Ultraviolet-curable resin was introduced as a bonding agent into the fabrication process of precision abrasive machining tools in this study, aiming to deliver a rapid, flexible, economical, and environment-friendly additive manufacturing process to replace the hot press and sintering process with thermal-curable resin. A laboratory manufacturing process was established to develop an ultraviolet-curable resin bond diamond lapping plate, the machining performance of which on the ceramic workpiece was examined through a series of comparative experiments with slurry-based iron plate lapping. The machined surface roughness and weight loss of the workpieces were periodically recorded to evaluate the surface finish quality and the material removal rate. The promising results in terms of a 12% improvement in surface roughness and 25% reduction in material removal rate were obtained from the ultraviolet-curable resin plate-involved lapping process. A summarized hypothesis was drawn to describe the dynamically-balanced state of the hybrid precision abrasive machining process integrated both the two-body and three-body abrasion mode.

Resistance spot welding poses potential challenges for automotive manufacturing enterprises with regard to ensuring the real-time and accurate quality detection of each welding spot. Nowadays, many machine learning and deep learning methods have been proposed to utilize monitored sensor data to solve these challenges. However, poor detection results or process interpretations are still unaddressed key issues. To bridge the gap, this paper takes the automotive bodies as objects, and proposes a resistance spot welding quality online detection method with dynamic current and resistance data based on a combined convolutional neural network (CNN), long short-term memory network (LSTM), and an attention mechanism. First, an overall online detection framework using an edge–cloud collaboration was proposed. Second, an online quality detection model was established. In it, the combined CNN and LSTM network were used to extract local detail features and temporal correlation features of the data. The attention mechanism was introduced to improve the interpretability of the model. Moreover, the imbalanced data problem was also solved with a multiclass imbalance algorithm and weighted cross-entropy loss function. Finally, an experimental verification and analysis were conducted. The results show that the quality detection accuracy was 98.5%. The proposed method has good detection performance and real-time detection abilities for the in-site welding processes of automobile bodies.

Traditional welding quality inspection methods for pipelines and pressure vessels are time-consuming, labor-intensive, and suffer from false and missed inspection problems. With the development of smart manufacturing, there is a need for fast and accurate in-situ inspection of welding quality. Therefore, detection models with higher accuracy and lower computational complexity are required for technical support. Based on that, an in-situ weld surface defect recognition method is proposed in this paper based on an improved lightweight MobileNetV2 algorithm. It builds a defect classification model with MobileNetV2 as the backbone of the network, embeds a Convolutional Block Attention Module (CBAM) to refine the image feature information, and reduces the network width factor to cut down the number of model parameters and computational complexity. The experimental results show that the proposed weld surface defect recognition method has advantages in both recognition accuracy and computational efficiency. In summary, the method in this paper overcomes the limitations of traditional methods and achieves the goal of reducing labor intensity, saving time, and improving accuracy. It meets the actual needs of in-situ weld surface defect recognition for pipelines, pressure vessels, and other industrial complex products.

With the increase in environmental awareness, coupled with an emphasis on environmental policy, achieving sustainable manufacturing is increasingly important. Additive manufacturing (AM) is an attractive technology for achieving sustainable manufacturing. However, with the diversity of AM types and various working states of machines’ components, a general method to forecast the energy consumption of AM is lacking. This paper proposes a new model considering the power of each component, the time of each process and the working state of each component to predict the energy consumption. Fused deposition modeling, which is a typical AM process, was selected to demonstrate the effectiveness of the proposed model. It was found that the proposed model had a higher prediction accuracy compared to the specific energy model and the process-based energy consumption model. The proposed model could be easily integrated into the software to visualize the printing time and energy consumption of each process in each component, and, further, provide a reference for coordinating the optimization of parts’ quality and energy consumption.

Additive manufacturing of conductive layers on a dielectric substrate has garnered significant interest due to its promise to produce printed electronics efficiently and its capability to print on curved substrates. A considerable challenge encountered is the conductive layer’s potential peeling due to inadequate adhesion with the dielectric substrate, which compromises the durability and functionality of the electronics. This study strives to facilitate the binding force through dielectric substrate surface modification using concentrated sulfuric acid and ultraviolet (UV) laser treatment. First, polyetheretherketone (PEEK) and nanoparticle silver ink were employed as the studied material. Second, the surface treatment of PEEK substrates was conducted across six levels of sulfuric acid exposure time and eight levels of UV laser scanning velocity. Then, responses such as surface morphology, roughness, elemental composition, chemical bonding characteristics, water contact angle, and surface free energy (SFE) were assessed to understand the effects of these treatments. Finally, the nanoparticle silver ink layer was deposited on the PEEK surface, and the adhesion force measured using a pull-off adhesion tester. Results unveiled a binding force of 0.37 MPa on unmodified surface, which escalated to 1.99 MPa with sulfuric acid treatment and 2.21 MPa with UV laser treatment. Additionally, cross-approach treatment investigations revealed that application sequence significantly impacts results, increasing binding force to 2.77 MPa. The analysis further delves into the influence mechanism of the surface modification on the binding force, elucidating that UV laser and sulfuric acid surface treatment methods hold substantial promise for enhancing the binding force between heterogeneous materials in the additive manufacturing of electronics.