288 results about "Vertical acceleration" patented technology

The invention discloses a bridge sensor self-optimization arrangement and state evaluation method based on a modal confidence criterion, and relates to the technical field of big data analysis and processing. The method comprises the following steps: step 1, acquiring a vertical acceleration time sequence at candidate installation coordinates of each sensor through preset vehicle excitation; 2, a physical information neural network is adopted to drive sparse damage reconstruction and sensor importance joint optimization algorithm to determine a bridge sensor self-optimization arrangement result; and step 3, installing a vertical acceleration sensor on the target bridge according to a bridge sensor self-optimization arrangement result, dividing bridge state grades according to a finite element unit damage estimation result, and outputting a bridge state evaluation result. The method can be continuously used in the bridge operation period, quantitative and traceable structure state evaluation results are provided, potential risks can be found in advance, and the reliability, practicability and intelligent level of bridge health monitoring are remarkably improved.

The invention discloses a backfill soil foundation compactness nondestructive testing method based on an intelligent sensor. The backfill soil foundation compactness nondestructive testing method comprises the following steps of S1, the intelligent sensor, S2, a GPS positioning system, S3, a wireless transmission network and S4, an information monitoring and collecting system. An on-site road roller is modified, an RTK-GPS receiver, a wireless communication antenna and an acceleration sensor are installed, accurate measurement of the position and the running speed of the rolling machine can be achieved through an automatic rolling system based on RTK-GPS and closed-loop feedback control, the acceleration sensor is fixed to a vibrating wheel, vertical acceleration signals of the vibrating wheel are collected in real time, and the vibration speed of the vibrating wheel is measured. A CMV value and a field compaction degree evaluation result are analyzed in real time through a background development system, then a correlation relation is established between a compaction degree value and the CMV value which are measured by using a standard compaction degree inspection method in a test section, and real-time compaction degree monitoring control can be carried out.

A wheel action-based active suspension damping adjustment apparatus recognizes wheel actions through a steering apparatus, distance measuring apparatuses and force sensors and calculates an action damping magnitude according to damping parameters determined by different wheel actions, thereby achieving optimal adjustment under different actions. The changes in an inclination angle of a vehicle cabin floor and a vertical acceleration are monitored by using an inclination angle sensor and acceleration sensors, and meanwhile, an inclination angle damping and an acceleration damping are determined according to exceeding amplitudes, and a total damping of active suspensions is fed back and corrected, thereby further enhancing an adjustment and control effect of the active suspensions. According to the method, basic damping, action damping, inclination angle damping and acceleration damping data is output and recorded, and classified according to a vehicle state and the wheel actions, data changes under a same classification are compared.

The invention discloses a vehicle control method and device, equipment and a storage medium, and relates to the technical field of vehicle control, and the method comprises the steps: obtaining the longitudinal acceleration data and vertical acceleration data of a vehicle when the vehicle is in a self-adaptive crawling condition; determining a user driving style according to the longitudinal acceleration data, and determining a road bumping level according to the vertical acceleration data; determining a target creeping speed according to the accelerator data and the brake data of the vehicle; and determining an increment torque function based on the target creeping speed, the road bumping level and the user driving style, and controlling the vehicle according to the increment torque function so as to maintain the creeping speed of the vehicle at the target creeping speed. The target crawling speed is determined according to the accelerator and brake data of the vehicle, and the incremental torque function is constructed based on the target crawling speed to control the vehicle, so that the crawling speed of the vehicle can meet the actual crawling requirement of a user as much as possible, the user operation is simplified, and the driving experience is improved.

The invention provides a method and a device for determining a linear operation and maintenance standard of a long-span bridge. The method comprises the following steps of: firstly, determining a quantitative relation between a track static long-wave uneven cis-chord measurement value and vehicle body vertical acceleration data; determining a vehicle body vibration acceleration limit value caused by the dynamic deformation of the high-speed railway bridge according to a vehicle body vertical acceleration limit value caused by the uneven static long wave of the track on the high-speed railway bridge, a vehicle body vibration acceleration value caused by the dynamic deformation of the high-speed railway bridge and a vehicle body vibration acceleration value caused by the random irregularity of the track; and finally, determining a linear chord measurement value of the high-speed railway bridge according to the quantitative relation and a vehicle body vibration acceleration limit value caused by dynamic deformation of the high-speed railway bridge. The method can effectively solve the problem that in the technical field of rail transit, the operation and maintenance standard of the line shape of a long-span bridge is not accurate.

The invention discloses an automobile semi-active suspension PID parameter adaptive adjustment and vibration control method and system based on reinforcement learning, and the method mainly comprises the following working steps: 1, constructing a reinforcement learning environment comprising a suspension dynamics high-fidelity simulation model and a PID controller; 2, defining a state space including a vehicle body vertical acceleration error e (t), an error integral term summa e (t) dt, an error differential term de (t) / dt, a suspension dynamic stroke zdef (t), a driving vehicle speed v (t) and road surface unevenness estimation xi (t); and 3, defining an action space including a proportion coefficient increment delta Kp, an integral coefficient increment delta Ki, a differential coefficient increment delta Kd and an output compensation amount delta e (t) of the PID controller. According to the method, the problem that the suspension performance is reduced due to the fact that control parameters of a traditional PID control method are fixed under the non-linear and time-varying working conditions is solved, and the riding comfort and the handling stability of the vehicle are remarkably improved.

The invention belongs to the technical field of vehicles, and particularly relates to an ABS function trigger control method and device, a vehicle and a medium. The method comprises the following steps: calculating a wheel slip rate; determining driver intention according to the hydraulic sensor signal, the brake pedal sensor signal and the accelerator pedal sensor signal, wherein the driver intention comprises emergency braking, conventional braking, sliding and acceleration; the road bumping state is determined according to the wheel slip rate, the vehicle vertical acceleration and the suspension displacement; according to the intention of the driver and the road bumping state, the triggering condition of the ABS function is determined; and determining whether the triggering condition of the ABS function is met or not according to the wheel slip rate. By judging the intention of the driver and the road bumping state and adjusting the triggering condition of the ABS function in real time according to the intention of the driver and the road bumping state, false triggering of the ABS function when the vehicle passes through the bumping road is avoided.

The invention discloses a new energy automobile shock absorber state intelligent early warning method based on attitude monitoring, and relates to the field of state intelligent early warning, and the method comprises the steps: collecting multi-dimensional attitude data such as the vertical acceleration, the pitch angle speed and the roll angle speed of an automobile in real time, and carrying out the self-adaptive detection of an impact event through combining with a dynamic threshold algorithm; and normal driving vibration and abnormal impact working conditions can be accurately distinguished. In the feature extraction stage, multi-dimensional physical features such as a peak-to-peak value, a root-mean-square value, a damping ratio and the like are combined and coded, so that the dynamic attenuation characteristics of the shock absorber in an impact event can be comprehensively represented. By establishing a similar event feature database in a healthy state and performing multi-feature space deviation calculation by adopting a mahalanobis distance, the robustness of anomaly detection is remarkably improved. Therefore, the technical problems of poor environmental adaptability, low diagnosis precision and the like of the traditional method can be effectively solved.

The invention discloses a dynamic analysis model for a linear full-scale anchored floating bridge under the action of waves, which provides support for dynamic response analysis and vibration control of a large anchored floating bridge structure, and comprises the following steps: firstly, constructing a numerical model of the full-scale anchored floating bridge, and then constructing an environmental load action model; the dynamic analysis model has open source performance and good compatibility and has advantages when solving the complex multi-disaster coupling problem, and the flexible parametric modeling capability of the dynamic analysis model is also beneficial to analysis of the floating bridge structure; the invention further discloses a structural response control method for the dynamic analysis model of the linear full-scale anchored floating bridge under the wave action. According to the dynamic characteristics of the anchoring type floating bridge structure, the tuned mass dampers can be additionally arranged on the cross section of the main beam of the bridge, the vertical acceleration of the main beam of the bridge is controlled by reasonably selecting the parameters, the arrangement number and the arrangement positions of the tuned mass dampers, and therefore the driving comfort is improved.

The invention provides a road surface type identification method and device based on bidirectional time sequence characteristic adaptive fusion, and relates to the technical field of data processing, and the method comprises the steps: obtaining a longitudinal acceleration, a transverse acceleration and a vertical acceleration collected in a vehicle driving process, determining a dynamic temperature, and obtaining a characteristic used for representing a road surface type; then, based on the longitudinal acceleration, the transverse acceleration, the vertical acceleration and the dynamic temperature, time stamps of the longitudinal acceleration, the transverse acceleration and the vertical acceleration are collected, and time sequence features are constructed; and finally, processing the time sequence features by using a neural network model, and outputting a classification result of pavement types. According to the road surface type identification method based on bidirectional time sequence feature adaptive fusion provided by the invention, the accuracy and reliability of road surface type identification are improved, and accurate identification and accurate prediction of the type of the road surface where the automobile tire is located are realized.

A wheel action-based active suspension damping adjustment apparatus recognizes wheel actions through a steering apparatus, distance measuring apparatuses and force sensors and calculates an action damping magnitude according to damping parameters determined by different wheel actions, thereby achieving optimal adjustment under different actions. The changes in an inclination angle of a vehicle cabin floor and a vertical acceleration are monitored by using an inclination angle sensor and acceleration sensors, and meanwhile, an inclination angle damping and an acceleration damping are determined according to exceeding amplitudes, and a total damping of active suspensions is fed back and corrected, thereby further enhancing an adjustment and control effect of the active suspensions. According to the method, basic damping, action damping, inclination angle damping and acceleration damping data is output and recorded, and classified according to a vehicle state and the wheel actions, data changes under a same classification are compared.

The invention discloses a hovering accelerator estimation method and system for an electric power inspection unmanned aerial vehicle, equipment and a medium, and the method comprises the steps: taking a hovering accelerator of the unmanned aerial vehicle as an estimator, taking a vertical acceleration as a measurement quantity, and carrying out the real-time estimation of the hovering accelerator of the unmanned aerial vehicle through an extended Kalman filtering algorithm; the extended Kalman filtering algorithm is integrated into hovering control of the unmanned aerial vehicle for the first time, compared with an existing PID control algorithm, the control precision and the dynamic response capability of fixed-point hovering of the unmanned aerial vehicle are improved, better robustness is achieved, high-precision, real-time and dynamic stable hovering control can be achieved, the method can be suitable for the unmanned aerial vehicle with the weight changing in real time, and the hovering control accuracy of the unmanned aerial vehicle is improved. And the method has better generalization ability.

The invention relates to a multi-signal fusion real-time deduction method for three-dimensional wave parameters along with a ship, and a deduction device consists of a state sensor, a one-way stress sensor, a vertical acceleration sensor, a shunt, a terminal junction box, a signal acquisition instrument, a host, analysis software, a signal transmission cable and the like. The deduction method comprises the processes of system state matrix discretization, transfer function calculation, Kalman filtering deduction model construction, convergence analysis, result comparison and the like, and three-dimensional time-frequency parameters of waves are deduced in real time through fusion analysis of ship motion and actual measurement data of a key position stress response sensor. Real-time information of surrounding waves can be provided for more sailing ships, more comprehensive reference basis can be provided for ship sailing and ship type optimization, and the method has practical significance and market value.

The invention relates to the technical field of elevator running state evaluation, in particular to an elevator running state evaluation method and system based on multi-source heterogeneous data. Comprising the following steps that elevator car vertical acceleration signals, traction machine output torque signals, traction machine output current signals, motor encoder rotating speed signals, elevator running log time, stopping floor records, running frequency records and door opening and closing frequency records are collected, all data are aligned based on timestamps, and the elevator car vertical acceleration signals and the traction machine output current signals are obtained according to starting and running of elevator running. The stop state segments the data stream to form a period of time, generating a synchronized multi-source operating data stream. Multi-source heterogeneous data such as elevator car vertical acceleration signals, traction machine output torque signals and motor encoder rotating speed signals are integrated, synchronization data streams are generated based on timestamp alignment and running state segmentation, and the problem of feature misjudgment caused by data asynchronization or state mixing is solved.

The invention discloses a method for evaluating the use performance and driving comfort of a bridge after an explosion load effect. The method comprises the following steps: establishing a finite element model of the bridge under the explosion effect, and extracting the residual area of the section of the bridge after the explosion and the elevation of the bridge floor after the explosion; calculating distribution of bridge section damage degree and bridge deck irregularity level; and the traffic capacity of the bridge is evaluated accordingly. For a bridge which can still be used, a result file of a bridge part after explosion is imported, then an axle coupling model after explosion is established, and unevenness after explosion is formed; and extracting the calculated and analyzed vertical acceleration of the vehicle, and calculating the root mean square value of the acceleration to evaluate the driving comfort of the vehicle. According to the method, through coupling evaluation of the damage degree and the bridge floor irregularity level, the composite influence of explosion on the bridge safety and the driving comfort is comprehensively quantified, and the misjudgment risk caused by one-sided evaluation is avoided; and meanwhile, the economic cost is greatly reduced through a simulation analysis and calculation mode, and the safety risk of post-disaster scene survey is avoided.

The invention provides a vehicle control method and a vehicle, and relates to the technical field of chassis control, and the method comprises the steps: obtaining the mass center vertical speed of the vehicle during the driving period of the vehicle; determining the wheel mass center vertical acceleration of each wheel according to the mass center vertical speed, the speed of the wheel moving in the vertical direction caused by the vehicle pitching motion corresponding to each wheel and the speed of the wheel moving in the vertical direction caused by the vehicle rolling motion; according to the mass center vertical speed and the wheel mass center vertical acceleration of each wheel, target action parameters of a suspension corresponding to each wheel are determined; and according to the target action parameters of the suspension corresponding to each wheel, the actual main power or the actual damping force output by the suspension corresponding to each wheel is controlled. According to the invention, the driving stability and riding comfort of the vehicle can be maintained during the driving period of the vehicle.

The invention relates to a vehicle jumping method, a storage medium, a program product, equipment, a system and a vehicle. The vehicle jumping method comprises the steps that in the vehicle jumping process, the tire pressure of a vehicle is adjusted so as to assist the vehicle in jumping. By adjusting the tire pressure of the vehicle, on one hand, the rigidity of the tire can be changed, and on the other hand, the vertical acceleration of the vehicle can be changed, so that the jumping capacity of the vehicle is optimized, for example, the take-off stroke is increased, the leap distance is increased, the oscillation curve is optimized, and landing buffering is increased, and more efficient and comfortable jumping is achieved.

The invention discloses a high-speed railway vertical curve dynamic long wave irregularity optimization method, which comprises the following steps: acquiring a line vertical section of a new line or an operation line and parameters thereof, and dynamically detecting filtering and / or driving dynamics indexes according to a preset high-speed railway, determining an easement curve mathematical model corresponding to the initial easement curve line type and the length and the circular curve radius thereof, adding the initial easement curve line type to the head and the tail of the line vertical section circular curve, constructing constraint conditions according to the vertical section characteristics of the new line or the operation line, and solving all vertical section vertical curve optimization parameters meeting the constraint conditions; and designing and constructing according to actual engineering conditions. The method is wide in application range, can effectively eliminate the sudden change of the vertical acceleration of the train body when the high-speed train passes through the head and the tail of the longitudinal section circular curve, can weaken the irregularity of long waves of 120 m and above in dynamic detection of the head and the tail of the high-speed railway circular curve, and effectively improves the dynamic vertical smoothness of the high-speed railway.

The invention discloses a shock absorber control method and device based on excitation frequency and a vehicle, and belongs to the technical field of vehicle control. The shock absorber control method comprises the steps that the vertical acceleration of a vehicle body and the sprung and unsprung relative displacement of a shock absorber are obtained; according to the vertical acceleration of the vehicle body and the sprung and unsprung relative displacement of a shock absorber, initial ceiling damping force and initial ground ceiling damping force are determined respectively; acquiring a current driving mode of the vehicle, determining a frequency division point according to the current driving mode, and performing high-pass and low-pass filtering on the initial ceiling damping force and the initial ground ceiling damping force according to the frequency division point to determine a final ceiling damping force and a final ground ceiling damping force; and the final ceiling damping force and the final ground ceiling damping force are summed to obtain final damping force, control current needed for achieving the damping force at the current speed is determined according to the current speed of the shock absorber and the final damping force, and the shock absorber is controlled according to the control current needed for achieving the damping force at the speed.

An electronic stability control system for a vehicle is disclosed. The electronic stability control system for a vehicle may include: first, second, third, and fourth acceleration sensors mounted on each wheel of the vehicle to detect the lateral acceleration and vertical acceleration of the corresponding wheel; a controller configured to be connected to first, second, third, and fourth acceleration sensors and receives lateral accelerations and vertical accelerations of the four wheels, calculate maximum values of lateral accelerations of front and rear wheels and lateral tire stiffness of the front and rear wheels considering load movement based on the lateral accelerations and vertical accelerations of the four wheels, calculate side slip angles of the front and rear wheels and a difference between the side slip angles of the front and rear wheels based on maximum values of lateral angular velocities of the front and rear wheels and the lateral tire stiffness of the front and rear wheels considering load movement, and determine brake pressure and a target wheel to which the brake pressure is to be applied in response to the difference between the side slip angles of the front and rear wheels exceeding a set value; and an actuator configured to receive a control signal from the controller and apply the brake pressure to the target wheel.An electronic stability control method for a vehicle using the electronic stability control system is further disclosed.

The invention relates to the technical field of model construction, and discloses a control model construction method based on an intelligent suspension system, which comprises the steps of data acquisition, feature extraction, control parameter analysis, control model construction and suspension system control. According to the method, key data such as vehicle body vertical acceleration and wheel vertical displacement are accurately collected, feature extraction and control parameter analysis are combined, accurate calculation of the damping coefficient and the spring stiffness coefficient of the suspension system is achieved, and a basis is provided for real-time control; mutual relations among parameters of the suspension system, such as correlation between a stress value and a damping coefficient and correlation between wheel vertical displacement and a spring stiffness coefficient, are comprehensively considered, so that the control is more scientific and reasonable; a kinetic equation is constructed according to the mechanics principle, data and parameters are substituted into the equation to determine an adjustment coefficient, and a solid theoretical basis is provided for control; the suspension system can be dynamically adjusted in real time according to road conditions, the driving comfort and safety are improved, and the intelligent development requirement of modern automobiles is met.

The invention provides a vehicle control method, a vehicle control device and a vehicle, and relates to the technical field of vehicle control. The method comprises the steps that under the condition that a target instruction is received, the vehicle sinking depth of a vehicle is obtained, and the target instruction is used for indicating that the requirement for controlling the vehicle to be disengaged from the trapped state exists; based on the vehicle sinking depth, target output power of the suspension system is determined, and the target output power is used for controlling the suspension system to enable the vehicle to generate vertical acceleration; a suspension system is controlled based on the target output power, and a drive system is controlled to cause the vehicle to jump and drive away from the trapped state. According to the method, the vehicle can be controlled when the vehicle is in a trapped state, so that the success rate of vehicle escape is increased.

The invention belongs to the field of bridge detection and evaluation, and discloses a bridge line shape detection and damage prediction method based on a smart phone and a hybrid neural network, and the method comprises the steps: obtaining a bridge image through the smart phone by employing a distributed vision method, and obtaining vertical acceleration response data and environment temperature when a standard vehicle passes through a bridge through a mobile phone sensor; a YOLOv5s-CECA target detection model is used to obtain the pixel coordinates of the feature points; taking gyroscope attitude parameters during shooting as initial external parameters, converting positioning feature point pixel coordinates into a world coordinate system in combination with a pre-calibrated mobile phone internal parameter matrix, optimizing feature point coordinates by minimizing a re-projection error, drawing an actual bridge line shape, and obtaining a target line shape. And inputting the obtained bridge data into the trained AFTCNN-LSTM model to obtain a damage degree prediction result. The method can be rapidly deployed in a complex engineering field environment, improves the efficiency of bridge line shape detection and damage prediction, and reduces the bridge detection and evaluation cost.

The invention discloses a vehicle full-temporal cooperative control method and system based on multi-source sensing data fusion, and belongs to the field of vehicle control. Comprising the following steps that S1, vertical pressure signals, yaw velocity, vehicle three-axis acceleration, vertical acceleration generated by road excitation, front obstacle distance and relative velocity and front road images of all suspensions are synchronously collected, and multi-source sensing data are formed; s2, fusing the preprocessed multi-source sensing data of the same timestamp, determining the real-time three-dimensional gravity center, the vehicle body attitude angle and the real-time road surface state of the vehicle, and obtaining the predicted road surface state based on the historical multi-source sensing data; and S3, cooperatively controlling braking force distribution, steer-by-wire and an active suspension. According to the vehicle full-temporal cooperative control method and system based on multi-source sensing data fusion, through fusion of the multi-source sensing data, full-dimensional coverage of vehicle state-road environment-obstacle information is achieved, and it is ensured that the sensing result is stable and reliable.

The invention relates to a method and device for a biped robot to wear common sports shoes, and belongs to the technical field of robots. The method comprises the steps that a pre-planned gait track is initialized and generated; calculating the actual centroid position of the robot at each moment; a Kalman filtering algorithm is adopted to fuse multi-source data to update the normal stiffness and the friction coefficient of the sole in real time, and the rate is updated through adaptive gain adjustment parameters; adjusting a zero moment point constraint range, and generating a centroid reference position of a preset step number; establishing a sole characteristic database, training a machine learning model, inputting shoe parameters into the machine learning model, and outputting step length, step frequency and ankle joint rigidity by the machine learning model; an ankle joint target angle and a knee joint target angle are solved through inverse kinematics, and a joint motor is driven in combination with a PD control algorithm and a self-adaptive item; when the vertical acceleration of the IMU sensor is larger than a preset acceleration threshold value, the time period before grounding is judged, and a compliant mode is triggered to control the ankle joint rigidity and the torque borne by the joint.

The invention relates to the technical field of motorcycle lamp control, in particular to a self-adaptive control method and system for a motorcycle lamp, and the method comprises the steps: taking the ratio of the yaw velocity to the driving speed of a motorcycle as the steering intensity, and taking the change trend of the steering intensity in a preset time period as the steering trend; the fluctuation amplitude of the vertical acceleration in the preset time period serves as the jolting degree; correcting the vehicle body inclination angle based on the bumping degree and the steering trend to obtain a corrected inclination angle; and the corrected inclination angle is substituted into a preset mapping relation to output a basic steering angle, the vehicle lamp assembly is controlled to rotate to a target steering angle, and the target steering angle is equal to the basic steering angle. According to the technical scheme, the steering trend and the jolting degree in the driving process can be analyzed, and high-stability illumination control over the motorcycle lamp can be achieved.

The invention belongs to the technical field of vehicle attitude control, and discloses a magneto-rheological suspension control method and system based on IMU resolving, and the method comprises the following steps: obtaining measurement data of an inertial sensor at an initial installation position of a vehicle body, building a vehicle body coordinate system, and determining space coordinate positions of four corners of a suspension; decomposing the motion process of the vehicle body to obtain a resolving formula, and analyzing the obtained vertical acceleration of the four-corner measuring points of the vehicle suspension; calculating the vertical acceleration of the four corners of the vehicle suspension through a resolving formula in combination with the measured data and the spatial positions of the four corners of the vehicle suspension; and an expected force value is obtained through an H-infinity control algorithm, the magneto-rheological damper is controlled in real time, and the magneto-rheological suspension is controlled. By the adoption of the magneto-rheological suspension control method and system based on IMU calculation, the arrangement process is simplified, the precision and response speed of the system are improved, and the high-precision control requirement of the magneto-rheological suspension system under various road conditions and driving working conditions is met in combination with a control algorithm.

The invention relates to the technical field of vehicle electric control suspensions, in particular to a chassis prediction control system and method based on binocular vision and multi-domain cooperation, and constructs the chassis prediction control system based on binocular vision and multi-domain cooperation based on an ADAS binocular camera. IMU data of a binocular camera is obtained by using a data acquisition module of the chassis prediction control system, visual observation data of a vehicle body is obtained by using a binocular visual processing module, and then the IMU data and the visual observation data are fused and converted into a three-dimensional image by using modules such as an extended Kalman filtering fusion module and a motion conversion module. The sprung mass vertical acceleration and sprung mass vertical speed of the vehicle four-corner suspension provide accurate suspension four-corner vertical motion state input for an electric control suspension controller, and the accuracy and real-time performance of the electric control suspension for vehicle body posture control are guaranteed. Meanwhile, the problems that a special IMU is difficult to arrange, high in cost and insufficient in precision and IMU resources of an ADAS system are wasted are solved.

The invention belongs to the technical field of action recognition, and particularly relates to an electric power engineering construction safety early warning method and system, and the method comprises the steps: carrying out the threshold segmentation and Hough straight line detection of a monitoring image of an electric power engineering construction site, obtaining a rigid support structure set, obtaining a scene instantaneous motion potential index according to the optical flow vector of a visible key point, and carrying out the calculation of the scene instantaneous motion potential index. Constructing a human body and rigid structure interaction stability index in combination with the distance between a visible key point in the possible contact set and the rigid support structure, calculating a posture risk bias factor, complementing the key point by using a graph convolutional network, and correcting a preliminary complete posture estimation result according to the posture risk bias factor and a vector representing gravity influence, so as to obtain a posture estimation result. And determining the position of the human body centroid key point according to the correction result for calculating the vertical acceleration of the human body centroid key point and performing personnel falling risk judgment. According to the method, the problem that the graph convolutional network model generates the pseudo-true attitude under the shielding of the key points is solved.

The invention relates to the technical field of automatic control, and discloses a suction force self-adaptive adjusting method based on a suction cup base, comprising the following steps: collecting current attitude disturbance information of to-be-adsorbed objects including a lamp, glass, a steel plate, a plastic box body and a wood material plate, the attitude disturbance information comprises a pitch angle, a roll angle, an angular velocity and a vertical acceleration; estimating the offset of the gravity center of the to-be-adsorbed object relative to the center of the sucker array based on the attitude disturbance information; according to the offset, target adsorption force of the object to be adsorbed is determined, and distribution is carried out according to a set load distribution weight; the invention further discloses a suction force self-adaptive adjusting system based on the suction cup base. The system comprises a posture sensing module; an offset calculation module; an adsorption force distribution module; and an adsorption control module. According to the invention, dynamic coordination and accurate tracking control of multi-sucker adsorption force are realized by fusing attitude sensing, adsorption modeling and nonlinear predictive control.