An Intelligent Machine Condition Monitoring Model for Servo Systems

Hayri Mutlu,Caner Akuner,Gazi Akgün

doi:10.17694/bajece.1018947

Hayri Mutlu, Caner Akuner + Show 1 more

Open Access

https://doi.org/10.17694/bajece.1018947

Copy DOI

Abstract

The installation of industrial servo systems and the determination of control parameters are limited to the skills and knowledge of the commissioner. In addition, commissioned systems are often not re-optimized if environmental influences or loads change. The goal of this research is to create an artificial neural network (ANN) model for servo systems that will keep the servo system's proportional, integral, and derivative (PID) parameters working optimally. For this process, a machine condition monitoring algorithm developed with the ANN technique, which uses the data such as actual current, torque, power, position to be obtained from the servo system on an industrial controller, for the control and rearrangement of the parameters.

Highlights

SERVO MOTORS are preferred in the industry because of their fast and precise positioning features [1]
The whole formed together with the servo motor and the driver used for its control is described as a servo system
The performance of the artificial neural network (ANN) is tested by experiments obtained with different loads that are not used in the training process

Summary

Introduction

SERVO MOTORS are preferred in the industry because of their fast and precise positioning features [1]. Servo motors are controlled by servo drives that contain many adjustable parameters that will significantly affect their response [2]. The whole formed together with the servo motor and the driver used for its control is described as a servo system. Servo systems are time-varying and non-linear control structures [3] [4]. Servo systems must be installed in accordance with the mechanics and load characteristics they drive. PID controllers are widely used in industrial settings. The basic concept of PID controller is to regulate error, calculated with desired and actual state set to zero

Objectives

Methods

Conclusion