Robust unsupervised-learning based crack detection for stamped metal products
Crack detection plays an important role in the industrial inspection of stamped metal products. While supervised learning methods are commonly used in the quality assessment process, they often require a substantial amount of labeled data, which can be challenging to obtain in a well-tuned production line. Unsupervised learning has demonstrated exceptional performance in anomaly detection. This study proposes an unsupervised algorithm for crack detection on stamped metal surfaces, capable of classification and segmentation without the need for crack images during training. The approach leverages the Vector Quantized-Variational Autoencoder 2 (VQ-VAE2) based model to reconstruct input images, while retaining crack details. Additionally, latent features at different scales are quantized into discrete representations using a codebook. To learn the distribution of these discrete representations from non-crack samples, the study utilizes PixelSNAIL, an autoregressive model used for sequential modeling. In the testing stage, the model assigns low probabilities to discrete features that deviate from the non-crack distribution. These potential crack candidate features are resampled using vectors in the codebook that exhibit the highest dissimilarity. The edited representations are then fed into the decoder to generate resampled images that have the most significant differences in the crack area from the original reconstruction. Crack patterns are extracted at the pixel level by subtracting resampled images from the reconstruction. Prior knowledge that crack patterns often appear darker is leveraged to enhance the crack features. A robust classification criterion is introduced based on the probability given by the autoregressive model. Extensive experiments were conducted using images captured from stamped metal panels. The results demonstrate that the proposed technique exhibits robust performance and high accuracy.
🧠 Monitoring the misalignment of machine tools with autoencoders after they are trained with transfer learning data
CNC machines have revolutionized manufacturing by enabling high-quality and high-productivity production. Monitoring the condition of these machines during production would reduce maintenance cost and avoid manufacturing defective parts. Misalignment of the linear tables in CNCs can directly affect the quality of the manufactured parts, and the components of the linear tables wear out over time due to the heavy and fluctuating loads. To address these challenges, an intelligent monitoring system was developed to identify normal operation and misalignments. Since damaging a CNC machine for data collection is too expensive, transfer learning was used in two steps. First, a specially designed experimental feed axis test platform (FATP) was used to sample the current signal at normal and five levels of left-side misalignment conditions ranging from 0.05 to 0.25 mm. Four different algorithm combinations were trained to detect misalignments. These combinations included a 1D convolution neural network (CNN) and autoencoder (AE) combination, a temporal convolutional network (TCN) and AE combination, a long short-term memory neural network (LSTM) and AE combination, and a CNN, LSTM, and AE combination. At the second step, Wasserstein deep convolutional generative adversarial network (W-DCGAN) was used to generate data by integrating the observed characteristics of the FATP at different misalignment levels and collected limited data from the actual CNC machines. To evaluate the similarity and limited diversity of generated and real signals, t-distributed stochastic neighbor embedding (T-SNE) method was used. The hyperparameters of the model were optimized by random and grid search. The CNN, LSTM, and AE combination demonstrated the best performance, which provides a practical way to detect misalignments without stopping production or cluttering the work area with sensors. The proposed intelligent monitoring system can detect misalignments of the linear tables of CNCs, thus enhancing the quality of manufactured parts and reducing production costs.
Achieving World-Class Predictive Maintenance with Normal Behavior Modeling
Central to the normal behavior modeling (NBM) concept is an algorithm known as an autoencoder, shown in Figure 1. Over time, the autoencoder’s input layer ingests a continuous stream of quantitative data from equipment sensors (temperature, pressure, etc.). This data is then fed to a hidden layer (of which there are typically several), where it gets compressed. Numerical weights (a value between 0 and 1) are then applied to each node, with the goal of eventually reproducing the input values at the output layer.
The principal purpose of NBM is to define the normal state of a complex system and then proactively identify instances where the system is operating outside of normal with sufficient advance warning to allow maintenance or repair actions to take place to avoid revenue loss, repair costs, and safety compromises that typically come with such failures.