KEYWORDS: Wafer bonding, Semiconductors, Packaging, Design, Data storage, Semiconducting wafers, Education and training, Manufacturing, Detection and tracking algorithms, Decision making
The wire bonding process is a significant production bottleneck in the semiconductor chip packaging and testing workshops, which has the characteristics of large-scale multi-type production orders and parallel machine. Production order splitting is critical for improving the scheduling performance of the wire bonding process. This paper proposes a wire bonding process order splitting method using deep reinforcement learning (DQN), aiming to split production orders into optimized sub-batches. Firstly, factors such as order types, quantities, processing times, and machine capacities are adopted to construct the DQN’s state space. Then, an innovative sub-batch order temporary storage location is designed to build the action space. Finally, a reward function considering the makespan is built to guide DQN’s decision-making. Experimental results show that the proposed order splitting method is superior to traditional order splitting methods in terms of the complete time. Therefore, the proposed method is effective.
In order to solve the problem of unstructured environments in the riveting assembly process of aircraft. A human-robot collaborative intelligent riveting system based on compliant control is proposed, which mainly consists of a UR robot, a six-dimensional force sensor, an impact force sensor, a bucking bar, a controller and other components. The experimental time of robot riveting is similar to simulation time, and the quality of human-robot collaborative riveting is obviously higher than that of robot automatic riveting. Through virtual simulation and experiments, this system not only addresses issues such as poor positioning accuracy and poor riveting quality in robotic automated riveting but also tackles concerns related to inconsistent quality and high labor intensity in manual pneumatic riveting. The findings of this study hold significant practical value.
Besides the driven head, the rivet shank expansion is one key product characteristic of riveted joint. The paper studies accurate mathematical modeling of pneumatic percussive riveting based on impacting dynamics. The pneumatic percussive riveting hammer and rivet are modelled as the piston-striker-rivet impacting system. Based on the proposed pressure bar impacting model, the numerical model of the pneumatic percussive riveting is constructed in the ABAQUS. The rivet’s dynamic behavior under high strain rate and the percussive squeezing forces are studied intensively. A pneumatic percussive riveting platform is constructed to gather the percussive squeezing force during the course of pneumatic percussive riveting experiments. The riveted plates and the gathered percussive squeezing forces are considered to validate the proposed numerical model. The experimental results show that the proposed numerical model predicts the pneumatic percussive riveting well. The proposed impacting model successfully modelled the percussive riveting process of the pneumatic hammer.
Manual percussive riveting quality varies due to the different operations of the workers, which result from different training categories and processes. The paper proposed a squeezing force based percussive riveting training system to improve the recruits’ operation skills and the training efficiency. Force sensor is installed in the bucking bar to gather the squeezing force signal of the percussive riveting. The squeezing force signal of the expert technicians is used as the standard operation of the manual pneumatic percussive riveting. Quantitative indices are extracted from the squeezing force signals in order to provide the recruits with quantitative parameter for efficient training. Data-driven training categories based on the proposed training platform are developed to assure the operators maintain the qualified skills constantly. The squeezing force-based training system for pneumatic percussive riveting provides good platform for the recruits training. The proposed system can be used for high-skilled technicians training with good quality and efficiency.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.