A pure electric four-wheel drive cargo handling chassis system

Abstract

The present invention relates to a pure electric four-wheel drive cargo handling chassis system. By collecting handling data of pure electric four-wheel drive vehicles over a large historical period, the system analyzes the relationship between driving condition data and chassis status data, thereby resolving the problem that prior art pays less attention to the relationship between driving conditions and chassis status, making it difficult to adjust vehicle speed according to road conditions and load to keep the chassis in good condition. In the process, the system analyzes the correlation between the driving condition data and the chassis status data variables, establishes connections for the data variables with significant correlations, clarifies the driving condition variables that have an impact on each chassis status variable, and improves the accuracy of the correlation analysis. Furthermore, by analyzing and quantifying the response relationship between the driving condition data and chassis status data variables that have established a connection relationship, the system reflects the quantitative change relationship between the chassis status and driving conditions, providing a reference for controlling the driving conditions to achieve the optimal chassis state.

Description

Technical Field

[0001] The invention belongs to the technical field of chassis control and relates to a pure electric four-wheel drive cargo handling chassis system. Background Art

[0002] The all-electric four-wheel drive cargo handling chassis is a chassis system for cargo handling vehicles. It primarily consists of an electric drive system, energy management system, suspension system, and braking system, designed to provide an efficient, environmentally friendly, and reliable power source for cargo handling vehicles. By combining electric drive technology with four-wheel drive, the all-electric four-wheel drive cargo handling chassis achieves high-efficiency conversion and energy conservation and environmental protection for cargo handling vehicles. It boasts zero emissions, low noise, high energy efficiency, and intelligent management. It is suitable for various logistics, warehousing, and manufacturing scenarios, and is a key technology driving sustainable development in the cargo handling sector.

[0003] However, under different driving conditions (such as road conditions, load, vehicle speed, etc.), the chassis state (driving state, energy state, suspension state and braking state) of the four-wheel drive electric vehicle continues to change. Existing technologies pay less attention to the relationship between driving conditions and chassis state, which makes it difficult to adjust the vehicle speed according to road conditions and load to keep the chassis in good condition. Summary of the Invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides a pure electric four-wheel drive cargo handling chassis system.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The present application provides a pure electric four-wheel drive cargo handling chassis system, including a chassis analysis module, a real-time monitoring module, and a chassis control module, wherein the chassis analysis module, the real-time monitoring module, and the chassis control module are communicatively connected, wherein:

[0007] The chassis analysis module collects a large amount of historical handling data of pure electric four-wheel drive vehicles and analyzes the relationship between driving condition data and chassis status data; the handling data includes driving condition data and chassis status data; the driving condition data includes vehicle speed data, road condition data, and load data; the chassis status data includes driving status, energy status, suspension status, and braking status;

[0008] The analysis of the association between the driving condition data and the chassis status data specifically includes:

[0009] Analyze the correlation between driving condition data and chassis status data variables, and establish connection relationships for data variables with significant correlation;

[0010] Analyze and quantify the response relationship between driving condition data and chassis status data variables that have established a connection relationship;

[0011] The real-time monitoring module is used to monitor and collect the driving condition data and chassis status data of the pure electric four-wheel drive vehicle in real time;

[0012] The chassis control module uses the response relationship to control and adjust the vehicle speed based on the real-time monitoring result to maintain a preset optimal chassis state.

[0013] Furthermore, the vehicle speed data includes the speed and acceleration of the vehicle; and the road condition data includes the slope, ground friction and ground bumpiness.

[0014] Furthermore, the analysis of the correlation between the driving condition data and the chassis status data variables, and establishing connections for the data variables with significant correlation, specifically includes the following steps:

[0015] S1. Using driving condition data as explanatory variables and chassis status data as response variables, a redundancy analysis model is constructed.

[0016] S2. Use the Monte Carlo permutation test to check the significance of the full model and the first axis of the model. If the full model and the first axis of the model are significant, the model passes the test.

[0017] S3. Draw a ranking diagram based on the scores of each variable in the ranking axis, and determine the correlation between each variable in the driving condition data and the chassis status data based on the angle between the arrows in the diagram;

[0018] S4. When the angle between the variable arrows of the driving condition data and the chassis status data is less than a set angle threshold, a connection relationship between the two is established.

[0019] Furthermore, in step S3, the Pearson correlation coefficient of the scores of the driving condition data and the chassis status data in the sorting axis is calculated to assist in analyzing the correlation between the variables of the driving condition data and the chassis status data. When the Pearson correlation coefficient is greater than 0.7, a connection relationship between the two is established.

[0020] Furthermore, the Pearson correlation coefficient is calculated as follows:

[0021]

[0022] Where: r ij Represents the driving condition data variable x i and chassis status data variable x j Pearson correlation coefficient between ki Represents x iThe kth sample, x kj Represents x j The k-th sample of , k = 1, 2, ..., n, where n is the number of samples.

[0023] Furthermore, the response relationship between the driving condition data and the chassis status data variables that have established a connection relationship is analyzed and quantified. Specifically, a random forest model is used to quantify the response relationship between the two. The steps of constructing the random forest model are as follows:

[0024] T1. Data preparation: Prepare a data set containing explanatory variables and response variables. The explanatory variables are driving condition data, and the response variables are chassis status data variables that establish a connection relationship with the driving condition data.

[0025] T2. Dataset division: Divide the collected dataset into training set and test set, using 70% of the data samples in the dataset as the training set and 30% of the data samples as the test set;

[0026] T3, random sampling: randomly extract a certain number of explanatory variables and data samples from the training set, and construct multiple different training sets with replacement;

[0027] T4. Build a decision tree: For each randomly sampled training set, build a decision tree model;

[0028] Furthermore, in step T4, the decision tree model is configured as a CART model.

[0029] T5. Ensemble Decision Tree: Integrate multiple decision tree models into a random forest model and use a voting mechanism or average to make the final prediction.

[0030] T6. Model evaluation: Use evaluation metrics to evaluate the prediction performance of the random forest model on the test set and determine the final model with good prediction performance.

[0031] Furthermore, in step T6, the evaluation index adopts accuracy, precision, recall rate or F1 value.

[0032] Furthermore, in the chassis control module, the vehicle speed is controlled and adjusted, specifically using FOC technology to control the magnetic field and current of the drive motor to achieve precise control of the speed and torque.

[0033] Beneficial effects of the present invention:

[0034] 1) By utilizing large-scale historical data collected on the handling of pure electric four-wheel drive vehicles, the relationship between driving condition data and chassis status data is analyzed. This solves the problem that existing technologies pay little attention to the relationship between driving conditions and chassis status, making it difficult to adjust the vehicle speed according to road conditions and load to keep the chassis in good condition.

[0035] 2) In analyzing the association between driving condition data and chassis status data, by analyzing the correlation between the driving condition data and the chassis status data variables, connections are established for data variables with significant correlations, and the driving condition variables that have an impact on each chassis status variable are clarified, thereby improving the accuracy of the association analysis.

[0036] 3) In analyzing the association between driving condition data and chassis status data, by analyzing and quantifying the response relationship between the driving condition data and chassis status data variables that have established a connection relationship, the quantitative change relationship between the chassis status and driving conditions is reflected, providing a reference for controlling driving conditions to achieve the optimal chassis state. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0038] Figure 1 This is a structural diagram of a pure electric four-wheel drive cargo handling chassis system in the present invention. DETAILED DESCRIPTION

[0039] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0040] See also Figure 1 The present application provides a pure electric four-wheel drive cargo handling chassis system, including a chassis analysis module, a real-time monitoring module and a chassis control module, wherein the chassis analysis module, the real-time monitoring module and the chassis control module are communicatively connected, wherein:

[0041] The chassis analysis module collects a large amount of historical handling data of pure electric four-wheel drive vehicles and analyzes the relationship between driving condition data and chassis status data; the handling data includes driving condition data and chassis status data; the driving condition data includes vehicle speed data, road condition data, and load data; the chassis status data includes driving status, energy status, suspension status, and braking status;

[0042] Furthermore, the vehicle speed data includes the speed and acceleration of the vehicle; and the road condition data includes the slope, ground friction and ground bumpiness.

[0043] In this embodiment, the relationship between driving conditions and chassis status is analyzed using historical handling data of pure electric four-wheel drive vehicles. The handling data includes driving condition data and chassis status data; the driving condition data includes vehicle speed data, road condition data, and load data; and the chassis status data includes driving status, energy status, suspension status, and braking status. The following are the explanations of these data variables:

[0044] 1) Vehicle speed data: This refers to the vehicle's current speed. Speed ​​is an important indicator for assessing driving safety and vehicle performance, and is the basis for many driving decisions. By controlling speed, the chassis can maintain optimal condition under varying road conditions and loads.

[0045] 2) Road condition data: This includes information such as slope, ground friction, and road roughness. Slope refers to the inclination of the road and affects the vehicle's power performance and fuel consumption. Ground friction refers to the friction between the ground and the vehicle, affecting the vehicle's braking and handling performance. Road roughness refers to the unevenness of the road surface and affects the vehicle's suspension system and driving comfort.

[0046] 3) Load Data: This refers to the weight of the cargo or passengers currently on board the vehicle. Load data affects the vehicle's suspension, braking system, and fuel consumption. Overloading increases vehicle safety risks, reduces suspension and braking performance, and increases fuel consumption.

[0047] 4) Driving status: The driving status can be judged by evaluating the vehicle's power performance and handling performance, such as acceleration speed and steering response sensitivity.

[0048] 5) Energy Status: The energy status can be judged by evaluating energy consumption efficiency and range, such as fuel consumption or electricity consumption per unit distance. In this embodiment, electricity consumption is used.

[0049] 6) Suspension Condition: The quality of a vehicle's suspension can be determined by evaluating its performance under different road conditions. For example, this can be assessed by the vehicle's ride comfort on bumpy roads or its ability to control the vehicle's posture.

[0050] 7) Braking Status: The braking status of a vehicle can be judged by evaluating the response time, braking force, and brake shoe wear of the vehicle's braking system. For example, the braking distance and braking effect can be used to evaluate the good operation of the braking system.

[0051] The analysis of the correlation between the driving condition data and the chassis status data specifically includes:

[0052] Analyze the correlation between driving condition data and chassis status data variables, and establish connection relationships for data variables with significant correlation;

[0053] Analyze and quantify the response relationship between driving condition data and chassis status data variables that have established a connection relationship;

[0054] In this embodiment, different driving condition variables (the driving condition data include vehicle speed data, road condition data and load data) have different degrees of influence on different chassis state variables (the chassis state data include drive state, energy state, suspension state and braking state). When establishing an association between the driving condition data and the chassis state data, it is necessary to clarify the driving condition variables that have an impact on each chassis state variable in order to establish a control connection relationship between them.

[0055] Furthermore, the analysis of the correlation between the driving condition data and the chassis status data variables, and establishing connections for the data variables with significant correlation, specifically includes the following steps:

[0056] S1. Using driving condition data as explanatory variables and chassis status data as response variables, a redundancy analysis model is constructed.

[0057] In this embodiment, redundancy analysis (RDA) is a ranking method that combines regression analysis and principal component analysis (PCA) and is used to expand multiresponse regression analysis. RDA uses PCA analysis on the fitted value matrix of multiple linear regression between the response variable matrix and the explanatory variables to extract and summarize the variation in a set of response variables and explain these variations through a set of explanatory variables. This method allows multiple response variables to be regressed on multiple explanatory variables, and then the fitted value matrix generated by the multiple linear regression is processed by principal component analysis (PCA). RDA can be considered a constrained version of PCA, in which the canonical axes (constructed from linear combinations of the response variables) must also be linear combinations of the explanatory variables. Interpreting a redundancy analysis plot (RDA plot) involves understanding the ranking axes and linear combinations of the explanatory variables displayed in the plot. These plots are often used to show how explanatory variables affect the variation of the response variable. In an RDA plot, the ranking axes are actually linear combinations of the explanatory variables, which can be used to intuitively see which explanatory variables have the greatest impact on the response variable. In addition, RDA plots can be used to compare differences between different samples or treatment groups and identify patterns and trends. The difference between redundancy analysis and correlation analysis is that correlation analysis focuses on the strength of the direct relationship between variables, while redundancy analysis goes a step further and extracts and summarizes the changes in a set of response variables through a combination of regression analysis and principal component analysis, and explains these changes through a set of explanatory variables. The advantage of this method is that it can handle the relationship between multiple response variables and explanatory variables, not just the correlation between them. Compared with principal component analysis (PCA), redundancy analysis (RDA) is a constrained version of principal component analysis, in which the canonical axes (constructed by linear combinations of response variables) must also be linear combinations of explanatory variables. This means that in RDA, the extracted principal components take into account not only the direction of maximum variation in the data, but also the constraints introduced by the explanatory variables. Therefore, RDA provides a more direct way to understand how explanatory variables affect the changes in the response variable.

[0058] S2. Use the Monte Carlo permutation test to check the significance of the full model and the first axis of the model. If the full model and the first axis of the model are significant, the model passes the test.

[0059] S3. Draw a ranking diagram based on the scores of each variable in the ranking axis, and determine the correlation between each variable in the driving condition data and the chassis status data based on the angle between the arrows in the diagram;

[0060] S4. When the angle between the variable arrows of the driving condition data and the chassis status data is less than a set angle threshold, a connection relationship between the two is established.

[0061] Furthermore, in step S3, the Pearson correlation coefficient of the scores of the driving condition data and the chassis status data in the sorting axis is calculated to assist in analyzing the correlation between the variables of the driving condition data and the chassis status data. When the Pearson correlation coefficient is greater than 0.7, a connection relationship between the two is established.

[0062] Furthermore, the Pearson correlation coefficient is calculated as follows:

[0063]

[0064] Where: r ij Represents the driving condition data variable x i and chassis status data variable x j Pearson correlation coefficient between ki Represents x i The kth sample, x kj Represents x j The k-th sample of , k = 1, 2, ..., n, where n is the number of samples.

[0065] In this embodiment, after establishing a connection relationship between the chassis state variable and the driving condition variable with significant correlation, it is necessary to reflect the quantitative change relationship between the chassis state and the driving condition by analyzing the response relationship between the two, so as to provide a reference for controlling the driving conditions to achieve the optimal chassis state.

[0066] Furthermore, the analysis and quantification of the response relationship between the driving condition data and the chassis status data variables that have established a connection relationship specifically uses a random forest model to quantify the response relationship between the two. Random forest is a machine learning method based on ensemble learning, consisting of multiple decision trees. Each decision tree is constructed independently, and the diversity of the model is increased by random sampling and feature selection of the input data. The final prediction result is obtained by integrating the prediction results of all decision trees. Random forests are generally used to solve classification and regression problems, and have achieved important applications in data mining, financial risk assessment, medical diagnosis and other fields. The steps for constructing the random forest model in this embodiment are as follows:

[0067] T1. Data preparation: Prepare a data set containing explanatory variables and response variables. The explanatory variables are driving condition data, and the response variables are chassis status data variables that establish a connection relationship with the driving condition data.

[0068] T2. Dataset division: Divide the collected dataset into training set and test set, using 70% of the data samples in the dataset as the training set and 30% of the data samples as the test set;

[0069] T3, random sampling: randomly extract a certain number of explanatory variables and data samples from the training set, and construct multiple different training sets with replacement;

[0070] T4. Build a decision tree: For each randomly sampled training set, build a decision tree model;

[0071] Furthermore, in step T4, the decision tree model is configured as a CART model.

[0072] Classification and Regression Trees (CART) is a decision tree algorithm used for classification and regression analysis. CART recursively partitions a dataset into smaller subsets, selecting the optimal features and split points at each node to minimize the Gini impurity (for classification) or mean squared error (for regression), ultimately generating a single tree to make predictions. CART models are easy to understand and interpret, and can handle nonlinear relationships and high-dimensional data. By repeatedly partitioning the dataset, CART effectively captures complex patterns in the data and is robust to missing values ​​and outliers. In a random forest, each decision tree is constructed based on the Classification and Regression Trees (CART) algorithm. Specifically, each tree in a random forest is an independent CART decision tree that uses randomly selected features for modeling. Random forests integrate the predictions of multiple CART decision trees to make a final decision, thereby improving the accuracy and generalization of the overall model. Each tree is constructed for a different random subset of the training data, and only features from that random subset are considered when selecting the best feature at each node. This gives the random forest a certain degree of randomness and reduces the risk of overfitting. Therefore, the random forest leverages the advantages of the CART decision tree and combines the prediction results of multiple trees, improving the model's stability and predictive power, achieving widespread success in practical applications.

[0073] T5. Ensemble Decision Tree: Integrate multiple decision tree models into a random forest model and use a voting mechanism or average to make the final prediction.

[0074] It's important to note that in a random forest, each decision tree is constructed based on a different training dataset and feature subset, resulting in a certain degree of randomness. The final prediction can be determined through a voting mechanism or by taking an average. In classification problems, majority voting can be used to select the category with the most votes as the final prediction. In regression problems, the predictions of multiple trees can be averaged as the final output. By combining multiple decision trees into a random forest model, the risk of overfitting can be effectively reduced, improving the model's robustness and accuracy.

[0075] T6. Model evaluation: Use evaluation metrics to evaluate the prediction performance of the random forest model on the test set and determine the final model with good prediction performance.

[0076] Furthermore, in step T6, the evaluation index adopts accuracy, precision, recall rate or F1 value.

[0077] In this embodiment, accuracy is the ratio of the number of samples correctly predicted by the model to the total number of samples. It is one of the most commonly used evaluation indicators and is calculated as follows: Accuracy = (TP+TN) / (TP+TN+FP+FN), where TP represents true positive examples, TN represents true negative examples, FP represents false positive examples, and FN represents false negative examples.

[0078] Precision measures how many of the positive examples predicted by the model are actually positive examples. It is an important indicator for evaluating the accuracy of model predictions. The calculation formula is: Precision = TP / (TP+FP).

[0079] The recall rate measures the ratio of the number of positive examples that the model can correctly predict to the actual number of positive examples, also known as the recall rate. The calculation formula is: recall rate = TP / (TP+FN).

[0080] The F1 value is the harmonic mean of precision and recall, which comprehensively considers the accuracy and comprehensiveness of the model. The higher the F1 value, the better the balance between precision and recall. The calculation formula is: F1 = 2 × (precision × recall) / (precision + recall).

[0081] The real-time monitoring module is used to monitor and collect the driving condition data and chassis status data of the pure electric four-wheel drive vehicle in real time;

[0082] The chassis control module uses the response relationship to control and adjust the vehicle speed based on the real-time monitoring result to maintain a preset optimal chassis state.

[0083] In this embodiment, the real-time monitored driving condition data includes vehicle speed, road condition data, and load data. However, in real-world operations, road condition and load data are immutable during the transport process, leaving vehicle speed as the only controllable variable. Therefore, this embodiment leverages the quantified relationship between driving conditions and chassis status data to control and adjust vehicle speed under varying road conditions and loads, enabling the electric vehicle to maintain a preset optimal chassis state, which is individually determined.

[0084] Furthermore, in the chassis control module, the vehicle speed is controlled and adjusted, specifically using FOC technology to control the magnetic field and current of the drive motor to achieve precise control of the speed and torque.

[0085] In this embodiment, FOC technology (Field-Oriented Control) is a method for accurately controlling vehicle speed, rotational speed, and torque. It converts the input voltage into a control current signal using space vector modulation (SVM), and combines the principles of magnetic field orientation and current control to achieve precise control of the magnetic field and current of the drive motor. FOC technology can achieve the required speed and torque output by accurately measuring the motor rotor position and adjusting the current and magnetic field angle. This technology is widely used in electric vehicles and industrial applications, providing efficient energy utilization and good dynamic response capabilities for the motor system.

[0086] Beneficial effects of the present invention:

[0087] 1) By utilizing large-scale historical data collected on the handling of pure electric four-wheel drive vehicles, the relationship between driving condition data and chassis status data is analyzed. This solves the problem that existing technologies pay little attention to the relationship between driving conditions and chassis status, making it difficult to adjust the vehicle speed according to road conditions and load to keep the chassis in good condition.

[0088] 2) In analyzing the association between driving condition data and chassis status data, by analyzing the correlation between the driving condition data and the chassis status data variables, connections are established for data variables with significant correlations, and the driving condition variables that have an impact on each chassis status variable are clarified, thereby improving the accuracy of the association analysis.

[0089] 3) In analyzing the association between driving condition data and chassis status data, by analyzing and quantifying the response relationship between the driving condition data and chassis status data variables that have established a connection relationship, the quantitative change relationship between the chassis status and driving conditions is reflected, providing a reference for controlling driving conditions to achieve the optimal chassis state.

[0090] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A pure electric four-wheel drive cargo handling chassis system, characterized by: It includes a chassis analysis module, a real-time monitoring module and a chassis control module, which are communicatively connected to each other, wherein: The chassis analysis module collects a large amount of historical handling data of pure electric four-wheel drive vehicles and analyzes the relationship between driving condition data and chassis status data; the handling data includes driving condition data and chassis status data; the driving condition data includes vehicle speed data, road condition data, and load data; the chassis status data includes driving status, energy status, suspension status, and braking status; The analysis of the association between the driving condition data and the chassis status data specifically includes: Analyze the correlation between driving condition data and chassis status data variables, and establish connection relationships for data variables with significant correlation; Analyze and quantify the response relationship between driving condition data and chassis status data variables that have established a connection relationship; The real-time monitoring module is used to monitor and collect the driving condition data and chassis status data of the pure electric four-wheel drive vehicle in real time; The chassis control module uses the response relationship to control and adjust the vehicle speed based on the real-time monitoring result to maintain a preset optimal chassis state.

2. The pure electric four-wheel drive cargo handling chassis system according to claim 1, characterized in that: The vehicle speed data includes the speed and acceleration of the vehicle; the road condition data includes the slope, ground friction and ground bumpiness.

3. The pure electric four-wheel drive cargo handling chassis system according to claim 1, characterized in that: The analysis of the correlation between the driving condition data and the chassis status data variables, and establishing connections for the data variables with significant correlation, specifically includes the following steps: S1. Using driving condition data as explanatory variables and chassis status data as response variables, a redundancy analysis model is constructed. S2. Use the Monte Carlo permutation test to check the significance of the full model and the first axis of the model. If the full model and the first axis of the model are significant, the model passes the test. S3. Draw a ranking diagram based on the scores of each variable in the ranking axis, and determine the correlation between each variable in the driving condition data and the chassis status data based on the angle between the arrows in the diagram; S4. When the angle between the variable arrows of the driving condition data and the chassis status data is less than a set angle threshold, a connection relationship between the two is established.

4. The pure electric four-wheel drive cargo handling chassis system according to claim 3, characterized in that: In step S3, the Pearson correlation coefficient of the driving condition data and chassis status data scores in the sorting axis is calculated to assist in analyzing the correlation between the driving condition data and the chassis status data variables. When the Pearson correlation coefficient is greater than 0.7, a connection relationship between the two is established.

5. The pure electric four-wheel drive cargo handling chassis system according to claim 4, characterized in that: The Pearson correlation coefficient is calculated as follows: ， Where: r ij Represents driving condition data variables x i Chassis status data variables x j Pearson correlation coefficient between ; x ki express x i No. k samples, x kj express x j No. k samples, k =1, 2, ..., n ,in n is the number of samples.

6. The pure electric four-wheel drive cargo handling chassis system according to claim 1, characterized in that: The response relationship between the driving condition data and the chassis status data variables that have established a connection relationship is analyzed and quantified. Specifically, a random forest model is used to quantify the response relationship between the two. The steps of constructing the random forest model are as follows: T1. Data preparation: Prepare a data set containing explanatory variables and response variables. The explanatory variables are driving condition data, and the response variables are chassis status data variables that establish a connection relationship with the driving condition data. T2. Dataset division: Divide the collected dataset into training set and test set, using 70% of the data samples in the dataset as the training set and 30% of the data samples as the test set; T3, random sampling: randomly extract a certain number of explanatory variables and data samples from the training set, and construct multiple different training sets with replacement; T4. Build a decision tree: For each randomly sampled training set, build a decision tree model; T5. Ensemble Decision Tree: Integrate multiple decision tree models into a random forest model and use a voting mechanism or average to make the final prediction. T6. Model evaluation: Use evaluation metrics to evaluate the prediction performance of the random forest model on the test set and determine the final model with good prediction performance.

7. The pure electric four-wheel drive cargo handling chassis system according to claim 6, characterized in that: In step T4, the decision tree model is configured as a CART model.

8. The pure electric four-wheel drive cargo handling chassis system according to claim 6, characterized in that: In step T6, the evaluation index adopts accuracy, precision, recall or F1 value, where F1 value is the harmonic mean of precision and recall, F1 = 2×(precision×recall) / (precision+recall).

9. The pure electric four-wheel drive cargo handling chassis system according to claim 1, characterized in that: In the chassis control module, the vehicle speed is controlled and adjusted, specifically using FOC technology to control the magnetic field and current of the drive motor to achieve precise control of speed and torque.

Images