US 12,130,613 B2
Industrial internet of things system, control method, and storage medium for monitoring sheet workpiece production
Zehua Shao, Chengdu (CN); Yong Li, Chengdu (CN); and Junyan Zhou, Chengdu (CN)
Assigned to CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD., Chengdu (CN)
Filed by CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD., Sichuan (CN)
Filed on Jan. 9, 2024, as Appl. No. 18/407,634.
Application 18/407,634 is a continuation of application No. 18/315,489, filed on May 10, 2023, granted, now 11,906,949.
Claims priority of application No. 202310044323.X (CN), filed on Jan. 30, 2023.
Prior Publication US 2024/0142956 A1, May 2, 2024
Int. Cl. G05B 19/418 (2006.01)
CPC G05B 19/41865 (2013.01) [G05B 19/4183 (2013.01); G05B 19/4185 (2013.01); G05B 19/41875 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An industrial Internet of Things (IoT) system for monitoring sheet workpiece production, comprising:
a non-transitory computer-readable storage medium storing computer instructions; and
at least one processor in communication with the non-transitory computer-readable storage medium, when executing the computer instructions, the at least one processor is directed to cause the IoT system to perform operations including:
obtaining a first target image on a production line through a sensor network platform; wherein the first target image is an image of a target sheet workpiece under a fixed focal length condition;
performing sharpness analysis on the first target image to generate a sharpness matrix, calculating a tilt direction and a tilt angle of the target sheet workpiece as tilt data according to the sharpness matrix, and determining deformation data of the target sheet workpiece through a first preset method based on the first target image;
inputting the tilt data and the first target image into a tilt correction model, and receiving a second target image output by the tilt correction model; wherein the second target image is an image of the target sheet workpiece in a completely horizontal state;
performing calibration and identification on the second target image, generating horizontal adjustment data and rotational adjustment data corresponding to the second target image, and calculating tilt adjustment data according to the tilt data;
processing the tilt data and the deformation data of the plurality of target sheet workpieces to obtain feature value;
in response to the feature value not satisfying a preset condition, constructing a feature vector based on the feature value;
selecting one or more vectors whose distance from the feature vector is smaller than a threshold in a vector database based on the feature vector as reference vectors, wherein the vector database is used for storing a plurality of sets of historical feature values, and each set of historical feature values includes the historical feature values, feature vectors corresponding to the historical feature values, and clamping parameters;
determining the clamping parameters corresponding to the reference vectors as candidate adjustment clamping parameters;
determining adjustment coefficients based on vector distances between the feature vector and the reference vectors;
determining target adjustment clamping parameters based on the adjustment coefficients;
sending the horizontal adjustment data, the rotational adjustment data, the tilt adjustment data, and the target adjustment clamping parameters to the production line through the sensor network platform, adjusting a bearing mechanism of the target sheet workpiece based on the horizontal adjustment data, the rotational adjustment data, and the tilt adjustment data;
adjusting clamping of the target sheet workpiece based on the target adjustment clamping parameters; and
sending the horizontal adjustment data, the rotational adjustment data, the tilt adjustment data, and the target adjustment clamping parameters to a user platform through a service platform for display.