Industrial Laser Welding Defect Detection and Image Defect Recognition Based on Deep Learning Model Developed

Image Data-Centric Visual Feature Selection on Roll-to-Roll Slot-Die Coating Systems for Edge Wave Coating Defect Detection

Roll-to-roll (R2R) manufacturing depends on a system's capability to deposit high-quality coatings with precise thickness, width, and uniformity. Therefore, consistent maintenance requires the immediate and accurate detection of coating defects. This study proposes a primary color selection (PCS) method to detect edge defects in R2R systems. This method addresses challenges associated with training data demands, complexity, and defect adaptability through a vision data-centric approach, ensuring precise edge coating defect detection. Using color information, high accuracy was achieved while minimizing data capacity requirements and processing time. Precise edge detection was facilitated by accurately distinguishing coated and noncoated regions by selecting the primary color channel based on color variability. The PCS method achieved superior accuracy (95.8%), outperforming the traditional weighted sum method (78.3%). This method is suitable for real-time detection in manufacturing systems and mitigates edge coating defects, thus facilitating quality control and production optimization.

Optimal Design of Convolutional Neural Network Architectures Using Teaching–Learning-Based Optimization for Image Classification

Convolutional neural networks (CNNs) have exhibited significant performance gains over conventional machine learning techniques in solving various real-life problems in computational intelligence fields, such as image classification. However, most existing CNN architectures were handcrafted from scratch and required significant amounts of problem domain knowledge from designers. A novel deep learning method abbreviated as TLBOCNN is proposed in this paper by leveraging the excellent global search ability of teaching–learning-based optimization (TLBO) to obtain an optimal design of network architecture for a CNN based on the given dataset with symmetrical distribution of each class of data samples. A variable-length encoding scheme is first introduced in TLBOCNN to represent each learner as a potential CNN architecture with different layer parameters. During the teacher phase, a new mainstream architecture computation scheme is designed to compute the mean parameter values of CNN architectures by considering the information encoded into the existing population members with variable lengths. The new mechanisms of determining the differences between two learners with variable lengths and updating their positions are also devised in both the teacher and learner phases to obtain new learners. Extensive simulation studies report that the proposed TLBOCNN achieves symmetrical performance in classifying the majority of MNIST-variant datasets, displays the highest accuracy, and produces CNN models with the lowest complexity levels compared to other state-of-the-art methods due to its promising search ability.

An Implementation of Trust Chain Framework with Hierarchical Content Identifier Mechanism by Using Blockchain Technology

Advances in information technology (IT) and operation technology (OT) accelerate the development of manufacturing systems (MS) consisting of integrated circuits (ICs), modules, and systems, toward Industry 4.0. However, the existing MS does not support comprehensive identity forensics for the whole system, limiting its ability to adapt to equipment authentication difficulties. Furthermore, the development of trust imposed during their crosswise collaborations with suppliers and other manufacturers in the supply chain is poorly maintained. In this paper, a trust chain framework with a comprehensive identification mechanism is implemented for the designed MS system, which is based and created on the private blockchain in conjunction with decentralized database systems to boost the flexibility, traceability, and identification of the IC-module-system. Practical implementations are developed using a functional prototype. First, the decentralized application (DApp) and the smart contracts are proposed for constructing the new trust chain under the proposed comprehensive identification mechanism by using blockchain technology. In addition, the blockchain addresses of IC, module, and system are automatically registered to InterPlanetary File System (IPFS), individually. In addition, their corresponding hierarchical CID (content identifier) values are organized by using Merkle DAG (Directed Acyclic Graph), which is employed via the hierarchical content identifier mechanism (HCIDM) proposed in this paper. Based on insights obtained from this analysis, the trust chain based on HCIDM can be applied to any MS system, for example, this trust chain could be used to prevent the counterfeit modules and ICs employed in the monitoring system of a semiconductor factory environment. The evaluation results show that the proposed scheme could work in practice under the much lower costs, compared to the public blockchain, with a total cost of 0.002094 Ether. Finally, this research is developed an innovation trust chain mechanism that could be provided the system-level security for any MS toward Industrial 4.0 in order to meet the requirements of both manufacturing innovation and product innovation in Sustainable Development Goals (SDGs).

Deep Neural Networks for Defects Detection in Gas Metal Arc Welding

Welding is one of the most complex industrial processes because it is challenging to model, control, and inspect. In particular, the quality inspection process is critical because it is a complex and time-consuming activity. This research aims to propose a system of online inspection of the quality of the welded items with gas metal arc welding (GMAW) technology through the use of neural networks to speed up the inspection process. In particular, following experimental tests, the deviations of the welding parameters—such as current, voltage, and welding speed—from the Welding Procedure Specification was used to train a fully connected deep neural network, once labels have been obtained for each weld seam of a multi-pass welding procedure through non-destructive testing, which made it possible to find a correspondence between welding defects (e.g., porosity, lack of penetrations, etc.) and process parameters. The final results have shown an accuracy greater than 93% in defects classification and an inference time of less than 150 ms, which allow us to use this method for real-time purposes. Furthermore in this work networks were trained to reach a smaller false positive rate for the classification task on test data, to reduce the presence of faulty parts among non-defective parts.