. In one embodiment, the present invention is a method for calibrating an on-board diagnostic system for an automobile including the steps of generating a three dimensional surface corresponding to an engine operating under a first condition, generating a three dimensional surface corresponding to the engine operating under a second condition, and generating a three dimensional threshold surface using the three dimensional surface corresponding to the engine operating under the first condition and the three dimensional surface corresponding to the engine operating under the second condition.

Abstract: An EGR valve control system includes a motor 5 exercising the opening and closing control of an EGR valve; a sensor 6 detecting the actual opening position of the EGR valve; and a motor control apparatus (control arithmetic section 1) computing a drive duty of the motor 5 based on a target opening position of the EGR valve and the actual opening position thereof detected by the sensor 6; and the control apparatus is arranged such that the control arithmetic section 1, when a target opening position of the EGR valve is set, computes an integral term based on the deviation between the target opening position and the actual opening position of the EGR valve, a proportional term and a differential term based on the change of the actual opening position of the EGR valve, and a feedforward term based on the change of the target opening position, respectively, and the control arithmetic section further exercises the opening and closing control of the EGR valve by computing the drive duty of the motor 5 by performing

Abstract: A method of sensing the air/fuel ratio in a combustion chamber of an internal combustion engine that may be easily implemented by a respective low-cost device includes a pressure sensor and a learning machine that generates a sensing signal representing the air/fuel ratio by processing the waveform of the pressure in at least one cylinder of the engine. In practice, the learning machine extracts characteristic parameters of the waveform of the pressure and as a function of a certain number of them generates the sensing signal.