4 results about "Corrective control" patented technology

The application discloses a sitting posture monitoring control system of an intelligent learning desk and chair, and relates to the technical field of smart home and ergonomics equipment. The system comprises a sitting posture data acquisition module, which is used for acquiring multi-dimensional original data of a user's body posture in real time; a sitting posture state analysis module, which is used for fusion calculation and feature extraction based on the multi-dimensional original data collected by the sitting posture data acquisition module, accurate identification of a current sitting posture state and judgment of whether the current sitting posture state deviates from a health benchmark; a control strategy generation module, which is used for generating optimal correction control instructions according to the type and degree of sitting posture deviation, in combination with historical sitting posture data and personalized parameters; and an actuator driving module, which is used for accurately driving corresponding mechanical execution units of the desk and chair to adjust according to the control instructions. The application evolves from passive correction to active prevention through multi-sensor fusion perception, real-time feature extraction and personalized control strategy generation, and comprehensively monitors and dynamically corrects the sitting posture state of a user.

This application relates to the field of industrial automatic control technology, and in particular to a method and system for correcting fabric deviation based on non-contact sensing data. The method includes: acquiring the deflection angle of the fabric on the first guide roller, the transmission line speed of the fabric production line, and the original edge deviation value of the fabric at the second guide roller; determining the lateral migration rate of the fabric using the deflection angle, transmission line speed, and a preset fabric slip coefficient; performing weighted integral processing based on the lateral migration rate to determine the expected coupling deviation value of the fabric's movement from the first guide roller to the second guide roller; determining the intrinsic deviation amount of the fabric using the expected coupling deviation value; and adjusting the angle of the second guide roller based on the intrinsic deviation amount. Through the above technical solution, more accurate correction control of fabric deviation can be achieved.

This invention discloses a control system for intelligent medical mobile devices, relating to the field of intelligent medical device control technology. The system includes a data acquisition module, a feature acquisition module, a dynamic model, an error compensator, and a torque synthesis module. The data acquisition module collects kinematic data such as the device's three-axis acceleration, three-axis angular velocity, and center-of-mass coordinates. The feature acquisition module collects biometric data such as the pulse wave, respiratory rate, and blood oxygen saturation of the patient being served. Both types of data are simultaneously injected into an embedded dynamic model with preset no-load and load coupling inertial parameters. An ideal torque vector is obtained through forward dynamic inference. A closed-loop error compensator compares torque differences to generate torque correction increments, which are then superimposed to form a corrective control command. This system can adapt to different load conditions of the device, reduce torque output deviation, and improve the accuracy and adaptability of device control.

This application relates to the field of intelligent control technology and discloses a virtual-physical interactive digital twin full-closed-loop control method and system. The method includes: collecting multimodal time-series sensor data from manufacturing equipment to establish an execution-layer semantic benchmark library and a cognitive-layer confidence parameter set; selecting corresponding commands from three levels of control commands based on the confidence level and issuing them to the actuator; registering a semantic blind zone hypothesis when the confidence level is below a threshold and calculating the optimal detection action to superimpose and issue it to the actuator; and continuously issuing corrective control commands after updating the execution-layer semantic benchmark library using the detection residual vector. This application solves the problems of existing digital twin control systems being unable to recognize semantic mapping failures under operating condition drift and the virtual model being unable to actively apply directional detection to the physical actuator to eliminate cognitive blind zones.