Driving regeneration control method, device, storage medium and program product

Abstract

The application discloses a driving regeneration control method and device, a storage medium and a program product, relates to the technical field of driving regeneration, and comprises the following steps: acquiring real-time road spectrum data of a vehicle in a driving process, predicting driving condition distribution in a future preset time period based on at least the real-time road spectrum data and historical road spectrum data, and obtaining a prediction result; adjusting a target triggering condition of driving regeneration according to the prediction result, wherein the target triggering condition comprises a carbon load threshold and an exhaust temperature threshold; and when the adjusted target triggering condition is met and a vehicle operating condition meets a driving regeneration condition, driving regeneration is performed. Through the real-time road spectrum data and the historical road spectrum data, the application predicts the driving condition distribution in the future, adaptively adjusts the carbon load threshold and the exhaust temperature threshold of the driving regeneration according to the prediction result, actively and prospectively plans the regeneration timing and control parameters, improves the driving regeneration efficiency, and significantly reduces fuel consumption in the driving regeneration process.

Description

Technical Field

[0001] This application relates to the field of vehicle regeneration technology, and in particular to a vehicle regeneration control method, device, storage medium and program product. Background Technology

[0002] In diesel engine exhaust aftertreatment systems, the diesel particulate filter (DPF) is a key component for meeting increasingly stringent emission standards. Its function is to capture carbon particles in engine exhaust. As carbon particles accumulate, the DPF becomes clogged, leading to increased exhaust back pressure, which in turn affects engine power and fuel economy. To remove the particles captured in the DPF, it needs to be regenerated, which involves increasing the exhaust temperature to oxidize and remove the accumulated carbon particles. On-the-go regeneration is an automatic regeneration method that occurs while the vehicle is in motion, requiring no driver intervention and offering advantages such as convenience and no impact on availability.

[0003] Existing vehicle regeneration control schemes typically rely on fixed parameter thresholds for their core logic. For example, when the real-time monitored DPF carbon load reaches a preset, fixed threshold, the regeneration process is triggered. During regeneration, the control system adjusts the engine's fuel injection parameters and exhaust temperature to achieve a preset target exhaust temperature, thereby completing the oxidation of carbon particles. This control method is a passive response mode, meaning that regeneration is only passively initiated when the carbon load accumulates to a certain level.

[0004] However, this passive response control scheme based on a fixed threshold has inherent technical problems. Diesel engines operate under complex and varied conditions, with significant differences in exhaust temperature and engine operating status under different conditions. Fixed regeneration trigger thresholds and regeneration parameters cannot be effectively matched with changing operating conditions, resulting in a mismatch between regeneration timing and actual operating conditions, manifested as low regeneration efficiency and high fuel consumption during the regeneration process. Summary of the Invention

[0005] In view of the above problems, this application provides a vehicle regeneration control method, device, storage medium, and program product to improve vehicle regeneration efficiency and reduce vehicle regeneration fuel consumption. The specific solution is as follows:

[0006] The first aspect of this application provides a vehicle regeneration control method, comprising:

[0007] Acquire real-time road spectrum data of the vehicle during its driving process;

[0008] Based on the real-time road spectrum data and historical road spectrum data, the distribution of driving conditions within a preset time period is predicted to obtain the prediction result.

[0009] Based on the prediction results, the target triggering conditions for vehicle regeneration are adjusted; the target triggering conditions include: carbon load threshold and exhaust temperature threshold.

[0010] When the adjusted target triggering conditions are met and the vehicle operating conditions meet the driving regeneration conditions, driving regeneration is executed.

[0011] In one possible implementation, predicting the distribution of driving conditions within a future preset time period based on the real-time road spectrum data and historical road spectrum data includes:

[0012] The real-time road spectrum data is matched with the historical road spectrum data in the historical operating condition feature database;

[0013] If a historical road spectrum data segment exists that matches the real-time road spectrum data, then the driving condition distribution recorded in the historical road spectrum data segment within a preset time period after the historical road spectrum data segment is determined as the driving condition distribution within the preset time period in the future.

[0014] One possible implementation also includes:

[0015] If no historical road spectrum data segment matches the real-time road spectrum data, the historical average operating condition distribution of vehicles stored in the historical operating condition feature database is determined as the driving operating condition distribution within the future preset time period.

[0016] One possible implementation also includes:

[0017] Obtain future traffic information provided by the vehicle navigation system;

[0018] The prediction results are corrected based on the future road condition information.

[0019] One possible implementation also includes:

[0020] The length of the future preset time period is dynamically adjusted based on the degree of matching between the predicted driving condition distribution within the future preset time period and the actual driving condition distribution within the future preset time period.

[0021] In one possible implementation, adjusting the target carbon loading threshold includes:

[0022] For each driving condition in the prediction results, query at least one of the following in the historical road spectrum data: the percentage of that driving condition, the percentage of conditions reaching the preset exhaust temperature, and the historical regeneration fuel consumption rate.

[0023] Based on the query results, the pre-stored basic carbon load threshold corresponding to the driving condition is corrected to obtain the target carbon load threshold corresponding to the driving condition.

[0024] In one possible implementation, adjusting the exhaust temperature threshold includes:

[0025] For each driving condition in the prediction results, based on the historical road spectrum data associated with that driving condition, the percentage of driving conditions that reach the preset exhaust temperature is determined, and / or the estimated fuel consumption rate required to reach the preset exhaust temperature is determined.

[0026] Based on the determined operating condition ratio and / or estimated fuel consumption rate, the pre-stored basic exhaust temperature threshold corresponding to the driving condition is corrected to obtain the target exhaust temperature threshold.

[0027] If the proportion of operating conditions that reach the preset exhaust temperature is higher than the first preset proportion, the basic exhaust temperature threshold is increased; if the estimated fuel consumption rate required to reach the preset exhaust temperature is higher than the second preset proportion, the basic exhaust temperature threshold is decreased.

[0028] A second aspect of this application provides a computer program product including computer-readable instructions that, when executed on an electronic device, cause the electronic device to implement the vehicle regeneration control method described in the first aspect or any implementation thereof.

[0029] A third aspect of this application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0030] The memory is used to store computer programs;

[0031] The processor is used to execute the computer program so that the electronic device can implement the vehicle regeneration control method of the first aspect or any implementation thereof.

[0032] A fourth aspect of this application provides a computer storage medium carrying one or more computer programs, which, when executed by an electronic device, enable the electronic device to implement the vehicle regeneration control method described in the first aspect or any implementation thereof.

[0033] Using the above technical solutions, the driving regeneration control method, device, storage medium, and program product provided in this application acquire real-time road spectrum data of the vehicle during driving, and predict the distribution of driving conditions within a preset time period based at least on the real-time road spectrum data and historical road spectrum data, thereby obtaining a prediction result; according to the prediction result, the target triggering conditions for driving regeneration are adjusted, including: carbon load threshold and exhaust temperature threshold; when the adjusted target triggering conditions are met, and the vehicle operating conditions meet the driving regeneration conditions, driving regeneration is executed. This application uses real-time and historical road spectrum data to predict future driving condition distribution, and then adaptively adjusts the carbon load threshold and exhaust temperature threshold for vehicle regeneration based on the prediction results. This enables proactive and forward-looking planning of regeneration timing and control parameters, transforming the vehicle regeneration process from a traditional passive response mode based on fixed thresholds to an optimized decision-making mode that proactively adapts to future driving conditions. This reduces the number of times regeneration is initiated under inefficient and high-fuel-consumption conditions and increases the chance of completing regeneration under efficient and low-fuel-consumption conditions. While improving vehicle regeneration efficiency, it significantly reduces fuel consumption during the vehicle regeneration process. Attached Figure Description

[0034] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0035] Figure 1 A flowchart illustrating an implementation of the vehicle regeneration control method provided in this application;

[0036] Figure 2 A flowchart illustrating an implementation of this application for predicting the distribution of driving conditions within a preset time period based on real-time road spectrum data and historical road spectrum data;

[0037] Figure 3 A flowchart illustrating one implementation of adjusting the target carbon loading threshold provided in this application;

[0038] Figure 4 A flowchart illustrating one implementation of adjusting the exhaust temperature threshold provided in this application;

[0039] Figure 5 A schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0040] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.

[0041] As will be known to those skilled in the art, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0042] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements, but may include other elements not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0043] Regeneration of a particulate filter (DPF) includes parking regeneration (which can be simply referred to as parking regeneration) and driving regeneration.

[0044] The stationary regeneration mode is a DPF cleaning mode that is manually triggered after the vehicle has come to a complete stop, when the engine is off or the vehicle is idling. During the stationary regeneration process, the vehicle cannot be moved (i.e., the vehicle cannot be driven). It is suitable for situations where the DPF is severely clogged and the conditions for regeneration while driving are not met for a long time.

[0045] Driving-based regeneration involves the system automatically cleaning the DPF during normal vehicle operation, requiring no human intervention, not affecting normal driving, and saving time—making it a more convenient regeneration method. This application presents an optimized solution for driving-based regeneration.

[0046] like Figure 1 The diagram shown is a flowchart of one implementation of the vehicle regeneration control method provided in this application, which may include:

[0047] Step S101: Obtain real-time road spectrum data of the vehicle during its driving process.

[0048] Real-time road spectrum data refers to a multi-dimensional parameter sequence that can characterize the current operating status of a vehicle and environmental characteristics. It can be collected in real time through onboard sensors and the CAN bus.

[0049] Real-time road spectrum data may include, but is not limited to:

[0050] Engine operating parameters, such as speed, torque, load, and fuel injection quantity;

[0051] DPF status parameters, such as carbon load and engine exhaust temperature;

[0052] Environmental parameters, such as ambient temperature and altitude;

[0053] Driving condition parameters, such as vehicle speed, road condition type, load level, etc.

[0054] In other words, this application records engine operating parameters, DPF status parameters, environmental parameters, and driving condition parameters in real time during vehicle operation. This comprehensive data collection accurately depicts the vehicle's current actual operating trajectory and load status, providing a high-fidelity input basis for subsequent condition prediction. This step aims to construct a digital mapping of the vehicle's current operating environment, ensuring that subsequent decisions are based on real and real-time driving behavior data.

[0055] Step S102: Based on real-time road spectrum data and historical road spectrum data, predict the distribution of driving conditions within a preset time period in the future, and obtain the prediction result.

[0056] The distribution of driving conditions can refer to the types of driving conditions that may occur within a preset time period in the future (such as high-speed constant speed light load, high-speed constant speed heavy load, low-speed congestion light load, low-speed congestion heavy load, hill driving light load, hill driving heavy load, etc.) and the proportion of the duration of each type of driving condition.

[0057] Optionally, prediction results can be generated by matching and analyzing real-time road spectrum data with historical road spectrum data stored in a historical operating condition feature database.

[0058] Real-time road spectrum can refer to the sequence of driving parameters (i.e., road spectrum) collected by a vehicle at the current moment and within a preset time window before it, including engine speed, load, fuel injection quantity, exhaust temperature (i.e., DPF inlet temperature), DPF carbon load, vehicle speed, road condition type (e.g., high speed / low speed, slope / flat road), load (light load / heavy load), ambient temperature and altitude, etc.

[0059] Optionally, suspension deflection (displacement) can be monitored in real time using a suspension displacement sensor installed on the vehicle (e.g., mounted on a leaf spring suspension). The output signal of this sensor is acquired and processed by the vehicle control unit (ECU).

[0060] The ECU calculates the vehicle's actual load based on a pre-calibrated mapping between suspension deflection and actual vehicle load. It then compares this actual load with the vehicle's rated load capacity to classify the load status. For example, if the actual load is less than or equal to a third preset percentage of the rated load capacity (e.g., 50%), it is classified as a light load; if the actual load is greater than or equal to a fourth preset percentage of the rated load capacity (e.g., 70% or 80%), it is classified as a heavy load. The fourth preset percentage is greater than the third preset percentage.

[0061] The historical driving condition feature database is a pre-built database that stores historical road spectrum data. It stores regenerated and non-regenerated driving condition road spectrum data of vehicles over the past few months in a time-dimension manner, and labels the corresponding driving condition type (such as high-speed constant speed light load, low-speed congested heavy load, etc.). In other words, the historical road spectrum data in the historical driving condition feature database is stored in segments according to regenerated and non-regenerated time periods, and each historical road spectrum data segment is stored sequentially according to the time of collection.

[0062] Step S103: Adjust the target triggering conditions for vehicle regeneration based on the prediction results; the target triggering conditions include: carbon load threshold and exhaust temperature threshold.

[0063] Optionally, the target trigger condition is the critical judgment criterion required to initiate the vehicle regeneration operation, including the dynamically adjusted carbon load threshold and exhaust temperature threshold. This can be obtained by querying the regeneration feature database for adaptive adjustment rules associated with the predicted operating conditions, and then correcting the pre-stored base thresholds (base carbon load threshold and base exhaust temperature threshold) based on the found adaptive adjustment rules.

[0064] Step S104: When the adjusted target triggering conditions are met and the vehicle operating conditions meet the driving regeneration conditions, drive regeneration is executed.

[0065] Vehicle regeneration refers to the process of controlling exhaust temperature to oxidize and remove carbon particles from the DPF (Diesel Particulate Filter) during normal vehicle operation by adjusting fuel injection strategy and exhaust throttle valve opening. Its execution requires meeting two constraints: first, the real-time monitored carbon load and exhaust temperature must reach the target triggering conditions after the aforementioned adjustments; second, the current vehicle operating conditions (such as stable speed, non-rapid deceleration, and normal coolant temperature) must meet the basic requirements for safe regeneration.

[0066] After confirming that all the above conditions are met (the adjusted target triggering conditions are met, and the vehicle operating conditions meet the vehicle regeneration conditions), the vehicle control unit (ECU) automatically coordinates the fuel injection system and aftertreatment system to implement a multi-stage injection or late injection strategy based on the adjusted exhaust temperature threshold, in order to raise the DPF inlet temperature to the adjusted exhaust temperature threshold and maintain it within a temperature range [T0, T]. max Until the carbon load drops to a safe level. T0 is the adjusted exhaust temperature threshold, T max The preset maximum temperature is greater than the adjusted exhaust temperature threshold.

[0067] This step effectively prevents forced regeneration under unsuitable conditions by introducing a dual verification mechanism that adapts the adjusted threshold to the current vehicle operating conditions, significantly improving the safety and economy of the regeneration process.

[0068] The vehicle regeneration control method provided in this application predicts the distribution of future driving conditions using real-time road spectrum data and historical road spectrum data. Then, it adaptively adjusts the carbon load threshold and exhaust temperature threshold of vehicle regeneration based on the prediction results. This achieves proactive and forward-looking planning of regeneration timing and control parameters. This allows the vehicle regeneration process to change from a traditional passive response mode based on fixed thresholds to an optimized decision-making mode that actively adapts to future driving conditions. This reduces the number of times regeneration is initiated under inefficient and high-fuel-consumption conditions and increases the chance of completing regeneration under efficient and low-fuel-consumption conditions. While improving vehicle regeneration efficiency, it significantly reduces fuel consumption during the vehicle regeneration process.

[0069] In an optional embodiment, the flowchart of one method for predicting the distribution of driving conditions within a preset time period based on real-time road spectrum data and historical road spectrum data is as follows: Figure 2 As shown, it may include:

[0070] Step S201: Match the real-time road spectrum data with the historical road spectrum data in the historical working condition feature database.

[0071] Optionally, the real-time road spectrum data sequence within the preceding A time period can be matched with the road spectrum data stored in the historical operating condition feature database over the past n months based on similarity. Assuming the current time is t, the preceding A time period refers to the period from tA to the current time t.

[0072] At least a portion of the real-time road spectrum data within the previous A time period can be used as the search key to traverse the historical road spectrum data segment with the highest similarity in the historical operating condition feature database.

[0073] As an example, the parameters used as search keys can include at least the following key parameters: load (i.e., load), vehicle speed, torque, exhaust temperature, etc.

[0074] For each key parameter, the mean square error (MSE) (or root mean square error (RMSE) of each value of the key parameter within the previous A time period at the current time can be calculated, and compared with the mean square error (RMSE) of each value of the key parameter within each historical road spectrum data segment of the same duration in the historical operating condition feature database. This RMSE is used as the matching degree of the key parameter. The average of the matching degrees of each key parameter corresponding to the same historical road spectrum data segment is then calculated to obtain the matching degree between the road spectrum data segment within the previous A time period at the current time and the historical road spectrum data segment. If the matching degree is greater than or equal to a preset matching threshold, the road spectrum data segment within the previous A time period at the current time is determined to match the historical road spectrum data segment; otherwise, the road spectrum data segment within the previous A time period at the current time is determined to not match the historical road spectrum data segment. It should be noted that if the duration of the historical road spectrum data segment stored in the historical operating condition feature database is greater than A, a historical road spectrum data segment of duration A can be extracted from that historical road spectrum data segment for key parameter matching degree calculation.

[0075] This retrieval and matching method based on historical measured data can leverage the high repetition of vehicle driving routes to transform the complex problem of predicting operating conditions into an efficient retrieval and reuse problem, effectively avoiding the generalization error that pure statistical models are prone to in small sample scenarios.

[0076] Step S202: If there is a historical road spectrum data segment that matches the real-time road spectrum data, then the driving condition distribution recorded in the historical road spectrum data segment within a preset time period after the historical road spectrum data segment is determined as the driving condition distribution within the future preset time period.

[0077] The preset duration refers to the length of future time that needs to be predicted. Its value can be dynamically adjusted, for example, initially set to 30 minutes in the future.

[0078] When a historical road spectrum segment that matches the real-time road spectrum data is found, the data segment immediately following the historical segment on the timeline with a preset duration can be directly extracted, and the recorded driving condition sequence can be used as the future prediction result for the current moment.

[0079] For example, during vehicle operation, if the road spectrum data within the current 20 minutes matches the road spectrum data within a historical record of the past 20 minutes in the historical driving condition feature database with a matching degree of up to 95%, then the actual driving data of the latter half of that historical record (i.e., the corresponding future time period) is directly retrieved to conclude that the vehicle will experience a driving condition distribution of 20 minutes of high-speed constant speed + 5 minutes of incline + 5 minutes of low-speed congestion within the next 30 minutes. This process demonstrates a logical closed loop from real-time data input and database matching retrieval to direct output of the predicted driving condition distribution, ensuring that the prediction results have real physical meaning and high confidence, thereby providing a reliable basis for the accurate adjustment of subsequent driving regeneration trigger conditions.

[0080] In an optional embodiment, if there is no historical road spectrum data segment that matches the real-time road spectrum data, the historical average operating condition distribution of vehicles stored in the historical operating condition feature database is determined as the driving operating condition distribution within a preset time period in the future.

[0081] This situation, where no historical road spectrum data segment matches the real-time road spectrum data, typically occurs when a vehicle is traveling on a completely new route and encounters sudden changes in road conditions. In this case, inferences based on a single historical road spectrum data segment are no longer reliable. Therefore, the proportion of each driving condition and its duration over a longer period (e.g., the past 3 or 6 months) can be determined as the distribution of driving conditions for a future preset duration at the current moment.

[0082] As an example, the cumulative proportion of each driving condition in the historical driving condition feature database can be statistically analyzed, and the statistical results can be used as the distribution of driving conditions within a future preset time period at the current moment.

[0083] For example, the cumulative percentages of each driving condition in the historical driving condition feature database are as follows: high-speed constant speed light load condition accounts for 30%, high-speed constant speed heavy load condition accounts for 20%, low-speed congested light load condition accounts for 25%, low-speed congested heavy load condition accounts for 15%, and hill driving condition accounts for 10%, etc.

[0084] The historical operating condition characteristic database continuously records and updates the proportion of vehicle operating time under various loads and road conditions.

[0085] This approach leverages the law of large numbers, replacing short-term path dependence with long-term statistical regularities. This ensures that even in the absence of high-precision matching objects, the prediction model can still output statistically significant operating condition distribution data, aiming to solve prediction failures caused by unfamiliar routes or sudden changes in road conditions. By using long-accumulated average operating condition data as a backup prediction source, the continuity of the vehicle regeneration control logic is guaranteed. Based on the aforementioned acquired historical average operating condition distribution of the vehicle, the control system can continue to execute subsequent regeneration parameter adjustment operations, avoiding degradation to a fixed threshold mode due to prediction interruptions, thereby maintaining the robustness and stability of the regeneration strategy under different driving scenarios.

[0086] In an optional embodiment, the vehicle regeneration control method provided in this application may further include:

[0087] Obtain future traffic information provided by the vehicle navigation system.

[0088] When the navigation system is turned on, it can integrate future road condition information provided by the navigation system to predict the distribution of driving conditions within a preset time period.

[0089] Future traffic information refers to road attribute data obtained through in-vehicle navigation terminals or cloud map service interfaces, covering a preset distance ahead of the vehicle's current driving route. This information may include the road segment's elevation change curve, gradient value, speed limit, real-time congestion level, and road segment type (such as highway, national road, tunnel, toll station, etc.).

[0090] Future road condition information can be obtained in real time through the communication bus (such as the CAN bus) between the vehicle navigation system and the vehicle control unit (ECU). Its function is to provide macroscopic prior knowledge of the road environment for predicting driving condition distribution, compensating for the limitations of relying solely on historical data from vehicle sensors for predictions over long distances or in non-repetitive road conditions. For example, when a vehicle is about to enter a continuous long uphill section, the navigation system can output information in advance that the average gradient of this section is 3%-5% and its length is 10 kilometers; or when there is severe congestion ahead, it can output that the average speed of this section is less than 20 km / h and the estimated travel time. By introducing this multi-source data, the effective prediction distance range can be significantly expanded from the traditional several kilometers to tens of kilometers, thus supporting intelligent planning for regenerative driving throughout the entire journey.

[0091] The prediction results are revised based on future traffic information.

[0092] Optionally, deterministic parameters (such as known long downhill sections or congested road segments) in the future road condition information can be replaced with the corresponding parameters in the prediction results to obtain corrected prediction results.

[0093] For example, if future traffic information indicates that there is a smooth highway section 20 kilometers ahead, and historical data shows that the vehicle model usually travels at a constant speed of 80 km / h on such sections, the prediction result will allocate a high proportion of high-speed constant speed driving conditions; conversely, if the navigation indicates that there is construction and congestion ahead, even if the historical habit is high-speed driving, the prediction result will be dynamically adjusted to low-speed congestion driving conditions dominating.

[0094] The prediction scheme, which corrects prediction results based on navigation information, is based on a multi-source fusion modeling mechanism. Real-time road spectrum data reflects the vehicle's current transient operating characteristics (such as current engine speed, load, and exhaust temperature), historical road spectrum data records the vehicle's driving behavior preferences and statistical patterns of driving conditions under similar road conditions over a specific time period, and future road condition information provides deterministic constraints on the external environment. This hybrid prediction framework, combining vehicle-side perception and cloud-based prior knowledge, effectively improves the ability to anticipate critical adverse regeneration conditions such as slopes, tunnels, and toll stations, avoiding misjudgments of regeneration timing due to prediction bias.

[0095] In an optional embodiment, the vehicle regeneration control method provided in this application may further include:

[0096] As time progresses to the end of the future preset duration, the length of the future preset duration is dynamically adjusted based on the matching degree between the predicted driving condition distribution within the future preset duration and the actual driving condition distribution within the future preset duration.

[0097] The distribution of actual driving conditions within a future preset time period refers to the sequence of actual driving conditions and their statistical characteristics recorded by the vehicle during that time period as time progresses to the end of the future preset time period.

[0098] For example, if the initial preset duration is 30 minutes, the prediction might show the first 20 minutes as high-speed, constant-speed operation, followed by 10 minutes of low-speed, congested operation. However, after 30 minutes, the system retrieves historical data for that period and finds that the actual operation was high-speed, constant-speed for the first 25 minutes, followed by 5 minutes of low-speed, congested operation. By comparing these two sets of data, the accuracy of the prediction model under the current environment can be quantified. This step aims to provide an objective evaluation basis for subsequent duration adjustments, ensuring that the adjustment strategy is based on actual operational deviations rather than blind guessing.

[0099] Optionally, the system can calculate the feature vector of the predicted driving condition distribution within a preset future time period (denoted as the first feature vector for ease of distinction and description) and the feature vector of the actual driving condition distribution within the preset future time period (denoted as the second feature vector for ease of distinction and description). The cosine distance between the first and second feature vectors is then calculated as the degree of matching between the predicted driving condition distribution within the preset future time period and the actual driving condition distribution within the preset future time period. A smaller cosine distance indicates a higher degree of matching. This degree of matching directly reflects the accuracy of the current prediction model in capturing vehicle driving patterns. A high degree of matching means that historical road patterns or navigation data can effectively guide the future, while a low degree of matching indicates sudden changes in road conditions or significant changes in driving habits. By introducing the degree of matching calculation, the system transforms qualitative inaccuracy into quantitative numerical signals, providing precise input for dynamic adjustments.

[0100] Dynamic adjustment can refer to establishing feedback control logic between the matching degree and the prediction duration, so that the prediction window length (i.e., the preset duration) adaptively expands or contracts as the prediction accuracy changes. Adjustment rules may include:

[0101] When the matching degree is higher than the first preset threshold (e.g., 85%), the current prediction model is determined to have high confidence. The system automatically increases the length of the preset future time (e.g., from 30 minutes to 45 minutes) to use the high-precision prediction results to cover a longer regeneration planning cycle, thereby laying out a better fuel-saving strategy in advance.

[0102] When the matching degree is lower than the second preset threshold (e.g., 60%), it is determined that the current road conditions are complex or the model is invalid. The system automatically shortens the length of the preset future time (e.g., from 30 minutes to 15 minutes) to reduce the cumulative error caused by long-term prediction and ensure that the regeneration triggering conditions are corrected only based on highly reliable short-term conditions.

[0103] For example, in highway cruising scenarios, due to stable road conditions, the matching degree calculated multiple times is higher than 90%, and the system gradually extends the prediction time to 60 minutes, allowing DPF regeneration to start earlier on more distant highway sections. However, in urban areas with frequent start-stop sections, the matching degree fluctuates greatly and is often lower than 60%, so the system locks the prediction time to a shorter 10-15 minutes to avoid regeneration interruption or fuel consumption surge due to misjudgment of the road conditions ahead.

[0104] By dynamically adjusting the length of the preset future duration, the optimal balance of prediction granularity is achieved, ensuring both forward-looking planning capability under stable operating conditions and response sensitivity and local accuracy under transient operating conditions.

[0105] In an optional embodiment, a flowchart of one implementation of adjusting the target carbon loading threshold provided in this application is as follows: Figure 3 As shown, it may include:

[0106] Step S301: For each driving condition in the prediction results, query at least one of the following in the historical road spectrum data: the percentage of that driving condition, the percentage of that driving condition that reaches the preset exhaust temperature, and the historical regeneration fuel consumption rate.

[0107] This application pre-configures a regeneration feature database, which stores basic regeneration thresholds (basic carbon load threshold for starting vehicle regeneration, basic exhaust temperature threshold) and adaptive adjustment rules corresponding to different driving conditions. Specifically, it includes: driving condition classification (high-speed constant speed light / heavy load, low-speed congested light / heavy load, hill driving light / heavy load, idling, etc.), and each driving condition category is associated with other parameters in the road spectrum data besides the driving condition parameters (e.g., engine parameters, DPF status parameters, and environmental parameters).

[0108] The basic regeneration threshold is the calibrated threshold when the engine leaves the factory, and it is determined according to the engine and aftertreatment.

[0109] The percentage of any driving condition refers to the proportion of the occurrences of that particular driving condition, obtained from road spectrum data in the historical driving condition feature database, to the total occurrences of all driving conditions, and is used to characterize the frequency of that condition. Alternatively, the percentage of any driving condition refers to the proportion of the total duration of that particular driving condition, obtained from road spectrum data in the historical driving condition feature database, to the total duration of all driving conditions, and is used to characterize the frequency of that condition.

[0110] The percentage of driving conditions that reach the preset exhaust temperature can refer to the ratio of the number of times the exhaust temperature naturally rises to the preset exhaust temperature under this driving condition to the total number of times this driving condition occurs in historical road spectrum data. It reflects the ease with which the vehicle itself generates high-temperature exhaust under the current predicted driving condition.

[0111] Historical regeneration fuel consumption rate refers to the additional fuel consumption per unit of carbon load that is reduced when performing regeneration operations under this operating condition; that is, the additional fuel consumption per unit of carbon load that is reduced compared to not performing on-road regeneration.

[0112] For example, regarding the high-speed, constant-speed, heavy-load condition in the prediction results, the system retrieved historical road spectrum data and found that this condition accounted for 40% of historical driving over the past 3 months; under this condition, the exhaust temperature exceeded 250°C without additional fuel injection in 85% of cases; and the historical regeneration fuel consumption rate under this condition was only 0.5L / 100km. Conversely, for the low-speed, congested, light-load condition, the query results might show a historical proportion of 20%, with less than 10% reaching the preset exhaust temperature, while the historical regeneration fuel consumption rate was as high as 2.0L / 100km. By querying these key statistics, the system can quantitatively evaluate the economy and efficiency of regeneration under different conditions, providing data support for subsequent differentiated adjustments to thresholds. This step aims to extract feature indicators strongly correlated with the current predicted condition from massive historical data, transforming abstract condition types into quantifiable statistical parameters. This breaks through the limitations of traditional technologies that rely solely on a single carbon load value for judgment, laying the foundation for refined regeneration control.

[0113] Step S302: Based on the query results, the pre-stored basic carbon load threshold corresponding to the driving condition is corrected to obtain the target carbon load threshold corresponding to the driving condition.

[0114] Optionally, if the query results indicate that the proportion of high-speed heavy-load conditions exceeds the first proportion, and the proportion of operating conditions where the exhaust temperature reaches (greater than or equal to) the first preset exhaust temperature (e.g., 250°C) exceeds the second proportion, the carbon load threshold can be increased.

[0115] If the query results indicate that the proportion of light-load conditions exceeds the third proportion, and the proportion of operating conditions where the exhaust temperature reaches the second preset exhaust temperature (e.g., 200°C) is greater than the fourth proportion, the carbon load threshold can be lowered. The second preset exhaust temperature is lower than the first preset exhaust temperature.

[0116] Optionally, if the query results show that the proportion of exhaust temperature meeting the standard under a certain driving condition is high and the historical regeneration fuel consumption rate is low, it indicates that the driving condition is conducive to efficient and low-consumption regeneration. In this case, the system will increase the basic carbon load threshold corresponding to the driving condition, allowing the DPF to accumulate more carbon particles before starting regeneration, thereby extending the regeneration interval and reducing the regeneration frequency. Conversely, if the proportion of exhaust temperature meeting the standard under a certain driving condition is low and the historical regeneration fuel consumption rate is high, it indicates that forced regeneration under this driving condition will lead to deterioration of fuel economy and incomplete regeneration. In this case, the system will lower the basic carbon load threshold corresponding to the driving condition, prompting the vehicle to seek a better driving condition or intervene in control in advance when the carbon load is low, so as to avoid wasting fuel under inefficient driving conditions.

[0117] For example, in high-speed, constant-speed, heavy-load conditions, due to the high exhaust temperature compliance rate and low fuel consumption, the system can adjust the basic carbon load threshold from 6g / L to 7.5g / L to make full use of the waste heat of this efficient condition for regeneration; while in low-speed, congested, light-load conditions, due to the difficulty in meeting the exhaust temperature standard and high fuel consumption, the system adjusts its basic carbon load threshold downward to 4.5g / L to prevent forced regeneration with high fuel consumption due to excessive carbon deposits under this condition.

[0118] Through this dynamic correction based on historical data statistical characteristics, the final target carbon load threshold is no longer a fixed constant, but a dynamic variable that adapts in real time to changes in predicted operating conditions. This step, by combining historical statistical characteristics with the basic threshold, enables personalized customization of regeneration triggering conditions, ensuring that regeneration operations always occur within the operating window of optimal fuel economy and highest regeneration efficiency, effectively solving the problem of mismatch between regeneration timing and operating conditions caused by traditional fixed thresholds.

[0119] In an optional embodiment, a flowchart of one implementation of adjusting the exhaust temperature threshold provided in this application is as follows: Figure 4 As shown, it may include:

[0120] Step S401: For each driving condition in the prediction results, based on the historical road spectrum data associated with that driving condition, determine the proportion of driving conditions that reach the preset exhaust temperature (which can be simply referred to as the temperature reach ratio), and / or the estimated fuel consumption rate required to reach the preset exhaust temperature.

[0121] For any driving condition, the percentage of driving conditions that reach the preset exhaust temperature refers to the ratio of the number of times the exhaust temperature under any given driving condition can naturally rise to the preset exhaust temperature to the total number of occurrences of that driving condition in the historical driving condition feature database. It reflects the ease with which the vehicle itself generates high-temperature exhaust under the current predicted driving condition.

[0122] The estimated fuel consumption rate required to reach the preset exhaust temperature can be defined as the ratio of the amount of fuel consumed by additional fuel injection to the driving mileage or time required to raise the exhaust temperature to the target regeneration temperature. This value is calculated based on the difference between fuel consumption under non-regeneration conditions and fuel consumption under regeneration conditions in historical data.

[0123] For example, if it is predicted that the vehicle will be under high-speed, constant-speed, heavy-load conditions for a period of time, the system searches the historical operating condition characteristic database and finds that under such conditions, due to the high engine load, the exhaust temperature naturally exceeds 250°C for up to 80% of the time. Therefore, the operating condition that reaches the preset exhaust temperature is determined to be 80%. Simultaneously, if another predicted operating condition is low-speed, congested, and light-load, historical data shows that a large amount of post-injection fuel is needed to barely reach the regeneration temperature, resulting in a high additional fuel consumption rate. Therefore, its estimated fuel consumption rate is determined to be high. By quantifying these two indicators, the energy cost and natural potential for increasing exhaust temperature under different operating conditions can be accurately assessed. This step aims to provide objective data support for subsequent exhaust temperature threshold adjustments, avoiding blindly setting exhaust temperature parameters based on experience.

[0124] Step S402: Based on the determined operating condition ratio and / or estimated fuel consumption rate, the pre-stored basic exhaust temperature threshold corresponding to the driving condition is corrected to obtain the target exhaust temperature threshold.

[0125] If the proportion of operating conditions that reach the preset exhaust temperature is higher than the first preset proportion, it means that the vehicle is very likely to reach a high temperature naturally under this condition. Therefore, the basic exhaust temperature threshold is increased to utilize the natural high temperature for more thorough carbon particle oxidation, while reducing the frequency of active fuel injection for warming. If the estimated fuel consumption rate required to reach the preset exhaust temperature is higher than the second preset proportion, it means that the economy of forcibly warming up under this condition is extremely poor. Therefore, the basic exhaust temperature threshold is decreased to allow regeneration to start at a relatively low but safe temperature to avoid excessive fuel consumption.

[0126] For example, a first preset ratio is set to 60%, and a second preset ratio is set to 0.5L / 100km. If the temperature reach rate for a certain operating condition is 75% (higher than 60%), the base exhaust temperature threshold is increased from the standard 260℃ to 280℃ to fully utilize waste heat. If the estimated fuel consumption rate for a certain operating condition is 0.8L / 100km (higher than 0.5L / 100km), the base exhaust temperature threshold is decreased from 260℃ to 240℃ to prioritize fuel economy. This adjustment method makes the target exhaust temperature threshold no longer a rigid number, but an intelligent parameter that fluctuates in real time according to road conditions.

[0127] In other words, if it is predicted that high exhaust temperature conditions (such as high-speed cruising) will account for a relatively high proportion in the future, the basic exhaust temperature threshold should be appropriately increased to reduce unnecessary active fuel injection warming operations, thereby reducing fuel consumption; conversely, if it is predicted that the future will mainly involve low exhaust temperature conditions (such as urban congestion), the exhaust temperature threshold should be reduced or the carbon load threshold should be adjusted so that regeneration can be started as early as possible within the limited suitable window period.

[0128] By increasing the threshold under high-efficiency conditions, thermal shock to components caused by excessive intervention can be prevented. By decreasing the threshold under low-efficiency conditions, fuel waste caused by forcing high temperatures can be avoided, thus ensuring that the vehicle regeneration process is both efficient and fuel-saving.

[0129] This application ensures that the regeneration triggering conditions are precisely matched with the actual upcoming operating conditions by coordinating the adjustment of the carbon load threshold and the exhaust temperature threshold. This avoids regeneration delays and DPF blockage risks caused by excessively high thresholds, and also eliminates ineffective regeneration and fuel waste caused by excessively low thresholds.

[0130] In an optional embodiment, regeneration fuel consumption can be predicted based on adjusted target triggering conditions. If the predicted regeneration fuel consumption is higher than the parking regeneration fuel consumption, the regeneration strategy is planned as parking regeneration to prioritize fuel-saving targets. Based on this, a parking regeneration prompt can be output. If the user refuses parking regeneration, driving regeneration will be executed when the adjusted target triggering conditions are met and the vehicle operating conditions meet driving regeneration conditions; if the user selects parking regeneration, driving regeneration will not be executed when the adjusted target triggering conditions are met and the vehicle operating conditions meet driving regeneration conditions.

[0131] This application also stores the collected real-time road spectrum data in a historical operating condition feature database so as to update the historical operating condition feature database in real time, so that the example operating condition feature database always stores historical road spectrum data within the most recent preset time period (e.g., n months).

[0132] Corresponding to the method embodiments, this application also provides an electronic device. (See reference...) Figure 5 As shown, it illustrates a structural schematic diagram of an electronic device suitable for implementing embodiments of this application. Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0133] like Figure 5As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. When the electronic device is powered on, the RAM 503 also stores various programs and data required for the operation of the electronic device. The processing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0134] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, memory cards, hard drives, etc.; and communication devices 509. Communication device 509 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0135] This application also provides a computer program product including computer-readable instructions, which, when executed on an electronic device, cause the electronic device to implement any of the vehicle regeneration control methods provided in this application.

[0136] This application also provides a computer-readable storage medium carrying one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any of the vehicle regeneration control methods provided in this application.

[0137] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0138] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0139] In the above embodiments, the functionality can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented entirely or partially as a computer program product. Those skilled in the art can use different methods to implement the described functions for each specific solution, but such implementation should not be considered beyond the scope of this application.

[0140] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

[0141] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0142] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for controlling vehicle regeneration, characterized in that, include: Acquire real-time road spectrum data of the vehicle during its driving process; Based on the real-time road spectrum data and historical road spectrum data, the distribution of driving conditions within a preset time period is predicted to obtain the prediction result. Based on the prediction results, adjust the target triggering conditions for vehicle regeneration; The target triggering conditions include: carbon loading threshold and exhaust temperature threshold; When the adjusted target triggering conditions are met and the vehicle operating conditions meet the driving regeneration conditions, driving regeneration is executed.

2. The method according to claim 1, characterized in that, Based on the real-time road spectrum data and historical road spectrum data, predict the distribution of driving conditions within a future preset time period, including: The real-time road spectrum data is matched with the historical road spectrum data in the historical operating condition feature database; If a historical road spectrum data segment exists that matches the real-time road spectrum data, then the driving condition distribution recorded in the road spectrum data segment within a preset time period after the historical road spectrum data segment is determined as the driving condition distribution within the future preset time period.

3. The method according to claim 2, characterized in that, Also includes: If no historical road spectrum data segment matches the real-time road spectrum data, the historical average operating condition distribution of vehicles stored in the historical operating condition feature database is determined as the driving operating condition distribution within the future preset time period.

4. The method according to claim 1, characterized in that, Also includes: Obtain future traffic information provided by the vehicle navigation system; The prediction results are corrected based on the future road condition information.

5. The method according to claim 1, characterized in that, Also includes: The length of the future preset time period is dynamically adjusted based on the degree of matching between the predicted driving condition distribution within the future preset time period and the actual driving condition distribution within the future preset time period.

6. The method according to claim 1, characterized in that, Adjusting the target carbon loading threshold includes: For each driving condition in the prediction results, query at least one of the following in the historical road spectrum data: the percentage of that driving condition, the percentage of conditions reaching the preset exhaust temperature, and the historical regeneration fuel consumption rate. Based on the query results, the pre-stored basic carbon load threshold corresponding to the driving condition is corrected to obtain the target carbon load threshold corresponding to the driving condition.

7. The method according to claim 1, characterized in that, Adjusting the exhaust temperature threshold includes: For each driving condition in the prediction results, based on the historical road spectrum data associated with that driving condition, the percentage of driving conditions that reach the preset exhaust temperature is determined, and / or the estimated fuel consumption rate required to reach the preset exhaust temperature is determined. Based on the determined operating condition ratio and / or estimated fuel consumption rate, the pre-stored basic exhaust temperature threshold corresponding to the driving condition is corrected to obtain the target exhaust temperature threshold. If the proportion of operating conditions that reach the preset exhaust temperature is higher than the first preset proportion, the basic exhaust temperature threshold is increased; if the estimated fuel consumption rate required to reach the preset exhaust temperature is higher than the second preset proportion, the basic exhaust temperature threshold is decreased.

8. An electronic device, characterized in that, The electronic device includes at least one processor and a memory connected to the processor; wherein: The memory is used to store computer programs; The processor is used to execute the computer program to enable the electronic device to implement the vehicle regeneration control method as described in any one of claims 1 to 7.

9. A computer program product, characterized in that, It includes computer-readable instructions that, when executed on an electronic device, cause the electronic device to implement the vehicle regeneration control method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The storage medium carries one or more computer programs that, when executed by an electronic device, enable the electronic device to implement the vehicle regeneration control method as described in any one of claims 1 to 7.

Images