An optimization method and system for the ride comfort of sightseeing vehicles based on big data

Abstract

The present invention relates to the technical field of ride comfort optimization, and specifically relates to a ride comfort optimization method and system for a sightseeing vehicle based on big data, including multi-dimensional data acquisition: obtaining the vibration acceleration data, the front road surface image data, and the passenger heart rate variability data of the sightseeing vehicle; multi-source data fusion processing: extracting the frequency domain characteristics of the vibration acceleration data to obtain the vibration energy distribution spectrum, performing texture segmentation and pothole identification on the road surface image data to generate a road surface roughness matrix, and performing standardization processing on the passenger heart rate variability data to generate a somatic discomfort index; dynamic weight ride comfort evaluation: inputting a preset fuzzy logic model and outputting a comprehensive ride comfort index; multi-objective optimization strategy generation: generating a multi-parameter collaborative adjustment instruction set; closed-loop feedback dynamic optimization: performing correlation verification and correcting the weight allocation rule of the fuzzy logic model. The present invention improves the comfort and stability during the operation of the sightseeing vehicle and enhances the intelligence of the control system.

Description

Technical Field

[0001] The present invention relates to the technical field of ride comfort optimization, and particularly to a ride comfort optimization method and system for sightseeing vehicles based on big data. Background Art

[0002] With the continuous promotion of the integration of culture and tourism development and the construction of smart scenic spots, as an important tool for carrying tourists for short-distance movement, sightseeing vehicles have put forward higher requirements for ride comfort and comfort during the ride. The ride comfort control of traditional sightseeing vehicles mainly relies on suspension structure design, path detour strategies or manual experience adjustment, and usually only makes passive responses based on the acceleration data of the vehicle body itself, lacking the multi-dimensional perception ability of the driving environment, road conditions and passengers' subjective feelings, and it is difficult to achieve personalized and intelligent ride comfort management; in addition, most of the existing systems lack a feedback mechanism and cannot dynamically optimize the control strategy according to the immediate physiological or behavioral responses of passengers, resulting in unstable comfort performance of the vehicle in complex road conditions or changing passenger flow scenarios.

[0003] In recent years, with the gradual application of technologies such as big data perception, fuzzy control, and machine learning in the field of intelligent transportation, researchers have begun to try to introduce multi-source heterogeneous data for vehicle comfort modeling, such as using cameras to identify road potholes, monitoring the heart rate changes of passengers through wearable devices, and combining vibration signals for road condition and response analysis, etc.; however, the existing methods generally have problems such as insufficient data fusion dimensions, fixed parameter weights, and lagging feedback mechanisms, and it is difficult to achieve global optimization of the ride comfort control of sightseeing vehicles. Summary of the Invention

[0004] The present invention provides a ride comfort optimization method and system for sightseeing vehicles based on big data, a big data-driven intelligent optimization method that integrates vehicle dynamic response, environmental image recognition and passenger physiological state perception, and constructs a ride comfort control system that can be closed-loop and adaptively adjusted to improve the overall operation quality and user ride experience of intelligent sightseeing vehicles.

[0005] A ride comfort optimization method for sightseeing vehicles based on big data includes the following steps:

[0006] S1, multi-dimensional data acquisition: obtaining the vibration acceleration data of the sightseeing vehicle through in-vehicle sensors, collecting the front road surface image data through cameras, and obtaining the passenger heart rate variability data through wearable devices;

[0007] S2, multi-source data fusion processing: extracting the frequency domain characteristics of the vibration acceleration data to obtain the vibration energy distribution spectrum, performing texture segmentation and pothole recognition on the road surface image data to generate the road surface roughness matrix, and performing standardization processing on the passenger heart rate variability data to generate the somatic discomfort index;

[0008] S3, Dynamic Weight Smoothness Evaluation: Input the vibration energy distribution spectrum, road surface roughness matrix, and somatic discomfort index into a preset fuzzy logic model, dynamically allocate the weights of each parameter according to the current driving scenario, and output the comprehensive smoothness index;

[0009] S4, Multi-objective Optimization Strategy Generation: According to the comprehensive smoothness index, simultaneously optimize the suspension damping coefficient, drive motor torque distribution coefficient, and path planning priority parameters through a genetic algorithm to generate a multi-parameter collaborative adjustment instruction set;

[0010] S5, Closed-loop Feedback Dynamic Optimization: Verify the correlation between the real-time collected passenger facial expression data and the somatic discomfort index, and correct the weight allocation rule of the fuzzy logic model according to the verification result.

[0011] Optionally, the S1 includes:

[0012] S11, Real-time collect vehicle vibration acceleration data through triaxial acceleration sensors installed at the center positions of the front and rear axles of the vehicle body;

[0013] S12, Continuously collect the road image frame sequence within 5 meters in front through a wide-angle camera installed at the front of the vehicle head, and identify the rough road surface area by using image texture features and edge gradient change rates;

[0014] S13, Collect heart rate variability data through a photoplethysmograph device worn on the passenger's wrist, and use time-domain indicators to calculate the body's stress level.

[0015] Optionally, the S2 includes:

[0016] S21, Perform a fast Fourier transform on the vibration acceleration data, extract frequency-domain features to obtain the vibration energy distribution spectrum;

[0017] S22, Perform texture segmentation and pothole identification on the collected front road surface image sequence to generate a road surface roughness matrix, and the roughness matrix is jointly constructed based on image gradients and local binary pattern texture features;

[0018] S23, Standardize the heart rate variability index to generate a somatic discomfort index .

[0019] Optionally, the S3 includes:

[0020] S31, Input the vibration energy distribution spectrum, road surface roughness matrix, and somatic discomfort index into the input end of the fuzzy logic model respectively to construct a ternary input variable set;

[0021] S32. Dynamically allocate the weights of each input variable according to the current driving scenario information to form a set of normalized weight coefficients;

[0022] S33. Calculate the output comprehensive ride comfort index based on the allocated weight coefficients and the ternary input variables.

[0023] Optionally, the S4 includes:

[0024] S41. Optimization variable modeling: According to the comprehensive ride comfort index , construct a multi-objective optimization model with the suspension damping coefficient , the motor torque distribution coefficient and the path planning priority parameter as the optimization variables;

[0025] S42. Fitness function construction: Based on the multi-objective optimization model, define a fitness function as the optimization basis for measuring the ride comfort of each parameter combination;

[0026] S43. Genetic algorithm iterative optimization: Initialize the population and perform iterative search through selection, crossover, and mutation operations, and finally output the optimal parameter combination , and generate a multi-parameter collaborative adjustment instruction set.

[0027] Optionally, the S43 uses a genetic algorithm to globally search and optimize the parameter vector, and the iterative process includes:

[0028] S431. Population initialization: Set the population size to , randomly generate initial individuals, and each individual is a set of control parameter combinations to be optimized ;

[0029] S432. Fitness evaluation: Input the individual parameters into the comprehensive ride comfort model and calculate the fitness value , which is used to measure the ride comfort performance of the current combination;

[0030] S433. Selection operation: According to the fitness level, preferentially select excellent individuals from the current population as the parent generation of the next generation;

[0031] S434. Crossover operation: Generate new individuals among the parent generations through the crossover algorithm to expand the search space and transfer excellent features;

[0032] S435. Mutation operation: Perturb the newly generated individuals to enhance the global search ability and avoid falling into local optima;

[0033] S436. Termination determination: When the set iteration number or the fitness convergence condition is reached, end the optimization process;

[0034] S437, Output result: Extract the optimal parameter combination , Generate an adjustment instruction set including suspension damping, motor torque distribution, and path priority .

[0035] Optionally, the S5 includes:

[0036] S51, Facial expression - somatosensory correlation verification: Real - time collect passenger facial image data through an in - vehicle camera, extract facial expression features using a trained convolutional neural network model, and convert them into an emotion score sequence, which is time - synchronized with the somatosensory discomfort index collected and standardized by a wearable device;

[0037] S52, Fuzzy model weight correction: Dynamically adjust the set value of the somatosensory weight in the fuzzy logic model according to the calculated correlation strength, while maintaining the normalization constraint that the sum of weights is 1.

[0038] Optionally, in the S51 facial expression - somatosensory correlation verification, real - time collect passenger facial image data through an in - vehicle camera, and extract facial expression feature vectors through a convolutional neural network model , and combine with the somatosensory discomfort index , and calculate the correlation between the two using the Pearson correlation coefficient .

[0039] Optionally, in the S52 fuzzy logic model weight correction, when the correlation coefficient is higher than the set threshold , it is considered that the facial expression can be used as a somatosensory supplementary index, and the somatosensory discomfort weight coefficient in the fuzzy logic model is dynamically adjusted using the exponential sliding update method .

[0040] A sightseeing vehicle ride comfort optimization system based on big data, used to implement the above - mentioned sightseeing vehicle ride comfort optimization method based on big data, includes the following modules:

[0041] Multi - dimensional data acquisition module: Obtain vibration acceleration data, front - road surface image data, and passenger heart rate variability data during the operation of the sightseeing vehicle;

[0042] Multi - source data fusion and processing module: Extract frequency - domain features from vibration data to generate a vibration energy distribution spectrum, perform texture segmentation and pothole recognition on image data to generate a road surface roughness matrix, and perform standardization processing on heart rate variability data to generate a somatosensory discomfort index;

[0043] Ride comfort evaluation module: Input the vibration energy distribution spectrum, road surface roughness matrix, and somatosensory discomfort index into the fuzzy logic model, and dynamically allocate parameter weights according to the current driving scenario, and output a comprehensive ride comfort index;

[0044] Multi-objective optimization control module: Based on the comprehensive ride comfort index, optimize the suspension damping coefficient, drive motor torque distribution coefficient and path planning priority parameters through genetic algorithm, and generate a multi-parameter collaborative adjustment instruction set;

[0045] Closed-loop feedback adaptive module: Collect passenger facial expression data, conduct correlation analysis with the somatic discomfort index, and modify the weight allocation rules in the fuzzy logic model according to the analysis results to achieve dynamic optimization.

[0046] Advantages of the present invention:

[0047] The present invention first establishes a ride comfort evaluation model for the joint perception of the three elements of "vehicle-road-passenger" by integrating multi-dimensional heterogeneous data such as vibration acceleration, front road surface image and passenger physiological reactions during the operation of the sightseeing vehicle, breaking through the limitations of traditional methods that rely on single acceleration or fixed suspension adjustment; Utilize the fuzzy logic dynamic weighting mechanism to realize the adaptive fusion evaluation of vibration energy distribution, road condition roughness and somatic discomfort index, effectively improving the objectivity of the comprehensive ride comfort index and the individual sensitivity response ability.

[0048] The present invention realizes the multi-parameter collaborative optimization of suspension damping, drive torque distribution and path priority through genetic algorithm, constructs a closed-loop dynamic adjustment mechanism, and introduces the relevant feedback of passenger facial expressions and somatic data to correct the weights of the fuzzy model in real time, significantly improving the adaptability of the system to changing road conditions and individual reactions; Compared with the prior art, the present invention not only improves the comfort and stability during the operation of the sightseeing vehicle, but also enhances the intelligence, accuracy and user perception consistency of the control system, and has good application prospects and promotion value. Description of the drawings

[0049] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only those of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0050] Figure 1 It is the method flow chart of the embodiment of the present invention;

[0051] Figure 2 It is the system module diagram of the embodiment of the present invention. Detailed implementation manners

[0052] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; moreover, the accompanying drawings are only for more specifically describing the embodiments, and are not intended to specifically limit the present invention.

[0053] It should be noted that in the specification, references to "an embodiment", "embodiments", "exemplary embodiments", "some embodiments", etc. indicate that the described embodiments may include specific features, structures, or characteristics, but not necessarily every embodiment includes such specific features, structures, or characteristics. Additionally, when combining embodiments to describe specific features, structures, or characteristics, implementing such features, structures, or characteristics in combination with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the relevant art.

[0054] Generally, terms can be understood at least in part from their use in context. For example, at least in part depending on the context, the term "one or more" used herein can be used to describe any feature, structure, or characteristic in a singular sense, or can be used to describe a combination of features, structures, or characteristics in a plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey a set of exclusive factors, but rather can alternatively, at least in part depending on the context, allow for the existence of other factors that may not be explicitly described.

[0055] As Figure 1 shown, a method for optimizing the ride comfort of a sightseeing vehicle based on big data includes the following steps:

[0056] S1, multi-dimensional data acquisition: Obtain the vibration acceleration data of the sightseeing vehicle through in-vehicle sensors, collect the front road surface image data through cameras, and obtain the passenger heart rate variability data through wearable devices;

[0057] S2, multi-source data fusion processing: Extract the frequency domain features of the vibration acceleration data to obtain the vibration energy distribution spectrum, perform texture segmentation and pothole identification on the road surface image data to generate the road surface roughness matrix, and perform standardization processing on the passenger heart rate variability data to generate the somatic discomfort index;

[0058] S3, dynamic weight ride comfort evaluation: Input the vibration energy distribution spectrum, the road surface roughness matrix, and the somatic discomfort index into a preset fuzzy logic model, dynamically allocate the weights of each parameter according to the current driving scenario, and output the comprehensive ride comfort index;

[0059] S4, multi-objective optimization strategy generation: According to the comprehensive ride comfort index, simultaneously optimize the suspension damping coefficient, the drive motor torque distribution coefficient, and the path planning priority parameter through a genetic algorithm to generate a multi-parameter collaborative adjustment instruction set;

[0060] S5, Closed-loop feedback dynamic optimization: Verify the correlation between the real-time collected passenger facial expression data and the somatosensory discomfort index, and correct the weight distribution rules of the fuzzy logic model according to the verification results.

[0061] S1 includes:

[0062] S11, Real-time collect vehicle vibration acceleration data through triaxial acceleration sensors installed at the center positions of the front and rear axles of the vehicle body. The vibration acceleration data is represented in vector form as:

[0063] ;

[0064] Among them, respectively represent the accelerations of the vehicle in the front-back direction, left-right direction, and up-down direction, represents the timestamp, and the acceleration signal is recorded at the sampling frequency ;

[0065] S12, Continuously collect the road image frame sequence within 5 meters in front through a wide-angle camera installed at the front of the vehicle. Use image texture features and edge gradient change rates to identify the rough road surface area. The roughness matrix is represented as:

[0066] ;

[0067] Among them, represents the image gray intensity value, represents the gradient amplitude of the image at the pixel point , is the local texture complexity coefficient, obtained by calculating the gray-level co-occurrence matrix;

[0068] S13, Collect heart rate variability (HRV) data through a photoplethysmograph device worn on the passenger's wrist, and use the time-domain index to calculate the somatosensory stress level, represented as:

[0069] ;

[0070] Among them, is the time interval between two consecutive heartbeats, is the average value of all intervals, is the number of intervals within the sampling period, the interval reflects the time length between each heartbeat, the smaller it is, the higher the current physiological stress level of the passenger, reflecting their somatosensory discomfort level.

[0071] S2 includes:

[0072] S21, perform a fast Fourier transform (FFT) on the vibration acceleration data to extract frequency-domain features to obtain a vibration energy distribution spectrum , expressed as:

[0073] ;

[0074] where, represents the Fourier transform of the vertical acceleration signal , is the frequency component, represents the vibration energy density at frequency ;

[0075] S22, perform texture segmentation and pothole identification on the collected front road surface image sequence to generate a road surface roughness matrix , and the roughness matrix is jointly constructed based on image gradients and local binary pattern (LBP) texture features, expressed as:

[0076] ;

[0077] where, represents the gradient magnitude of the image at pixel , represents the local binary pattern texture response value of the local area of this pixel, used to characterize the road surface texture roughness, is an empirical weight factor that satisfies , and is used to adjust the fusion ratio of gradient features and texture features, the larger the

[0078] S23, perform normalization on the heart rate variability index to generate a somatic discomfort index , and the normalization uses the Z-score method, expressed as:

[0079] ;

[0080] where, represents the mean value of SDNN calculated based on historical samples, represents the standard deviation of SDNN of historical samples, the larger the

[0081] S3 includes:

[0082] S31, the vibration energy distribution spectrum , road roughness matrix and discomfort index Input them to the input end of the fuzzy logic model respectively to construct a set of ternary input variables, expressed as:

[0083] ;

[0084] ;

[0085] in, Represents the integrated energy of the frequency band in the vibration energy distribution spectrum, represents the resonance frequency range of the vehicle structure, , Represents the road roughness matrix The mean of is used to characterize the overall road condition level. is the body discomfort index;

[0086] S32, based on the current driving scene information (vehicle speed and path curvature ), the weights of each input variable are dynamically allocated by the fuzzy logic rule base to form a normalized weight coefficient set, which is expressed as:

[0087] ;

[0088] in, are the relative importance of vibration energy, road roughness and physical discomfort in the current scenario, , the weight distribution is derived by fuzzy rules, which include: "If the speed is high and the road condition is bad, the vibration energy weight is high; if the speed is low and the facial stress is significant, the body sensation weight is high";

[0089] S33, based on the assigned weight coefficient and the ternary input variables, calculates and outputs the comprehensive smoothness index , expressed as:

[0090] ;

[0091] in, is a comprehensive smoothness index. Respectively The result after normalization is in the range of , The larger the value, the more unstable the vehicle's current running state is.

[0092] S4 includes:

[0093] S41, Optimization variable modeling: Based on comprehensive smoothness index , constructed with suspension damping coefficient , motor torque distribution coefficient and path planning priority parameter for multi-objective optimization modeling with optimization variables including:

[0094] ;

[0095] ;

[0096] Among them, is the damping coefficient of the active suspension of the sightseeing vehicle, and the domain is , used to adjust the vehicle body vibration response, is the drive motor torque distribution coefficient, and are the driving forces of the motors of the front and rear wheels of the vehicle respectively, represents the distribution ratio of the torque to the front wheels, is the path planning priority parameter, representing the weight of the ride comfort objective in the planning process, and the domain is , the larger the value, the more inclined to choose a route with a relatively flat road surface but possibly a longer path;

[0097] S42, fitness function construction: Based on multi-objective optimization modeling, define the fitness function , as the optimization basis for measuring the ride comfort of each parameter combination, expressed as:

[0098] ;

[0099] Among them, is the optimized fitness value, and the larger the value, the better the ride comfort, is the comprehensive ride comfort index output by the fuzzy logic model, representing the comprehensive evaluation of the ride comfort of the current vehicle running state, and the larger the value, the more uneven, and the goal is to maximize the fitness function , that is, to minimize the unevenness;

[0100] S43, genetic algorithm iterative optimization: Initialize the population and perform iterative search through selection, crossover and mutation operations, and finally output the optimal parameter combination , generating a multi-parameter collaborative adjustment instruction set.

[0101] S43 uses the genetic algorithm to globally search and optimize the parameter vector, and the iterative process includes:

[0102] S431, population initialization: Set the population size to , randomly generate initial individuals, and each individual is a set of control parameter combinations to be optimized ;

[0103] S432, Fitness Evaluation: Input the individual parameters into the comprehensive ride comfort model , calculate the fitness value , which is used to measure the ride performance of the current combination and is expressed as:

[0104] ;

[0105] S433, Selection Operation: According to the fitness level, preferentially select excellent individuals from the current population as the parents of the next generation;

[0106] S434, Crossover Operation: Generate new individuals among the parents through the crossover algorithm to expand the search space and transfer excellent features, which is expressed as:

[0107] ;

[0108] Among them, is the crossover control factor, and its value is a function of the distance between parent individuals to control the balance between local search and global exploration;

[0109] S435, Mutation Operation: Perturb the newly generated individuals to enhance the global search ability and avoid falling into local optima, which is expressed as:

[0110] ;

[0111] Among them, is the perturbation factor obeying the normal distribution, is the allowable range of parameters;

[0112] S436, Termination Judgment: When the set number of iterations or the fitness convergence condition is reached, end the optimization process;

[0113] S437, Output Result: Extract the optimal parameter combination , generate an adjustment instruction set including suspension damping, motor torque distribution, and path priority .

[0114] S5 includes:

[0115] S51, Facial-Somatosensory Correlation Verification: Real-time collect the facial image data of passengers through an in-vehicle camera, use the trained convolutional neural network model to extract facial expression features, and convert them into an emotion score sequence, which is synchronized with the somatosensory discomfort index collected by the wearable device and standardized;

[0116] S52, Fuzzy Model Weight Correction: Dynamically adjust the set value of the somatosensory weight in the fuzzy logic model according to the calculated correlation strength, while maintaining the normalization constraint that the sum of the weights is 1.

[0117] S51 Facial Expression - Somatosensory Correlation Verification: Real - time collect passenger facial image data using an in - vehicle camera, and extract facial expression feature vectors through a Convolutional Neural Network (CNN) model , , and combine with the somatosensory discomfort index , and use the Pearson correlation coefficient to calculate the correlation between the two , expressed as:

[0118] ;

[0119] Among them, represents the somatosensory discomfort index at the th time slice, represents the facial expression feature score in the th time slice, and are respectively the means of and , is the total number of sampling points, , and the larger its absolute value, the stronger the consistency between the facial expression and the somatosensory data.

[0120] In S52 Fuzzy Logic Model Weight Correction, when the correlation coefficient is higher than the set threshold , it is considered that the facial expression can be used as a somatosensory supplementary index, and the somatosensory discomfort weight coefficient in the fuzzy logic model is dynamically adjusted using the exponential sliding update method , expressed as:

[0121] ;

[0122] Among them, and represent the current and updated somatosensory weights respectively, is the estimated value based on the influence of facial emotions, which can be normalized according to the proportion of facial tension, is the weight update rate coefficient, which determines the response speed, .

[0123] As Figure 2 shown, a sightseeing vehicle ride comfort optimization system based on big data, used to implement the above - mentioned sightseeing vehicle ride comfort optimization method based on big data, includes the following modules:

[0124] Multi - dimensional Data Acquisition Module: Obtain vibration acceleration data, front - road surface image data, and passenger heart rate variability data during the operation of the sightseeing vehicle;

[0125] Multi-source data fusion processing module: Extract the frequency-domain features of vibration data to generate a vibration energy distribution spectrum, perform texture segmentation and pothole recognition on image data to generate a road surface roughness matrix, and perform normalization processing on heart rate variability data to generate a somatic discomfort index;

[0126] Ride comfort evaluation module: Input the vibration energy distribution spectrum, road surface roughness matrix, and somatic discomfort index into a fuzzy logic model, dynamically allocate parameter weights according to the current driving scenario, and output a comprehensive ride comfort index;

[0127] Multi-objective optimization control module: Based on the comprehensive ride comfort index, optimize the suspension damping coefficient, drive motor torque distribution coefficient, and path planning priority parameters through a genetic algorithm to generate a multi-parameter collaborative adjustment instruction set;

[0128] Closed-loop feedback adaptive module: Collect passenger facial expression data, perform a correlation analysis with the somatic discomfort index, and correct the weight allocation rule in the fuzzy logic model according to the analysis result to achieve dynamic optimization.

[0129] The present invention covers any alternatives, modifications, equivalent methods, and solutions made within the spirit and scope of the present invention. For the public to have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, and those skilled in the art can fully understand the present invention without the description of these details. Additionally, well-known methods, processes, procedures, components, and circuits are not described in detail to avoid unnecessary confusion to the essence of the present invention.

[0130] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for optimizing the ride comfort of a sightseeing vehicle based on big data, characterized in that It includes the following steps: S1, Multi-dimensional data collection: Obtain the vibration acceleration data of the sightseeing vehicle through in-vehicle sensors, collect the front road surface image data through cameras, and obtain the passenger heart rate variability data through wearable devices; S2, Multi-source data fusion processing: Extract the frequency-domain features of the vibration acceleration data to obtain the vibration energy distribution spectrum, perform texture segmentation and pothole identification on the road surface image data to generate the road surface roughness matrix, and perform standardization processing on the passenger heart rate variability data to generate the somatosensory discomfort index; S3, Dynamic weight ride comfort evaluation: Input the vibration energy distribution spectrum, the road surface roughness matrix, and the somatosensory discomfort index into a preset fuzzy logic model, dynamically allocate the weights of each parameter according to the current driving scenario, and output the comprehensive ride comfort index; S4, Generation of multi-objective optimization strategy: According to the comprehensive ride comfort index, simultaneously optimize the suspension damping coefficient, the drive motor torque distribution coefficient, and the path planning priority parameters through a genetic algorithm, and generate a multi-parameter collaborative adjustment instruction set; S5, Closed-loop feedback dynamic optimization: Verify the correlation between the real-time collected passenger facial expression data and the somatosensory discomfort index, and correct the weight allocation rule of the fuzzy logic model according to the verification result.

2. The smoothness optimization method of a sightseeing vehicle based on big data according to claim 1, wherein, The S1 includes: S11, Real-time collect the vehicle vibration acceleration data through a triaxial acceleration sensor installed at the center position of the front and rear axles of the vehicle body; S12, Continuously collect the road image frame sequence within 5 meters in front through a wide-angle camera installed at the front of the vehicle head, and identify the rough road surface area using the image texture features and the edge gradient change rate; S13, collect heart rate variability data through a photoplethysmogram device worn on the passenger's wrist, and calculate the body's stress level using heart rate variability metrics Calculate the body's stress level.

3. The smoothness optimization method of a sightseeing vehicle based on big data according to claim 2, characterized in that, The S2 includes: S21, Perform a fast Fourier transform on the vibration acceleration data, and extract the frequency-domain features to obtain the vibration energy distribution spectrum; S22, Perform texture segmentation and pothole identification on the collected front road surface image data to generate the road surface roughness matrix, and the road surface roughness matrix is jointly constructed based on the image gradient and the local binary pattern texture features; S23, standardize the heart rate variability index to generate a somatic discomfort index .

4. A method for optimizing the ride comfort of a sightseeing vehicle based on big data according to claim 3, characterized in that, The S3 includes: S31, Input the vibration energy distribution spectrum, the road surface roughness matrix, and the somatosensory discomfort index into the input end of the fuzzy logic model respectively to construct a ternary input variable set; S32, Dynamically allocate the weights of each input variable according to the current driving scenario information by the fuzzy logic rule base to form a normalized weight coefficient set; S33, Calculate and output the comprehensive ride comfort index based on the allocated weight coefficients and the ternary input variables.

5. A method for optimizing the ride comfort of a sightseeing vehicle based on big data according to claim 4, characterized in that, The S4 includes: S41, Optimize variable modeling: Based on the comprehensive ride comfort index , construct a multi-objective optimization model with the suspension damping coefficient , the drive motor torque distribution coefficient and the path planning priority parameter as the optimization variables; S42, Fitness function construction: Based on multi-objective optimization modeling, define the fitness function as the optimization basis for measuring the ride comfort of each parameter combination; S43, Genetic algorithm iterative optimization: Initialize the population and perform iterative search through selection, crossover, and mutation operations, and finally output the optimal parameter combination , and generate a multi-parameter collaborative adjustment instruction set.

6. The optimized method for ride comfort of a sightseeing vehicle based on big data according to claim 5, characterized in that, The S43 uses a genetic algorithm to perform global search optimization on the parameter vector, and the iterative process includes: S431, Population Initialization: Set the population size to , and randomly generate initial individuals, where each individual is a set of control parameter combinations to be optimized ; S432, Fitness Evaluation: Input the individual parameters into the comprehensive ride comfort model to calculate the fitness value , which is used to measure the ride comfort performance of the current combination; S433, Selection operation: According to the fitness level, preferentially select excellent individuals from the current population as the next-generation parents; S434, Crossover operation: Generate new individuals among the parents through the crossover algorithm, expand the search space, and transfer excellent features; S435, Mutation operation: Perturb the newly generated individuals to enhance the global search ability and avoid falling into local optima; S436, Termination determination: When the set iteration times or the fitness convergence condition is reached, end the optimization process; S437, Output result: Extract the optimal parameter combination , and generate an adjustment instruction set including suspension damping coefficient, drive motor torque distribution coefficient, and path planning priority parameter .

7. A method for optimizing the ride comfort of a sightseeing vehicle based on big data according to claim 6, characterized in that, The said S5 includes: S51, Facial expression - Somatosensory correlation verification: Real - time collect passenger facial image data through an in - vehicle camera, use a trained convolutional neural network model to extract facial expression features, and convert them into an emotion score sequence, which is time - synchronized with the somatosensory discomfort index collected by a wearable device and standardized; S52, Fuzzy model weight correction: Dynamically adjust the set value of the somatosensory weight in the fuzzy logic model according to the calculated correlation strength, while maintaining the normalization constraint that the sum of the weights is 1.

8. A method for optimizing the ride comfort of a sightseeing vehicle based on big data according to claim 7, characterized in that, The S51 facial expression-body sensation correlation verification uses an in-vehicle camera to collect passenger facial image data in real time, and extracts facial expression feature vectors through a convolutional neural network model , and combines it with the body sensation discomfort index , and uses the Pearson correlation coefficient to calculate the correlation between the two .

9. A method for optimizing the ride comfort of a sightseeing vehicle based on big data according to claim 7, characterized in that, In the weight correction of the S52 fuzzy logic model, when the correlation coefficient is higher than the set threshold , it is considered that the facial expression can be used as a supplementary index for the somatosensory, and the exponential sliding update method is used to dynamically adjust the somatosensory discomfort weight coefficient in the fuzzy logic model .

10. A smoothness optimization system for a sightseeing vehicle based on big data, which is used to implement a smoothness optimization method for a sightseeing vehicle based on big data as described in any one of claims 1-9, characterized in that, It includes the following modules: Multi - dimensional data acquisition module: Obtain vibration acceleration data, front - road surface image data, and passenger heart rate variability data during the operation of the sightseeing vehicle; Multi - source data fusion and processing module: Extract frequency - domain features from the vibration acceleration data to generate a vibration energy distribution spectrum, perform texture segmentation and pothole identification on the road surface image data to generate a road surface roughness matrix, and perform standardization processing on the heart rate variability data to generate a somatosensory discomfort index; Ride comfort evaluation module: Input the vibration energy distribution spectrum, road surface roughness matrix, and somatosensory discomfort index into the fuzzy logic model, and dynamically allocate parameter weights according to the current driving scenario, and output a comprehensive ride comfort index; Multi - objective optimization control module: Based on the comprehensive ride comfort index, optimize the suspension damping coefficient, drive motor torque distribution coefficient, and path planning priority parameters through a genetic algorithm, and generate a multi - parameter collaborative adjustment instruction set; Closed - loop feedback adaptive module: Collect passenger facial expression data, perform a correlation analysis with the somatosensory discomfort index, and correct the weight distribution rule in the fuzzy logic model according to the analysis result to achieve dynamic optimization.

Images