Object reciprocating motion distance evaluation method based on deep learning

Abstract

The invention relates to an object reciprocating motion distance evaluation method based on deep learning, and the method comprises the following steps: carrying out the data sampling, and collectingthe motion acceleration change data of an object; segmenting a pressing waveform in a pulse form; correcting the data label so as to clearly see the discrete condition of the curve; marking data, integrating all pulse waveform data, calculating the weighted mean square error of each waveform, marking whether a single waveform is normal or abnormal according to the overall weighted mean square error range of the correct waveform and the abnormal waveform, disturbing a data set after marking is completed, and selecting a training set and a test set according to a certain proportion; establishinga convolutional neural network model for training, debugging parameters, optimizing the model, and storing the model to a file for subsequent reciprocating motion distance evaluation; evaluating data: putting to-be-evaluated data into the trained convolutional neural network model, and judging whether an evaluation result is normal or abnormal; and outputting an evaluation result to evaluate whether the object movement distance is proper.

Description

technical field [0001] The invention relates to a method for evaluating object movement distance, especially a method for evaluating object reciprocating movement distance based on deep learning under regular pressing movement. Background technique [0002] The measurement of distance is a problem often encountered in contemporary production practice. Displacement sensors are currently the most used in the field of displacement measurement. [0003] The existing sensor-based distance calculation is mainly based on the acceleration sensor, by calculating the speed, and then calculating the distance. In recent years, because these methods do not consider software calibration, the calculation distance is too long, resulting in large errors, and they are rarely used in distance calculations. [0004] Software calibration and sampling distance are important basis for judging short-distance movement, but there are many problems. First of all, the sampling is simple, and most of ...

AI Technical Summary

Problems solved by technology

First of all, the sampling is simple, and most of them are obtained directly by sensors. Due to the influence of noise errors and cumulative calculation errors, the distance cannot be calculated more accurately; second, the sampling frequency directly leads to calculation errors, which cannot be combined with the target movement information in the scene, so only relying on it is Unreliable

In addition, due to the large volume of the displacement sensor itself, it is difficult to install and cannot find a stable fixed point with the movement of the entire device. During the pressing process, it needs to be pressed multiple times in a short period of time. and other problems, the existing methods have no way to meet the requirements of miniaturization, portability, and low power consumption of components and parts for pressing depth detection. At the same time, it is difficult to achieve millimeter-level high precision in most cases

Images