A control method and system for a horizontal actuator of a long slide rail for a new energy vehicle seat.

Abstract

This invention discloses a horizontal actuator control method and system for a long sliding rail of a new energy vehicle seat, relating to the field of sliding rail automation control. It addresses the problem that special passengers must manually adjust their seats before boarding, failing to meet the user's need for comfortable and quick boarding. The method collects data on user-applied seat pressure, differences in automatic seat adjustment, and actuator movement speed; establishes a data analysis model; obtains adjustment evaluation coefficients; compares these coefficients with adjustment thresholds; and obtains comparison results. Based on the comparison result labels and their adjustment evaluation coefficient values, a comprehensive analysis is performed to determine the current user's feature similarity and similar historical user setting preference values, and then uses a set of fuzzy rules to perform fuzzy inference to determine the initial seat adjustment scheme for the current user. This allows for faster satisfaction of the user's comfort angle and position, optimizing the riding experience.

Description

Technical Field

[0001] This invention relates to the field of automated control of slide rails, and more specifically, to a method and system for controlling a horizontal drive of a long slide rail for a new energy vehicle seat. Background Technology

[0002] In new energy vehicles, seat adjustment functionality is crucial for driving comfort and passenger experience. Currently, most seat adjustment systems use electric actuators for position adjustment, offering multiple adjustment modes, including fore-aft, he-aft, and tilt adjustments. This allows drivers and passengers to easily adjust the seat position according to their personal preferences, meeting their individual needs for riding or driving.

[0003] The existing technology has the following shortcomings:

[0004] Currently, with the development of technology, automatic memory seats have emerged. Based on the user-set adjustment position, when the user presses the automatic memory button, the system receives the memory data and controls the long slide rail horizontal actuator to adjust the seat towards the user's preset adjustment position. However, the initial position of the seat is usually unchanged. This requires some special passengers to manually adjust the seat before getting into the vehicle. Manual adjustment lacks precision and wastes time, failing to meet the user's need for comfort and speed when getting into the vehicle. Therefore, this paper proposes a control method and system for a long slide rail horizontal actuator for new energy vehicle seats.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a method and system for controlling a horizontal drive for a long slide rail of a new energy vehicle seat, which solves the problems mentioned in the background art by employing different product testing methods.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a method for controlling a horizontal actuator of a long slide rail for a new energy vehicle seat, comprising:

[0008] S1: Collect user-applied information and seat feature information, and through data processing, obtain the user-applied seat pressure value, seat automatic adjustment difference, and drive movement rate;

[0009] S2: Obtain the user-applied seat pressure value, seat automatic adjustment difference, and drive movement rate, establish a data analysis model, and obtain adjustment evaluation coefficients;

[0010] S3: Obtain the adjustment evaluation coefficient and compare it with the adjustment threshold to obtain the comparison result. Based on the comparison result label and its adjustment evaluation coefficient value, conduct a comprehensive analysis to determine the next seat adjustment range.

[0011] S4: Obtain the seat adjustment range, collect the seat pressure value applied by the current user and compare it with the maximum and minimum values ​​of the previous historical user, select the current user features based on the comparison results and calculate the similarity between the current user features and the user features of each historical segment to obtain the current user feature similarity, and then perform cluster analysis based on the historical user setting preferences in the user feature similarity to obtain the similar historical user setting preference values.

[0012] S5: Input the current user's feature similarity and the preference values ​​of similar historical users into the fuzzy logic to determine the initial adjustment result of the current user's seat.

[0013] In a preferred embodiment, the user-applied information includes the user-applied seat pressure value; the seat characteristic information includes differences in automatic seat adjustment and the drive motion rate.

[0014] The pressure Cp applied by the user to the seat is obtained by measuring the pressure on the seat surface using a pressure sensor. i Where i represents the time of the i-th data collection;

[0015] First, define the coordinates of the original position and the memorized position. Then, calculate the difference between each coordinate axis and obtain the seat automatic adjustment difference De based on the Euclidean distance. i ;

[0016] The ratio of the distance difference between the user-preset memory position and the current seat position to the time required for the drive to move to the target position is calculated, and then multiplied by the pressure function to obtain the drive's motion rate Sv. i .

[0017] In a preferred embodiment, the user-applied seat pressure value Cp is obtained. i Automatic seat adjustment differences i and the drive motion rate Sv i Generate adjusted evaluation coefficient Ec i The formula used is:

[0018]

[0019] In the formula, Ec i To adjust the evaluation coefficients, as well as Each of these parameters has a preset proportional coefficient for applying seat pressure to the user, adjusting seat automatically, and adjusting drive speed. as well as All are greater than 0.

[0020] In a preferred embodiment, after obtaining the adjustment evaluation coefficient, the adjustment evaluation coefficient is compared and analyzed with the continuously iterative adjustment threshold.

[0021] If the adjustment evaluation coefficient is greater than or equal to the adjustment threshold, the next wheel slip distance of the current seat is marked as a larger adjustment distance, and an adjustment signal is generated;

[0022] If the adjustment evaluation coefficient is less than the adjustment threshold, the next wheel slip distance of the current seat will be marked as the adjustment distance will remain unchanged, and a hold signal will be generated.

[0023] In a preferred embodiment, the comparison result labels include larger adjustment distance and unchanged adjustment distance;

[0024] Count the number of labels with larger adjustment distances and their total adjustment evaluation coefficients, as well as the number of labels with unchanged adjustment distances and their total adjustment evaluation coefficients. Label the number of labels with larger adjustment distances as Q and the number of labels with unchanged adjustment distances as P, and substitute them into the formula for calculation:

[0025]

[0026] In the formula, W represents the seat adjustment range, and Ec... 较大 To adjust the total number of adjustment evaluation factors for the distance labels, Ec 不变 To adjust the total value of the evaluation coefficient for distance-invariant labels;

[0027] The seat adjustment range is compared with a preset range threshold. If the seat adjustment range is greater than or equal to the range threshold, the seat position is adjusted backward to the first distance. If the seat adjustment range is less than the range threshold, the seat position is adjusted backward to the second distance.

[0028] In a preferred embodiment, historical users correspond to each historical segment; the seat pressure value applied by the current user is collected and compared with the maximum and minimum values ​​of the previous historical user. If it is less than the minimum value or greater than the maximum value, the current user's features are collected and similarity is calculated with the features of users in each historical segment. Otherwise, the adjustment is made according to the memory position of the previous historical user.

[0029] The current user features include user weight, height, and waist circumference; the user features of each historical segment correspond to the current user features, and the similarity of the current user features is obtained through cosine similarity.

[0030] Calculate the similarity of features of all current users, set the memory location of similar historical users as feature data, perform cluster analysis calculation, construct feature matrix X, and set the number of clusters k. The specific number of clusters k is calculated by the cost function.

[0031] When the cluster centers no longer change significantly, or the user assignments no longer change, the algorithm is considered to have converged, yielding the final cluster centers and cluster labels for each user feature. A weighted average is then used to obtain the preference values ​​for similar historical users.

[0032] In a preferred embodiment, the current user feature similarity and the preference values ​​of similar historical users are defined as input variables and divided into different fuzzy sets respectively;

[0033] Define the initial adjustment result of the current user's seat as the output variable and divide it into a fuzzy set;

[0034] Formulate fuzzy rules to describe the impact of current user feature similarity and similar historical user preference settings on the initial adjustment result of the current user's seat;

[0035] Based on fuzzy rules, fuzzy reasoning is used to determine the initial adjustment plan for the current user's seat.

[0036] A new energy vehicle seat long slide rail horizontal drive control system includes a data acquisition module, a data processing module, an adjustment and analysis module, and a user optimization module;

[0037] The data acquisition module is used to collect user-applied information and seat feature information. Through data processing, it obtains the user-applied seat pressure value, seat automatic adjustment difference, and drive movement rate, and sends them to the data processing module.

[0038] The data processing module is used to acquire the user-applied seat pressure value, seat automatic adjustment differences, and drive movement rate, establish a data analysis model, obtain adjustment evaluation coefficients, and send them to the adjustment analysis module;

[0039] The adjustment analysis module is used to obtain the adjustment evaluation coefficient and compare it with the adjustment threshold to obtain the comparison result. Based on the comparison result label and its adjustment evaluation coefficient value, a comprehensive analysis is performed to determine the next seat adjustment range and send it to the user optimization module.

[0040] The user optimization module is used to obtain the seat adjustment range, collect the seat pressure value applied by the current user and compare it with the maximum and minimum values ​​of the previous historical user, select to collect the current user features based on the comparison results and calculate the similarity between the current user features and the user features of each historical segment to obtain the current user feature similarity, and then perform cluster analysis based on the historical user setting preferences in the user feature similarity to obtain the similar historical user setting preference values, and use them to determine the preliminary seat adjustment result of the current user.

[0041] The technical effects and advantages of this invention are as follows:

[0042] 1. This invention establishes a data analysis model by collecting user-applied seat pressure values, seat automatic adjustment differences, and drive movement speed. It obtains adjustment evaluation coefficients and compares them with adjustment thresholds to obtain comparison results. Based on the comparison result labels and their adjustment evaluation coefficient values, a comprehensive analysis is performed to determine the next seat adjustment range. The seat can more quickly meet the user's comfort angle and position, optimize the riding experience, improve seat adjustment efficiency and accuracy, and extend the service life of the long slide rail horizontal drive.

[0043] 2. This invention obtains the next seat adjustment range, formulates a set of fuzzy rules based on the similarity of current user characteristics and the setting preference values ​​of similar historical users, and performs fuzzy inference to determine the initial seat adjustment plan for the current user, thereby reducing unnecessary position adjustments, meeting the riding needs of new users, and improving the accuracy and operational intelligence of the long slide rail horizontal drive. Attached Figure Description

[0044] Figure 1 This is a flowchart of a method for controlling a horizontal drive of a long slide rail for a new energy vehicle seat according to the present invention.

[0045] Figure 2 This is a schematic diagram of a module of a horizontal drive control system for a long slide rail of a new energy vehicle seat according to the present invention. Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] Specifically, this invention achieves further refinement of the automatic memory seat by adjusting the seat based on user and seat feature information, thereby further optimizing and realizing automated control of the automotive seat long slide rail horizontal drive.

[0048] Example 1

[0049] Please see Figure 1 A control method for a horizontal actuator of a long slide rail for a new energy vehicle seat, the specific operation process of which is as follows:

[0050] S1: Collect user-applied information and seat feature information, and through data processing, obtain the user-applied seat pressure value, seat automatic adjustment difference, and drive movement rate;

[0051] The user-applied information includes the seat pressure value applied by the user; the seat characteristic information includes differences in automatic seat adjustment and drive motion rate.

[0052] The user-applied seat pressure value refers to the vertical pressure generated by the user's weight and posture when sitting in the seat. The greater the user-applied seat pressure value, the greater the travel pressure of the long slide rail horizontal drive, which is more likely to cause slide rail fatigue, reduce energy efficiency and lifespan. Therefore, the seat adjustment range should be smaller to reduce the travel distance of the long slide rail horizontal drive.

[0053] Its acquisition logic is to measure the pressure on the seat surface using a pressure sensor to obtain the user-applied seat pressure value Cp. i Where i represents the time of the i-th data collection;

[0054] The specific formula for calculating pressure is as follows:

[0055]

[0056] In the formula, Cp i The pressure value applied to the user by the chair is F, where F is the force exerted by the user on the chair, and A is the area of ​​the contact zone between the user and the chair.

[0057] It should be noted that the data collection time was set by the researchers based on the frequency of changes in the user's applied seat pressure or the number of times the long slide rail horizontal drive moved. During movement, the seat would adjust towards the user's preset memory position, and the user's applied seat pressure would change accordingly, etc., which will not be elaborated here.

[0058] The automatic seat adjustment difference refers to the difference between the user-preset memory position and the original position. Its acquisition logic first defines the coordinates of the original and memory positions, calculates the difference along each coordinate axis, and then obtains the automatic seat adjustment difference (De) based on Euclidean distance. i ;

[0059] Specifically, let the original position coordinates be (x1, y1, z1), and the memorized position coordinates be (x2, y2, z2); calculate the differences between each coordinate axis, specifically:

[0060] Δx = x2 - x1, Δy = y2 - y1, and Δz = z2 - z1;

[0061] In the formula, Δx, Δy, and Δz represent the differences along the x-axis, y-axis, and z-axis, respectively.

[0062] The automatic seat adjustment difference is calculated based on Euclidean distance, using the following formula:

[0063]

[0064] In the formula, De i Automatic seat adjustment for differences;

[0065] It should be noted that the original position refers to the seat that will be adjusted to the original position after the vehicle is turned off and the user leaves. This position is usually a unified standard and specification in the current automotive industry. The memory position refers to the position that is saved after the user manually adjusts the seat and clicks the memory button. The specific memory position is not limited, but is based on the result of the user's manual adjustment, which will not be elaborated here.

[0066] The drive motion rate refers to the speed at which the drive moves when adjusting the seat. Specifically, the movement speed is usually a uniform adjustment process, which is relatively slow to accommodate each user. This uniform adjustment process was set by the researchers based on relevant production requirements and is not limited here.

[0067] Its acquisition logic calculates the ratio of the distance difference between the user-preset memory position and the current seat position to the time required for the drive to move to the target position, and then multiplies this ratio by a pressure function to obtain the drive's motion rate Sv. i ;

[0068] It should be noted that the current seat position does not refer to the original position, but rather the distance difference between the adjusted seat position and the memory position, at which point the user is sitting in the seat.

[0069] Specifically, the distance difference between the user's preset memory position and the current seat position is obtained through Euclidean distance. A pressure function is established, with pressure as the independent variable and movement speed as the dependent variable. The best-fit curve is found using the least squares method, and then the parameters of the pressure function are calculated. The specific formula is expressed as follows:

[0070]

[0071] In the formula, Sv i Let D be the speed of the drive movement, D be the distance difference between the user's preset memory position and the current seat position, T be the time required for the drive to start moving to reach the target position, and K(p) be the pressure function.

[0072] The pressure function is expressed using an exponential model, specifically as follows:

[0073] K(p)=e ―dp

[0074] In the formula, e is the natural logarithm, p is the applied pressure, and -d is a positive parameter used to control the degree of influence of pressure on the rate;

[0075] Furthermore, when a user sits in the seat for the first time, they can manually adjust it to a satisfactory position and then click the memory button. The system will receive and save the current seat position data. When the user sits in the seat again and clicks the memory button, the seat will automatically adjust to the position of the last seat adjustment based on the data information sent by the system.

[0076] Furthermore, when a user presses and holds the memory button while getting out of the car, the system will calculate the adjustment range of the seat based on the user's characteristics and the seat's characteristics. After the user unlocks the vehicle, the seat inside the car will be adjusted to a suitable position based on the adjustment range calculated by the system, saving the user's time getting into the car and meeting the user's needs.

[0077] Therefore, all the above parameters are historical (data collected after the last time the passenger sat down), and will not be elaborated on here;

[0078] S2: Obtain the user-applied seat pressure value, seat automatic adjustment difference, and drive movement rate, establish a data analysis model, and obtain adjustment evaluation coefficients;

[0079] Among them, the data analysis model refers to the weighted analysis model, which generates adjusted evaluation coefficients through weighted calculations;

[0080] Get the user-applied seat pressure value Cp i Automatic seat adjustment differences i and the drive motion rate Sv i Generate adjusted evaluation coefficient Ec i The formula used is:

[0081]

[0082] In the formula, Ec i To adjust the evaluation coefficients, as well as Each of these parameters has a preset proportional coefficient for applying seat pressure to the user, adjusting seat automatically, and adjusting drive speed. as well as All are greater than 0;

[0083] Among them, the user-applied seat pressure value, the difference in automatic seat adjustment, and the drive motion rate are all data-driven representations that directly express the current trend of seat adjustment.

[0084] As can be seen from the above formula, when the user applies seat pressure and the seat automatically adjusts, the greater the difference, the more difficult the seat adjustment becomes. This indicates that the drive needs to overcome a greater load to achieve the adjustment, and the smaller the adjustment evaluation coefficient becomes. Conversely, the greater the drive's movement speed, the larger the adjustment evaluation coefficient becomes.

[0085] S3: Obtain the adjustment evaluation coefficient and compare it with the adjustment threshold to obtain the comparison result. Based on the comparison result label and its adjustment evaluation coefficient value, conduct a comprehensive analysis to determine the next seat adjustment range.

[0086] The logic for obtaining the adjustment threshold is to collect a set of historical seat adjustment positions, including adjustments made manually by users and adjustments made automatically by the seats. The dataset is then divided into a training set and a test set. Evaluation metrics and clustering algorithms are set. In each iteration of cross-validation, the model is trained on the training set and the model performance is evaluated on the test set. The threshold is then adjusted based on the performance of the validation set. Therefore, the adjustment threshold is constantly iterated and updated.

[0087] In this invention, clustering algorithms are a type of unsupervised learning algorithms used to divide data points in a dataset into groups or clusters with similarity. A common example is K-means clustering, which divides the data points in the dataset into K clusters such that the distance between each data point on the curve and the centroid of its cluster is minimized. Finally, the effect of the adjusted threshold is measured by Euclidean distance, thereby setting the adjustment threshold.

[0088] After obtaining the adjustment evaluation coefficients, the adjustment evaluation coefficients are compared and analyzed with the continuously iterated adjustment thresholds;

[0089] If the adjustment evaluation coefficient is greater than or equal to the adjustment threshold, the next wheel slip distance of the current seat is marked as a larger adjustment distance, and an adjustment signal is generated;

[0090] If the adjustment evaluation coefficient is less than the adjustment threshold, the next wheel slip distance of the current seat will be marked as the adjustment distance remains unchanged, and a hold signal will be generated;

[0091] The comparison results are labeled as having a larger adjustment distance and having no change in adjustment distance.

[0092] Count the number of labels with larger adjustment distances and their total adjustment evaluation coefficients, as well as the number of labels with unchanged adjustment distances and their total adjustment evaluation coefficients. Label the number of labels with larger adjustment distances as Q and the number of labels with unchanged adjustment distances as P, and substitute them into the formula for calculation:

[0093]

[0094] In the formula, W represents the seat adjustment range, and Ec... 较大 To adjust the total number of adjustment evaluation factors for the distance labels, Ec 不变 To adjust the total value of the evaluation coefficient for distance-invariant labels;

[0095] It should be noted that although the user is the same, the state of each ride or drive may be different. It is necessary to continuously adjust the next wheel slip distance of the seat based on historical data (i.e., the time of i data collection). Generally speaking, the average value of the seat pressure applied by the user is considered as the pressure index. When the user applies seat pressure greater than the average value, it means that the user is in a relaxed state. The drive speed will decrease slightly as the pressure increases. Therefore, it is necessary to reduce or keep the adjustment distance unchanged to complete the automatic memory adjustment of the seat as soon as possible and reduce fatigue on the seat slide rail.

[0096] The seat adjustment range is compared with the preset range threshold. If the seat adjustment range is greater than or equal to the range threshold, the seat position is adjusted backward to the first distance. If the seat adjustment range is less than the range threshold, the seat position is adjusted backward to the second distance.

[0097] It should be noted that the first distance and the second distance are adjustment distances determined by the researchers based on the specific user's height or weight. For example, adjusting the seat position back by 30% based on the user's height is set as the first distance, and adjusting the seat position back by 10% based on the user's weight is set as the second distance, etc., which will not be elaborated here.

[0098] The magnitude threshold is calculated based on the current adjustment evaluation coefficient and the historical seat adjustment magnitude set, and is not limited here;

[0099] This invention establishes a data analysis model by collecting data on the user-applied seat pressure, seat automatic adjustment differences, and drive movement speed. It obtains adjustment evaluation coefficients and compares them with adjustment thresholds to obtain comparison results. Based on the comparison result labels and their adjustment evaluation coefficient values, a comprehensive analysis is performed to determine the next seat adjustment range. The seat can more quickly meet the user's comfort angle and position, optimize the riding experience, improve seat adjustment efficiency and accuracy, and extend the service life of the long slide rail horizontal drive.

[0100] Example 2

[0101] In Embodiment 1 of this invention, a data analysis model is established by collecting user-applied seat pressure values, automatic seat adjustment differences, and actuator movement speed. Adjustment evaluation coefficients are obtained and compared with adjustment thresholds to obtain comparison results. Based on the comparison result labels and their adjustment evaluation coefficient values, a comprehensive analysis is performed to determine the operational strategy for the next seat adjustment. However, Embodiment 1 only considers the perspective of a single user's long-term use. Obviously, if the user does not delete the set automatic seat memory information, other users will make unnecessary position adjustments when using the seat, which not only fails to meet the needs of new users but also affects the usage frequency of the long-rail horizontal actuator. To address these issues, Embodiment 2 of this invention provides further refinement.

[0102] S4: Obtain the next seat adjustment range, collect the current user's applied seat pressure value and compare it with the maximum and minimum values ​​of the previous historical user, select to collect the current user's features based on the comparison results and calculate the similarity between the current user's features and the features of users in each historical segment to obtain the current user's feature similarity, and then perform cluster analysis based on the historical user's setting preferences in the user feature similarity to obtain the similar historical user's setting preference values.

[0103] The adjustment range for the next seat adjustment will follow the adjustment strategy described in Example 1 above, and will not be repeated here;

[0104] Each historical user corresponds to a historical segment. Specifically, when a user presses the memory button twice consecutively during a ride, it is recorded as one historical segment. The historical segment is determined based on the user's actions. When the next passenger enters the vehicle, the seat will remain in its original position, and the new user will need to manually adjust it to a suitable position and then press the memory button to lock the current memory position. Alternatively, if the current user applies seat pressure less than the minimum value or greater than the maximum value during a ride, the system will automatically divide it into a historical segment. The time from the end of the previous historical segment to the current time is recorded as one historical segment.

[0105] It should be noted that the historical segmentation is different from the collection time i mentioned above. The historical segmentation includes multiple collection times. Those skilled in the art will understand that the historical segmentation is usually set by different body weights of different users or by resetting memory buttons, etc., which is not limited here.

[0106] The current user's applied seat pressure value is compared with the maximum and minimum values ​​of the previous historical user. If it is less than the minimum value or greater than the maximum value, the current user's characteristics are collected and similarity is calculated with the characteristics of users in each historical segment. Otherwise, the adjustment is made according to the memory position of the previous historical user.

[0107] For example, the maximum seat pressure applied by a user (100 kg) during use of the seat is 3266 Pa (assuming the seat area is 0.3 square meters and there is no backrest), and the minimum is 1960 Pa (assuming the seat area with backrest is 0.5 square meters and there is a full backrest). The current user applies a seat pressure of 1300 Pa. The current user is completely different from the previous user, so the memory position needs to be readjusted. However, the current user has blankness (that is, it is impossible to know the seat position and angle that he / she feels comfortable in, and it is impossible to know his / her other parameters except for weight or height. Even if the memory position is verified by inputting weight or height into a large model database, it still has universality and cannot improve the possibility of satisfying the user). It is impossible to analyze the memory position required by him / her according to the parameters in Example 1.

[0108] The current user characteristics include user weight, height, and waist circumference; the user characteristics of each historical segment correspond to the current user characteristics.

[0109] Specifically, the user's weight, height, and waist circumference are calculated by multiplying the area of ​​the user's seat coverage by the pressure values ​​obtained from pressure sensors. Height is measured using laser sensors. Waist circumference is calculated by substituting the average and maximum pressure values ​​in the waist area obtained from pressure sensors into a linear regression model. Historical data is used to establish the relationship between pressure and waist circumference, as shown in the following formula:

[0110] Wa = a·average pressure value + b·maximum pressure value + c

[0111] Where Wa is the user's waist circumference, and a, b, and c are coefficients trained based on historical data;

[0112] Furthermore, the current user feature similarity is obtained through cosine similarity, with the specific formula as follows:

[0113]

[0114] In the formula, Cs n Let A be the feature similarity of the current user, B be the feature vector of the current user, ‖A‖ be the feature vector magnitude of the current user, ‖B‖ be the feature vector magnitude of the historical user, and n be the nth comparison number.

[0115] Specifically, the feature vector of the current user is expressed as {We,He,Wa}, and the feature vector of the historical user is expressed as {hitoricalWe,hitoricalHe,hitoricalWa}; where We is the user's weight and He is the user's height.

[0116] Furthermore, the current user's feature vector magnitude is:

[0117]

[0118] The feature vector magnitude of historical users is:

[0119]

[0120] Calculate the similarity of features for all current users, set the memory location of similar historical users as feature data, and construct a feature matrix X. Set the number of clusters k, and calculate the value J(k) of the specific number of clusters k through a cost function, the specific formula of which is:

[0121]

[0122] In the formula, S j For the j-th cluster, C j x is the center of the j-th cluster. iSample points belonging to this cluster;

[0123] The calculated k value and J(k) value are plotted together, usually with k as the horizontal axis and J(k) as the vertical axis.

[0124] Observe the trend of J(k) changing with k in the graph. As k increases, J(k) gradually decreases; find the position in the curve where the rate of decrease slows down significantly, and take it as the optimal value of the number of clusters k;

[0125] Randomly select k user features as initial cluster centers C. For each user feature x i Calculate its relationship with each cluster center C j The Euclidean distance is used to assign user features to the nearest cluster;

[0126] Update cluster center C j For the current cluster S j The mean of all user characteristics is calculated using the following formula:

[0127]

[0128] When the cluster centers no longer change significantly, or the user assignments no longer change, the algorithm is considered to have converged. The final cluster centers and cluster labels for each user feature are obtained, and the weighted average is used to obtain the preference values ​​of similar historical users.

[0129] S5: Input the current user's feature similarity and the preference values ​​of similar historical users into fuzzy logic to determine the initial adjustment result of the current user's seat;

[0130] For example, "High", "Low", and "Medium" indicate the high, medium, and low similarity of current user characteristics, while "Many", "Less", and "Average" indicate the high, medium, and low preference values ​​of similar historical users.

[0131] Develop a set of fuzzy rules to describe the impact of different input variables on the output variable. The rules can be defined based on expertise or obtained through data analysis and experimentation. For example:

[0132] Label the current user's feature similarity as X, label the similar historical user's preference value as U, and label the current user's initial seat adjustment result as C_results;

[0133] Then it can be defined as:

[0134] Rule 1:IF(X is High)AND(U is Many)THEN(C_results is Recommend)

[0135] Rule 2:IF(U is Low)AND(U is Less)THEN(C_results is Objection) ...

[0137] Based on fuzzy rules, perform fuzzy reasoning to determine the initial seat adjustment plan for the current user;

[0138] It should be noted that the division of fuzzy sets can be adjusted according to the actual situation. For example, although this embodiment uses three fuzzy sets as an example, it can actually be divided into more than three sets to facilitate more precise adjustment based on different similarities.

[0139] Furthermore, the judgment of the similarity of current user features and the high, medium and low preferences of similar historical users can be made by setting thresholds according to the actual situation. For example, when the similarity of current user features exceeds 80%, it is marked as "High", and when the similarity of historical users' preferences is higher than 74%, it is marked as "Many", etc., which will not be elaborated here.

[0140] This invention obtains the next seat adjustment range, formulates a set of fuzzy rules based on the similarity of current user characteristics and the setting preference values ​​of similar historical users, and performs fuzzy inference to determine the initial seat adjustment plan for the current user. This reduces unnecessary position adjustments, meets the riding needs of new users, and improves the accuracy and operational intelligence of the long slide rail horizontal drive.

[0141] Example 3

[0142] Please see Figure 2 A horizontal drive control system for a long slide rail of a new energy vehicle seat includes a data acquisition module, a data processing module, an adjustment and analysis module, and a user optimization module.

[0143] The data acquisition module is used to collect user-applied information and seat feature information. Through data processing, it obtains the user-applied seat pressure value, seat automatic adjustment difference, and drive movement rate, and sends them to the data processing module.

[0144] The data processing module is used to acquire the user-applied seat pressure value, seat automatic adjustment differences, and drive movement rate, establish a data analysis model, obtain adjustment evaluation coefficients, and send them to the adjustment analysis module;

[0145] The adjustment analysis module is used to obtain the adjustment evaluation coefficient and compare it with the adjustment threshold to obtain the comparison result. Based on the comparison result label and its adjustment evaluation coefficient value, a comprehensive analysis is performed to determine the next seat adjustment range and send it to the user optimization module.

[0146] The user optimization module is used to obtain the next seat adjustment range. It collects the seat pressure value applied by the current user and compares it with the maximum and minimum values ​​of the previous historical user. Based on the comparison results, it selects to collect the current user features and calculates the similarity between the current user features and the user features of each historical segment. Then, it performs cluster analysis based on the historical user setting preferences in the user feature similarity to obtain the similar historical user setting preference values ​​and uses them to determine the preliminary seat adjustment result for the current user.

[0147] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0148] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0149] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0150] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0151] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0152] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0153] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0154] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0155] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0156] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A control method of a horizontal driver of a long slide rail of a new energy vehicle seat, characterized in that: The method comprises the following steps: S1: Collect user exertion information and seat characteristic information, and obtain user exertion seat pressure value, seat automatic adjustment difference and driver movement rate through data processing; S2: Obtain user exertion seat pressure value, seat automatic adjustment difference and driver movement rate, establish a data analysis model, and obtain an adjustment evaluation coefficient; S3: Obtain the adjustment evaluation coefficient, compare it with an adjustment threshold value, obtain a comparison result, comprehensively analyze the comparison result label and the adjustment evaluation coefficient value, and determine the next seat adjustment amplitude; S4: Obtain the seat adjustment amplitude, collect the current user exertion seat pressure value, compare it with the maximum value and the minimum value of the previous historical user, select the current user characteristics according to the comparison result, calculate the similarity between the current user characteristics and the characteristics of each historical segmented user, obtain the current user characteristic similarity, and perform clustering analysis according to the similar historical user setting preference in the user characteristic similarity, to obtain a similar historical user setting preference value; S5: Bring the current user characteristic similarity and the similar historical user setting preference value into fuzzy logic to determine the current user seat preliminary adjustment result; The user exertion information comprises user exertion seat pressure value; The seat characteristic information comprises seat automatic adjustment difference and driver movement rate; Measuring the pressure on the seat surface by means of a pressure sensor gives the user-applied seat pressure value ; wherein i denotes the i-th acquisition time; The coordinates of the original position and the memory position are defined, the difference of each coordinate axis is calculated, and the seat automatic adjustment difference is obtained according to the Euclidean distance ; The distance difference between the memory position preset by the user and the current seat position is compared with the time required for the driver to start moving to reach the target position, and multiplied by a pressure function to obtain the driver movement rate . 2.The control method of the horizontal driver of the long slide rail of the new energy vehicle seat according to claim 1, characterized in that: Obtaining a user-applied seat pressure value , seat automatic adjustment variance , and driver motion rate , generating an adjustment evaluation coefficient , according to the formula: In the formula, to adjust the evaluation coefficient, , and are respectively preset proportional coefficients of the user-applied seat pressure value, the seat automatic adjustment difference, and the driver motion rate, and , and are all greater than 0. 3.The control method of the horizontal driver of the long slide rail of the new energy vehicle seat according to claim 2, characterized in that: After obtaining the adjustment evaluation coefficient, compare the adjustment evaluation coefficient with the continuously iterated adjustment threshold value; If the adjustment evaluation coefficient is greater than or equal to the adjustment threshold value, mark the next wheel slip distance of the current seat as a large adjustment distance, and generate an adjustment signal; If the adjustment evaluation coefficient is less than the adjustment threshold value, mark the next wheel slip distance of the current seat as an unchanged adjustment distance, and generate a keep signal.

4. The control method of claim 3, wherein: The comparison result label comprises a large adjustment distance and an unchanged adjustment distance; Statistically, the number of labels of the large adjustment distance and the total value of the adjustment evaluation coefficient, and the number of labels of the unchanged adjustment distance and the total value of the adjustment evaluation coefficient are obtained; the number of labels of the large adjustment distance is marked as Q, and the number of labels of the unchanged adjustment distance is marked as P, which are substituted into the formula to calculate: In the formula, is the adjustment range of the seat, is the total value of the adjustment evaluation coefficient of the adjustment distance label, is the total value of the adjustment evaluation coefficient of the adjustment distance constant label; Compare the seat adjustment amplitude with a preset amplitude threshold value; if the seat adjustment amplitude is greater than or equal to the amplitude threshold value, adjust the seat position backward to a first distance; if the seat adjustment amplitude is less than the amplitude threshold value, adjust the seat position backward to a second distance.

5. The new energy vehicle seat long slide rail horizontal driver control method according to claim 4, characterized in that: The historical user corresponds to each historical segment; collect the current user exertion seat pressure value, compare it with the maximum value and the minimum value of the previous historical user, collect the current user characteristics if it is less than the minimum value or greater than the maximum value, and calculate the similarity between the current user characteristics and the characteristics of each historical segmented user; otherwise, adjust the memory position of the previous historical user; The current user characteristics comprise user weight, height and waist circumference; the characteristics of each historical segmented user correspond to the current user characteristics, and the current user characteristic similarity is obtained through cosine similarity; Statistically, all current user characteristic similarities are obtained, the similar historical user setting memory position is taken as characteristic data, clustering analysis is performed, a characteristic matrix X is constructed, the number k of clusters is set, and the specific number k of clusters is obtained through a cost function. When the clustering center no longer changes significantly, or the user assignment no longer changes, the algorithm is recorded as converging, and the final clustering center and clustering label of each user feature are obtained. The weighted average is used to obtain the similar historical user setting preference value. 6.The control method of the horizontal driver of the long slide rail of the new energy vehicle seat according to claim 5, characterized in that: The current user feature similarity and the similar historical user setting preference value are defined as input variables and are divided into different fuzzy sets respectively; The current user seat preliminary adjustment result is defined as an output variable and is divided into a fuzzy set; Fuzzy rules are developed to describe the influence of the current user feature similarity and the similar historical user setting preference value on the current user seat preliminary adjustment result. According to the fuzzy rules, the fuzzy reasoning is carried out to determine the current user seat preliminary adjustment scheme.

7. A new energy vehicle seat long slide rail horizontal driver control system for implementing the new energy vehicle seat long slide rail horizontal driver control method of any one of claims 1-6, characterized in that: The system comprises a data acquisition module, a data processing module, an adjustment analysis module, and a user optimization module. The data acquisition module is used to collect user applied information and seat feature information, and through data processing, user applied seat pressure values, seat automatic adjustment differences, and driver movement rates are obtained and sent to the data processing module. The data processing module is used to obtain user applied seat pressure values, seat automatic adjustment differences, and driver movement rates, establish a data analysis model, obtain adjustment evaluation coefficients, and send them to the adjustment analysis module. The adjustment analysis module is used to obtain adjustment evaluation coefficients and compare them with adjustment threshold values to obtain comparison results. Based on the comparison result labels and their adjustment evaluation coefficient values, the next seat adjustment amplitude is determined and sent to the user optimization module. The user optimization module is used to obtain the seat adjustment amplitude, collect the current user applied seat pressure value, and compare it with the previous historical user maximum and minimum values. According to the comparison result, the current user feature is selected and the similarity between each historical segmented user feature is calculated to obtain the current user feature similarity. Then, the clustering analysis is carried out according to the user feature similarity and the historical user setting preference to obtain the similar historical user setting preference value, which is input into the fuzzy logic to determine the current user seat preliminary adjustment result.

Images