This paper explores the development and application of industrial collaborative dual-arm robots for flexible, small-batch production. Compared to single-arm robots, dual-arm systems offer greater dexterity and coordination, reducing fixture requirements and improving efficiency in complex assembly tasks. Since 2011, PMC has developed dual-arm robots featuring modular design, EtherCAT-based control, and integrated safety mechanisms. Demonstrations include automated tool transport systems integrated with AMRs. Looking ahead, industrial automation will increasingly focus on human-robot collaboration rather than full labor replacement.

TMTS 2024, themed “Dual-Axis Smart Manufacturing x Sustainable Future,” focuses on digital and green transformation in the machine tool industry, integrating AI, cloud computing, big data, and digital twins to drive smart manufacturing and energy efficiency. Generative AI applications are emerging, with companies adopting them for after-sales service, maintenance, and training, while exploring AI models and knowledge management for R&D and production. Industry-academia collaboration accelerates AI implementation, enabling smart factories, improving machining quality and efficiency, and leveraging cloud platforms and common industry standards to enhance supply chain integration and sustainable development.

This paper introduces a modular smart manufacturing service platform that integrates various APPs across five production stages. Through a service solution editor, XML Process Definition Language (XPDL), task dispatch processor, and standardized JSON data structures, the platform enables flexible data exchange and collaborative operations among APPs. Built on private cloud and NoSQL technologies, it reduces integration complexity and shortens implementation time from four weeks to one hour, accelerating smart manufacturing upgrades, increasing productivity, and driving industrial digital transformation.

This study addresses preload monitoring for ball screws by introducing a diagnostic approach based on small-sample data augmentation. Prolonged operation reduces preload, compromising positioning accuracy, while traditional methods struggle to collect sufficient data. We employ Generative Adversarial Networks (GAN) to augment vibration signals and mitigate data imbalance, comparing CNN, MLP, and XGBoost models. Results show GAN-generated data significantly improves prediction accuracy and generalization, offering an effective solution for industrial machinery health monitoring.

The global wind power industry is rapidly expanding due to energy transition demands, with the wind turbine casting market projected to reach USD 6.37 billion by 2031. Manufacturing technologies are evolving toward smart, automated, and energy-efficient processes, integrating IoT and AI for improved efficiency. Leading firms like PAMA and Taiwan’s Rong Tian Precision Machinery have introduced large-scale boring and milling equipment, while quality inspection and surface treatment technologies continue to advance. The WeldCast project promotes modular welding to reduce costs. Taiwan must strengthen equipment partnerships to enhance competitiveness in the global wind energy supply chain.

The article introduces a “Rapid Detection Technology for Feed System Rigidity Attenuation in Machine Tool Drive Systems.” It utilizes servo motor sine-wave sweep measurements to obtain the Frequency Response Function (FRF), converting resonance frequency and amplitude into data for comparison with a sensitivity database to assess screw preload conditions. By integrating a digital model database, the method predicts rigidity attenuation trends, with experimental verification showing less than 3% error compared to simulations. This approach enables early fault warnings, reduces downtime losses, and improves equipment utilization and maintenance efficiency. It is well-suited for automated production lines, offering low cost and high accuracy.

This study presents the development of an “Automated Welding Preheat Temperature Monitoring and Warning System,” jointly created by ITRI and China Steel Machinery to enhance welding quality and safety. The system integrates a thermal imaging sensor mounted on a six-axis robotic arm to monitor workpiece surface temperature in real time. When the temperature exceeds preset limits, the system issues alerts and ensures compliance with welding procedure specifications. A multi-angle batch temperature measurement interface enables rapid parameter switching for different workpieces, displaying average, maximum, and minimum temperatures. Additionally, the system supports three operational modes—manual, identity-authenticated, and remote control—meeting Industry 4.0 automation requirements. This solution improves efficiency, reduces human error, and minimizes operational risks in welding processes

Machine tools are widely used across various industries. Once a processing plant receives an order, production scheduling is typically managed manually or through a Manufacturing Execution System (MES). While simple workpieces can be completed by a single machine, complex parts require multiple machines. Consequently, any accuracy deviation in a machine tool within the production line can lead to defective parts, wasting time and increasing management costs. The condition of each machine is critical; therefore, factories can ensure smooth production through annual machine tool calibration. This allows for scheduled maintenance, the activation of backup machines, and a reduction in defect rates, ultimately achieving high availability, production flexibility, and minimized waste .