Adjusting system and method for controlling rotating speed of automobile engine

Abstract

The invention discloses an adjusting system for controlling the rotating speed of an automobile engine, and the system is characterized in that the system comprises a data collection module which collects the conventional operation parameters of the automobile engine in real time, the conventional operation parameters comprise the rotating speed, the torque, the air inflow, the oil temperature and the oil pressure, and also collects the acceleration, the gradient information, the external environment temperature and humidity of a vehicle and the driving behavior data of a driver; such as accelerator pedal depth change rate and brake frequency; the data analysis module is connected with the data acquisition module and is used for deeply mining a relationship and a potential rule in data by applying a long short-term memory (LSTM) network algorithm in deep learning and a fusion analysis method based on a physical model, identifying a real-time running state and a future change trend of the engine and intelligently diagnosing potential fault hidden dangers; the fuel injection amount and the ignition time can reach the optimal state through accurate rotation speed adjustment, fuel consumption is greatly reduced, fuel economy is improved, and expenditure is saved for users.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile engines, and more specifically, to a regulating system and method for controlling the speed of an automobile engine. Background Art

[0002] With the rapid development of the automobile industry and the continuous improvement of people's requirements for automobile performance, precise control of engine speed has become a key factor in improving automobile power, economy and emission performance. In traditional automobile engine control systems, the adjustment of speed often relies on relatively simple sensor data and fixed control strategies, which is difficult to cope with complex and changeable actual working conditions and driving needs.

[0003] Most engine speed control systems on the market today have a limited data collection scope, usually focusing only on some basic engine operating parameters, such as speed and torque, while ignoring important factors such as vehicle acceleration, slope, external environmental conditions, and driver driving behavior. This results in the system's understanding of the engine's operating status being incomplete and inaccurate, thus limiting the accuracy and effectiveness of speed control.

[0004] In terms of data analysis, traditional methods mostly use simple statistical analysis or linear models, which cannot effectively mine the deep relationships and potential laws in the data, and it is difficult to accurately predict the operating trends and potential failures of the engine. This may cause problems such as unstable performance, excessive fuel consumption, and substandard emissions during engine operation.

[0005] In terms of control strategies, existing engine speed regulation strategies are often rigid and lack flexibility and adaptability. They cannot adjust control parameters in time according to real-time changing working conditions and vehicle status, resulting in unsatisfactory engine performance under different conditions.

[0006] In addition, the response speed and accuracy of existing actuators need to be improved, and they are unable to execute control instructions quickly and accurately, affecting the real-time and accuracy of speed regulation.

[0007] In the feedback monitoring link, the monitoring indicators of many systems are not comprehensive enough to promptly detect potential problems after engine speed adjustment, nor can they provide sufficient and effective data support for system optimization.

[0008] In summary, in order to meet the higher requirements of modern automobiles for engine performance, there is an urgent need for an innovative, comprehensive, and intelligent engine speed regulation system and method that can collect data more accurately, analyze data more deeply, formulate control strategies more flexibly, execute control instructions more quickly and accurately, and achieve continuous optimization of the system through comprehensive and effective feedback monitoring. Summary of the invention

[0009] 1. Technical issues to be solved

[0010] The object of the present invention is to provide a regulating system and method for controlling the speed of an automobile engine to solve the problems raised in the above-mentioned background technology.

[0011] 2. Technical solution

[0012] A regulating system for controlling the speed of an automobile engine, comprising:

[0013] The data acquisition module collects the regular operating parameters of the automobile engine in real time, including: speed, torque, intake volume, oil temperature, oil pressure, as well as the vehicle's acceleration, slope information, external environment temperature and humidity, and the driver's driving behavior data, such as the rate of change of the accelerator pedal depth and the braking frequency;

[0014] The data analysis module is connected to the data acquisition module, and uses the long short-term memory network LSTM algorithm in deep learning and the fusion analysis method based on the physical model to deeply mine the relationship and potential rules in the data, identify the real-time operating status and future change trend of the engine, and intelligently diagnose potential fault hazards;

[0015] An intelligent optimization control module is connected to the data analysis module, and generates ultra-precise and dynamically optimized control instructions based on the analysis results based on a deep reinforcement learning algorithm and a genetic algorithm. The control instructions include adjustment of throttle opening, fuel injection amount, ignition advance angle, valve lift, and intelligent control of variable compression ratio technology and exhaust gas recirculation system;

[0016] An execution module, connected to the intelligent control module, adopts a combination of an electric actuator and a hydraulic actuator to ensure instant and error-free execution of control instructions and achieve real-time and precise adjustment of the engine speed;

[0017] The real-time feedback monitoring module is equipped with sensors and intelligent diagnostic units to monitor the effect of engine speed adjustment in real time, including exhaust emission components and particulate matter quantity, and quickly transmit multi-dimensional feedback information to the data acquisition module to form a closed-loop control;

[0018] The adaptive learning module is connected to all other modules and can automatically adjust the parameters and algorithms of each module according to the characteristics of different vehicle models, different usage scenarios and regions, as well as the aging degree and maintenance history of the engine.

[0019] Preferably, the sensor in the data acquisition module has self-calibration and fault self-diagnosis functions to ensure the accuracy and reliability of the data, and its self-calibration formula is:

[0020] C=M+K×(RM)

[0021] Among them, C represents the corrected value, M represents the measured value, K is the calibration coefficient, and R represents the reference value.

[0022] Preferably, the data analysis module can perform natural language processing and image recognition analysis on the collected unstructured data, and the image recognition accuracy calculation formula used is:

[0023]

[0024] Where A represents the accuracy, N ci Indicates the number of correctly identified images, N t Represents the total number of images. This formula is used to calculate the proportion of correctly identified images in image recognition to the total number of images to evaluate the effect of image recognition.

[0025] Preferably, the intelligent optimization control module has a built-in optimization algorithm based on quantum computing to further improve the optimization speed and quality of the control strategy, and the state evolution formula of its quantum bit is:

[0026] |ψ(t)>=U(t)|ψ(0)>

[0027] Where |ψ(t)> represents the quantum state at time t, U(t) is the time-dependent evolution operator, and |ψ(0)> represents the initial quantum state. This formula describes the state changes of the quantum bit at different times.

[0028] Preferably, the actuator in the execution module has power-off protection and emergency manual operation mode to ensure the safety and reliability of the system. The power-off protection response time calculation formula is:

[0029] T r =t d +t s

[0030] Where T r Represents the response time, t d Indicates the power failure detection time, t s Represents the switching time. This formula calculates the response time of power failure protection by the sum of detection time and switching time.

[0031] Preferably, the present invention discloses a method for controlling the speed of an automobile engine, comprising the following steps:

[0032] The data acquisition module comprehensively and in real time collects the multi-dimensional operating parameters of the automobile engine and related environmental and driving behavior data;

[0033] The data analysis module uses deep learning and fusion analysis methods to deeply analyze the collected data, predict the operating status and change trend of the engine, and diagnose potential faults. The loss function of deep learning is:

[0034]

[0035] Where L represents the loss value, yi is the true value, For the predicted value, the loss function is used to measure the difference between the predicted value and the true value to optimize the training of the model;

[0036] Based on the analysis results, the intelligent optimization control module uses deep reinforcement learning and genetic algorithms to generate highly optimized and dynamically adjusted control instructions, accurate to subtle parameter adjustments and complex system control;

[0037] The execution module executes control instructions quickly and accurately, and makes real-time and fine adjustments to the engine speed;

[0038] The real-time feedback monitoring module monitors the comprehensive effect of the adjustment in real time, including multiple indicators such as exhaust emissions, and transmits comprehensive feedback information to the data acquisition module in a timely manner;

[0039] The adaptive learning module automatically adjusts system parameters and algorithms according to changes in vehicles and usage conditions, and continuously optimizes the adjustment strategy. The adjustment formula for adaptive learning is:

[0040] P n =P o +α×(TC)

[0041] Where P n represents the new parameter, P o represents the old parameters, α is the learning rate, T is the target value, and C is the current value. This formula obtains the adjusted new parameters by calculating the old parameters, learning rate, target value, and current value.

[0042] Preferably, in the deep learning algorithm, an autoencoder is used to perform feature extraction and dimensionality reduction on the data, and the reconstruction error formula of the autoencoder is:

[0043]

[0044] Where E r represents the reconstruction error, x j is the original data, To reconstruct the data, the formula is used to calculate the difference between the original data and the reconstructed data to evaluate the performance of the autoencoder.

[0045] Preferably, in the genetic algorithm, the generation process of the control instructions is optimized by crossover and mutation operations, and the fitness function calculation formula is:

[0046] F=f(C i )

[0047] Where F represents fitness, C i Represents the control instruction, and the fitness function is used to evaluate the quality of the control instruction to guide the optimization process of the genetic algorithm.

[0048] Preferably, when the real-time feedback monitoring module detects that the exhaust emissions exceed the standard or other abnormal conditions, the system automatically starts the emergency adjustment mode to give priority to ensuring emission compliance and safe engine operation. The exhaust emissions exceeding the standard judgment formula is:

[0049] E>T h

[0050] Where E represents the actual emission value, T h Indicates the emission standard threshold. When the actual emission value exceeds the threshold, it is judged that the exhaust emission exceeds the standard.

[0051] Preferably, the adjustment method can be seamlessly connected and work in coordination with the vehicle's automatic driving system and intelligent transportation system to achieve more intelligent and efficient vehicle speed and power control. The efficiency improvement formula of the coordinated control is:

[0052]

[0053] Where I represents the efficiency improvement percentage, N represents the new efficiency, and O represents the old efficiency. The formula calculates the efficiency improvement ratio by comparing the new efficiency with the old efficiency.

[0054] 3. Beneficial effects

[0055] Compared with the prior art, the advantages of the present invention are:

[0056] First, in terms of performance improvement, the engine speed can be controlled more accurately, thereby optimizing the engine's power output. This allows the car to perform better under conditions such as acceleration and climbing, significantly improving the vehicle's power performance. At the same time, precise speed regulation can achieve the best fuel injection amount and ignition timing, greatly reducing fuel consumption, improving fuel economy, and saving money for users.

[0057] Secondly, the present invention performs well in terms of environmental protection and reliability. Through intelligent optimization control, it ensures that the engine burns more fully under various working conditions, effectively reduces the emission of harmful gases and particulate matter, and makes a significant contribution to environmental protection. In addition, it diagnoses potential faults in real time, and makes timely adjustments and optimizations, which reduces the wear and failure rate of the engine, prolongs the service life of the engine, and enhances the reliability and durability of the vehicle.

[0058] Finally, the present invention also has many comprehensive advantages. It can adapt to various complex working conditions, whether it is urban congestion, highways or mountain roads, it can adaptively adjust the engine speed to provide stable and reliable power. It can make personalized adjustments according to the driver's driving behavior and habits, which improves the driving experience. In an emergency, it can quickly start the emergency adjustment mode to ensure safety. The collaborative work with automatic driving and intelligent transportation systems promotes the intelligent development of automobiles. In addition, it also reduces the maintenance cost of the vehicle and improves the overall use efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a schematic block diagram of a regulating system for controlling the speed of an automobile engine according to the present invention;

[0060] Figure 2 The present invention is a schematic block diagram of a method for controlling the speed of an automobile engine. DETAILED DESCRIPTION

[0061] Example: See Figure 1-2 , a regulating system for controlling the speed of an automobile engine, comprising:

[0062] The data acquisition module collects the regular operating parameters of the automobile engine in real time, including: speed, torque, intake volume, oil temperature, oil pressure, as well as the vehicle's acceleration, slope information, external environment temperature and humidity, and the driver's driving behavior data, such as the rate of change of the accelerator pedal depth and the braking frequency;

[0063] The data analysis module is connected to the data acquisition module, and uses the long short-term memory network LSTM algorithm in deep learning and the fusion analysis method based on the physical model to deeply mine the relationship and potential rules in the data, identify the real-time operating status and future change trend of the engine, and intelligently diagnose potential fault hazards;

[0064] An intelligent optimization control module is connected to the data analysis module, and generates ultra-precise and dynamically optimized control instructions based on the analysis results based on a deep reinforcement learning algorithm and a genetic algorithm. The control instructions include adjustment of throttle opening, fuel injection amount, ignition advance angle, valve lift, and intelligent control of variable compression ratio technology and exhaust gas recirculation system;

[0065] An execution module, connected to the intelligent control module, adopts a combination of an electric actuator and a hydraulic actuator to ensure instant and error-free execution of control instructions and achieve real-time and precise adjustment of the engine speed;

[0066] The real-time feedback monitoring module is equipped with sensors and intelligent diagnostic units to monitor the effect of engine speed adjustment in real time, including exhaust emission components and particulate matter quantity, and quickly transmit multi-dimensional feedback information to the data acquisition module to form a closed-loop control;

[0067] The adaptive learning module is connected to all other modules and can automatically adjust the parameters and algorithms of each module according to the characteristics of different vehicle models, different usage scenarios and regions, as well as the aging degree and maintenance history of the engine.

[0068] In the present invention, the sensor in the data acquisition module has self-calibration and fault self-diagnosis functions to ensure the accuracy and reliability of the data. The self-calibration formula is:

[0069] C=M+K×(RM)

[0070] Among them, C represents the corrected value, M represents the measured value, K is the calibration coefficient, and R represents the reference value.

[0071] In the present invention, the data analysis module can perform natural language processing and image recognition analysis on the collected unstructured data, and the image recognition accuracy calculation formula used is:

[0072]

[0073] Where A represents the accuracy, N ci Indicates the number of correctly identified images, N t Represents the total number of images. This formula is used to calculate the proportion of correctly identified images in image recognition to the total number of images to evaluate the effect of image recognition.

[0074] In the present invention, the intelligent optimization control module has a built-in optimization algorithm based on quantum computing to further improve the optimization speed and quality of the control strategy. The state evolution formula of its quantum bit is:

[0075] |ψ(t)>=U(t)|ψ(0)>

[0076] Where |ψ(t)> represents the quantum state at time t, U(t) is the time-dependent evolution operator, and |ψ(0)> represents the initial quantum state. This formula describes the state changes of the quantum bit at different times.

[0077] In the present invention, the actuator in the execution module has power-off protection and emergency manual operation mode to ensure the safety and reliability of the system. The power-off protection response time calculation formula is:

[0078] T r =t d +t s

[0079] Where T r Represents the response time, t d Indicates the power failure detection time, t s Represents the switching time. This formula calculates the response time of power failure protection by the sum of detection time and switching time.

[0080] In the present invention, a method for controlling the speed of an automobile engine is disclosed, comprising the following steps:

[0081] The data acquisition module comprehensively and in real time collects the multi-dimensional operating parameters of the automobile engine and related environmental and driving behavior data;

[0082] The data analysis module uses deep learning and fusion analysis methods to deeply analyze the collected data, predict the operating status and change trend of the engine, and diagnose potential faults. The loss function of deep learning is:

[0083]

[0084] Among them, L represents the loss value, yi is the true value, For the predicted value, the loss function is used to measure the difference between the predicted value and the true value to optimize the training of the model;

[0085] Based on the analysis results, the intelligent optimization control module uses deep reinforcement learning and genetic algorithms to generate highly optimized and dynamically adjusted control instructions, accurate to subtle parameter adjustments and complex system control;

[0086] The execution module executes control instructions quickly and accurately, and makes real-time and fine adjustments to the engine speed;

[0087] The real-time feedback monitoring module monitors the comprehensive effect of the adjustment in real time, including multiple indicators such as exhaust emissions, and transmits comprehensive feedback information to the data acquisition module in a timely manner;

[0088] The adaptive learning module automatically adjusts system parameters and algorithms according to changes in vehicles and usage conditions, and continuously optimizes the adjustment strategy. The adjustment formula for adaptive learning is:

[0089] P n =P o +α×(TC)

[0090] Among them, P n represents the new parameter, P o represents the old parameters, α is the learning rate, T is the target value, and C is the current value. This formula obtains the adjusted new parameters by calculating the old parameters, learning rate, target value, and current value.

[0091] In the present invention, in the deep learning algorithm, an autoencoder is used to perform feature extraction and dimensionality reduction on the data, and the reconstruction error formula of the autoencoder is:

[0092]

[0093] Among them, E r represents the reconstruction error, x j is the original data, To reconstruct the data, the formula is used to calculate the difference between the original data and the reconstructed data to evaluate the performance of the autoencoder.

[0094] In the present invention, in the genetic algorithm, the generation process of the control instruction is optimized by crossover and mutation operations, and the fitness function calculation formula is:

[0095] F=f(C i )

[0096] Among them, F represents fitness, C i Represents the control instruction, and the fitness function is used to evaluate the quality of the control instruction to guide the optimization process of the genetic algorithm.

[0097] In the present invention, when the real-time feedback monitoring module detects that the exhaust emissions exceed the standard or other abnormal conditions, the system automatically starts the emergency adjustment mode to give priority to ensuring emission compliance and safe operation of the engine. The exhaust emissions exceeding the standard judgment formula is:

[0098] E>T h

[0099] Where E represents the actual emission value, T h Indicates the emission standard threshold. When the actual emission value exceeds the threshold, it is judged that the exhaust emission exceeds the standard.

[0100] In the present invention, the adjustment method can seamlessly connect and work with the vehicle's automatic driving system and intelligent transportation system to achieve more intelligent and efficient vehicle speed and power control. The efficiency improvement formula of the collaborative control is:

[0101]

[0102] Among them, I represents the efficiency improvement percentage, N represents the new efficiency, and O represents the old efficiency. The formula calculates the efficiency improvement ratio by comparing the new efficiency with the old efficiency.

[0103] The regulation system and method for controlling the speed of an automobile engine of the present invention realizes precise and intelligent engine speed regulation through the following modules working in coordination.

[0104] The data acquisition module comprehensively collects various operating parameters of the automobile engine, vehicle information, external environment and driver behavior data. These rich data provide the basis for subsequent analysis and control.

[0105] The data analysis module uses advanced long short-term memory network (LSTM) algorithms and fusion analysis methods based on physical models to deeply mine the complex relationships and potential laws in the data. It can accurately identify the real-time operating status and future change trends of the engine, and intelligently diagnose potential fault hazards.

[0106] The intelligent optimization control module is based on deep reinforcement learning algorithms and genetic algorithms, and generates ultra-precise and dynamically optimized control instructions based on the results of the data analysis module. These instructions cover the fine adjustment of key components and the intelligent control of complex systems to achieve the best engine speed regulation effect.

[0107] The execution module uses a combination of electric actuators and hydraulic actuators to quickly and accurately execute control instructions and adjust the engine speed in real time and accurately.

[0108] The real-time feedback monitoring module uses the equipped sensors and intelligent diagnostic units to monitor various effects of engine speed adjustment, including exhaust emissions, and quickly transmits feedback information to the data acquisition module to form an effective closed-loop control.

[0109] The adaptive learning module is connected to other modules to automatically adjust the parameters and algorithms of each module according to different vehicle models, usage scenarios, regional characteristics, engine conditions, etc., so that the entire system always maintains optimal performance.

[0110] In the adjustment method, firstly, the data acquisition module is used to obtain comprehensive data, and then the data analysis module is used to perform in-depth analysis and fault diagnosis. The intelligent optimization control module generates control instructions, the execution module executes the instructions, the real-time feedback monitoring module monitors the effect, and the adaptive learning module continuously optimizes according to the changes. Each step cooperates with each other to form a continuously optimized workflow.

[0111] In addition, multiple formulas in the present invention are used to quantify and evaluate the performance and effects of various parts of the system. For example, the self-calibration formula of the data acquisition module ensures data accuracy, the image recognition accuracy calculation formula evaluates the image recognition effect of the data analysis module, the state evolution formula of the quantum bit describes the optimization process of the intelligent optimization control module, and the power-off protection response time calculation formula ensures the security of the execution module. These formulas together support the efficient and reliable operation of the entire system.

[0112] In summary, this patent achieves intelligent, accurate and efficient regulation of automobile engine speed through the coordinated work of various modules and precise algorithms, and continuously optimizes it to adapt to various complex situations.

[0113] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A regulating system for controlling the speed of an automobile engine, characterized in that: Including: A data acquisition module that real-time collects the conventional operating parameters of an automotive engine, including: rotational speed, torque, intake air volume, oil temperature, oil pressure, and also collects the vehicle's acceleration, slope information, external environmental temperature and humidity, as well as the driver's driving behavior data, such as the change rate of the throttle pedal depth and the braking frequency; A data analysis module, connected to the data acquisition module, uses the long short-term memory network (LSTM) algorithm in deep learning and a fusion analysis method based on a physical model to deeply mine the relationships and potential patterns in the data, identify the real-time operating state and future change trends of the engine, and at the same time can intelligently diagnose potential fault hazards; An intelligent optimization control module, connected to the data analysis module, based on the deep reinforcement learning algorithm and the genetic algorithm, generates ultra-precise and dynamically optimized control instructions according to the analysis results. The control instructions include the adjustment of the throttle valve opening, fuel injection volume, ignition advance angle, valve lift, and the intelligent control of the variable compression ratio technology and the exhaust gas recirculation system; An execution module, connected to the intelligent control module, adopts a combination of an electric actuator and a hydraulic actuator to ensure the instant and error-free execution of the control instructions, and realizes the real-time and precise adjustment of the engine rotational speed; A real-time feedback monitoring module, equipped with sensors and an intelligent diagnosis unit, is used to real-time monitor the effects after the engine rotational speed is adjusted, including the exhaust gas emission components and the number of particulate matters, and quickly transmits the multi-dimensional feedback information to the data acquisition module to form a closed-loop control; An adaptive learning module, connected to all other modules, can automatically adjust the parameters and algorithms of each module according to the characteristics of different vehicle models, different usage scenarios and regions, as well as the aging degree and maintenance history of the engine.

2. The regulating system and method for controlling the speed of an automobile engine according to claim 1, characterized in that: The sensors in the data acquisition module have self-calibration and fault self-diagnosis functions to ensure the accuracy and reliability of the data. Its self-calibration formula is: C = M + K×(R - M) Where, C represents the corrected value, M represents the measured value, K is the calibration coefficient, and R represents the reference value.

3. The regulating system and method for controlling the speed of an automobile engine according to claim 1, characterized in that: The data analysis module can perform natural language processing and image recognition analysis on the collected unstructured data. The calculation formula for the image recognition accuracy rate used is: Where A represents the accuracy, N ci Indicates the number of correctly identified images, N t Represents the total number of images. This formula is used to calculate the proportion of correctly identified images in image recognition to the total number of images to evaluate the effect of image recognition.

4. The regulating system and method for controlling the speed of an automobile engine according to claim 1, characterized in that: The intelligent optimization control module has an optimization algorithm based on quantum computing built-in to further improve the optimization speed and quality of the control strategy. The state evolution formula of its quantum bits is: |ψ(t)> = U(t)|ψ(0)> Where |ψ(t)> represents the quantum state at time t, U(t) is the time-dependent evolution operator, and |ψ(0)> represents the initial quantum state. This formula describes the state change of the quantum bits at different times.

5. The regulating system and method for controlling the speed of an automobile engine according to claim 1, characterized in that: The actuators in the execution module have power-off protection and emergency manual operation modes to ensure the safety and reliability of the system. The calculation formula for the power-off protection response time is: T r =t d +t s Where T r Represents the response time, t d Indicates the power failure detection time, t s Represents the switching time. This formula calculates the response time of power failure protection by the sum of detection time and switching time.

6. A method for controlling the speed of an automobile engine, characterized in that: Including the following steps: Comprehensively and real-time collect the multi-dimensional operating parameters of the automotive engine and relevant environmental and driving behavior data through the data acquisition module; The data analysis module uses deep learning and fusion analysis methods to deeply analyze the collected data, predict the operating state and change trends of the engine, and diagnose potential faults. The loss function of deep learning is: Where L represents the loss value, yi is the true value, For the predicted value, the loss function is used to measure the difference between the predicted value and the true value to optimize the training of the model; Based on the analysis results, the intelligent optimization control module uses deep reinforcement learning and genetic algorithms to generate highly optimized and dynamically adjusted control instructions to adjust parameters and control complex systems; The execution module executes control instructions quickly and accurately, and makes real-time and fine adjustments to the engine speed; The real-time feedback monitoring module monitors the comprehensive effect of the adjustment in real time, including multiple indicators such as exhaust emissions, and transmits comprehensive feedback information to the data acquisition module in a timely manner; The adaptive learning module automatically adjusts system parameters and algorithms according to changes in vehicles and usage conditions, and continuously optimizes the adjustment strategy. The adjustment formula for adaptive learning is: P n =P o +α×(T-C) Where P n represents the new parameter, P o represents the old parameters, α is the learning rate, T is the target value, and C is the current value. This formula obtains the adjusted new parameters by calculating the old parameters, learning rate, target value, and current value.

7. The method for controlling the speed of an automobile engine according to claim 6, characterized in that: In the deep learning algorithm, an autoencoder is used to extract features and reduce the dimension of the data. The reconstruction error formula of the autoencoder is: Where E r represents the reconstruction error, x j is the original data, To reconstruct the data, the formula is used to calculate the difference between the original data and the reconstructed data to evaluate the performance of the autoencoder.

8. The method for controlling the speed of an automobile engine according to claim 6, characterized in that In the genetic algorithm, the generation process of control instructions is optimized through crossover and mutation operations, and the fitness function calculation formula is: F=f(C i ) Where F represents fitness, C i Represents the control instruction, and the fitness function is used to evaluate the quality of the control instruction to guide the optimization process of the genetic algorithm.

9. The method for controlling the speed of an automobile engine according to claim 6, characterized in that: When the real-time feedback monitoring module detects that the exhaust emissions exceed the standard or other abnormal conditions, the system automatically starts the emergency adjustment mode to prioritize emission compliance and engine safe operation. The formula for judging the exhaust emissions exceeding the standard is: E>T h Where E represents the actual emission value, T h Indicates the emission standard threshold. When the actual emission value exceeds the threshold, it is judged that the exhaust emission exceeds the standard.

10. The method for controlling the speed of an automobile engine according to claim 6, characterized in that: The adjustment method can seamlessly connect and work with the vehicle's automatic driving system and intelligent transportation system to achieve more intelligent and efficient vehicle speed and power control. The efficiency improvement formula of the collaborative control is: Where I represents the efficiency improvement percentage, N represents the new efficiency, and O represents the old efficiency. The formula calculates the efficiency improvement ratio by comparing the new efficiency with the old efficiency.

Images