Automobile sunroof sealing strip self-adapting adjustment method and device based on smart material

Abstract

The application provides a smart material-based sunroof sealing strip adaptive adjustment method and device, and relates to the technical field of sealing adjustment. The method comprises the following steps: performing driving mode identification, and activating an adaptive adjustment channel; activating a collection sensor, establishing a perception state set, converting the perception state set into a fusion state vector, and sending the fusion state vector to an adaptive adjustment channel adaptive comparison layer to generate a first adjustment influence factor; reading navigation data and driving behavior data, performing adjustment demand prediction, and establishing a second adjustment influence factor; and generating an adaptive adjustment scheme after compensating the adjustment layer of the adaptive adjustment channel by using the first adjustment influence factor and the second adjustment influence factor. The application solves the technical problem that the sealing effect is unstable and air leakage and water seepage are prone to occur because the current sealing strip cannot automatically adjust the pressing force according to the change of the environment, and improves the sealing effect of the sealing strip by adaptively controlling the sealing property of the smart material according to the change of the external environment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sealing adjustment, and particularly relates to a self-adaptive adjustment method and device for a sunroof sealing strip based on intelligent materials. BACKGROUND

[0002] At present, the sunroof sealing strip of a vehicle is usually in a fixed form, and once installed, it depends on the elasticity and shape of the sealing strip material. However, this design can provide a certain sealing effect, but cannot self-adjust under different environmental conditions (such as temperature changes, humidity changes, etc.), especially in different seasons or extreme weather conditions. The sealing strip will become hard or soft, resulting in a decrease in sealing effect, and the occurrence of air leakage or water seepage, thereby affecting the air quality in the vehicle, and also causing other problems in the vehicle interior, such as an increase in noise and a decrease in comfort in the vehicle. In addition, with the passage of time, the traditional sealing strip will harden, age or crack due to long-term exposure to ultraviolet rays, extreme weather or high-temperature environments, resulting in a gradual weakening of the sealing effect of the sealing strip, and the occurrence of problems such as noise and water seepage.

[0003] In summary, in the prior art, there is a technical problem that the sealing effect is unstable and air leakage or water seepage is prone to occur due to the fact that the sealing strip cannot automatically adjust its compression force according to environmental changes. SUMMARY

[0004] The purpose of the present application is to provide a self-adaptive adjustment method and device for a sunroof sealing strip based on intelligent materials, so as to solve the technical problem in the prior art that the sealing effect is unstable and air leakage or water seepage is prone to occur due to the fact that the sealing strip cannot automatically adjust its compression force according to environmental changes.

[0005] In view of the above problems, the present application provides a self-adaptive adjustment method and device for a sunroof sealing strip based on intelligent materials.

[0006] In a first aspect, the application provides a smart material-based sunroof sealing strip adaptive adjustment method, which is realized by a smart material-based sunroof sealing strip adaptive adjustment device. The method comprises the following steps: after the system is started, a vehicle-mounted controller is initialized, a driving mode is identified by the vehicle-mounted controller, and an adaptive adjustment channel corresponding to the driving mode is activated; based on the driving mode identification result, a collection sensor is activated, and after the collection accuracy of the collection sensor is configured, multi-source data collection is performed, a perception state set is established, and the perception state set comprises sealing strip state data, in-vehicle environment data, and external environment data; after the perception state set is converted into a fusion state vector, the fusion state vector is sent to an adaptive adjustment channel adaptive comparison layer, and a first adjustment influence factor is generated by the adaptive comparison layer; navigation data and driving behavior data are read by the vehicle-mounted controller, adjustment demand prediction is performed based on the navigation data and the driving behavior data, and a second adjustment influence factor is established; after the first adjustment influence factor and the second adjustment influence factor are used to compensate the adjustment layer of the adaptive adjustment channel, an adaptive adjustment scheme is generated based on the fusion state vector.

[0007] Optionally, the driving mode comprises a sports mode, a normal mode, a kinetic energy recovery mode, and a parking mode.

[0008] Optionally, a rule matching module of the adaptive comparison layer is called to perform adaptive preliminary screening of the fusion state vector, and an abnormality screening result is established; the abnormality screening result is synchronized to a deep decision evaluation module to perform adaptive analysis under the constraints of pressure, response rate, adhesion priority, and energy consumption, and the first adjustment influence factor is established.

[0009] Optionally, road condition information is called based on the navigation data, a real-time road condition position is taken as a reference road condition, an incremental road condition database is established, external environment data is called, weather perception prediction is performed, and a perception prediction result is established; the incremental road condition database, the perception prediction result, and the driving behavior data are used to perform adjustment demand prediction.

[0010] Optionally, a mutation time sequence node is established by using the incremental road condition database and the perception prediction result; a sensitive analysis of wind pressure adaptation is performed by using the driving behavior data to generate a driving behavior enhancement factor; a mutation response window is constructed based on the driving behavior enhancement factor and the mutation time sequence node, and adjustment demand prediction is completed by using the mutation response window.

[0011] Optionally, it is judged whether the response node of the mutation response window in the second adjustment influence factor exceeds the stable adjustment period; if the response node of the mutation response window exceeds the stable adjustment period, a temporary punishment factor is activated, the second adjustment influence factor is punished by using the temporary punishment factor, and the compensation of the adjustment layer is completed.

[0012] Optionally, a target function is established, the evaluation features of the target function include pressure stability features, energy consumption features, response time features, and fitting degree features; the first adjustment influence factor is called to adjust the priority and the expected value of the target function, the first compensation is completed; the second adjustment influence factor is called to adjust the weight factor of the target function, the second compensation is completed; after the compensation of the target function in the adjustment layer is completed by using the first compensation and the second compensation, the adjustment action optimization is executed, and the adaptive adjustment scheme is generated.

[0013] Optionally, a control variable space is established, the control variables in the control variable space include driving voltage, driving duration, driving frequency, and partition excitation strategy; after the initial control data is established based on the control variable space, the control adaptation analysis is performed by using the compensated target function, and the search iteration is executed; the adaptive adjustment scheme is generated by using the search iteration result.

[0014] Optionally, the in-vehicle pressure value, the energy consumption data, and the fitting state image after adjustment are obtained in real time by using the acquisition sensor, and real-time adjustment feedback data is constructed; the achievement verification of the real-time adjustment feedback data is performed based on the expected index, and the correction feedback is established according to the achievement verification result.

[0015] In a second aspect, the application also provides a smart material-based sunroof sealing strip adaptive adjustment device for executing the smart material-based sunroof sealing strip adaptive adjustment method of the first aspect, wherein the smart material-based sunroof sealing strip adaptive adjustment device comprises: a driving mode recognition module, configured to perform vehicle-mounted controller initialization after system startup, perform driving mode recognition by using the vehicle-mounted controller, and activate an adaptive adjustment channel mapped with the driving mode; a perception state acquisition module, configured to activate a collection sensor according to a driving mode recognition result, configure collection accuracy of the collection sensor, perform multi-source data collection, and establish a perception state set after the collection sensor is configured with the collection accuracy, wherein the perception state set comprises sealing strip state data, in-vehicle environment data, and external environment data; a first influence factor module, configured to send the perception state set to an adaptive adjustment channel adaptive comparison layer after the perception state set is converted into a fusion state vector, and generate a first adjustment influence factor by the adaptive comparison layer; a second influence factor module, configured to read navigation data and driving behavior data by the vehicle-mounted controller, perform adjustment demand prediction according to the navigation data and the driving behavior data, and establish a second adjustment influence factor; and an adaptive adjustment module, configured to generate an adaptive adjustment scheme based on the fusion state vector after compensating an adjustment layer of the adaptive adjustment channel by using the first adjustment influence factor and the second adjustment influence factor.

[0016] The one or more technical solutions provided in the application have at least the following beneficial effects:

[0017] By performing vehicle-mounted controller initialization after system startup, performing driving mode recognition by using the vehicle-mounted controller, and activating an adaptive adjustment channel mapped with the driving mode according to a driving mode recognition result, configuring collection accuracy of a collection sensor, performing multi-source data collection, and establishing a perception state set after the collection sensor is configured with the collection accuracy, wherein the perception state set comprises sealing strip state data, in-vehicle environment data, and external environment data, converting the perception state set into a fusion state vector, sending the fusion state vector to an adaptive adjustment channel adaptive comparison layer, and generating a first adjustment influence factor by the adaptive comparison layer, reading navigation data and driving behavior data by the vehicle-mounted controller, performing adjustment demand prediction according to the navigation data and the driving behavior data, and establishing a second adjustment influence factor, and generating an adaptive adjustment scheme based on the fusion state vector after compensating an adjustment layer of the adaptive adjustment channel by using the first adjustment influence factor and the second adjustment influence factor, that is, introducing smart materials, accurately adjusting the shape, hardness, and compression force according to real-time environment and driving mode by means of electric heating or voltage control of the driving voltage, automatically adapting to external environment changes, ensuring that the sunroof sealing performance can remain stable under various weather conditions, reducing air and water leakage, and improving the sealing effect of the sealing strip and the in-vehicle comfort.

[0018] The above description is only a summary of the technical solutions of the present application. In order to enable one skilled in the art to better understand the technical means of the present application, the specific embodiments of the present application can be implemented according to the content of the description, and in order to enable the above and other purposes, characteristics and advantages of the present application to be more apparent and easy to understand, the following specific embodiments of the present application are described. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only exemplary, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of the provided drawings.

[0020] Figure 1 The flowchart of the self-adaptive adjustment method of the automobile sunroof sealing strip based on intelligent material of the present application.

[0021] Figure 2 The structural schematic diagram of the self-adaptive adjustment device of the automobile sunroof sealing strip based on intelligent material of the present application.

[0022] Explanation of reference numerals: driving mode recognition module 11, perception state acquisition module 12, first influence factor module 13, second influence factor module 14, self-adaptive adjustment module 15. DETAILED DESCRIPTION

[0023] The present application provides a self-adaptive adjustment method and device of automobile sunroof sealing strip based on intelligent material, which solves the technical problem in the prior art that the sealing effect is unstable and wind leakage and water leakage are prone to occur because the current sealing strip cannot automatically adjust its compression force according to environmental changes. By introducing intelligent material and through electric heating or voltage control means of driving voltage, the shape, hardness and compression force are accurately adjusted according to real-time environment and driving mode, the external environmental changes are automatically adapted, the sealing performance of the vehicle window can be kept stable under various weather conditions, the problems of wind leakage and water leakage are reduced, and the sealing effect of the sealing strip and the comfort in the vehicle are improved.

[0024] Below, the technical solutions in the present application will be described clearly and completely with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application. In addition, it should be noted that, for the convenience of description, only parts related to the present application are shown in the drawings, not all.

[0025] Embodiment one, please refer to the attached Figure 1 The present application provides a smart material-based sunroof sealing strip adaptive adjustment method, wherein the smart material-based sunroof sealing strip adaptive adjustment method is executed by a smart material-based sunroof sealing strip adaptive adjustment device, and the smart material-based sunroof sealing strip adaptive adjustment method specifically includes the following steps:

[0026] S100: After the system is started, the vehicle-mounted controller is initialized, the driving mode recognition is performed by using the vehicle-mounted controller, and the adaptive adjustment channel mapped with the driving mode is activated.

[0027] The driving mode includes a sports mode, a normal mode, a kinetic energy recovery mode, and a parking mode.

[0028] Specifically, after the system is started, the vehicle-mounted controller is initialized to prepare to start the adaptive adjustment system. The initialization includes starting the vehicle-mounted computing unit, configuring the internal hardware, ensuring that all sensors, actuators, and control modules are operating normally, and ensuring that the entire vehicle system is working normally. The vehicle-mounted controller is the core control unit in the car for performing various tasks, responsible for processing signals from different sensors and systems, and executing corresponding control instructions according to preset algorithms.

[0029] Through the vehicle-mounted controller, the current mode of the vehicle is determined based on sensor data (such as acceleration, vehicle speed, steering angle, pressure of the accelerator and brake pedals, etc.), that is, the driving state of the vehicle is judged, so as to identify the current driving mode. For example, under high-speed driving, sharp steering, and heavy accelerator pedal stepping, the vehicle-mounted controller will identify the vehicle as a sports mode; when driving smoothly, it is identified as a normal mode; when the vehicle is braking and the vehicle is at low speed, it may be identified as a kinetic energy recovery mode; when the vehicle is completely stationary, it is identified as a parking mode.

[0030] Driving mode is a kind of different operation mode set by vehicle according to different driving needs, including sports mode, normal mode, kinetic energy recovery mode and parking mode. Each mode will change some parameters of the vehicle, such as power distribution, suspension stiffness, throttle response, etc., to provide different driving experience. In sports mode, the power system of the vehicle will be adjusted to high performance mode, usually providing higher power output, harder suspension and more sensitive brake feedback, suitable for high-speed driving; normal mode is the standard driving mode; kinetic energy recovery mode recovers the energy generated during braking process through brake to enhance the auxiliary system of vehicle power; parking mode is when the vehicle is parked, the vehicle will enter low power consumption mode to reduce energy consumption and ensure stable parking.

[0031] According to the identified driving mode, the adaptive adjustment channel mapped with the identified mode is activated to adjust the performance of the sealing strip, such as compression force, shape and hardness. For example, in sports mode, the driving voltage is prompted to generate heat, causing the sealing strip of smart material to become soft and easy to deform, increasing the contact area and compression force between the sealing strip and the window frame, preventing the increase of wind noise during high-speed driving. By adjusting various functions according to different driving modes, it ensures that the driver and passengers can obtain the most comfortable experience in different scenarios, while providing better vehicle stability and safety in extreme driving conditions.

[0032] S200: After activating the collection sensor according to the driving mode recognition result and configuring the collection accuracy of the collection sensor, multi-source data collection is performed to establish a perception state set, which includes sealing strip state data, in-vehicle environment data and external environment data.

[0033] Specifically, according to the driving mode recognition result, the corresponding collection sensor is activated, including environmental sensors (such as temperature, humidity, air quality sensors), mechanical sensors (such as pressure, deformation sensors) and electrical sensors (such as battery power, energy recovery efficiency sensors), and the corresponding sensor collection accuracy is configured, that is, the collection accuracy of the sensor is adjusted according to the data accuracy required by the driving mode. For example, in sports mode, sealing strip compression force sensor, suspension state sensor, etc. are needed to ensure the maneuverability and comfort of the vehicle, and high-precision data is also needed to accurately adjust the sealing strip; in kinetic energy recovery mode, more sensors about battery state and energy recovery efficiency are needed to be activated; in parking mode, external environment sensors are needed to monitor whether there is heavy rain that needs to be avoided to prevent water seepage, and the collection accuracy can be reduced to save computing resources and improve response speed.

[0034] The prepared sensor is started to collect multi-source data, and the collection data of multiple sensors are obtained, a perception state set is established, including seal strip state data (such as seal strip compression force, hardness, shape change, etc.), in-vehicle environment data (such as in-vehicle temperature, humidity, air quality, etc.), and external environment data (such as external temperature, humidity, wind speed, etc.). For example, when the vehicle is in a moving mode, the seal strip pressure sensor is activated to monitor the compression force of the seal strip; the in-vehicle temperature and humidity sensor is activated to obtain the in-vehicle environment; and the external environment sensor (such as temperature, humidity, and wind speed) is activated to obtain real-time external environment data. The accuracy of the seal strip sensor is improved to ensure that the pressure change is accurate to 0.1N; the accuracy of the in-vehicle environment sensor is set to decimal level accuracy, which is sufficient to provide comfort data; and the accuracy of the external environment sensor is set to integer set accuracy, which is used for environmental adaptability adjustment. Real-time data are obtained from all activated sensors, including a seal strip pressure of 8N, an in-vehicle temperature of 22.5℃, an external temperature of 30℃, and a wind speed of 15km / h. By activating multiple sensors and adjusting the collection accuracy according to the driving mode, high-precision data are obtained in different driving modes, so that the vehicle can comprehensively perceive the environmental changes inside and outside the vehicle, the seal strip state and other information, thereby dynamically adjusting the seal strip compression force of the vehicle to adapt to the changes of the external environment and the driving state, and enhancing the driving experience and comfort.

[0035] S300: After converting the perception state set into a fusion state vector, the fusion state vector is sent to the adaptive adjustment channel of the adaptive adjustment channel, and the adaptive adjustment channel generates a first adjustment influence factor.

[0036] Further, the S300 of the present application comprises:

[0037] The rule matching module of the adaptive adjustment channel is called to perform adaptive preliminary screening of the fusion state vector, and an abnormal screening result is established; the abnormal screening result is synchronized to the deep decision evaluation module, adaptive analysis under the constraints of compression force, response rate, fitting priority, and energy consumption is performed, and a first adjustment influence factor is established.

[0038] Specifically, data preprocessing and fusion processing are performed on the perception state set, and different dimensions of data (such as temperature, humidity, and seal bar pressure) are converted into a unified fusion state vector, which is a multi-dimensional data structure that can comprehensively reflect the current vehicle state. Before fusion, different data sources may have different units and scales (such as vehicle speed in km / h, temperature in Celsius, and seal bar pressure in N). Therefore, first, all data need to be standardized to convert them to a unified scale and unit. The standardized data is integrated through different fusion algorithms to generate a fusion state vector. For example, different data sources are weighted according to their importance to give different weights. For example, the seal bar state may be more important than the vehicle speed in some scenarios, so the seal bar state is given a higher weight. The data after fusion is integrated into a unified vector that contains the feature representation of all related data, and in the calculation process, the relationship between the data is effectively preserved.

[0039] The fusion state vector is transmitted to the adaptive adjustment channel's adaptive comparison layer, which compares the fusion state vector with predefined rules, models, or standards to identify any abnormal state that does not conform to the normal working range. The adaptive comparison layer marks all data that does not meet expectations as abnormal as an abnormal screening result. The abnormal screening result is synchronized to the deep decision evaluation module for more in-depth analysis. The deep decision evaluation module will consider more factors to evaluate how to adjust the pressure, response rate, fit priority, and energy consumption constraints to achieve the best adjustment, resulting in a first adjustment influence factor that indicates how much adjustment is needed to achieve the best performance under the current state.

[0040] The deep decision evaluation module is also a module in the adaptive comparison layer responsible for detailed analysis of abnormal data and formulating appropriate adjustment strategies based on pre-set rules and constraints. Based on the incoming abnormal screening result (i.e., data that does not meet the standard), analysis is performed considering multiple factors to determine how to adjust the vehicle's parameters to restore normal state or optimize performance. Adaptive analysis refers to the trade-off analysis of different input conditions (such as environmental data and vehicle state data) and vehicle goals (such as comfort, safety, and energy efficiency) to find the optimal adjustment scheme, considering multiple constraints such as pressure, response rate, fit priority, and energy consumption. That is, during adjustment, the pressure cannot be too high or too low, the response rate should be as fast as possible, the energy consumption should be as low as possible, and when multiple factors conflict, the fit priority of each factor is considered.

[0041] According to the results of the adaptive analysis, the first adjustment influence factor is established, which represents the adjustment range or adjustment mode required by the sunroof sealing strip under the constraints of pressure, response rate, fit priority and energy consumption, etc. Through the rule matching module of the adaptive comparison layer, the abnormal data under the current driving mode, such as pressure, temperature, humidity and other data that do not meet the standard, are accurately screened out, so as to effectively monitor the vehicle state, and the deep decision evaluation module ensures effective adjustment under the premise of ensuring comfort and performance by comprehensively analyzing multiple constraint conditions (such as pressure, response rate, energy consumption, etc.), so that the vehicle can adaptively adjust the sealing strip in multiple driving modes, thereby improving the comfort, energy efficiency and stability of the vehicle.

[0042] S400: reading navigation data and driving behavior data by the vehicle-mounted controller, performing adjustment demand prediction according to the navigation data and the driving behavior data, and establishing a second adjustment influence factor.

[0043] Further, the present application S400 comprises:

[0044] Based on the navigation data, road condition information is called to take the real-time road condition position as the reference road condition, and an incremental road condition database is established; external environment data is called to perform weather perception prediction, and a perception prediction result is established; the incremental road condition database, the perception prediction result and the driving behavior data are used to perform adjustment demand prediction.

[0045] Further, the present application further comprises the following steps:

[0046] The incremental road condition database and the perception prediction result are used to establish a mutation timing node; the driving behavior data is used to perform sensitive analysis of wind pressure adaptation to generate a driving behavior enhancement factor; based on the driving behavior enhancement factor and the mutation timing node, a mutation response window is constructed, and the mutation response window is used to complete the adjustment demand prediction.

[0047] Specifically, through the vehicle-mounted controller, real-time navigation data (including current vehicle speed, destination, road information) and driving behavior data (including acceleration, brake frequency, steering angle, etc.) are read from the vehicle-mounted navigation system and the sensors of the vehicle. The navigation data helps to understand the current driving state and path of the vehicle, and the driving behavior data helps to analyze the behavior of the driver and the influence of the vehicle speed on the performance of the vehicle.

[0048] According to the navigation data, real-time road condition information is called, including the driving route of the vehicle, road condition changes (such as traffic jams, road construction, etc.) and real-time traffic flow information, etc. As the vehicle travels, the database is continuously expanded, and new road condition data is added. The incremental road condition database is a database that is updated and expanded by continuously obtaining real-time road condition information (such as traffic flow, traffic jam conditions, etc.), and records the road condition information at different times and different locations.

[0049] The vehicle controller calls external environment data in the perception state set (such as temperature, humidity, wind speed, rainfall, etc.), combines meteorological models and historical data, and performs weather perception prediction to predict future weather changes. Using the obtained external environment data, the vehicle controller uses the built-in weather prediction algorithm to predict future weather changes. For example, based on the current temperature, humidity, wind speed, etc. information, the weather conditions (such as rainfall, snowfall, temperature change, etc.) in the future 1 hour, 3 hours or even longer are calculated.

[0050] According to the incremental road condition database and the weather perception prediction result, a sudden time sequence node is analyzed and identified, that is, a major change (such as a sudden traffic accident, severe weather, etc.) occurring in a short time. The incremental road condition database includes road traffic conditions, accidents, road construction, etc., which can be used to determine the traffic conditions that the vehicle may encounter on the driving route in the future, such as congestion, etc.; according to the weather perception prediction result, the weather conditions that may occur in the future can be determined, such as rainfall, strong wind, etc.

[0051] By analyzing the incremental road condition database and the perception prediction result, the vehicle controller identifies nodes in the time series data that may experience dramatic changes, including path mutations, weather change mutations, and driving environment mutations, to obtain mutation time nodes. The mutation time node refers to a dramatic change point or a key turning point in the time series data, which is a data point with suddenness, abnormality or importance.

[0052] Sensitive analysis of wind pressure adaptation to driving behavior data, that is, how different driving behaviors of the driver affect the wind pressure distribution. Analyze the influence of different driving behaviors on the aerodynamic characteristics and wind pressure of the vehicle, and determine the influence of wind pressure on the sunroof sealing strip under different driving situations. For example, on the highway, if the driver frequently accelerates and decelerates, the airflow around the vehicle changes dramatically, thereby changing the wind pressure, especially the wind pressure in the roof area increases, which may cause the sunroof sealing strip to be insufficiently pressed.

[0053] Wind pressure adaptation refers to the ability of the sunroof weatherstrip to self-adapt its form, hardness, or adhesion under different wind speed and pressure conditions to maintain optimal sealing effectiveness. During high-speed driving, the aerodynamic characteristics of the vehicle can cause wind pressure on the roof, which can affect the tight adhesion of the sunroof weatherstrip. Sensitivity analysis is an analysis method used to assess the degree of influence of different factors (such as driving behavior, environmental conditions, etc.) on a specific output (such as wind pressure, vehicle performance), and to analyze how different driving behaviors (such as acceleration, braking, steering, etc.) of the driver affect the changes in wind pressure, and thus affect the sealing effect. Based on the results of sensitivity analysis, a driving behavior enhancement factor is generated to represent the degree of influence of driving behavior on wind pressure adaptation, which is usually a numerical factor that can be adjusted according to different operations of the driver (such as acceleration, braking, etc.) and external wind speed, wind direction conditions.

[0054] The mutation response window is defined based on the mutation timing node and the driving behavior enhancement factor, i.e., based on the mutation timing node, a time window is set to evaluate and respond to the impact of the mutation event on the vehicle performance within this time period, and the adjustment strategy of the sunroof weatherstrip is adjusted within this time window. For example, in the moment of sudden braking, the weatherstrip may loosen due to the vibration of the vehicle body, and the system will strengthen the compression force of the weatherstrip within the response window to ensure the sealing effect and avoid sudden noise in the vehicle. Using the data within the mutation response window, including the behavior of the driver, changes in the external environment, etc., the adjustment demand prediction is performed, i.e., based on historical data, current state, and future trend of changes, the adjustment measures that the vehicle needs to perform on the sunroof weatherstrip under mutation conditions are predicted.

[0055] Based on the adjustment demand prediction of the mutation response window, the second adjustment influence factor is determined, which is usually related to driving behavior and external environmental changes, and is one of the key input factors for the adaptive adjustment of the sunroof weatherstrip. For example, assume that the vehicle is driving on a highway, the vehicle controller reads that the vehicle is currently located on A section, the speed is 100 km / h, there is slight traffic congestion, and the weather perception predicts that there will be precipitation (heavy rain) in the next 30 minutes, at this time the driver is accelerating slightly and the speed increases by 5 km / h. Call the navigation data and real-time traffic information to confirm that the traffic condition of A section belongs to slight congestion, so there may be certain wind pressure and air flow influence. Using weather perception prediction, it is known that there will be heavy rain in the future, and the weatherstrip needs to strengthen waterproof and sealing. Combined with the acceleration behavior of the driver, it is predicted that the wind pressure may increase in heavy rain, and the vehicle may generate additional air flow when passing through the congested section, affecting the adhesion of the sunroof weatherstrip, so the intelligent material adhesion needs to be controlled using the driving voltage.

[0056] By integrating navigation data, weather forecasts, and driving behavior data, future environmental changes are predicted, and adjustments to the sealing strip are made in advance to ensure that the sealing performance of the sunroof remains optimal in adverse weather, wind pressure, or complex road conditions, thereby reducing wind noise, rain leakage, and other issues, and improving the driving experience and in-vehicle comfort.

[0057] Further, the present application further comprises the following steps:

[0058] It is determined whether the response nodes of the mutation response window in the second adjustment influencing factor exceed the stable adjustment period. If the response nodes of the mutation response window exceed the stable adjustment period, a temporary punishment factor is activated, and the second adjustment influencing factor is punished using the temporary punishment factor to complete the adjustment layer compensation.

[0059] Specifically, it is determined whether each response node within the mutation response window in the second adjustment factor exceeds the preset stable adjustment period. If the response nodes exceed the stable adjustment period, it indicates that the adjustment demand of the sealing strip has become too urgent. The stable adjustment period is the adjustment period required by the sealing strip under normal circumstances, which is usually a relatively long and predictable period of time. Within this period, the sealing strip can adapt to environmental changes and maintain good sealing performance.

[0060] When the response nodes of the mutation response window exceed the stable adjustment period, a temporary punishment factor is automatically activated to reduce the frequency or intensity of the adjustment action, preventing excessive adjustment and avoiding excessive adjustment, energy waste, or affecting the long-term stability of the sealing strip. The temporary punishment factor limits the intensity of the adjustment behavior, preventing excessive or ineffective adjustment, and ensuring that the sealing strip operates within a reasonable range. That is, the temporary punishment factor reduces the intensity, frequency, or range of the sealing strip adjustment operation. For example, according to the mutation timing node analysis, the time span of the mutation response window is 2 seconds, and the stable adjustment period is 1 second. Since the mutation response window (2 seconds) exceeds the stable adjustment period (1 second), measures need to be taken to compensate for this difference, reducing the original adjustment amplitude from 10% to 6%. That is, the pressure adjustment range of the sealing strip will be ±6% instead of ±10%, making the adjustment amplitude smoother and reducing the risk of excessive response.

[0061] After punishing the second adjustment influencing factor with the temporary punishment factor, the adjustment layer compensation is completed, the adjustment scheme is re-evaluated, and necessary compensation is performed. The purpose of compensation is to ensure that the adjustment action of the sealing strip can be completed without exceeding the specified period and without excessive energy consumption or affecting the long-term stability of the sealing strip. Adjustment layer compensation refers to modifying the adjustment result through a compensation mechanism based on the second adjustment influencing factor and the temporary punishment factor, so that the adjustment operation of the sealing strip is neither excessive nor lagging, and the behavior of excessive or insufficient adjustment is adjusted, allowing the sealing strip to maintain optimal sealing performance.

[0062] Through temporary punishment of the activation and adjustment compensation of the factor, over-adjustment of the sealing strip is effectively prevented, energy consumption is optimized, frequent and ineffective adjustment actions are avoided, thereby prolonging the service life of the sealing strip and improving the efficiency of the overall system. Even in emergency situations, the balance of the adjustment operation can be maintained, and the performance of the sealing strip will not be reduced due to overreaction. At the same time, the problem of sealing (such as air leakage and water leakage) caused by slow reaction is also avoided.

[0063] S500: After compensating the adjustment layer of the adaptive adjustment channel using the first adjustment influence factor and the second adjustment influence factor, an adaptive adjustment scheme is generated based on the fusion state vector.

[0064] Further, the S500 of the present application comprises:

[0065] A target function is established, the evaluation characteristics of the target function include pressure stability characteristics, energy consumption characteristics, response time characteristics, and fit degree characteristics; the first adjustment influence factor is called to adjust the priority and expected value of the target function, to complete the first compensation; the second adjustment influence factor is called to adjust the weight factor of the target function, to complete the second compensation; after the compensation of the target function in the adjustment layer is completed using the first compensation and the second compensation, the adjustment action optimization is executed, and an adaptive adjustment scheme is generated.

[0066] A control variable space is established, the control variables in the control variable space include driving voltage, driving duration, driving frequency, and partition excitation strategy; after the initial control data is established based on the control variable space, the control adaptation analysis is performed using the compensated target function, and search iteration is executed; the adaptive adjustment scheme is generated using the search iteration result.

[0067] Specifically, the target function is established, including four key evaluation characteristics: pressure stability, energy consumption, response time, and fit degree. Each characteristic represents an optimization goal of the sealing strip adjustment. For example, the pressure stability characteristic requires the sealing strip to maintain a relatively stable pressing force under different driving conditions; the energy consumption characteristic requires the energy consumption to be minimized without sacrificing performance. The target function is used to quantify the optimization goal of the adjustment task, and multiple factors (such as pressure stability, energy consumption, response time, and fit degree) are measured to help select the best adjustment scheme, and each target characteristic has a corresponding weight value and expected value.

[0068] The priority of the target function determines the priority order of each adjustment target, and the expected value is the performance level expected to be achieved by each target. Based on the first adjustment factor, the priority of each feature in the target function is dynamically adjusted. For example, in the highway driving mode, the response time feature is given priority to respond to sudden environmental changes that may occur. In the city driving mode, the pressure stability feature and the energy consumption feature are given higher priority to adapt to frequent start-stop.

[0069] Based on the priority adjustment, the expected value is also dynamically adjusted. The expected value refers to the expected effect of each feature in the target function. When adjusting the expected value, the current state of the vehicle (such as speed, driving mode, etc.) is considered, and the target value of each feature in the target function is dynamically adjusted according to these states. After adjusting the priority and expected value of the target function, the first compensation is performed on the target function, so that the target function can better reflect the adjustment requirements under the current driving mode and environmental conditions, thereby achieving the best adjustment effect. For example, if a large wind speed is detected, the priority of the pressure stability feature in the target function will be increased, so that the adjustment of the sealing strip will focus more on the stability of the pressure, ensuring the sealing of the sunroof.

[0070] According to the second adjustment factor, the weight factor of the target function is weighted and adjusted, and the weight of different features is dynamically adjusted according to real-time environmental information (such as weather changes, wind speed, temperature, etc.) and driving behavior (such as acceleration, braking, etc.). In the adjustment process, each feature in the target function will dynamically adjust its weight according to the current driving mode, environmental conditions, and other factors. The adjustment of the weight factor helps to focus on the most important features in different situations.

[0071] Combining the first compensation and the second compensation, the target function is finally compensated to ensure that all adjustment targets (such as pressure stability, response time, energy consumption, etc.) can be reasonably optimized under different driving modes and environmental conditions. Different adaptive adjustment channels correspond to different driving modes, and their corresponding target functions are different. Through compensation, it is ensured that the target function can reflect the most appropriate adjustment requirements under different driving conditions. For example, the kinetic energy recovery mode may be more energy-saving, so the weight of energy consumption is high.

[0072] A control variable space is established, which is used to adjust and optimize the performance of the sealing strip in adaptive adjustment, including the set of all variable parameters such as driving voltage, driving duration, driving frequency, and partition excitation strategy. The driving voltage is the voltage used to drive the smart material or electric actuator, which affects the shape change, hardness, and response speed of the material; the driving duration is the time for which the control voltage is applied; the driving frequency is the frequency at which the voltage or excitation signal changes; and the partition excitation strategy is to apply different excitation methods in different areas of the sealing strip to achieve more accurate adjustment.

[0073] Based on the existing adjustment requirements (such as the desired sealing performance, response time, etc.), initial control data is set to start the adjustment process and provide a starting point for subsequent optimization iterations. Using the compensated objective function, control adaptation analysis is performed, and all combinations in the control variable space are evaluated by the compensated objective function to determine the performance of each combination scheme (such as pressure stability, energy consumption, response time, and fit). A particle swarm is used, and each particle represents a possible solution, i.e., a combination of control variables, which is composed of parameters in the control variable space, including driving voltage, driving duration, driving frequency, and partition excitation strategy.

[0074] Each particle is randomly initialized in the search space with a position and a velocity, which represents how the particle updates its position in the next iteration. Each particle updates its position according to the updated velocity. After each update, the position of the particle (i.e., the combination of control variables) is evaluated by the objective function. According to the value of the objective function, the particle calculates its fitness and updates its personal best position. If the fitness of a particle is better than its historical best, the best position is updated. The global best position (i.e., the optimal solution) in the population is the position with the best fitness among all particles. After each iteration, the fitness values of all particles in the population are compared, and the best particle position is selected as the global best. The particle swarm constantly iterates and updates the velocity and position to approach the optimal solution. In each iteration, the particle swarm updates the combination of control variables until a certain stopping condition is reached, such as the maximum number of iterations or the convergence of fitness. When the particle swarm optimization is complete, the optimal particle position found is the best combination of control variables (driving voltage, driving duration, driving frequency, and partition excitation strategy), i.e., the adaptive adjustment scheme.

[0075] After compensating the adjustment layer of the adaptive adjustment channel by the first and second adjustment influence factors, the current adjustment demand is determined in combination with the fusion state vector, including the optimization requirements of the target performance, such as the sealing performance, energy consumption, pressure stability, etc. Different driving modes correspond to different adjustment demands. For example, in the sports mode, more attention is paid to the response speed and pressure stability; in the kinetic energy recovery mode, more attention is paid to the energy consumption optimization; in the normal mode, all adjustment targets are balanced; and in the parking mode, the sealing performance and static stability are mainly focused on. By analyzing the key features in the fusion state vector, the adjustment demand suitable for the current scene is derived. After determining the adjustment demand, the corresponding adaptive adjustment scheme is generated according to the above process.

[0076] Once the adjustment scheme is generated, the adjustment operation is performed, such as adjusting the driving voltage, frequency, duration, etc., and the execution result is monitored in real time. By dynamically adjusting the weights and expected values of the objective function, the best adjustment of the sunroof sealing strip is achieved in different driving modes, the sealing performance is improved, and the adjustment scheme is automatically adjusted according to different driving behaviors and environmental changes, ensuring that the sunroof sealing strip can provide the best sealing performance in various situations.

[0077] Further, the present application also includes the following steps:

[0078] The collected sensors are used to obtain the adjusted in-vehicle pressure value, energy consumption data, and fitting state image in real time to construct real-time adjustment feedback data; the achievement verification of the real-time adjustment feedback data is performed based on the expected indicators, and the correction feedback is established according to the achievement verification result.

[0079] Specifically, after the adaptive adjustment scheme is executed, the feedback data after adjustment is obtained in real time by the collection sensors, including the in-vehicle pressure value, energy consumption data, and fitting state image. The pressure sensor is used to monitor the air pressure change in the vehicle in real time to ensure that the sealing strip is working correctly and prevent air penetration. The energy consumption is monitored in real time to ensure that the adjustment operation is within the scope of energy efficiency optimization and avoid unnecessary energy waste. The image sensor or visual perception system is used to obtain the fitting state between the sealing strip and the window to ensure that the sealing strip is tightly fitted and maximizes its performance.

[0080] The in-vehicle pressure value, energy consumption data, and fitting state image constitute the real-time adjustment feedback data, which reflects whether the sealing strip adjustment operation has achieved the expected effect. Before the adaptive adjustment scheme is executed, a series of expected indicators will be set in advance, which are usually dynamically set according to the vehicle operating mode, external environment, driving behavior, etc. For example, the in-vehicle pressure should be maintained within a certain stable range, such as about one thousand pascals, the energy consumption should be maintained at about 5W, and the fitting error should not exceed 0.5mm. The collected adjustment feedback data is compared and verified with these expected indicators, and if the actual data meets the expected value, it is considered that the adjustment target has been achieved.

[0081] If the feedback data fails to meet the preset expected indicators (such as the pressure in the vehicle is not within the target range, or the energy consumption is too high), a corrective feedback is generated to modify and optimize the current adjustment scheme. Based on the unmet feedback data, a series of adjustment measures are taken, for example, if the pressure in the vehicle is not within the target range, the excitation voltage or working frequency of the sealing strip is adjusted to make it fit the window more tightly and increase the sealing effect; if the energy consumption exceeds the expectation, the driving voltage is reduced or the excitation strategy is adjusted to optimize the energy efficiency; if there is an error in the fit, the driving duration or frequency of the sealing strip is adjusted according to the image sensor feedback to improve the fit effect.

[0082] According to the correction feedback, the adaptive adjustment scheme is re-optimized to ensure that all expected indicators can be met, such as changing the driving voltage, driving duration, driving frequency, or partition excitation strategy to ensure that the sealing strip can continuously reach or approach the expected indicators. By real-time acquisition of the adjusted pressure value in the vehicle, energy consumption data, and fit state image, and based on the expected indicators for achievement verification and correction feedback, it is ensured that the sealing strip always reaches or approaches the preset performance standard, improving the adaptability and sealing performance of the sealing strip, reducing the possibility of air leakage and water seepage, and thus improving the comfort of passengers and the overall performance of the vehicle.

[0083] In summary, the adaptive adjustment method for the automobile sunroof sealing strip based on intelligent materials provided by the present application has the following beneficial effects:

[0084] By executing the vehicle-mounted controller initialization after the system starts, the vehicle-mounted controller is used to perform driving mode recognition, activate the adaptive adjustment channel mapped with the driving mode; after activating the collection sensor according to the driving mode recognition result and configuring the collection accuracy of the collection sensor, multi-source data collection is performed to establish a perception state set, the perception state set including sealing strip state data, vehicle interior environment data, and external environment data; after converting the perception state set into a fusion state vector, the fusion state vector is sent to the adaptive adjustment channel of the adaptive adjustment channel, and the adaptive adjustment channel generates a first adjustment influence factor; the navigation data and driving behavior data are read by the vehicle-mounted controller, adjustment demand prediction is performed according to the navigation data and the driving behavior data, and a second adjustment influence factor is established; after compensating the adjustment layer of the adaptive adjustment channel by using the first adjustment influence factor and the second adjustment influence factor, an adaptive adjustment scheme is generated based on the fusion state vector. That is, by introducing intelligent materials, the shape, hardness, and compression force are accurately adjusted according to the real-time environment and driving mode through electric heating or voltage control means of the driving voltage, the external environment changes are automatically adapted, the sealing performance of the vehicle window can be maintained stable under various weather conditions, the problems such as air leakage and water leakage are reduced, and the sealing effect of the sealing strip and the comfort in the vehicle are improved.

[0085] Embodiment two, based on the same inventive concept as the adaptive adjustment method of the smart material-based automobile sunroof sealing strip in the aforementioned embodiment one, the present application also provides an adaptive adjustment device of a smart material-based automobile sunroof sealing strip, please refer to the attached Figure 2 , the adaptive adjustment device of the smart material-based automobile sunroof sealing strip comprises:

[0086] The driving mode recognition module 11 is used to perform vehicle controller initialization after system startup, perform driving mode recognition by using the vehicle controller, and activate the adaptive adjustment channel mapped with the driving mode; the perception state acquisition module 12 is used to activate the collection sensor according to the driving mode recognition result, configure the collection accuracy of the collection sensor, perform multi-source data collection, and establish a perception state set after the collection, the perception state set includes sealing strip state data, in-vehicle environment data, and external environment data; the first influence factor module 13 is used to convert the perception state set into a fusion state vector, and send it to the adaptive adjustment channel of the adaptive adjustment channel. The adaptive adjustment channel generates a first adjustment influence factor by the adaptive adjustment channel; the second influence factor module 14 is used to read navigation data and driving behavior data by the vehicle controller, perform adjustment demand prediction according to the navigation data and the driving behavior data, and establish a second adjustment influence factor; the adaptive adjustment module 15 is used to generate an adaptive adjustment scheme based on the fusion state vector after compensating the adjustment layer of the adaptive adjustment channel by using the first adjustment influence factor and the second adjustment influence factor.

[0087] Further, the driving mode recognition module 11 in the adaptive adjustment device of the smart material-based automobile sunroof sealing strip is also used for:

[0088] The driving mode includes a sports mode, a normal mode, a kinetic energy recovery mode, and a parking mode.

[0089] Further, the first influence factor module 13 in the adaptive adjustment device of the smart material-based automobile sunroof sealing strip is also used for:

[0090] The rule matching module of the adaptive adjustment layer is called to perform adaptive preliminary screening of the fusion state vector, and an abnormal screening result is established; the abnormal screening result is synchronized to the deep decision evaluation module to perform adaptive analysis under the constraints of pressure, response rate, adhesion priority, and energy consumption, and a first adjustment influence factor is established.

[0091] Further, the second influence factor module 14 in the adaptive adjustment device of the smart material-based automobile sunroof sealing strip is also used for:

[0092] Performing real-time road condition information calling based on the navigation data, taking the real-time road condition position as a reference road condition, establishing an incremental road condition database; calling external environment data, performing weather perception prediction, and establishing a perception prediction result; using the incremental road condition database, the perception prediction result, and the driving behavior data to perform adjustment demand prediction.

[0093] Further, the second influence factor module 14 in the intelligent material-based automobile sunroof sealing strip adaptive adjustment device is further used for:

[0094] Using the incremental road condition database and the perception prediction result to establish a mutation timing node; using the driving behavior data to perform sensitive analysis of wind pressure adaptation, and generating a driving behavior enhancement factor; based on the driving behavior enhancement factor and the mutation timing node, constructing a mutation response window, and using the mutation response window to complete adjustment demand prediction.

[0095] Further, the adaptive adjustment module 15 in the intelligent material-based automobile sunroof sealing strip adaptive adjustment device is further used for:

[0096] Judging whether the response node of the mutation response window in the second adjustment influence factor exceeds the stable adjustment period; if the response node of the mutation response window exceeds the stable adjustment period, activating a temporary punishment factor, punishing the second adjustment influence factor using the temporary punishment factor, and completing adjustment layer compensation.

[0097] Further, the adaptive adjustment module 15 in the intelligent material-based automobile sunroof sealing strip adaptive adjustment device is further used for:

[0098] Establishing a target function, the evaluation characteristics of the target function including pressure stability characteristics, energy consumption characteristics, response time characteristics, and fitting degree characteristics; calling the first adjustment influence factor, adjusting the priority and expected value of the target function, completing first compensation; calling the second adjustment influence factor, weighting and adjusting the weight factor of the target function, completing second compensation; after using the first compensation and the second compensation to complete compensation of the target function in the adjustment layer, performing adjustment action optimization, and generating an adaptive adjustment scheme.

[0099] Further, the adaptive adjustment module 15 in the intelligent material-based automobile sunroof sealing strip adaptive adjustment device is further used for:

[0100] Establishing a control variable space, the control variables in the control variable space including driving voltage, driving duration, driving frequency, and partition excitation strategy; based on the initial control data established based on the control variable space, performing control adaptation analysis using the compensated target function, and executing search iteration; using the search iteration result to generate an adaptive adjustment scheme.

[0101] Further, the adaptive adjustment module 15 in the smart material-based sunroof sealing strip adaptive adjustment device is further used for:

[0102] The acquisition sensor is used to acquire the adjusted vehicle interior pressure value, energy consumption data and fitting state image in real time, to construct real-time adjustment feedback data; the expected index is used to verify the achievement of the real-time adjustment feedback data, and the correction feedback is established according to the achievement verification result.

[0103] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The foregoing Figure 1 The smart material-based sunroof sealing strip adaptive adjustment method and specific examples in embodiment one are also applicable to the smart material-based sunroof sealing strip adaptive adjustment device in the present embodiment. Through the foregoing detailed description of the smart material-based sunroof sealing strip adaptive adjustment method, those skilled in the art can clearly know the smart material-based sunroof sealing strip adaptive adjustment device in the present embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0104] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0105] Obviously, for those skilled in the art, without departing from the principles of the present application, the present application can be improved and modified in several ways, and these improvements and modifications also fall within the protection scope of the present application.

Claims

1. A method for adaptive adjustment of a sunroof seal strip based on smart materials, characterized in that The system comprises: After the system is started, the vehicle-mounted controller initialization is performed, the driving mode recognition is performed by using the vehicle-mounted controller, and the adaptive adjustment channel mapped with the driving mode is activated; After the acquisition sensor is activated according to the driving mode recognition result and the acquisition accuracy of the acquisition sensor is configured, the multi-source data acquisition is performed, the perception state set is established, and the perception state set comprises the seal strip state data, the in-vehicle environment data and the external environment data; After the perception state set is converted into the fusion state vector, the fusion state vector is sent to the adaptive adjustment channel, the first adjustment influence factor is generated by the adaptive adjustment channel; The navigation data and the driving behavior data are read by the vehicle-mounted controller, the adjustment demand prediction is performed according to the navigation data and the driving behavior data, and the second adjustment influence factor is established; After the first adjustment influence factor and the second adjustment influence factor are used to compensate the adjustment layer of the adaptive adjustment channel, the adaptive adjustment scheme is generated based on the fusion state vector; The conversion of the perception state set into the fusion state vector and the sending of the fusion state vector to the adaptive adjustment channel of the adaptive adjustment channel to generate the first adjustment influence factor comprise: The rule matching module of the adaptive adjustment layer is called, the adaptive preliminary screening of the fusion state vector is performed, and the abnormal screening result is established; The abnormal screening result is synchronized to the deep decision evaluation module, the adaptive analysis under the constraints of the pressure, the response rate, the priority of adhesion and the energy consumption is performed, and the first adjustment influence factor is established; The adjustment demand prediction according to the navigation data and the driving behavior data comprises: The road condition information is called based on the navigation data, the real-time road condition position is taken as the reference road condition, the incremental road condition database is established; The external environment data is called, the weather perception prediction is performed, and the perception prediction result is established; The adjustment demand prediction is performed by using the incremental road condition database, the perception prediction result and the driving behavior data; The adjustment demand prediction by using the incremental road condition database, the perception prediction result and the driving behavior data comprises: The mutation time sequence node is established by using the incremental road condition database and the perception prediction result; The sensitive analysis of the wind pressure adaptation is performed by using the driving behavior data, and the driving behavior enhancement factor is generated; The mutation response window is constructed based on the driving behavior enhancement factor and the mutation time sequence node, and the adjustment demand prediction is completed by using the mutation response window; The compensation of the adjustment layer of the adaptive adjustment channel by using the first adjustment influence factor and the second adjustment influence factor comprises: It is judged whether the response node of the mutation response window in the second adjustment influence factor exceeds the stable adjustment period or not; If the response node of the mutation response window exceeds the stable adjustment period, a temporary punishment factor is activated, the second adjustment influence factor is punished by using the temporary punishment factor, and the compensation of the adjustment layer is completed; After the compensation of the adjustment layer of the adaptive adjustment channel by using the first adjustment influence factor and the second adjustment influence factor, the adaptive adjustment scheme is generated based on the fusion state vector. A target function is established, and evaluation features of the target function include pressure stability features, energy consumption features, response time features, and fitting degree features; The first adjustment influence factor is called to adjust the priority and expected value of the target function, and first compensation is completed; The second adjustment influence factor is called to adjust the weight factor of the target function, and second compensation is completed; After the first compensation and the second compensation are completed to compensate the target function in the adjustment layer, an adjustment action is executed to optimize and generate an adaptive adjustment scheme; The adjustment action is executed to optimize and generate the adaptive adjustment scheme, including: A control variable space is established, and control variables in the control variable space include driving voltage, driving duration, driving frequency, and partition excitation strategy; After the initial control data is established based on the control variable space, control adaptation analysis is performed on the compensated target function, and search iteration is executed; An adaptive adjustment scheme is generated based on the search iteration result.

2. The smart material based sunroof weatherstrip self-adapting adjustment method of claim 1, wherein, The driving mode includes a sports mode, a normal mode, a kinetic energy recovery mode, and a parking mode.

3. The smart material based sunroof weatherstrip adaptive adjustment method of claim 1, wherein, After the adaptive adjustment scheme is generated based on the fusion state vector, including: Real-time adjustment feedback data is constructed by using the acquisition sensor to obtain the adjusted in-vehicle pressure value, energy consumption data, and fitting state image; Based on the expected index, the real-time adjustment feedback data is verified, and a correction feedback is established according to the verification result.

4. A self-adaptive adjusting device for a sunroof sealing strip based on smart materials, characterized in that The adaptive adjustment device based on intelligent materials for the automobile sunroof sealing strip includes: A driving mode recognition module is used to execute vehicle controller initialization after system startup, perform driving mode recognition by using the vehicle controller, and activate the adaptive adjustment channel mapped with the driving mode; A perception state acquisition module is used to activate the acquisition sensor according to the driving mode recognition result, configure the acquisition accuracy of the acquisition sensor, perform multi-source data acquisition, and establish a perception state set including sealing strip state data, in-vehicle environment data, and external environment data; A first influence factor module is used to convert the perception state set into a fusion state vector, and send it to the adaptive adjustment channel of the adaptive adjustment channel to generate a first adjustment influence factor by the adaptive adjustment channel; A second influence factor module is used to read navigation data and driving behavior data by the vehicle controller, perform adjustment demand prediction according to the navigation data and the driving behavior data, and establish a second adjustment influence factor; An adaptive adjustment module is used to generate an adaptive adjustment scheme based on the fusion state vector after the adjustment layer of the adaptive adjustment channel is compensated by using the first adjustment influence factor and the second adjustment influence factor.

Images