A CNN Prediction Method for Belt Grinding Tool Wear in a Polishing Process Utilizing 3-Axes Force and Vibration Data

Abstract

This paper presents a tool wear monitoring methodology on the abrasive belt grinding process using vibration and force signatures on a convolutional neural network (CNN). A belt tool typically has a random orientation of abrasive grains and grit size variation for coarse or fine material removal. Degradation of the belt condition is a critical phenomenon that affects the workpiece quality during grinding. This work focuses on the identifation and the study of force and vibrational signals taken from sensors along an axis or combination of axes that carry important information of the contact conditions, i.e., belt wear. Three axes of the two sensors are aligned and labelled as X-axis (parallel to the direction of the tool during the abrasive process), Y-axis (perpendicular to the direction of the tool during the abrasive process) and Z-axis (parallel to the direction of the tool during the retract movement). The grinding process was performed using a customized abrasive belt grinder attached to a multi-axis robot on a mild-steel workpiece. The vibration and force signals along three axes (X, Y and Z) were acquired for four discrete sequential belt wear conditions: brand-new, 5-min cycle time, 15-min cycle time, and worn-out. The raw signals that correspond to the sensor measurement along the different axes were used to supervisedly train a 10-Layer CNN architecture to distinguish the belt wear states. Different possible combinations within the three axes of the sensors (X, Y, Z, XY, XZ, YZ and XYZ) were fed as inputs to the CNN model to sort the axis (or combination of axes) in the order of distinct representation of the belt wear state. The CNN classification results revealed that the combination of the XZ-axes and YZ-axes of the accelerometer sensor provides more accurate predictions than other combinations, indicating that the information from the Z-axis of the accelerometer is significant compared to the other two axes. In addition, the CNN accuracy of the XY-axes combination of dynamometer outperformed that of other combinations.

An Embedded System Using Convolutional Neural Network Model for Online and Real-Time ECG Signal Classification and Prediction

“…The matrix from the convolution layer output will be reduced in dimension to speed up the computation process [30]. Several ways are commonly done, namely, by using max-pooling, minimum-pooling, or average-pooling [31]. The 2D matrix from the pooling layer will be converted into a 1D matrix on the Flatten layer.…”

“…In this layer, all matrix elements will be placed in a 1D array before entering the fully connected layer. At the fully connected layer, the classification process will be carried out [31]. The architecture of CNN is presented in Figure 6.…”

Sound Classification for Javanese Eagle Based on Improved Mel-Frequency Cepstral Coefficients and Deep Convolutional Neural Network

“…Example of case studies in image recognition on CNN have three stages, namely the input, CNN, and output stages [20]. Input layer is the stage for inserting images into the program and further be processed by changing the image into a binary form so that it can be process at the CNN stage [30]. The CNN algorithm develops multi-layer perceptron (MLP) to process data, one of which is two-dimensional image data, for example images.…”

A Material Removal State Prediction Method Based on Multi-Scale Attention Mechanism

“…CNN is widely used in fault diagnosis, tool wear, and other applications, and has achieved good results [18] [19]. 1D CNN is mainly used to process one-dimensional signal data, and its convolution kernel and pooling kernel are both one-dimensional.…”