Pre-judgment engine combustion optimization control method and system

Abstract

The application discloses a pre-judgment type engine combustion optimization control method and system, and relates to the field of engine control, and comprises the following steps: S1, acquiring road condition data and collecting vehicle body operation data in real time; S2, fusing the road condition data and the vehicle body operation data, extracting key characteristic parameters, outputting a working condition type of a future first preset time length based on a working condition pre-judgment model, and generating a pre-judgment working condition; S3, constructing a user driving habit database based on vehicle body operation historical data, and dynamically optimizing the characteristic weight of the working condition pre-judgment model and a combustion parameter matching coefficient; S4, outputting a control signal in advance according to the pre-judgment working condition and the optimized combustion parameter matching coefficient, and adjusting the combustion parameter of the engine; and S5, comparing the pre-judgment working condition and an actual working condition in real time, correcting the combustion parameter when a deviation exceeds a preset deviation threshold, and feeding back the deviation data to optimize the working condition pre-judgment model. Through collaborative design, the pre-judgment type optimization of the engine combustion system is realized.

Description

Technical Field

[0001] This invention relates to the field of engine control, and more particularly to a predictive engine combustion optimization control method and a predictive engine combustion optimization control system. Background Technology

[0002] As the automotive industry moves towards energy conservation and environmental protection, optimizing the fuel economy of engine combustion systems has become a core focus. Current combustion control methods are mainly real-time feedback and fixed-parameter methods, which have significant drawbacks: First, real-time feedback suffers from adjustment lag, leading to incomplete combustion and significant fuel waste during sudden changes in operating conditions; second, predictive solutions focus on overall control, lacking specificity for combustion optimization, and some even lack predictive capabilities for operating conditions; third, they lack personalized adaptation, as uniform parameters cannot meet the needs of different driving habits; and fourth, the absence of an emergency correction mechanism means that predictive errors can easily lead to combustion instability, limiting fuel economy improvements. Summary of the Invention

[0003] The purpose of this invention is to provide a predictive engine combustion optimization control method and a predictive engine combustion optimization control system, which solves at least one of a number of technical problems.

[0004] Key technical challenges: addressing issues such as delayed combustion parameter adjustments and fuel waste during sudden changes in operating conditions, and overcoming the shortcomings of real-time feedback delays in related patents; addressing the issues of insufficient targeting, cloud reliance, and system complexity in predictive combustion optimization solutions, and achieving localized, lightweight predictive analysis; addressing the lack of personalized adaptation to driving habits; and addressing the issues of combustion instability caused by the absence of emergency correction mechanisms and predictive biases.

[0005] This invention provides the following solution: According to a first aspect of the present invention, a predictive engine combustion optimization control method is provided, comprising the following steps: S1: Acquire road condition data and collect vehicle operation data in real time; S2 integrates road condition data and vehicle operation data, extracts key feature parameters, and outputs the working condition type for the first preset duration (3~5 seconds) based on the working condition prediction model, generating the predicted working condition. S3 builds a user driving habit database based on vehicle operation history data and dynamically optimizes the feature weights and combustion parameter matching coefficients of the operating condition prediction model. S4, based on the predicted operating conditions and the optimized combustion parameter matching coefficient, outputs a control signal in advance to adjust the engine's combustion parameters; S5 compares the predicted operating conditions with the actual operating conditions in real time. When the deviation exceeds the preset deviation threshold, it corrects the combustion parameters and feeds back the deviation data to optimize the operating condition prediction model.

[0006] Furthermore, including: In step S1, the road condition data includes gradient, road condition type, and traffic light information; Vehicle operating data includes vehicle speed, throttle opening, brake signal, torque, and engine speed; In step S2, based on the road condition data and vehicle operation data from step S1, the key feature parameters extracted include vehicle speed change rate, gradient value, throttle opening change rate, and traffic light countdown. The operating conditions are set as acceleration, deceleration, constant speed, and climbing.

[0007] Furthermore, including: In step S3, the vehicle's historical operating data includes the number of times it accelerates rapidly, the number of times it brakes suddenly, the percentage of time it travels at a constant speed, and the throttle opening habit data under different slopes. Based on historical vehicle operation data, a gradient descent algorithm is used for optimization. Every time a preset mileage (1000km) is accumulated, the feature weights of the operating condition prediction model and the matching coefficient of combustion parameters are automatically updated.

[0008] Furthermore, including: In step S4, a control signal is output 2-3 seconds in advance for a second preset time period to adjust the engine's combustion parameters, including: When anticipating acceleration conditions, increase the injection pressure above 350 bar, advance the injection time by 10° and 30°CA, advance the ignition time by 2° and 3°CA, and increase the intake air volume by 10% and 15%. When anticipating deceleration conditions, reduce the injection pressure to below 250 bar, delay the injection timing by 10° to 30°CA, delay the ignition timing by 1° to 2°CA, and reduce the intake air volume by 5% to 10%. When anticipating climbing conditions, increase the fuel injection pressure to above 350 bar, advance the fuel injection timing by 20° to 40°CA, advance the ignition timing by 3° to 4°CA, and increase the intake air volume by 15% to 20%. When anticipating a constant-speed operating condition, maintain the current combustion parameters unchanged.

[0009] Furthermore, including: Step S5, when the deviation exceeds a preset threshold, includes correcting the combustion parameters as follows: With a vehicle speed change rate deviation ≥10km / h s is used as the preset deviation threshold; When the deviation exceeds the preset deviation threshold, the combustion parameters will be immediately adjusted to the optimal value corresponding to the actual operating conditions. The control index for adjusting the combustion parameters to the optimal value corresponding to the actual operating conditions is set to a third preset duration of no more than (0.1 seconds); If the combustion parameters fail to be adjusted to the optimal value corresponding to the actual operating conditions within the third preset time (0.1 seconds), the condition judgment for switching the control mode will be initiated. The conditions for switching control modes include: if the deviation exceeds the preset deviation threshold for more than the fourth preset duration (2 seconds), the current operation mode of adjusting engine combustion parameters by outputting control signals in advance will be exited and the operation mode of adjusting engine combustion parameters by outputting control signals in normal mode will be switched.

[0010] According to a second aspect of the present invention, a predictive engine combustion optimization control system is provided, comprising a navigation module, a vehicle body sensor group, an on-board ECU, and an engine combustion system; The navigation module and the vehicle sensor group are respectively connected to the input of the vehicle ECU, and the output of the vehicle ECU controls the engine combustion system. The vehicle ECU has a built-in operating condition prediction module, machine learning adaptation module, combustion parameter control module, and emergency correction module; The input end of the working condition prediction module receives road condition data output from the navigation module and vehicle operation data output from the vehicle sensor group, and the output end outputs the predicted working condition to the combustion parameter control module and the emergency correction module. The machine learning adaptation module receives historical vehicle operation data from the vehicle sensor group and deviation data from the emergency correction module as inputs. Its outputs are connected to the operating condition prediction module and the combustion parameter control module, respectively, to output optimized feature weights and combustion parameter matching coefficients. The combustion parameter control module receives the predicted operating conditions, combustion parameter matching coefficients, and parameter correction signals output by the emergency correction module at its input end, and outputs combustion control signals to the engine combustion system at its output end. The emergency correction module's input end receives the predicted operating conditions and the real-time vehicle operation data output by the vehicle's sensor group. Its output end is connected to the combustion parameter control module and the machine learning adaptation module, respectively, to output parameter correction signals and deviation data.

[0011] Furthermore, including: The working condition prediction module has a built-in working condition prediction model; Road condition data includes gradient, road condition type and traffic light information; vehicle operation data includes vehicle speed, throttle opening, brake signal, torque and speed. The condition prediction module is used to extract key feature parameters such as vehicle speed change rate, gradient value, throttle opening change rate and traffic light countdown, and output the condition type of acceleration, deceleration, constant speed and climbing conditions for the first preset duration (3~5 seconds) in the future.

[0012] Furthermore, including: The machine learning adaptation module has a built-in user driving habit database, which stores vehicle operation history data including the number of times of rapid acceleration, the number of times of emergency braking, the percentage of time spent driving at a constant speed, and throttle opening habit data under different slopes. Based on historical vehicle operation data, a gradient descent algorithm is used for optimization. Every time a preset mileage (1000km) is accumulated, the feature weights of the operating condition prediction model and the matching coefficient of combustion parameters are automatically updated.

[0013] Furthermore, the combustion parameter control module outputs a control signal 2-3 seconds in advance for a second preset time period to adjust the engine's combustion parameters, including: When anticipating acceleration conditions, increase the injection pressure above 350 bar, advance the injection time by 10° and 30°CA, advance the ignition time by 2° and 3°CA, and increase the intake air volume by 10% and 15%. When anticipating deceleration conditions, reduce the injection pressure to below 250 bar, delay the injection timing by 10° to 30°CA, delay the ignition timing by 1° to 2°CA, and reduce the intake air volume by 5% to 10%. When anticipating climbing conditions, increase the fuel injection pressure to above 350 bar, advance the fuel injection timing by 20° to 40°CA, advance the ignition timing by 3° to 4°CA, and increase the intake air volume by 15% to 20%. When anticipating a constant-speed operating condition, maintain the current combustion parameters unchanged.

[0014] Furthermore, the deviation data output by the emergency correction module includes deviations in vehicle speed change rate ≥ 10 km / h. s is used as the preset deviation threshold; The output parameter correction signal includes: when the deviation exceeds the preset deviation threshold, it will immediately trigger the adjustment of the combustion parameters to the optimal value corresponding to the actual working conditions; The control index for adjusting the combustion parameters to the optimal value corresponding to the actual operating conditions is set to a third preset duration of no more than (0.1 seconds); If the combustion parameters are not adjusted to the optimal value corresponding to the actual operating conditions within the third preset time (0.1) seconds, the condition judgment for switching the control mode will be initiated. The conditions for switching control modes include: if the deviation exceeds the preset deviation threshold for more than the fourth preset duration (2 seconds), the current operation mode of adjusting engine combustion parameters by outputting control signals in advance will be exited and the operation mode of adjusting engine combustion parameters by outputting control signals in normal mode will be switched.

[0015] The above solution achieves the following beneficial technical effects: This invention proactively adjusts parameters to improve fuel economy by 9% to 13%; it reduces power fluctuations and enhances driving smoothness; its lightweight design requires no additional hardware, resulting in low modification costs and high applicability; its machine learning adapts to different driving habits, offering superior compatibility; its emergency correction module ensures stable combustion, reduces carbon buildup, and extends engine life; and it aligns with energy conservation and environmental protection trends, demonstrating significant industrial application value. This invention achieves predictive optimization of the engine combustion system through the collaborative design of a "condition prediction module + combustion parameter control module + emergency correction module + machine learning adaptation module." Attached Figure Description

[0016] Figure 1 This is a flowchart of a predictive engine combustion optimization control method provided by one or more embodiments of the present invention.

[0017] Figure 2 This is a structural diagram of a predictive engine combustion optimization control system provided by one or more embodiments of the present invention.

[0018] Figure 3 This is a schematic diagram of the overall system structure provided in a specific embodiment of the present invention. Detailed Implementation

[0019] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Figure 1 This is a flowchart of a predictive engine combustion optimization control method provided by one or more embodiments of the present invention.

[0021] Example 1, such as Figure 1 The predictive engine combustion optimization control method shown includes the following steps: S1: Acquire road condition data and collect vehicle operation data in real time; S2 integrates road condition data and vehicle operation data, extracts key feature parameters, and outputs the working condition type for the first preset duration (3~5 seconds) based on the working condition prediction model, generating the predicted working condition. S3 builds a user driving habit database based on vehicle operation history data and dynamically optimizes the feature weights and combustion parameter matching coefficients of the operating condition prediction model. S4, based on the predicted operating conditions and the optimized combustion parameter matching coefficient, outputs a control signal in advance to adjust the engine's combustion parameters; S5 compares the predicted operating conditions with the actual operating conditions in real time. When the deviation exceeds the preset deviation threshold, it corrects the combustion parameters and feeds back the deviation data to optimize the operating condition prediction model.

[0022] In this embodiment, it includes: In step S1, the road condition data includes gradient, road condition type, and traffic light information; Vehicle operating data includes vehicle speed, throttle opening, brake signal, torque, and engine speed; In step S2, based on the road condition data and vehicle operation data from step S1, the key feature parameters extracted include vehicle speed change rate, gradient value, throttle opening change rate, and traffic light countdown. The operating conditions are set as acceleration, deceleration, constant speed, and climbing.

[0023] The rule for determining the operating condition type is: vehicle speed change rate ≥ 5km / h s represents acceleration, with a speed change rate ≤ -5km / h. 's' represents deceleration; a gradient ≥ 5° and throttle opening ≥ 50% represent climbing; and the rate of change of vehicle speed is between -5 and 5 km / h. The speed is constant in the s interval.

[0024] In this embodiment, it includes: In step S3, the vehicle's historical operating data includes the number of times it accelerates rapidly, the number of times it brakes suddenly, the percentage of time it travels at a constant speed, and the throttle opening habit data under different slopes. Based on historical vehicle operation data, a gradient descent algorithm is used for optimization. Every time a preset mileage (1000km) is accumulated, the feature weights of the operating condition prediction model and the matching coefficient of combustion parameters are automatically updated.

[0025] In this embodiment, it includes: In step S4, a control signal is output 2-3 seconds in advance for a second preset time period to adjust the engine's combustion parameters, including: When anticipating acceleration conditions, increase the injection pressure above 350 bar, advance the injection time by 10° and 30°CA, advance the ignition time by 2° and 3°CA, and increase the intake air volume by 10% and 15%. When anticipating deceleration conditions, reduce the injection pressure to below 250 bar, delay the injection timing by 10° to 30°CA, delay the ignition timing by 1° to 2°CA, and reduce the intake air volume by 5% to 10%. When anticipating climbing conditions, increase the fuel injection pressure to above 350 bar, advance the fuel injection timing by 20° to 40°CA, advance the ignition timing by 3° to 4°CA, and increase the intake air volume by 15% to 20%. When anticipating a constant-speed operating condition, maintain the current combustion parameters unchanged.

[0026] Specifically: CA is an abbreviation for Crank Angle, which is the standard phase unit in the field of internal combustion engines.

[0027] "Injection timing advanced by 10~30°CA" and "Ignition timing advanced by 2~3°CA" refer to the injection and ignition actions being performed before the crankshaft has rotated by the corresponding angle, relative to the original reference phase.

[0028] The reason for using crankshaft angle instead of absolute time is that engine speed changes in real time, and the absolute time corresponding to the same angle will change with the speed, but the combustion phase relative to the piston position is fixed, which can ensure the accuracy and consistency of combustion control across the entire speed range.

[0029] In this embodiment, it includes: Step S5, when the deviation exceeds a preset threshold, includes correcting the combustion parameters as follows: With a vehicle speed change rate deviation ≥10km / h s is used as the preset deviation threshold; When the deviation exceeds the preset deviation threshold, the combustion parameters will be immediately adjusted to the optimal value corresponding to the actual operating conditions. The control index for adjusting the combustion parameters to the optimal value corresponding to the actual operating conditions is set to a third preset duration of no more than (0.1 seconds); If the combustion parameters fail to be adjusted to the optimal value corresponding to the actual operating conditions within the third preset time (0.1 seconds), the condition judgment for switching the control mode will be initiated. The conditions for switching control modes include: if the deviation exceeds the preset deviation threshold for more than the fourth preset duration (2 seconds), the current operation mode of adjusting engine combustion parameters by outputting control signals in advance will be exited and the operation mode of adjusting engine combustion parameters by outputting control signals in normal mode will be switched.

[0030] Figure 2 This is a structural diagram of a predictive engine combustion optimization control system provided by one or more embodiments of the present invention.

[0031] like Figure 2 The predictive engine combustion optimization control system shown includes a navigation module, a body sensor group, an on-board ECU, and an engine combustion system; The navigation module and the vehicle sensor group are respectively connected to the input of the vehicle ECU, and the output of the vehicle ECU controls the engine combustion system. The vehicle ECU has a built-in operating condition prediction module, machine learning adaptation module, combustion parameter control module, and emergency correction module; The input end of the working condition prediction module receives road condition data output from the navigation module and vehicle operation data output from the vehicle sensor group, and the output end outputs the predicted working condition to the combustion parameter control module and the emergency correction module. The machine learning adaptation module receives historical vehicle operation data from the vehicle sensor group and deviation data from the emergency correction module as inputs. Its outputs are connected to the operating condition prediction module and the combustion parameter control module, respectively, to output optimized feature weights and combustion parameter matching coefficients. The combustion parameter control module receives the predicted operating conditions, combustion parameter matching coefficients, and parameter correction signals output by the emergency correction module at its input end, and outputs combustion control signals to the engine combustion system at its output end. The emergency correction module's input end receives the predicted operating conditions and the real-time vehicle operation data output by the vehicle's sensor group. Its output end is connected to the combustion parameter control module and the machine learning adaptation module, respectively, to output parameter correction signals and deviation data.

[0032] In this embodiment, it includes: The working condition prediction module has a built-in working condition prediction model; Road condition data includes gradient, road condition type and traffic light information; vehicle operation data includes vehicle speed, throttle opening, brake signal, torque and speed. The condition prediction module extracts key feature parameters such as vehicle speed change rate, gradient value, throttle opening change rate, and traffic light countdown, and outputs the condition type for the first preset duration (3-5 seconds) of acceleration, deceleration, constant speed, and hill climbing. The condition determination rule is: vehicle speed change rate ≥ 5 km / h. s represents acceleration, with a speed change rate ≤ -5km / h. 's' represents deceleration; a gradient ≥ 5° and throttle opening ≥ 50% represent climbing; and the rate of change of vehicle speed is between -5 and 5 km / h. The speed is constant in the s interval.

[0033] In this embodiment, it includes: The machine learning adaptation module has a built-in user driving habit database, which stores vehicle operation history data including the number of times of rapid acceleration, the number of times of emergency braking, the percentage of time spent driving at a constant speed, and throttle opening habit data under different slopes. Based on historical vehicle operation data, a gradient descent algorithm is used for optimization. Every time a preset mileage (1000km) is accumulated, the feature weights of the operating condition prediction model and the matching coefficient of combustion parameters are automatically updated.

[0034] In this embodiment, the combustion parameter control module outputs a control signal 2-3 seconds in advance for a second preset time period to adjust the engine's combustion parameters, including: When anticipating acceleration conditions, increase the injection pressure above 350 bar, advance the injection time by 10° and 30°CA, advance the ignition time by 2° and 3°CA, and increase the intake air volume by 10% and 15%. When anticipating deceleration conditions, reduce the injection pressure to below 250 bar, delay the injection timing by 10° to 30°CA, delay the ignition timing by 1° to 2°CA, and reduce the intake air volume by 5% to 10%. When anticipating climbing conditions, increase the fuel injection pressure to above 350 bar, advance the fuel injection timing by 20° to 40°CA, advance the ignition timing by 3° to 4°CA, and increase the intake air volume by 15% to 20%. When anticipating a constant-speed operating condition, maintain the current combustion parameters unchanged.

[0035] In this embodiment, the deviation data output by the emergency correction module includes deviations with a vehicle speed change rate ≥ 10 km / h. s is used as the preset deviation threshold; The output parameter correction signal includes: when the deviation exceeds the preset deviation threshold, it will immediately trigger the adjustment of the combustion parameters to the optimal value corresponding to the actual working conditions; The control index for adjusting the combustion parameters to the optimal value corresponding to the actual operating conditions is set to a third preset duration of no more than (0.1 seconds); If the combustion parameters are not adjusted to the optimal value corresponding to the actual operating conditions within the third preset time (0.1) seconds, the condition judgment for switching the control mode will be initiated. The conditions for switching control modes include: if the deviation exceeds the preset deviation threshold for more than the fourth preset duration (2 seconds), the current operation mode of adjusting engine combustion parameters by outputting control signals in advance will be exited and the operation mode of adjusting engine combustion parameters by outputting control signals in normal mode will be switched.

[0036] It is worth noting that although this system / device only discloses the above-mentioned modules / units, it does not mean that this system / device is limited to the above-mentioned basic functional modules. On the contrary, what this invention intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can add one or more functional modules in combination with the prior art to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. It cannot be assumed that the scope of protection of the claims of this invention is limited to the above-disclosed basic functional modules just because this embodiment only discloses a few basic functional modules.

[0037] Example 4, in one specific embodiment, discloses as follows: Figure 3 The system structure shown consists of an onboard ECU (core control unit), onboard equipment, and an engine combustion system. The onboard ECU includes modules such as a condition prediction module, a combustion parameter control module, an emergency correction module, and a machine learning adaptation module. The onboard equipment includes a navigation module and a body sensor group. All modules work together without the need for additional complex hardware, as detailed below: 1. Navigation module: Provides road condition data (slope, road condition type, traffic light location and duration) to the working condition prediction module. 2. Vehicle body sensor group: including vehicle speed sensor, throttle opening sensor, brake signal sensor, torque sensor, and speed sensor, which are connected to the vehicle ECU to collect vehicle operation data in real time and transmit it to the working condition prediction module; 3. Operating Condition Prediction Module: Integrated into the vehicle ECU, it receives data from the navigation module and the vehicle sensor group, completes the operating condition prediction, and outputs the prediction result (operating condition type in the next 3-5 seconds: acceleration, deceleration, constant speed, climbing), thus realizing advance prediction; 4. Machine Learning Adaptation Module: Integrated into the vehicle ECU, it receives historical data from the vehicle's sensor array (related to driving habits: frequency of rapid acceleration, duration of constant speed, braking frequency, etc.) and optimizes prediction accuracy and combustion parameter matching through algorithms. 5. Combustion parameter control module: Integrated into the vehicle ECU, it receives the prediction results from the operating condition prediction module and the optimized parameters from the machine learning adaptation module, outputs control signals, and controls the core combustion parameters of the engine. 6. Emergency Correction Module: Integrated into the vehicle ECU, it compares the predicted operating conditions with the actual operating conditions in real time, and quickly corrects the combustion parameters when the deviation exceeds the threshold; 7. Engine Combustion System: Receives control signals from the combustion parameter control module, adjusts parameters such as injection pressure, injection timing, ignition timing, and intake air volume to complete the combustion process.

[0038] Example 5: Detailed technical implementation of each module in the above examples: (I) Working Condition Prediction Module Core function: Based on the fusion of navigation data and vehicle sensor data, predict the engine operating condition 3-5 seconds in advance. Specific implementation steps: 1. Data Acquisition: The navigation module collects real-time road condition data (slope: 0°~30°, road condition type: flat / climbing / downhill, traffic light location and countdown), and the vehicle body sensor group collects real-time data on vehicle speed (0~120km / h), throttle opening (0%~100%), brake signal (present / absent), actual torque (0~500N·m), and actual speed (0~6000rpm). All data is transmitted to the working condition prediction module. 2. Operating Condition Feature Extraction: Key feature parameters are extracted using feature extraction algorithms, including: current vehicle speed change rate (to determine acceleration / deceleration), gradient value (to determine climbing / descent), throttle opening change rate (to assist in determining acceleration intention), and traffic light countdown (to determine when the vehicle is about to stop / start). 3. Predictive Model Calculation: The built-in working condition prediction model, based on the extracted feature parameters and combined with the historical optimization data of the machine learning adaptation module, outputs the working condition type for the next 3 to 5 seconds (acceleration: vehicle speed change rate ≥ 5 km / h·s; deceleration: vehicle speed change rate ≤ -5 km / h·s; climbing: slope ≥ 5° and throttle opening ≥ 50%; constant speed: vehicle speed change rate between -5 and 5 km / h·s).

[0039] (ii) Machine Learning Adaptation Module Core function: Accumulate user driving habit data to optimize prediction accuracy and combustion parameter matching. Specific implementation: 1. Data accumulation: Real-time collection of historical data during user driving, including the number of times of rapid acceleration, the number of times of emergency braking, the percentage of time spent driving at a constant speed, and throttle opening habits under different slopes, to establish a user driving habit database; 2. Algorithm optimization: The gradient descent algorithm is adopted, and based on historical data, the feature weights of the working condition prediction model are optimized (e.g., for users who frequently accelerate rapidly, the weight of the throttle opening change rate is increased), while the matching coefficient of combustion parameters is optimized. 3. Dynamic updates: The model parameters are automatically updated and optimized every 1,000 km of cumulative driving to ensure continuous improvement in adaptability.

[0040] (III) Combustion Parameter Control Module Core Function: Based on predicted operating conditions, adjust core combustion parameters in advance. Specific control logic: 1. Anticipate acceleration conditions: 2-3 seconds in advance, increase the fuel injection pressure to 350 bar, advance the fuel injection timing by 10-30°CA, advance the ignition timing by 2-3°CA, and increase the intake air volume by 10%-15% to ensure sufficient power and complete fuel combustion during acceleration; 2. Anticipate deceleration conditions: Reduce the fuel injection pressure to 250 bar 2-3 seconds in advance, delay the fuel injection timing by 10-30°CA, delay the ignition timing by 1-2°CA, and reduce the intake air volume by 5%-10% to reduce power waste; 3. Anticipate climbing conditions: 2-3 seconds in advance, increase the fuel injection pressure to 350 bar, advance the fuel injection timing by 20-40°CA, advance the ignition timing by 3-4°CA, and increase the intake air volume by 15%-20% to ensure that the power meets the climbing requirements, while avoiding incomplete combustion of fuel. 4. Predicting constant speed operation: The injection pressure, injection timing, ignition timing, and intake air volume remain unchanged to maintain the current optimal combustion state.

[0041] (iv) Emergency Correction Module Core function: To avoid combustion instability caused by prediction deviations; specific implementation: 1. Deviation detection: Real-time comparison between predicted and actual operating conditions (judged by real-time data collected by the vehicle's sensor group), and setting deviation thresholds (e.g., if the predicted acceleration is followed by actual deceleration, the deviation in vehicle speed change rate is ≥10km / h·s). 2. Rapid correction: When the deviation exceeds the threshold, the emergency correction module immediately intervenes and adjusts the combustion parameters to the optimal value corresponding to the current actual operating conditions within 0.1 seconds. At the same time, the deviation data is fed back to the machine learning adaptation module to optimize the prediction model. 3. Emergency protection: When the deviation lasts for more than 2 seconds, it will automatically switch to the normal real-time feedback mode to avoid engine damage.

[0042] This embodiment produces the following beneficial effects: 1. Solve the problem of delayed waste: The operating condition prediction module predicts the operating condition 3-5 seconds in advance, and the combustion parameter control module adjusts the parameters in advance to avoid incomplete combustion of fuel when the operating condition changes suddenly, directly improving fuel economy (9%~13%) and reducing carbon deposits at the same time; 2. Improve smoothness: Pre-adapt combustion parameters to avoid power fluctuations, resolve jerking issues during acceleration and deceleration, and enhance the driving experience; 3. Lightweight and easy to implement: No cloud data processing is required. It can be implemented by upgrading the ECU software using existing navigation and sensors, with low modification costs and rapid industrial application. 4. Personalized Adaptation: The machine learning adaptation module optimizes parameters based on user driving habits to ensure that different users can achieve optimal fuel economy; 5. Stability assurance: The emergency correction module quickly handles predicted deviations, avoids combustion instability, extends engine life, and reduces maintenance costs.

[0043] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A predictive engine combustion optimization control method, characterized in that, Includes the following steps: S1: Acquire road condition data and collect vehicle operation data in real time; S2 integrates road condition data and vehicle operation data, extracts key feature parameters, and outputs the type of working condition for the first preset duration based on the working condition prediction model, generating the predicted working condition. S3 builds a user driving habit database based on vehicle operation history data and dynamically optimizes the feature weights and combustion parameter matching coefficients of the operating condition prediction model. S4, based on the predicted operating conditions and the optimized combustion parameter matching coefficient, outputs a control signal in advance to adjust the engine's combustion parameters; S5 compares the predicted operating conditions with the actual operating conditions in real time. When the deviation exceeds the preset deviation threshold, it corrects the combustion parameters and feeds back the deviation data to optimize the operating condition prediction model.

2. The predictive engine combustion optimization control method according to claim 1, characterized in that, include: In step S1, the road condition data includes gradient, road condition type, and traffic light information; The vehicle's operating data includes vehicle speed, throttle opening, brake signal, torque, and engine speed; In step S2, based on the road condition data and vehicle operation data from step S1, the key feature parameters extracted include vehicle speed change rate, gradient value, throttle opening change rate, and traffic light countdown. The operating conditions are set as acceleration, deceleration, constant speed, and climbing.

3. The predictive engine combustion optimization control method according to claim 1, characterized in that, include: In step S3, the vehicle's historical driving data includes the number of times it accelerates rapidly, the number of times it brakes suddenly, the percentage of time it travels at a constant speed, and the throttle opening habit data under different slopes. Based on the vehicle's historical operating data, a gradient descent algorithm is used for optimization. Every time a preset mileage is accumulated, the feature weights of the operating condition prediction model and the matching coefficients of the combustion parameters are automatically updated.

4. The predictive engine combustion optimization control method according to claim 1, characterized in that, include: In step S4, a control signal is output a second preset time in advance to adjust the engine's combustion parameters, including: When anticipating acceleration conditions, increase the injection pressure above 350 bar, advance the injection time by 10° and 30°CA, advance the ignition time by 2° and 3°CA, and increase the intake air volume by 10% and 15%. When anticipating deceleration conditions, reduce the injection pressure to below 250 bar, delay the injection timing by 10° to 30°CA, delay the ignition timing by 1° to 2°CA, and reduce the intake air volume by 5% to 10%. When anticipating climbing conditions, increase the fuel injection pressure to above 350 bar, advance the fuel injection timing by 20° to 40°CA, advance the ignition timing by 3° to 4°CA, and increase the intake air volume by 15% to 20%. When anticipating a constant-speed operating condition, maintain the current combustion parameters unchanged.

5. The predictive engine combustion optimization control method according to claim 1, characterized in that, include: Step S5, when the deviation exceeds a preset threshold, includes correcting the combustion parameters as follows: With a vehicle speed change rate deviation ≥10km / h s is used as the preset deviation threshold; When the deviation exceeds the preset deviation threshold, the combustion parameters will be immediately adjusted to the optimal value corresponding to the actual operating conditions. The control index for adjusting combustion parameters to the optimal value corresponding to actual operating conditions is set to not exceed the third preset time. If the combustion parameters fail to be adjusted to the optimal value corresponding to the actual operating conditions within the third preset time period, the condition judgment for switching the control mode will be initiated. The conditions for switching control modes include: when the deviation exceeds the preset threshold for a fourth preset duration, the current operating mode of adjusting engine combustion parameters by outputting control signals in advance is exited, and the operating mode of adjusting engine combustion parameters by outputting control signals in normal mode is switched.

6. A predictive engine combustion optimization control system, characterized in that, This includes the navigation module, the vehicle sensor group, the onboard ECU, and the engine combustion system; The navigation module and the vehicle sensor group are respectively connected to the input terminal of the vehicle ECU, and the output terminal of the vehicle ECU controls the connection to the engine combustion system. The vehicle ECU has a built-in operating condition prediction module, machine learning adaptation module, combustion parameter control module, and emergency correction module. The input end of the working condition prediction module receives road condition data output by the navigation module and vehicle operation data output by the vehicle sensor group, and the output end outputs the predicted working condition to the combustion parameter control module and the emergency correction module. The machine learning adaptation module receives historical vehicle operation data output by the vehicle sensor group and deviation data output by the emergency correction module at its input end, and its output end is connected to the operating condition prediction module and the combustion parameter control module respectively, for outputting optimized feature weights and combustion parameter matching coefficients. The combustion parameter control module receives the predicted operating conditions, combustion parameter matching coefficients, and parameter correction signals output by the emergency correction module at its input end, and outputs combustion control signals to the engine combustion system at its output end. The emergency correction module's input end receives the predicted operating conditions and the real-time vehicle operation data output by the vehicle's sensor group. Its output end is connected to the combustion parameter control module and the machine learning adaptation module, respectively, to output parameter correction signals and deviation data.

7. The predictive engine combustion optimization control system according to claim 6, characterized in that, include: The working condition prediction module has a built-in working condition prediction model; The road condition data includes gradient, road condition type and traffic light information, and the vehicle operation data includes vehicle speed, throttle opening, brake signal, torque and speed. The condition prediction module is used to extract key feature parameters such as vehicle speed change rate, gradient value, throttle opening change rate and traffic light countdown, and output the condition types of acceleration, deceleration, constant speed and climbing conditions for the first preset duration in the future.

8. The predictive engine combustion optimization control system according to claim 6, characterized in that, include: The machine learning adaptation module has a built-in user driving habit database, which stores vehicle operation history data including the number of times of rapid acceleration, the number of times of emergency braking, the percentage of time spent driving at a constant speed, and throttle opening habit data under different slopes. Based on the vehicle's historical operating data, a gradient descent algorithm is used for optimization. Every time a preset mileage is accumulated, the feature weights of the operating condition prediction model and the matching coefficients of the combustion parameters are automatically updated.

9. The predictive engine combustion optimization control system according to claim 6, characterized in that, The combustion parameter control module outputs a control signal a second preset time in advance to adjust the engine's combustion parameters, including: When anticipating acceleration conditions, increase the injection pressure above 350 bar, advance the injection time by 10° and 30°CA, advance the ignition time by 2° and 3°CA, and increase the intake air volume by 10% and 15%. When anticipating deceleration conditions, reduce the injection pressure to below 250 bar, delay the injection timing by 10° to 30°CA, delay the ignition timing by 1° to 2°CA, and reduce the intake air volume by 5% to 10%. When anticipating climbing conditions, increase the fuel injection pressure to above 350 bar, advance the fuel injection timing by 20° to 40°CA, advance the ignition timing by 3° to 4°CA, and increase the intake air volume by 15% to 20%. When anticipating a constant-speed operating condition, maintain the current combustion parameters unchanged.

10. The predictive engine combustion optimization control system according to claim 6, characterized in that, The deviation data output by the emergency correction module includes deviations with a vehicle speed change rate ≥ 10 km / h. s is used as the preset deviation threshold; The output parameter correction signal includes: when the deviation exceeds the preset deviation threshold, it will immediately trigger the adjustment of the combustion parameters to the optimal value corresponding to the actual working conditions; The control index for adjusting combustion parameters to the optimal value corresponding to actual operating conditions is set to not exceed the third preset time. If the combustion parameters fail to be adjusted to the optimal value corresponding to the actual operating conditions within the third preset time period, the condition judgment for switching the control mode will be initiated. The conditions for switching control modes include: when the deviation exceeds the preset threshold for a fourth preset duration, the current operating mode of adjusting engine combustion parameters by outputting control signals in advance is exited, and the operating mode of adjusting engine combustion parameters by outputting control signals in normal mode is switched.

Images