Vehicle fuel consumption prediction method based on ensemble learning

Through integrated learning methods and improved Pelican optimization algorithm, combined with multiple models to predict vehicle fuel consumption, the problems of high data accuracy and computing resource requirements in the prior art are solved, and high-precision and real-time fuel consumption prediction are achieved.

CN118928414AActive Publication Date: 2024-11-12TONGJI UNIV
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202410993801.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-12
Estimated Expiration
2044-07-23

AI Technical Summary

Technical Problem

The existing fuel consumption prediction methods have problems such as high data accuracy and high computing resource requirements, local characteristics problems, and insufficient consideration of external environmental factors, resulting in extended prediction errors and calculation time.

Method used

Using the vehicle fuel consumption prediction method based on integrated learning, the vehicle CAN data is obtained, and the key features are screened using the XGBoost method, and the improved Pelican optimization algorithm is introduced to optimize the deep echo state network, combining multiple models for prediction, reducing the deviation of a single model and Computing resource requirements.

Benefits of technology

It realizes high-precision and real-time fuel consumption prediction, reduces hardware dependence and computing resource requirements, and significantly improves the accuracy and practicality of prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118928414A_ABST
    Figure CN118928414A_ABST
Patent Text Reader

Abstract

The invention discloses a vehicle fuel consumption prediction method based on integrated learning, and the method comprises the steps: obtaining vehicle-mounted CAN data, selecting key features through employing an XGBoost method, introducing an improved pelican optimization algorithm to optimize the hyper-parameters of a deep echo state network, constructing a diesel truck fuel consumption prediction model, and obtaining a fuel consumption prediction result. High-precision prediction of the fuel consumption of the vehicle is realized, and the practicability and the economical efficiency of the fuel consumption prediction method are further improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to a fuel consumption prediction method, and in particular to a vehicle fuel consumption prediction method based on ensemble learning. Background Art

[0002] With the rapid development of society and the continuous growth of transportation demand, China's road freight transportation volume has increased year by year. This makes it particularly important to accurately predict vehicle fuel consumption. The fuel consumption of road freight trucks depends not only on factors such as the vehicle's own characteristics, driving conditions, cargo type and load, but also on the actual driving environment and external conditions. Especially in traffic congestion, frequent acceleration and deceleration and low average speed will significantly increase fuel consumption and emissions. Although existing technologies have attempted to use various sensors and professional equipment for direct measurement and prediction, these methods are often limited by high costs, implementation complexity and real-time issues. In addition, methods that rely solely on vehicle dynamics models and neural networks for fuel consumption estimation are difficult to avoid errors due to data noise, nonlinear system characteristics and the need for a large amount of computing resources. In complex driving environments and road conditions, the prediction deviation of traditional methods is also more obvious.

[0003] The Chinese patent application "A method and device for evaluating the energy consumption of heavy-duty diesel vehicles" with application number 202010918106.5 uses the vehicle's ignition switch signal and engine status signal to determine the mileage, and collects driving data based on the CAN bus. By refining and extracting key features, and using the Pearson correlation coefficient to screen out features that are highly correlated with energy consumption. Subsequently, a pre-trained neural network-based model is used to combine these features for energy consumption evaluation. Disadvantages: The Pearson correlation coefficient has limitations and may ignore certain nonlinear or more complex feature relationships. A large amount of data is required to train the neural network, and there may be evaluation biases for certain specific driving scenarios or models not involved.

[0004] The Chinese patent application "Transient Automobile Fuel Consumption Estimation Method and System Based on Correction of Strongly Correlated Parameters of Fuel Consumption" with application number 202210310009.7 proposes a method for estimating fuel consumption based on steady-state and non-steady-state driving data of the vehicle. This method combines a variety of data analysis techniques, such as principal component analysis, cluster analysis, and polynomial fitting, to establish a vehicle fuel consumption model. Disadvantages: The impact of traffic flow conditions is not taken into account. For example, frequent starting and stopping of vehicles on busy urban roads or in traffic jams may cause increased fuel consumption. These unconsidered actual driving scenario factors may cause fuel consumption estimates to deviate in some cases.

[0005] The Chinese patent application "Engine Dynamic Fuel Consumption Prediction Method and System Based on BP Neural Network" with application number 202111517192.X adopts the mean value filtering method and VSP-3σ method to pre-process the fuel consumption data and eliminate outliers. The method is divided into a steady-state module and a transient correction module. The steady-state module uses a polynomial structure to fit and output the steady-state fuel consumption rate based on the engine torque and speed. The transient correction module considers the speed, acceleration and engine speed, fits through the BP neural network, and outputs the difference between the actual and steady-state fuel consumption rates for correcting the prediction. To improve the accuracy, the method considers the vehicle's specific power VSP and uses two BP networks to fit data in different VSP intervals. Verification shows that the prediction method has high accuracy. Disadvantages: The BP neural network may fall into a local minimum; new fuel consumption data in actual driving may affect the prediction; two BP neural networks with the same structure are used for fitting, which means that double the training time and computing resources are required.

[0006] The patent application number CN 111460381B, "Multi-operating condition fuel vehicle fuel consumption prediction method and system based on Gaussian process regression", provides a fuel vehicle fuel consumption prediction solution, which uses the Gaussian process regression model for training, optimizes the data set through the sequential sampling algorithm, and repeatedly executes until the predetermined stop condition is reached to output the prediction result. Disadvantages: Repeated sequential sampling may prolong the calculation time, and the Gaussian process-based model may require greater computing resources.

[0007] Patent application number 202210511971.7, "Method and device for predicting vehicle fuel consumption based on machine learning and GPS positioning", proposes a fuel consumption prediction method that combines GPS and XGBoost machine learning algorithms. This method first collects a training data set through the GPS vehicle management system and extracts the required algorithm data set from it. After model training with the XGBoost algorithm, this method can obtain and predict the actual fuel consumption of the vehicle in real time. Disadvantages: Depends on the accuracy of GPS data, data deviation may lead to prediction errors; predictions based on historical data may be inaccurate when facing new road conditions.

[0008] The prior art has the following deficiencies:

[0009] 1. Data accuracy and training requirements: Most methods are highly dependent on data accuracy. For example, in the GPS-based fuel consumption prediction method, data bias may lead to prediction errors. At the same time, some methods, such as neural network-based models, require a large amount of data for training, and there may be evaluation biases for certain specific driving scenarios or uninvolved models.

[0010] 2. Computational resources and time constraints: Many methods, such as Gaussian process-based models and BP neural networks, require large amounts of computing resources, which may result in extended computing time and make it difficult to meet real-time application requirements. For example, using two BP neural networks with the same structure for fitting means double the training time and computing resources.

[0011] 3. Local feature problem: Some methods use technical means with limitations, which may ignore some nonlinear or more complex feature relationships. For example, the Pearson correlation coefficient may ignore some nonlinear or complex feature relationships, and the BP neural network may fall into a local minimum.

[0012] 4. External environmental factors are not considered: Some methods do not fully consider the possible variability in the actual driving environment, such as traffic flow status, emergency situations, etc. For example, the transient automobile fuel consumption estimation method based on the correction of fuel consumption-related parameters does not consider the influence of the vehicle's nonlinear system characteristics, which may lead to prediction deviations in specific actual driving scenarios.

[0013] Therefore, developing a fuel consumption prediction method that can combine multiple data, reduce hardware dependence, and ensure high real-time and high accuracy has become a research and application need. Summary of the invention

[0014] Purpose of the invention: The purpose of the present invention is to provide a fuel consumption prediction method that can combine multiple data, reduce hardware dependence, and ensure high real-time performance and high accuracy.

[0015] Technical solution: A vehicle fuel consumption prediction method based on ensemble learning, characterized in that it includes the following steps:

[0016] Step 1: Obtain basic parameters of vehicles with CAN function;

[0017] Step 2: Collect vehicle CAN data in real time;

[0018] Step 3: Preprocess the acquired vehicle CAN data according to the time window;

[0019] Step 4: Filter key features that are highly correlated with fuel consumption from the preprocessed vehicle CAN data as prediction input features;

[0020] Step 5: Divide the preprocessed CAN data into training set and test set in a ratio of 7:3;

[0021] Step 6: Build an improved Pelican optimization algorithm that introduces Tent chaos mapping, nonlinear weight factors, Cauchy mutation strategy, and sparrow alert mechanism;

[0022] Step 7: Use the output of step 6 as the optimal hyperparameter to construct a deep echo state network;

[0023] Step 8: Based on the training set in step 5, the network constructed in step 7 is trained so that its accuracy in the test set reaches a threshold of 90%, an integrated learning model for predicting the fuel consumption of diesel trucks is obtained, and the prediction results are output;

[0024] Step 9: Construct an echo state network, a support vector machine, and a random forest, compare the prediction results, and select the best result for output.

[0025] Furthermore, the preprocessing in step 3 includes checking time jumps, filling in missing data, and adjusting or eliminating abnormal or illogical data.

[0026] Furthermore, in step 4, the XGBoost method is used to select 10 key features that are highly correlated with fuel consumption from the preprocessed vehicle CAN data as prediction input features.

[0027] Furthermore, j )·z i (α), i=1, 2,..., N, j=1, 2,..., m

[0028]

[0029] In the formula, x i,j is the value of the jth dimension of the i-th pelican, l j and u j are the lower and upper limits of the dimension boundaries, respectively, z i (α) is a chaotic sequence, α is a constant. N is the population size; m is the dimension;

[0030] 6.3 Calculate the fitness value of each pelican individual as follows:

[0031]

[0032] Where X is the entire pelican population, and each X i Each is a candidate solution, F is the fitness function value, N is the population size, and m is the dimension;

[0033] 6.4 Determine whether the number of iterations has reached the maximum value T. If not, proceed to step 6.5. If so, proceed to step 6.14.

[0034] 6.5 Randomly select prey individuals and record their fitness values;

[0035] 6.6 In the phase of moving towards prey (exploration phase), a nonlinear weight factor ω is introduced to adjust the correlation between the pelican position update and the current position information, as follows:

[0036]

[0037] In the formula, is the updated value of the i-th candidate solution in the j-th dimension, p j is the position of the prey in the ,th dimension, I is a random number, F p and F i are the objective function values ​​of the prey and candidate solution, respectively; rand is a random number between [0, 1]; ω is small in the early stage of algorithm iteration, which is conducive to global search; it becomes larger as the number of iterations increases, improving local search capabilities;

[0038] 6.7 Compare the individual fitness value with the prey fitness value and calculate the new individual position;

[0039] 6.8 Determine whether the pelican is skimming the water surface. If so, proceed to step 6.9. If so, proceed to step 6.10.

[0040] 6.9 In the water skimming stage (development stage), the Cauchy mutation strategy is introduced to increase diversity, as follows:

[0041]

[0042] In the formula, is the update value of the ith candidate solution in the th dimension, Cauchy(σ) is the Cauchy distribution, σ is the mutation intensity, and t is the iteration counter. Then execute step 6.11;

[0043] 6.10 During the water skimming phase (development phase), the original update method is adopted, as follows:

[0044]

[0045] In the formula, R is a constant and the coefficient Represents the neighborhood radius of the population member, which decreases as the number of iterations increases, and then executes step 6.11

[0046] 6.11 adds a sparrow alert mechanism to make pelicans aware of danger move quickly to a safe area. Pelicans in the middle of the population move randomly to speed up convergence and improve global search capabilities. The details are as follows:

[0047] 1) For the pelican in danger (marginal individual), the update formula is as follows:

[0048] x i,j =x i,j +rand·(x best,j -x i,j )

[0049] In the formula, x best,j is the current optimal solution position of the population.

[0050] 2) For the pelican in a safe state (intermediate individual), the update formula is as follows:

[0051]

[0052] In the formula, randn is a standard normal distribution random number, is the average position of the population.

[0053] 6.12 Calculate the fitness value of the new individual and update the individual position as follows:

[0054]

[0055] In the formula, and are the new positions after the exploration phase and the development phase, respectively. and are their objective function values ​​respectively;

[0056] 6.13 The number of algorithm iterations t increases by 1 and step 6.4 is executed;

[0057] 6.14 Output the optimal pelican individual x best And the optimal fitness value F best .

[0058] Furthermore, the method of step 7 is as follows:

[0059] 7.1 At each time step, for the first layer, the state equation of DeepESN is updated as follows:

[0060]

[0061] Where x is the internal state of the network at a given time point, u is the external input signal received by the network, a is the leakage rate, and W (1) is the input weight matrix, W (i) is the inter-layer connection weight matrix, is the recursive weight matrix, a (i) is the leakage rate, f is the activation function,

[0062] 7.2 The states of all layers at each time step are used as the input of the output layer to calculate the output, as follows:

[0063] y(t)=W out x(t)

[0064] Where W out is the output layer weight matrix.

[0065] Furthermore, in step 9, the comparison indicators are mean absolute error (MAE), mean absolute percentage error (MAPE) and goodness of fit R2, as follows:

[0066]

[0067] Where yi is the true value of the i-th real fuel consumption, is the predicted value of fuel consumption for the ith time, is the average value of the true fuel consumption, and n is the number of test set samples.

[0068] The present invention obtains vehicle-mounted CAN data, uses the XGBoost method to select key features, introduces the improved Pelican optimization algorithm to optimize the hyperparameters of the deep echo state network, and constructs a diesel truck fuel consumption prediction model to obtain fuel consumption prediction results, thereby achieving high-precision prediction of vehicle fuel consumption.

[0069] Compared with the prior art, the present invention has the following beneficial effects:

[0070] 1. Comprehensive data utilization and real-time performance: The integrated learning method adopted by the present invention is different from the traditional method that highly relies on data volume and features. It can automatically update the vehicle CAN data and read it in real time. Through comprehensive analysis of massive data, the real-time and accuracy of fuel consumption prediction is ensured.

[0071] 2. Efficient feature screening: The present invention adopts the XGBoost method to screen key vehicle condition features that are highly correlated with fuel consumption, which significantly reduces feature redundancy and avoids the problem of local feature limitations.

[0072] 3. Combining the advantages of multiple models: The present invention can effectively reduce the deviation of a single model by combining multiple models for prediction. This method combines the advantages of each model, each model provides favorable data support for other models, and the final prediction result is more reliable and accurate.

[0073] 4. Simplicity and low cost: Compared with other methods, the present invention only needs to obtain the CAN data of the vehicle, without the need for additional sensors or professional monitoring equipment, thus reducing the implementation cost. At the same time, since ensemble learning can significantly speed up model training and prediction through parallel computing, it reduces the dependence on a large amount of computing resources, further improving the practicality and economy of the method. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 is a flow chart of the method of the present invention;

[0075] Figure 2This is a flow chart of step 6 of the present invention. DETAILED DESCRIPTION

[0076] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be further described below.

[0077] Figure 1 The specific process of the vehicle fuel consumption prediction method based on ensemble learning of the present invention is shown below. Figure 1 Describe the steps in detail:

[0078] Step 1. Obtain the basic parameters of a vehicle with CAN function.

[0079] Step 2. Collect vehicle CAN data in real time.

[0080] Step 3. Preprocess the acquired vehicle CAN data according to the time window, including but not limited to: checking time jumps, filling in missing data, and adjusting or eliminating abnormal or illogical data.

[0081] Step 4. Use the XGBoost method to select 10 key features that are highly correlated with fuel consumption from the preprocessed vehicle CAN data as prediction input features.

[0082] Step 5. Divide the preprocessed CAN data into training set and test set in a ratio of 7:3.

[0083] Step 6. Build the Improved Pelican Optimization Algorithm (IPOA) optimization algorithm that introduces Tent chaos mapping, nonlinear weight factors, Cauchy mutation strategy and sparrow alert mechanism. The process is as follows: Figure 2 As shown, the details are as follows:

[0084] 6.1 Set the maximum number of algorithm iterations T.

[0085] 6.2 Use Tent chaos mapping to initialize the pelican population within the specified range, as follows:

[0086] x i,j = l j +(u j -l j )·z i (α),i=1,2,…,N,j=1,2,…,m

[0087]

[0088] In the formula, x i,j is the value of the jth dimension of the i-th pelican, lj and u j are the lower and upper limits of the dimension boundaries, respectively, z i (α) is a chaotic sequence, α is a constant. N is the population size; m is the dimension;

[0089] 6.3 Calculate the fitness value of each pelican individual as follows:

[0090]

[0091] Where X is the entire pelican population, and each X i are all candidate solutions, F is the fitness function value, N is the population size, and m is the dimension.

[0092] 6.4 Determine whether the number of iterations has reached the maximum value T. If not, proceed to step 6.5. If so, proceed to step 6.14.

[0093] 6.5 Randomly select prey individuals and record their fitness values.

[0094] 6.6 In the phase of moving towards prey (exploration phase), a nonlinear weight factor ω is introduced to adjust the correlation between the pelican position update and the current position information, as follows:

[0095]

[0096] In the formula, is the updated value of the i-th candidate solution in the j-th dimension, p j is the position of the prey in the ,th dimension, I is a random number, F p and F i are the objective function values ​​of the prey and the candidate solution respectively, rand is a random number between [0, 1], ω is small in the early stage of the algorithm iteration, which is conducive to global search, and becomes larger as the number of iterations increases, improving the local search ability.

[0097] 6.7 Compare the individual fitness value with the prey fitness value and calculate the new individual position.

[0098] 6.8 Determine whether the pelican is skimming the water surface. If so, proceed to step 6.9. If so, proceed to step 6.10.

[0099] 6.9 In the water skimming stage (development stage), the Cauchy mutation strategy is introduced to increase diversity, as follows:

[0100]

[0101] In the formula, is the updated value of the i-th candidate solution in the j-th dimension, Cauchy(σ) is the Cauchy distribution, σ is the mutation intensity, and t is the iteration counter. Then execute step 6.11.

[0102] 6.10 During the water skimming phase (development phase), the original update method is adopted, as follows:

[0103]

[0104] In the formula, R is a constant and the coefficient Represents the neighborhood radius of the population member, which decreases as the number of iterations increases. Then execute step 6.11

[0105] 6.11 adds a sparrow alert mechanism to make pelicans aware of danger move quickly to a safe area. Pelicans in the middle of the population move randomly to speed up convergence and improve global search capabilities. The details are as follows:

[0106] 1) For the pelican in danger (marginal individual), the update formula is as follows:

[0107] x i,j =x i,j +rand·(x best,j -x i,j )

[0108] In the formula, x best,j is the current optimal solution position of the population.

[0109] 2) For the pelican in a safe state (intermediate individual), the update formula is as follows:

[0110]

[0111] In the formula, randn is a standard normal distribution random number, is the average position of the population.

[0112] 6.12 Calculate the fitness value of the new individual and update the individual position as follows:

[0113]

[0114] In the formula, and are the new positions after the exploration phase and the development phase, respectively. and are their objective function values ​​respectively.

[0115] 6.13 The number of algorithm iterations t increases by 1 and step 6.4 is executed.

[0116] 6.14 Output the optimal pelican individual x best And the optimal fitness value F best .

[0117] Step 7. Use the output of step 6.14 as the optimal hyperparameters to construct a Deep Echo State Network (DeepESN), as follows:

[0118] 7.1 At each time step, for the first layer, the state equation of DeepESN is updated as follows:

[0119]

[0120] Where x is the internal state of the network at a given time point, u is the external input signal received by the network, a is the leakage rate, and W (1) is the input weight matrix, W (i) is the inter-layer connection weight matrix, is the recursive weight matrix, a (i) is the leakage rate, and f is the activation function.

[0121] 7.2 The states of all layers at each time step are used as the input of the output layer to calculate the output, as follows:

[0122] y(t)=W out x(t)

[0123] Where W out is the output layer weight matrix.

[0124] Step 8. Based on the training set in step 5, train the DeepESN network constructed in step 7 so that its accuracy in the test set reaches the 90% threshold, obtain an integrated learning model for predicting diesel truck fuel consumption, and output the prediction results.

[0125] Step 9. Construct an echo state network (ESN), support vector machine (SVM) and random forest (RF), compare the prediction results respectively, select the best result for output, and use the mean absolute error (MAE), mean absolute percentage error (MAPE) and goodness of fit R2 as follows:

[0126]

[0127] Where yi is the true value of the i-th real fuel consumption, is the predicted value of fuel consumption for the ith time, is the average value of the true fuel consumption, and n is the number of test set samples.

[0128] The above is only a preferred embodiment of the present invention and does not limit the present invention in any way. Any technician in the relevant technical field, without departing from the scope of the technical solution of the present invention, makes any form of equivalent replacement or modification to the technical solution and technical content disclosed in the present invention, which does not depart from the content of the technical solution of the present invention and still falls within the protection scope of the present invention.

Claims

1. A vehicle fuel consumption prediction method based on ensemble learning, characterized in that: The steps include: Step 1: Obtain basic parameters of vehicles with CAN function; Step 2: Collect vehicle CAN data in real time; Step 3: Preprocess the acquired vehicle CAN data according to the time window; Step 4: Filter key features that are highly correlated with fuel consumption from the preprocessed vehicle CAN data as prediction input features; Step 5: Divide the preprocessed CAN data into training set and test set in a ratio of 7:3; Step 6: Build an improved Pelican optimization algorithm that introduces Tent chaos mapping, nonlinear weight factors, Cauchy mutation strategy, and sparrow alert mechanism; Step 7: Use the output of step 6 as the optimal hyperparameter to construct a deep echo state network; Step 8: Based on the training set in step 5, the network constructed in step 7 is trained so that its accuracy in the test set reaches a threshold of 90%, an integrated learning model for predicting the fuel consumption of diesel trucks is obtained, and the prediction results are output; Step 9: Construct an echo state network, a support vector machine, and a random forest, compare the prediction results, and select the best result for output.

2. The vehicle fuel consumption prediction method based on ensemble learning according to claim 1 is characterized in that: The preprocessing in step 3 includes checking time jumps, filling in missing data, and adjusting or eliminating abnormal or illogical data.

3. The vehicle fuel consumption prediction method based on ensemble learning according to claim 2 is characterized in that: In step 4, the XGBoost method is used to select 10 key features that are highly correlated with fuel consumption from the preprocessed vehicle CAN data as prediction input features.

4. The vehicle fuel consumption prediction method based on ensemble learning according to claim 3 is characterized in that: The optimization algorithm in step 6 is as follows: 6.1 Set the maximum number of algorithm iterations T; 6.2 Use Tent chaos mapping to initialize the pelican population within the specified range, as follows: x i,j =l j +(u j -l j )·z i (α),i=1,2,…,N,j=1,2,…,m In the formula, x i,j is the value of the jth dimension of the i-th pelican, l j and u j are the lower and upper limits of the dimension boundaries, respectively, z i (α) is a chaotic sequence, α is a constant. N is the population size; m is the dimension; 6.3 Calculate the fitness value of each pelican individual as follows: Where X is the entire pelican population, and each X i Each is a candidate solution, F is the fitness function value, N is the population size, and m is the dimension; 6.4 Determine whether the number of iterations has reached the maximum value r. If not, proceed to step 6.

5. If so, proceed to step 6.

14. 6.5 Randomly select prey individuals and record their fitness values; 6.6 In the phase of moving towards prey (exploration phase), a nonlinear weight factor ω is introduced to adjust the correlation between the pelican position update and the current position information, as follows: In the formula, is the updated value of the i-th candidate solution in the j-th dimension, p j is the position of the prey in the jth dimension, I is a random number, F p and F i are the objective function values ​​of the prey and candidate solution, respectively; rand is a random number between [0, 1]; ω is small in the early stage of algorithm iteration, which is conducive to global search; it becomes larger as the number of iterations increases, improving local search capabilities; 6.7 Compare the individual fitness value with the prey fitness value and calculate the new individual position; 6.8 Determine whether the pelican is skimming the water surface. If so, proceed to step 6.

9. If so, proceed to step 6.

10. 6.9 In the water skimming stage (development stage), the Cauchy mutation strategy is introduced to increase diversity, as follows: In the formula, is the update value of the ith candidate solution in the th dimension, Cauchy(σ) is the Cauchy distribution, σ is the mutation intensity, and t is the iteration counter. Then execute step 6.11; 6.10 During the water skimming phase (development phase), the original update method is adopted, as follows: In the formula, R is a constant and the coefficient Represents the neighborhood radius of the population member, which decreases as the number of iterations increases, and then executes step 6.11 6.11 adds a sparrow alert mechanism to make pelicans aware of danger move quickly to a safe area. Pelicans in the middle of the population move randomly to speed up convergence and improve global search capabilities. The details are as follows: 1) For the pelican in danger (marginal individual), the update formula is as follows: x i,j =x i,j +rand·(x best,j -x i,j ) In the formula, x best,j is the current optimal solution position of the population. 2) For the pelican in a safe state (intermediate individual), the update formula is as follows: In the formula, randn is a standard normal distribution random number, is the average position of the population. 6.12 Calculate the fitness value of the new individual and update the individual position as follows: In the formula, and are the new positions after the exploration phase and the development phase, respectively. and are their objective function values ​​respectively; 6.13 The number of algorithm iterations t increases by 1 and step 6.4 is executed; 6.14 Output the optimal pelican individual x best And the optimal fitness value F best .

5. The vehicle fuel consumption prediction method based on ensemble learning according to claim 4 is characterized in that: The method of step 7 is as follows: 7.1 At each time step, for the first layer, the state equation of DeepESN is updated as follows: Where x is the internal state of the network at a given time point, u is the external input signal received by the network, a is the leakage rate, and W (1) is the input weight matrix, W (i) is the inter-layer connection weight matrix, is the recursive weight matrix, a (i) is the leakage rate, f is the activation function, 7.2 The states of all layers at each time step are used as the input of the output layer to calculate the output, as follows: y(t)=W out x(t) Where W out is the output layer weight matrix.

6. The vehicle fuel consumption prediction method based on ensemble learning according to claim 5 is characterized in that: In step 9, the comparison indicators are mean absolute error (MAE), mean absolute percentage error (MAPE) and goodness of fit R2, as follows: Where yi is the true value of the i-th real fuel consumption, is the predicted value of fuel consumption for the ith time, is the average value of the true fuel consumption, and n is the number of test set samples.

7. The vehicle fuel consumption prediction method based on ensemble learning according to claim 1 is characterized in that: The vehicle is a diesel truck.

Citation Information

Patent Citations

  • Wireless sensor constraint optimization positioning method

    CN114900788A

  • INGO algorithm based on multi-strategy improvement

    CN118350403A

  • Carbon emission prediction method and system based on ISWO-LSTM model

    CN118350513A