Motorcycle engine control system

Abstract

The invention relates to a motorcycle engine control system which is characterized in that motorcycle engine driving data including working condition data and air-fuel ratio are acquired in real time; inputting the driving data into a preset tail gas emission analysis model, and predicting the concentration of harmful gas in the current tail gas; and constructing a generalized additive model to quantify a response relationship between the driving data and the concentration of the harmful gas in the tail gas, and controlling the air-fuel ratio of the current engine working condition according to the response relationship. The problem that in the prior art, the air-fuel ratio is difficult to accurately control according to different working conditions of an engine, so that the concentration of harmful gas is increased, and the environment is polluted is solved. A random forest model is constructed to serve as a tail gas emission analysis model, and the concentration of harmful gas emitted by tail gas is accurately predicted through engine working conditions. The problem that the nonlinear relationship between the driving data and the harmful gas concentration is difficult to quantify is solved by establishing the generalized additive model, so that the control precision of the air-fuel ratio of the engine under different working conditions is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of motorcycles and relates to a motorcycle engine control system. Background Art

[0002] Motorcycle engines produce various pollutants during operation, such as carbon monoxide (CO), nitrogen oxides (NO x ), etc. These pollutants not only cause serious harm to the environment, but also affect people's health. In traditional motorcycle engine technology, the control of the engine is relatively extensive, especially in air-fuel ratio control and ignition control.

[0003] In the past, motorcycle engines mostly used a relatively simple carburetor system to mix the mixture. This mechanical control method is difficult to accurately control the air-fuel ratio according to different engine operating conditions (such as speed, cylinder temperature, etc.). The carburetor mainly adjusts the fuel supply based on the vacuum suction during the intake process, but its adjustment accuracy for the intake volume and fuel volume is limited. For example, when the engine is cold started, the carburetor may provide an overly rich mixture to ensure that the engine can start smoothly, but as the engine temperature rises, this overly rich mixture is no longer suitable, which will lead to incomplete fuel combustion and increase pollutant emissions. Moreover, under complex operating conditions such as different loads, the carburetor cannot flexibly and accurately adjust the air-fuel ratio, so that the engine cannot operate at the optimal air-fuel ratio in many cases, causing energy waste and aggravating environmental pollution. Summary of the invention

[0004] In order to solve the above-mentioned problems existing in the prior art, the present invention provides a motorcycle engine control system, which aims to configure a suitable air-fuel ratio for the motorcycle engine under different operating conditions by establishing a response relationship model between the air-fuel ratio and the concentration of harmful gases in the exhaust gas under different engine operating conditions, thereby improving the control accuracy of the engine and reducing the emission of harmful gases.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The present application provides a motorcycle engine control system, including a driving data acquisition module, an exhaust emission analysis module and an air-fuel ratio control module, wherein the driving data acquisition module, the exhaust emission analysis module and the air-fuel ratio control module are communicatively connected, wherein:

[0007] The driving data acquisition module is used to collect the driving data of the motorcycle engine in real time, and the driving data includes working condition data and air-fuel ratio; the working condition data includes engine speed and engine cylinder temperature;

[0008] The exhaust gas emission analysis module is used to input the driving data into a preset exhaust gas emission analysis model to predict the concentration of harmful gases in the current exhaust gas;

[0009] The air-fuel ratio control module is used to construct a generalized additive model to quantify the response relationship between driving data and the concentration of harmful gases in exhaust gas, and control the air-fuel ratio of the current engine operating condition according to the response relationship.

[0010] Furthermore, in the driving data acquisition module, the engine speed is detected by an engine crankshaft speed sensor, the engine cylinder temperature is detected by a cylinder temperature sensor, and the air-fuel ratio is characterized by the oxygen concentration in the exhaust gas.

[0011] Furthermore, the exhaust emission analysis model includes the following construction steps:

[0012] S1. Collect historical motorcycle engine driving data and the corresponding harmful gas concentration in exhaust gas;

[0013] S2. Divide the data samples into different exhaust emission levels according to the concentration of harmful gases;

[0014] S3, using driving data as input features and exhaust emission levels as corresponding prediction labels, training a random forest model;

[0015] S4. The random forest model is used as an exhaust emission analysis model to determine the exhaust emission level under different driving data.

[0016] Furthermore, the generalized additive model includes the following construction steps:

[0017] T1. Data preparation: Collect the historical motorcycle engine driving data and the corresponding harmful gas concentration in the exhaust gas, and pre-process the collected data, which includes data cleaning and data standardization; the driving data is the response variable, and the harmful gas concentration in the exhaust gas is the explanatory variable;

[0018] T2. Model selection and setting: determine the distribution family and smooth function of the model response variable, the distribution family is configured as a normal distribution, and the smooth function is configured as a cubic spline function;

[0019] T3, model fitting: Substitute the preprocessed data into the selected generalized additive model form and use iterative weighted least squares method to fit the model;

[0020] T4, model evaluation and diagnosis: use evaluation indicators to judge the fitting effect of the model, and the evaluation indicators include mean square error, mean absolute error and determination coefficient;

[0021] T5. Model output: After the generalized additive model is established, the response relationship curve between the driving data and the concentration of harmful gases in the exhaust gas is output to determine the response relationship between the driving data and the concentration of harmful gases in the exhaust gas.

[0022] Furthermore, the generalized additive model is expressed as follows:

[0023] E(y)=μ+s(x1)+s(x2)+...+s(x i ),

[0024] Where, E(y) is the response variable, i.e., the concentration of harmful gases in the exhaust gas; μ is the intercept term; s(x i ) represents a smooth function; x1, x2, …, x i represents the explanatory variable, that is, the driving data.

[0025] Further, controlling the air-fuel ratio of the current engine operating condition according to the response relationship comprises the following steps:

[0026] E1. Set the concentration threshold of harmful gases according to relevant emission standards;

[0027] E2. Calculate the relative deviation between the current concentration of harmful gases in the exhaust gas and the harmful gas concentration threshold;

[0028] E3. When the relative deviation exceeds the set threshold, the air-fuel ratio control mode is turned on, specifically including:

[0029] Identify current engine operating condition data;

[0030] According to the response relationship between driving data and the concentration of harmful gases in exhaust gas, combined with the current working condition data, determine the appropriate air-fuel ratio data range;

[0031] According to the determined air-fuel ratio data range, the ratio of the intake air amount and the fuel amount is adjusted.

[0032] Furthermore, the relative deviation is calculated as follows:

[0033]

[0034] In the formula, R t is the relative deviation; A t is the concentration of harmful gases in the current exhaust gas; B t is the concentration threshold of harmful gases.

[0035] Furthermore, the air-fuel ratio control module also constructs an adaptive control model to coordinate the ignition advance angle and the air-fuel ratio according to different working conditions, specifically including:

[0036] Under acceleration conditions, the fuel injection amount is increased while the air-fuel ratio is increased, and the ignition advance angle is increased to provide power output;

[0037] Under idling conditions, the air-fuel ratio is controlled to be reduced to ensure stable engine operation and compliance with emission standards.

[0038] Furthermore, the adaptive control model includes the following construction steps:

[0039] P1. Working condition data collection: Collect the ignition advance angle data and air-fuel ratio data of the motorcycle engine under different working conditions;

[0040] P2. Determine the model architecture: take the operating condition data as input, and the ignition advance angle data and the air-fuel ratio data as output, and determine the adaptive control model, wherein the adaptive control model is configured as a neural network model or a fuzzy logic model;

[0041] P3, Model parameter estimation: According to the type of the selected model, the model parameters are initialized and set, specifically: for the neural network model, the connection weights and thresholds between neurons are initialized; for the fuzzy logic model, the membership function and rule base of the fuzzy set are determined;

[0042] P4. Model training: The model is trained by a specific training algorithm, and the model parameters are continuously adjusted so that the error between the model's prediction result of the training data and the actual output reaches a preset condition, wherein the training algorithm is specifically a back propagation algorithm for a neural network model and a fuzzy reasoning algorithm for a fuzzy logic model;

[0043] P5. Model evaluation and optimization: By calculating the error index between the predicted value and the actual value, the model's predictive ability and fitting effect on new data can be judged.

[0044] Furthermore, the air-fuel ratio control module also uses a real-time operating system to control the air-fuel ratio according to dynamic changes in motorcycle engine operating condition data.

[0045] Beneficial effects of the present invention:

[0046] (1) Real-time collection of motorcycle engine driving data, the driving data including operating condition data and air-fuel ratio; inputting the driving data into a preset exhaust emission analysis model to predict the current concentration of harmful gases in the exhaust; constructing a generalized additive model to quantify the response relationship between the driving data and the concentration of harmful gases in the exhaust, and controlling the air-fuel ratio of the current engine operating condition according to the response relationship. The present invention solves the problem that it is difficult to accurately control the air-fuel ratio according to different engine operating conditions in the prior art, thereby increasing the concentration of harmful gases and polluting the environment.

[0047] (2) By constructing a random forest model as an exhaust emission analysis model, the concentration of harmful gases in exhaust emissions can be accurately predicted using engine operating conditions, providing a basis for subsequent control of the air-fuel ratio.

[0048] (3) By establishing a generalized additive model, the problem of the nonlinear relationship between driving data and harmful gas concentration being difficult to quantify is solved, thereby improving the control accuracy of the air-fuel ratio under different engine operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0050] Figure 1 The figure is a structural diagram of a motorcycle engine control system in the present invention.

[0051] Figure 2 The flowchart of constructing an exhaust emission analysis model in one embodiment of the present invention.

[0052] Figure 3 The flowchart of constructing a generalized additive model in one embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0054] See also Figure 1-Figure 3 The present application provides a motorcycle engine control system, including a driving data acquisition module, an exhaust emission analysis module and an air-fuel ratio control module, wherein the driving data acquisition module, the exhaust emission analysis module and the air-fuel ratio control module are communicatively connected, wherein:

[0055] The driving data acquisition module is used to collect the driving data of the motorcycle engine in real time, and the driving data includes working condition data and air-fuel ratio; the working condition data includes engine speed and engine cylinder temperature;

[0056] In this embodiment, the driving data collection module plays a key role and is responsible for real-time collection of the driving data of the motorcycle engine. These data include working condition data (including engine speed and engine cylinder temperature) and air-fuel ratio. The engine speed can directly reflect the different operating states of the engine, such as power output and fuel consumption during idling, acceleration, and high-speed driving; the engine cylinder temperature is related to the engine performance, life, and exhaust emissions, and the requirements for mixed gas supply are different under different cylinder temperatures.

[0057] Furthermore, in the driving data acquisition module, the engine speed is detected by an engine crankshaft speed sensor, the engine cylinder temperature is detected by a cylinder temperature sensor, and the air-fuel ratio is characterized by the oxygen concentration in the exhaust gas.

[0058] In this embodiment, the engine speed is detected by means of an engine crankshaft speed sensor. The engine crankshaft speed sensor can accurately sense the rotation speed of the engine crankshaft. Since the crankshaft speed directly reflects the overall operating speed of the engine, the engine speed at each moment can be accurately obtained through the sensor. This data plays an extremely critical role in determining the current operating condition of the engine, such as idling, accelerating or driving at a constant speed, and also provides an important basis for subsequent system control and analysis.

[0059] The detection of engine cylinder temperature relies on cylinder temperature sensors. During the operation of the engine, the combustion of fuel will generate heat inside the cylinder, causing the cylinder temperature to change. The cylinder temperature sensor can monitor the temperature of the cylinder in real time, because the cylinder temperature not only affects the performance and life of the engine itself, but is also closely related to many aspects such as exhaust emissions. Therefore, accurate acquisition of cylinder temperature data is crucial for the entire engine control system to fully understand the working status of the engine.

[0060] As for the data collection of air-fuel ratio, an indirect characterization method is adopted here, that is, it is reflected by the oxygen concentration in the exhaust gas. The air-fuel ratio is the ratio of the air mass to the fuel mass in the mixture. When the mixture is burned, the oxygen concentration in the exhaust gas is closely related to the air-fuel ratio before combustion. If the air-fuel ratio of the mixture is appropriate and the combustion is sufficient, the oxygen concentration in the exhaust gas will be in a specific reasonable range; if the air-fuel ratio is too rich or too lean, the oxygen concentration in the exhaust gas will also be high or low accordingly. Therefore, by detecting the oxygen concentration in the exhaust gas, the current air-fuel ratio of the engine can be characterized to a certain extent, thereby providing data support for subsequent control based on the air-fuel ratio.

[0061] The exhaust gas emission analysis module is used to input the driving data into a preset exhaust gas emission analysis model to predict the concentration of harmful gases in the current exhaust gas;

[0062] In this embodiment, the preset exhaust emission analysis model is constructed based on a large amount of experimental data, theoretical research, and a deep understanding of the operating characteristics of motorcycle engines and the laws of exhaust emissions. It contains complex mathematical relationships and algorithmic logic, and can simulate the actual combustion process of the engine and the exhaust gas generation under the current working conditions based on different combinations of input driving data, and then accurately predict the concentration level of harmful gases such as carbon monoxide, nitrogen oxides, hydrocarbons, etc. in the exhaust gas under this working condition. Specifically, the exhaust emission analysis model includes the following construction steps:

[0063] Step S1: Data collection:

[0064] First, we need to conduct extensive data collection. We need to collect historical motorcycle engine driving data and the corresponding harmful gas concentration data in exhaust gas. These driving data cover various information such as engine speed, engine cylinder temperature, and air-fuel ratio represented by oxygen concentration in exhaust gas. By accumulating a large amount of actual data under different working conditions, we can provide a rich and real material basis for the construction of subsequent models, so as to fully and accurately reflect the relationship between motorcycle engines and exhaust emissions under various operating conditions.

[0065] Step S2: Data division:

[0066] After obtaining a large number of data samples, these data samples are classified and divided according to the concentration of harmful gases in the exhaust gas, and divided into different exhaust emission levels. This division method helps to more clearly sort out the characteristic differences of engine driving data under different emission levels, so that the subsequent model can better capture the inherent connection between different emission conditions and driving data during the learning process, thereby improving the accuracy and pertinence of the model's prediction of exhaust emissions.

[0067] Step S3: Model training:

[0068] The sorted driving data is used as input features, and the classified exhaust emission levels are used as corresponding prediction labels. The random forest model is trained using these data. The random forest model is an ensemble learning model based on decision trees. It improves the accuracy and stability of predictions by building multiple decision trees and combining their prediction results. During the training process, the model will continuously learn the mapping relationship between the input driving data features and the exhaust emission levels, and gradually adjust its own parameters to better fit the data, so that it has the ability to accurately predict the exhaust emission levels based on the given driving data.

[0069] Step S4: Model application:

[0070] After sufficient training, the random forest model is determined as an exhaust emission analysis model, which can be used to determine the exhaust emission level under different driving data. When new motorcycle engine driving data is input into the model, it can quickly output the corresponding exhaust emission level based on the previously learned rules and relationships, thereby providing a strong basis for judging the current motorcycle exhaust emission status, so as to take corresponding measures to control exhaust emissions, such as adjusting the air-fuel ratio, and realizing effective management of motorcycle exhaust emissions.

[0071] The air-fuel ratio control module is used to construct a generalized additive model to quantify the response relationship between driving data and the concentration of harmful gases in exhaust gas, and control the air-fuel ratio of the current engine operating condition according to the response relationship.

[0072] In this embodiment, the air-fuel ratio control module mainly achieves effective control of exhaust emissions by constructing a generalized additive model. First, the generalized additive model takes various types of driving data as input, which include engine speed, engine cylinder temperature, and air-fuel ratio characterized by oxygen concentration in exhaust gas, and outputs the concentration of harmful gases in exhaust gas. By analyzing and fitting a large number of relevant data collected in historical periods, the model can accurately capture the complex and nonlinear response relationship between driving data and harmful gas concentration. Secondly, when the motorcycle is actually running, the driving data acquisition module collects the latest driving data of the engine in real time and passes it into the generalized additive model. The model quickly calculates the predicted value of the harmful gas concentration under the current working condition based on the quantified response relationship. Then, if the predicted value shows that the harmful gas concentration is higher than the preset threshold, it indicates that there may be a problem with the current air-fuel ratio and it needs to be adjusted. At this time, the air-fuel ratio control module will operate with the help of relevant actuators, such as the fuel injection system. For example, if the carbon monoxide concentration in the exhaust gas is too high, it may mean that the mixture is too rich, that is, the air-fuel ratio is too small. The module will instruct the fuel injection system to reduce the fuel injection amount, increase the air-fuel ratio, and promote complete combustion of the mixture, thereby reducing the concentration of harmful gases.

[0073] Among them, the generalized additive model (GAM) is a statistical model used to analyze the nonlinear relationship between variables. The following introduces its principles and construction steps:

[0074] Principle: The generalized additive model is an extension of the traditional linear regression model. Traditional linear regression assumes that there is a simple linear relationship between the dependent variable and the independent variable, and describes the relationship between them by fitting a straight line. However, in reality, the relationship between many variables is not a simple linear relationship. The generalized additive model breaks through this limitation and allows nonlinear relationships between dependent and independent variables. The basic idea is to express the expectation of the dependent variable as the sum of some smooth functions of the independent variables, and to capture various nonlinear relationships that may exist between the independent and dependent variables through these smooth functions.

[0075] Build steps:

[0076] T1. Data preparation:

[0077] Collect relevant data samples. For the example of motorcycle engine control system, it means collecting driving data including engine speed, engine cylinder temperature, air-fuel ratio as independent variables (explanatory variables), and the corresponding harmful gas concentration in exhaust as dependent variable (response variable). These data should be representative and sufficient in quantity to cover the engine under various working conditions.

[0078] The collected data are preprocessed, including data cleaning (removing outliers, processing missing values, etc.), data standardization (converting variables of different magnitudes into forms with similar scales for better model fitting), and other operations to ensure the quality and availability of the data.

[0079] T2. Model selection and setting:

[0080] Determine the specific form of the generalized additive model to be used. Depending on the characteristics of the data and the purpose of the study, different distribution families can be selected to fit the dependent variable, such as normal distribution, Poisson distribution, binomial distribution, etc., depending on the nature of the dependent variable (such as continuous, count, binary, etc.).

[0081] Select a method for estimating a smooth function, commonly spline functions (such as cubic spline), local polynomial regression, etc. These methods can generate smooth function curves by locally fitting the data to capture the nonlinear relationship between the independent variable and the dependent variable.

[0082] T3. Model fitting:

[0083] Substitute the preprocessed data into the selected generalized additive model form and use a suitable algorithm to fit the model. Commonly used fitting algorithms include iterative reweighted least squares (IRLS), which optimizes the model parameters through continuous iteration so that the model can best fit the data, that is, minimize the difference between the predicted value and the actual value (such as indicators such as the residual sum of squares).

[0084] T4. Model evaluation and diagnosis:

[0085] Some evaluation indicators are used to judge the fitting effect of the model, such as mean square error (MSE), mean absolute error (MAE), determination coefficient (R 2 ) etc. These indicators can reflect the degree of fit of the model to the data from different perspectives. The smaller the value (for MSE and MAE) or the larger the value (for R 2 ) indicates that the model fits better.

[0086] Perform model diagnosis to check whether the model is overfitting or underfitting. Overfitting means that the model fits the training data too perfectly, but performs poorly on new data; underfitting means that the model does not fully capture the patterns in the data, and the fitting effect is not good for both training data and new data. You can use methods such as cross-validation to determine whether the model has these problems, and adjust the model based on the diagnosis results, such as increasing or decreasing the complexity of the model.

[0087] T5. Model output:

[0088] When the generalized additive model is established, the response relationship curve between different driving data such as engine speed, cylinder temperature and air-fuel ratio and the concentration of harmful gases is output to determine the response relationship between the driving data and the concentration of harmful gases in the exhaust gas.

[0089] Furthermore, the generalized additive model is expressed as follows:

[0090] E(y)=μ+s(x1)+s(x2)+...+s(x i ),

[0091] Where, E(y) is the response variable, i.e., the concentration of harmful gases in the exhaust gas; μ is the intercept term; s(x i ) represents a smooth function; x1, x2, …, x i represents the explanatory variable, that is, the driving data.

[0092] Further, controlling the air-fuel ratio of the current engine operating condition according to the response relationship comprises the following steps:

[0093] Step E1: Setting the hazardous gas concentration threshold

[0094] This step is an important basis for the entire air-fuel ratio control process. Relevant departments will formulate corresponding emission standards based on environmental protection requirements and the actual operating characteristics of motorcycle engines. These standards clearly stipulate the maximum concentration values ​​of various harmful gases (such as carbon monoxide, nitrogen oxides, hydrocarbons, etc.) allowed to be emitted in exhaust gas.

[0095] In the motorcycle engine control system, the maximum allowable concentration of each type of harmful gas will be set as the harmful gas concentration threshold according to these authoritative emission standards. For example, the concentration threshold of carbon monoxide is set to a specific value (such as X ppm), and that of nitrogen oxides is set to another value (such as Y ppm). These thresholds will serve as key reference standards for subsequent judgments on whether the engine exhaust emissions meet the standards.

[0096] Step E2: Calculate relative deviation

[0097] During the actual operation of the motorcycle, the exhaust emission analysis module can be used to obtain the actual concentration values ​​of various harmful gases in the current exhaust in real time.

[0098] Then, for each harmful gas, its current actual concentration is compared with the corresponding harmful gas concentration threshold set in step E1 to calculate the relative deviation between the two. The calculation formula of the relative deviation is usually: (current harmful gas concentration-harmful gas concentration threshold) / harmful gas concentration threshold×100%. By calculating the relative deviation, we can intuitively understand the degree of deviation of the current harmful gas concentration in the exhaust gas compared with the standard threshold, thereby providing a quantitative basis for the subsequent judgment of whether the air-fuel ratio control mode needs to be turned on.

[0099] Step E3: Start the air-fuel ratio control mode and specific operations

[0100] Start-up condition judgment: When the calculated relative deviation for one or more harmful gases exceeds the set threshold (this set threshold is also determined based on comprehensive consideration of multiple factors such as engine performance and emission control), it means that the current engine exhaust emissions do not meet the requirements and the air-fuel ratio needs to be adjusted. At this time, the air-fuel ratio control mode is turned on.

[0101] Identify engine operating data: After turning on the air-fuel ratio control mode, the first thing to do is to accurately identify the current engine operating data. These operating data include engine speed, engine cylinder temperature, etc., which are collected in real time through corresponding sensors (such as engine crankshaft speed sensor, cylinder temperature sensor, etc.). Accurately grasping the engine operating data is crucial for determining the appropriate air-fuel ratio in the future, because the engine has different requirements for air-fuel ratio under different operating conditions.

[0102] Determine the appropriate air-fuel ratio data range: Based on the response relationship between the previously constructed driving data (such as engine speed, engine cylinder temperature, air-fuel ratio characterized by oxygen concentration in exhaust gas, etc.) and the concentration of harmful gases in exhaust gas, combined with the currently identified engine operating condition data, a comprehensive analysis is performed to determine the appropriate air-fuel ratio data range under the current operating condition. For example, when the engine is at a certain speed and cylinder temperature, if the carbon monoxide concentration in the exhaust gas is too high, the response relationship analysis shows that the air-fuel ratio may need to be increased, so a corresponding appropriate increased air-fuel ratio data range can be determined.

[0103] Adjust the ratio of intake air volume and fuel volume: Finally, adjust the ratio of intake air volume and fuel volume according to the determined air-fuel ratio data range. The air-fuel ratio is essentially the proportional relationship between intake air volume and fuel volume. If it is determined that the air-fuel ratio needs to be increased, it means increasing the intake air volume or reducing the fuel volume. In actual operation, this is usually achieved by controlling the engine's intake system (such as throttle and other components) and fuel injection system. For example, by adjusting the opening of the throttle to increase the intake air volume, or by controlling the fuel injector to reduce the fuel injection volume, the ratio of intake air volume and fuel volume can reach the determined appropriate air-fuel ratio data range, thereby reducing the concentration of harmful gases in the exhaust gas and making the engine exhaust emissions meet the relevant standards.

[0104] Furthermore, the relative deviation is calculated as follows:

[0105]

[0106] In the formula, R t is the relative deviation; A t is the concentration of harmful gases in the current exhaust gas; B t is the concentration threshold of harmful gases.

[0107] Furthermore, the air-fuel ratio control module also constructs an adaptive control model to coordinate the ignition advance angle and the air-fuel ratio according to different working conditions, specifically including:

[0108] Under acceleration conditions, the fuel injection amount is increased and the ignition advance angle is enlarged to provide strong power output;

[0109] Under idle conditions, the air-fuel ratio is precisely controlled to ensure stable engine operation and compliance with emission standards.

[0110] In this embodiment, the adaptive control model aims to perform intelligent and coordinated control of the two key parameters, ignition advance angle and air-fuel ratio, according to different operating conditions of the engine, so as to achieve the best performance of the engine under various operating conditions while meeting emission requirements.

[0111] The core principle of this model is based on an in-depth understanding and analysis of the characteristics and requirements of the engine under different working conditions. Through a large number of tests, data collection and precise grasp of the engine operating principles, the influence of changes in ignition advance angle and air-fuel ratio on engine power output, fuel economy and exhaust emissions under different working conditions has been clarified, and then based on this, a control logic that can automatically adapt to different working conditions has been constructed.

[0112] When the motorcycle is accelerating, the engine needs to quickly increase power output to meet the needs of vehicle acceleration. At this time, the adaptive control model will trigger the corresponding control strategy:

[0113] Increase fuel injection amount: During acceleration, the engine speed rises rapidly, and the demand for energy increases sharply. In order to provide enough fuel for full combustion, thereby releasing more energy to drive the vehicle to accelerate, the adaptive control model will instruct the fuel injection system to increase the fuel injection amount. This ensures that there is enough fuel in the cylinder to mix with the air to form a combustible mixture, laying a material foundation for strong power output.

[0114] Adjust the ignition advance angle: At the same time, it is not enough to simply increase the amount of fuel injection, and the ignition advance angle needs to be adjusted reasonably. The ignition advance angle refers to the advance angle of the spark plug ignition timing relative to the piston reaching the top dead center. Under acceleration conditions, properly advancing the ignition timing (i.e. increasing the ignition advance angle) can allow the mixture to start burning before the piston reaches the top dead center, so that the pressure generated by the combustion can more effectively push the piston downward, thereby improving the power output efficiency of the engine. By accurately adjusting the ignition advance angle, the combustion process can be more coordinated with the mechanical movement of the engine, further enhancing the power performance of the engine during acceleration.

[0115] In the idling condition, the engine only needs to maintain its basic operation, and the control focus at this time is completely different from that in the acceleration condition:

[0116] Fine control of the air-fuel ratio: When idling, the engine speed is low and the fuel consumption is relatively low, but the control requirements for the air-fuel ratio are more precise. Because if the air-fuel ratio is out of balance, it may cause unstable engine operation, jitter or even flameout, and also affect exhaust emissions. The adaptive control model will accurately control the air-fuel ratio within a suitable range that can ensure stable engine operation and meet exhaust emissions by adjusting the fuel injection amount based on the real-time collected engine operation data (such as engine cylinder temperature, intake volume, etc.). For example, at idle, a relatively lean mixture is usually required to reduce the emission of pollutants such as carbon monoxide, while ensuring that the engine can run smoothly.

[0117] Through such targeted control strategies, under different working conditions, the adaptive control model can effectively coordinate the ignition advance angle and air-fuel ratio, so that the motorcycle engine can maintain good operating stability and environmental performance while meeting the power output requirements.

[0118] Furthermore, the adaptive control model includes the following construction steps:

[0119] Step 1: Working condition data collection and analysis:

[0120] Extensive collection of data under different operating conditions: Collect detailed data of motorcycle engines under various actual operating conditions, including idling, acceleration, deceleration, constant speed driving, climbing, etc. For each operating condition, the data that needs to be recorded include engine speed, engine cylinder temperature, intake volume, throttle opening, load conditions, and corresponding ignition advance angle, air-fuel ratio setting, and exhaust emission indicators. By installing high-precision sensors on multiple motorcycles and collecting data for a long time under different driving scenarios, it is ensured that the collected data is comprehensive and representative, and can truly reflect the actual operating status of the engine under different operating conditions.

[0121] Analyze the relationship between operating condition characteristics and parameters: Conduct in-depth analysis of a large amount of collected data on different operating conditions, and study the operating characteristics of the engine under various operating conditions, as well as the intrinsic relationship between key parameters such as ignition advance angle, air-fuel ratio, and other operating data. For example, under acceleration conditions, observe the changing trend of the intake volume, how the fuel injection volume is adjusted, and the impact of this adjustment on the ignition advance angle and air-fuel ratio when the engine speed rises rapidly, and analyze the relationship between these parameter changes and power output and exhaust emissions; under idling conditions, explore the stability of the cylinder temperature, the control method of the intake volume, and the effect of fine adjustment of the air-fuel ratio and ignition advance angle on engine stability and emissions when the engine maintains low speed operation. Through this meticulous analysis, the mutual influence between the parameters under different operating conditions is sorted out, providing a solid theoretical foundation for subsequent model construction.

[0122] Step 2: Determine the model architecture:

[0123] Choose the appropriate model type: Based on the analysis of operating data and the needs of engine control, select a suitable mathematical model as the basic architecture of the adaptive control model. Common choices include neural network models, fuzzy logic models, or rule-based expert system models. For example, the neural network model has a strong nonlinear mapping capability and can well capture the complex nonlinear relationship between engine operating parameters; the fuzzy logic model is good at dealing with situations with ambiguity and uncertainty, and is more suitable for the fuzzy description of engine operating conditions and the fuzzy formulation of control decisions; the rule-based expert system model can construct control logic based on existing professional knowledge and empirical rules, which is suitable for situations where there are clear rules for engine control.

[0124] Define model input and output: Determine the input and output variables of the selected model. In this adaptive control model, the input variables usually include real-time collected engine operating data such as engine speed, engine cylinder temperature, intake volume, throttle opening, load conditions, etc. These data can fully describe the current working state of the engine. The output variables are set as the ignition advance angle and air-fuel ratio, two key parameters that need to be controlled and adjusted. By clarifying the input and output of the model, the model construction has a clear goal and direction, which is convenient for subsequent parameter estimation and model training.

[0125] Step 3: Model parameter estimation and training:

[0126] Initialize model parameters: Initialize the parameters of the model according to the type of model selected. For example, for a neural network model, you need to initialize the connection weights and thresholds between neurons; for a fuzzy logic model, you need to determine the membership function of the fuzzy set, the rule base and other parameters. The settings of these initial parameters are usually based on some empirical values ​​or random assignments, but they will be continuously optimized and adjusted during the subsequent training process.

[0127] Training with data: Divide the collected data of various working conditions into training sets and test sets according to a certain ratio. First, use the training set to train the model, take the engine operation data in the training set as input, and the corresponding ignition advance angle and air-fuel ratio as output, so that the model can learn the relationship between the input data and the output data. During the training process, the parameters of the model are continuously adjusted through specific training algorithms (such as back propagation algorithm for neural network models, fuzzy inference algorithm for fuzzy logic models, etc.), so that the error between the model's prediction results of the training data and the actual output is as small as possible. For example, for the neural network model, the connection weights and thresholds between neurons are continuously updated through the back propagation algorithm to minimize the sum of squares of the error between the ignition advance angle and air-fuel ratio output by the model and the actual ignition advance angle and air-fuel ratio.

[0128] Step 4: Model evaluation and optimization:

[0129] Use the test set to evaluate the model: After the model has been trained for a certain number of rounds, use the reserved test set to evaluate the trained model. Input the engine operation data in the test set into the trained model to obtain the ignition advance angle and air-fuel ratio predicted by the model, and then compare them with the actual ignition advance angle and air-fuel ratio in the test set. By calculating the error index (such as mean square error, mean absolute error, etc.) between the predicted value and the actual value, the model's prediction ability and fitting effect on new data can be judged. If the error index is too large, it means that the model may be overfitting or underfitting, and the model needs to be further optimized.

[0130] Optimize model performance: Based on the evaluation results, if the model is found to have overfitting or underfitting problems, take appropriate measures to optimize it. For overfitting problems, it can be solved by increasing training data, adjusting model complexity (such as reducing the number of layers or neurons in the neural network), and using regularization technology; for underfitting problems, it can be improved by increasing model complexity (such as increasing the number of layers or neurons in the neural network), improving training algorithms, and extending training time. Through continuous evaluation and optimization, ensure that the model has good predictive ability and fitting effect, and can accurately predict the ignition advance angle and air-fuel ratio based on the engine operation data to meet the requirements of the engine control system.

[0131] Furthermore, the air-fuel ratio control module also uses a real-time operating system to control the air-fuel ratio according to dynamic changes in motorcycle engine operating condition data.

[0132] In this embodiment, the real-time operating system (RTOS) plays an extremely critical role. The primary feature of RTOS is excellent real-time performance. The working conditions of motorcycle engines change all the time, and the air-fuel ratio needs to be adjusted in real time. RTOS ensures that the entire process can be completed in a very short time, from collecting working condition data such as engine speed, cylinder temperature, and intake volume, to analyzing and processing and making air-fuel ratio adjustment decisions, and then transmitting control instructions to actuators such as the fuel injection system. For example, when the engine accelerates, it can respond quickly and adapt the air-fuel ratio to the new working conditions in just a few milliseconds to avoid problems such as power and emissions. Its task scheduling and priority management are efficient. Air-fuel ratio control involves multiple tasks such as data collection, analysis, and instruction sending. RTOS assigns priorities based on the importance and urgency of the task. Tasks such as timely adjusting the air-fuel ratio based on the latest working conditions will receive high priority because of their great impact on engine performance and emissions. When multiple tasks are requested to be executed at the same time, high-priority tasks are processed first to ensure that key links are not delayed and precise control is achieved. In terms of resource allocation management, RTOS performs well. The resources of the motorcycle engine control system are limited, and it reasonably allocates processor computing power, memory space, etc. Data collection requires temporary storage of data in memory, which ensures its smooth progress and also ensures that other tasks obtain resources to maintain a smooth control process. RTOS also has high reliability and stability. Engine operation is susceptible to electromagnetic interference, etc., and it responds through fault-tolerant mechanisms and data protection measures. Data transmission errors can be verified and corrected. When sensors or actuators fail, they can be handled according to preset mechanisms, such as switching spare parts or adjusting strategies, to ensure safe and stable operation of the engine and effective control of the air-fuel ratio. In short, RTOS provides a solid guarantee for the air-fuel ratio control of motorcycle engines.

[0133] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A motorcycle engine control system, characterized in that: It includes a driving data acquisition module, an exhaust emission analysis module and an air-fuel ratio control module, which are communicatively connected to each other, wherein: The driving data acquisition module is used to collect the driving data of the motorcycle engine in real time, and the driving data includes working condition data and air-fuel ratio; the working condition data includes engine speed and engine cylinder temperature; The exhaust gas emission analysis module is used to input the driving data into a preset exhaust gas emission analysis model to predict the concentration of harmful gases in the current exhaust gas; The air-fuel ratio control module is used to construct a generalized additive model to quantify the response relationship between driving data and the concentration of harmful gases in exhaust gas, and control the air-fuel ratio of the current engine operating condition according to the response relationship.

2. A motorcycle engine control system according to claim 1, characterized in that: In the driving data acquisition module, the engine speed is detected by an engine crankshaft speed sensor, the engine cylinder temperature is detected by a cylinder temperature sensor, and the air-fuel ratio is characterized by the oxygen concentration in the exhaust gas.

3. A motorcycle engine control system according to claim 1, characterized in that: The exhaust emission analysis model includes the following construction steps: S1. Collect historical motorcycle engine driving data and the corresponding harmful gas concentration in exhaust gas; S2. Divide the data samples into different exhaust emission levels according to the concentration of harmful gases; S3, using driving data as input features and exhaust emission levels as corresponding prediction labels, training a random forest model; S4. The random forest model is used as an exhaust emission analysis model to determine the exhaust emission level under different driving data.

4. A motorcycle engine control system according to claim 1, characterized in that: The generalized additive model includes the following construction steps: T1. Data preparation: Collect the historical motorcycle engine driving data and the corresponding harmful gas concentration in the exhaust gas, and pre-process the collected data, which includes data cleaning and data standardization; the driving data is the response variable, and the harmful gas concentration in the exhaust gas is the explanatory variable; T2. Model selection and setting: determine the distribution family and smooth function of the model response variable, the distribution family is configured as a normal distribution, and the smooth function is configured as a cubic spline function; T3, model fitting: Substitute the preprocessed data into the selected generalized additive model form and use iterative weighted least squares method to fit the model; T4, model evaluation and diagnosis: use evaluation indicators to judge the fitting effect of the model, and the evaluation indicators include mean square error, mean absolute error and determination coefficient; T5. Model output: After the generalized additive model is established, the response relationship curve between the driving data and the concentration of harmful gases in the exhaust gas is output to determine the response relationship between the driving data and the concentration of harmful gases in the exhaust gas.

5. A motorcycle engine control system according to claim 1, characterized in that: The generalized additive model is expressed as follows: E(y)=μ+s(x1)+s(x2)+...+s(x i ), Where, E(y) is the response variable, i.e., the concentration of harmful gases in the exhaust gas; μ is the intercept term; s(x i ) represents a smooth function; x1, x2, …, x i represents the explanatory variable, that is, the driving data.

6. A motorcycle engine control system according to claim 1, characterized in that: The controlling of the air-fuel ratio of the current engine operating condition according to the response relationship comprises the following steps: E1. Set the concentration threshold of harmful gases according to relevant emission standards; E2. Calculate the relative deviation between the current concentration of harmful gases in the exhaust gas and the harmful gas concentration threshold; E3. When the relative deviation exceeds the set threshold, the air-fuel ratio control mode is turned on, specifically including: Identify current engine operating condition data; According to the response relationship between driving data and the concentration of harmful gases in exhaust gas, combined with the current working condition data, determine the appropriate air-fuel ratio data range; According to the determined air-fuel ratio data range, the ratio of the intake air amount and the fuel amount is adjusted.

7. A motorcycle engine control system according to claim 6, characterized in that: The relative deviation is calculated as follows: In the formula, R t is the relative deviation; A t is the concentration of harmful gases in the current exhaust gas; B t is the concentration threshold of harmful gases.

8. A motorcycle engine control system according to claim 1, characterized in that: The air-fuel ratio control module also constructs an adaptive control model to coordinate the ignition advance angle and the air-fuel ratio according to different working conditions, specifically including: Under acceleration conditions, the fuel injection amount is increased while the air-fuel ratio is increased, and the ignition advance angle is increased to provide power output; Under idling conditions, the air-fuel ratio is controlled to be reduced to ensure stable engine operation and compliance with emission standards.

9. A motorcycle engine control system according to claim 8, characterized in that: The adaptive control model includes the following construction steps: P1. Working condition data collection: Collect the ignition advance angle data and air-fuel ratio data of the motorcycle engine under different working condition data; P2. Determine the model architecture: take the operating condition data as input, and the ignition advance angle data and the air-fuel ratio data as output, and determine the adaptive control model, wherein the adaptive control model is configured as a neural network model or a fuzzy logic model; P3, Model parameter estimation: According to the type of the selected model, the model parameters are initialized and set, specifically: for the neural network model, the connection weights and thresholds between neurons are initialized; for the fuzzy logic model, the membership function and rule base of the fuzzy set are determined; P4. Model training: The model is trained by a specific training algorithm, and the model parameters are continuously adjusted so that the error between the model's prediction result of the training data and the actual output reaches a preset condition, wherein the training algorithm is specifically a back propagation algorithm for a neural network model and a fuzzy reasoning algorithm for a fuzzy logic model; P5. Model evaluation and optimization: By calculating the error index between the predicted value and the actual value, the model's predictive ability and fitting effect on new data can be judged.

10. A motorcycle engine control system according to claim 1, characterized in that: The air-fuel ratio control module also uses a real-time operating system to control the air-fuel ratio according to dynamic changes in the motorcycle engine operating condition data.

Images