A preventive maintenance embedded for the fused deposition modeling (FDM) printing technique is proposed. A monitoring and control integrated system is developed to reduce the risk of having thermal degradation on the fabricated products and prevent printing failure; nozzle clogging. As for the monitoring program, the proposed temporal neural network with a two-stage sliding window strategy (TCN-TS-SW) is utilized to accurately provide the predicted thermal values of the nozzle tip. These estimated thermal values are utilized to be the stimulus of the control system that performs countermeasures to prevent the anomaly that is bound to happen. The performance of the proposed TCN-TS-SW is presented in three case studies. The first scenario is when the proposed system outperforms the other existing machine learning algorithms namely multi-look back LSTM, GRU, LSTM, and the generic TCN architecture in terms of obtaining the highest training accuracy and lowest training loss. TCN-TS-SW also outperformed the mentioned algorithms in terms of prediction accuracy measured by the performance metrics like RMSE, MAE, and R2 scores. In the second case, the effect of varying the window length and the changing length of the forecasting horizon. This experiment reveals the optimized parameters for the network to produce an accurate nozzle thermal estimation.
Additive manufacturing is one of the rising manufacturing technologies in the future; however, due to its operational mechanism, printing failures are still prominent, leading to waste of both time and resources. The development of a real-time process monitoring system with the ability to properly forecast anomalous behaviors within fused deposition modeling (FDM) additive manufacturing is proposed as a solution to the particular problem of nozzle clogging. A set of collaborative sensors is used to accumulate time-series data and its processing into the proposed machine learning algorithm. The multi-head encoder–decoder temporal convolutional network (MH-ED-TCN) extracts features from data, interprets its effect on the different processes which occur during an operational printing cycle, and classifies the normal manufacturing operation from the malfunctioning operation. The tests performed yielded a 97.2% accuracy in anticipating the future behavior of a 3D printer.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.