Commercial vehicle transient fuel consumption accurate prediction method, device and equipment based on random mixture model and storage medium

Abstract

The application discloses a commercial vehicle transient fuel consumption accurate prediction method and device based on a random mixed model, equipment and a storage medium, relates to the technical field of commercial vehicle fuel consumption prediction, and comprises the following steps: acquiring model input data and a transient fuel consumption model set, pre-processing the model input data to obtain pre-processed model input data; constructing an experience distribution based on the model input data and the transient fuel consumption model set, determining a model experience distribution set, and the model experience distribution set comprises a model prior distribution set and a model posterior distribution set; selecting a reliable model to predict fuel consumption based on the model input data and the model experience distribution set and updating the prior distribution, determining a target predicted transient fuel consumption set, and completing transient fuel consumption accurate prediction based on the target predicted transient fuel consumption set. The pre-processed data is input into multiple transient fuel consumption models for training, a reliable model is selected by constructing an experience distribution, and the prediction accuracy is dynamically updated and significantly improved, so that the fuel consumption is effectively reduced.

Description

Technical Field

[0001] This application relates to the field of commercial vehicle fuel consumption prediction technology, and in particular to a method, device, equipment and storage medium for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model. Background Technology

[0002] Commercial vehicles are crucial carriers of transportation, undertaking a significant portion of logistics and personnel transport in global economic activities. In terms of economic costs, commercial vehicles consume enormous amounts of fuel. While accounting for only 12% of the total vehicle fleet, they contribute a staggering 55% of carbon emissions. Fuel consumption constitutes a considerable proportion of the operating costs of commercial vehicles. Besides impacting the economic efficiency of transportation operations, fuel consumption also affects the transportation costs of goods, ultimately influencing the costs of the entire supply chain and even the prices of goods across society. Regarding environmental impact, commercial vehicles, due to their long mileage and high fuel consumption, are major contributors to exhaust emissions in the transportation sector. Their emissions of gases and particulate matter have a significant impact on air quality and global climate. Therefore, reducing fuel consumption in commercial vehicles is of great importance to both the economy and the environment. Fuel consumption models are the core of predictive cruise control systems for commercial vehicles, and their accuracy directly affects the energy efficiency of the predictive cruise system. Therefore, establishing accurate and rapid fuel consumption models is currently a key focus and a significant challenge in the field.

[0003] Existing fuel consumption models can be categorized into two types: steady-state fuel consumption models and transient fuel consumption models. Steady-state fuel consumption models describe fuel consumption under stable driving conditions by establishing a mapping function between parameters such as engine speed, torque, and power and fuel consumption rate. Transient fuel consumption models describe fuel consumption under dynamically changing conditions, including two modeling methods: "steady-state initial value + transient correction" and direct modeling based on transient variables. The "steady-state initial value + transient correction" modeling method in transient fuel consumption models adds a transient correction amount or multiplies it by a transient correction coefficient to the predicted fuel consumption based on transient variables, building upon the steady-state model. The direct modeling method based on transient variables directly uses transient variables to model fuel consumption and then corrects the model based on historical information.

[0004] However, existing steady-state fuel consumption models require the vehicle's powertrain to be in a relatively stable operating state and necessitate separate calibration for different powertrains, resulting in high testing costs and hindering large-scale deployment. Furthermore, the transient correction parameters in the "steady-state initial value + transient correction" modeling method for transient fuel consumption are difficult to obtain, and the historical information and datasets of the direct modeling method based on transient variables are strongly coupled, making it difficult to extend to other operating conditions. Therefore, how to more efficiently and accurately predict transient fuel consumption to adapt to complex and variable driving conditions has become an urgent problem to be solved.

[0005] 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

[0006] The main objective of this application is to provide a method, device, equipment, and storage medium for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic hybrid model, aiming to solve the technical problem of how to perform transient fuel consumption prediction more efficiently and accurately to adapt to complex and changing driving conditions.

[0007] To achieve the above objectives, this application proposes a method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model. The method includes:

[0008] Obtain model input data and transient fuel consumption model set, and preprocess the model input data to obtain preprocessed model input data;

[0009] Based on the model input data and the transient fuel consumption model set, an empirical distribution is constructed, and a model empirical distribution set is determined. The model empirical distribution set includes a model prior distribution set and a model posterior distribution set.

[0010] Based on the model input data and the model experience distribution set, a reliable model is selected to predict fuel consumption and the prior distribution is updated. The target predicted transient fuel consumption set is determined, and the accurate prediction of transient fuel consumption is completed based on the target predicted transient fuel consumption set.

[0011] In one embodiment, the step of obtaining model input data and transient fuel consumption model set includes:

[0012] The system acquires vehicle characteristic parameters, driver control signals, road map information, a steady-state initial value transient correction model, a polynomial transient fuel consumption prediction model, and a target fuel consumption prediction model. The vehicle characteristic parameters include vehicle speed information, vehicle acceleration information, and vehicle mass information. The driver control signals include accelerator pedal opening information, brake pedal opening information, steering wheel angle information, steering wheel torque information, and vehicle gear information. The road map information includes road surface adhesion information, slope information, and speed limit information.

[0013] The model input data is determined based on the vehicle characteristic parameters, the driver's control signals, and the road map information;

[0014] The transient fuel consumption model set is determined based on the steady-state initial value transient correction model, the polynomial transient fuel consumption prediction model, and the target fuel consumption prediction model.

[0015] In one embodiment, the step of constructing an empirical distribution based on the model input data and the transient fuel consumption model set, and determining the model empirical distribution set, includes:

[0016] The model input data is input into the transient fuel consumption model set for training to determine the predicted transient fuel consumption set;

[0017] Based on the model input data, filter fuel consumption data and construct the model prior distribution set;

[0018] The model posterior distribution set is calculated based on the predicted transient fuel consumption set and the model prior distribution set.

[0019] The model empirical distribution set is obtained based on the model prior distribution set and the model posterior distribution set.

[0020] In one embodiment, the step of filtering fuel consumption data based on the model input data and constructing a model prior distribution set includes:

[0021] Based on the input data of the model, filter fuel consumption data and determine historical fuel consumption data and operating condition similarity values;

[0022] A prior distribution set for the model is constructed based on the historical fuel consumption data and the operating condition similarity values.

[0023] In one embodiment, the step of calculating the model posterior distribution set based on the predicted transient fuel consumption set and the model prior distribution set includes:

[0024] Methods for obtaining posterior distribution calculations;

[0025] The model posterior distribution set is calculated based on the posterior distribution calculation method, the predicted transient fuel consumption set, and the model prior distribution set.

[0026] In one embodiment, the step of selecting a reliable model to predict fuel consumption and updating the prior distribution based on the model input data and the model empirical distribution set, and determining the target predicted transient fuel consumption set, includes:

[0027] Obtain the location of the posterior subdivision interval;

[0028] The confidence level is calculated based on the model's posterior distribution set in the model's empirical distribution set and the confidence interval position of the posterior distribution set.

[0029] Based on the confidence level, the reliability of the model is determined, the fuel consumption confidence model is determined, and the transient fuel consumption prediction value is predicted based on the fuel consumption confidence model.

[0030] Based on the model input data and the transient fuel consumption prediction value, adjust the historical fuel consumption data, reconstruct the model prior distribution set, and determine the updated model prior distribution set.

[0031] The fuel consumption model is trained based on the prior distribution set of the updated model, and the fuel consumption prediction optimization model set is determined.

[0032] The target predicted transient fuel consumption set is output based on the fuel consumption prediction optimization model set.

[0033] In one embodiment, the step of accurately predicting transient fuel consumption based on the target predicted transient fuel consumption set includes:

[0034] Integrating the target predicted transient fuel consumption set yields the target accurate transient fuel consumption prediction value;

[0035] Accurate prediction of transient fuel consumption is achieved based on the target accuracy transient fuel consumption prediction value.

[0036] Furthermore, to achieve the above objectives, this application also proposes a device for accurately predicting the transient fuel consumption of commercial vehicles based on a stochastic mixture model. The device includes:

[0037] The acquisition module is used to acquire model input data and transient fuel consumption model set, and to preprocess the model input data to obtain preprocessed model input data.

[0038] The processing module is used to construct an empirical distribution based on the model input data and the transient fuel consumption model set, and to determine the model empirical distribution set, which includes the model prior distribution set and the model posterior distribution set.

[0039] The execution module is used to select a reliable model to predict fuel consumption and update the prior distribution based on the model input data and the model experience distribution set, determine the target predicted transient fuel consumption set, and complete the accurate prediction of transient fuel consumption based on the target predicted transient fuel consumption set.

[0040] Furthermore, to achieve the above objectives, this application also proposes a device for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model. The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model as described above.

[0041] 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. When the computer program is executed by a processor, it implements the steps of the method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model as described above.

[0042] One or more technical solutions proposed in this application have at least the following technical effects:

[0043] This embodiment proposes a method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model. The method involves acquiring model input data and a transient fuel consumption model set; preprocessing the model input data to obtain preprocessed model input data; constructing an empirical distribution based on the model input data and the transient fuel consumption model set to determine a model empirical distribution set, which includes a model prior distribution set and a model posterior distribution set; selecting a reliable model to predict fuel consumption and updating the prior distribution based on the model input data and the model empirical distribution set to determine a target predicted transient fuel consumption set; and completing the accurate prediction of transient fuel consumption based on the target predicted transient fuel consumption set. This application preprocesses the model input data to improve the signal-to-noise ratio, and trains multiple transient fuel consumption models to construct the model's prior and posterior distributions. By evaluating the reliability of each model's prediction results, a reliable model is selected for transient fuel consumption prediction. The prior distribution is updated based on the prediction results, and finally, the prediction results of each model are integrated to output a high-precision transient fuel consumption prediction value. This significantly improves prediction accuracy, is applicable to different driving conditions, enhances the model's generalization ability, facilitates large-scale deployment in different vehicles and driving conditions, effectively reduces fuel consumption in commercial vehicles, and reduces carbon emissions. Attached Figure Description

[0044] 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.

[0045] 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.

[0046] Figure 1 This is a flowchart illustrating an embodiment of the method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model in this application.

[0047] Figure 2 This is a flowchart illustrating Embodiment 2 of the method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model in this application.

[0048] Figure 3 A simplified flowchart illustrating the method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model, provided in this application embodiment;

[0049] Figure 4 This is a schematic diagram of the module structure of the commercial vehicle transient fuel consumption accurate prediction device based on a stochastic mixture model according to an embodiment of this application;

[0050] Figure 5This is a schematic diagram of the equipment structure of the hardware operating environment involved in the method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model in the embodiments of this application.

[0051] 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

[0052] 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.

[0053] 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.

[0054] The main solution of this application embodiment is as follows: Obtain model input data and a transient fuel consumption model set; preprocess the model input data to obtain preprocessed model input data; construct an empirical distribution based on the model input data and the transient fuel consumption model set, and determine a model empirical distribution set, which includes a model prior distribution set and a model posterior distribution set; select a reliable model to predict fuel consumption based on the model input data and the model empirical distribution set, update the prior distribution, determine a target transient fuel consumption prediction set, and complete accurate transient fuel consumption prediction based on the target transient fuel consumption prediction set.

[0055] In this embodiment, for ease of description, the following description will focus on identifying a commercial vehicle transient fuel consumption prediction device based on a stochastic hybrid model.

[0056] Because existing steady-state fuel consumption models require the vehicle powertrain to be in a relatively stable operating state and need to be calibrated separately for different powertrains, the testing costs are high, which is not conducive to large-scale deployment. In contrast, the parameters of the transient correction amount in the "steady-state initial value + transient correction" modeling method of transient fuel consumption model are not easy to obtain, and the historical information and dataset of the direct modeling method based on transient variables in transient fuel consumption model are strongly coupled, making it difficult to extend to other operating conditions.

[0057] This application provides a solution that involves acquiring model input data and a transient fuel consumption model set, preprocessing the model input data to obtain preprocessed model input data, constructing an empirical distribution based on the model input data and the transient fuel consumption model set, determining a model empirical distribution set, which includes a model prior distribution set and a model posterior distribution set, selecting a reliable model to predict fuel consumption based on the model input data and the model empirical distribution set, updating the prior distribution, determining a target transient fuel consumption prediction set, and completing accurate transient fuel consumption prediction based on the target transient fuel consumption prediction set.

[0058] As can be seen from the above embodiments, this application preprocesses the model input data to improve the signal-to-noise ratio, and inputs multiple transient fuel consumption models for training, constructs the model's prior and posterior distributions, and selects a reliable model for transient fuel consumption prediction by evaluating the reliability of the prediction results of each model, and updates the prior distribution based on the prediction results, and finally integrates the prediction results of each model to output a high-precision transient fuel consumption prediction value, which significantly improves the prediction accuracy, can be applied to different driving conditions, enhances the model's generalization ability, facilitates large-scale deployment in different vehicles and under different driving conditions, effectively reduces the fuel consumption of commercial vehicles, and reduces carbon emissions.

[0059] Based on this, embodiments of this application provide a method for accurately predicting the transient fuel consumption of commercial vehicles based on a stochastic mixture model, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model, as described in this application.

[0060] In this embodiment, the method for accurately predicting the transient fuel consumption of commercial vehicles based on a stochastic mixture model includes steps S10 to S30:

[0061] Step S10: Obtain model input data and transient fuel consumption model set, and preprocess the model input data to obtain preprocessed model input data;

[0062] It should be noted that the model input data reflects the characteristics of various states and environmental factors of the vehicle during actual driving, and the transient fuel consumption model set reflects the characteristics of a set of models that model and predict transient fuel consumption from different perspectives.

[0063] It is understood that the model input data can characterize the fuel consumption changes of a vehicle under different operating conditions, and the transient fuel consumption model set can adapt to a variety of complex driving conditions through different modeling methods and data processing methods, and more accurately predict vehicle fuel consumption. By acquiring and preprocessing the model input data and using multiple transient fuel consumption models for prediction, the accuracy of transient fuel consumption prediction can be significantly improved, as can the accuracy of fuel consumption prediction. At the same time, the applicability of the model under different vehicles and different driving conditions is enhanced, effectively reducing the fuel consumption of commercial vehicles.

[0064] For ease of understanding, we will take the acquisition of model input data and transient fuel consumption model set as an example, where the information acquisition device is the information acquisition module and the storage device is the memory.

[0065] The information acquisition module obtains vehicle characteristic parameters, driver control signals, road map information, a steady-state initial value transient correction model, a polynomial transient fuel consumption prediction model, and a target fuel consumption prediction model. The vehicle characteristic parameters include vehicle speed information, vehicle acceleration information, and vehicle mass information. The driver control signals include accelerator pedal opening information, brake pedal opening information, steering wheel angle information, steering wheel torque information, and vehicle gear information. The road map information includes road surface adhesion information, slope information, and speed limit information. Based on the vehicle characteristic parameters, driver control signals, and road map information, the model input data is determined, i.e., the vehicle parameters, driver control signals, and vehicle mass information are acquired. The model requires inputs such as map information of the road segment where the vehicle is located to obtain model input data. Vehicle parameters include dynamic and static parameters such as vehicle speed, acceleration, and mass. Driver control signals include inputs from the driver during driving, such as accelerator pedal opening, brake pedal opening, steering wheel angle, steering wheel torque, and vehicle gear position. Map information includes road surface adhesion, gradient, and speed limits of the road segments where the vehicle is located and will subsequently pass through. Vehicle parameters and driver control signals can be directly measured by onboard sensors or indirectly measured by algorithms. Map information is extracted from high-precision maps by combining vehicle GPS coordinates, vehicle route planning, and other information to obtain model input data.

[0066] The model input data is preprocessed to obtain preprocessed model input data. This preprocessing aims to reduce noise and eliminate outliers in the data. Noise reduction and outlier elimination include, but are not limited to, noise generated by sensors or data acquisition modules, and data with significant errors. After eliminating outliers, a symmetric exponential shift filter is used to reduce noise and improve the signal-to-noise ratio of the input data. The expression for the symmetric exponential shift filter is:

[0067]

[0068] D = min{3Δ, i-1, N} α -1}

[0069] Where, x α (t k () represents the original data of vehicle α at sampling time k. For the smoothed data, N α α represents the total number of sample points, T represents the time span of the smoothing operation, and dt represents the time interval between each frame.

[0070] The transient fuel consumption model set is determined based on the steady-state initial value transient correction model, the polynomial transient fuel consumption prediction model, and the target fuel consumption prediction model. That is, the selected transient fuel consumption models include, but are not limited to, two types of transient fuel consumption models: "steady-state initial value + transient correction" or direct modeling based on transient variables.

[0071] The model based on "steady-state initial value + transient correction" can be represented by multiple formulas.

[0072] The steady-state initial fuel consumption estimate is expressed as:

[0073]

[0074] in, To obtain the steady-state fuel consumption rate, a logarithmic transformation is performed to obtain the logarithmic steady-state fuel consumption rate m. s Using engine torque T e and rotational speed ω e As input, a polynomial fitting is performed. Since the vehicle fuel consumption rate is generally a bivariate function of engine speed or torque, with an order of 2 or 3, three different polynomial structures are used for estimation.

[0075] Using the transient correction module, the vehicle speed v and acceleration a are fitted, and the result is expressed as:

[0076]

[0077] Where β is the parameter corresponding to the power.

[0078] The steady-state estimate is then combined with the transient correction factor to predict the transient fuel consumption rate, expressed as:

[0079]

[0080] Thus, we obtain the model of "steady-state initial value + transient correction", that is, the steady-state initial value and transient correction model.

[0081] The polynomial transient fuel consumption estimation model based on the least squares method is expressed as follows:

[0082]

[0083] Where α0, α1, α2, and α3 are coefficients obtained by fitting using the least squares method, β0 is the fuel consumption rate when the vehicle is idling, a is the vehicle acceleration, and v is the vehicle speed.

[0084] Thus, a polynomial transient fuel consumption estimation model based on the least squares method is obtained, which is the polynomial transient fuel consumption prediction model.

[0085] The CNN-LSTM fuel consumption prediction model is represented as follows:

[0086]

[0087] Where f is a function representing the transient fuel consumption prediction neural network, x is the network input vector, and Φ is the network parameter.

[0088] The input vector x can be represented by the relevant variables as follows:

[0089] x(t) = {v(t), a(t), P} x (t),P y (t),y(t)}

[0090] Where, v(t), a(t), P x (t), P y y(t) and y(t) represent the vehicle's speed, acceleration, longitude, latitude, and instantaneous fuel consumption at time t, respectively.

[0091] Thus, the CNN-LSTM fuel consumption prediction model is obtained, which is the target fuel consumption prediction model.

[0092] The transient fuel consumption model set is determined based on the steady-state initial value transient correction model, the polynomial transient fuel consumption prediction model, and the target fuel consumption prediction model.

[0093] Subsequent processing is performed based on the model input data and the transient fuel consumption model set.

[0094] In one feasible implementation, step S10 may include steps A11 to A13:

[0095] Step A11: Obtain vehicle characteristic parameters, driver control signals, road map information, steady-state initial value transient correction model, polynomial transient fuel consumption prediction model, and target fuel consumption prediction model. The vehicle characteristic parameters include vehicle speed information, vehicle acceleration information, and vehicle mass information. The driver control signals include accelerator pedal opening information, brake pedal opening information, steering wheel angle information, steering wheel torque information, and vehicle gear information. The road map information includes road surface adhesion information, slope information, and speed limit information.

[0096] It should be noted that the vehicle characteristic parameters reflect the characteristics of the vehicle's dynamic driving state, the driver's control signals reflect the characteristics of the driver's operating intentions and behaviors, the road map information reflects the characteristics of detailed information about the vehicle's driving environment, the steady-state initial value transient correction model reflects the characteristics of correcting the predicted fuel consumption by introducing transient variables based on the steady-state fuel consumption model, the polynomial transient fuel consumption prediction model reflects the characteristics of directly modeling and predicting transient fuel consumption by fitting vehicle speed and acceleration variables using the least squares method, and the target fuel consumption prediction model reflects the characteristics of integrating multi-source information for high-precision fuel consumption prediction.

[0097] Step A12: Determine the model input data based on the vehicle characteristic parameters, the driver's control signals, and the road map information;

[0098] It is understood that the vehicle characteristic parameters may include vehicle speed information, vehicle acceleration information, and vehicle mass information, which are collected in real time by onboard sensors to more accurately predict fuel consumption. The driver operation signals may include accelerator pedal opening information, brake pedal opening information, steering wheel angle information, steering wheel torque information, and vehicle gear information, which directly reflect the driver's operating intentions and behaviors, and thus directly affect fuel consumption prediction. The road map information may include road surface adhesion information, slope information, and speed limit information, which are extracted from high-precision maps through the vehicle's GPS coordinates and route planning to predict fuel consumption changes under different road conditions.

[0099] Step A13: Determine the transient fuel consumption model set based on the steady-state initial value transient correction model, the polynomial transient fuel consumption prediction model, and the target fuel consumption prediction model.

[0100] It is understood that the steady-state initial value transient correction model is a combination of steady-state initial value fuel consumption estimation, transient correction module and transient fuel consumption rate, which can more accurately reflect the fuel consumption of the vehicle under dynamic changing conditions. The polynomial transient fuel consumption prediction model can estimate fuel consumption through polynomial structure and accurately capture the nonlinear relationship between fuel consumption and vehicle dynamic parameters. The target fuel consumption prediction model can provide more comprehensive and accurate fuel consumption prediction results by integrating multi-source information.

[0101] Step S20: Construct an empirical distribution based on the model input data and the transient fuel consumption model set, and determine the model empirical distribution set, which includes the model prior distribution set and the model posterior distribution set;

[0102] It should be noted that the model's empirical distribution set reflects the characteristics of more accurate fuel consumption distribution estimation through different distribution calculation methods.

[0103] It is understood that the model experience distribution set only represents the inclusion relationship between the model prior distribution set and the model posterior distribution set, that is, it cannot be calculated by jointly using the model prior distribution set and the model posterior distribution set. The model prior distribution set can provide statistical information of historical data, while the model posterior distribution set is dynamically adjusted according to new data, thereby significantly improving the accuracy of transient fuel consumption prediction.

[0104] For ease of understanding, we will take the determination of the model's empirical distribution set as an example, where the information acquisition device is the information acquisition module, the storage device is the memory, and the processing device is the processing module.

[0105] The information acquisition module obtains model input data and inputs it into the transient fuel consumption model set. The model input data is then used to train the transient fuel consumption model set, determining the predicted transient fuel consumption set. This involves pre-training the model using the fuel consumption dataset, and then inputting the pre-trained data into various selected transient fuel consumption models to predict the transient fuel consumption at the next moment. Fuel consumption data is filtered based on the model input data to determine historical fuel consumption data and operating condition similarity values. A model prior distribution set is constructed based on the historical fuel consumption data and the operating condition similarity values. This involves sampling historical fuel consumption data and constructing prior distributions for each model. Historical fuel consumption data includes existing datasets and fuel consumption data continuously collected during vehicle operation. Similar operating conditions are extracted from the fuel consumption dataset based on the model input data. Fuel consumption data with similar vehicle loads under the same road segment or conditions are extracted, and the data are weighted based on the similarity of operating conditions to obtain the model prior distribution set. A Gaussian mixture model is then used to fit the prior distribution.

[0106] Among them, the Gaussian mixture model is a linear combination of multiple normal distribution functions, which can fit different types of distributions. A single multidimensional normal distribution can be expressed as:

[0107]

[0108] The Gaussian mixture model, obtained by weighting multiple multidimensional normal distributions, is expressed as:

[0109]

[0110] Where X is the sample, μ is the sample mean, Σ is the variance matrix, and α is the variance matrix. j This represents the weight of the j-th multidimensional normal distribution.

[0111] A method for calculating the posterior distribution is obtained. Based on this method, the predicted transient fuel consumption set, and the model prior distribution set, the model posterior distribution set is calculated. Specifically, approximate Bayesian computation is used to estimate the posterior distribution based on the predicted values ​​of each model. According to the prediction results of each model and the constructed prior distribution, the posterior distribution is estimated using the approximate Bayesian computation method. The basic idea of ​​approximate Bayesian computation is to estimate the posterior distribution of parameters through simulated data and observed data. The posterior distribution is estimated using the prediction results of each model and fuel consumption data under similar operating conditions, resulting in the model posterior distribution set. The posterior distribution is expressed by Bayes' theorem as follows:

[0112] P(θD)∝P(D|θ)P(θ)

[0113] Where P(θD) is the posterior probability, P(D|θ) is the likelihood function representing the probability of observing data D under parameter θ, and P(θ) is the prior distribution of the parameter.

[0114] Since the likelihood function is difficult to calculate, the posterior distribution can be approximated by comparing the prediction results of each model with fuel consumption data under similar operating conditions.

[0115] The distance metrics used for comparison include Euclidean distance, Wasserstein distance, etc.

[0116] For two vectors x and y, the Euclidean distance can be expressed as:

[0117]

[0118] The Wasserstein distance, also known as the Earth-Mover distance, is often used to compare the similarity between the distributions of simulated and observed data. The Wasserstein distance measures the minimum average distance that needs to be moved from distribution P to distribution Q.

[0119] Using the Wasserstein distance, it can be expressed as:

[0120]

[0121] In the formula, P and Q are two probability distributions, and Π(P,Q) is the set of joint distributions γ.

[0122] Subsequent processing is performed based on the model's prior distribution set and posterior distribution set.

[0123] Step S30: Select a reliable model to predict fuel consumption and update the prior distribution based on the model input data and the model experience distribution set, determine the target predicted transient fuel consumption set, and complete the accurate prediction of transient fuel consumption based on the target predicted transient fuel consumption set.

[0124] It should be noted that the target predicted transient fuel consumption set reflects the characteristics of the model prediction value set of the final determined transient fuel consumption prediction values ​​used to complete the accurate prediction of transient fuel consumption.

[0125] It is understood that the target predicted transient fuel consumption set is a set of model predictions with high confidence and strong credibility obtained by filtering the model posterior distribution sets of each model from multiple model prediction results using the posterior distribution confidence interval position, and organizing the model prediction values ​​into a set.

[0126] For ease of understanding, we will take the determination of the target prediction transient fuel consumption set as an example, where the information acquisition device is the information acquisition module, the storage device is the memory, and the execution device is the execution module.

[0127] The information acquisition module obtains the model input data, the model's empirical distribution set, and the position of the posterior distribution's confidence interval. Based on the model's posterior distribution set within the empirical distribution set and the position of the posterior distribution's confidence interval, it calculates the confidence score. Based on this confidence score, it judges the model's credibility, determines the fuel consumption confidence model, and predicts transient fuel consumption values ​​based on the fuel consumption confidence model. This evaluates the credibility of each model's transient fuel consumption prediction results for real-time input. The credibility of the model's prediction results is evaluated based on their position within the posterior distribution's confidence interval. If the confidence score is lower than a set threshold, the model is directly rejected. The Metropolis-Hasting method can be used to evaluate the acceptance of the sample. The Metropolis-Hasting method is expressed as:

[0128]

[0129] The Metropolis-Hasting method uses the acceptance rate ρ to determine the degree of acceptance of a sample and assigns a corresponding weight.

[0130] Determine if the prediction confidence level is lower than the set threshold. If the prediction confidence level is lower than the set threshold, retrain all models in the model library using all historical fuel consumption data to obtain new model parameters.

[0131] If the prediction confidence is not lower than the set threshold, adjust the historical fuel consumption data based on the model input data and the transient fuel consumption prediction value, reconstruct the model prior distribution set, determine the updated model prior distribution set, train the fuel consumption model based on the updated model prior distribution set, and determine the fuel consumption prediction optimization model set. This means storing the model's input data and output transient fuel consumption prediction value as historical fuel consumption data and updating the prior distribution. The historical fuel consumption data is stored as an input matrix X and an output value Y. The input vector X is composed of preprocessed map information vectors, vehicle information vectors, and driver driving behavior vectors. The input matrix X can be represented as:

[0132]

[0133] By using threshold judgment, the dynamic updating of models in the model library can be achieved, significantly improving the accuracy of model predictions.

[0134] Based on the optimized fuel consumption prediction model set, a target predicted transient fuel consumption set is output. This target predicted transient fuel consumption set is then integrated to obtain a target-accuracy transient fuel consumption prediction value. Based on this target-accuracy transient fuel consumption prediction value, a precise transient fuel consumption prediction is completed; that is, the transient fuel consumption prediction value is output by combining the prediction results of each model. All accepted models' transient fuel consumption predictions for the next time moment are output, and a normalized weighted sum is performed according to the calculated weights. The prediction results of multiple models are integrated, and historical fuel consumption data is used to integrate the predictions of each model, ultimately obtaining a high-accuracy transient fuel consumption prediction value, thus completing the precise transient fuel consumption prediction.

[0135] In one feasible implementation, step S30 may include steps B11 to B16:

[0136] Step B11: Obtain the location of the posterior substantive distribution information interval;

[0137] It should be noted that the position of the posterior distribution confidence interval reflects the specific location of the confidence interval in which the model prediction result is located.

[0138] It is understood that the location of the posterior distribution confidence interval can characterize the reliability of the model prediction results. The closer the location is to the center of the posterior distribution, the higher the reliability of the prediction results.

[0139] Step B12: Calculate the confidence level based on the model posterior distribution set in the model empirical distribution set and the confidence interval position of the posterior distribution set;

[0140] It should be noted that the confidence level reflects the degree of credibility of the model's prediction results in the posterior distribution.

[0141] It is understood that the confidence level can characterize the relative position of the model prediction result in the posterior distribution, and is usually represented by a value between 0 and 1. The higher the confidence level, the more reliable the model prediction result is and the closer it is to the true value.

[0142] Step B13: Based on the confidence level, determine the reliability of the model, determine the fuel consumption confidence model, and predict the transient fuel consumption forecast value based on the fuel consumption confidence model;

[0143] It should be noted that the transient fuel consumption prediction value reflects the characteristics of the value obtained by predicting the fuel consumption of commercial vehicles at a specific time based on a selected reliable model.

[0144] It is understood that the transient fuel consumption prediction value can characterize the fuel consumption of a vehicle under dynamically changing operating conditions. The high-precision prediction value is obtained by integrating the prediction results of multiple models and weighting and summing them according to the confidence level, thereby enabling energy-saving control and route planning for commercial vehicles.

[0145] Step B14: Adjust historical fuel consumption data based on the model input data and the transient fuel consumption prediction value, reconstruct the model prior distribution set, and determine the updated model prior distribution set;

[0146] It should be noted that the updated model prior distribution set reflects the characteristics of the new prior distribution set obtained by dynamically updating the model's prior distribution based on new prediction results and historical data during the model prediction process.

[0147] It is understandable that updating the model prior distribution set allows the model to continuously learn and adapt to new data, thereby improving the model's prediction accuracy and generalization ability. By continuously adjusting the prior distribution, the model can better reflect the current driving conditions and vehicle status.

[0148] Step B15: Train the fuel consumption model based on the prior distribution set of the updated model, and determine the fuel consumption prediction optimization model set;

[0149] It should be noted that the oil consumption prediction optimization model set reflects the characteristics of the model set that is retrained after dynamically updating the model prior distribution set during the model prediction process, and has higher prediction accuracy and adaptability.

[0150] It is understandable that the fuel consumption prediction optimization model set can more accurately predict the transient fuel consumption of commercial vehicles under different driving conditions.

[0151] Step B16: Output the target predicted transient fuel consumption set based on the fuel consumption prediction optimization model set.

[0152] It is understood that the target predicted transient fuel consumption set can more accurately characterize the transient fuel consumption of commercial vehicles under different driving conditions, thereby enabling energy-saving control and route planning for commercial vehicles.

[0153] In another feasible implementation, step S30 may include steps C11 to C12:

[0154] Step C11: Integrate the target predicted transient fuel consumption set to obtain the target accurate transient fuel consumption prediction value;

[0155] It should be noted that the target accuracy transient fuel consumption prediction value reflects the characteristics of the final transient fuel consumption prediction value obtained by integrating the prediction results of multiple reliable models and weighting and summing them according to the confidence level of each model.

[0156] It is understood that the target accuracy transient fuel consumption prediction value can characterize the fuel consumption of commercial vehicles at a specific moment, and has high accuracy and high reliability.

[0157] Step C12: Based on the target accuracy transient fuel consumption prediction value, complete the accurate prediction of transient fuel consumption.

[0158] Understandably, by integrating the prediction results of multiple reliable models and weighting and summing them according to the confidence level of each model, the accuracy of transient fuel consumption prediction is significantly improved, ensuring high accuracy and high reliability of the prediction results. Furthermore, by continuously learning and adapting to new data, the fuel consumption of commercial vehicles is significantly reduced.

[0159] This embodiment proposes a method for accurate prediction of transient fuel consumption in commercial vehicles based on a stochastic mixture model. The method involves acquiring model input data and a set of transient fuel consumption models, preprocessing the model input data to obtain preprocessed model input data, constructing an empirical distribution based on the model input data and the transient fuel consumption model set, and determining a model empirical distribution set, which includes a model prior distribution set and a model posterior distribution set. Based on the model input data and the model empirical distribution set, a reliable model is selected to predict fuel consumption, and the prior distribution is updated to determine a target predicted transient fuel consumption set. Based on the target predicted transient fuel consumption set, accurate transient fuel consumption prediction is completed. This method solves the technical problem of how to perform transient fuel consumption prediction more efficiently to adapt to complex and changing driving conditions. Compared with existing technologies, this application constructs prior and posterior distributions by combining multiple transient fuel consumption models, selects reliable models for fuel consumption prediction, dynamically updates the prior distribution, and integrates the prediction results to complete high-precision transient fuel consumption prediction. This significantly improves prediction accuracy, enhances model adaptability, and can be applied to different driving conditions, effectively reducing fuel consumption in commercial vehicles.

[0160] Based on the first embodiment of this application, in the second embodiment of this application, the same or similar content as the first embodiment can be referred to the above description, and will not be repeated hereafter.

[0161] In this embodiment, refer to Figure 2 , Figure 2 This is a flowchart illustrating Embodiment 2 of the method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model, wherein step S20 specifically includes steps S21 to S24:

[0162] Step S21: Input the model input data into the transient fuel consumption model set for training, and determine the predicted transient fuel consumption set;

[0163] It should be noted that the predicted transient fuel consumption set reflects the characteristics of the set of fuel consumption prediction values ​​obtained by using multiple different transient fuel consumption models.

[0164] Understandably, each model has its own unique modeling method and data processing approach, which can predict transient fuel consumption from different perspectives. By inputting the model input data into multiple transient fuel consumption models, a combination of predicted values ​​can be obtained, i.e., a set of predicted transient fuel consumption, which can characterize the fuel consumption of commercial vehicles under different driving conditions.

[0165] For ease of understanding, we will take the determination of the predicted transient fuel consumption set as an example, where the information acquisition device is the information acquisition module, the storage device is the memory, and the processing device is the processing module.

[0166] The information acquisition module obtains the model input data and inputs it into the transient fuel consumption model set. The model input data is then input into the transient fuel consumption model set for training to determine the predicted transient fuel consumption set. That is, the fuel consumption dataset is used to pre-train the model input data, and then the pre-trained data is input into the selected transient fuel consumption models to predict the transient fuel consumption at the next moment, thus obtaining the predicted transient fuel consumption set. Subsequent processing is then performed based on the predicted transient fuel consumption set.

[0167] Step S22: Based on the model input data, filter fuel consumption data and construct the model prior distribution set;

[0168] It should be noted that the model prior distribution set reflects the characteristics of the prior probability distribution set obtained by fitting a Gaussian mixture model based on historical fuel consumption data and operating condition similarity values.

[0169] For ease of understanding, we will take the construction of a prior distribution set of the model as an example, where the information acquisition device is the information acquisition module, the storage device is the memory, and the processing device is the processing module.

[0170] The information acquisition module obtains model input data and a predicted transient fuel consumption set. Based on the model input data, it filters fuel consumption data, determines historical fuel consumption data and operating condition similarity values, and constructs a model prior distribution set based on the historical fuel consumption data and the operating condition similarity values. This involves sampling historical fuel consumption data and constructing prior distributions for each model. Historical fuel consumption data includes existing datasets and fuel consumption data continuously collected during vehicle operation. Based on the model input data, similar operating conditions are extracted from the fuel consumption dataset. Fuel consumption data under the same road segment or road conditions with similar vehicle loads are extracted, and the data are weighted based on the degree of similarity to obtain the model prior distribution set. A Gaussian mixture model is then used to fit the prior distribution.

[0171] Among them, the Gaussian mixture model is a linear combination of multiple normal distribution functions, which can fit different types of distributions. A single multidimensional normal distribution can be expressed as:

[0172]

[0173] The Gaussian mixture model, obtained by weighting multiple multidimensional normal distributions, is expressed as:

[0174]

[0175] Where X is the sample, μ is the sample mean, Σ is the variance matrix, and α is the variance matrix.j This represents the weight of the j-th multidimensional normal distribution.

[0176] In one feasible implementation, step S22 may include steps D11 to D12:

[0177] Step D11: Based on the input data of the model, filter fuel consumption data and determine historical fuel consumption data and operating condition similarity values;

[0178] It should be noted that the historical fuel consumption data reflects the fuel consumption data that is continuously collected and accumulated during vehicle operation, including the characteristics of fuel consumption records of the vehicle under different road sections and driving conditions. The operating condition similarity value reflects the characteristics of the similarity index calculated by comparing multiple parameters of the current operating condition with the historical operating condition.

[0179] It is understood that the historical fuel consumption data represents the fuel consumption of the vehicle under various operating conditions and is used to construct the prior distribution. The operating condition similarity value is used to filter the historical fuel consumption data that is most similar to the current operating condition, so as to ensure that the prior distribution can accurately reflect the fuel consumption under the current operating condition.

[0180] Step D12: Construct a prior distribution set for the model based on the historical fuel consumption data and the operating condition similarity value.

[0181] It is understood that the model prior distribution set can represent the prior distribution constructed based on historical statistical information of commercial vehicle fuel consumption under different driving conditions.

[0182] Step S23: Calculate the model posterior distribution set based on the predicted transient fuel consumption set and the model prior distribution set;

[0183] It should be noted that the model posterior distribution set reflects the characteristics of the posterior probability distribution set obtained by using an approximate Bayesian calculation method, combining the model prediction results and historical data, given the model input data and prior distribution.

[0184] For ease of understanding, we will use the posterior distribution set of the computational model as an example, where the information acquisition device is the information acquisition module, the storage device is the memory, and the processing device is the processing module.

[0185] The information acquisition module obtains the model prior distribution set, the predicted transient fuel consumption set, and the posterior distribution calculation method. Based on the posterior distribution calculation method, the predicted transient fuel consumption set, and the model prior distribution set, it calculates the model posterior distribution set, that is, it uses approximate Bayesian calculation to estimate the posterior distribution based on the predicted values ​​of each model. Based on the prediction results of each model and the constructed prior distribution, the posterior distribution is estimated using the approximate Bayesian calculation method. The basic idea of ​​approximate Bayesian calculation is to estimate the posterior distribution of parameters through simulated data and observed data. By estimating the posterior distribution through the prediction results of each model and fuel consumption data under similar operating conditions, the model posterior distribution set is obtained. The posterior distribution given by Bayes' theorem is expressed as:

[0186] P(θD)∝P(D|θ)P(θ)

[0187] Where P(θD) is the posterior probability, P(D|θ) is the likelihood function representing the probability of observing data D under parameter θ, and P(θ) is the prior distribution of the parameter.

[0188] Since the likelihood function is difficult to calculate, the posterior distribution can be approximated by comparing the prediction results of each model with fuel consumption data under similar operating conditions.

[0189] The distance metrics used for comparison include Euclidean distance, Wasserstein distance, etc.

[0190] For two vectors x and y, the Euclidean distance can be expressed as:

[0191]

[0192] The Wasserstein distance, also known as the Earth-Mover distance, is often used to compare the similarity between the distributions of simulated and observed data. The Wasserstein distance measures the minimum average distance that needs to be moved from distribution P to distribution Q.

[0193] Using the Wasserstein distance, it can be expressed as:

[0194]

[0195] In the formula, P and Q are two probability distributions, and Π(P,Q) is the set of joint distributions γ.

[0196] In one feasible implementation, step S23 may include steps E11 to E12:

[0197] Step E11: Obtain the posterior distribution calculation method;

[0198] It should be noted that the posterior distribution calculation method reflects the characteristics of estimating the posterior distribution of parameters by combining the model prediction results and the prior distribution through an approximate Bayesian calculation method.

[0199] It is understood that the posterior distribution calculation method compares simulated data with observed data and uses distance metrics to evaluate the similarity between the model's prediction results and historical data, thereby estimating the posterior distribution and ensuring that the model can better adapt to new data and operating conditions.

[0200] Step E12: Calculate the model posterior distribution set based on the posterior distribution calculation method, the predicted transient fuel consumption set, and the model prior distribution set.

[0201] Understandably, by using an approximate Bayesian calculation method combined with a distance metric to estimate the posterior distribution, the prediction accuracy of the model is significantly improved. Furthermore, the dynamic update mechanism of the posterior distribution allows the model to continuously learn and adapt to new data and operating conditions. By continuously adjusting the posterior distribution, the model can better adapt to different driving conditions and vehicle states, enhancing its adaptability. At the same time, calculating a high-precision posterior distribution can more efficiently perform energy-saving control and route planning for commercial vehicles, effectively reducing fuel consumption.

[0202] Step S24: Obtain the model empirical distribution set based on the model prior distribution set and the model posterior distribution set.

[0203] It should be noted that the model prior distribution set is obtained by filtering historical fuel consumption data similar to the current operating conditions and fitting it with a Gaussian mixture model, thus providing a prior probability distribution of fuel consumption. The model posterior distribution set is obtained by using an approximate Bayesian calculation method, combining the predicted transient fuel consumption set and the model prior distribution set, and updating the posterior distribution by comparing the similarity between the prediction results and historical data, thereby more accurately representing the fuel consumption distribution under the current data conditions.

[0204] For ease of understanding, we will take the example of obtaining the model's empirical distribution set, where the information acquisition device is the information acquisition module, the storage device is the memory, and the processing device is the processing module.

[0205] The model experience distribution set only represents the inclusion relationship between the model prior distribution set and the model posterior distribution set. That is, it cannot be calculated by combining the model prior distribution set and the model posterior distribution set. Subsequent processing is based on the model prior distribution set and the model posterior distribution set.

[0206] This embodiment proposes a method for accurately predicting the transient fuel consumption of commercial vehicles based on a stochastic mixture model. The method involves training the model using the input data from the transient fuel consumption model set to determine the predicted transient fuel consumption set; filtering fuel consumption data based on the input data to construct a model prior distribution set; calculating the model posterior distribution set based on the predicted transient fuel consumption set and the model prior distribution set; and obtaining the model empirical distribution set based on the model prior distribution set and the model posterior distribution set. This invention addresses the technical challenge of more accurately predicting transient fuel consumption to adapt to complex and variable driving conditions. Compared to existing technologies, this application trains multiple transient fuel consumption models by inputting preprocessed model input data into them. It establishes a fuel consumption empirical distribution as a prior distribution based on existing datasets and continuously accumulated fuel consumption data. Then, it builds a transient fuel consumption model library composed of various transient models, such as those using "steady-state initial values ​​+ transient corrections" or direct modeling based on transient variables. By using an approximate Bayesian calculation method to adjust the weights of each model, a hybrid model capable of accurately predicting transient fuel consumption is obtained. This allows for easier deployment on different vehicles and application to various driving conditions, significantly improving the model's accuracy and generalization ability.

[0207] For example, to help understand the implementation process of the method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model obtained by combining this embodiment with the above embodiment one, please refer to... Figure 3 , Figure 3 A simplified flowchart of a method for accurate prediction of transient fuel consumption in commercial vehicles based on a stochastic mixture model is provided, specifically:

[0208] Referring to Example 1, model input data and a transient fuel consumption model set are obtained. The model input data is preprocessed to obtain preprocessed model input data. An empirical distribution is constructed based on the model input data and the transient fuel consumption model set to determine the model empirical distribution set, which includes a model prior distribution set and a model posterior distribution set. A reliable model is selected to predict fuel consumption based on the model input data and the model empirical distribution set, and the prior distribution is updated to determine the target predicted transient fuel consumption set. Accurate prediction of transient fuel consumption is completed based on the target predicted transient fuel consumption set. Referring to Example 2, the model input data is input into the transient fuel consumption model set for training to determine the predicted transient fuel consumption set. Fuel consumption data is filtered based on the model input data to construct a model prior distribution set. The model posterior distribution set is calculated based on the predicted transient fuel consumption set and the model prior distribution set. The model empirical distribution set is obtained based on the model prior distribution set and the model posterior distribution set. The system acquires map information, including vehicle route planning, vehicle GPS coordinates, road surface adhesion and slope, and other map information; vehicle information, including vehicle speed, vehicle acceleration, vehicle load, and other vehicle information; and driver behavior, including pedal information, steering wheel signals, gear signals, and other driving behaviors. This data forms the model input data, which is then preprocessed. A prior distribution is constructed using historical fuel consumption data. The preprocessed data is then input into a multivariate nonlinear fuel consumption model, a least-squares fitted linear fuel consumption model, and a neural network model to construct a posterior distribution. Prediction reliability is assessed, and if the prediction falls below a reliability threshold, the system is retrained or the historical fuel consumption data is updated. Finally, the system outputs the final transient fuel consumption prediction value.

[0209] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the method for accurate prediction of transient fuel consumption of commercial vehicles based on stochastic hybrid models. Any simple modifications based on this technical concept are within the protection scope of this application.

[0210] This application also provides a device for accurately predicting the transient fuel consumption of commercial vehicles based on a stochastic mixture model. Please refer to [link / reference]. Figure 4 The commercial vehicle transient fuel consumption accurate prediction device based on a stochastic mixture model includes:

[0211] The acquisition module 10 is used to acquire model input data and transient fuel consumption model set, and to preprocess the model input data to obtain preprocessed model input data.

[0212] Processing module 20 is used to construct an empirical distribution based on the model input data and the transient fuel consumption model set, and to determine the model empirical distribution set, wherein the model empirical distribution set includes the model prior distribution set and the model posterior distribution set;

[0213] The execution module 30 is used to select a reliable model to predict fuel consumption and update the prior distribution based on the model input data and the model experience distribution set, determine the target predicted transient fuel consumption set, and complete the accurate prediction of transient fuel consumption based on the target predicted transient fuel consumption set.

[0214] The acquisition module 10 is also used to acquire vehicle characteristic parameters, driver control signals, road map information, steady-state initial value transient correction model, polynomial transient fuel consumption prediction model and target fuel consumption prediction model. The vehicle characteristic parameters include vehicle speed information, vehicle acceleration information and vehicle mass information. The driver control signals include accelerator pedal opening information, brake pedal opening information, steering wheel angle information, steering wheel torque information and vehicle gear information. The road map information includes road surface adhesion information, slope information and speed limit information.

[0215] The model input data is determined based on the vehicle characteristic parameters, the driver's control signals, and the road map information;

[0216] The transient fuel consumption model set is determined based on the steady-state initial value transient correction model, the polynomial transient fuel consumption prediction model, and the target fuel consumption prediction model.

[0217] The processing module 20 is further configured to input the model input data into the transient fuel consumption model set for training, and determine the predicted transient fuel consumption set;

[0218] Based on the model input data, filter fuel consumption data and construct the model prior distribution set;

[0219] The model posterior distribution set is calculated based on the predicted transient fuel consumption set and the model prior distribution set.

[0220] The model empirical distribution set is obtained based on the model prior distribution set and the model posterior distribution set.

[0221] The processing module 20 is also used to filter fuel consumption data based on the model input data and determine historical fuel consumption data and operating condition similarity values;

[0222] A prior distribution set for the model is constructed based on the historical fuel consumption data and the operating condition similarity values.

[0223] The processing module 20 is also used to obtain the posterior distribution calculation method;

[0224] The model posterior distribution set is calculated based on the posterior distribution calculation method, the predicted transient fuel consumption set, and the model prior distribution set.

[0225] The execution module 30 is also used to obtain the position of the posterior distribution information interval;

[0226] The confidence level is calculated based on the model's posterior distribution set in the model's empirical distribution set and the confidence interval position of the posterior distribution set.

[0227] Based on the confidence level, the reliability of the model is determined, the fuel consumption confidence model is determined, and the transient fuel consumption prediction value is predicted based on the fuel consumption confidence model.

[0228] Based on the model input data and the transient fuel consumption prediction value, adjust the historical fuel consumption data, reconstruct the model prior distribution set, and determine the updated model prior distribution set.

[0229] The fuel consumption model is trained based on the prior distribution set of the updated model, and the fuel consumption prediction optimization model set is determined.

[0230] The target predicted transient fuel consumption set is output based on the fuel consumption prediction optimization model set.

[0231] The execution module 30 is also used to integrate the target predicted transient fuel consumption set to obtain the target accuracy transient fuel consumption prediction value;

[0232] Accurate prediction of transient fuel consumption is achieved based on the target accuracy transient fuel consumption prediction value.

[0233] The transient fuel consumption prediction device for commercial vehicles based on a stochastic mixture model provided in this application employs the transient fuel consumption prediction method for commercial vehicles based on a stochastic mixture model described in the above embodiments. This addresses the technical problem of how to more efficiently and accurately predict transient fuel consumption to adapt to complex and changing driving conditions. Compared with the prior art, the beneficial effects of the transient fuel consumption prediction device for commercial vehicles based on a stochastic mixture model provided in this application are the same as those of the transient fuel consumption prediction method for commercial vehicles based on a stochastic mixture model provided in the above embodiments. Furthermore, other technical features of the transient fuel consumption prediction device for commercial vehicles based on a stochastic mixture model are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0234] This application provides a device for accurately predicting the transient fuel consumption of commercial vehicles based on a stochastic mixture model. The device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable 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 method for accurately predicting the transient fuel consumption of commercial vehicles based on a stochastic mixture model as described in Embodiment 1 above.

[0235] The following is for reference. Figure 5This document illustrates a structural schematic diagram of a commercial vehicle transient fuel consumption accurate prediction device based on a stochastic mixture model, suitable for implementing embodiments of this application. The commercial vehicle transient fuel consumption accurate prediction device based on a stochastic mixture model in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The illustrated device for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0236] like Figure 5 As shown, the commercial vehicle transient fuel consumption accurate prediction device based on a stochastic hybrid model may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the commercial vehicle transient fuel consumption accurate prediction device based on a stochastic hybrid model. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An 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 commercial vehicle transient fuel consumption prediction device based on a stochastic mixture model to wirelessly or wiredly communicate with other devices to exchange data. Although the figure shows a commercial vehicle transient fuel consumption prediction device based on a stochastic mixture model 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.

[0237] 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.

[0238] The transient fuel consumption prediction device for commercial vehicles based on a stochastic mixture model provided in this application employs the transient fuel consumption prediction method for commercial vehicles based on a stochastic mixture model described in the above embodiments. This addresses the technical problem of how to more efficiently and accurately predict transient fuel consumption to adapt to complex and changing driving conditions. Compared with the prior art, the beneficial effects of the transient fuel consumption prediction device for commercial vehicles based on a stochastic mixture model provided in this application are the same as those of the transient fuel consumption prediction method for commercial vehicles based on a stochastic mixture model provided in the above embodiments. Furthermore, other technical features of this transient fuel consumption prediction device for commercial vehicles based on a stochastic mixture model are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0239] 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.

[0240] 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.

[0241] 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 method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic hybrid model in the above embodiments.

[0242] 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.

[0243] The aforementioned computer-readable storage medium may be included in the commercial vehicle transient fuel consumption accurate prediction device based on a stochastic mixture model; or it may exist independently and not be assembled into the commercial vehicle transient fuel consumption accurate prediction device based on a stochastic mixture model.

[0244] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the commercial vehicle transient fuel consumption accurate prediction device based on a stochastic mixture model, the commercial vehicle transient fuel consumption accurate prediction device based on a stochastic mixture model performs the following: acquires model input data and a transient fuel consumption model set; preprocesses the model input data to obtain preprocessed model input data; constructs an empirical distribution based on the model input data and the transient fuel consumption model set, determines a model empirical distribution set, the model empirical distribution set including a model prior distribution set and a model posterior distribution set; selects a reliable model to predict fuel consumption and updates the prior distribution based on the model input data and the model empirical distribution set, determines a target predicted transient fuel consumption set, and completes the accurate prediction of transient fuel consumption based on the target predicted transient fuel consumption set.

[0245] 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).

[0246] 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.

[0247] 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.

[0248] 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 method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model. This method can solve the technical problem of how to more efficiently and accurately predict transient fuel consumption to adapt to complex and changing driving conditions. 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 method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic mixture model provided in the above embodiments, and will not be repeated here.

[0249] 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. A method for accurate prediction of transient fuel consumption of commercial vehicles based on stochastic mixing model, characterized in that, The method includes: Obtain model input data and transient fuel consumption model set, and preprocess the model input data to obtain preprocessed model input data; Based on the model input data and the transient fuel consumption model set, an empirical distribution is constructed, and a model empirical distribution set is determined. The model empirical distribution set includes a model prior distribution set and a model posterior distribution set. Based on the model input data and the model experience distribution set, a reliable model is selected to predict fuel consumption and the prior distribution is updated. A target predicted transient fuel consumption set is determined, and an accurate prediction of transient fuel consumption is completed based on the target predicted transient fuel consumption set. The steps to obtain the transient fuel consumption model set include: Obtain the steady-state initial value transient correction model, the polynomial transient fuel consumption prediction model, and the target fuel consumption prediction model; The transient fuel consumption model set is determined based on the steady-state initial value transient correction model, the polynomial transient fuel consumption prediction model, and the target fuel consumption prediction model. The step of selecting a reliable model to predict fuel consumption and updating the prior distribution based on the model input data and the model empirical distribution set, and determining the target predicted transient fuel consumption set, includes: Obtain the location of the posterior subdivision interval; The confidence level is calculated based on the model's posterior distribution set in the model's empirical distribution set and the confidence interval position of the posterior distribution set. The confidence level is used to determine the model's credibility, and the fuel consumption confidence model is determined. The transient fuel consumption prediction value is then predicted based on the fuel consumption confidence model. The fuel consumption confidence model is obtained by retraining the model in the model library using all historical fuel consumption data when the model's credibility is lower than the set threshold, or by retraining the model in the model library after adjusting the historical fuel consumption data according to the model input data and the transient fuel consumption prediction value when the model's credibility is not lower than the set threshold. Based on the model input data and the transient fuel consumption prediction value, adjust the historical fuel consumption data, reconstruct the model prior distribution set, and determine the updated model prior distribution set. The fuel consumption model is trained based on the prior distribution set of the updated model, and the fuel consumption prediction optimization model set is determined. Based on the fuel consumption prediction optimization model set, the target predicted transient fuel consumption set is output. The target predicted transient fuel consumption set is obtained by filtering the model posterior distribution set of each model from multiple model prediction results using the posterior distribution confidence interval position, and the model prediction values ​​with high confidence and strong credibility are then organized into a set.

2. The method of claim 1, wherein, The steps for obtaining model input data include: The system acquires vehicle characteristic parameters, driver control signals, road map information, a steady-state initial value transient correction model, a polynomial transient fuel consumption prediction model, and a target fuel consumption prediction model. The vehicle characteristic parameters include vehicle speed information, vehicle acceleration information, and vehicle mass information. The driver control signals include accelerator pedal opening information, brake pedal opening information, steering wheel angle information, steering wheel torque information, and vehicle gear information. The road map information includes road surface adhesion information, slope information, and speed limit information. The model input data is determined based on the vehicle characteristic parameters, the driver's control signals, and the road map information.

3. The method of claim 1, wherein, The step of constructing an empirical distribution based on the model input data and the transient fuel consumption model set, and determining the model empirical distribution set, includes: The model input data is input into the transient fuel consumption model set for training to determine the predicted transient fuel consumption set; Based on the model input data, filter fuel consumption data and construct the model prior distribution set; The model posterior distribution set is calculated based on the predicted transient fuel consumption set and the model prior distribution set. The model empirical distribution set is obtained based on the model prior distribution set and the model posterior distribution set.

4. The method of claim 3, wherein, The step of filtering fuel consumption data based on the model input data and constructing the model prior distribution set includes: Based on the input data of the model, filter fuel consumption data and determine historical fuel consumption data and operating condition similarity values; A prior distribution set for the model is constructed based on the historical fuel consumption data and the operating condition similarity values.

5. The method of claim 3, wherein, The step of calculating the model posterior distribution set based on the predicted transient fuel consumption set and the model prior distribution set includes: Methods for obtaining posterior distribution calculations; The model posterior distribution set is calculated based on the posterior distribution calculation method, the predicted transient fuel consumption set, and the model prior distribution set.

6. The method of claim 1, wherein, The steps for accurately predicting transient fuel consumption based on the target predicted transient fuel consumption set include: Integrating the target predicted transient fuel consumption set yields the target accurate transient fuel consumption prediction value; Accurate prediction of transient fuel consumption is achieved based on the target accuracy transient fuel consumption prediction value.

7. A device for accurately predicting transient fuel consumption of commercial vehicles based on a stochastic mixture model, characterized in that, The device includes: The acquisition module is used to acquire model input data and transient fuel consumption model set, and to preprocess the model input data to obtain preprocessed model input data. The processing module is used to construct an empirical distribution based on the model input data and the transient fuel consumption model set, and to determine the model empirical distribution set, which includes the model prior distribution set and the model posterior distribution set. The execution module is used to select a reliable model to predict fuel consumption and update the prior distribution based on the model input data and the model experience distribution set, determine the target predicted transient fuel consumption set, and complete the accurate prediction of transient fuel consumption based on the target predicted transient fuel consumption set; The acquisition module is also used to acquire the steady-state initial value transient correction model, the polynomial transient fuel consumption prediction model, and the target fuel consumption prediction model; The transient fuel consumption model set is determined based on the steady-state initial value transient correction model, the polynomial transient fuel consumption prediction model, and the target fuel consumption prediction model. The execution module is also used to obtain the position of the posterior distribution information interval; The confidence level is calculated based on the model's posterior distribution set in the model's empirical distribution set and the confidence interval position of the posterior distribution set. The confidence level is used to determine the model's credibility, and the fuel consumption confidence model is determined. The transient fuel consumption prediction value is then predicted based on the fuel consumption confidence model. The fuel consumption confidence model is obtained by retraining the model in the model library using all historical fuel consumption data when the model's credibility is lower than the set threshold, or by retraining the model in the model library after adjusting the historical fuel consumption data according to the model input data and the transient fuel consumption prediction value when the model's credibility is not lower than the set threshold. Based on the model input data and the transient fuel consumption prediction value, adjust the historical fuel consumption data, reconstruct the model prior distribution set, and determine the updated model prior distribution set. The fuel consumption model is trained based on the prior distribution set of the updated model, and the fuel consumption prediction optimization model set is determined. Based on the fuel consumption prediction optimization model set, the target predicted transient fuel consumption set is output. The target predicted transient fuel consumption set is obtained by filtering the model posterior distribution set of each model from multiple model prediction results using the posterior distribution confidence interval position, and the model prediction values ​​with high confidence and strong credibility are then organized into a set.

8. A commercial vehicle transient fuel consumption accurate prediction device based on a stochastic mixing model, characterized by, 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 method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic hybrid model as described in any one of claims 1 to 6.

9. A storage medium, characterized by 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 steps of the method for accurate prediction of transient fuel consumption of commercial vehicles based on a stochastic hybrid model as described in any one of claims 1 to 6.

Images