A Mold Damage Monitoring Algorithm for Power Metallurgy Molding Machines Using Bidirectional Long Short-Term Memory on an Internet of Things Platform

TL;DR

This paper introduces a mold damage monitoring system using vibration data and a bidirectional LSTM model on an IoT platform to enable early warnings and predictive maintenance.

Contribution

A novel mold health evaluation algorithm using Bi-LSTM with attention mechanism and IoT integration for early damage detection.

Findings

The vibration data from mold stamping can be used to detect mold damage with a Bi-LSTM model.

The average MSE for normal samples is below 0.5, while for abnormal samples it exceeds 1.0.

The system successfully provides early warnings for mold damage, improving predictive maintenance.

Abstract

What are the main findings?
Damage to the mold will be reflected in the vibration.The vibration caused by the damaged mold is very small.

Damage to the mold will be reflected in the vibration.

The vibration caused by the damaged mold is very small.

What are the implications of the main finding?
Bidirectional LSTM can be used to determine the mold status through vibration.The accuracy highly depends on the captured data, with a high sampling rate.

Bidirectional LSTM can be used to determine the mold status through vibration.

The accuracy highly depends on the captured data, with a high sampling rate.

In this paper, an analysis and monitoring algorithm is proposed for mold health evaluation using vibration data. Two inertial measurement units (IMUs) and an embedded system are first used to acquire vibration data from a powder metallurgy molding machine. These data are collected on an Internet of Things (IoT) platform using the Message Queueing Telemetry Transport (MQTT) protocol. For data analysis, the vibration signal on the Z axis is segmented to label the contact section of the upper and middle molds, and the corresponding vibration data of the stamping friction on the X, Y, and Z axes are extracted. Using only historical vibration data from normal stamping, a Bidirectional Long Short-Term Memory (Bi-LSTM) model with an attention mechanism is trained to predict normal stamping vibrations several minutes in advance. By comparing the predicted stamping vibrations with the observed data at the current time, the mean square errors (MSEs) are calculated to evaluate the health status of the mold. Several ablation experiments were conducted to assess the performance of the trained model. The average MSE values for normal samples and abnormal samples were smaller than 0.5 and larger than 1.0, respectively. The experimental results confirm that the trained prediction model and evaluation indicators can effectively notify operators in advance. An early warning system using vibration data for mold damage was successfully implemented, enhancing predictive maintenance.

Figures