Intelligent seat control system and control method

Abstract

The invention discloses an intelligent seat control system and method, and the system comprises a sensing module which is used for collecting a physiological state signal of a driver, a dynamic driving signal of a vehicle, and an environment signal of a carriage; the control module is connected with the sensing module and is used for performing fusion processing on the received multi-source signals and outputting a control instruction based on preset judgment logic; the execution module is connected with the control module and used for driving an adjusting mechanism of the seat according to the control instruction; wherein the control module is configured to judge the fatigue level of the driver according to the physiological state signal; the real-time control state of the vehicle is judged according to the dynamic driving signal; and based on the fatigue level or the real-time control state, generating a corresponding adaptive adjustment instruction to control the execution module to act. According to the intelligent seat system, the problems of physiological monitoring limitation, high control delay and individuation deficiency of an existing intelligent seat system are solved, and a timely, comfortable and safe seat is provided for a driver.

Description

Technical Field

[0001] This invention relates to the field of intelligent cockpit technology, and in particular to an intelligent seat control system and control method. Background Technology

[0002] Currently, intelligent seat systems still have significant limitations in improving the driving experience. First, insufficient perception capabilities: most systems rely on static pressure sensors to detect posture, failing to monitor deeper physiological states such as driver muscle fatigue in real time, leading to inaccurate adjustments. Second, simple control logic and slow response: existing systems are mostly isolated controls, failing to deeply integrate driver status, vehicle dynamics (such as steering and acceleration), and environmental information for decision-making. This results in the system's inability to anticipate road conditions and proactively adjust, and a high latency from perception to execution (typically >150ms), making it difficult to meet the immediate safety protection needs in emergency situations. Finally, lack of personalized adaptation: the so-called "memory function" can only store fixed positions and cannot continuously learn and optimize based on the driver's long-term usage habits and real-time feedback, failing to achieve true personalized comfort adaptation.

[0003] Therefore, existing technologies struggle to provide timely, comfortable, and safe seat support for drivers in complex driving scenarios. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide an intelligent seat control system and control method, which solves the problems of physiological monitoring limitations, high control delay and lack of personalization in existing intelligent seat systems, making it difficult to provide timely, comfortable and safe adaptive seat support for drivers in complex driving scenarios.

[0005] The technical problem to be solved by the present invention is achieved through the following technical solution: An intelligent seat control system includes: The sensing module is used to collect the driver's physiological state signals, the vehicle's dynamic driving signals, and the environmental signals of the passenger compartment. The control module is communicatively connected to the sensing module and is used to fuse the received multi-source signals and output control commands based on preset judgment logic. An execution module, which is communicatively connected to the control module, is used to drive the seat adjustment mechanism according to the control commands; The control module is configured to determine the driver's fatigue level based on the physiological state signal; determine the vehicle's real-time control status based on the dynamic driving signal; and generate corresponding adaptive adjustment commands based on the fatigue level or the real-time control status to control the action of the execution module.

[0006] Preferably, in the above technical solution, the sensing module includes: The biomechanical monitoring unit is used to acquire electromyographic signals of the erector spinae muscle group at a sampling rate of not less than 1 kHz and simultaneously acquire a seat pressure distribution map with a resolution of 2 cm² to establish a fatigue prediction model. The vehicle dynamic sensing unit is used to detect seat vibration and posture changes, with a frequency response range of 0.5-200Hz; The environmental sensing unit is used to detect the temperature, humidity, and air quality inside the carriage.

[0007] Preferably, in the above technical solution, the control module runs a real-time operating system with a task scheduling cycle of no more than 10ms; and has a built-in machine learning model for dual-modal fusion of electromyography and pressure distribution to output a fatigue index.

[0008] Preferably, in the above technical solution, the judgment logic includes: When the fatigue level exceeds the first threshold of 70, a command is generated to activate the seat massage function, and the backrest angle is continuously finely adjusted within a range of ±3° every 5 minutes. When the dynamic driving signal indicates that the lateral acceleration exceeds the second threshold of 0.4g, a command is generated to increase the pressure on the seat side wing support.

[0009] Preferably, in the above technical solution, the specific method of enhancing the side wing support pressure is as follows: when the lateral acceleration is detected to be >0.4g, the side wing airbag is pre-inflated to 80kPa at a rate of 30-50kPa / s 300ms in advance; when the vehicle navigation predicts that the radius of curvature of the continuous curves ahead is <200m, inflation is also completed 300ms in advance.

[0010] Preferably, in the above technical solution, the execution module further includes a graphene heating film; the control module starts heating when the temperature in the carriage is ≤-20℃ and increases the temperature at 3℃ / min, while reducing the motor torque by 15% to prevent overload.

[0011] Preferably, in the above technical solution, the control module is further configured to: receive a collision warning signal from the vehicle; and when the predicted collision time TTC < 1s, execute a safety response according to the following timing sequence: TTC < 800ms, headrest moves forward 20mm; TTC < 500ms; the seat returns to center within ±1°. The TTC (Time To Cost) is less than 300ms, and the side airbags inflate to 80kPa; while maintaining a time synchronization error of less than 5ms with the seatbelt pretensioner.

[0012] Preferably, in the above technical solution, the coordination time error between the safety response command sequence and the seat belt pretensioner is less than 5ms.

[0013] A control method for an intelligent seat system, comprising: S1. Collect driver physiological state signals and vehicle dynamic driving signals; S2. Using a machine learning model to fuse electromyography and pressure modes, fatigue level and lateral acceleration are obtained. S3. Generate adaptive adjustment commands based on the combination of fatigue level >70 or lateral acceleration >0.4g; S4. Perform massage, side wing inflation, backrest ±3° micro-adjustment, heating, or three-level collision response according to instructions; S5. Records of comfort scores <3 after each adjustment are uploaded to the cloud. After accumulating 100 sets, the personalized parameters are recombined within 2 seconds and sent to the vehicle terminal.

[0014] A vehicle equipped with an intelligent seat control system.

[0015] The above-described technical solution of the present invention has the following beneficial effects: 1. Improved driving comfort (1) Dynamic adaptation effect: By using a 16-channel bioelectric detection array and a high-resolution pressure distribution sensor to capture changes in sitting posture, the system can achieve minute-level fine-tuning of backrest angle and lumbar support. Through a real-time control architecture based on RTOS (task scheduling cycle ≤10ms) and a minute-level dynamic fine-tuning strategy, the system can make a fast and smooth continuous response to changes in the driver's physiological state.

[0016] (2) Scenario-based optimization: For continuous driving scenarios on highways, the system automatically adjusts the backrest angle by 1° every 30 minutes, and in conjunction with the pulse massage module, improves the driver's heart rate variability (HRV) by 12.7%.

[0017] 2. Enhanced security

[0018] (1) Emergency response mechanism: When the ESP system triggers ABS activation, the seat side wings inflate to 50 kPa within 80 ms, working in conjunction with the seat belt pretensioning system.

[0019] (2) Predictive protection: The lateral acceleration (±1.5g range) and steering angular velocity data are obtained through the CAN bus, and the lateral support module is activated 300ms in advance to effectively suppress body roll when driving in curves.

[0020] 3. Energy and environmental adaptability

[0021] Climate compensation function: After receiving meteorological data, the heating strategy is automatically optimized in a -20℃ environment, and the temperature uniformity of the seat surface is improved to ±1.5℃; in hot weather, the ventilation volume is dynamically adjusted according to the humidity, and the humidity of the skin contact surface is reduced by 35%.

[0022] 4. Personalized learning for users

[0023] (1) Incremental algorithm: After accumulating 100 sets of data, a personalized curve is generated, and the best parameter combination under different driving scenarios is memorized (such as raising the seat by 3cm when in urban congestion).

[0024] (2) Abnormal pattern recognition: Automatically record the characteristics of violent adjustment (force > 150N) or mechanical blockage (abnormal motor current) and feed them back to the cloud, with a fault warning accuracy rate of 92%.

[0025] In summary, this invention, through a closed-loop technology system of multi-source deep perception, real-time intelligent decision-making, proactive safety collaboration, and continuous evolutionary learning, brings a qualitative leap in driving comfort, proactive safety, and personalized experience, and has promising prospects for industrial application. Attached Figure Description

[0026] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments of the invention and, together with their description, serve to explain the principles of the invention.

[0027] Figure 1 This is a system architecture diagram of an intelligent seat control system.

[0028] Figure 2 This is a schematic diagram of the intelligent seat control system. Detailed Implementation

[0029] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the invention.

[0030] The intelligent seat control system provided by this invention adopts a hierarchical architecture, mainly including a sensing module 100, a control module 200, and an execution module 300. The sensing module 100 is responsible for collecting information from multiple sources; the control module 200 is responsible for data fusion, intelligent decision-making, and learning; and the execution module 300 completes specific physical adjustment actions according to instructions.

[0031] Example 1 System Hardware Composition

[0032] 1. Sensor module 100: Used to collect various signals related to driver status, vehicle dynamics and cabin environment in real time.

[0033] The biomechanical monitoring unit's core is a 16-channel bioelectrical sensing array positioned beneath the seat back cushion. This array simultaneously acquires electrocardiogram (ECG) and electromyography (EMG) signals from the driver's erector spinae muscles at a sampling rate of 1 kHz to assess muscle activity and fatigue levels. Simultaneously, a high-resolution pressure distribution sensor (e.g., with a resolution of up to 2 cm²) is embedded within the seat cushion to monitor real-time changes in posture.

[0034] Vehicle Dynamics Sensing Unit: This mainly includes a 9-axis IMU mounted on the seat frame. It detects the seat's vibration, acceleration, and angular velocity in three-dimensional space, with a frequency response range of 0.5-200Hz. It can effectively capture dynamic changes caused by vehicle steering, acceleration, braking, and road bumps. This unit communicates with the vehicle network via the onboard CAN bus to acquire key vehicle parameters in real time, such as lateral acceleration, steering angular velocity, and ABS activation signals.

[0035] Environmental sensing unit: Temperature and humidity sensors and PM2.5 sensors are integrated near the seat headrest or dashboard to monitor the environmental conditions inside the vehicle, with accuracies of ±0.5℃ and ±5μg / m³, respectively.

[0036] 2. Control Module 200: As the core of the system, its hardware foundation is a microprocessor running a real-time operating system (RTOS). This RTOS ensures that the task scheduling cycle is no more than 10 ms to meet high real-time requirements. The microprocessor is connected to the sensing module 100 and the execution module 300 through corresponding interface circuits.

[0037] 3. Execution module 300: includes multiple controlled physical actuators.

[0038] Side airbag modules: Located on both sides of the seat, they are controlled by high-speed air pumps and solenoid valves, and can increase the airbag pressure to 80 kPa within 50 ms to provide lateral support.

[0039] Posture adjustment module: includes a backrest angle adjustment motor, lumbar support air cushion, and headrest fore-and-aft adjustment mechanism. The backrest angle can be continuously fine-tuned in 0.5° increments within a range of ±3°.

[0040] Comfort module: Includes graphene heating film and ventilation fan integrated into the seat surface for actively regulating the temperature and humidity of the contact surface.

[0041] 4. Cloud Interaction Module: The control module 200 establishes a connection with the cloud server through the vehicle-mounted T-Box or 4G / 5G communication module for data uploading and model updates.

[0042] Example 2: Control Method and Workflow

[0043] 1. Data Acquisition and Feature Extraction: After the system is powered on, the sensor module 100 continuously acquires raw signals. The microprocessor of the control module 200 preprocesses and extracts features from these signals. For example, wavelet transform is performed on the EMG signal for denoising, and its root mean square value and other time-domain and frequency-domain features are calculated; the pressure distribution signal is analyzed by partitioning, and the pressure center offset is calculated. These features, together with the vehicle parameters obtained from the CAN bus, constitute a multi-dimensional feature vector.

[0044] 2. Multi-source information fusion and intelligent decision-making: The processed feature vectors are input into a pre-built machine learning model for fusion analysis and decision-making. This model is preferably a three-layer LSTM network incorporating an attention mechanism, with input dimensions of 12 classes of physiological signal features and 8 classes of vehicle parameters.

[0045] 3. Fatigue Driving Intervention: The model outputs a fatigue index from 0 to 100. When the index is >70 and remains above 70 for more than 30 seconds, and the vehicle is traveling in a stable straight line, the driver is determined to be fatigued. The system then generates control commands to activate the three-level gradient massage function of the execution module 300, and finely adjusts the backrest angle by ±0.5° to ±1° every 5 minutes to dynamically relieve muscle fatigue.

[0046] 4. Curve Support Prediction: The model analyzes vehicle dynamics in real time. When the lateral acceleration is greater than 0.4g or when navigation data predicts a curve with a radius of curvature of less than 200m within 300 meters ahead, the system will pre-inflate the side airbags 300ms in advance at a rate of 50 kPa / s, with a target pressure of 80 kPa, to counteract centrifugal force and suppress driver body roll.

[0047] 5. Emergency Safety Coordinated Response: When an emergency signal (e.g., deceleration > 0.6g) is received via the CAN bus from the ESP system or a TTC (Time to Collision) signal < 1s from the collision warning system, the system enters safety mode. The control module 200 initiates a high-priority task, executing a three-level response according to precise timing: Warning phase (TTC < 800ms): Control the headrest forward movement mechanism to move the headrest forward by 20mm.

[0048] Pre-tensioning phase (TTC < 500ms): Control the backrest angle adjustment motor to return the seat to a position within ±1° of the vehicle's centerline.

[0049] During the collision phase (TTC < 300ms): The side airbags are rapidly inflated to 80kPa and coordinated with the seatbelt pretensioners using hardware timestamp synchronization technology to ensure that the time error between their actions is less than 5ms, thus forming an integrated safety protection.

[0050] 6. Personalized Incremental Learning: After each adjustment, the system invites the driver to rate the comfort level (1-5 points) through a human-machine interface (such as voice or touch feedback). When the rating is less than 3 points, all relevant parameters (sensor data, execution commands) for this adjustment are marked as "records to be optimized" and uploaded to the cloud server via the cloud interaction module. When the cumulative number of records reaches more than 100, the cloud server triggers a parameter reorganization algorithm to generate updated personalized model parameters within 2 seconds and distribute them to the vehicle's microprocessor, enabling continuous evolution of the control strategy.

[0051] Example 3 Environmental Adaptation Treatment

[0052] As a further optimization of the above embodiments, the system also possesses environmental adaptability. For example, when the environmental sensing unit detects that the cabin temperature is below -20°C, the control module 200 will activate the graphene heating film and increase the temperature at a gradient of 3°C / min. Simultaneously, to prevent motor overload at low temperatures, the maximum output torque of all motors in the attitude adjustment module will be reduced by 15%, thereby improving comfort while ensuring system reliability.

[0053] It should be noted that the above-mentioned control strategies, such as fatigue level detection, curve curvature prediction, ambient temperature compensation, and collision warning response, can operate independently or be activated simultaneously in any combination. The system can automatically activate any one or several of these strategies based on the real-time scenario. This invention does not impose any limitations on the number of combinations or the logical order of triggering conditions.

[0054] Although the present invention has been disclosed above with reference to embodiments, it is not intended to limit the present invention. Any person skilled in the art can make various different choices and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention is defined by the claims and their equivalents.

Claims

1. An intelligent seat control system, characterized in that, include: The sensing module is used to collect the driver's physiological state signals, the vehicle's dynamic driving signals, and the environmental signals of the passenger compartment. The control module is communicatively connected to the sensing module and is used to fuse the received multi-source signals and output control commands based on preset judgment logic. An execution module, which is communicatively connected to the control module, is used to drive the seat adjustment mechanism according to the control commands; The control module is configured to determine the driver's fatigue level based on the physiological state signal and to determine the vehicle's real-time control status based on the dynamic driving signal. Based on the fatigue level or the real-time control state, a corresponding adaptive adjustment command is generated to control the action of the execution module.

2. The system according to claim 1, characterized in that, The sensing module includes: The biomechanical monitoring unit is used to acquire electromyographic signals of the erector spinae muscle group at a sampling rate of not less than 1 kHz and simultaneously acquire a seat pressure distribution map with a resolution of 2 cm² to establish a fatigue prediction model. The vehicle dynamic sensing unit is used to detect seat vibration and posture changes, with a frequency response range of 0.5-200Hz; The environmental sensing unit is used to detect the temperature, humidity, and air quality inside the carriage.

3. The system according to claim 1, characterized in that, The control module runs a real-time operating system with a task scheduling cycle of no more than 10ms; it also has a built-in machine learning model for dual-modal fusion of electromyography and pressure distribution to output a fatigue index.

4. The system according to claim 1, characterized in that, The judgment logic includes: When the fatigue level exceeds the first threshold of 70, a command is generated to activate the seat massage function, and the backrest angle is continuously finely adjusted within a range of ±3° every 5 minutes. When the dynamic driving signal indicates that the lateral acceleration exceeds the second threshold of 0.4g, a command is generated to increase the pressure on the seat side wing support.

5. The system according to claim 4, characterized in that, The enhanced side wing support pressure includes: when a lateral acceleration >0.4g is detected, the side wing airbag is pre-inflated to 80kPa at a rate of 30-50kPa / s 300ms in advance; when the vehicle navigation predicts that the radius of curvature of the continuous curves ahead is <200m, inflation is also completed 300ms in advance.

6. The system according to claim 1, characterized in that, The execution module also includes a graphene heating film; the control module starts heating when the temperature in the carriage is ≤-20℃ and increases the temperature at 3℃ / min, while reducing the motor torque by 15% to prevent overload.

7. The system according to claim 1, characterized in that, The control module is further configured to: receive a collision warning signal from the vehicle; and when the predicted collision time TTC is less than 1 second, execute a safety response according to the following timing sequence: TTC < 800ms, headrest moves forward 20mm; TTC < 500ms; the seat returns to center within ±1°. The TTC (Time To Cost) is less than 300ms, and the side airbags inflate to 80kPa; while maintaining a time synchronization error of less than 5ms with the seatbelt pretensioner.

8. The system according to claim 7, characterized in that, The coordination time error between the safety response command sequence and the seat belt pretensioner is less than 5ms.

9. A control method for an intelligent seat system as described in any one of claims 1-8, characterized in that, include: S1. Collect driver physiological state signals and vehicle dynamic driving signals; S2. Using a machine learning model to fuse electromyography and pressure modes, fatigue level and lateral acceleration are obtained. S3. Generate adaptive adjustment commands based on the combination of fatigue level >70 or lateral acceleration >0.4g; S4. Perform massage, side wing inflation, backrest ±3° micro-adjustment, heating, or three-level collision response according to instructions; S5. Records of comfort scores <3 after each adjustment are uploaded to the cloud. After accumulating 100 sets, the personalized parameters are recombined within 2 seconds and sent to the vehicle terminal.

10. A vehicle, characterized in that, The device is equipped with the intelligent seat control system according to any one of claims 1-8 and is configured to perform the method of claim 9.

Images