A method and system for calibrating a low temperature start threshold for a natural gas vehicle

Abstract

The application provides a natural gas vehicle low-temperature starting temperature threshold calibration method and system, which comprises the following steps: constructing a mapping database of gas component-temperature-physical property parameters; adjusting the ignition coil voltage and ignition advance angle of each cylinder group of the engine in a gradient manner to determine the optimal ignition parameter interval of each cylinder group at different low temperatures; dividing the starting process of the target vehicle into an idle starting stage and a low-speed warming-up stage, combining the optimal ignition parameter interval, taking the starting stability and gas consumption rate of each stage as constraint conditions, and using a particle swarm algorithm to iteratively solve the critical starting temperature of each stage to obtain an initial temperature threshold; constructing a threshold correction function based on time series data, and synchronously correcting the initial temperature threshold through the threshold correction function to calibrate the target low-temperature starting temperature threshold corresponding to the target vehicle. The application can objectively and accurately calibrate the starting temperature and improve the efficiency.

Description

Technical Field

[0001] This invention relates to the field of automotive technology, and in particular to a method and system for calibrating the low-temperature start-up temperature threshold of natural gas vehicles. Background Technology

[0002] Compressed natural gas (CNG) is widely used in commercial and passenger vehicles due to its cleanliness, environmental friendliness, and low carbon emissions, especially in pickup trucks and taxis. However, CNG vehicles face difficulties starting in cold environments (-30°C and below), severely limiting their adoption in such conditions. The industry generally adopts a "gasoline-assisted starting" solution, the core of which is setting the starting and fuel switching temperature thresholds. Therefore, accurate threshold calibration is crucial for ensuring adaptability in cold regions.

[0003] The existing "gasoline-assisted start" strategy controls fuel switching by setting a fixed temperature threshold, such as "starting with gasoline when the ambient temperature is below 0°C and switching back to natural gas when the coolant temperature is above 70°C". However, the existing temperature thresholds lack a targeted and precise calibration method and are mostly determined by analogy with other models or rough testing, without a systematic calibration process adapted to specific models.

[0004] Furthermore, different natural gas vehicles exhibit significant differences in parameters such as gas supply pipelines, engine compartment layout, and thermal management efficiency, resulting in varying requirements for start-up and switching temperatures. Fixed or empirically based thresholds cannot be accurately matched, leading to problems such as start-up failures, switching jitter, and even engine stalling in cold regions, impacting user experience and vehicle reliability. Therefore, existing technologies lack scientifically accurate temperature threshold calibration methods, necessitating the development of targeted low-temperature start-up temperature threshold calibration methods for natural gas vehicles to address these shortcomings. Summary of the Invention

[0005] Based on this, the purpose of this invention is to provide a method and system for calibrating the low-temperature start-up temperature threshold of natural gas vehicles, so as to solve the problem that the existing technology cannot objectively and accurately calibrate the low-temperature start-up temperature threshold of different natural gas vehicles, which easily leads to start-up failure, switching vibration or even stalling.

[0006] The first aspect of the present invention proposes:

[0007] A method for calibrating the low-temperature start-up temperature threshold of a natural gas vehicle, specifically including the following steps:

[0008] The composition data of the natural gas used in the target vehicle are collected, and the dew point, atomization particle size and combustion rate corresponding to the composition data at different temperatures are detected simultaneously through a low temperature physical property testing device, so as to construct a mapping database of gas composition-temperature-physical property parameters;

[0009] Based on the mapping database, different low temperature gradients are simulated in the environmental simulation chamber, and the ignition coil voltage and ignition advance angle of each cylinder group of the engine are simultaneously adjusted in a gradient manner to determine the optimal ignition parameter range of each cylinder group under different low temperatures.

[0010] The starting process of the target vehicle is divided into an idle start-up stage and a low-speed warm-up stage. Combining the optimal ignition parameter range, and with the starting stability and fuel consumption rate of each stage as constraints, the particle swarm optimization algorithm is used to iteratively solve the critical start-up temperature of different stages to obtain the initial temperature threshold.

[0011] Real-world vehicle start-up data from different years of use and different low-temperature regions are collected to construct a threshold correction function based on time-series data. The initial temperature threshold is then corrected using the threshold correction function to calibrate the target low-temperature start-up temperature threshold corresponding to the target vehicle.

[0012] The beneficial effects of this invention are as follows: This solution constructs a database mapping gas composition, temperature, and physical property parameters, determines the optimal ignition parameter range for each cylinder group at different low temperatures, iteratively solves the initial temperature threshold using a particle swarm optimization algorithm, and corrects the target threshold based on real vehicle time-series data. This allows for the objective and accurate calibration of the low-temperature start-up temperature threshold for different natural gas vehicles, effectively solving the problems of start-up failure, switching jitter, and stalling in the prior art, and improving the stability of vehicle low-temperature start-up and gas utilization efficiency.

[0013] Furthermore, the step of gradient-adjusting the ignition coil voltage and ignition advance angle of each cylinder group of the engine to determine the optimal ignition parameter range for each cylinder group at different low temperatures includes:

[0014] Based on the simulation results of the flow field inside the engine cylinder, a multi-field coupling model of temperature field, flow field and combustion field is constructed, and the key influencing factors of the ignition coil voltage and the ignition advance angle are detected simultaneously according to the multi-field coupling model;

[0015] Using the aforementioned key influencing factors as feedback variables, the cylinder pressure curves, combustion heat release rates, and vibration signals of each cylinder group are collected accordingly. The adjustment step size is dynamically corrected through a PID algorithm to obtain the candidate ignition parameter set for each cylinder group.

[0016] The extreme fluctuation conditions of the target at low temperature are simulated in the environmental simulation chamber, and the candidate ignition parameter set is simultaneously subjected to extreme verification to generate the optimal ignition parameter range.

[0017] Furthermore, the step of performing limit verification on the candidate ignition parameter set to generate the optimal ignition parameter range includes:

[0018] Collect real-world extreme start-up failure cases of the target vehicle model in low-temperature regions, and simultaneously extract the operating condition timing features when the failure occurs, so as to detect the corresponding timing logic in the operating condition timing features;

[0019] Based on the timing logic, the parameters in the candidate ignition parameter set are dynamically verified one by one, and the combustion heat release rate curve, the highest temperature in the cylinder and the exhaust oxygen concentration signal generated during the verification process are collected simultaneously to output the corresponding verification value.

[0020] The verification values ​​are subjected to correlation verification, and a continuous parameter interval is generated simultaneously through polynomial fitting to generate the corresponding optimal firing parameter interval.

[0021] Furthermore, the step of using the particle swarm optimization algorithm to iteratively solve for the critical start-up temperature at different stages to obtain the initial temperature threshold includes:

[0022] Based on the critical start-up temperature and physical property adaptation coefficient of the idle start-up stage and the low-speed warm-up stage, the corresponding three-dimensional optimization variables are constructed, and the corresponding particle position vector is constructed simultaneously using temperature-coefficient coupling encoding.

[0023] An initial population adapted to the critical start-up temperature is constructed, and the initial population is iteratively optimized according to the three-dimensional optimization variables and the particle position vector.

[0024] Extract the critical temperature corresponding to the globally optimal particle, and simultaneously generate the initial temperature threshold based on the critical temperature.

[0025] Furthermore, the step of iteratively optimizing the initial population based on the three-dimensional optimization variables and the particle position vector includes:

[0026] Based on the optimal ignition parameter range, a three-layer constraint of temperature-physical property-ignition is constructed, and effective particles are simultaneously screened from the initial population according to the three-layer constraint.

[0027] Based on startup stability and gas consumption rate as the basic objectives, an ignition parameter adaptation deviation correction term is introduced to calculate the fitness value corresponding to each effective particle.

[0028] If the fitness value is detected to meet the preset conditions, the iteration stops and the corresponding optimal particle is output.

[0029] Furthermore, the step of correcting the initial temperature threshold using the threshold correction function to determine the target low-temperature start-up temperature threshold corresponding to the target vehicle includes:

[0030] A domain adaptive algorithm is used to correct the distribution deviation of the actual vehicle start-up data for different service years and different low-temperature regions, and the corresponding core factors are extracted simultaneously through grey relational analysis.

[0031] The in-cylinder dynamic changes of the engine during the start-up process under different operating conditions are simulated, and a dynamic correction coefficient adapted to the initial temperature threshold is generated with the minimum combustion pressure for successful start-up as a constraint.

[0032] Substitute the dynamic correction coefficient into the threshold correction function to obtain the corresponding initial correction threshold range, and simultaneously generate the target low-temperature start-up temperature threshold based on the initial correction threshold range.

[0033] Furthermore, the step of generating the target low-temperature start-up temperature threshold based on the initial correction threshold range includes:

[0034] Based on the extreme operating condition parameters, the feasibility of starting each candidate threshold within the initial correction threshold range is verified by Monte Carlo simulation in order to eliminate invalid candidate values ​​and simultaneously obtain the intermediate threshold range.

[0035] Based on the core factors, each candidate threshold within the intermediate threshold range is scored and filtered to obtain the optimal threshold set.

[0036] Each candidate value in the optimal threshold set is tested on a real vehicle. By collecting the corresponding feedback signals, if the feedback signals are found to meet the preset requirements, the optimal threshold set is set as the target low-temperature start-up temperature threshold.

[0037] The second aspect of the present invention proposes:

[0038] A low-temperature start-up temperature threshold calibration system for natural gas vehicles, wherein the system comprises:

[0039] The detection module is used to collect the composition data of the natural gas used in the target vehicle, and simultaneously detect the dew point, atomization particle size and combustion rate corresponding to the composition data at different temperatures through a low temperature physical property testing device, so as to construct a mapping database of gas composition-temperature-physical property parameters;

[0040] The adjustment module is used to simulate different low temperature gradients in the environmental simulation chamber based on the mapping database, and simultaneously adjust the ignition coil voltage and ignition advance angle of each cylinder group of the engine to determine the optimal ignition parameter range of each cylinder group under different low temperatures.

[0041] The segmentation module is used to divide the starting process of the target vehicle into an idle start-up stage and a low-speed warm-up stage. Combined with the optimal ignition parameter range, and with the starting stability and fuel consumption rate of each stage as constraints, the particle swarm optimization algorithm is used to iteratively solve the critical start-up temperature of different stages to obtain the initial temperature threshold.

[0042] The module is used to collect real vehicle start-up data from different years of use and different low-temperature regions to construct a threshold correction function based on time-series data. Simultaneously, the initial temperature threshold is corrected through the threshold correction function to calibrate the target low-temperature start-up temperature threshold corresponding to the target vehicle.

[0043] Furthermore, the adjustment module is specifically used for:

[0044] Based on the simulation results of the flow field inside the engine cylinder, a multi-field coupling model of temperature field, flow field and combustion field is constructed, and the key influencing factors of the ignition coil voltage and the ignition advance angle are detected simultaneously according to the multi-field coupling model;

[0045] Using the aforementioned key influencing factors as feedback variables, the cylinder pressure curves, combustion heat release rates, and vibration signals of each cylinder group are collected accordingly. The adjustment step size is dynamically corrected through a PID algorithm to obtain the candidate ignition parameter set for each cylinder group.

[0046] The extreme fluctuation conditions of the target at low temperature are simulated in the environmental simulation chamber, and the candidate ignition parameter set is simultaneously subjected to extreme verification to generate the optimal ignition parameter range.

[0047] Furthermore, the adjustment module is specifically used for:

[0048] Collect real-world extreme start-up failure cases of the target vehicle model in low-temperature regions, and simultaneously extract the operating condition timing features when the failure occurs, so as to detect the corresponding timing logic in the operating condition timing features;

[0049] Based on the timing logic, the parameters in the candidate ignition parameter set are dynamically verified one by one, and the combustion heat release rate curve, the highest temperature in the cylinder and the exhaust oxygen concentration signal generated during the verification process are collected simultaneously to output the corresponding verification value.

[0050] The verification values ​​are subjected to correlation verification, and a continuous parameter interval is generated simultaneously through polynomial fitting to generate the corresponding optimal firing parameter interval.

[0051] Furthermore, the partitioning module is specifically used for:

[0052] Based on the critical start-up temperature and physical property adaptation coefficient of the idle start-up stage and the low-speed warm-up stage, the corresponding three-dimensional optimization variables are constructed, and the corresponding particle position vector is constructed simultaneously using temperature-coefficient coupling encoding.

[0053] An initial population adapted to the critical start-up temperature is constructed, and the initial population is iteratively optimized according to the three-dimensional optimization variables and the particle position vector.

[0054] Extract the critical temperature corresponding to the globally optimal particle, and simultaneously generate the initial temperature threshold based on the critical temperature.

[0055] Furthermore, the partitioning module is specifically used for:

[0056] Based on the optimal ignition parameter range, a three-layer constraint of temperature-physical property-ignition is constructed, and effective particles are simultaneously screened from the initial population according to the three-layer constraint.

[0057] Based on startup stability and gas consumption rate as the basic objectives, an ignition parameter adaptation deviation correction term is introduced to calculate the fitness value corresponding to each effective particle.

[0058] If the fitness value is detected to meet the preset conditions, the iteration stops and the corresponding optimal particle is output.

[0059] Furthermore, the building module is specifically used for:

[0060] A domain adaptive algorithm is used to correct the distribution deviation of the actual vehicle start-up data for different service years and different low-temperature regions, and the corresponding core factors are extracted simultaneously through grey relational analysis.

[0061] The in-cylinder dynamic changes of the engine during the start-up process under different operating conditions are simulated, and a dynamic correction coefficient adapted to the initial temperature threshold is generated with the minimum combustion pressure for successful start-up as a constraint.

[0062] Substitute the dynamic correction coefficient into the threshold correction function to obtain the corresponding initial correction threshold range, and simultaneously generate the target low-temperature start-up temperature threshold based on the initial correction threshold range.

[0063] Furthermore, the building module is specifically used for:

[0064] Based on the extreme operating condition parameters, the feasibility of starting each candidate threshold within the initial correction threshold range is verified by Monte Carlo simulation in order to eliminate invalid candidate values ​​and simultaneously obtain the intermediate threshold range.

[0065] Based on the core factors, each candidate threshold within the intermediate threshold range is scored and filtered to obtain the optimal threshold set.

[0066] Each candidate value in the optimal threshold set is tested on a real vehicle. By collecting the corresponding feedback signals, if the feedback signals are found to meet the preset requirements, the optimal threshold set is set as the target low-temperature start-up temperature threshold.

[0067] The third aspect of the present invention proposes:

[0068] A computer includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the natural gas vehicle low-temperature start-up temperature threshold calibration method as described above.

[0069] The fourth aspect of the present invention proposes:

[0070] A readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method for calibrating the low-temperature start-up temperature threshold of a natural gas vehicle as described above.

[0071] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0072] Figure 1 This is a flowchart of the method for calibrating the low-temperature start-up temperature threshold of a natural gas vehicle according to the first embodiment of the present invention;

[0073] Figure 2 The structural block diagram of the natural gas vehicle low-temperature start-up temperature threshold calibration system provided in the third embodiment of the present invention is shown.

[0074] The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0075] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0076] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0077] 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. The terminology used herein in the specification of this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0078] Please see Figure 1 The figure shows a method for calibrating the low-temperature starting temperature threshold of a natural gas vehicle according to the first embodiment of the present invention. The method for calibrating the low-temperature starting temperature threshold of a natural gas vehicle provided in this embodiment can objectively and accurately calibrate the low-temperature starting temperature of a natural gas vehicle, thereby improving the starting efficiency.

[0079] Specifically, this embodiment provides:

[0080] A method for calibrating the low-temperature start-up temperature threshold of a natural gas vehicle, specifically including the following steps:

[0081] Step S10: Collect the composition data of the natural gas used in the target vehicle, and simultaneously use a low-temperature physical property testing device to detect the dew point, atomization particle size and combustion rate corresponding to the composition data at different temperatures, so as to construct a mapping database of gas composition-temperature-physical property parameters.

[0082] It should be noted that, firstly, to address the issue of variations in low-temperature physical properties (dew point, atomization particle size, combustion rate) caused by the diversity of natural gas components (such as differences in the proportion of methane and ethane), the composition data of the natural gas used in the target vehicle (such as the volume fraction of each component detected by gas chromatography) is collected. Simultaneously, low-temperature physical property testing devices (such as a low-temperature environment chamber, laser particle size analyzer, and combustion rate tester) are used to detect the dew point (the critical temperature for the precipitation of liquid hydrocarbons in natural gas; excessively high dew points can easily lead to fuel line blockage), atomization particle size (smaller particle size results in more uniform mixing and higher combustion efficiency), and combustion rate (a decrease in combustion rate at low temperatures can easily lead to start-up failure) at different temperatures (such as -40℃ to 0℃). A mapping database of gas composition, temperature, and physical properties is constructed. Specifically, this database is the basis for subsequent ignition parameter optimization and temperature threshold solution, avoiding the shortcomings of traditional calibration that ignores differences in fuel composition.

[0083] Step S20: Based on the mapping database, simulate different low temperature gradients in the environmental simulation chamber, and simultaneously adjust the ignition coil voltage and ignition advance angle of each cylinder group of the engine to determine the optimal ignition parameter range of each cylinder group under different low temperatures.

[0084] It should be noted that, secondly, to address the issue of poor adaptability of ignition parameters at low temperatures, different low-temperature gradients (e.g., every 5°C as a gradient, covering the target low-temperature range) are simulated in an environmental simulation chamber based on a mapping database. Simultaneously, the ignition coil voltage of each cylinder group of the engine is adjusted (too low a voltage will not break down the air-fuel mixture, too high a voltage will easily damage the ignition coil) and the ignition advance angle (too large an advance angle will easily cause detonation, too small an advance angle will result in incomplete combustion). By controlling a single variable, the starting effect of different combinations of ignition parameters is tested at each low-temperature gradient. In-cylinder combustion pressure, starting time, exhaust pollutants, and other indicators are collected to determine the optimal ignition parameter range for each cylinder group at different low temperatures. Specifically, cylinder group calibration can solve the problem of uneven starting caused by differences between cylinders in multi-cylinder engines. The optimal ignition parameter range provides key parameter constraints for subsequent critical temperature calculation.

[0085] Step S30: Divide the starting process of the target vehicle into an idle start-up stage and a low-speed warm-up stage. Combined with the optimal ignition parameter range, and with the starting stability and fuel consumption rate of each stage as constraints, use the particle swarm optimization algorithm to iteratively solve the critical start-up temperature of different stages to obtain the initial temperature threshold.

[0086] It should be noted that, considering that the low-temperature start-up of natural gas vehicles is divided into an idling start-up stage (from ignition to stable idling, the core is to ensure stable flame propagation) and a low-speed warm-up stage (from idling to low-speed operation, the core is to increase the cylinder temperature and reduce gas consumption), the start-up requirements and constraints of the two stages are different. Therefore, combining the optimal ignition parameter range, and using the start-up stability (e.g., speed fluctuation rate ≤ 5%) and gas consumption rate (e.g., gas consumption ≤ 5m³ / h in the idling stage) of each stage as constraints, the particle swarm optimization algorithm is used to iteratively solve the critical start-up temperature of different stages. The particle swarm optimization algorithm has global optimization capabilities and can quickly find the lowest temperature value that meets the start-up requirements under multiple constraints, i.e., the initial temperature threshold. Specifically, the staged solution ensures the adaptability of the threshold in different start-up stages and avoids the problem that a single threshold cannot take into account the entire start-up process.

[0087] Step S40: Collect real vehicle start-up data from different years of use and different low-temperature regions to construct a threshold correction function based on time-series data. Simultaneously, use the threshold correction function to correct the initial temperature threshold to calibrate the target low-temperature start-up temperature threshold corresponding to the target vehicle.

[0088] It should be noted that, finally, to address the shortcomings of the initial temperature threshold not considering vehicle age (such as decreased sealing due to engine wear in older vehicles) and regional differences in low temperatures (such as the impact of low air pressure on combustion in high-altitude areas), real-world vehicle start-up data of different ages and in different low-temperature regions were collected (e.g., the start-up success rate of a 5-year-old vehicle in Northeast China at -30℃, and the start-up parameters of a 2-year-old vehicle in Northwest China at -20℃). A threshold correction function based on time-series data was constructed (function variables include age, regional altitude, and ambient humidity). The initial temperature threshold was compensated and corrected through the correction function, and finally, a target low-temperature start-up temperature threshold that is fully compatible with the target vehicle was calibrated. Specifically, the real-world data correction transformed the threshold from "laboratory calibration" to "actual operating condition adaptation," significantly improving the low-temperature start-up success rate.

[0089] Second Embodiment

[0090] Furthermore, the step of gradient-adjusting the ignition coil voltage and ignition advance angle of each cylinder group of the engine to determine the optimal ignition parameter range for each cylinder group at different low temperatures includes:

[0091] Based on the simulation results of the flow field inside the engine cylinder, a multi-field coupling model of temperature field, flow field and combustion field is constructed, and the key influencing factors of the ignition coil voltage and the ignition advance angle are detected simultaneously according to the multi-field coupling model;

[0092] Using the aforementioned key influencing factors as feedback variables, the cylinder pressure curves, combustion heat release rates, and vibration signals of each cylinder group are collected accordingly. The adjustment step size is dynamically corrected through a PID algorithm to obtain the candidate ignition parameter set for each cylinder group.

[0093] The extreme fluctuation conditions of the target at low temperature are simulated in the environmental simulation chamber, and the candidate ignition parameter set is simultaneously subjected to extreme verification to generate the optimal ignition parameter range.

[0094] It should be noted that, firstly, due to the complex coupling relationship between the temperature field (low cylinder wall temperature at low temperatures affects air-fuel mixture ignition), flow field (intake vortex intensity affects air-fuel mixture uniformity), and combustion field (flame propagation speed affects combustion stability) within the engine cylinder, a multi-field coupling model of temperature field, flow field, and combustion field is constructed based on the simulation results of the flow field within the engine cylinder (such as the in-cylinder airflow velocity distribution and vortex ratio data obtained through CFD simulation). This model can accurately depict the correlation between "ignition parameters - in-cylinder multi-field states - combustion effect," and through simulation analysis, the key influencing factors of ignition coil voltage and ignition advance angle (such as voltage affecting spark energy and advance angle affecting flame propagation phase) are determined. Specifically, multi-field coupling modeling avoids the one-sidedness of traditional empirical adjustment and provides a theoretical basis for the precise adjustment of ignition parameters.

[0095] Secondly, using key influencing factors as feedback variables (such as increasing the ignition coil voltage when spark energy is insufficient), the cylinder pressure curves (reflecting changes in in-cylinder combustion pressure and determining whether combustion is complete), combustion heat release rate (reflecting combustion speed; a low heat release rate can easily lead to start-up failure), and vibration signals (reflecting engine running stability; excessive vibration indicates uneven combustion) of each cylinder group were collected. Simultaneously, the adjustment step size of the ignition parameters was dynamically corrected using a PID algorithm: when the combustion effect deviates significantly from the target value, the adjustment step size was increased to accelerate convergence; when the deviation was small, the step size was decreased to avoid overshoot. Through multiple rounds of testing, candidate ignition parameter sets for each cylinder group were obtained. Specifically, the PID dynamic correction ensured the stability and efficiency of the adjustment process, and the candidate parameter set provided a rich sample basis for subsequent limit verification.

[0096] Finally, to ensure the reliability of the ignition parameter range under extreme conditions, extreme fluctuations in the target low temperature were simulated in an environmental simulation chamber (such as low temperature + sudden change in intake humidity, low temperature + instantaneous fluctuation of fuel composition). The candidate ignition parameter set was subjected to extreme verification: the starting success rate, combustion stability and exhaust pollutant emissions of each candidate parameter combination under extreme conditions were tested, and parameter combinations that failed to start or did not meet the performance standards were eliminated. The verified parameter combinations were integrated to generate the optimal ignition parameter range covering different low temperature gradients and different cylinder groups. Specifically, the extreme condition verification improved the robustness of the parameter range and ensured that the vehicle could still start stably in complex low temperature environments.

[0097] Furthermore, the step of performing limit verification on the candidate ignition parameter set to generate the optimal ignition parameter range includes:

[0098] Collect real-world extreme start-up failure cases of the target vehicle model in low-temperature regions, and simultaneously extract the operating condition timing features when the failure occurs, so as to detect the corresponding timing logic in the operating condition timing features;

[0099] Based on the timing logic, the parameters in the candidate ignition parameter set are dynamically verified one by one, and the combustion heat release rate curve, the highest temperature in the cylinder and the exhaust oxygen concentration signal generated during the verification process are collected simultaneously to output the corresponding verification value.

[0100] The verification values ​​are subjected to correlation verification, and a continuous parameter interval is generated simultaneously through polynomial fitting to generate the corresponding optimal firing parameter interval.

[0101] It should be noted that, firstly, real-world extreme starting failure cases of the target vehicle model in low-temperature regions are collected (such as flameout during starting at -35℃, or excessive engine vibration due to detonation). The timing characteristics of the operating conditions at the time of the failure are extracted (such as changes in ignition voltage before the failure, cylinder pressure curve trends, and fluctuation patterns of fuel composition). The corresponding timing logic is then detected (such as "ignition voltage below 8kV + cylinder pressure peak below 0.5MPa → starting failure"). Specifically, the timing logic of the failure cases provides clear failure boundaries for parameter verification, preventing the verification process from deviating from the actual failure scenario.

[0102] Secondly, based on the extracted timing logic, the parameters in the candidate ignition parameter set are dynamically verified one by one: the fault timing logic is reproduced in the environmental simulation chamber, the starting performance of each candidate parameter combination under fault boundary conditions is tested, and the combustion heat release rate curve (to determine whether the flame propagation is stable), the highest cylinder temperature (to determine whether there is a risk of detonation) and the exhaust oxygen concentration signal (to determine whether the combustion is complete) generated during the verification process are collected simultaneously, and the corresponding verification values ​​(such as starting success rate and combustion efficiency score) are output. In particular, dynamic verification combines actual fault scenarios and is more in line with the actual use of vehicles than conventional steady-state verification.

[0103] Finally, the correlation of the verification values ​​is checked: the correlation strength between combustion heat release rate, maximum in-cylinder temperature, exhaust oxygen concentration and start-up success rate is analyzed, and invalid verification values ​​with low correlation are eliminated; discrete candidate parameter combinations are transformed into continuous parameter ranges through polynomial fitting (e.g., the optimal range of ignition coil voltage at -30℃ is 10kV~14kV, and the ignition advance angle is 5°~12°), and finally the optimal ignition parameter range is generated. Specifically, continuous parameter ranges are more practical for engineering than discrete parameters and can directly guide the parameter settings of the engine ECU.

[0104] Furthermore, the step of using the particle swarm optimization algorithm to iteratively solve for the critical start-up temperature at different stages to obtain the initial temperature threshold includes:

[0105] Based on the critical start-up temperature and physical property adaptation coefficient of the idle start-up stage and the low-speed warm-up stage, the corresponding three-dimensional optimization variables are constructed, and the corresponding particle position vector is constructed simultaneously using temperature-coefficient coupling encoding.

[0106] An initial population adapted to the critical start-up temperature is constructed, and the initial population is iteratively optimized according to the three-dimensional optimization variables and the particle position vector.

[0107] Extract the critical temperature corresponding to the globally optimal particle, and simultaneously generate the initial temperature threshold based on the critical temperature.

[0108] It should be noted that, firstly, based on the critical starting temperatures (the core variables to be solved) and property matching coefficients (reflecting the degree of matching between gas properties and ignition parameters, such as the higher the matching coefficient for smaller atomized particle size) during the idling start-up and low-speed warm-up phases, corresponding three-dimensional optimization variables (idling critical temperature, warm-up critical temperature, and property matching coefficients) are constructed. Simultaneously, a temperature-coefficient coupling coding method is used to construct particle position vectors: each dimension of the vector corresponds to an optimization variable, and the position of the particle represents a set of candidate critical temperatures and matching coefficient combinations. Specifically, the coupling coding achieves multi-variable collaborative optimization, avoiding the limitations of single-variable optimization.

[0109] Secondly, an initial population adapted to the critical start-up temperature is constructed: the number of particles in the population is determined according to the dimension of the optimization variables (e.g., 50-100 particles for three-dimensional variables), and the initial positions of the particles cover the possible critical temperature range (e.g., -40℃ to 0℃) and the property adaptation coefficient range (e.g., 0.6 to 1.0). Based on the three-dimensional optimization variables and particle position vectors, the velocity-position update formula of the particle swarm optimization algorithm is used to iteratively optimize the initial population: each particle adjusts its velocity and position according to its own historical best position and global best position, gradually approaching the optimal solution that satisfies the constraints. Specifically, the reasonable setting of the initial population ensures the global coverage of the optimization process and avoids getting trapped in local optima.

[0110] Finally, during the iteration process, the start-up stability and gas consumption rate corresponding to each particle are calculated in real time. When the index corresponding to a particle meets the constraints, it is marked as a potential optimal particle. After the iteration ends, the critical temperature value corresponding to the global optimal particle is extracted (such as the critical temperature of the idling stage -28℃ and the critical temperature of the warm-up stage -25℃). The critical temperatures of the two stages are integrated to generate the initial temperature threshold. Specifically, the extraction of the global optimal particle ensures the optimality of the initial threshold under multiple constraints.

[0111] Furthermore, the step of iteratively optimizing the initial population based on the three-dimensional optimization variables and the particle position vector includes:

[0112] Based on the optimal ignition parameter range, a three-layer constraint of temperature-physical property-ignition is constructed, and effective particles are simultaneously screened from the initial population according to the three-layer constraint.

[0113] Based on startup stability and gas consumption rate as the basic objectives, an ignition parameter adaptation deviation correction term is introduced to calculate the fitness value corresponding to each effective particle.

[0114] If the fitness value is detected to meet the preset conditions, the iteration stops and the corresponding optimal particle is output.

[0115] It should be noted that, firstly, a three-layer constraint system of temperature, physical properties, and ignition is constructed based on the optimal ignition parameter range: temperature constraint limits the range of critical temperature (e.g., not lower than -40℃), physical property constraint requires the gas physical property parameters to be within a reasonable range in the mapping database (e.g., atomized particle size ≤ 50μm), and ignition constraint requires the ignition parameters to be within the optimal range (e.g., voltage 10kV~14kV). Based on these three layers of constraints, effective particles are screened in the initial population, and invalid particles that exceed the constraint range are removed. Specifically, constraint screening significantly reduces the workload of iterative calculations and improves optimization efficiency.

[0116] Secondly, based on the starting stability (speed fluctuation rate) and gas consumption rate as the basic objectives, an ignition parameter adaptation deviation correction term is introduced (such as adding a penalty value when the ignition parameters deviate from the optimal range), and a fitness function is constructed to calculate the fitness value corresponding to each effective particle. The higher the fitness value, the better the combination of the critical temperature and adaptation coefficient of the particle. Specifically, the introduction of the ignition parameter adaptation deviation correction term ensures that the optimal solution not only meets the temperature requirements, but also adapts to the optimal ignition parameter range.

[0117] Finally, preset conditions for stopping the iteration are set (such as the rate of change of fitness value ≤1% for 10 consecutive generations, or reaching the maximum number of iterations): if the fitness value is found to meet the preset conditions, it means that the optimization process has converged and the iteration stops; the global optimal particle at this time is extracted and the corresponding critical temperature value is output. Specifically, the setting of the iteration stopping conditions balances the optimization accuracy and computational efficiency, and avoids the waste of computing power caused by excessive iteration.

[0118] Furthermore, the step of correcting the initial temperature threshold using the threshold correction function to determine the target low-temperature start-up temperature threshold corresponding to the target vehicle includes:

[0119] A domain adaptive algorithm is used to correct the distribution deviation of the actual vehicle start-up data for different service years and different low-temperature regions, and the corresponding core factors are extracted simultaneously through grey relational analysis.

[0120] The in-cylinder dynamic changes of the engine during the start-up process under different operating conditions are simulated, and a dynamic correction coefficient adapted to the initial temperature threshold is generated with the minimum combustion pressure for successful start-up as a constraint.

[0121] Substitute the dynamic correction coefficient into the threshold correction function to obtain the corresponding initial correction threshold range, and simultaneously generate the target low-temperature start-up temperature threshold based on the initial correction threshold range.

[0122] It should be noted that, firstly, due to the distribution deviation of real-world vehicle start-up data from different service years and low-temperature regions (e.g., the data distribution of older vehicles differs from that of newer vehicles, and the data distribution of high-altitude regions differs from that of plains), a domain adaptive algorithm is used to correct the data distribution deviation. This involves using laboratory calibration data as the source domain and real-world vehicle data as the target domain, transforming the target domain data into a form consistent with the source domain data distribution through feature mapping. Simultaneously, grey relational analysis is used to extract the core factors affecting start-up performance (e.g., vehicle service life, regional altitude, and ambient humidity). Specifically, the domain adaptive algorithm addresses the correction deviation caused by inconsistent data distribution, and the extraction of core factors provides key variables for constructing the correction function.

[0123] Secondly, engine dynamics simulation models (such as GT-Power) are used to simulate the in-cylinder dynamic changes during the engine start-up process under different operating conditions (such as the changes in in-cylinder pressure, temperature, and air-fuel mixture concentration). The minimum combustion pressure for successful start-up (such as 0.5 MPa, below which the flame cannot propagate stably) is used as a constraint. Combined with the extracted core factors, a dynamic correction coefficient adapted to the initial temperature threshold is generated: for example, the correction coefficient increases by 0.05 for every year of service life; and by 0.08 for every 1000m increase in altitude. Specifically, the minimum combustion pressure constraint ensures that the corrected threshold still meets the basic requirements for start-up, and the dynamic correction coefficient achieves accurate compensation for vehicle service life and regional differences.

[0124] Finally, the dynamic correction coefficient is substituted into the threshold correction function to calculate the initial correction threshold range (e.g., the initial threshold of -28℃ is corrected to -25℃~-22℃). Based on the upper and lower limits and the median value of the initial correction threshold range, combined with the verification results of real vehicle start-up data, the target low-temperature start-up temperature threshold is generated. Specifically, the application of the correction function transforms the threshold from a "general value" to a "target vehicle-specific value", greatly improving the adaptability of low-temperature start-up.

[0125] Furthermore, the step of generating the target low-temperature start-up temperature threshold based on the initial correction threshold range includes:

[0126] Based on the extreme operating condition parameters, the feasibility of starting each candidate threshold within the initial correction threshold range is verified by Monte Carlo simulation in order to eliminate invalid candidate values ​​and simultaneously obtain the intermediate threshold range.

[0127] Based on the core factors, each candidate threshold within the intermediate threshold range is scored and filtered to obtain the optimal threshold set.

[0128] Each candidate value in the optimal threshold set is tested on a real vehicle. By collecting the corresponding feedback signals, if the feedback signals are found to meet the preset requirements, the optimal threshold set is set as the target low-temperature start-up temperature threshold.

[0129] It should be noted that, firstly, based on extreme operating condition parameters (such as extreme low temperature, extreme humidity, and extreme fluctuations in fuel composition), Monte Carlo simulation is used to verify the activation feasibility of each candidate threshold within the initial correction threshold range: a large number of extreme operating condition samples are randomly generated, the activation success rate of each candidate threshold in the samples is tested, and invalid candidate values ​​with activation success rates lower than a preset value (such as 95%) are removed to obtain the intermediate threshold range. Specifically, Monte Carlo simulation can efficiently simulate massive random operating conditions and more comprehensively verify the robustness of the threshold than traditional single-point testing.

[0130] Secondly, based on the core factors extracted by grey relational analysis (such as service life and altitude), a scoring model is constructed: each candidate threshold within the intermediate threshold range is scored, and the scoring indicators include the core factor fit, start-up success rate, and gas consumption rate. The candidate thresholds with the highest scores are selected to form the optimal threshold set. Specifically, the core factor scoring ensures that the thresholds in the optimal set are highly compatible with the actual working conditions of the target vehicle.

[0131] Finally, the candidate values ​​in the optimal threshold set are tested in a real vehicle: a low-temperature start-up test is conducted in the actual usage area of ​​the target vehicle, and corresponding feedback signals (such as start-up time, speed fluctuation rate, and fuel consumption rate) are collected; if the feedback signal is found to meet the preset requirements (such as start-up time ≤ 10s, speed fluctuation rate ≤ 5%), then the optimal threshold set is set as the target low-temperature start-up temperature threshold. Specifically, the real vehicle test run is the final verification step of the threshold calibration, ensuring the effectiveness and stability of the target threshold in actual application, and completing the entire accurate calibration process of the low-temperature start-up temperature threshold.

[0132] Please see Figure 2 The third embodiment of the present invention provides:

[0133] A low-temperature start-up temperature threshold calibration system for natural gas vehicles, wherein the system comprises:

[0134] The detection module is used to collect the composition data of the natural gas used in the target vehicle, and simultaneously detect the dew point, atomization particle size and combustion rate corresponding to the composition data at different temperatures through a low temperature physical property testing device, so as to construct a mapping database of gas composition-temperature-physical property parameters;

[0135] The adjustment module is used to simulate different low temperature gradients in the environmental simulation chamber based on the mapping database, and simultaneously adjust the ignition coil voltage and ignition advance angle of each cylinder group of the engine to determine the optimal ignition parameter range of each cylinder group under different low temperatures.

[0136] The segmentation module is used to divide the starting process of the target vehicle into an idle start-up stage and a low-speed warm-up stage. Combined with the optimal ignition parameter range, and with the starting stability and fuel consumption rate of each stage as constraints, the particle swarm optimization algorithm is used to iteratively solve the critical start-up temperature of different stages to obtain the initial temperature threshold.

[0137] The module is used to collect real vehicle start-up data from different years of use and different low-temperature regions to construct a threshold correction function based on time-series data. Simultaneously, the initial temperature threshold is corrected through the threshold correction function to calibrate the target low-temperature start-up temperature threshold corresponding to the target vehicle.

[0138] Furthermore, the adjustment module is specifically used for:

[0139] Based on the simulation results of the flow field inside the engine cylinder, a multi-field coupling model of temperature field, flow field and combustion field is constructed, and the key influencing factors of the ignition coil voltage and the ignition advance angle are detected simultaneously according to the multi-field coupling model;

[0140] Using the aforementioned key influencing factors as feedback variables, the cylinder pressure curves, combustion heat release rates, and vibration signals of each cylinder group are collected accordingly. The adjustment step size is dynamically corrected through a PID algorithm to obtain the candidate ignition parameter set for each cylinder group.

[0141] The extreme fluctuation conditions of the target at low temperature are simulated in the environmental simulation chamber, and the candidate ignition parameter set is simultaneously subjected to extreme verification to generate the optimal ignition parameter range.

[0142] Furthermore, the adjustment module is specifically used for:

[0143] Collect real-world extreme start-up failure cases of the target vehicle model in low-temperature regions, and simultaneously extract the operating condition timing features when the failure occurs, so as to detect the corresponding timing logic in the operating condition timing features;

[0144] Based on the timing logic, the parameters in the candidate ignition parameter set are dynamically verified one by one, and the combustion heat release rate curve, the highest temperature in the cylinder and the exhaust oxygen concentration signal generated during the verification process are collected simultaneously to output the corresponding verification value.

[0145] The verification values ​​are subjected to correlation verification, and a continuous parameter interval is generated simultaneously through polynomial fitting to generate the corresponding optimal firing parameter interval.

[0146] Furthermore, the partitioning module is specifically used for:

[0147] Based on the critical start-up temperature and physical property adaptation coefficient of the idle start-up stage and the low-speed warm-up stage, the corresponding three-dimensional optimization variables are constructed, and the corresponding particle position vector is constructed simultaneously using temperature-coefficient coupling encoding.

[0148] An initial population adapted to the critical start-up temperature is constructed, and the initial population is iteratively optimized according to the three-dimensional optimization variables and the particle position vector.

[0149] Extract the critical temperature corresponding to the globally optimal particle, and simultaneously generate the initial temperature threshold based on the critical temperature.

[0150] Furthermore, the partitioning module is specifically used for:

[0151] Based on the optimal ignition parameter range, a three-layer constraint of temperature-physical property-ignition is constructed, and effective particles are simultaneously screened from the initial population according to the three-layer constraint.

[0152] Based on startup stability and gas consumption rate as the basic objectives, an ignition parameter adaptation deviation correction term is introduced to calculate the fitness value corresponding to each effective particle.

[0153] If the fitness value is detected to meet the preset conditions, the iteration stops and the corresponding optimal particle is output.

[0154] Furthermore, the building module is specifically used for:

[0155] A domain adaptive algorithm is used to correct the distribution deviation of the actual vehicle start-up data for different service years and different low-temperature regions, and the corresponding core factors are extracted simultaneously through grey relational analysis.

[0156] The in-cylinder dynamic changes of the engine during the start-up process under different operating conditions are simulated, and a dynamic correction coefficient adapted to the initial temperature threshold is generated with the minimum combustion pressure for successful start-up as a constraint.

[0157] Substitute the dynamic correction coefficient into the threshold correction function to obtain the corresponding initial correction threshold range, and simultaneously generate the target low-temperature start-up temperature threshold based on the initial correction threshold range.

[0158] Furthermore, the building module is specifically used for:

[0159] Based on the extreme operating condition parameters, the feasibility of starting each candidate threshold within the initial correction threshold range is verified by Monte Carlo simulation in order to eliminate invalid candidate values ​​and simultaneously obtain the intermediate threshold range.

[0160] Based on the core factors, each candidate threshold within the intermediate threshold range is scored and filtered to obtain the optimal threshold set.

[0161] Each candidate value in the optimal threshold set is tested on a real vehicle. By collecting the corresponding feedback signals, if the feedback signals are found to meet the preset requirements, the optimal threshold set is set as the target low-temperature start-up temperature threshold.

[0162] The fourth embodiment of the present invention provides a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the natural gas vehicle low-temperature start-up temperature threshold calibration method as described above.

[0163] The fifth embodiment of the present invention provides a readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the natural gas vehicle low-temperature start-up temperature threshold calibration method as described above.

[0164] In summary, the method and system for calibrating the low-temperature starting temperature threshold of natural gas vehicles provided in the above embodiments of the present invention can objectively and accurately calibrate the low-temperature starting temperature of natural gas vehicles, thereby improving the starting efficiency.

[0165] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0166] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0167] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0168] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0169] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0170] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the appended claims.

Claims

1. A method for calibrating the low-temperature start-up temperature threshold of a natural gas vehicle, characterized in that, The method includes: The composition data of the natural gas used in the target vehicle are collected, and the dew point, atomization particle size and combustion rate corresponding to the composition data at different temperatures are detected simultaneously through a low temperature physical property testing device, so as to construct a mapping database of gas composition-temperature-physical property parameters; Based on the mapping database, different low temperature gradients are simulated in the environmental simulation chamber, and the ignition coil voltage and ignition advance angle of each cylinder group of the engine are simultaneously adjusted in a gradient manner to determine the optimal ignition parameter range of each cylinder group under different low temperatures. The starting process of the target vehicle is divided into an idle start-up stage and a low-speed warm-up stage. Combining the optimal ignition parameter range, and with the starting stability and fuel consumption rate of each stage as constraints, the particle swarm optimization algorithm is used to iteratively solve the critical start-up temperature of different stages to obtain the initial temperature threshold. Collect real vehicle start-up data from different years of use and different low-temperature regions to construct a threshold correction function based on time-series data. Simultaneously, use the threshold correction function to correct the initial temperature threshold to calibrate the target low-temperature start-up temperature threshold corresponding to the target vehicle. The step of gradient-adjusting the ignition coil voltage and ignition advance angle of each cylinder group of the engine to determine the optimal ignition parameter range of each cylinder group at different low temperatures includes: Based on the simulation results of the flow field inside the engine cylinder, a multi-field coupling model of temperature field, flow field and combustion field is constructed, and the key influencing factors of the ignition coil voltage and the ignition advance angle are detected simultaneously according to the multi-field coupling model; Using the aforementioned key influencing factors as feedback variables, the cylinder pressure curves, combustion heat release rates, and vibration signals of each cylinder group are collected accordingly. The adjustment step size is dynamically corrected through a PID algorithm to obtain the candidate ignition parameter set for each cylinder group. The extreme fluctuation conditions of the target at low temperature are simulated in the environmental simulation chamber, and the candidate ignition parameter set is simultaneously subjected to extreme verification to generate the optimal ignition parameter range.

2. The method for calibrating the low-temperature start-up temperature threshold of a natural gas vehicle according to claim 1, characterized in that, The step of performing limit verification on the candidate ignition parameter set to generate the optimal ignition parameter range includes: Collect real-world extreme start-up failure cases of the target vehicle model in low-temperature regions, and simultaneously extract the operating condition timing features when the failure occurs, so as to detect the corresponding timing logic in the operating condition timing features; Based on the timing logic, the parameters in the candidate ignition parameter set are dynamically verified one by one, and the combustion heat release rate curve, the highest temperature in the cylinder and the exhaust oxygen concentration signal generated during the verification process are collected simultaneously to output the corresponding verification value. The verification values ​​are subjected to correlation verification, and a continuous parameter interval is generated simultaneously through polynomial fitting to generate the corresponding optimal firing parameter interval.

3. The method for calibrating the low-temperature start-up temperature threshold of a natural gas vehicle according to claim 1, characterized in that, The step of using the particle swarm optimization algorithm to iteratively solve for the critical start-up temperature at different stages to obtain the initial temperature threshold includes: Based on the critical start-up temperature and physical property adaptation coefficient of the idle start-up stage and the low-speed warm-up stage, the corresponding three-dimensional optimization variables are constructed, and the corresponding particle position vector is constructed simultaneously using temperature-coefficient coupling encoding. An initial population adapted to the critical start-up temperature is constructed, and the initial population is iteratively optimized according to the three-dimensional optimization variables and the particle position vector. Extract the critical temperature corresponding to the globally optimal particle, and simultaneously generate the initial temperature threshold based on the critical temperature.

4. The method for calibrating the low-temperature start-up temperature threshold of a natural gas vehicle according to claim 3, characterized in that, The step of iteratively optimizing the initial population based on the three-dimensional optimization variables and the particle position vector includes: Based on the optimal ignition parameter range, a three-layer constraint of temperature-physical property-ignition is constructed, and effective particles are simultaneously screened from the initial population according to the three-layer constraint. Based on startup stability and gas consumption rate as the basic objectives, an ignition parameter adaptation deviation correction term is introduced to calculate the fitness value corresponding to each effective particle. If the fitness value is detected to meet the preset conditions, the iteration stops and the corresponding optimal particle is output.

5. The method for calibrating the low-temperature start-up temperature threshold of a natural gas vehicle according to claim 1, characterized in that, The step of correcting the initial temperature threshold using the threshold correction function to determine the target low-temperature start-up temperature threshold corresponding to the target vehicle includes: A domain adaptive algorithm is used to correct the distribution deviation of the actual vehicle start-up data for different service years and different low-temperature regions, and the corresponding core factors are extracted simultaneously through grey relational analysis. The in-cylinder dynamic changes of the engine during the start-up process under different operating conditions are simulated, and a dynamic correction coefficient adapted to the initial temperature threshold is generated with the minimum combustion pressure for successful start-up as a constraint. Substitute the dynamic correction coefficient into the threshold correction function to obtain the corresponding initial correction threshold range, and simultaneously generate the target low-temperature start-up temperature threshold based on the initial correction threshold range.

6. The method for calibrating the low-temperature start-up temperature threshold of a natural gas vehicle according to claim 5, characterized in that, The step of generating the target low-temperature start-up temperature threshold based on the initial correction threshold range includes: Based on the extreme operating condition parameters, the feasibility of starting each candidate threshold within the initial correction threshold range is verified by Monte Carlo simulation in order to eliminate invalid candidate values ​​and simultaneously obtain the intermediate threshold range. Based on the core factors, each candidate threshold within the intermediate threshold range is scored and filtered to obtain the optimal threshold set. Each candidate value in the optimal threshold set is tested on a real vehicle. By collecting the corresponding feedback signals, if the feedback signals are found to meet the preset requirements, the optimal threshold set is set as the target low-temperature start-up temperature threshold.

7. A low-temperature start-up temperature threshold calibration system for natural gas vehicles, characterized in that, The system is used to implement the method for calibrating the low-temperature start-up temperature threshold of a natural gas vehicle as described in any one of claims 1 to 6, the system comprising: The detection module is used to collect the composition data of the natural gas used in the target vehicle, and simultaneously detect the dew point, atomization particle size and combustion rate corresponding to the composition data at different temperatures through a low temperature physical property testing device, so as to construct a mapping database of gas composition-temperature-physical property parameters; The adjustment module is used to simulate different low temperature gradients in the environmental simulation chamber based on the mapping database, and simultaneously adjust the ignition coil voltage and ignition advance angle of each cylinder group of the engine to determine the optimal ignition parameter range of each cylinder group under different low temperatures. The segmentation module is used to divide the starting process of the target vehicle into an idle start-up stage and a low-speed warm-up stage. Combined with the optimal ignition parameter range, and with the starting stability and fuel consumption rate of each stage as constraints, the particle swarm optimization algorithm is used to iteratively solve the critical start-up temperature of different stages to obtain the initial temperature threshold. The module is used to collect real vehicle start-up data from different years of use and different low-temperature regions to construct a threshold correction function based on time-series data. Simultaneously, the initial temperature threshold is corrected through the threshold correction function to calibrate the target low-temperature start-up temperature threshold corresponding to the target vehicle.

8. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for calibrating the low-temperature start-up temperature threshold of natural gas vehicles as described in any one of claims 1 to 6.

9. A readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method for calibrating the low-temperature start-up temperature threshold of natural gas vehicles as described in any one of claims 1 to 6.

Images