WO2016206920A1 - An ecm to determine air-fuel ratio of an engine - Google Patents
An ecm to determine air-fuel ratio of an engine Download PDFInfo
- Publication number
- WO2016206920A1 WO2016206920A1 PCT/EP2016/062171 EP2016062171W WO2016206920A1 WO 2016206920 A1 WO2016206920 A1 WO 2016206920A1 EP 2016062171 W EP2016062171 W EP 2016062171W WO 2016206920 A1 WO2016206920 A1 WO 2016206920A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- ratio
- engine
- operating parameters
- ecm
- engine operating
- Prior art date
Links
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D41/00—Electrical control of supply of combustible mixture or its constituents
- F02D41/02—Circuit arrangements for generating control signals
- F02D41/14—Introducing closed-loop corrections
- F02D41/1401—Introducing closed-loop corrections characterised by the control or regulation method
- F02D41/1405—Neural network control
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D41/00—Electrical control of supply of combustible mixture or its constituents
- F02D41/02—Circuit arrangements for generating control signals
- F02D41/14—Introducing closed-loop corrections
- F02D41/1401—Introducing closed-loop corrections characterised by the control or regulation method
- F02D41/1404—Fuzzy logic control
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D41/00—Electrical control of supply of combustible mixture or its constituents
- F02D41/02—Circuit arrangements for generating control signals
- F02D41/14—Introducing closed-loop corrections
- F02D41/1438—Introducing closed-loop corrections using means for determining characteristics of the combustion gases; Sensors therefor
- F02D41/1444—Introducing closed-loop corrections using means for determining characteristics of the combustion gases; Sensors therefor characterised by the characteristics of the combustion gases
- F02D41/1454—Introducing closed-loop corrections using means for determining characteristics of the combustion gases; Sensors therefor characterised by the characteristics of the combustion gases the characteristics being an oxygen content or concentration or the air-fuel ratio
- F02D41/1458—Introducing closed-loop corrections using means for determining characteristics of the combustion gases; Sensors therefor characterised by the characteristics of the combustion gases the characteristics being an oxygen content or concentration or the air-fuel ratio with determination means using an estimation
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D41/00—Electrical control of supply of combustible mixture or its constituents
- F02D41/24—Electrical control of supply of combustible mixture or its constituents characterised by the use of digital means
- F02D41/2406—Electrical control of supply of combustible mixture or its constituents characterised by the use of digital means using essentially read only memories
- F02D41/2425—Particular ways of programming the data
- F02D41/2429—Methods of calibrating or learning
- F02D41/2451—Methods of calibrating or learning characterised by what is learned or calibrated
- F02D41/2454—Learning of the air-fuel ratio control
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D41/00—Electrical control of supply of combustible mixture or its constituents
- F02D41/02—Circuit arrangements for generating control signals
- F02D41/14—Introducing closed-loop corrections
- F02D41/1401—Introducing closed-loop corrections characterised by the control or regulation method
- F02D2041/1433—Introducing closed-loop corrections characterised by the control or regulation method using a model or simulation of the system
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D41/00—Electrical control of supply of combustible mixture or its constituents
- F02D41/02—Circuit arrangements for generating control signals
- F02D41/14—Introducing closed-loop corrections
- F02D41/1401—Introducing closed-loop corrections characterised by the control or regulation method
- F02D2041/1433—Introducing closed-loop corrections characterised by the control or regulation method using a model or simulation of the system
- F02D2041/1437—Simulation
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02D—CONTROLLING COMBUSTION ENGINES
- F02D2200/00—Input parameters for engine control
- F02D2200/02—Input parameters for engine control the parameters being related to the engine
- F02D2200/04—Engine intake system parameters
- F02D2200/0402—Engine intake system parameters the parameter being determined by using a model of the engine intake or its components
Definitions
- the present disclosure relates to method and device to determine air-fuel ratio of an internal combustion engine.
- a method for using a computer for determining an air-to-fuel (A/F) ratio of an internal combustion engine in which information characteristic of the engine relating the A/F ratio of the engine, the exhaust gas temperature of the engine, the speed of the engine and a parameter related to the load of the engine is previously stored in the computer.
- the method comprises the steps of: measuring the exhaust gas temperature of the engine; measuring the speed of the engine; measuring the parameter related to the load of the engine; computing the A/F ratio based on the previously stored information, the measured exhaust gas temperature, the measured speed and the measured parameter related to the load; and providing an output signal representative of the A/F ratio.
- Fig. 1 illustrates a block diagram of an ECM to determine A/F ratio of an engine, according to an embodiment of the present disclosure
- Fig. 2 illustrates a flow diagram of a method for determining A/F ratio of an engine, according to an embodiment of the present disclosure.
- Fig. 1 illustrates a block diagram of an ECM to determine A/F ratio of an engine, according to an embodiment of the present disclosure.
- the Electronic Control Module (ECM) 102 is provided to determine air-fuel ratio of an Internal Combustion Engine (ICE) 112.
- the ECM of the present disclosure aims to estimate/determine A/F ratio without using a lambda sensor.
- the ECM 102 is adapted to receive signals relating to plurality of engine operating parameters comprising at least one exhaust temperature, an engine speed, an engine load, an ignition angle and a relative fuel mass.
- the ECM 102 accesses a global model, at least one weighing function and at least one data map from a memory element (not shown) to determine the A/F ratio.
- the global model comprises at least two local models.
- the global model is a combination of at least two independent local models and corresponding weighing functions.
- the at least one data map comprises empirically derived values (e.g. coefficients) corresponding to the engine operating parameters.
- the ECM 102 processes the received signals of the engine operating parameters through the global model, a corresponding weighing function and at least one data map and determines/predicts/forecasts the A/F ratio.
- a real time signal of the engine operating parameters is used for determining the A/F ratio.
- the global model can be a neural network model such as a Local Linear Model Tree (LoLiMoT), a Local Polynomial Model Tree (POLYMoT), and a combination of LoLiMoT and POLYMoT.
- LoLiMoT Local Linear Model Tree
- POLYMoT Local Polynomial Model Tree
- the development of the global model is explained in detail in the following paragraphs.
- the set of engine operating parameters are selected during testing phase of the vehicle. During testing, a vehicle is run for different load conditions and values for different engine parameters are noted. A co-relation matrix is formed and those parameters which are found to have more influence on lambda value are selected.
- the operating parameters thus selected comprises but not limited to the exhaust gas temperature, the engine speed, the engine load, the ignition angle and the relative fuel mass.
- the ECM 102 is also configurable to take further at least one engine operating parameters selected from a group comprising a throttle angle, a desired A/F ratio, a relative air mass/charge, an engine temperature, a manifold air pressure, a coolant temperature, an exhaust gas pressure and a spark energy. Other operating parameters are allowed to be considered and taken and improve the accuracy further by the ECM 102 at a time.
- the influence of the selected operating parameters on A/F ratio is known or computed or plotted. Based on the known/ expected response, the global model to determine the A/F ratio is created.
- the ECM 102 determines the A/F ratio at an upstream (also referred as pre-cat position) of a catalytic converter 106.
- the ECM 102 uses at least one of further engine operating parameters selected from a group comprising the relative air charge, the engine temperature, the manifold air pressure, the coolant temperature, the exhaust gas pressure and the spark energy.
- upstream and pre-cat will be used interchangeably hereinafter.
- the ECM 102 determines the A/F ratio at an downstream (also referred as post-cat) of the catalytic converter 106 by using at least one of further engine operating parameters selected from a group comprising the relative air charge, the engine temperature, the manifold air pressure, the coolant temperature, the exhaust gas pressure, the spark energy, an A/F ratio at an upstream end of the catalytic converter 106, a catalyst efficiency, a rate of change of temperature due to chemical reactions at the catalyst.
- the A/F ratio is selected from a group comprising an A/F ratio determined without lambda sensor 104 and an A/F ratio measured using a lambda sensor 104.
- the term downstream and post-cat will be used interchangeably.
- the global model is pre-stored in a memory element associated with the ECM 102.
- the global model establishes a relationship between the plurality of engine operating parameters and the A/F ratio.
- the global model is selected from a group comprising a linear model and a non-linear model.
- the global model is selected from a group comprising a Local Linear Model Tree (LoLiMoT), a Local Polynomial Model Tree (POLYMoT), and a combination of LoLiMoT and POLYMoT.
- the global model is also allowed to use single local model with a corresponding weighing function. Further, the global model is also allowed to use just a regression model as well, i.e. only one local model and hence a corresponding weighing function is used.
- the global model is processed based on a sum of products of weighted local models.
- the global model is first built/developed offline.
- the process of developing global model involves selecting a single model approximately matching the required response data or curve of the lambda sensor.
- a weighing function is constructed and the first single model is fit using least square estimation process.
- the weighing function validates the selected single model with respect to the required response curve which signifies the region where the single model is valid.
- the single model is further checked for different partition techniques.
- An error in the partition techniques of the selected single model and the required response curve is calculated with the help of the weighing function.
- the partition technique providing least error (or the best partition technique) is selected and taken forward for further processing.
- the single model is split/ divided into at least two local models using the partition technique providing least error.
- the single model undergoes a test based on a convergence factor once split.
- the convergence factor is at least one selected from a group comprising number of iterations, the error tolerance, complexity of the model and the like. The iteration of the offline model building continues till the test of convergence is satisfied/ fulfilled.
- the global model is built using plurality of engine operating parameters and comprises at least one or combination of a Two-Dimensional (2D), Three-Dimensional (3D) or multi dimensional input space.
- the present disclosure performs the offline model building using at least one selected from a group comprising a linear model and a polynomial model.
- a polynomial model provides a more flexible model where an order of the polynomial is selected in a manner to be fit to each part of the input space.
- the use of polynomial model provides a mixture of first, second, third and multi-order polynomials.
- a device or means to determine air-fuel equivalence ratio (lambda value) is provided.
- the ECM 102 estimates the A/F ratio equivalence ratio (lambda) based on a stoichiometric A/F ratio.
- the ECM 102 divides the determined A/F ratio by the stoichiometric A/F ratio.
- the device is the ECM 102.
- a system 100 to determine Air- Fuel (A/F) ratio of an Internal Combustion Engine (ICE) 112 comprises means/sensors to measure engine operating parameters comprising an exhaust temperature, an engine speed, an engine load, an ignition angle and a relative fuel mass.
- the system 100 further comprises the ECM 102 in communication with the means to measure the engine operating parameters.
- the ECM 102 determines the A/F ratio which is used to control or enhance the combustion process in the engine 112.
- the at least one device to provide input signals for respective operating parameters is selected from a group comprising a engine speed sensor 116, a Manifold Absolute Pressure (MAP) sensor, a mass air flow sensor, a engine load sensor 118, at least one temperature sensor 110, an oxygen/lambda sensor 104, a relative fuel mass sensing means 114, a controller/ processor for selecting fuel injection quantity based on a map and the like.
- MAP Manifold Absolute Pressure
- At least one temperature sensor 110 and a lambda sensor 104 is provided before and after a catalytic converter 106 in an exhaust path/line/pipe 108 in various combinations.
- the different combination of arranging the at least temperature sensor 110 and the lambda sensor 104 are possible for two-wheeler, three-wheeler, four-wheeler and other type of vehicles.
- the combinations comprises but not limited to a temperature sensor 110 at pre-cat and lambda sensor 104 at post-cat position, a lambda sensor 104 at pre-cat and temperature sensor 110 at post-cat location.
- a temperature sensor 110 at both pre- cat and post-cat positions are provided.
- the lambda sensor 104 is selected from a group comprising universal type and a two step type based on requirement.
- the input signals from the temperature sensor 110 and other engine operating parameters are used and processed to determine the A/F ratio before the catalyst i.e. pre-cat position.
- an A/F ratio after the catalyst i.e. post-cat position is determined.
- the input signals from the two sensors along with the other appropriate engine operating parameters are used to determine the A/F ratio before and after the catalyst.
- the lambda sen- sor 104 directly provides the A/F ratio, and the A/F ratio is used with the values of temperature sensor 110 and other suitable engine operating parameters to determine A/F ratio after the catalyst.
- the ECM 102 controls/adjusts the ignition or combustion process through a control signal 120 for injectors, throttle and the like.
- the lambda or the A/F ratio determined from the model is used in the fuel mixture adaptation.
- the deviation in the lambda that results in a deviation in the fuel mixture is corrected in the fuel path via mixture adaptation.
- the injection time is corrected in all operating modes and engine speed-load ranges.
- Fig. 2 illustrates a flow diagram of a method for determining A/F ratio for the engine, according to an embodiment of the present disclosure.
- the step 202 comprises receiving a set of engine operating parameters comprising an exhaust gas temperature, an engine speed, an engine load, an ignition angle and a relative fuel mass from respective sensing means.
- the sensing means comprises but not limited to a temperature sensor 110 for the exhaust gas, speed sensor 116 for engine speed, Manifold Air Pressure (MAP) sensor and the like.
- the step 204 comprises accessing a global model comprising at least two local models, at least two weighing functions and at least one data map, from a memory element.
- the at least one data map comprises empirically derived values corresponding to said engine operating parameters.
- the step 206 comprises determining an A/F ratio based on the received set of engine operating parameters by processing the global model, the weighing function and the at least one data map.
- the set of engine operating parameters further comprises at least one selected from a group comprising a throttle angle, a desired A/F ratio, a relative air charge, an engine temperature, manifold air pressure, coolant temperature, exhaust gas pressure and spark energy.
- the sensing means are in communication with the ECM 102 through a wired or wireless connection.
- the real time input signals or measured/ calculated values are feature scaled/ normalized to bring all inputs values to a common range.
- the feature scaling is done as various engine operating parameters with different units and different types of values are used.
- the modified input values of the engine operating parameters are used to process the at least two local models and the corresponding weighing functions. While processing the value of the at least two local models, at least one data map is used to use various pre-stored coefficients or constants as per the respective engine operating parameters. An output value of the each of the local models is calculated and stored in the memory element.
- the method further comprises calculating a closeness of each local model to the required model using the at least two weighing function and values from the at least data map.
- the at least one data map is used for computing the corresponding weighing functions.
- the result provides a value (hereinafter referred as weight) indicating how well is the particular local model matches to the required/expected local model.
- the result is stored for each local model in the memory element.
- the weights for each local model is calculated and stored.
- a total of all the weights is calculated and stored separately. Now the output value of each local model is multiplied with the respective weights. The multiplication provides the contribution of each local model in determining the A/F ratio. The sum/ addition of all the contributions from each of the local models determine the A/F ratio. The determined A/F ratio is said to be a forecasted or predicted or estimated A/F ratio.
- the A/F ratio is determined in at least one site/location in an exhaust path 108 of a vehicle.
- the site is an upstream of the catalytic converter 106 i.e. before a catalyst of a catalytic converter 106.
- the site is a downstream of the catalytic converter 106 i.e. after the catalyst of the catalytic converter 106.
- the A/F ratio is determined after the catalyst, assists in On-Board Diagnostics (OBD) of the catalyst.
- OBD On-Board Diagnostics
- the global model is a regression model
- the A/F ratio is directly calculated by inserting the real time operating parameters values in the regression model.
- estimation of the A/F ratio is cost effective as no lambda sensor or oxygen sensor is used.
- the present disclosure is applicable to existing vehicles by using sensors inputs already existing in the vehicle. By adding a temperature sensor in the exhaust line, the estimation of A/F ratio is made more accurate in existing vehicles.
- the A/F ratio is also possible to be calculated for different fuels comprising gasoline, Compressed Natural Gas (CNG), Piped Natural Gas (PNG), ethanol, diesel, flex-fuel and the like.
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
- Electrical Control Of Air Or Fuel Supplied To Internal-Combustion Engine (AREA)
Abstract
The various embodiments herein provide an Electronic Control Module (ECM) 102 to determine Air-Fuel (A/F) ratio of an engine 112. The ECM 102 is adapted to receive signals relating to engine operating parameters comprising at least one exhaust tem¬ perature, an engine speed, an engine load, an ignition angle and a relative fuel mass. The ECM 102 then accesses a global model, at least one weighing function and at least one data map from a memory element to determine the A/F ratio. The global model comprises at least two local models. The weighing function for each of the local model is used. The at least one data map comprises empirically derived values corre¬ sponding to the engine operating parameters. The ECM 102 processes the received signals of the engine operating parameters through the global model, the at least one weighing function and the data map and determines/predicts the A/F ratio.
Description
COMPLETE SPECIFICATION
TITLE
AN ECM TO DETERMINE AIR-FUEL RATIO OF AN ENGINE
The following specification describes and ascertains the nature of this invention and the manner in which it is to be performed:
Field of the invention:
The present disclosure relates to method and device to determine air-fuel ratio of an internal combustion engine.
Background of the invention:
According to a patent literature WO2001000978, a method is disclosed for using a computer for determining an air-to-fuel (A/F) ratio of an internal combustion engine in which information characteristic of the engine relating the A/F ratio of the engine, the exhaust gas temperature of the engine, the speed of the engine and a parameter related to the load of the engine is previously stored in the computer. The method comprises the steps of: measuring the exhaust gas temperature of the engine; measuring the speed of the engine; measuring the parameter related to the load of the engine; computing the A/F ratio based on the previously stored information, the measured exhaust gas temperature, the measured speed and the measured parameter related to the load; and providing an output signal representative of the A/F ratio.
Brief description of the accompanying drawings:
An embodiment of the disclosure is described with reference to the following accompanying drawings,
Fig. 1 illustrates a block diagram of an ECM to determine A/F ratio of an engine, according to an embodiment of the present disclosure, and Fig. 2 illustrates a flow diagram of a method for determining A/F ratio of an engine, according to an embodiment of the present disclosure.
Detailed description of the embodiments:
Fig. 1 illustrates a block diagram of an ECM to determine A/F ratio of an engine, according to an embodiment of the present disclosure. The Electronic Control Module (ECM) 102 is provided to determine air-fuel ratio of an Internal Combustion Engine (ICE) 112. The ECM of the present disclosure aims to estimate/determine A/F ratio without using a lambda sensor. The ECM 102 is adapted to receive signals relating to plurality of engine operating parameters comprising at least one exhaust temperature, an engine speed, an engine load, an ignition angle and a relative fuel mass. The ECM 102 then accesses a global model, at least one weighing function and at least one data map from a memory element (not shown) to determine the A/F ratio. The global model comprises at least two local models. In other words, the global model is a combination of at least two independent local models and corresponding weighing functions. The at least one data map comprises empirically derived values (e.g. coefficients) corresponding to the engine operating parameters. The ECM 102 processes the received signals of the engine operating parameters through the global model, a corresponding weighing function and at least one data map and determines/predicts/forecasts the A/F ratio. A real time signal of the engine operating parameters is used for determining the A/F ratio.
The global model can be a neural network model such as a Local Linear Model Tree (LoLiMoT), a Local Polynomial Model Tree (POLYMoT), and a combination of LoLiMoT and POLYMoT. The development of the global model is explained in detail in the following paragraphs.
The set of engine operating parameters are selected during testing phase of the vehicle. During testing, a vehicle is run for different load conditions and values for different engine parameters are noted. A co-relation matrix is formed and those parameters which are found to have more influence on lambda value are selected. The operating
parameters thus selected comprises but not limited to the exhaust gas temperature, the engine speed, the engine load, the ignition angle and the relative fuel mass.
The ECM 102 is also configurable to take further at least one engine operating parameters selected from a group comprising a throttle angle, a desired A/F ratio, a relative air mass/charge, an engine temperature, a manifold air pressure, a coolant temperature, an exhaust gas pressure and a spark energy. Other operating parameters are allowed to be considered and taken and improve the accuracy further by the ECM 102 at a time. The influence of the selected operating parameters on A/F ratio is known or computed or plotted. Based on the known/ expected response, the global model to determine the A/F ratio is created.
According to an embodiment of the present disclosure, the ECM 102 determines the A/F ratio at an upstream (also referred as pre-cat position) of a catalytic converter 106. The ECM 102 uses at least one of further engine operating parameters selected from a group comprising the relative air charge, the engine temperature, the manifold air pressure, the coolant temperature, the exhaust gas pressure and the spark energy. The term upstream and pre-cat will be used interchangeably hereinafter.
According to yet another embodiment of the present disclosure, the ECM 102 determines the A/F ratio at an downstream (also referred as post-cat) of the catalytic converter 106 by using at least one of further engine operating parameters selected from a group comprising the relative air charge, the engine temperature, the manifold air pressure, the coolant temperature, the exhaust gas pressure, the spark energy, an A/F ratio at an upstream end of the catalytic converter 106, a catalyst efficiency, a rate of change of temperature due to chemical reactions at the catalyst. The A/F ratio is selected from a group comprising an A/F ratio determined without lambda sensor 104 and an A/F ratio measured using a lambda sensor 104. The term downstream and post-cat will be used interchangeably.
The global model is pre-stored in a memory element associated with the ECM 102. The global model establishes a relationship between the plurality of engine operating parameters and the A/F ratio.
As described earlier, the global model is selected from a group comprising a linear model and a non-linear model. For example, the global model is selected from a group comprising a Local Linear Model Tree (LoLiMoT), a Local Polynomial Model Tree (POLYMoT), and a combination of LoLiMoT and POLYMoT. The global model is also allowed to use single local model with a corresponding weighing function. Further, the
global model is also allowed to use just a regression model as well, i.e. only one local model and hence a corresponding weighing function is used.
The global model is processed based on a sum of products of weighted local models. The global model is first built/developed offline. The process of developing global model involves selecting a single model approximately matching the required response data or curve of the lambda sensor. A weighing function is constructed and the first single model is fit using least square estimation process. The weighing function validates the selected single model with respect to the required response curve which signifies the region where the single model is valid. The single model is further checked for different partition techniques. An error in the partition techniques of the selected single model and the required response curve is calculated with the help of the weighing function. The partition technique providing least error (or the best partition technique) is selected and taken forward for further processing. The single model is split/ divided into at least two local models using the partition technique providing least error. The single model undergoes a test based on a convergence factor once split.
The convergence factor is at least one selected from a group comprising number of iterations, the error tolerance, complexity of the model and the like. The iteration of the offline model building continues till the test of convergence is satisfied/ fulfilled. The global model is built using plurality of engine operating parameters and comprises at least one or combination of a Two-Dimensional (2D), Three-Dimensional (3D) or multi dimensional input space.
The present disclosure performs the offline model building using at least one selected from a group comprising a linear model and a polynomial model. Implementing a polynomial model provides a more flexible model where an order of the polynomial is selected in a manner to be fit to each part of the input space. The use of polynomial model provides a mixture of first, second, third and multi-order polynomials.
According to an embodiment of the present disclosure, a device or means to determine air-fuel equivalence ratio (lambda value) is provided. Once the A/F ratio is calculated, the ECM 102 estimates the A/F ratio equivalence ratio (lambda) based on a stoichiometric A/F ratio. The ECM 102 divides the determined A/F ratio by the stoichiometric A/F ratio. The device is the ECM 102.
According to an embodiment of the present disclosure, a system 100 to determine Air- Fuel (A/F) ratio of an Internal Combustion Engine (ICE) 112 is provided. The system 100 comprises means/sensors to measure engine operating parameters comprising an
exhaust temperature, an engine speed, an engine load, an ignition angle and a relative fuel mass. The system 100 further comprises the ECM 102 in communication with the means to measure the engine operating parameters. The ECM 102 determines the A/F ratio which is used to control or enhance the combustion process in the engine 112.
The at least one device to provide input signals for respective operating parameters is selected from a group comprising a engine speed sensor 116, a Manifold Absolute Pressure (MAP) sensor, a mass air flow sensor, a engine load sensor 118, at least one temperature sensor 110, an oxygen/lambda sensor 104, a relative fuel mass sensing means 114, a controller/ processor for selecting fuel injection quantity based on a map and the like.
According to an embodiment of the present disclosure, at least one temperature sensor 110 and a lambda sensor 104 is provided before and after a catalytic converter 106 in an exhaust path/line/pipe 108 in various combinations. The different combination of arranging the at least temperature sensor 110 and the lambda sensor 104 are possible for two-wheeler, three-wheeler, four-wheeler and other type of vehicles. The combinations comprises but not limited to a temperature sensor 110 at pre-cat and lambda sensor 104 at post-cat position, a lambda sensor 104 at pre-cat and temperature sensor 110 at post-cat location. In another combination a temperature sensor 110 at both pre- cat and post-cat positions are provided. The lambda sensor 104 is selected from a group comprising universal type and a two step type based on requirement.
The input signals from the temperature sensor 110 and other engine operating parameters are used and processed to determine the A/F ratio before the catalyst i.e. pre-cat position.
Based on the determined A/F ratio and other catalyst related parameters comprising catalyst efficiency, heat released due to chemical reactions at the catalyst and the like, an A/F ratio after the catalyst i.e. post-cat position is determined.
In the combination where a temperature sensor 110 before and a temperature sensor 110 after the catalyst are provided, the input signals from the two sensors along with the other appropriate engine operating parameters are used to determine the A/F ratio before and after the catalyst.
In the combination where a lambda sensor 104 before the catalytic converter 106 and a temperature sensor 110 after the catalytic converter 106 are provided, the lambda sen-
sor 104 directly provides the A/F ratio, and the A/F ratio is used with the values of temperature sensor 110 and other suitable engine operating parameters to determine A/F ratio after the catalyst.
The ECM 102 controls/adjusts the ignition or combustion process through a control signal 120 for injectors, throttle and the like. The lambda or the A/F ratio determined from the model is used in the fuel mixture adaptation. The lambda controller will operate the engine always at lambda=l.The deviation in the lambda that results in a deviation in the fuel mixture is corrected in the fuel path via mixture adaptation. The injection time is corrected in all operating modes and engine speed-load ranges.
Fig. 2 illustrates a flow diagram of a method for determining A/F ratio for the engine, according to an embodiment of the present disclosure. The step 202 comprises receiving a set of engine operating parameters comprising an exhaust gas temperature, an engine speed, an engine load, an ignition angle and a relative fuel mass from respective sensing means. The sensing means comprises but not limited to a temperature sensor 110 for the exhaust gas, speed sensor 116 for engine speed, Manifold Air Pressure (MAP) sensor and the like. The step 204 comprises accessing a global model comprising at least two local models, at least two weighing functions and at least one data map, from a memory element. The at least one data map comprises empirically derived values corresponding to said engine operating parameters. The step 206 comprises determining an A/F ratio based on the received set of engine operating parameters by processing the global model, the weighing function and the at least one data map.
The set of engine operating parameters further comprises at least one selected from a group comprising a throttle angle, a desired A/F ratio, a relative air charge, an engine temperature, manifold air pressure, coolant temperature, exhaust gas pressure and spark energy.
The sensing means are in communication with the ECM 102 through a wired or wireless connection. The real time input signals or measured/ calculated values are feature scaled/ normalized to bring all inputs values to a common range. The feature scaling is done as various engine operating parameters with different units and different types of values are used. The modified input values of the engine operating parameters are used to process the at least two local models and the corresponding weighing functions. While processing the value of the at least two local models, at least one data map is used to use various pre-stored coefficients or constants as per the respective
engine operating parameters. An output value of the each of the local models is calculated and stored in the memory element.
The method further comprises calculating a closeness of each local model to the required model using the at least two weighing function and values from the at least data map. The at least one data map is used for computing the corresponding weighing functions. The result provides a value (hereinafter referred as weight) indicating how well is the particular local model matches to the required/expected local model. The result is stored for each local model in the memory element. The weights for each local model is calculated and stored.
A total of all the weights is calculated and stored separately. Now the output value of each local model is multiplied with the respective weights. The multiplication provides the contribution of each local model in determining the A/F ratio. The sum/ addition of all the contributions from each of the local models determine the A/F ratio. The determined A/F ratio is said to be a forecasted or predicted or estimated A/F ratio.
The A/F ratio is determined in at least one site/location in an exhaust path 108 of a vehicle. In one embodiment the site is an upstream of the catalytic converter 106 i.e. before a catalyst of a catalytic converter 106. In another embodiment, the site is a downstream of the catalytic converter 106 i.e. after the catalyst of the catalytic converter 106. The A/F ratio is determined after the catalyst, assists in On-Board Diagnostics (OBD) of the catalyst.
In accordance to an embodiment, the global model is a regression model, and the A/F ratio is directly calculated by inserting the real time operating parameters values in the regression model.
According to an embodiment of the present disclosure, estimation of the A/F ratio is cost effective as no lambda sensor or oxygen sensor is used. The present disclosure is applicable to existing vehicles by using sensors inputs already existing in the vehicle. By adding a temperature sensor in the exhaust line, the estimation of A/F ratio is made more accurate in existing vehicles. The A/F ratio is also possible to be calculated for different fuels comprising gasoline, Compressed Natural Gas (CNG), Piped Natural Gas (PNG), ethanol, diesel, flex-fuel and the like.
It should be understood that embodiments explained in the description above are only illustrative and do not limit the scope of this invention. Many such embodiments and
other modifications and changes in the embodiment explained in the description are envisaged. The scope of the invention is only limited by the scope of the claims.
Claims
1. A method for determining Air-Fuel (A/F) ratio of an Internal Combustion Engine (ICE) (112), the method comprising the steps of: a. receiving a set of engine operating parameters comprising an exhaust gas temperature, an engine speed, an engine load, an ignition angle and a relative fuel mass from respective sensing means;
b. accessing a global model comprising at least two local models, at least two weighing functions and at least one data map, from a memory element, said at least one data map comprises empirically derived values corresponding to said engine operating parameters;
c. determining an A/F ratio based on the received set of engine operating parameters by processing said global model, said weighing function and said at least one data map.
2. The method as claimed in claim 1, wherein said set of engine operating parameters further comprises at least one selected from a group comprising a throttle angle, a desired A/F ratio, a relative air charge, an engine temperature, a manifold air pressure, a coolant temperature, a exhaust gas pressure and a spark energy.
3. The method as claimed in claim 1, wherein said set of engine operating parameters and said at least one data map are used for computing said at least two weighing functions and said at least two local models.
4. The method as claimed in claim 1, wherein determining said A/F ratio comprises multiplying an output of said at least two weighing functions by an output of respective local models, followed by adding said multiplied results.
5. The method as claimed in claim 1, wherein said A/F ratio is determined for at least one selected from a group comprising an upstream of a catalytic converter (106) and a downstream of a catalytic converter (106).
An Electronic Control Module (ECM) (102) to determine Air-Fuel (A/F) ratio of an Internal Combustion Engine (ICE) (112), said ECM (102) is adapted to:
receive a set of engine operating parameters comprising an exhaust gas temperature, an engine speed, an engine load, an ignition angle and a relative fuel mass from respective sensing means,
access a global model comprising at least two local models, a respective weighing function, and at least one data map, all from a memory element; said at least one data map comprises empirically derived values corresponding to a set of engine operating parameters and
determine an A/F ratio based on the received set of engine operating parameters using said global model, said weighing function and said at least one data map.
The ECM (102) as claimed in claim 6, wherein said A/F ratio is determined at an upstream of a catalytic converter (106) by using at least one of further engine operating parameters selected from a group comprising a throttle angle, a desired A/F ratio, a relative air charge, an engine temperature, a manifold air pressure, a coolant temperature, an exhaust gas pressure and a spark energy.
The ECM (102) as claimed in claim 6, wherein said A/F ratio is determined at an downstream of a catalytic converter (106) by using at least one of further engine operating parameters selected from a group comprising a relative air charge, an engine temperature, a manifold air pressure, a coolant temperature, an exhaust gas pressure, a spark energy, an A/F ratio corresponding to upstream of said catalytic converter (106), a catalyst efficiency, a rate of change of temperature due to chemical reactions at said catalyst converter (106).
The ECM (102) as claimed in claim 6, wherein at least one of said at least two local models are selected from a group comprising a linear model and a non-linear model.
The ECM (102) as claimed in claim 6, wherein said global model is selected from a group comprising a Local Linear Model Tree (LoLiMoT), a Local Polynomial Model Tree (POLYMoT), and a combination of LoLiMoT and POLYMoT.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
IN3238/CHE/2015 | 2015-06-26 | ||
IN3238CH2015 | 2015-06-26 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2016206920A1 true WO2016206920A1 (en) | 2016-12-29 |
Family
ID=56087274
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2016/062171 WO2016206920A1 (en) | 2015-06-26 | 2016-05-30 | An ecm to determine air-fuel ratio of an engine |
Country Status (2)
Country | Link |
---|---|
TW (1) | TW201708691A (en) |
WO (1) | WO2016206920A1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR3086346A1 (en) * | 2018-09-26 | 2020-03-27 | Psa Automobiles Sa | METHOD AND DEVICE FOR PREDICTIVE ESTIMATION OF THE TEMPERATURE OF EXHAUST GASES FROM A VEHICLE HEAT ENGINE |
CN113239966A (en) * | 2021-04-14 | 2021-08-10 | 联合汽车电子有限公司 | Gas mixture deviation self-learning method and system, readable storage medium and electronic equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5784879A (en) * | 1995-06-30 | 1998-07-28 | Nippondenso Co., Ltd. | Air-fuel ratio control system for internal combustion engine |
US5915368A (en) * | 1996-05-28 | 1999-06-29 | Matsushita Electric Industrial Co, Ltd | Air/fuel ratio control apparatus that uses a neural network |
EP0962871A2 (en) * | 1998-06-02 | 1999-12-08 | Yamaha Hatsudoki Kabushiki Kaisha | Data estimation method in engine control |
WO2001000978A1 (en) | 1999-06-29 | 2001-01-04 | Heraeus Electro-Nite International N.V. | Method and apparatus for determining the a/f ratio of an internal combustion engine |
EP1854984A1 (en) * | 2006-05-10 | 2007-11-14 | HONDA MOTOR CO., Ltd. | Air-fuel ratio control system and method for internal combustion engine |
DE102013225768A1 (en) * | 2013-12-12 | 2015-06-18 | Robert Bosch Gmbh | Method and apparatus for determining a LOLIMOT model |
-
2016
- 2016-05-30 WO PCT/EP2016/062171 patent/WO2016206920A1/en active Application Filing
- 2016-06-04 TW TW105117727A patent/TW201708691A/en unknown
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5784879A (en) * | 1995-06-30 | 1998-07-28 | Nippondenso Co., Ltd. | Air-fuel ratio control system for internal combustion engine |
US5915368A (en) * | 1996-05-28 | 1999-06-29 | Matsushita Electric Industrial Co, Ltd | Air/fuel ratio control apparatus that uses a neural network |
EP0962871A2 (en) * | 1998-06-02 | 1999-12-08 | Yamaha Hatsudoki Kabushiki Kaisha | Data estimation method in engine control |
WO2001000978A1 (en) | 1999-06-29 | 2001-01-04 | Heraeus Electro-Nite International N.V. | Method and apparatus for determining the a/f ratio of an internal combustion engine |
EP1854984A1 (en) * | 2006-05-10 | 2007-11-14 | HONDA MOTOR CO., Ltd. | Air-fuel ratio control system and method for internal combustion engine |
DE102013225768A1 (en) * | 2013-12-12 | 2015-06-18 | Robert Bosch Gmbh | Method and apparatus for determining a LOLIMOT model |
Non-Patent Citations (4)
Title |
---|
BARGHI F ET AL: "An intelligent control policy for fuel injection control of SI Engines (case study: CNG engine)", INTELLIGENT ENGINEERING SYSTEMS (INES), 2011 15TH IEEE INTERNATIONAL CONFERENCE ON, IEEE, 23 June 2011 (2011-06-23), pages 115 - 119, XP031893621, ISBN: 978-1-4244-8954-1, DOI: 10.1109/INES.2011.5954730 * |
FERESHTEH BARGHI ET AL: "Experimental validation of recurrent Neuro-Fuzzy Networks for AFR estimation and control in SI engines", COMPUTATIONAL INTELLIGENCE FOR MEASUREMENT SYSTEMS AND APPLICATIONS (CIMSA), 2011 IEEE INTERNATIONAL CONFERENCE ON, IEEE, 19 September 2011 (2011-09-19), pages 1 - 6, XP032065436, ISBN: 978-1-61284-924-9, DOI: 10.1109/CIMSA.2011.6059918 * |
M. HAFNER ET AL: "Fast neural networks for diesel engine control design", CONTROL ENGINEERING PRACTICE., vol. 8, no. 11, 1 November 2000 (2000-11-01), GB, pages 1211 - 1221, XP055295667, ISSN: 0967-0661, DOI: 10.1016/S0967-0661(00)00057-5 * |
ROLF ISERMANN: "Engine Modeling and Control", 14 July 2014, SPRINGER, ISBN: 978-3-642-39933-6, XP055295547 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR3086346A1 (en) * | 2018-09-26 | 2020-03-27 | Psa Automobiles Sa | METHOD AND DEVICE FOR PREDICTIVE ESTIMATION OF THE TEMPERATURE OF EXHAUST GASES FROM A VEHICLE HEAT ENGINE |
CN113239966A (en) * | 2021-04-14 | 2021-08-10 | 联合汽车电子有限公司 | Gas mixture deviation self-learning method and system, readable storage medium and electronic equipment |
CN113239966B (en) * | 2021-04-14 | 2024-03-01 | 联合汽车电子有限公司 | Mixed gas deviation self-learning method, system, readable storage medium and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
TW201708691A (en) | 2017-03-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10635976B2 (en) | Machine learning system for estimating a temperature of an exhaust purification catalyst | |
EP0326065B2 (en) | Controlling engine fuel injection | |
EP0582085A2 (en) | Fuel metering control system and cylinder air flow estimation method in internalcombustion engine | |
US7831371B2 (en) | Control apparatus for an internal combustion engine | |
US20080127938A1 (en) | Control device for internal combustion engine | |
CN110582628B (en) | Method for filtering and correcting oscillation of abundance signal from detector | |
US7735478B1 (en) | Method of calculating mass fraction burnt in an internal combustion engine based on rassweiler-withrow method for real-time applications | |
US9482169B2 (en) | Optimization-based controls for diesel engine air-handling systems | |
JP3610839B2 (en) | Air-fuel ratio control device for internal combustion engine | |
CN101755115A (en) | Abnormality detection device for internal combustion engine and air/fuel ratio control apparatus for internal combustion engine | |
US7099767B2 (en) | Control device for internal combustion engine | |
WO2016206920A1 (en) | An ecm to determine air-fuel ratio of an engine | |
US7069139B2 (en) | Control device for internal combustion engine | |
JP2007126997A (en) | Simulation method and simulation device for heat generation in cylinder | |
CN113417776B (en) | Flow measuring method and controller | |
JP5218166B2 (en) | Control device for internal combustion engine | |
Unver et al. | Modeling and validation of turbocharged diesel engine airpath and combustion systems | |
JP6234531B1 (en) | Internal combustion engine control device | |
JP3239575B2 (en) | Temperature prediction device and temperature control device for internal combustion engine | |
JP4492802B2 (en) | Air-fuel ratio control device | |
JP4661325B2 (en) | Control device for internal combustion engine | |
JP4577239B2 (en) | Method and apparatus for determining Wiebe function parameters | |
Lahti et al. | Dynamic engine control for HCCI combustion | |
Moreno et al. | FPGA Implementation of In-Cycle Closed-Loop Combustion Control Methods | |
Shiao et al. | Model-based cylinder-by-cylinder air-fuel ratio control for SI engines using sliding observers |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16725856 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 16725856 Country of ref document: EP Kind code of ref document: A1 |