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

A solenoid is used to push or pull an object, and the stroke is typically controlled in two states of ON and OFF. Various studies have been carried out to measure and control the plunger position of a solenoid at an intermediate position by measuring the electrical characteristics of the solenoid. We previously reported a method for measuring the stroke of a solenoid (plunger position) using its electric characteristics without mechanical attachments. However, the method is limited by the differences in the electrical characteristics of the target solenoid and the solenoids to which it can be applied. In this study, we proposed a method to measure the stroke and temperature of a solenoid using a convolution neural network for two measured values of driving current and evaluated its accuracy. Herein, we have described the results obtained for the preliminary experiments carried out to control the plunger position without mechanical attachments. © 2025 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.