Sensorless Measurement of Solenoid Stroke and Temperature using Convolution Neural Network with Two Points of PWM Driving Current

TL;DR

This paper presents a CNN-based algorithm for sensorless measurement of solenoid stroke and temperature using PWM signals, enabling non-mechanical monitoring and control of solenoid actuators.

Contribution

It introduces a novel method leveraging PWM-driven current and CNN to estimate solenoid stroke and temperature without mechanical sensors.

Findings

Accurate prediction of solenoid stroke and temperature from PWM signals

Successful preliminary control of solenoid stroke at intermediate positions

Demonstrated effectiveness of CNN in electric characteristic analysis

Abstract

In this paper, we describe the algorithm to measure the stroke and the temperature of solenoid using PWM driving current at two points based on the electric characteristics of the solenoid with CNN, without mechanical attachments. We describe the evaluation experimental results of the stroke and the temperature prediction. We also describe the preliminary experimental results of controlling the solenoid stroke at intermediate position.