He, T., Li, D., Yoon, S.W.: An adaptive clustering-based genetic algorithm for the dual-gantry pick-and-place machine optimization. He, T., Li, D., Yoon, S.W.: A multi-phase planning heuristic for a dual-delivery SMT placement machine optimization. Wang, H., Lu, H., Won, D., Yoon, S.W., Srihari, K.: A boosting-based intelligent model for stencil cleaning prediction in surface mount technology. Wang, H., He, T., Yoon, S.W.: Recurrent neural network-based stencil cleaning cycle predictive modeling. 10(9), 1560–1568 (2020)Īlelaumi, S., He, J., Li, Y., Khader, N., Yoon, S.W.: Cleaning Profile Classification Using Convolutional Neural Network in Stencil Printing. 11(2), 333–341 (2020)Īlelaumi, S., Wang, H., Lu, H., Yoon, S.W.: A predictive abnormality detection model using ensemble learning in stencil printing process. Lu, H., He, J., Won, D., Yoon, S.W.: A guided evolutionary search approach for real-time stencil printing optimization. Lu, H., Wang, H., Yoon, S.W., Won, D., Park, S.: Dynamic predictive modeling of solder paste volume with real time memory update in a stencil printing process. Khader, N., Yoon, S.W.: Stencil printing process optimization to control solder paste volume transfer efficiency. Khader, N., Lee, J., Lee, D., Yoon, S.W., Yang, H.: Multi-objective optimization approach to enhance the stencil printing quality. Li, Y., He, J., Won, D., Yoon, S.W.: Noncontact reflow oven thermal profile prediction based on artificial neural network. He, T., Li, D., Yoon, S.W.: A heuristic algorithm to balance workloads of high-speed SMT machines in a PCB assembly line. Khader, N., Yoon, S.W.: Online control of stencil printing parameters using reinforcement learning approach. The model is consistent with the actual experimental results in the first approach, and the second method identified recipe shows 99% fitness in terms of \(R^2\) to the targeted profile within 10 min of starting the experiment. Specifically, the identified recipe reduces the defects by 54% compared with the original recipe. The experimental results prove the effectiveness of the entire model. The application of the simulation model makes the optimization process efficient while saving a lot of experimental materials and time. According to the requirements of Industry 4.0, the machine learning method is applied in this research to explore more information from the data to build an efficient simulation model. The second approach is adopting a Backpropagation Neural Network to simulate the air temperature from the stage-based (ramp, soak, and reflow) input data segmentation to boost the computational efficiency and optimize the recipe settings according to the simulation. The proposed model has essential significance for the solder reflow process (SRP). The optimization model adopts an Evolution Strategy (ES) with an adaptive search region and identifies the best recipe. The RFR is trained with empirical, experimental data and serves as the objective function of an optimization model. DM is a customized measure calculated from the post-Automatic Optical Inspection (AOI). The first uses a Random Forest Regression (RFR) model to generate the defect metric (DM) with different recipe inputs. In this paper, two approaches are introduced. That method takes a lot of time and effort, and it cannot guarantee consistent product quality because it depends on the engineers’ skills. The conventional method tunes the recipe to gather thermal data with a thermal measurement device and adjusts the profile through trial-and-error. Solder paste manufacturers generally provide the ideal thermal profile (i.e., target profile), and PCB manufacturers have attempted to meet the given profile by fine-tuning the oven's recipe. Inappropriate temperature profiles cause various defects, such as cracks, bridging, and delamination. The temperature settings for the reflow oven chamber (i.e., the recipe) are critical to the quality of a Printed Circuit Board (PCB) in the surface mount technology because solder joints are formed on the boards with the placed components during the reflow.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |