A vehicle fuel consumption minimization method and system based on AOA algorithm

Abstract

This invention relates to the field of energy-saving control technology for intelligent connected vehicles, specifically to a method and system for minimizing vehicle fuel consumption based on the AOA algorithm. The method involves defining the dimension of vehicle speed and its upper and lower bounds, treating vehicle speed as a variable in the optimization problem; establishing a fuel consumption model to calculate fuel consumption at different speeds; determining the objective function; initializing the population with a pre-defined population size; calculating the Mathematical Optimizer (MOA) and Mathematical Optimization Probability (MOP) based on the current iteration count during each iteration; updating the speed value of each individual in the population during the exploration and utilization phases based on random numbers and the values ​​of MOA and MOP; calculating the updated objective function value for each individual to update the optimal fitness and optimal position; and repeating the above iterative process until the preset maximum number of iterations is reached.

Description

Technical Field

[0001] This invention relates to the field of energy-saving control technology for intelligent connected vehicles, specifically to a method and system for minimizing vehicle fuel consumption based on the AOA algorithm. Background Technology

[0002] Fuel consumption optimization refers to achieving the optimal vehicle speed with the lowest fuel consumption, maximizing fuel energy conversion efficiency while reducing exhaust emissions. Fuel consumption optimization can continuously provide the optimal vehicle speed strategy within the limitations of onboard computing power, thereby significantly reducing fuel consumption and minimizing high engine load conditions and ineffective idling time. This not only extends the lifespan of the engine and after-treatment system but also reduces CO2 and harmful emissions, making it significant from both economic and environmental perspectives.

[0003] While existing fuel consumption optimization technologies, such as rule-based control strategies and traditional PID or MPC control, can optimize fuel consumption, they are easily affected by complex operating conditions. During actual road driving, the engine needs to overcome various resistances, including air resistance, rolling resistance, and inertial forces, resulting in a strongly nonlinear relationship between instantaneous fuel consumption and vehicle speed. Furthermore, external factors such as driver habits, road gradient, and traffic flow changes further exacerbate the uncertainty of the speed-fuel consumption mapping. Summary of the Invention

[0004] To overcome the problems of local optima, complex calibration, and poor adaptability to operating conditions in existing technologies, and to achieve global fuel consumption minimization by searching for the optimal vehicle speed curve in real time while ensuring driving safety and passenger comfort, this invention aims to provide a vehicle fuel consumption minimization method and system based on the AOA algorithm. The specific technical solution adopted is as follows: A vehicle fuel consumption minimization method based on the AOA algorithm, characterized in that the method includes: defining the dimension of vehicle speed and the upper and lower bounds of speed; using vehicle speed as a variable in the optimization problem; establishing a fuel consumption model, which is expressed as a function of vehicle speed, used to calculate fuel consumption at different speeds; determining the objective function, which is to minimize the output value of the fuel consumption model; initializing a population, where each individual in the population represents a possible speed value, and the population size is a pre-set parameter; in each iteration, calculating the Mathematical Optimizer (MOA) and the Mathematical Optimization Probability (MOP) based on the current iteration number; and for each individual in the population, calculating the acceleration mathematical optimizer (MOA) and the mathematical optimization probability (MOP) based on a random number and MOA and MOP. The value of the individual's velocity is updated during the exploration and utilization phases, respectively. The updated velocity value must be kept between the upper and lower bounds of the velocity. The objective function value corresponding to each individual after the update is calculated. If the value is less than the currently recorded best fitness, the best fitness and best position are updated. The above iterative process is repeated until the preset maximum number of iterations is reached. The best position obtained is the optimal velocity value, and the corresponding objective function value is the minimum fuel consumption value.

[0005] Furthermore, the method for establishing the fuel consumption model includes: selecting representative vehicles; selecting a flat, windless test site; designing a series of steady-state driving conditions covering the typical operating speed range of the vehicle; and recording key parameters such as instantaneous fuel consumption, vehicle speed, engine speed, and torque under each steady-state condition.

[0006] Furthermore, the method for determining the objective function includes: selecting a quadratic function form as the fuel consumption model based on the fundamental principles of vehicle dynamics and fuel consumption, wherein the formula for the quadratic function is as follows: In the formula, F(v) represents the fuel consumption of the vehicle per unit time, v represents the vehicle's speed, a is related to air resistance and reflects the increase in fuel consumption caused by air resistance when driving at high speed, b is related to rolling resistance and reflects the change in fuel consumption caused by rolling resistance when driving at low and medium speeds, and c is related to engine idling fuel consumption and represents the basic fuel consumption of the vehicle at idle speed.

[0007] Furthermore, the initial population method includes: defining population-related parameters, setting the number of individuals in the population, setting the range of vehicle speed values ​​based on actual working conditions and vehicle performance; randomly generating an initial population; checking population diversity; and recording the initial population.

[0008] Furthermore, the mathematical optimization probability method includes controlling the probability of individual updates, the value of which gradually decreases during the iteration process to enhance the algorithm's exploration capability. The principle formula is as follows: In the formula, This represents the current iteration number. The maximum number of iterations is denoted by α, which controls the curvature of the MOP descent. As the MOP gradually decreases, the probability of individual updates gradually decreases, thereby reducing interference with the global optimal solution and enhancing the convergence ability of the algorithm.

[0009] Furthermore, the accelerated mathematical optimizer method includes controlling the acceleration of individual updates, the value of which gradually increases during the iteration process to enhance the algorithm's development capability. The principle formula is as follows: MOA determines whether an individual tends to move closer to the global optimum or to conduct a broader search in the solution space.

[0010] Furthermore, the method for updating individual velocity values ​​during the exploration phase includes: if the random number is less than the MOA, then the update formula is: Otherwise, update the formula as follows: ,in, For the best position, For velocity; determine the current iteration state; calculate MOA and MOP; update the velocity value during the exploration phase.

[0011] Furthermore, the iterative process method includes: initializing iteration parameters; calculating the initial population objective function; determining the initial optimal solution; calculating MOA and MOP; updating the individual values ​​in the population during the exploration and development phase; calculating the updated objective function value and updating the optimal solution; and finally completing the iteration to obtain the optimal solution.

[0012] This invention offers the following advantages: It defines the dimension of vehicle speed and its upper and lower bounds, treating vehicle speed as a variable in the optimization problem; it establishes a fuel consumption model, expressed as a function of vehicle speed, used to calculate fuel consumption at different speeds; since existing fuel consumption models typically require extensive experimental data for complex calibration, which is costly and time-consuming, this invention employs a simple quadratic function form, requiring only a few steady-state experiments to complete parameter fitting, significantly reducing calibration costs; because traditional optimization methods are prone to getting trapped in local optima and struggling to find the global optimum, this invention dynamically adjusts MOA and MOP, adaptively balancing exploration and development, effectively avoiding local optima and ensuring the finding of the global optimum; due to complex traffic and road conditions, through real-time data acquisition and feedback control, the optimization strategy can be dynamically adjusted according to real-time traffic and road conditions, meeting real-time requirements. This invention also considers the limited fuel-saving effects of traditional driving methods and optimization approaches, which are insufficient to meet increasingly stringent energy conservation and emission reduction requirements. It designs a real-time optimization algorithm closed-loop control, sending the optimization results to the vehicle control system or the driver's mobile device via a communication module, improving fuel economy and driving comfort. Attached Figure Description

[0013] To more clearly illustrate the implementation of the present invention or the solutions in the prior art, the drawings used in the description of the implementation examples or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a flowchart of a method and system for minimizing vehicle fuel consumption based on the AOA algorithm, provided by an embodiment of the present invention. Detailed Implementation

[0015] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a deep learning-based method and system for segmenting and analyzing precipitates in high-temperature alloys according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0016] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0017] The following description, in conjunction with the accompanying drawings, details a specific scheme for a vehicle fuel consumption minimization method and system based on the AOA algorithm provided by this invention.

[0018] Please see Figure 1 This invention illustrates a method for minimizing vehicle fuel consumption based on the AOA algorithm. The method includes: Step S1: Defining the dimension of vehicle speed and the upper and lower bounds of speed, and using vehicle speed as a variable in the optimization problem; establishing a fuel consumption model, which is expressed as a function of vehicle speed, to calculate fuel consumption at different speeds.

[0019] This invention is primarily applied to vehicle fuel consumption optimization scenarios. To obtain fuel consumption data for vehicles at different speeds, the dimensions and upper and lower bounds of vehicle speed are first defined, and then a mathematical model that accurately describes the relationship between vehicle fuel consumption and speed is established. Since this invention employs the AOA algorithm to optimize vehicle fuel consumption, and the algorithm requires a large dataset sample containing fuel consumption data for vehicles at different speeds, the dataset sample size is ensured to be sufficiently large.

[0020] Preferably, in one embodiment of the present invention, the method for establishing a fuel consumption model includes: using the vehicle's longitudinal speed as a decision variable, and specifying its feasible region. , Subsequently, based on vehicle dynamics and the principle of energy conservation, a quadratic steady-state fuel consumption model was established. F(v) represents the vehicle's fuel consumption per unit time, v represents the vehicle's speed, a is related to air resistance and reflects the increase in fuel consumption caused by air resistance when driving at high speed, b is related to rolling resistance and reflects the change in fuel consumption caused by rolling resistance when driving at medium and low speeds, c is related to engine idling fuel consumption and represents the basic fuel consumption of the vehicle at idle speed, and finally obtains the fuel consumption model.

[0021] Step S2: Determine the objective function, which is to minimize the output value of the fuel consumption model; initialize the population, where each individual in the population represents a possible speed value, and the population size is a pre-set parameter.

[0022] Preferably, in one embodiment of the present invention, the objective function is formalized as minimizing The specific principle formula is as follows: .

[0023] Preferably, the population initialization method includes: constructing an initial population according to a preset population size; ensuring that individuals follow a uniform random distribution within the feasible region to guarantee sufficient coverage and diversity of the initial solution space; and using Latin hypercube sampling to initialize individuals in order to reduce the initial clustering degree and improve the global search efficiency.

[0024] Step S3: In each iteration, calculate the Mathematical Optimizer (MOA) and Mathematical Optimization Probability (MOP) based on the current iteration number; for each individual in the population, update the individual's velocity value in the exploration phase and the exploitation phase respectively based on the random number and the values ​​of MOA and MOP, and the updated velocity value must be kept between the upper and lower bounds of the velocity.

[0025] Preferably, in one embodiment of the present invention, the iterative process adopts an AOA two-stage update strategy; MOA and MOP are calculated based on the current iteration number and the maximum iteration number; each individual in the population is divided into stages; and an arithmetic weighted update is performed based on the current global optimum to ensure that the new individuals always satisfy the boundary constraints.

[0026] Preferably, in one embodiment of the present invention, the method for updating the individual velocity value during the exploration phase includes: if the random number is less than the MOA, then the update formula is: Otherwise, update the formula as follows: ,in, The best position; For speed.

[0027] Step S4: Calculate the objective function value for each individual after the update. If the value is less than the best fitness of the current record, update the best fitness and the best position. Repeat the above iterative process until the preset maximum number of iterations is reached. The best position obtained is the optimal speed value, and the corresponding objective function value is the minimum fuel consumption value.

[0028] Preferably, in one embodiment of the present invention, the iterative process includes: calculating the fitness of the updated individual and recording the corresponding fuel consumption value; terminating the iteration when the number of iterations reaches a preset maximum number of iterations or the fitness improvement is less than a threshold, thereby obtaining the global optimal speed and its corresponding minimum fuel consumption.

[0029] Preferably, in one embodiment of the present invention, the termination criterion considers both the number of iterations and fitness stagnation to prevent overcomputation; finally, v is sent to the vehicle ECU in real time via the CAN bus to achieve closed-loop cruise control, and the measured fuel saving rate is 12.4% ± 1.3% (95% confidence interval) higher than that of the traditional strategy.

[0030] This completes the fuel-saving control of minimizing vehicle fuel consumption.

[0031] In summary, we define the dimension of vehicle speed and its upper and lower bounds, treating vehicle speed as a variable in the optimization problem; establish a fuel consumption model, which is a function of vehicle speed, to calculate fuel consumption at different speeds; determine the objective function, which minimizes the output value of the fuel consumption model; initialize a population, where each individual in the population represents a possible speed value, and the population size is a pre-set parameter; in each iteration, calculate the Mathematical Optimizer (MOA) and Mathematical Optimization Probability (MOP) based on the current iteration count; for each individual in the population, update the individual's speed value during the exploration and utilization phases based on a random number and the values ​​of MOA and MOP, ensuring the updated speed value remains between the upper and lower bounds; calculate the objective function value corresponding to each individual after the update; if this value is less than the currently recorded best fitness, update the best fitness and best position; repeat the above iterative process until the preset maximum number of iterations is reached, and the final best position is the optimal speed value, and the corresponding objective function value is the minimum fuel consumption value.

[0032] An embodiment of the present invention also provides a vehicle fuel consumption minimization system based on the AOA algorithm. This system includes a storage module for storing fuel consumption model parameters, population data, optimization results, and other information; a parameter adjustment module for adjusting fuel consumption model parameters, population size, maximum iteration count, and control parameter α according to actual operating conditions; a simulation module for simulating the fuel consumption optimization process under different operating conditions to verify the effectiveness and adaptability of the optimization algorithm; an analysis module for statistically analyzing the optimization results and generating a fuel consumption optimization report; a data acquisition module for real-time acquisition of vehicle speed, fuel consumption, and other relevant parameters; a display module for displaying real-time data, fuel consumption optimization curves, and optimal speed value suggestions during the optimization process; and a communication module for sending the optimization results to the vehicle control system or the driver's mobile device. The system is characterized in that when executing the computer program, it implements the steps of the vehicle fuel consumption minimization method based on the AOA algorithm as described in any one of claims 1 to 4.

[0033] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0034] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for minimizing vehicle fuel consumption based on the AOA algorithm, characterized in that, The method includes: defining the dimension of vehicle speed and its upper and lower bounds, treating vehicle speed as a variable in the optimization problem; establishing a fuel consumption model, which is expressed as a function of vehicle speed, used to calculate fuel consumption at different speeds; determining an objective function, which minimizes the output value of the fuel consumption model; initializing a population, where each individual in the population represents a possible speed value, and the population size is a pre-set parameter; calculating the Mathematical Optimizer (MOA) and Mathematical Optimization Probability (MOP) based on the current iteration count; updating the speed value of each individual in the population during the exploration and utilization phases based on a random number and the values ​​of MOA and MOP, respectively, ensuring that the updated speed value remains between the upper and lower bounds; calculating the objective function value corresponding to each individual after the update, and if this value is less than the currently recorded best fitness, updating the best fitness and best position; repeating the above iterative process until the preset maximum number of iterations is reached, and the final best position is the optimal speed value, and the corresponding objective function value is the minimum fuel consumption value.

2. The method for minimizing vehicle fuel consumption based on the AOA algorithm according to claim 1, characterized in that, The fuel consumption model is in quadratic function form, and its specific expression is as follows: Where a, b, and c are model parameters. The vehicle's speed is the reference point. This fuel consumption model is based on the fundamental principles of vehicle dynamics and fuel consumption. During vehicle operation, the engine needs to overcome various resistances, including air resistance, rolling resistance, and the vehicle's own inertia, thus consuming fuel. Air resistance is proportional to the square of the vehicle's speed, rolling resistance is linearly related to the vehicle's speed, while the engine's idling fuel consumption is constant. Therefore, the quadratic function form of the fuel consumption model can better reflect the relationship between vehicle fuel consumption and speed. The model parameters a, b, and c can be obtained by fitting experimental data. Specifically, the actual fuel consumption of the vehicle is measured at different speeds, and then the model parameters are determined using fitting methods such as the least squares method, enabling the model to accurately describe the vehicle's fuel consumption characteristics under different operating conditions.

3. The method for minimizing vehicle fuel consumption based on the AOA algorithm according to claim 1, characterized in that, The method for updating individual velocity values ​​during the exploration phase includes: if the random number is less than MOA, the update formula is: Otherwise, update the formula as follows: ,in, The best position; For speed.

4. The method for minimizing vehicle fuel consumption based on the AOA algorithm according to claim 1, characterized in that, The method further includes the following steps: during each iteration, recording the speed value and corresponding fuel consumption value of each individual in the current population; after the iteration ends, generating a fuel consumption optimization curve to analyze the convergence and stability of the optimization process; and providing suggestions for the optimal speed value based on the optimization results to guide actual driving operations.

5. A vehicle fuel consumption minimization system based on the AOA algorithm, the system further comprising: The storage module is used to store information such as fuel consumption model parameters, population data, and optimization results; The parameter tuning module is used to adjust the fuel consumption model parameters, population size, maximum number of iterations, and control parameter α according to actual operating conditions. The simulation module is used to simulate the fuel consumption optimization process under different operating conditions to verify the effectiveness and adaptability of the optimization algorithm. The analysis module performs statistical analysis on the optimization results and generates a fuel consumption optimization report. The data acquisition module collects vehicle speed, fuel consumption, and other relevant parameters in real time. The display module is used to display real-time data, fuel consumption optimization curves, and optimal speed recommendations during the optimization process. A communication module is used to send optimization results to a vehicle control system or a driver's mobile device, characterized in that when the system executes the computer program, it implements the steps of a vehicle fuel consumption minimization method based on the AOA algorithm as described in any one of claims 1 to 4.

Images