US 12,259,271 B2
Automatic weighing calibration method, system and excavator
Xuefeng Ji, Shanghai (CN); and Chuangshuo Zeng, Shanghai (CN)
Assigned to SHANGHAI SANY HEAVY MACHINERY CO., LTD, Shanghai (CN)
Filed by SHANGHAI SANY HEAVY MACHINERY CO., LTD, Shanghai (CN)
Filed on Aug. 15, 2023, as Appl. No. 18/449,836.
Application 18/449,836 is a continuation of application No. PCT/CN2021/124373, filed on Oct. 18, 2021.
Claims priority of application No. 202110432627.4 (CN), filed on Apr. 21, 2021.
Prior Publication US 2023/0384146 A1, Nov. 30, 2023
Int. Cl. G01G 23/01 (2006.01); E02F 9/24 (2006.01)
CPC G01G 23/01 (2013.01) [E02F 9/24 (2013.01)] 5 Claims
OG exemplary drawing
 
1. An automatic weighing calibration method for an excavator, applied to an electronic device comprising a memory, a processor, and a computer program stored on the memory and running on the processor, wherein when the processor executes the computer program, the automatic weighing calibration method for the excavator is implemented, and the automatic weighing calibration method for the excavator comprises:
obtaining, by the processor, a reference data set of the excavator under a no-load working state; wherein the reference data set comprises a plurality of reference data groups, and each reference data group comprises geometry data of the excavator, pressure data of an oil cylinder, dynamic data and no-load weighing data output by a weighing model; wherein the weighing model is a multiple linear regression model or a machine learning model configured to represent the corresponding relationship between the geometry data of the excavator, the pressure data of an oil cylinder, the dynamic data and the no-load weighing data; and each reference data group in the reference data set comprises both historical reference data groups and acquired real-time reference data groups;
calibrating, by the processor, a coefficient matrix of the weighing model to realize automatic weighing calibration for the excavator based on the reference data set;
in response to that statistical data of the no-load weighing data in the reference data set satisfies a calibration condition, configuring, by the processor, the coefficient matrix of the weighing model as an unknown matrix; and performing, by the processor, a regression fitting on the no-load data corresponding to the no-load working state, the geometric data of the excavator in the reference data set, the pressure data of the oil cylinder and the dynamic data to obtain a calibrated coefficient matrix;
wherein, the weighing model is configured to automatically weigh the excavator;
wherein before the calibrating the coefficient matrix of the weighing model to realize the automatic weighing calibration for the excavator based on the reference data set, the method further comprises:
filtering out, by the processor, abnormal reference data in the reference data set to obtain a normal reference data set corresponding to normal reference data;
wherein the calibrating the coefficient matrix of the weighing model to realize the automatic weighing calibration for the excavator based on the reference data set comprises:
calibrating, by the processor, the coefficient matrix of the weighing model to realize the automatic weighing calibration for the excavator based on the normal reference data set.