Electric seat adjusting method and device and vehicle

Abstract

The invention discloses an electric seat adjusting method and device and a vehicle, and relates to the technical field of intelligent cabins, and the method comprises the steps: encoding an electric seat adjusting parameter into a first particle swarm, and optimizing the first particle swarm through employing a particle swarm algorithm every time an adjusting period, thereby achieving the dynamic optimization of the electric seat adjusting parameter, and improving the adjustment precision of the electric seat. Meanwhile, the dynamic change of the body shape of the user, the continuity requirement in the driving process and the balance between the comfort and the safety of the seat are considered, and deep optimization in the comfortable direction, the safe direction and the healthy direction can be achieved under the condition that the deep optimization condition is met; therefore, the adjustment of the electric seat in different emphasizing directions is realized.

Description

Technical Field

[0001] The present application relates to the technical field of smart cockpits, and more specifically, to an electric seat adjustment method, device, and vehicle. Background Art

[0002] With the development of smart cockpit technology, intelligent seat adjustment has become a core component in enhancing the driving experience. Existing seat adjustment technologies primarily rely on preset modes (such as memory seats) or simple manual adjustment mechanisms. Related technologies integrate vital sign sensors (such as pressure and temperature sensors) within the seat's soft protective layer, optimizing data acquisition accuracy and improving user comfort, thereby enhancing the intelligent cockpit experience. While these technologies achieve a certain degree of smart cockpit adjustment, they often rely on static preset parameters or a single optimization strategy, failing to simultaneously account for the dynamic changes in the user's body shape, the need for continuity during driving, and the balance between seat comfort and safety. Summary of the Invention

[0003] The present application provides an electric seat adjustment method, device and vehicle, aiming to solve the problem that related technologies cannot simultaneously take into account the dynamic changes in passenger body shape, the continuity requirements during driving, and the balance between seat comfort and safety.

[0004] A first aspect of the present application provides a method for adjusting an electric seat, comprising: Initializing a first particle swarm using the electric seat adjustment parameters, and iterating the first particle swarm every adjustment cycle to obtain a first particle swarm after iteration; determining a first target electric seat adjustment parameter value based on the first particle swarm after iteration, and adjusting the electric seat according to the first target electric seat adjustment parameter value; When the vehicle meets the deep optimization conditions, constructing second particle swarms in different optimization directions, and iterating the second particle swarms in different optimization directions to determine non-inferior solutions in different optimization directions; the optimization directions include comfort direction, safety direction, and health direction; The non-inferior solutions in different optimization directions are stored to provide a reference for personalized electric seat adjustment.

[0005] In this solution, the electric seat adjustment parameters are encoded into a first particle swarm, and the particle swarm algorithm is used to optimize the first particle swarm after each adjustment cycle, thereby achieving dynamic optimization of the electric seat adjustment parameters. At the same time, it takes into account the dynamic changes in the user's body shape, the continuity requirements during driving, and the balance between seat comfort and safety. At the same time, when the deep optimization conditions are met, deep optimization in three directions, namely comfort, safety, and health, can be achieved, thereby realizing electric seat adjustment with different emphasis directions.

[0006] In conjunction with the first aspect, in a possible implementation, the method further includes: In the event of emergency braking, a collision warning signal is generated; The collision warning signal is used as a trigger condition to trigger instantaneous optimization of the electric seat; the instantaneous optimization includes: adjusting the electric seat according to a second target electric seat adjustment parameter value under a preset collision scenario.

[0007] In this solution, by using the collision warning signal as a trigger condition to trigger the instantaneous optimization of the electric seat, collision warning can be effectively achieved and the user's driving safety can be improved.

[0008] In combination with the first aspect, in a possible implementation, iterating the first particle swarm to obtain the iterated first particle swarm includes: Obtaining the historical optimal particle and the swarm optimal particle corresponding to the particle in the first particle swarm; Clustering the first particle group to obtain a plurality of subgroups belonging to the first particle group; Extracting the local optimal particle in each subgroup, and iterating the particles in the subgroup according to the local optimal particle in the subgroup, the historical optimal particle corresponding to the particle, and the optimal particle of the population, to obtain a subgroup after iteration; The sub-groups after multiple iterations are merged into one particle group to obtain the first particle group after iteration.

[0009] In this scheme, the particle swarm algorithm is improved by clustering algorithm, which can effectively enhance the ability of particle swarm algorithm to escape local optimality, thereby improving the optimization ability of particle swarm algorithm and ultimately improving the optimization accuracy of electric seat adjustment parameters.

[0010] In combination with the first aspect, in a possible implementation, after iterating the first particle swarm and obtaining the iterated first particle swarm, the method further includes: Obtain the fitness of each particle in the first particle swarm after iteration, and update the historical optimal particle corresponding to each particle and the swarm optimal particle corresponding to all particles according to the fitness of the particle, so as to provide supporting data for the iteration of the first particle swarm in the next adjustment cycle.

[0011] In this solution, by maintaining the historical optimal particle corresponding to each particle and the population optimal particle corresponding to all particles, the continuous optimization capability of the electric seat adjustment parameters can be effectively guaranteed.

[0012] In conjunction with the first aspect, in a possible implementation, obtaining the fitness corresponding to each particle in the first particle swarm after iteration includes: The comfort, safety factor, and health index corresponding to the particles in the first particle swarm after iteration are obtained, and the comfort, safety factor, and health index are weighted and summed to obtain the fitness corresponding to the particles.

[0013] In this solution, the fitness corresponding to the particle is obtained by weighted summation of the comfort, safety factor and health index, so that the adjustment process of the electric seat adjustment parameters takes into account the comfort, safety factor and health index at the same time, thereby improving the user experience.

[0014] In combination with the first aspect, in one possible implementation, determining a first target electric seat adjustment parameter value based on the first particle swarm after iteration, and adjusting the electric seat according to the first target electric seat adjustment parameter value include: Based on the first particle swarm after iteration, the particle with the largest fitness is determined as the first target electric seat adjustment parameter value; The electric seat is adjusted according to the first target electric seat adjustment parameter value.

[0015] In this solution, the electric seat is adjusted by using the first target electric seat adjustment parameter value obtained through particle swarm algorithm optimization, thereby achieving rapid adjustment and continuous optimization of the electric seat.

[0016] In combination with the first aspect, in one possible implementation, when the vehicle satisfies the deep optimization condition, constructing second particle swarms in different optimization directions, and iterating the second particle swarms in different optimization directions to determine non-inferior solutions in different optimization directions includes: When the vehicle satisfies the deep optimization condition, adjusting the weighted weight of the comfort in the fitness function so that the weighted weight of the comfort is greater than the weight of the safety factor and the weight of the health index, thereby obtaining a first adjusted fitness function; Initializing a second particle swarm corresponding to a comfort direction using the electric seat adjustment parameter, and optimizing the second particle swarm corresponding to the comfort direction using the first adjustment fitness function as an optimization target to determine a non-inferior solution in the comfort direction; When the vehicle satisfies the deep optimization condition, adjusting the weighted weight of the safety factor in the fitness function so that the weighted weight of the safety factor is greater than the weight of the comfort level and the weight of the health index, thereby obtaining a second adjusted fitness function; Initializing a second particle swarm corresponding to a safety direction using the electric seat adjustment parameter, and optimizing the second particle swarm corresponding to the safety direction using the second adjustment fitness function as an optimization target to determine a non-inferior solution in the safety direction; When the vehicle satisfies the deep optimization condition, adjusting the weighted weight of the health index in the fitness function so that the weighted weight of the comfort is greater than the weight of the safety factor and the weighted weight of the comfort, thereby obtaining a third adjusted fitness function; The electric seat adjustment parameter is used to initialize the second particle swarm corresponding to the healthy direction, and the third adjustment fitness function is used as the optimization target to optimize the second particle swarm corresponding to the healthy direction to determine a non-inferior solution in the healthy direction.

[0017] In this solution, by determining the non-inferior solution in the comfort direction, the non-inferior solution in the safety direction, and the non-inferior solution in the health direction, the electric seat adjustment parameter values ​​suitable for different adjustment directions can be obtained to meet the needs of different users.

[0018] With reference to the first aspect, in one possible implementation, determining non-inferior solutions in different optimization directions includes: During the iterative process of the second particle swarm in the different optimization directions, the ε dominance criterion is used to screen and maintain the multi-objective Pareto front solutions to obtain non-inferior solutions in the different optimization directions.

[0019] In this scheme, the ε-dominance criterion is used to screen and maintain the multi-objective Pareto frontier solution, which can effectively solve the multi-dimensional parameters and improve the optimization capability.

[0020] Based on the same inventive concept, the second aspect of the present application provides an electric seat adjustment device, comprising: A first iteration module is configured to initialize a first particle swarm using the electric seat adjustment parameters, and iterate the first particle swarm every adjustment period to obtain a first particle swarm after iteration; a real-time adjustment module, configured to determine a first target electric seat adjustment parameter value based on the first particle swarm after iteration, and adjust the electric seat according to the first target electric seat adjustment parameter value; A deep optimization module is used to construct a second particle swarm in different optimization directions when the vehicle meets the deep optimization conditions, and iterate the second particle swarm in different optimization directions to determine non-inferior solutions in different optimization directions; the optimization directions include comfort direction, safety direction, and health direction; The database module is used to store non-inferior solutions in different optimization directions and provide a reference for personalized electric seat adjustment.

[0021] Based on the same inventive concept, a third aspect of the present application provides a vehicle, comprising an electric seat adjustment device as described in any possible embodiment of the first aspect.

[0022] Among them, the technical effects brought about by any implementation method in the second aspect and the third aspect can refer to the technical effects brought about by different implementation methods in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0024] Figure 1 This is a flow chart of a method for adjusting an electric seat proposed in one embodiment of the present application; Figure 2 This is a flowchart of iterating the first particle group proposed in one embodiment of the present application; Figure 3 This is a schematic structural diagram of an electric seat adjustment device proposed in one embodiment of the present application; Figure 4 This is a schematic structural diagram of an electronic device proposed in one embodiment of the present application; Explanation of the reference numerals: 301 - first iteration module, 302 - real-time adjustment module, 303 - depth optimization module, 304 - database module, 305 - instantaneous optimization module, 401 - memory, 402 - processor, 403 - communication bus. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0026] Related technologies mostly use static preset parameters or a single optimization strategy, which cannot simultaneously take into account the dynamic changes in the user's body shape, the continuity requirements during driving, and the balance between seat comfort and safety.

[0027] In view of this, an embodiment of the present application proposes an electric seat adjustment method, which realizes continuous optimization of electric seat adjustment parameters through particle swarm algorithm, taking into account the dynamic changes of user body shape and continuity requirements during driving, and obtains non-inferior solutions in different optimization directions through deep optimization, providing a reference basis for personalized electric seat adjustment and balancing seat comfort and safety.

[0028] Please refer to Figure 1 , is a flow chart of an electric seat adjustment method provided in an embodiment of the present application, the electric seat adjustment method comprising: S101: Initialize a first particle swarm using electric seat adjustment parameters, and iterate the first particle swarm every adjustment cycle to obtain the first particle swarm after iteration.

[0029] The electric seat adjustment parameters may be some adjustment parameters related to the electric seat shape, and may include: (1) Seat cushion tilt (0-15°), affecting the pelvic tilt angle and optimizing the lumbar spine force; (2) Backrest angle (90-135°), affecting back support; (3) Seat height (up and down adjustment range), affecting vision and pedal operation; (4) Lumbar support curvature radius (50-150mm), affecting the lumbar spine support form; (5) Side wing clamping force gradient (5-30N / cm²): enhancing lateral stability when cornering; (6) Seat cushion hardness gradient (N / mm² distribution), optimizing long-distance driving comfort; (7) Dynamic pressure distribution adjustment (multi-zone independent control), improving body pressure uniformity; (8) Headrest forward and backward movement range (0-50mm), optimizing neck support. After each adjustment cycle, these parameters are optimized through the particle swarm algorithm, which can effectively achieve dynamic adjustment of the electric seat. The particle swarm algorithm refers to a group intelligence optimization algorithm. The particle swarm refers to a group composed of multiple particles in the particle swarm algorithm during the optimization process. Each particle in the particle swarm represents a potential solution. The particle swarm algorithm iteratively optimizes the particle swarm so that the particles adjust their speed and position according to their own experience and the experience of the group, and continuously iterates to find the optimal solution. In an embodiment of the present application, any particle in the particle swarm can represent a combination of values ​​of the electric seat adjustment parameters. By optimizing the particle swarm, the optimal combination of values ​​of the electric seat adjustment parameters is found, thereby obtaining the optimal solution of the combination of values ​​of the electric seat adjustment parameters. In addition to the particle swarm algorithm, other group intelligence optimization algorithms can also be used to solve the optimal combination of values ​​of the electric seat adjustment parameters. For example, bionic optimization algorithms such as genetic algorithms and lion group optimization algorithms can also be used to solve the optimal combination of values ​​of the electric seat adjustment parameters.

[0030] Electric seat adjustment parameters can also include biomechanical parameters and vehicle dynamic environment related parameters. Biomechanical parameters can include: (1) BMI (body mass index) body adaptation factor (based on historical data acquisition); (2) spinal curvature adaptation parameters (3D modeling to correct sitting posture); (3) femur-calf angle (dynamic adjustment of leg support); (4) shoulder-waist pressure distribution balance coefficient; (5) electromyographic signal (EMG) optimization factor (based on muscle fatigue state for quantitative description). Vehicle dynamic environment related parameters can include: (1) driving mode related parameters (sport / comfort / economy mode switching); (2) posture adjustment coefficient during sudden braking (to prevent inertial forward rush); (3) long-distance driving fatigue accumulation parameter (to monitor the driver's fatigue level); (4) seat temperature adjustment parameters (to optimize thermal comfort); (5) vibration filtering factor (to reduce the impact of road vibration).

[0031] Biomechanical parameters and vehicle dynamic environment-related parameters can be set with corresponding electric seat adjustment strategies. For example, different BMI body adaptation factors may be adapted to the adjustment parameters of the front and rear travel of the electric seat. By adjusting the BMI body adaptation factor, adaptation to users of different body shapes can be achieved.

[0032] S102 : Determine a first target electric seat adjustment parameter value based on the first particle swarm after iteration, and adjust the electric seat according to the first target electric seat adjustment parameter value.

[0033] After one iteration of the first particle swarm, it can be considered that the electric seat adjustment parameters are optimized during driving. The particle with the largest fitness can be determined from the first particle swarm after the iteration as the first target electric seat adjustment parameter value, and the electric seat can be adjusted according to the first target electric seat adjustment parameter value, thereby meeting the continuity requirement for electric seat adjustment during driving.

[0034] The fitness can be a weighted sum of comfort, safety factor, and health index. By obtaining the fitness corresponding to the particle, the electric seat adjustment parameter value in the particle can be evaluated, thereby achieving comprehensive optimization of passenger comfort, safety, and health status.

[0035] Exemplarily, determining a first target power seat adjustment parameter value based on the first particle swarm after iteration and adjusting the power seat according to the first target power seat adjustment parameter value may include: determining the particle with the highest fitness as the first target power seat adjustment parameter value based on the first particle swarm after iteration. The first target power seat adjustment parameter value may be transmitted to a vehicle computer capable of controlling the power seat, so that the vehicle computer can adjust the power seat according to the first target power seat adjustment parameter value. Adjusting the power seat using the first target power seat adjustment parameter value obtained through particle swarm optimization achieves rapid adjustment and continuous optimization of the power seat.

[0036] S103: If the vehicle meets the deep optimization conditions, construct a second particle swarm in different optimization directions, and iterate the second particle swarm in different optimization directions to determine non-inferior solutions in different optimization directions. The optimization directions include comfort direction, safety direction, and health direction.

[0037] If the vehicle is charging or stationary for more than a preset time threshold, it is considered that the vehicle meets the deep optimization conditions. At this time, the vehicle's computing power is idle, and optimization can be performed in the comfort, safety and health directions respectively, so that the seat adjustment can meet the user's personalized requirements.

[0038] For example, the weights corresponding to the comfort level, safety factor, and health index in the fitness function can be adjusted, and a second particle swarm can be constructed in different optimization directions. The second particle swarm can be iterated using the adjusted fitness to determine non-inferior solutions in different optimization directions. For example, the comfort level in the fitness function can be modulated to the maximum to obtain a fitness function in the comfort direction. Then, a second particle swarm can be constructed. The constructed second particle swarm can be iterated using the fitness function in the comfort direction to determine a non-inferior solution in the comfort direction. The methods for obtaining non-inferior solutions in the safety and health directions are similar.

[0039] S104. Store non-inferior solutions in different optimization directions to provide a reference for personalized electric seat adjustment.

[0040] The non-inferior solutions in different optimization directions can be stored in a cloud database, allowing users to access and use the non-inferior solutions in the cloud database during subsequent use of the vehicle. Each non-inferior solution contains electric seat adjustment parameter values ​​with different optimization effects. By allowing users to access and use non-inferior solutions, the user's personalized needs are met.

[0041] By encoding the electric seat adjustment parameters into the first particle swarm and optimizing the first particle swarm using the particle swarm algorithm after each adjustment cycle, dynamic optimization of the electric seat adjustment parameters is achieved. At the same time, the dynamic changes in the user's body shape, the continuity requirements during driving, and the balance between seat comfort and safety are taken into account. At the same time, when the deep optimization conditions are met, deep optimization in three directions, namely comfort, safety, and health, can be achieved, thereby realizing electric seat adjustment with different focuses.

[0042] In a possible implementation, the electric seat adjustment method further includes: In the event of emergency braking, a collision warning signal is generated.

[0043] For example, when the brake depression stroke exceeds a preset threshold for a fixed time (such as when the brake depression stroke exceeds a preset threshold of 2S), it can be considered that emergency braking has occurred, and a collision warning signal can be generated.

[0044] The collision warning signal is used as a trigger condition to trigger instantaneous optimization of the electric seat. The instantaneous optimization includes: adjusting the electric seat according to a second target electric seat adjustment parameter value under a preset collision scenario.

[0045] The collision warning signal serves as a trigger signal. When the collision warning signal exists, the electric seat can be instantly optimized, which can effectively realize collision warning and improve the user's driving safety.

[0046] The method for obtaining the second target electric seat adjustment parameter value under a preset collision scenario may include: adjusting the weight of the safety factor in the fitness function to the maximum, and using the particle swarm algorithm to adjust the second target electric seat adjustment parameter value based on the fitness function in which the weight of the safety factor is adjusted to the maximum.

[0047] Please refer to Figure 2 , is a flowchart of iterating the first particle group provided in the embodiment of the present application. Figure 2 As shown, the first particle swarm is iterated to obtain the first particle swarm after iteration, including: S201: Obtain the historical optimal particle and the swarm optimal particle corresponding to the particle in the first particle swarm.

[0048] The historical optimal particle and the swarm optimal particle corresponding to the particles in the first particle group are updated after each iteration. Therefore, in step S201 , the historical optimal particle and the swarm optimal particle can be directly read.

[0049] S202: Cluster the first particle swarm to obtain multiple subgroups belonging to the first particle swarm.

[0050] The particles in the first particle swarm can be clustered using a k-means clustering algorithm to divide the particles in the first particle swarm into k subgroups. For example, the k value can be set to 5, thereby obtaining five subgroups belonging to the first particle swarm.

[0051] S203: extract the local optimal particle in each subgroup, and iterate the particles in the subgroup according to the local optimal particle in the subgroup, the historical optimal particle corresponding to the particle, and the optimal particle of the population to obtain the subgroup after iteration.

[0052] In the existing particle swarm algorithm, there is usually a problem of being easily trapped in the local optimum, which makes it impossible to accurately optimize the electric seat adjustment parameters. Therefore, the embodiment of the present application iterates the particles in the subgroup based on the local optimal particles in the subgroup, the historical optimal particles corresponding to the particles, and the optimal particles of the population, thereby improving the global optimization capability and making the optimization of the electric seat adjustment parameters more accurate.

[0053] For example, according to the local optimal particle in the subgroup, the historical optimal particle corresponding to the particle, and the optimal particle of the population, the particles in the subgroup are iterated as follows:

[0054]

[0055]

[0056] in, Indicates the t During the iteration i particles, Indicates the t During the iteration i The speed of each particle is Indicates the t During the +1 iteration i The speed of each particle is represents the inertia weight, represents the first learning factor, represents the second learning factor, represents the first random number between (0,1), represents the second random number between (0,1), Indicates the i The historical optimal particle corresponding to the particle, represents the optimal particle in the population, represents the third learning factor, represents the third random number between (0,1), represents the local optimal particle, Indicates the i Particles after iterations.

[0057] The inertia weight can be set as a dynamic weight, such as w =0.9-0.5×(number of iterations / preset total number of iterations)), ensuring that the algorithm has greater global exploration capabilities in the early stages of search, while focusing more on local details in the convergence stage.

[0058] In order to ensure that the adjustment parameters are always within the mechanical safety range, a constraint processing mechanism can also be designed: when a dimension parameter of a particle exceeds the mechanical limit, a mirror reflection repair strategy is adopted (for example: when the parameter x > upper limit a, x '=2 a - x When x < lower limit b hour, x '= 2 b - x , x 'Indicates the parameters after over-limit processing x ).

[0059] S204: Merge the subgroups after multiple iterations into one particle swarm to obtain the first particle swarm after iteration.

[0060] By improving the particle swarm algorithm through clustering algorithm, the ability of the particle swarm algorithm to escape local optimality can be effectively enhanced, thereby improving the optimization ability of the particle swarm algorithm and ultimately improving the optimization accuracy of the electric seat adjustment parameters.

[0061] In a possible implementation, after iterating the first particle swarm and obtaining the iterated first particle swarm, the method further includes: Obtain the fitness of each particle in the first particle swarm after iteration, and update the historical optimal particle corresponding to each particle and the swarm optimal particle corresponding to all particles according to the fitness of the particle, so as to provide support data for the iteration of the first particle swarm in the next adjustment cycle.

[0062] By maintaining the historical optimal particle corresponding to each particle and the population optimal particle corresponding to all particles, the continuous optimization capability of the electric seat adjustment parameters can be effectively guaranteed.

[0063] In a possible implementation, obtaining the fitness corresponding to each particle in the first particle swarm after iteration includes: The comfort, safety factor, and health index corresponding to the particles in the first particle swarm after iteration are obtained and weighted summed to obtain the corresponding fitness of the particles. This weighted sum of comfort, safety, and health index allows the adjustment process of the electric seat adjustment parameters to take into account comfort, safety, and health, improving the user experience.

[0064] Exemplarily, the fitness can be obtained through a fitness function, and the fitness function can be set to:

[0065] in, represents fitness, C Indicates comfort, S represents the safety factor, Represents the health index, represents the first weighted parameter corresponding to comfort, represents the second weighted coefficient corresponding to the safety factor, Indicates the third weighted coefficient corresponding to the health index.

[0066] In one possible implementation, comfort can be determined based on frequency-domain analysis of EMG signals (root mean square (RMS) <20μV). Safety factors can be determined based on head and neck injury criteria, ensuring an HIC (Head Injury Criterion) value of <700, in compliance with ECER17. A health index can be determined by monitoring lumbar spine L4-L5 segment pressure, maintaining it within a range of <0.5MPa, in compliance with ISO2631.

[0067] However, in the actual detection process, it is difficult to detect the comfort, safety factor, and health index corresponding to each particle. Therefore, a preliminary experiment can be conducted for each electric seat adjustment parameter to determine the comfort, safety factor, and health index corresponding to each electric seat adjustment parameter under different value states. Then, each electric seat adjustment parameter is set with a corresponding weighted weight. After weighting and summing the comfort of all electric seat adjustment parameters, the comfort corresponding to the particle can be obtained. The principle of obtaining the safety factor and health index corresponding to the particle is similar. To ensure the accuracy of the weighting, the sum of the weighted weights corresponding to all electric seat adjustment parameters should be 1, and the sum of the first weighted weight parameter, the second weighted weight coefficient, and the third weighted weight coefficient should also be 1.

[0068] Based on the above-mentioned method for obtaining adaptability, different weighted weights, first weighted weight parameters, second weighted weight coefficients and third weighted weight coefficients can be set for the electric seat adjustment parameters in different vehicle usage scenarios, thereby achieving special optimization in the vehicle usage scenario and realizing personalized electric seat adjustment.

[0069] In a possible implementation, when the vehicle meets the deep optimization conditions, second particle swarms in different optimization directions are constructed, and the second particle swarms in different optimization directions are iterated to determine non-inferior solutions in different optimization directions, including: When the vehicle meets the deep optimization conditions, the weighted weight of comfort in the fitness function is adjusted so that the weighted weight of comfort is greater than the weight of the safety factor and the weighted weight of the health index, thereby obtaining a first adjusted fitness function.

[0070] The electric seat adjustment parameters are used to initialize the second particle swarm corresponding to the comfort direction, and the first adjustment fitness function is used as the optimization target to optimize the second particle swarm corresponding to the comfort direction to determine the non-inferior solution in the comfort direction.

[0071] When the vehicle meets the deep optimization conditions, the weighted weight of the safety factor in the fitness function is adjusted so that the weighted weight of the safety factor is greater than the weight of the comfort and the weighted weight of the health index, thereby obtaining a second adjusted fitness function.

[0072] The electric seat adjustment parameters are used to initialize the second particle swarm corresponding to the safety direction, and the second adjustment fitness function is used as the optimization target to optimize the second particle swarm corresponding to the safety direction and determine the non-inferior solution in the safety direction.

[0073] When the vehicle meets the deep optimization conditions, the weighted weight of the health index in the fitness function is adjusted so that the weighted weight of the comfort is greater than the weight of the safety factor and the weighted weight of the comfort, thereby obtaining a third adjusted fitness function.

[0074] The electric seat adjustment parameters are used to initialize the second particle swarm corresponding to the healthy direction, and the third adjustment fitness function is used as the optimization target to optimize the second particle swarm corresponding to the healthy direction and determine the non-inferior solution in the healthy direction.

[0075] By determining the non-inferior solution in the comfort direction, the non-inferior solution in the safety direction, and the non-inferior solution in the health direction, the electric seat adjustment parameter values ​​suitable for different adjustment directions can be obtained to meet the needs of different users.

[0076] Different first, second, and third weighting coefficients can be pre-set for each optimization direction, enabling optimization focused on different directions. This improves the flexibility of power seat adjustment and meets the user's personalized needs for power seat adjustment. Different weightings can also be set for power seat adjustment parameters to further enhance flexibility. When constructing the second particle swarm for different optimization directions, the dimensions of the power seat adjustment parameters can be increased or decreased to meet the adjustment needs of more users.

[0077] In one possible implementation, determining non-inferior solutions in different optimization directions includes: During the iteration of the second particle swarm in different optimization directions, the ε-dominance criterion is used to screen and maintain the multi-objective Pareto front solutions, and non-inferior solutions in different optimization directions are obtained.

[0078] In the embodiment of the present application, only fitness can be used to confirm the dominance relationship. If the fitness of a particle is greater than the fitness of another particle, it is considered that the particle dominates the other particle, thereby realizing the ε dominance criterion screening and maintaining the multi-objective Pareto front solution, which can effectively realize the solution of multi-dimensional parameters and improve the optimization capability.

[0079] Please refer to Figure 3 Based on the same inventive concept, another embodiment of the present application provides an electric seat adjustment device. The electric seat adjustment device includes: The first iteration module 301 is used to initialize the first particle swarm using the electric seat adjustment parameters, and iterate the first particle swarm every adjustment period to obtain the first particle swarm after iteration.

[0080] The real-time adjustment module 302 is configured to determine a first target electric seat adjustment parameter value based on the first particle swarm after iteration, and adjust the electric seat according to the first target electric seat adjustment parameter value.

[0081] The deep optimization module 303 is used to construct a second particle swarm in different optimization directions when the vehicle meets the deep optimization conditions, and iterate the second particle swarm in different optimization directions to determine non-inferior solutions in different optimization directions. The optimization directions include comfort, safety, and health.

[0082] The database module 304 is used to store non-inferior solutions in different optimization directions to provide a reference for personalized electric seat adjustment.

[0083] In a possible implementation, the electric seat adjustment device further includes: The instantaneous optimization module 305 is configured to generate a collision warning signal in the event of an emergency braking situation. This collision warning signal triggers instantaneous optimization of the power seat. This includes adjusting the power seat according to a second target power seat adjustment parameter value set for the predetermined collision scenario.

[0084] In a possible implementation, the first iteration module 301 includes an initialization submodule, a data acquisition submodule, a clustering submodule, an iteration submodule, and a fusion submodule.

[0085] Initialization submodule, used to initialize the first particle swarm using the electric seat adjustment parameters The data acquisition submodule is used to obtain the historical optimal particle and the swarm optimal particle corresponding to the particles in the first particle swarm.

[0086] The clustering submodule is used to cluster the first particle swarm and obtain multiple subgroups belonging to the first particle swarm.

[0087] The iterative submodule is used to extract the local optimal particle in each subgroup, and iterate the particles in the subgroup according to the local optimal particle in the subgroup, the historical optimal particle corresponding to the particle, and the optimal particle of the population to obtain the subgroup after iteration.

[0088] The fusion submodule is used to merge the subgroups after multiple iterations into a particle swarm to obtain the first particle swarm after the iteration. After iterating the first particle swarm to obtain the first particle swarm after the iteration, the process also includes: obtaining the fitness corresponding to each particle in the first particle swarm after the iteration, and updating the historical optimal particle corresponding to each particle and the population optimal particle corresponding to all particles based on the fitness corresponding to the particle, providing support data for the iteration of the first particle swarm in the next adjustment cycle.

[0089] Exemplarily, obtaining the fitness corresponding to each particle in the first particle swarm after iteration includes: The comfort, safety factor, and health index corresponding to the particles in the first particle swarm after iteration are obtained, and the comfort, safety factor, and health index are weighted and summed to obtain the fitness corresponding to the particles.

[0090] In a possible implementation, the real-time adjustment module 302 includes a parameter value determination submodule and an adjustment submodule.

[0091] The parameter value determination submodule is used to determine the particle with the largest fitness as the first target electric seat adjustment parameter value based on the first particle group after iteration.

[0092] The adjustment submodule is used to adjust the electric seat according to the first target electric seat adjustment parameter value.

[0093] In a possible implementation, the depth optimization module 303 includes a comfort direction optimization submodule, a safety direction optimization submodule, and a health direction optimization submodule.

[0094] The comfort optimization submodule is used to adjust the weighted weight of comfort in the fitness function, assuming the vehicle meets the deep optimization conditions, so that the weighted weight of comfort is greater than the weight of the safety factor and the weight of the health index, thereby obtaining a first adjusted fitness function. The second particle swarm corresponding to the comfort direction is initialized using the power seat adjustment parameters. Using the first adjusted fitness function as the optimization objective, the second particle swarm corresponding to the comfort direction is optimized to determine a non-inferior solution in the comfort direction.

[0095] The safety direction optimization submodule is used to adjust the weighted weight of the safety factor in the fitness function, assuming the vehicle meets the deep optimization conditions, so that the weighted weight of the safety factor is greater than the weight of the comfort factor and the weight of the health index, thereby obtaining a second adjusted fitness function. The second particle swarm corresponding to the safety direction is initialized using the power seat adjustment parameters. The second adjusted fitness function is then used as the optimization objective to optimize the second particle swarm corresponding to the safety direction and determine a non-inferior solution in the safety direction.

[0096] The health-direction optimization submodule is used to adjust the weighted weights of the health index in the fitness function, if the vehicle meets the deep optimization conditions, so that the weighted weight of comfort is greater than the weight of the safety factor and the weighted weight of comfort, thereby obtaining a third adjusted fitness function. The second particle swarm corresponding to the health direction is initialized using the power seat adjustment parameters. The second particle swarm corresponding to the health direction is optimized using the third adjusted fitness function as the optimization target to determine a non-inferior solution in the health direction.

[0097] Exemplarily, during the iteration of the second particle swarm in different optimization directions, the ε-dominance criterion is used to screen and maintain multi-objective Pareto front solutions to obtain non-inferior solutions in different optimization directions.

[0098] An electric seat adjustment device provided in an embodiment of the present application is capable of executing the above-mentioned method and technical solution, and its principles and beneficial effects are similar, so they will not be repeated here.

[0099] Please refer to Figure 4 Based on the same inventive concept, another embodiment of the present application provides an electronic device. The electronic device includes a memory 401 and a processor 402. The memory 401 and the processor 402 communicate with each other via a communication bus 403.

[0100] The memory 401 is used to store code instructions.

[0101] The processor 402 is used to run code instructions so that the electronic device executes the electric seat adjustment method provided in the embodiment of the present application.

[0102] The communication bus 403 mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus 403 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or one type of bus. The communication interface is used for communication between the above-mentioned terminal and other devices. The memory 401 may include random access memory (RAM) or non-volatile memory, such as at least one disk storage. Optionally, the memory 401 may also be at least one storage device located away from the aforementioned processor 402.

[0103] The processor 402 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0104] Based on the same inventive concept, an embodiment of the present application further provides a vehicle, which includes the electric seat adjustment device in any possible embodiment described above.

[0105] In addition, to achieve the above-mentioned purpose, an embodiment of the present application further proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the electric seat adjustment method provided in the embodiment of the present application.

[0106] Those skilled in the art will appreciate that embodiments of the present application may be provided as methods, devices, or computer program products. Thus, embodiments of the present application may take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product implemented on one or more computer-usable devices (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0107] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (apparatuses), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0108] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0110] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. "" and / or "" indicate that either one or both of the two can be selected. Moreover, the terms "" include", "" contain", "" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements that are inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "" include a..."" does not exclude the presence of other identical elements in the process, method, article or terminal device that includes the elements.

[0111] The above are only specific embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and such modifications or substitutions should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for adjusting an electric seat, characterized in that: include: Initializing a first particle swarm using the electric seat adjustment parameters, and iterating the first particle swarm every adjustment cycle to obtain a first particle swarm after iteration; determining a first target electric seat adjustment parameter value based on the first particle swarm after iteration, and adjusting the electric seat according to the first target electric seat adjustment parameter value; When the vehicle meets the deep optimization conditions, constructing second particle swarms in different optimization directions, and iterating the second particle swarms in different optimization directions to determine non-inferior solutions in different optimization directions; the optimization directions include comfort direction, safety direction, and health direction; The non-inferior solutions in different optimization directions are stored to provide a reference for personalized electric seat adjustment.

2. The electric seat adjustment method according to claim 1, characterized in that: Also includes: In the event of emergency braking, a collision warning signal is generated; Using the collision warning signal as a trigger condition, triggering instantaneous optimization of the electric seat; The instantaneous optimization includes: adjusting the electric seat according to a second target electric seat adjustment parameter value under a preset collision scenario.

3. The electric seat adjustment method according to claim 1, characterized in that: The iterating the first particle swarm to obtain the first particle swarm after iteration includes: Obtaining the historical optimal particle and the swarm optimal particle corresponding to the particle in the first particle swarm; Clustering the first particle group to obtain a plurality of subgroups belonging to the first particle group; Extracting the local optimal particle in each subgroup, and iterating the particles in the subgroup according to the local optimal particle in the subgroup, the historical optimal particle corresponding to the particle, and the optimal particle of the population, to obtain a subgroup after iteration; The sub-groups after multiple iterations are merged into one particle group to obtain the first particle group after iteration.

4. The electric seat adjustment method according to claim 3, characterized in that: After iterating the first particle swarm and obtaining the first particle swarm after the iteration, the method further includes: Obtain the fitness of each particle in the first particle swarm after iteration, and update the historical optimal particle corresponding to each particle and the swarm optimal particle corresponding to all particles according to the fitness of the particle, so as to provide support data for the iteration of the first particle swarm in the next adjustment cycle.

5. The electric seat adjustment method according to claim 4, characterized in that: The step of obtaining the fitness of each particle in the first particle swarm after iteration includes: The comfort, safety factor, and health index corresponding to the particles in the first particle swarm after iteration are obtained, and the comfort, safety factor, and health index are weighted and summed to obtain the fitness corresponding to the particles.

6. The electric seat adjustment method according to claim 1, characterized in that: The method of determining a first target electric seat adjustment parameter value based on the first particle swarm after iteration, and adjusting the electric seat according to the first target electric seat adjustment parameter value, includes: Based on the first particle swarm after iteration, the particle with the largest fitness is determined as the first target electric seat adjustment parameter value; The electric seat is adjusted according to the first target electric seat adjustment parameter value.

7. The electric seat adjustment method according to claim 4, characterized in that: When the vehicle satisfies the deep optimization condition, constructing a second particle swarm in different optimization directions, and iterating the second particle swarm in different optimization directions to determine a non-inferior solution in different optimization directions, including: When the vehicle satisfies the deep optimization condition, adjusting the weighted weight of the comfort in the fitness function so that the weighted weight of the comfort is greater than the weight of the safety factor and the weight of the health index, thereby obtaining a first adjusted fitness function; Initializing a second particle swarm corresponding to a comfort direction using the electric seat adjustment parameter, and optimizing the second particle swarm corresponding to the comfort direction using the first adjustment fitness function as an optimization target to determine a non-inferior solution in the comfort direction; When the vehicle satisfies the deep optimization condition, adjusting the weighted weight of the safety factor in the fitness function so that the weighted weight of the safety factor is greater than the weight of the comfort level and the weight of the health index, thereby obtaining a second adjusted fitness function; Initializing a second particle swarm corresponding to a safety direction using the electric seat adjustment parameter, and optimizing the second particle swarm corresponding to the safety direction using the second adjustment fitness function as an optimization target to determine a non-inferior solution in the safety direction; When the vehicle satisfies the deep optimization condition, adjusting the weighted weight of the health index in the fitness function so that the weighted weight of the comfort is greater than the weight of the safety factor and the weighted weight of the comfort, thereby obtaining a third adjusted fitness function; The electric seat adjustment parameter is used to initialize the second particle swarm corresponding to the healthy direction, and the third adjustment fitness function is used as the optimization target to optimize the second particle swarm corresponding to the healthy direction to determine a non-inferior solution in the healthy direction.

8. The electric seat adjustment method according to claim 1, characterized in that: Determining non-inferior solutions in different optimization directions includes: During the iterative process of the second particle swarm in the different optimization directions, the ε dominance criterion is used to screen and maintain the multi-objective Pareto front solutions to obtain non-inferior solutions in the different optimization directions.

9. An electric seat adjustment device, characterized in that: include: A first iteration module is configured to initialize a first particle swarm using the electric seat adjustment parameters, and iterate the first particle swarm every adjustment period to obtain a first particle swarm after iteration; a real-time adjustment module, configured to determine a first target electric seat adjustment parameter value based on the first particle swarm after iteration, and adjust the electric seat according to the first target electric seat adjustment parameter value; A deep optimization module is used to construct a second particle swarm in different optimization directions when the vehicle meets the deep optimization conditions, and iterate the second particle swarm in different optimization directions to determine non-inferior solutions in different optimization directions; the optimization directions include comfort direction, safety direction, and health direction; The database module is used to store non-inferior solutions in different optimization directions and provide a reference for personalized electric seat adjustment.

10. A vehicle, characterized in that: The vehicle includes the electric seat adjustment device according to claim 9.

Images