Low cost digitalisation and smart transformation design based on micro controller for machine tools

Digitization and intelligence transformation are effective means to improve factory productivity, but the vast majority of enterprises do not yet have the manpower and financial resources for this transformation. With the development of chip manufacturing processes, the computing power of micro-controllers and single-board computers is increasing rapidly, while costs are gradually decreasing, and interfaces are becoming more diverse. This paper proposes a low-cost digital method using artificial neural network based predictive maintenance and control system to update actuator set points based on optimal conditions for one axis machine tools using micro-controllers or single board computers as core and vibration sensors as components. Similar to feedback regulation, the core of this proposed method is to reset actuators or sensors of a mechanical system (transformation gearbox) which is a critical element of the machine tool, communicate with the micro-controller or single board computer and to update the results in the main control terminals. The Artificial Neural Network (ANN) based Predictive Control is simulated to describe the tools more detailed and precise. The operator adjusts the machine tool after receiving the information. Compared to traditional digital and intelligent factory renovation solutions, this design has a relatively low material cost and does not require excessive interference with production scheduling, according to the finding the proposed solution has provided a error rate of less than 5‰. Through onboard intelligent algorithms such as decision trees and neural networks, machine tools can achieve a certain degree of intelligence.