Energy-saving driving method, device and equipment based on real-time load identification and storage medium

Abstract

The invention discloses an energy-saving driving method, device and equipment based on real-time load identification and a storage medium, and relates to the technical field of vehicle control, and the energy-saving driving method based on real-time load identification comprises the following steps: obtaining operation data of a vehicle in real time; inputting the operation data into a preset load identification model to obtain load information of the vehicle, the preset load identification model being obtained by training historical operation data and historical load information of the vehicle; and an energy-saving driving strategy containing power system control parameters is generated according to the load information, and the vehicle is controlled to conduct energy-saving driving according to the energy-saving driving strategy. The power energy consumption of vehicle driving can be reduced.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to an energy-saving driving method, device, equipment, and storage medium based on real-time load identification. Background Technology

[0002] In scenarios such as logistics and transportation, vehicle load conditions change frequently. Existing energy-saving control technologies typically rely on fixed vehicle calibration parameters and dynamic models to predict power demand, making it difficult to adapt to the impact of dynamic load changes. This results in a mismatch between control strategies and actual operating conditions, leading to high energy consumption. Therefore, reducing the power energy consumption of vehicle driving remains a problem that needs to be solved.

[0003] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this application is to provide an energy-saving driving method, device, equipment, and storage medium based on real-time load identification, aiming to solve the technical problem of how to reduce the power energy consumption of vehicle driving.

[0005] To achieve the above objectives, this application proposes an energy-saving driving method based on real-time load identification, the method comprising:

[0006] Real-time acquisition of vehicle operating data; The operating data is input into a preset load recognition model to obtain the load information of the vehicle. The preset load recognition model is trained using historical vehicle operating data and historical load information. An energy-saving driving strategy, including power system control parameters, is generated based on the load information, and the vehicle is controlled to drive in an energy-saving manner according to the energy-saving driving strategy.

[0007] In one embodiment, prior to the step of acquiring vehicle operating data in real time, the method further includes: Obtain the original operating data sequence collected during the vehicle's historical operation, and obtain the historical load information corresponding to the original operating data sequence in time; A feature parameter set is generated based on the original running data sequence; The initial model is trained based on the feature parameter set and the historical load information to obtain the preset load recognition model.

[0008] In one embodiment, the step of generating a feature parameter set based on the original running data sequence includes: The original running data sequence is subjected to time synchronization and resampling processing to generate time series data with equal intervals; A quality-sensitive candidate feature set is constructed based on the equal-interval time series data; The quality-sensitive candidate feature set is subjected to statistical feature expansion processing to generate a high-dimensional candidate feature set; Feature filtering is performed on the high-dimensional candidate feature set to determine the feature parameter set associated with load changes.

[0009] In one embodiment, the step of constructing a quality-sensitive candidate feature set based on the equally spaced time series data includes: Construct unit torque acceleration response characteristics based on the equal-interval time series data; The dynamic response features of the vehicle speed as it rises from zero to a preset threshold are extracted from the equally spaced time series data. The dynamic response data includes at least one of the following: acceleration rise time, peak acceleration, and acceleration rate of change. Extract torque demand characteristics of the vehicle during the constant speed driving phase from the equally spaced time series data; A mass-sensitive candidate feature set is determined based on the unit torque acceleration response characteristics, the dynamic response characteristics, and the torque demand characteristics.

[0010] In one embodiment, the step of performing feature filtering on the high-dimensional candidate feature set to determine the feature parameter set associated with load changes includes: The candidate features in the high-dimensional candidate feature set are compared with the historical load information to obtain the correlation analysis results. Based on the correlation analysis results, a set of feature parameters associated with load changes is determined from the high-dimensional candidate feature set.

[0011] In one embodiment, the step of generating an energy-saving driving strategy including powertrain control parameters based on the load information, and controlling the vehicle to perform energy-saving driving according to the energy-saving driving strategy, includes: Obtain the shift characteristic map of the preset load zone; Based on the load information, a target shifting strategy matching the current load is determined from the preset load zone shifting characteristic map. An energy-saving driving strategy is generated based on the target shifting strategy.

[0012] In one embodiment, the step of generating an energy-saving driving strategy including powertrain control parameters based on the load information, and controlling the vehicle to perform energy-saving driving according to the energy-saving driving strategy, includes: Obtain forecasts of future power demand; The predicted future power demand is corrected based on the load information to obtain the corrected final power demand prediction. An energy-saving driving strategy is generated based on the final power demand forecast.

[0013] Furthermore, to achieve the above objectives, this application also proposes an energy-saving driving device based on real-time load identification, wherein the energy-saving driving device based on real-time load identification includes: The acquisition module is used to acquire vehicle operating data in real time; The identification module is used to input the operating data into a preset load identification model to obtain the load information of the vehicle. The preset load identification model is trained by the vehicle's historical operating data and historical load information. The generation module is used to generate an energy-saving driving strategy that includes power system control parameters based on the load information, and to control the vehicle to drive in an energy-saving manner according to the energy-saving driving strategy.

[0014] In addition, to achieve the above objectives, this application also proposes an energy-saving driving device based on real-time load identification, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the energy-saving driving method based on real-time load identification as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the energy-saving driving method based on real-time load identification as described above.

[0016] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the energy-saving driving method based on real-time load identification as described above.

[0017] This application provides an energy-saving driving method based on real-time load identification. The method involves acquiring vehicle operating data in real time; inputting this operating data into a preset load identification model to obtain the vehicle's load information; the preset load identification model being trained using historical vehicle operating data and historical load information; generating an energy-saving driving strategy including powertrain control parameters based on the load information; and controlling the vehicle to drive in an energy-saving manner according to the energy-saving driving strategy. By identifying vehicle load information in real time and generating a matching energy-saving driving control strategy, this application ensures that the generated strategy accurately matches the vehicle load, thereby reducing the vehicle's energy consumption during driving. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating an embodiment of the energy-saving driving method based on real-time load identification in this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the energy-saving driving method based on real-time load identification in this application; Figure 3 This is a schematic diagram of the module structure of the energy-saving driving device based on real-time load identification in an embodiment of this application; Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the energy-saving driving method based on real-time load identification in the embodiments of this application.

[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0024] This application acquires vehicle operating data in real time; inputs the operating data into a preset load recognition model to obtain the vehicle's load information, the preset load recognition model being trained using historical vehicle operating data and historical load information; generates an energy-saving driving strategy including power system control parameters based on the load information, and controls the vehicle to perform energy-saving driving based on the energy-saving driving strategy.

[0025] In scenarios such as logistics and transportation, vehicle load conditions change frequently. Existing energy-saving control technologies typically rely on fixed vehicle calibration parameters and dynamic models to predict power demand, making it difficult to adapt to the impact of dynamic load changes. This results in a mismatch between control strategies and actual operating conditions, leading to high energy consumption. Therefore, reducing the power energy consumption of vehicle driving remains a problem that needs to be solved.

[0026] This application identifies vehicle load information in real time and generates a matching energy-saving driving control strategy, which accurately matches the vehicle load and thus reduces the power energy consumption of vehicle driving.

[0027] Based on this, embodiments of this application provide an energy-saving driving method based on real-time load identification, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the energy-saving driving method based on real-time load identification in this application.

[0028] In this embodiment, the energy-saving driving method based on real-time load identification includes steps S10 to S40: Step S10: Acquire vehicle operating data in real time; It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as an energy-saving driving device based on real-time load identification. The following description uses an energy-saving driving device based on real-time load identification as an example to illustrate this embodiment and the subsequent embodiments.

[0029] It should be noted that a data acquisition environment can be built based on the vehicle's existing standard sensor system. Specifically, the onboard data acquisition unit can acquire operational data from the vehicle controller area network in real time. This operational data includes at least engine output torque, engine speed, vehicle speed, longitudinal acceleration, transmission gear information, and state parameters related to changes in vehicle mass, such as suspension height or airbag pressure.

[0030] Step S20: Input the operating data into the preset load recognition model to obtain the load information of the vehicle. The preset load recognition model is trained by the vehicle's historical operating data and historical load information. It should be noted that the preset load identification model has undergone lightweight processing and is deployed in the vehicle's onboard computing unit. This onboard computing unit can be an intelligent communication terminal or a vehicle domain controller, used for online processing of real-time sensor data collected during vehicle operation. During vehicle operation, the onboard computing unit continuously receives vehicle operation data from the CAN bus and inputs this data into the load identification model for real-time inference, thereby dynamically outputting the current vehicle load status or estimated load value. In this way, vehicle load information can be continuously obtained throughout the entire vehicle operation without the need for additional dedicated weighing sensors, providing key input parameters for subsequent energy-saving control strategies.

[0031] Step S30: Generate an energy-saving driving strategy containing power system control parameters based on the load information, and control the vehicle to drive in an energy-saving manner according to the energy-saving driving strategy.

[0032] It should be noted that after obtaining the vehicle's load information, an energy-saving driving strategy can be generated based on this information, i.e., dynamically adjusting the vehicle's power control parameters. For example, when a heavy load is detected, the system automatically adjusts the transmission shift strategy to reduce the engine's high-speed operation time while ensuring power output; when an unloaded or lightly loaded state is detected, a more aggressive fuel-saving shift logic is adopted to reduce fuel consumption. For vehicles equipped with hybrid or range-extended powertrains, the system adjusts the predictive energy management strategy based on real-time load information, reserving or supplementing electrical energy in advance to cope with high load demands under heavy load conditions, and increasing the proportion of pure electric drive under light load conditions. For vehicles with predictive cruise control, the system pre-adjusts the power output or energy recovery intensity based on load information before uphill or downhill conditions, thereby avoiding energy waste caused by changes in mass.

[0033] In one feasible approach, the step of generating an energy-saving driving strategy including power system control parameters based on the load information, and controlling the vehicle to perform energy-saving driving based on the energy-saving driving strategy includes: obtaining a preset load zone shift characteristic map; determining a target shift strategy matching the current load from the preset load zone shift characteristic map based on the load information; and generating an energy-saving driving strategy based on the target shift strategy.

[0034] It should be noted that after identifying whether the vehicle is unloaded or lightly loaded based on the load information, it is not a simple matter of upshifting in advance, but rather a dynamic reconstruction of the shift decision boundary curve based on the load status. Specifically, in this embodiment, the optimal fuel economy engine specific fuel consumption curve and corresponding speed range under different load conditions are established in advance during the vehicle calibration stage, and a load-zone shift MAP table is formed. When the load identification module outputs that the current load is lower than a set threshold (e.g., 40% of the vehicle's rated weight), the control unit shifts the original standard shift speed threshold down by a predetermined proportion range, for example, reducing the upshift trigger speed from the original calibration value n1 to n1×(1 α), where α is an adjustment coefficient inversely proportional to the load. This method prioritizes keeping the engine operating point in the low specific fuel consumption range. Simultaneously, under light load conditions, the mapping relationship between throttle pedal opening and engine load needs to be recalibrated. Specifically, under the same throttle opening conditions, the target torque request value is appropriately reduced to decrease the probability of transient high fuel injection ranges. Furthermore, by adjusting the engagement timing of the transmission lock-up clutch, it is made to enter the lock-up state earlier in the lower vehicle speed range, reducing torque converter slip loss. In addition, under coasting conditions, when the throttle opening is detected to be zero and the longitudinal acceleration is less than a set threshold, the system triggers a coasting downshift suppression strategy in advance to avoid unnecessary downshift rev-matching, thereby reducing fuel consumption. When a heavy load condition is identified, the shifting strategy ensures power reserve by delaying the upshift speed boundary and increasing the downshift response sensitivity. Specifically, the upshift trigger speed is moved up to n2 = n1 × (1 + β), where β is an adjustment coefficient, and the downshift delay time Δt is shortened to avoid insufficient power response due to increased mass. At the same time, it limits frequent gear shifting to prevent increased fuel consumption caused by frequent speed fluctuations under high load. Through the aforementioned shift MAP reconstruction mechanism, load-zone adaptive shift control is achieved, optimizing fuel economy while ensuring power performance.

[0035] In one feasible approach, the step of generating an energy-saving driving strategy including power system control parameters based on the load information, and controlling the vehicle to perform energy-saving driving based on the energy-saving driving strategy includes: obtaining a future power demand prediction value; correcting the future power demand prediction value based on the load information to obtain a corrected final power demand prediction value; and generating an energy-saving driving strategy based on the final power demand prediction value.

[0036] It should be noted that for vehicles equipped with hybrid or range-extended powertrains, this embodiment introduces a load correction factor into the predictive energy management module to dynamically adjust the State of Charge (SOC) control range, the upper limit of motor output power, and the timing of engine intervention. In the predictive energy management strategy, the system typically calculates future energy demand based on future road gradient information, traffic condition information, and driving behavior predictions. This embodiment introduces a mass correction term, m_est, into the original prediction model, transforming the original power demand prediction model from: P 需求 = f(v, a, θ) expands to: P 需求= f(v, a, θ, m_est), where m_est is the real-time identified load, v is the velocity, a is the acceleration, and θ is the gradient. Under heavy load conditions, when m_est exceeds a preset threshold, the system raises the SOC lower limit control value. For example, the original SOC lower limit is raised from 30% to 35% or higher to ensure sufficient energy output under future incline or overtaking conditions. Simultaneously, the engine early intervention threshold is raised, allowing the engine to participate in power generation before the SOC approaches the lower limit, thus avoiding deep battery discharge. Under light load conditions, the upper limit of the SOC target range is lowered, allowing the battery to participate more in power output and delaying the engine start-up, thereby increasing the proportion of pure electric driving. Furthermore, the motor output power limit curve is scaled according to the load. Under heavy load conditions, the motor is allowed to output a higher proportion of peak power for short periods to meet acceleration requirements; under light load conditions, the duration of high peak power is limited to improve overall efficiency. Through the above-mentioned quality-corrected predictive control model, energy management is no longer based on a fixed quality assumption, but rather achieves dynamic quality closed-loop regulation.

[0037] Furthermore, under heavy load conditions, the system can pre-emptively schedule energy reserves based on future road condition predictions and the current load level. When the system identifies an uphill section or high-power demand zone within a certain distance and the current State of Charge (SOC) is below the target upper limit, the control unit proactively increases the engine's power generation, raising the SOC to the preset reserve range in advance, for example, controlling the SOC to above 40%, to ensure continuous motor output when entering the high-load zone. Simultaneously, the system limits the continuous output time of the high-power motor to prevent excessive battery discharge under heavy load conditions, which could lead to efficiency degradation or lifespan reduction. Under light load conditions, a high-purity electric priority strategy is adopted. Specifically, when the vehicle speed is below a set threshold (e.g., 60 km / h) and the torque demand is below the upper limit of the motor's economic output range, the motor is prioritized to drive the vehicle, expanding the permissible acceleration range for pure electric driving, allowing the driver to accelerate normally without engine intervention. In downhill conditions, the upper limit of energy recovery intensity is allowed to be increased under light load conditions to enhance the braking energy recovery ratio; while under heavy load conditions, the upper limit of recovery intensity is appropriately reduced to maintain braking stability. By employing the aforementioned energy storage pre-scheduling and power allocation strategies, quality-related proactive energy planning and control can be achieved, thereby avoiding energy waste caused by fixed control logic.

[0038] It should be noted that during the execution of the energy-saving control strategy, the system will display the currently identified load status and corresponding economical driving suggestions to the driver through the vehicle's human-machine interface. The displayed content includes load mode prompts and driving behavior suggestions matched to the current load, guiding the driver to adopt a driving style more consistent with the current vehicle weight, thereby further improving the overall energy-saving effect.

[0039] This embodiment acquires vehicle operating data in real time; inputs the operating data into a preset load recognition model to obtain the vehicle's load information, the preset load recognition model being trained using historical vehicle operating data and historical load information; generates an energy-saving driving strategy including powertrain control parameters based on the load information, and controls the vehicle to drive energy-efficiently according to the energy-saving driving strategy. This embodiment, by identifying vehicle load information in real time and generating a matching energy-saving driving control strategy, ensures that the generated strategy accurately matches the vehicle load, thereby reducing the vehicle's energy consumption during driving.

[0040] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 Before step S10, the energy-saving driving method based on real-time load identification further includes steps S01 to S03: Step S01: Obtain the original operating data sequence collected by the vehicle during its historical operation, and obtain the historical load information corresponding to the original operating data sequence in time; It should be noted that the original operational data sequence can be continuously collected during the actual historical operation of the vehicle and stored according to the time series. To obtain training labels for the load identification model, the vehicle's actual historical load information needs to be acquired synchronously at loading / unloading or operational nodes. This historical load information can be obtained through weighbridge weighing or freight document records and matched with the vehicle's operational data within the corresponding time period, thus forming a training dataset with load labels. Based on this training dataset, the load identification problem is modeled. Initially, the load status can be divided into discrete categories such as empty, half-loaded, and fully loaded. Subsequently, this can be further expanded to continuously predict the actual load weight of the vehicle. Step S02: Generate a feature parameter set based on the original running data sequence; It should be noted that during model construction, feature parameters highly correlated with load changes can be extracted from the original vehicle operation signals, such as longitudinal acceleration response under the same throttle opening conditions, torque demand characteristics when the vehicle is traveling at a constant speed, and power response characteristics during the vehicle's start-up phase.

[0041] In one feasible approach, the step of generating a feature parameter set based on the original operating data sequence includes: performing time synchronization and resampling processing on the original operating data sequence to generate equally spaced time series data; constructing a quality-sensitive candidate feature set based on the equally spaced time series data; performing statistical feature expansion processing on the quality-sensitive candidate feature set to generate a high-dimensional candidate feature set; and performing feature filtering on the high-dimensional candidate feature set to determine a feature parameter set associated with load changes.

[0042] It should be noted that since the acquisition periods of different signals in the CAN bus may differ, the acquired raw operational data sequence can be time-synchronized. Through interpolation or resampling methods, all signals are aligned to a unified time base, generating equally spaced time-series data. Then, based on the principles of vehicle longitudinal dynamics, a series of candidate features highly correlated with vehicle mass changes are constructed from the equally spaced time-series data. To mitigate the instantaneous impact of driving behavior differences on feature values, a sliding time window mechanism can be used to statistically expand the variables in the mass-sensitive candidate feature set. Finally, a data-driven method is used to filter the high-dimensional candidate feature set, obtaining a set of feature parameters associated with load changes.

[0043] It should be noted that the time synchronization and resampling process specifically involves synchronizing and resampling the engine output torque, engine speed, vehicle speed, longitudinal acceleration, transmission gear information, and suspension height or airbag pressure signals acquired via the CAN bus, so that each signal forms an equally spaced time sequence on a unified time scale. Subsequently, outlier detection and filtering can be performed on the original signals to eliminate abnormal fluctuations caused by communication delays, sensor jitter, or transient interference. A moving average filtering method is then used to smooth the signal, ensuring the stability of subsequent feature calculations.

[0044] It should be noted that the statistical feature expansion process for the aforementioned quality-sensitive candidate feature set can specifically employ a sliding time window mechanism to expand the statistical features of each variable. Within a sliding window with a predetermined time interval, the mean, variance, range, kurtosis, and first-order difference mean of each candidate variable are calculated, thereby transforming the instantaneous dynamic signal into a stable statistical representation feature. Through time window statistical processing, the instantaneous impact of driving behavior differences on feature values ​​can be weakened, improving the long-term stable representation ability of features for load changes.

[0045] In one feasible approach, the step of constructing a mass-sensitive candidate feature set based on the equally spaced time series data includes: constructing a unit torque acceleration response feature based on the equally spaced time series data; extracting dynamic response features from the equally spaced time series data during the process of vehicle speed rising from zero to a preset threshold, wherein the dynamic response data includes at least one of acceleration rise time, peak acceleration, and acceleration rate of change; extracting torque demand features during the vehicle's constant speed driving phase from the equally spaced time series data; and determining a mass-sensitive candidate feature set based on the unit torque acceleration response feature, the dynamic response feature, and the torque demand feature.

[0046] It should be noted that mass-sensitive candidate variables can be constructed based on the longitudinal dynamic balance relationship of the vehicle. According to the principles of vehicle dynamics, the driving force and mass of a vehicle satisfy the following relationship: the driving force equals the product of the total mass of the vehicle and the longitudinal acceleration, plus the sum of rolling resistance, gradient resistance, and air resistance. Therefore, when the road gradient change is small or predictable, the acceleration response coefficient generated by the unit torque of the vehicle is significantly negatively correlated with the total vehicle mass. Based on this principle, this embodiment constructs a unit torque acceleration response feature, that is, under the same engine torque or the same throttle opening, the average response value of the vehicle's longitudinal acceleration is statistically analyzed, and the ratio of torque to acceleration or the regression slope is calculated to characterize the trend of vehicle mass change. Furthermore, since the vehicle acceleration build-up time is significantly correlated with the load level during the vehicle's start-up phase or low-speed acceleration phase, this embodiment extracts dynamic response indicators such as acceleration rise time, peak acceleration, and acceleration change rate as the vehicle speed increases from zero or low speed range to a set threshold range, and uses these as mass-related candidate features. Simultaneously, during the constant-speed driving phase, the average torque value and torque fluctuation amplitude required to maintain a stable vehicle speed are extracted. These parameters vary significantly under different load conditions and can be used to enhance the model's sensitivity to mass changes. Furthermore, for vehicles equipped with air suspension or airbag systems, this embodiment further utilizes the suspension height change or the average airbag pressure as a static mass indication feature. After the vehicle is loaded with cargo, changes in axle load will cause changes in suspension compression. By statistically analyzing the mean and standard deviation of suspension height within the stable driving range, the overall vehicle mass change can be directly reflected. To avoid road surface excitation interference, this embodiment only collects suspension data when the absolute value of longitudinal acceleration is below a set threshold to ensure feature stability.

[0047] In one feasible approach, the step of performing feature filtering on the high-dimensional candidate feature set to determine the feature parameter set associated with load changes includes: performing correlation analysis between the candidate features in the high-dimensional candidate feature set and the historical load information to obtain correlation analysis results; and determining the feature parameter set associated with load changes from the high-dimensional candidate feature set based on the correlation analysis results.

[0048] It should be noted that this embodiment uses a data-driven approach for feature correlation screening. Specifically, candidate features are correlated with actual load data within the corresponding time period. The correlation coefficient or mutual information value between each feature and the load is calculated, and redundant features with correlation below a set threshold are removed. Simultaneously, feature importance weights can be calculated based on a tree model or sparsification can be performed using a regression model with L1 regularization to obtain the optimal set of feature parameters highly correlated with load changes.

[0049] Step S03: Train the initial model based on the feature parameter set and the historical load information to obtain the preset load recognition model.

[0050] It should be noted that, based on the aforementioned feature parameter set and historical load information, a lightweight machine learning model suitable for embedded environments is used to train and validate the load status, ultimately resulting in a load recognition model. This model can stably and accurately infer vehicle load under different road gradients, traffic conditions, and vehicle states.

[0051] It should be noted that after the load recognition model is trained, it is lightweighted and deployed to the vehicle's onboard computing unit. This onboard computing unit can be an intelligent communication terminal or a vehicle domain controller, used for online processing of real-time sensor data during vehicle operation. During vehicle operation, the onboard computing unit continuously receives vehicle operation data from the CAN bus and inputs this data into the load recognition model for real-time inference, thereby dynamically outputting the current vehicle load status or estimated load capacity. In this way, without the need for additional dedicated weighing sensors, vehicle load information can be continuously obtained throughout the entire driving process, providing key input parameters for subsequent fuel-saving control strategies.

[0052] This embodiment acquires the original operating data sequence collected during the vehicle's historical operation and obtains the historical load information corresponding to the original operating data sequence in time; generates a feature parameter set based on the original operating data sequence; and trains an initial model based on the feature parameter set and the historical load information to obtain a preset load recognition model. This embodiment, by selecting load-related features to form a training set, enables the trained model to output more accurate load information.

[0053] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the energy-saving driving method based on real-time load identification in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0054] This application also provides an energy-saving driving device based on real-time load recognition, please refer to... Figure 3 The energy-saving driving device based on real-time load identification includes: The acquisition module 10 is used to acquire vehicle operating data in real time; The identification module 20 is used to input the operating data into a preset load identification model to obtain the load information of the vehicle. The preset load identification model is trained by the vehicle's historical operating data and historical load information. The generation module 30 is used to generate an energy-saving driving strategy containing power system control parameters based on the load information, and to control the vehicle to drive in an energy-saving manner based on the energy-saving driving strategy.

[0055] This application acquires vehicle operating data in real time; inputs the operating data into a preset load recognition model to obtain the vehicle's load information, the preset load recognition model being trained using historical vehicle operating data and historical load information; generates an energy-saving driving strategy including powertrain control parameters based on the load information, and controls the vehicle to drive in an energy-saving manner according to the energy-saving driving strategy. This application, by identifying vehicle load information in real time and generating a matching energy-saving driving control strategy, ensures that the generated strategy accurately matches the vehicle load, thereby reducing the energy consumption of vehicle driving.

[0056] In one embodiment, the acquisition module 10 is further configured to acquire the original operating data sequence collected by the vehicle during historical operation, and acquire the historical load information corresponding to the original operating data sequence in time; generate a feature parameter set based on the original operating data sequence; and train an initial model based on the feature parameter set and the historical load information to obtain a preset load recognition model.

[0057] In one embodiment, the acquisition module 10 is further configured to perform time synchronization and resampling processing on the original running data sequence to generate equally spaced time series data; construct a quality-sensitive candidate feature set based on the equally spaced time series data; perform statistical feature expansion processing on the quality-sensitive candidate feature set to generate a high-dimensional candidate feature set; and perform feature filtering on the high-dimensional candidate feature set to determine a set of feature parameters associated with load changes.

[0058] In one embodiment, the acquisition module 10 is further configured to construct a unit torque acceleration response feature based on the equally spaced time series data; extract dynamic response features from the equally spaced time series data during the process of the vehicle speed rising from zero to a preset threshold, wherein the dynamic response data includes at least one of acceleration rise time, peak acceleration, and acceleration rate of change; extract torque demand features during the vehicle's constant speed driving phase from the equally spaced time series data; and determine a mass-sensitive candidate feature set based on the unit torque acceleration response feature, the dynamic response feature, and the torque demand feature.

[0059] In one embodiment, the acquisition module 10 is further configured to perform correlation analysis between the candidate features in the high-dimensional candidate feature set and the historical load information to obtain the correlation analysis result; and determine the feature parameter set associated with load change from the high-dimensional candidate feature set based on the correlation analysis result.

[0060] In one embodiment, the generation module 30 is further configured to acquire a preset load zone shift characteristic map; determine a target shift strategy matching the current load from the preset load zone shift characteristic map based on the load information; and generate an energy-saving driving strategy based on the target shift strategy.

[0061] In one embodiment, the generation module 30 is further configured to obtain a future power demand forecast; correct the future power demand forecast based on the load information to obtain a corrected final power demand forecast; and generate an energy-saving driving strategy based on the final power demand forecast.

[0062] The energy-saving driving device based on real-time load identification provided in this application, employing the energy-saving driving method based on real-time load identification in the above embodiments, can solve the technical problem of how to reduce the power energy consumption of vehicle driving. Compared with the prior art, the beneficial effects of the energy-saving driving device based on real-time load identification provided in this application are the same as the beneficial effects of the energy-saving driving method based on real-time load identification provided in the above embodiments, and other technical features in the energy-saving driving device based on real-time load identification are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0063] This application provides an energy-saving driving device based on real-time load identification. The energy-saving driving device based on real-time load identification includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the energy-saving driving method based on real-time load identification in the above embodiment 1.

[0064] The following is for reference. Figure 4 This document illustrates a structural schematic diagram of an energy-saving driving device based on real-time load identification, suitable for implementing embodiments of this application. The energy-saving driving device based on real-time load identification in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The energy-saving driving device based on real-time load identification shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0065] like Figure 4As shown, the energy-saving driving device based on real-time load identification may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the energy-saving driving device based on real-time load identification. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the energy-saving driving device based on real-time load identification to exchange data with other devices wirelessly or via wired communication. Although the figure shows an energy-saving driving device based on real-time load identification with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0066] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0067] The energy-saving driving device based on real-time load identification provided in this application, employing the energy-saving driving method based on real-time load identification in the above embodiments, can solve the technical problem of how to reduce the power energy consumption of vehicle driving. Compared with the prior art, the beneficial effects of the energy-saving driving device based on real-time load identification provided in this application are the same as the beneficial effects of the energy-saving driving method based on real-time load identification provided in the above embodiments, and other technical features in the energy-saving driving device based on real-time load identification are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0068] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0069] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0070] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the energy-saving driving method based on real-time load identification in the above embodiments.

[0071] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0072] The aforementioned computer-readable storage medium may be included in the energy-saving driving device based on real-time load identification; or it may exist independently and not be assembled into the energy-saving driving device based on real-time load identification.

[0073] The aforementioned computer-readable storage medium carries one or more programs that, when executed by an energy-saving driving device based on real-time load identification, cause the energy-saving driving device based on real-time load identification to: acquire vehicle operating data in real time; input the operating data into a preset load identification model to obtain the vehicle's load information, wherein the preset load identification model is trained using historical vehicle operating data and historical load information; generate an energy-saving driving strategy including power system control parameters based on the load information; and control the vehicle to perform energy-saving driving based on the energy-saving driving strategy.

[0074] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0075] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0076] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0077] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described energy-saving driving method based on real-time load identification, thereby solving the technical problem of how to reduce the power energy consumption of vehicle driving. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the energy-saving driving method based on real-time load identification provided in the above embodiments, and will not be repeated here.

[0078] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the energy-saving driving method based on real-time load identification as described above.

[0079] The computer program product provided in this application can solve the technical problem of how to reduce the power energy consumption of vehicle driving. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the energy-saving driving method based on real-time load identification provided in the above embodiments, and will not be repeated here.

[0080] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. An energy-saving driving method based on real-time load recognition, characterized in that, The method includes: Real-time acquisition of vehicle operating data; The operating data is input into a preset load recognition model to obtain the load information of the vehicle. The preset load recognition model is trained using historical vehicle operating data and historical load information. An energy-saving driving strategy, including power system control parameters, is generated based on the load information, and the vehicle is controlled to drive in an energy-saving manner according to the energy-saving driving strategy.

2. The method as described in claim 1, characterized in that, Before the step of acquiring vehicle operating data in real time, the method further includes: Obtain the original operating data sequence collected during the vehicle's historical operation, and obtain the historical load information corresponding to the original operating data sequence in time; A feature parameter set is generated based on the original running data sequence; The initial model is trained based on the feature parameter set and the historical load information to obtain the preset load recognition model.

3. The method as described in claim 2, characterized in that, The step of generating a feature parameter set based on the original running data sequence includes: The original running data sequence is subjected to time synchronization and resampling processing to generate time series data with equal intervals; A quality-sensitive candidate feature set is constructed based on the equal-interval time series data; The quality-sensitive candidate feature set is subjected to statistical feature expansion processing to generate a high-dimensional candidate feature set; Feature filtering is performed on the high-dimensional candidate feature set to determine the feature parameter set associated with load changes.

4. The method as described in claim 3, characterized in that, The step of constructing a quality-sensitive candidate feature set based on the equally spaced time series data includes: Construct unit torque acceleration response characteristics based on the equal-interval time series data; The dynamic response features of the vehicle speed as it rises from zero to a preset threshold are extracted from the equally spaced time series data. The dynamic response data includes at least one of the following: acceleration rise time, peak acceleration, and acceleration rate of change. Extract torque demand characteristics of the vehicle during the constant speed driving phase from the equally spaced time series data; A mass-sensitive candidate feature set is determined based on the unit torque acceleration response characteristics, the dynamic response characteristics, and the torque demand characteristics.

5. The method as described in claim 3, characterized in that, The step of performing feature filtering on the high-dimensional candidate feature set to determine the feature parameter set associated with load changes includes: The candidate features in the high-dimensional candidate feature set are compared with the historical load information to obtain the correlation analysis results. Based on the correlation analysis results, a set of feature parameters associated with load changes is determined from the high-dimensional candidate feature set.

6. The method as described in claim 1, characterized in that, The step of generating an energy-saving driving strategy including powertrain control parameters based on the load information includes: Obtain the shift characteristic map of the preset load zone; Based on the load information, a target shifting strategy matching the current load is determined from the preset load zone shifting characteristic map. An energy-saving driving strategy is generated based on the target shifting strategy.

7. The method as described in claim 1, characterized in that, The step of generating an energy-saving driving strategy including powertrain control parameters based on the load information includes: Obtain forecasts of future power demand; The predicted future power demand is corrected based on the load information to obtain the corrected final power demand prediction. An energy-saving driving strategy is generated based on the final power demand forecast.

8. An energy-saving driving device based on real-time load recognition, characterized in that, The device includes: The acquisition module is used to acquire vehicle operating data in real time; The identification module is used to input the operating data into a preset load identification model to obtain the load information of the vehicle. The preset load identification model is trained by the vehicle's historical operating data and historical load information. The generation module is used to generate an energy-saving driving strategy that includes power system control parameters based on the load information, and to control the vehicle to drive in an energy-saving manner according to the energy-saving driving strategy.

9. An energy-saving driving device based on real-time load recognition, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the energy-saving driving method based on real-time load identification as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the energy-saving driving method based on real-time load identification as described in any one of claims 1 to 7.

Images