Vehicle body posture online early warning method and system based on multiple sensors and medium

Abstract

The invention relates to a multi-sensor-based vehicle body posture online early warning method and system and a medium, and the method comprises the steps: S1, obtaining the motion state data information of the left front side of a vehicle body in real time based on a vehicle-mounted IMU sensor on the left front side, the motion state data information of the right front side of the vehicle body is obtained in real time based on the vehicle-mounted IMU sensor on the right front side, the motion state data information of the left rear side of the vehicle body is obtained in real time based on the vehicle-mounted IMU sensor on the left rear side, and the motion state data information of the right rear side of the vehicle body is obtained in real time based on the vehicle-mounted IMU sensor on the right rear side; s2, the motion state data information of the left front side, the motion state data information of the right front side, the motion state data information of the left rear side and the motion state data information of the right rear side of the vehicle body are obtained. According to the method, the monitoring range of the unmanned container truck at the port can be expanded, the safety and the prevention capability are improved, the possibility of accidents is reduced, and the safety of port operation is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned vehicles, and in particular to a vehicle body posture online early warning method, system and medium based on multiple sensors. Background Art

[0002] In recent years, as the country vigorously carries out the construction of smart ports, more and more ports have begun to use unmanned container trucks as a link between the stacking area and container ships to transport goods. Unmanned container trucks are often used in conjunction with intelligent supervision platforms, and operators can remotely view the current location information of the vehicle, such as lanes, target point operation yard bay numbers, and operation types. Due to the uneven road surface, the slope and the uneven distribution of goods in the container cause the vehicle body to tilt left and right, resulting in the risk of overturning. Therefore, in addition to the above position information, the body posture information detection is also crucial to the safety of the overall system. Body posture detection refers to the use of sensors on unmanned container trucks to detect the posture of the vehicle during operation, and the attitude processing and solution system outputs the vehicle's tilt angle, pitch angle, heading angle, speed acceleration and other information, which is crucial to the safety of the overall system. The data source of body posture detection generally relies on the IMU sensor installed at the center axis of the rear wheel of the vehicle body. Based on the assumption that the IMU is rigidly connected to the vehicle body, the posture change of the inertial measurement original IMU approximately reflects the change of the body posture. This method can only characterize the posture of a certain part of the vehicle. However, unmanned container trucks are different. Their bodies are too long, and the container cargo they carry is often more than 40 tons. The suspension system of the body changes greatly, and it is impossible to accurately characterize the changes in the body posture by relying solely on a single IMU installed at the center of the rear axle of the wheel. Therefore, the present invention integrates data from multiple IMUs installed around the body to accurately sense the posture changes of various parts of the body and predict risks in advance, so as to promptly discover abnormal situations during the driving of unmanned container trucks, help operators better understand the current status of the vehicle, and reduce the risk of safety accidents.

[0003] In the prior art, a Chinese patent (application number: 201780051103.2, publication number: CN109642783A) discloses a posture detection system for a vehicle, which is used to detect the posture of a vehicle traveling on a road surface paved with a magnetic marker. The posture detection system for a vehicle comprises: a sensor unit, which has a plurality of magnetic sensors arranged in the vehicle width direction, and measures the lateral offset relative to the magnetic marker; and a control unit, which calculates the difference in the lateral offset measured by the sensor units located in front and behind two parts separated in the front and rear directions of the vehicle for any magnetic marker. However, this solution requires a lot of time and cost in advance to transform the environment and lay magnetic nails. The cost of use is high and it is difficult to be quickly applied in existing ports, and the portability is poor. In addition, the magnetic identification sensor also needs to be regularly inspected and replaced, which increases the on-site operating costs, so it is not suitable for unmanned container truck posture detection. Summary of the invention

[0004] In view of the above deficiencies in the prior art, the present invention provides a vehicle body posture online warning method, system and medium based on multiple sensors, which can not only improve the monitoring range of unmanned container trucks in ports, improve safety and prevention capabilities, but also reduce the possibility of accidents and ensure the safety of port operations.

[0005] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows: a vehicle body posture online early warning method based on multiple sensors, the method comprising:

[0006] S1. The vehicle is driving on the road, and the motion state data information of the left front side of the vehicle body is obtained in real time based on the IMU sensor on the left front side of the vehicle, the motion state data information of the right front side of the vehicle body is obtained in real time based on the IMU sensor on the right front side of the vehicle, the motion state data information of the left rear side of the vehicle body is obtained in real time based on the IMU sensor on the left rear side of the vehicle, and the motion state data information of the right rear side of the vehicle body is obtained in real time based on the IMU sensor on the right rear side of the vehicle;

[0007] S2. Based on the motion state data information of the left front side, the motion state data information of the right front side, the motion state data information of the left rear side and the motion state data information of the right rear side of the vehicle body, a multi-source data fusion algorithm based on the Pearson correlation coefficient is used to fuse the motion states of different sides of the vehicle body to obtain fused motion state data information of the vehicle body;

[0008] S3. Based on the fused motion state data information of the vehicle body, the posture of the vehicle body is predicted by using a regression prediction algorithm of a gray neural network based on multi-objective sparrow optimization to obtain the predicted posture data information of the vehicle body;

[0009] S4. Based on the predicted body posture data information, construct a body posture evaluation function P, calculate the feasibility evaluation value of the body posture, and obtain the feasibility evaluation value data information of the body posture.

[0010] Furthermore, the method further comprises:

[0011] S5. Based on the feasibility evaluation value data information of the vehicle body posture, a preset threshold is set. If the feasibility evaluation value of the vehicle body posture is less than the preset threshold, the vehicle drives normally. If the feasibility evaluation value of the vehicle body posture is greater than the preset threshold, the vehicle will roll over and issue a warning.

[0012] Furthermore, in step S2, the fusing of the motion states of different sides of the vehicle body by using a multi-source data fusion algorithm based on the Pearson correlation coefficient includes:

[0013] S21. Based on the motion state data information of the left front side, the motion state data information of the right front side, the motion state data information of the left rear side and the motion state data information of the right rear side of the vehicle body, a Pearson correlation function G of the vehicle body motion state is established,

[0014]

[0015] , where x1 is the motion state data information of the left front side of the vehicle body, x2 is the motion state data information of the right front side of the vehicle body, x3 is the motion state data information of the left rear side of the vehicle body, x4 is the motion state data information of the right rear side of the vehicle body, α1, α2 and α3 are weight factors of the vehicle body motion state, the correlation of the motion state of different sides of the vehicle body is characterized, and the correlation matrix of the motion state of different sides of the vehicle body is constructed to obtain the correlation matrix data information of the motion state of different sides of the vehicle body;

[0016] S22. Based on the correlation matrix data information of the motion states of different sides of the vehicle body, a fusion function H of the motion states of different sides of the vehicle body is constructed.

[0017]

[0018] Among them, y is the correlation matrix data information of the motion state of different sides of the vehicle body, β1, β2 and β3 are the feature fusion factors of the motion state of different sides of the vehicle body;

[0019] S23. Based on the fusion function H of the motion states of different sides of the vehicle body, the motion states of different sides of the vehicle body are fused to obtain fused motion state data information of the vehicle body.

[0020] Furthermore, the characteristic fusion factors β1, β2 and β3 of the motion states of different sides of the vehicle body are:

[0021]

[0022] Among them, x1 is the motion state data information of the left front side of the vehicle body, x2 is the motion state data information of the right front side of the vehicle body, x3 is the motion state data information of the left rear side of the vehicle body, and x4 is the motion state data information of the right rear side of the vehicle body.

[0023] Furthermore, the constraints of the weight factors α1, α2 and α3 of the vehicle body motion state are:

[0024]

[0025] Furthermore, in step S3, the method of predicting the posture of the vehicle body by using a regression prediction algorithm of a grey neural network based on multi-objective sparrow optimization includes:

[0026] S31. Inputting the fused vehicle body motion state data information into the gray neural network model for training and learning, initializing the network parameters of the gray neural network, and obtaining a trained gray neural network model;

[0027] S32. Based on the trained gray neural network model, a network parameter matrix of the gray neural network model is constructed, the sparrow population is initialized, the maximum number of iterations is determined, and the data information of the initialized sparrow population is obtained;

[0028] S33. Based on the data information of the initialized sparrow population, establish the fitness function Q of the population individuals,

[0029]

[0030] Among them, z is the data information of the initialized sparrow population, δ1 and δ2 are the fitness determining factors of the sparrow population individuals, and the fitness values ​​of the sparrow population individuals are calculated to obtain the fitness value data information of the sparrow population individuals;

[0031] S34. Based on the fitness value data information of the sparrow population individuals, establish a target optimization function W,

[0032]

[0033] Among them, r is the fitness value data information of the sparrow population individuals, γ1, γ2 and γ3 are the adaptive adjustment factors of the target optimization, and the network parameters of the grey neural network are optimized to obtain the optimized grey neural network model;

[0034] S35. Based on the optimized grey neural network model, the fused vehicle body motion state data information is input, the vehicle body posture is predicted, and the predicted vehicle body posture data information is obtained.

[0035] Furthermore, the constraint function f of the adaptive adjustment factors γ1, γ2 and γ3 of the target optimization is,

[0036]

[0037] The constraint condition of the fitness determining factor of the sparrow population individuals is:

[0038]

[0039] Among them, the value range of the constraint function f is (3,5).

[0040] Furthermore, the posture evaluation function P of the vehicle body is:

[0041]

[0042] Among them, g is the predicted body posture data information, η1, η2 and η3 are the evaluation factors of the body posture.

[0043] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the multi-sensor based vehicle body posture online warning methods.

[0044] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the multi-sensor based vehicle body posture online warning methods.

[0045] The present invention has the following positive effects:

[0046] 1. The present invention adopts a multi-source data fusion algorithm based on the Pearson correlation coefficient to fuse the motion states of different sides of the vehicle body, and combines the regression prediction algorithm of the grey neural network based on multi-objective sparrow optimization to predict the posture of the vehicle body. It can not only improve the monitoring range of unmanned container trucks in ports, improve safety and prevention capabilities, but also reduce the possibility of accidents and ensure the safety of port operations.

[0047] 2. The present invention constructs a posture evaluation function P of the vehicle body, calculates the feasibility evaluation value of the vehicle body posture, and provides real-time feedback and predictive alarms. Operation supervisors can make timely adjustments, which can not only maintain the stability of the vehicle during driving, but also the body posture detection can also be used to diagnose faults of components such as the vehicle suspension system and steering system, helping to discover and solve problems in a timely manner, thereby improving the reliability and durability of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0049] Figure 2 It is a flow chart of a multi-source data fusion algorithm based on Pearson correlation coefficient of the present invention;

[0050] Figure 3 It is a flow chart of the regression prediction algorithm of the grey neural network based on multi-objective sparrow optimization of the present invention;

[0051] Figure 4 Schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION

[0052] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0053] Example 1: Figure 1 As shown, a vehicle body posture online early warning method based on multiple sensors, the method comprising:

[0054] S1. The vehicle is driving on the road, and the motion state data information of the left front side of the vehicle body is obtained in real time based on the IMU sensor on the left front side of the vehicle, the motion state data information of the right front side of the vehicle body is obtained in real time based on the IMU sensor on the right front side of the vehicle, the motion state data information of the left rear side of the vehicle body is obtained in real time based on the IMU sensor on the left rear side of the vehicle, and the motion state data information of the right rear side of the vehicle body is obtained in real time based on the IMU sensor on the right rear side of the vehicle;

[0055] S2. Based on the motion state data information of the left front side, the motion state data information of the right front side, the motion state data information of the left rear side and the motion state data information of the right rear side of the vehicle body, a multi-source data fusion algorithm based on the Pearson correlation coefficient is used to fuse the motion states of different sides of the vehicle body to obtain fused motion state data information of the vehicle body;

[0056] S3. Based on the fused motion state data information of the vehicle body, the posture of the vehicle body is predicted by using a regression prediction algorithm of a gray neural network based on multi-objective sparrow optimization to obtain the predicted posture data information of the vehicle body;

[0057] S4. Based on the predicted body posture data information, construct a body posture evaluation function P, calculate the feasibility evaluation value of the body posture, and obtain the feasibility evaluation value data information of the body posture.

[0058] In this embodiment, the method further includes:

[0059] S5. Based on the feasibility evaluation value data information of the vehicle body posture, a preset threshold is set. If the feasibility evaluation value of the vehicle body posture is less than the preset threshold, the vehicle drives normally. If the feasibility evaluation value of the vehicle body posture is greater than the preset threshold, the vehicle will roll over and issue a warning.

[0060] In this embodiment, if Figure 2 As shown, in step S2, the multi-source data fusion algorithm based on the Pearson correlation coefficient is used to fuse the motion states of different sides of the vehicle body, including:

[0061] S21. Based on the motion state data information of the left front side, the motion state data information of the right front side, the motion state data information of the left rear side and the motion state data information of the right rear side of the vehicle body, a Pearson correlation function G of the vehicle body motion state is established,

[0062]

[0063] , where x1 is the motion state data information of the left front side of the vehicle body, x2 is the motion state data information of the right front side of the vehicle body, x3 is the motion state data information of the left rear side of the vehicle body, x4 is the motion state data information of the right rear side of the vehicle body, α1, α2 and α3 are weight factors of the vehicle body motion state, the correlation of the motion state of different sides of the vehicle body is characterized, and the correlation matrix of the motion state of different sides of the vehicle body is constructed to obtain the correlation matrix data information of the motion state of different sides of the vehicle body;

[0064] S22. Based on the correlation matrix data information of the motion states of different sides of the vehicle body, a fusion function H of the motion states of different sides of the vehicle body is constructed.

[0065]

[0066] Among them, y is the correlation matrix data information of the motion state of different sides of the vehicle body, β1, β2 and β3 are the feature fusion factors of the motion state of different sides of the vehicle body;

[0067] S23. Based on the fusion function H of the motion states of different sides of the vehicle body, the motion states of different sides of the vehicle body are fused to obtain fused motion state data information of the vehicle body.

[0068] In this embodiment, the characteristic fusion factors β1, β2 and β3 of the motion states of different sides of the vehicle body are:

[0069]

[0070] Among them, x1 is the motion state data information of the left front side of the vehicle body, x2 is the motion state data information of the right front side of the vehicle body, x3 is the motion state data information of the left rear side of the vehicle body, and x4 is the motion state data information of the right rear side of the vehicle body.

[0071] In this embodiment, the constraints of the weight factors α1, α2 and α3 of the vehicle body motion state are:

[0072]

[0073] Embodiment 2: Based on the multi-sensor based vehicle body posture online early warning method of embodiment 1, the present invention is further illustrated and described below.

[0074] like Figure 1 As shown, a vehicle body posture online early warning method based on multiple sensors, the method comprising:

[0075] S1. The vehicle is driving on the road, and the motion state data information of the left front side of the vehicle body is obtained in real time based on the IMU sensor on the left front side of the vehicle, the motion state data information of the right front side of the vehicle body is obtained in real time based on the IMU sensor on the right front side of the vehicle, the motion state data information of the left rear side of the vehicle body is obtained in real time based on the IMU sensor on the left rear side of the vehicle, and the motion state data information of the right rear side of the vehicle body is obtained in real time based on the IMU sensor on the right rear side of the vehicle;

[0076] S2. Based on the motion state data information of the left front side, the motion state data information of the right front side, the motion state data information of the left rear side and the motion state data information of the right rear side of the vehicle body, a multi-source data fusion algorithm based on the Pearson correlation coefficient is used to fuse the motion states of different sides of the vehicle body to obtain fused motion state data information of the vehicle body;

[0077] S3. Based on the fused motion state data information of the vehicle body, the posture of the vehicle body is predicted by using a regression prediction algorithm of a gray neural network based on multi-objective sparrow optimization to obtain the predicted posture data information of the vehicle body;

[0078] S4. Based on the predicted body posture data information, construct a body posture evaluation function P, calculate the feasibility evaluation value of the body posture, and obtain the feasibility evaluation value data information of the body posture.

[0079] In this embodiment, if Figure 3 As shown, in step S3, the use of a regression prediction algorithm of a grey neural network based on multi-objective sparrow optimization to predict the posture of the vehicle body includes:

[0080] S31. Inputting the fused vehicle body motion state data information into the gray neural network model for training and learning, initializing the network parameters of the gray neural network, and obtaining a trained gray neural network model;

[0081] S32. Based on the trained gray neural network model, a network parameter matrix of the gray neural network model is constructed, the sparrow population is initialized, the maximum number of iterations is determined, and the data information of the initialized sparrow population is obtained;

[0082] S33. Based on the data information of the initialized sparrow population, establish the fitness function Q of the population individuals,

[0083]

[0084] Among them, z is the data information of the initialized sparrow population, δ1 and δ2 are the fitness determining factors of the sparrow population individuals, and the fitness values ​​of the sparrow population individuals are calculated to obtain the fitness value data information of the sparrow population individuals;

[0085] S34. Based on the fitness value data information of the sparrow population individuals, establish a target optimization function W,

[0086]

[0087] Among them, r is the fitness value data information of the sparrow population individuals, γ1, γ2 and γ3 are the adaptive adjustment factors of the target optimization, and the network parameters of the grey neural network are optimized to obtain the optimized grey neural network model;

[0088] S35. Based on the optimized grey neural network model, the fused vehicle body motion state data information is input, the vehicle body posture is predicted, and the predicted vehicle body posture data information is obtained.

[0089] In this embodiment, the constraint function f of the adaptive adjustment factors γ1, γ2 and γ3 of the target optimization is,

[0090]

[0091] The constraint condition of the fitness determining factor of the sparrow population individuals is:

[0092]

[0093] Among them, the value range of the constraint function f is (3,5).

[0094] In this embodiment, the posture evaluation function P of the vehicle body is:

[0095]

[0096] Among them, g is the predicted body posture data information, η1, η2 and η3 are the evaluation factors of the body posture.

[0097] In this embodiment, the present invention provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the multi-sensor based vehicle body posture online early warning methods.

[0098] In this embodiment, if Figure 4As shown in the figure, the posture of the vehicle in the no-load state is recorded as the initial value at the time of power-on; the speed, acceleration, roll angle, heading angle and other information obtained by the IMU installed at the four corners of the vehicle body are transmitted to the controller through wired transmission; the controller uses the data preprocessing algorithm to eliminate the interference of abnormal data and complete the time alignment. After receiving the information from multiple IMU sensors, the fusion algorithm solves the vehicle body posture and calculates the IMU zero bias value to compensate for each incoming data to obtain the real angle change, and predicts the change trend of the vehicle body posture in the next 30 seconds; the current vehicle body posture information solved by the fusion algorithm is compared with the predicted vehicle body change trend and the no-load state saved at the initial power-on time. If the set allowable change angle threshold is exceeded, a warning message is issued; the solved posture information and alarm signal are uploaded to the remote monitoring platform through the 5G wireless transmission facilities on the vehicle side, and the platform personnel promptly issue a speed reduction or parking command, which is sent to the vehicle side through the 5G transmission communication module.

[0099] In this embodiment, the present invention provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the multi-sensor based vehicle body posture online early warning methods.

[0100] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0101] In summary, the present invention can not only improve the monitoring range of unmanned container trucks in ports, improve safety and prevention capabilities, but also reduce the possibility of accidents and ensure the safety of port operations.

[0102] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A vehicle body posture online early warning method based on multiple sensors, characterized in that: The method comprises: S1. The vehicle is driving on the road, and the motion state data information of the left front side of the vehicle body is obtained in real time based on the IMU sensor on the left front side of the vehicle, the motion state data information of the right front side of the vehicle body is obtained in real time based on the IMU sensor on the right front side of the vehicle, the motion state data information of the left rear side of the vehicle body is obtained in real time based on the IMU sensor on the left rear side of the vehicle, and the motion state data information of the right rear side of the vehicle body is obtained in real time based on the IMU sensor on the right rear side of the vehicle; S2. Based on the motion state data information of the left front side, the motion state data information of the right front side, the motion state data information of the left rear side and the motion state data information of the right rear side of the vehicle body, a multi-source data fusion algorithm based on the Pearson correlation coefficient is used to fuse the motion states of different sides of the vehicle body to obtain fused motion state data information of the vehicle body; S3. Based on the fused motion state data information of the vehicle body, the posture of the vehicle body is predicted by using a regression prediction algorithm of a gray neural network based on multi-objective sparrow optimization to obtain the predicted posture data information of the vehicle body; S4. Based on the predicted body posture data information, construct a body posture evaluation function P, calculate the feasibility evaluation value of the body posture, and obtain the feasibility evaluation value data information of the body posture.

2. The multi-sensor based vehicle body posture online early warning method according to claim 1 is characterized in that: The method further comprises: S5. Based on the feasibility evaluation value data information of the vehicle body posture, a preset threshold is set. If the feasibility evaluation value of the vehicle body posture is less than the preset threshold, the vehicle drives normally. If the feasibility evaluation value of the vehicle body posture is greater than the preset threshold, the vehicle will roll over and issue a warning.

3. The vehicle body posture online early warning method based on multiple sensors according to claim 1 is characterized in that: In step S2, the multi-source data fusion algorithm based on the Pearson correlation coefficient is used to fuse the motion states of different sides of the vehicle body, including: S21. Based on the motion state data information of the left front side, the motion state data information of the right front side, the motion state data information of the left rear side and the motion state data information of the right rear side of the vehicle body, a Pearson correlation function G of the vehicle body motion state is established, Among them, x1 is the motion state data information of the left front side of the vehicle body, x2 is the motion state data information of the right front side of the vehicle body, x3 is the motion state data information of the left rear side of the vehicle body, x4 is the motion state data information of the right rear side of the vehicle body, α1, α2 and α3 are weight factors of the vehicle body motion state, the correlation of the motion state of different sides of the vehicle body is characterized, and the correlation matrix of the motion state of different sides of the vehicle body is constructed to obtain the correlation matrix data information of the motion state of different sides of the vehicle body; S22. Based on the correlation matrix data information of the motion states of different sides of the vehicle body, a fusion function H of the motion states of different sides of the vehicle body is constructed. Among them, y is the correlation matrix data information of the motion state of different sides of the vehicle body, β1, β2 and β3 are the feature fusion factors of the motion state of different sides of the vehicle body; S23. Based on the fusion function H of the motion states of different sides of the vehicle body, the motion states of different sides of the vehicle body are fused to obtain fused motion state data information of the vehicle body.

4. The multi-sensor based vehicle body posture online early warning method according to claim 3 is characterized by: The characteristic fusion factors β1, β2 and β3 of the motion states of different sides of the vehicle body are: Among them, x1 is the motion state data information of the left front side of the vehicle body, x2 is the motion state data information of the right front side of the vehicle body, x3 is the motion state data information of the left rear side of the vehicle body, and x4 is the motion state data information of the right rear side of the vehicle body.

5. The multi-sensor based vehicle posture online early warning method according to claim 3 is characterized by: The constraints of the weight factors α1, α2 and α3 of the vehicle body motion state are:

6. The multi-sensor based vehicle posture online early warning method according to claim 1 is characterized in that: In step S3, the method of predicting the posture of the vehicle body by using a regression prediction algorithm of a grey neural network based on multi-objective sparrow optimization includes: S31. Inputting the fused vehicle body motion state data information into the gray neural network model for training and learning, initializing the network parameters of the gray neural network, and obtaining a trained gray neural network model; S32. Based on the trained gray neural network model, a network parameter matrix of the gray neural network model is constructed, the sparrow population is initialized, the maximum number of iterations is determined, and the data information of the initialized sparrow population is obtained; S33. Based on the data information of the initialized sparrow population, establish the fitness function Q of the population individuals, Among them, z is the data information of the initialized sparrow population, δ1 and δ2 are the fitness determining factors of the sparrow population individuals, and the fitness values ​​of the sparrow population individuals are calculated to obtain the fitness value data information of the sparrow population individuals; S34. Based on the fitness value data information of the sparrow population individuals, establish a target optimization function W, Among them, r is the fitness value data information of the sparrow population individuals, γ1, γ2 and γ3 are the adaptive adjustment factors of the target optimization, and the network parameters of the grey neural network are optimized to obtain the optimized grey neural network model; S35. Based on the optimized grey neural network model, the fused vehicle body motion state data information is input, the vehicle body posture is predicted, and the predicted vehicle body posture data information is obtained.

7. The multi-sensor based vehicle body posture online early warning method according to claim 6 is characterized by: The constraint function f of the adaptive adjustment factors γ1, γ2 and γ3 of the target optimization is, The constraint condition of the fitness determining factor of the sparrow population individuals is: Among them, the value range of the constraint function f is (3,5).

8. The multi-sensor based vehicle body posture online early warning method according to claim 1, characterized in that: The posture evaluation function P of the vehicle body is: Among them, g is the predicted body posture data information, η1, η2 and η3 are the evaluation factors of the body posture.

9. A multi-sensor based vehicle posture online warning system, comprising a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the multi-sensor based vehicle body posture online warning method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program programmed or configured to execute the multi-sensor based vehicle body posture online warning method as described in any one of claims 1 to 8.

Images