Variable damping hydro-pneumatic suspension system based on self-organizing mapping algorithm

Abstract

The invention provides a variable damping hydro-pneumatic suspension system based on a self-organizing mapping algorithm, and the system comprises a combined suspension system intelligent control module which comprises a hydraulic cylinder, a proportional valve, a PID controller, an intelligent sensor and an energy accumulator; a damping-adjustable double-axle communicated type hydro-pneumatic suspension module comprises four hydraulic cylinder differential connection structures of a front axle and a rear axle. And the self-adaptive adjustment control module is configured to optimize PID parameters through a self-organizing mapping algorithm and a self-adaptive genetic algorithm so as to adjust the flow of a proportional valve, so that the suspension damping is dynamically controlled. Through an energy accumulator, a proportional valve and a self-organizing mapping algorithm, damping coefficient dynamic adjustment and multi-objective optimization are achieved. According to the system, the smoothness, the stability and the road surface protection performance are remarkably improved while the bearing capacity is guaranteed, and the system is suitable for different heavy-load transportation scenes.

Description

Technical Field

[0001] The present invention belongs to the technical fields such as oil-gas suspension, and particularly relates to a variable-damping oil-gas suspension system based on a self-organizing mapping algorithm. Background Art

[0002] The oil-gas suspension system is a core component for vibration reduction of heavy-duty vehicles. It attenuates vibrations caused by road unevenness through the coupling action of hydraulic pressure and gas. However, the optimization of system performance has long been limited by the stiffness-stability contradiction - reducing the suspension stiffness can improve ride comfort, but it will weaken the body attitude control ability, resulting in increased roll angle, pitch angle and decreased tire adhesion; while increasing the stiffness can enhance stability, but it will exacerbate the transmission of road impacts and affect ride comfort.

[0003] Existing technologies mostly rely on single-parameter adjustment strategies of adjustable dampers, and adjust the damping coefficient through preset rules or simple feedback mechanisms to balance ride comfort and stability. However, such methods expose significant limitations in complex and variable road conditions (such as continuous undulations, mixed obstacle scenarios): First, the environmental adaptability is insufficient, and it is difficult to dynamically respond to the random vibration characteristics of unstructured roads (such as gravel, muddy roads), and it is easy to have adjustment lags or overshoots; Second, the multi-objective coordination ability is weak, and the coupling conflicts of indicators such as ride comfort, stability and road friendliness are difficult to achieve global optimization through single-parameter adjustment; Third, the real-time performance is limited, and the ability to quickly process high-frequency vibration signals and make real-time decisions is insufficient, resulting in the control instruction update rate being difficult to match the actual requirements. Summary of the Invention

[0004] Aiming at the defects and deficiencies of the above-mentioned existing technologies, the purpose of the present invention is to optimize the oil-gas suspension of the heavy-duty vehicle chassis and improve the ride comfort and road friendliness of the heavy-duty vehicle. The present invention combines a self-organizing mapping algorithm and an adaptive genetic algorithm to solve and optimize servo parameters in real time, and thus controls the oil flow of the proportional valve through a PID controller to adjust the damping of the suspension system, so as to change the adaptability of the suspension to different roads, enable the suspension system to better adapt to the complex working environment of heavy-duty vehicles, and improve the ride comfort and road friendliness of heavy-duty vehicles to meet the comfort requirements. It realizes dynamic adjustment of the damping coefficient and multi-objective optimization through an accumulator, a proportional valve and a self-organizing mapping algorithm. While ensuring the load-bearing capacity, this system significantly improves ride comfort, stability and road protection performance, and is applicable to different heavy-duty transportation scenarios.

[0005] The technical solution specifically adopted by the present invention to solve its technical problems is:

[0006] A variable-damping oil-gas suspension system based on a self-organizing mapping algorithm, comprising:

[0007] An intelligent control module for a combined suspension system, comprising: a hydraulic cylinder, a proportional valve, a PID controller, an intelligent sensor and an accumulator;

[0008] Damping adjustable double - bridge connected oil - gas suspension module, including: damping adjustable front - bridge connected oil - gas suspension, damping adjustable rear - bridge connected oil - gas suspension, differential hydraulic cylinder connection structure between the front axle and the rear axle;

[0009] Adaptive adjustment control module, configured to optimize the PID parameters through self - organizing mapping algorithm and adaptive genetic algorithm to adjust the flow rate of the proportional valve, thereby dynamically controlling the suspension damping.

[0010] Further, in the differential hydraulic cylinder connection structure, the structures of the front axle and the rear axle are the same, and a total of 4 hydraulic cylinders of the front axle and the rear axle form a differential connection:

[0011] The structure of the front axle is the same as that of the rear axle, and the adopted structure is:

[0012] Two hydraulic cylinders form a differential circuit through a proportional valve;

[0013] The A port and B port of the proportional valve are respectively connected to the rodless cavity and the rod - end cavity of the corresponding side hydraulic cylinder;

[0014] The differential hydraulic cylinder connection structure between the front axle and the rear axle is symmetric and consistent and forms a differential connection.

[0015] Taking the front - axle structure as an example:

[0016] In the differential hydraulic cylinder connection structure:

[0017] Two hydraulic cylinders of the front axle form a differential circuit through proportional valves SV1 and SV2.

[0018] The A port and B port of the proportional valve SV1 are respectively connected to the rodless cavity and the rod - end cavity of the left - hand hydraulic cylinder of the front axle;

[0019] The A port and B port of the proportional valve SV2 are respectively connected to the rodless cavity and the rod - end cavity of the right - hand hydraulic cylinder of the front axle;

[0020] The differential hydraulic cylinder connection structure between the front axle and the rear axle is symmetric and consistent, and the hydraulic cylinders of the front and rear axles form a differential connection.

[0021] Further, the intelligent sensor in the rodless cavity of the hydraulic cylinder feeds back the pressure signal to the PID controller in real - time;

[0022] The output end of the PID controller is connected to the proportional valve electrical signal interface, and controls the hydraulic oil flow rate by adjusting the displacement direction and opening of the valve core;

[0023] The rodless cavities of the left - hand and right - hand hydraulic cylinders of the front axle and the rear axle are independently connected to intelligent sensors, forming a dual - channel feedback loop;

[0024] The accumulator is connected to the P port of the proportional valve through a pipeline, and is used to buffer hydraulic shock and maintain the stability of the circuit pressure.

[0025] Further, the adaptive adjustment control module performs the following steps:

[0026] Input Gaussian white noise functions with different amplitudes into the road surface spectrum model to generate multi-level road surface simulation curves;

[0027] Input the multi-level road surface simulation curves into the damping adjustable double-bridge module to obtain the corresponding ride comfort parameters and road friendliness related indicators;

[0028] Input the parameters into the self-organizing mapping model for unsupervised clustering training to generate the optimal parameter mapping relationship at different vibration frequencies;

[0029] Iteratively screen the PID parameter combinations through the adaptive genetic algorithm, and dynamically adjust the proportional valve flow rate to adapt to complex road conditions.

[0030] Further, the mathematical expression of the road surface spectrum model is:

[0031]

[0032] In the formula: S q (n0) is the road surface unevenness coefficient; n0 is the standard spatial frequency; W(t) is the Gaussian white noise function with different amplitudes; v0 is the vehicle driving speed; n c is the lower cut-off frequency of the road surface space, n c = 0.01m -1 ; B is the wheelbase on both sides; L is the distance between the front and rear axles; x1, x2, x3, x4 are intermediate state variables;

[0033] Further, the training of the self-organizing mapping algorithm includes:

[0034] Perform amplitude normalization processing on the input curve;

[0035] Calculate the distance between the input curve and the neuron weight vector through the Euclidean distance formula:

[0036]

[0037] Among them, x i is the i-th road surface curve vector, w jk is the neuron weight vector at the grid position (j,k);

[0038] Select the neuron with the minimum distance as the best matching unit, and update the weight vectors of the best matching unit and its neighborhood neurons;

[0039] The adaptive genetic algorithm includes:

[0040] Randomly extract individuals from the parameter library after self-organizing mapping model training to generate an initial population;

[0041] Select the individual with the highest fitness through the elitist retention selection strategy;

[0042] Decode the optimal individual to obtain the PID parameter combination.

[0043] Further, the output current I of the PID controller satisfies:

[0044]

[0045] where e is the deviation between the pressure feedback by the intelligent sensor and the target value, K p , K i , K d are the proportional, integral, and differential gains respectively, which are optimized by the genetic algorithm.

[0046] Further, the relationship between the flow rate Q of the proportional valve and the driving current I is:

[0047] Q = K v ·I

[0048] where K v is the flow rate gain coefficient of the proportional valve.

[0049] Further, in the differential hydraulic cylinder structure of the front axle and the rear axle:

[0050] The cylinder block of the hydraulic cylinder is hinged to the axle, and the hydraulic rod is rigidly fixed to the vehicle chassis;

[0051] The accumulator is connected to the P port of the proportional valve through a pipeline.

[0052] Further, the unevenness coefficient S q (n0) of the road surface spectrum model is determined according to the geometric average value of each level of road surface.

[0053] Compared with the prior art, the present invention and its preferred solutions can more accurately simulate the situation of a heavy-duty vehicle during actual driving through the intelligent control module of the combined suspension system, adjust the oil flow rate of the proportional valve in real time to change the damping of the oil-gas suspension system, and combine the adaptive adjustment control algorithm to more conveniently and specifically search for the best servo parameter combination to help the heavy-duty vehicle adapt to different driving environments, so as to meet the adaptability of the oil-gas suspension to different road surfaces, enable the suspension system to better adapt to the complex working environment of the heavy-duty vehicle, and improve the ride comfort and road friendliness of the heavy-duty vehicle in real time to meet the comfort requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The present invention will be further described in detail below in conjunction with the drawings and specific embodiments:

[0055] Figure 1 Schematic diagram of the process for building a four-wheel road surface spectrum model for the embodiments of the present invention.

[0056] Figure 2 Schematic diagram of the structure of the intelligent control module of the combined suspension system built for the embodiments of the present invention.

[0057] Figure 3 Schematic diagram of the process of the control method for the embodiments of the present invention. Detailed implementation manners

[0058] To make the features and advantages of this patent more obvious and understandable, specific embodiments are given below and described in detail as follows:

[0059] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanations for this application. Unless otherwise specified, all technical and scientific terms used in this specification have the same meanings as those commonly understood by those of ordinary skill in the technical field to which this application belongs.

[0060] It should be noted that the terms used herein are only for describing specific implementation manners and are not intended to limit the exemplary embodiments according to this application. As used herein, unless the context clearly indicates otherwise, the singular forms are also intended to include the plural forms. In addition, it should also be understood that when the terms "include" and / or "comprise" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0061] As Figure 2 shown, the overall solution of the embodiments of the present invention is built based on the following framework of a variable-damping oil-gas suspension system based on the self-organizing mapping algorithm:

[0062] This system framework includes:

[0063] An intelligent control module for the combined suspension system, which is used to automatically adjust the suspension servo parameters according to the road surface conditions;

[0064] A damping-adjustable double-bridge connected oil-gas suspension module: used to generate servo parameters under different excitation signals;

[0065] An adaptive adjustment control module: used to obtain the optimal servo parameters under different excitation signals.

[0066] As a more specific implementation manner:

[0067] The intelligent control module of the combined suspension system includes an accumulator, a hydraulic cylinder, a proportional valve, a PID controller, an intelligent sensor, and a control circuit. Among them, the external excitation signal is transmitted to the hydraulic cylinder, and the intelligent sensor on the rodless chamber of the hydraulic cylinder returns the signal to the input end of the PID controller. The output end of the PID controller is connected to the electrical signal interface of the proportional valve. The PID controller controls the movement of the spool of the proportional valve through the control circuit to change the flow direction and flow rate of the hydraulic oil. The A port of the proportional valve is connected to the rodless chamber of the hydraulic cylinder, the B port of the proportional valve is connected to the rod chamber of the hydraulic cylinder, the P port of the proportional valve is connected to the accumulator, and the P port of the proportional valve SV1 is connected to the T port of the proportional valve SV2.

[0068] The damping adjustable double-bridge connected oil-gas suspension module includes a hydraulic cylinder, an accumulator, and a proportional valve. Among them, considering that the hydraulic systems in the front axle and the rear axle are the same, the embodiment of the present invention only specifically describes the front axle hydraulic system: The front axle hydraulic system model is composed of core components such as a suspension hydraulic cylinder, an accumulator, a proportional valve, and hydraulic pipelines. In the front axle hydraulic system, the hydraulic cylinder is connected to the axle, the hydraulic rod in the hydraulic cylinder is connected to the chassis, and the two hydraulic cylinders are connected through pipelines and a proportional valve to form a differential connection. The accumulator is connected to the P port of the proportional valve, and the tire can be simplified as a linear spring-damper system.

[0069] The adaptive adjustment control module includes a PID controller, an intelligent sensor, a control circuit, and a proportional valve. Among them, the inputs of the intelligent sensors F N1 、F N2 are respectively connected to the rodless chambers of the two hydraulic cylinders, and their outputs are respectively connected to the input ends of the PID1 controller and the PID2 controller. The output ends of the PID1 controller and the PID2 controller are connected to the electrical signal interfaces of the proportional valves SV1 and SV2. The PID controller adjusts the flow direction, size, and direction of the hydraulic oil of the proportional valve through electrical signals, so as to change the damping of the oil-gas suspension system.

[0070] On the basis of this system framework, as another core of the solution of this embodiment, a control method for a variable damping oil-gas suspension system based on the self-organizing mapping algorithm is provided, including the following steps:

[0071] Step S1, input Gaussian white noise functions with different amplitudes into the road surface spectrum model, and calculate multi-level road surface simulation curves;

[0072] Step S2, input the multi-level road surface simulation curves into the damping adjustable double-bridge connected oil-gas suspension module to initially obtain the corresponding ride comfort and road friendliness parameters;

[0073] Step S3, import the initially obtained ride comfort and road friendliness parameters into the self-organizing mapping model for training, and calculate the optimal ride comfort and road friendliness parameters at different vibration frequencies;

[0074] Step S4: Use the adaptive genetic algorithm to search for the optimal PID controller parameters under the optimal solutions of the ride comfort and road friendliness parameters, and then calculate the flow rate of the proportional valve.

[0075] Among them, the road friendliness parameter is generally indirectly characterized by the pressure fluctuation characteristics of the rodless cavity of the hydraulic cylinder, and its physical meaning is the impact degree of the suspension system on the road surface. Specifically, the smaller the pressure fluctuation amplitude and the more uniform the frequency distribution, the smoother the dynamic load transfer of the suspension to the road surface, and the better the road friendliness.

[0076] As a preferred solution of this embodiment, in step S1, as Figure 1 shown, in the road surface spectrum model, the vertical vibration frequency of the road surface input is simulated by the Gaussian white noise function. Through the road surface spectrum model, the time-domain curve of the vertical vibration frequency of each of the four wheels of the vehicle with respect to time (the degree of road surface bumpiness), that is, the multi-level road surface simulation curve, is obtained through the state equation change. Its mathematical model is as follows:

[0077] Unevenness coefficient of each level of road surface

[0078]

[0079]

[0080] In the formula: S q (n0) is the unevenness coefficient of the road surface, and its value is shown as the geometric mean in the above table; n0 is the standard spatial frequency, n0 = 0.1m -1 ; W(t) is the Gaussian white noise function with different amplitudes; v0 is the vehicle driving speed; n c is the lower cut-off frequency of the road surface space, n c = 0.01m -1 ; B is the wheelbase on both sides; L is the distance between the front and rear axles; x1, x2, x3, x4 are intermediate state variables.

[0081] As a preferred solution of this embodiment, the self-organizing mapping model training method in step S3 is as follows:

[0082] Step S 31 , normalize each curve to eliminate the influence of the amplitude difference of different road surface grades on the distance calculation;

[0083] Step S 32 , randomly initialize the weight vector of each neuron on the grid, and each neuron represents a grid cell;

[0084] Step S 33 , use the Euclidean formula to calculate the distance between the input road surface simulation curve and the weight vector of each neuron, and select the neuron with the closest distance as the optimal neuron;

[0085] Step S 34 , update the weight vector of the optimal neuron and the sample vector to make the distance between them the closest;

[0086] Step S 35 , according to the position of the optimal neuron and the neighborhood function, update the weight vectors of other adjacent neurons to make the remaining neurons also approach the optimal neuron;

[0087] Step S 36 , repeat Step S 33 to Step S 35 , until the preset number of rounds is reached.

[0088] As a preferred solution of this embodiment, the steps of the adaptive genetic algorithm in Step S4 are as follows:

[0089] Step S 41 , perform digital serial number encoding on all samples as genetic encoding;

[0090] Step S 42 , randomly extract from the sample library generated in Step S3, extract a individuals each time, and extract b times in total to generate an initial population containing b individuals;

[0091] Step S 43 , decode the individual coding string, obtain the phenotype of the individual and calculate the objective function value of the individual, and find the fitness of the individual according to the conversion rule;

[0092] Step S 44 , expand and eliminate the initial population, continuously screen through the best retention selection to obtain the optimal population, and select the optimal sample of the final individual in the optimal population as the final servo parameter.

[0093] After solving the optimal ride comfort and road friendliness parameters, dynamically adjust the proportional valve drive current through the PID control algorithm Further calculate the proportional valve flow Q (Q = K v ·I), where K p , K i , K d are the proportional, integral, and differential gains respectively, and K v is the flow gain, thereby improving the performance of the heavy vehicle oil-gas suspension.

[0094] On the basis of the above design, as Figure 3 shown, obtain the control method flow of the preferred final variable oil-gas suspension system based on the self-organizing mapping algorithm in this embodiment, including the following steps:

[0095] In the first step, Gaussian white noise functions with different amplitudes are input into the road surface spectrum model to calculate multi-level road surface simulation curves;

[0096] In the second step, the multi-level road surface simulation curves are input into the damping-adjustable double-bridge connected oil-gas suspension module to preliminarily obtain the corresponding ride comfort and road friendliness parameters;

[0097] In the third step, the input multiple road surface simulation curves are normalized to eliminate the amplitude differences between different road levels to ensure the fairness of distance calculation; subsequently, the weight vectors of each neuron in the two-dimensional grid are randomly initialized and given initial values with the same dimension as the input data; in the iterative training stage, for each road surface curve, the Euclidean distance between it and all neuron weight vectors is calculated, and the neuron with the smallest distance is selected as the best matching unit, and the weight vector of the BMU is adjusted based on this sample to reduce the distance. At the same time, the weights of the neurons around the BMU are co-updated according to the neighborhood function, so that the road surface features with similar topology gradually gather in the grid; through multiple rounds of iteration, a low-dimensional mapping that preserves the spatial distribution characteristics of the high-dimensional data is finally formed, realizing the clustering analysis and visual expression of road surface features at different levels, and calculating the optimal ride comfort and road friendliness parameters at different vibration frequencies.

[0098] In the fourth step, an initial population is constructed by encoding the samples with digital serial numbers. After calculating the individual fitness through decoding, the best-preserved selection strategy is used to iteratively execute population expansion and elimination. Finally, the optimal solution of the servo parameters is optimized and selected, and the PID control parameters under this set of parameters are calculated. The proportional valve drive current is dynamically adjusted through the PID control algorithm. Furthermore, the flow rate Q of the proportional valve is calculated (Q = K v ·I), where K p , K i , K d are the proportional, integral, and differential gains respectively, and K v is the flow rate gain, thereby improving the performance of the oil-gas suspension of heavy-duty vehicles.

[0099] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention shall have the ordinary meanings understood by those of ordinary skill in the field to which the present invention pertains. The "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. Words such as "comprising" or "including" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. Words such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Upper", "lower", "left", "right", etc. are only used to indicate relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0100] As described above, the above are only preferred embodiments of the present invention, and are not limitations on the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes. However, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the technical solution content of the present invention still fall within the protection scope of the technical solution of the present invention.

[0101] This patent is not limited to the above best mode. Anyone inspired by this patent can obtain various other forms of a variable damping oil-gas suspension system based on the self-organizing mapping algorithm. All equal changes and modifications made according to the scope of the patent application of the present invention shall fall within the scope covered by this patent.

Claims

1. A variable damping oil-gas suspension system based on a self-organizing map algorithm, characterized in that: include: Intelligent control module of the combined suspension system, including: hydraulic cylinder, proportional valve, PID controller, intelligent sensor and accumulator; A damping-adjustable dual-axle interconnected oil-gas suspension module, comprising: a damping-adjustable front-axle interconnected oil-gas suspension, a damping-adjustable rear-axle interconnected oil-gas suspension, and a differential hydraulic cylinder connection structure between the front axle and the rear axle; The adaptive adjustment control module is configured to optimize PID parameters through a self-organizing map algorithm and an adaptive genetic algorithm to adjust the proportional valve flow, thereby dynamically controlling the suspension damping.

2. The variable damping oil-pneumatic suspension system based on the self-organizing map algorithm according to claim 1 is characterized in that: The front axle structure is the same as the rear axle structure, and the structures adopted are: The two hydraulic cylinders form a differential circuit through a proportional valve; The A port and the B port of the proportional valve are respectively connected to the rodless chamber and the rod chamber of the hydraulic cylinder on the corresponding side; The differential hydraulic cylinder connection structures of the front axle and the rear axle are symmetrical and consistent and form a differential connection.

3. The variable damping oil-gas suspension system based on the self-organizing map algorithm according to claim 1 is characterized in that: The intelligent sensor of the rodless chamber of the hydraulic cylinder feeds back the pressure signal to the PID controller in real time; The output end of the PID controller is connected to the electrical signal interface of the proportional valve, and the flow rate of the hydraulic oil is controlled by adjusting the displacement direction and opening of the valve core; The rodless chambers of the left and right hydraulic cylinders of the front and rear axles are independently connected to intelligent sensors to form a dual-channel feedback loop; The accumulator is connected to the P port of the proportional valve through a pipeline to buffer the hydraulic shock and maintain the circuit pressure stable.

4. The variable damping oil-pneumatic suspension system based on the self-organizing map algorithm according to claim 1 is characterized in that: The adaptive regulation control module performs the following steps: Gaussian white noise functions of different amplitudes are input into the road surface spectrum model to generate a multi-level road surface simulation curve; Input the multi-level road simulation curve into the damping adjustable double bridge module to obtain corresponding smoothness parameters and road friendliness related indicators; The parameters are input into a self-organizing map model for unsupervised clustering training to generate optimal parameter mapping relationships under different vibration frequencies; The PID parameter combination is iteratively screened through an adaptive genetic algorithm, and the proportional valve flow is dynamically adjusted to adapt to complex road conditions.

5. The variable damping oil-pneumatic suspension system based on the self-organizing map algorithm according to claim 4 is characterized in that: The mathematical expression of the road surface spectrum model is: Where: S q (n0) is the road roughness coefficient; n0 is the standard spatial frequency; W(t) is the Gaussian white noise function with different amplitudes; v0 is the vehicle speed; n c is the cut-off frequency in road space, n c =0.01m -1 ; B is the wheelbase on the left and right sides; L is the front and rear bridge distance; x1, x2, x3, x4 are intermediate state variables.

6. The variable damping oil-pneumatic suspension system based on the self-organizing map algorithm according to claim 4 is characterized in that: The training of the self-organizing map algorithm includes: Perform amplitude normalization on the input curve; The distance between the input curve and the neuron weight vector is calculated using the Euclidean distance formula: Among them, x i is the i-th road curve vector, w jk is the neuron weight vector at grid position (j,k); Select the neuron with the smallest distance as the best matching unit, and update the weight vector of the best matching unit and its neighboring neurons; The adaptive genetic algorithm comprises: Randomly extract individuals from the parameter library after the self-organizing map model is trained to generate the initial population; The individuals with the highest fitness are selected through the best retention selection strategy; The optimal individual is decoded to obtain the PID parameter combination.

7. The variable damping oil-pneumatic suspension system based on the self-organizing map algorithm according to claim 1 is characterized in that: The PID controller output current I satisfies: Where, e is the deviation between the feedback pressure of the intelligent sensor and the target value, K p , K i , K d are proportional, integral and differential gains respectively, which are obtained by genetic algorithm optimization.

8. The variable damping oil-pneumatic suspension system based on the self-organizing map algorithm according to claim 1 is characterized in that: The relationship between the proportional valve flow rate Q and the drive current I is: Q=K v ·I Among them, K v is the flow gain coefficient of the proportional valve.

9. The variable damping oil-pneumatic suspension system based on the self-organizing map algorithm according to claim 2 is characterized in that: In the differential hydraulic cylinder structure of the front axle and the rear axle: The cylinder body of the hydraulic cylinder is hinged to the axle, and the hydraulic rod is rigidly fixed to the vehicle chassis; The accumulator is connected to the P port of the proportional valve through a pipeline.

10. The variable damping oil-pneumatic suspension system based on the self-organizing map algorithm according to claim 4, characterized in that: The roughness coefficient S of the road spectrum model q (n0) is determined based on the geometric mean of each level of road surface.

Images