Design of a Chamfering Tool Diagnosis System Using Autoencoder Learning Method

Abstract

. In this paper, the autoencoder learning method is proposed for the system diagnosis of chamfering tool equipment. The autoencoder uses unsupervised learning architecture. The training dataset that requires only a positive sample is quite suitable for industrial production lines. The abnormal tool can be diagnosed by comparing the output and input of the autoencoder neural network. The adjustable threshold can effectively improve accuracy. This method can effectively adapt to the current environment when the data contain multiple signals. In the experimental setup, the main diagnostic signal is the current of the motor. The current reflects the torque change when the tool is abnormal. Four-step conversions are developed to process the current signal, including (1) current-to-voltage conversion, (2) analog-digital conversion, (3) downsampling rate, and (4) discrete Fourier transform. The dataset is used to find the best autoencoder parameters by grid search. In training results, the testing accuracy, true positive rate, and precision approach are 87.5%, 83.33%, and 90.91%, respectively. The best model of the autoencoder is evaluated by online testing. The online test means loading the diagnosis model in the production line and evaluating the model. It is shown that the proposed tool can effectively detect abnormal conditions. The online assessment accuracy, true positive rate, and precision are 75%, 90%, and 69.23% in the original threshold, respectively. The accuracy can be up to 90% after adjusting the threshold, and the true positive rate and precision are up to 80% and 100%, respectively.

End-to-End Deep Learning by MCU Implementation: An Intelligent Gripper for Shape Identification

“…This mean that the reconstruction error can be used to detect defects. This model is used in many applications requiring yield detection and device detection [ 12 , 13 ]. Thus, we combine the proposed STFT-CNN and AE to develop a modified model for identifying other objects.…”

“…There are many references that address data preprocessing methods, such as discrete wavelet transform and crest factor [ 11 , 12 , 13 , 14 , 15 ]. In general, a fast Fourier transform (FFT) is selected to preprocess and the frequency features are used for machine learning [ 12 , 13 , 14 , 15 ]. Different from standard Fourier transform to obtain a spectrum of fully time domain samples, while short-time Fourier transform (STFT) is a sequence of Fourier transforms for short intervals [ 16 ].…”

End-to-End Deep Learning by MCU Implementation: Indoor Localization by Sound Spectrum of Light Fingerprints

“…should be revised as "Besides, there are only few literatures on the AI implementation in Micro-Control Unit (MCU) or SOC platform. In [9], a chamfering tool diagnostic AI algorithm was developed and installed into a SOC. A smart grape with object shape classification function was proposed and implemented into an MCU in Hung et al [10].…”

Device Light Fingerprints Identification Using MCU-Based Deep Learning Approach

“…In addition, positive and negative sample imbalances often occur during the training of machine learning. In [6], owing to the extraction of the current data of a large number of undamaged machining tools and the usage of an autoencoder (AE) to fit the undamaged current data, a reconstruction error arose when abnormal samples were input. Thus, the purpose of detecting damaged tools was achieved, producing experimental results with an accuracy of 95%.…”