Digital acquisition system calibration method based on supervised learning

Abstract

The invention discloses a digital acquisition system calibration method based on an integrated supervised learning algorithm, and the method comprises the steps: constructing a calibration system which comprises an upper computer, a high-precision standard source and a high-precision digital acquisition system, and constructing a calibration model; the upper computer controls the to-be-calibrated digital acquisition system and the high-precision digital acquisition system to acquire source signals of the high-precision standard source and simultaneously acquires working operation parameter data of the to-be-calibrated digital acquisition system, and the upper computer processes to-be-calibrated data, reference data and the working operation parameter data. And obtaining a training sample data set to train and test the calibration model, and after the calibration accuracy reaches a target, using the trained calibration model to calibrate the to-be-calibrated data of the to-be-calibrated digital acquisition system. By improving the data processing method and comprehensively considering the signal data and the working operation parameter data of the to-be-calibrated digital acquisition system, the calibration speed and the calibration precision of the digital acquisition system are improved.

Description

technical field [0001] The invention belongs to the technical field of high-precision data acquisition modules, and more specifically relates to a method for calibrating a digital acquisition system based on supervised learning. Background technique [0002] In modern industry, the data acquisition system is a very widely used electronic system, and its accuracy is very important. The calibration work of the digital acquisition system often uses a high-precision multi-function calibrator to complete the accuracy regression analysis of any value by comparing the relative true value output by the calibrator with the actual measured value of the digital acquisition system. In the calibration work of the traditional digital acquisition system, the collected raw data is transferred to the hardware storage medium after simple outlier processing for persistence, and the model is repeatedly imported to complete the calibration process. There are also many problems with this data pr...

AI Technical Summary

Problems solved by technology

[0011] a. Due to the inconsistency of the thermal noise of the device and the operating temperature curve, the operating characteristics of the device at different temperatures are very different;

[0012] b. For the same AC signal, there is a significant correlation between its amplitude and frequency; and in the case of small AC signals, due to the loss of sampling accuracy, the random noise is extremely large, and the regression curve shows obvious nonlinearity

[0013] Traditional digital acquisition system calibration usually does not consider the above factors, resulting in large errors in the final calibration

Images