During the injection molding processes, the dimensions of molded parts were easily affected by the coupling of various complex factors. To improve prediction accuracy, a quality prediction method was proposed based on temporal convolutional networks (TCN), Bidirectional gated recurrent units (BiGRU), and squeeze-and-excitation (SE) attention mechanism (TCN-BiGRU-SE). The TCN-BiGRU-SE network was utilized to extract deep features from time-series data, characterizing the dynamic changes during the injection molding processes. Quantitative feature values and dimensionless values from the injection and holding phases were extracted and stacked into a three-dimensional matrix, which was then dimensionally reduced using convolutional neural networks (CNN) to capture the changing trends at critical phases. By integrating high-frequency data, statistical features, and machine state information, an end-to-end deep prediction model was constructed for the prediction of molded part size. Comparative, ablation, and stability tests were conducted on the Foxconn injection molding dataset, along with generalization tests on three types of injection experimental datasets. The results show that the model outperforms other methods on multiple evaluation metrics, demonstrating strong robustness and generalization capability.
WANGXinming, DANGKaifang, MAYitao, et al. Development of Fault Diagnosis Technology for Injection Molding Machines[J]. China Plastics Industry, 2023, 51(11): 15-20.
[3]
KHOSRAVANIM R, NASIRIS. Injection Molding Manufacturing Process: Review of Case-based Reasoning Applications[J]. Journal of Intelligent Manufacturing, 2020, 31(4): 847-864.
LIUYongxing, TANGXiaoqi, ZHONGJinglong, et al. Asymmetric Risk Injection Molding Product Size Prediction Model Based on LightGBM[J]. China Mechanical Engineering, 2022, 33(8): 965-969.
[6]
LOCKNERY, HOPMANNC, ZHAOWeibo. Transfer Learning with Artificial Neural Networks between Injection Molding Processes and Different Polymer Materials[J]. Journal of Manufacturing Processes, 2022, 73: 395-408.
CHENYu, XIANGWei, GONGChuan. Online Diagnostic Inspection and Prediction of Product Quality in Injection Molding Intelligent Factories Based on Data Mining[J]. China Mechanical Engineering, 2023, 34(14): 1749-1755.
[9]
LUFanlei, GUIWeihua, QINLiyang, et al. A Novel Semi-supervised Prediction Modeling Method Based on Deep Learning for Flotation Process with Large Drift of Working Conditions[J]. Advanced Engineering Informatics, 2024, 62: 102934.
[10]
SOBRIEL, VERSCHELDEM, HENNEBELV, et al. Capturing Complexity over Space and Time via Deep Learning: an Application to Real-time Delay Prediction in Railways[J]. European Journal of Operational Research, 2023, 310(3): 1201-1217.
[11]
ZHOUJingtao, ZHAOXu, GAOJing. Tool Remaining Useful Life Prediction Method Based on LSTM under Variable Working Conditions[J]. The International Journal of Advanced Manufacturing Technology, 2019, 104(9): 4715-4726.
[12]
HUALiang. Comprehensive Early Warning of Power Quality in Distribution Network Based on Deep Learning[J]. Wireless Networks, 2024, 30(7): 6371-6384.
[13]
MUAZM, YUHanxin, SUNGW L, et al. A Multitask Encoder–Decoder Model for Quality Prediction in Injection Moulding[J]. Journal of Manufacturing Processes, 2023, 103: 238-247.
[14]
XIETingli, HUANGXufeng, CHOIS K. Intelligent Mechanical Fault Diagnosis Using Multisensor Fusion and Convolution Neural Network[J]. IEEE Transactions on Industrial Informatics, 2022, 18(5): 3213-3223.
[15]
DUANXiaoyan, XUELinlin, LEIChunli, et al. Rolling Bearing Fault Diagnosis Method Based on Multi-information Fusion Characteristics under Complex Working Conditions[J]. Applied Acoustics, 2023, 214: 109685.
[16]
MATianchi, SHENJunxian, SONGDi, et al. Multi-sensor and Multi-level Information Fusion Model for Compressor Blade Crack Detection[J]. Measurement, 2023, 222: 113622.
QIANQingjie, YUJunhe, ZHANHongfei, et al. Dimension Prediction Method of Injection Molded Parts Based on Multi-feature Fusion of DL-BiGRU[J]. Journal of Zhejiang University (Engineering Science), 2024, 58(3): 646-654.
[19]
CHENJianyu, ZHUANGJiaxiang, HUANGM S. Enhancing the Quality Stability of Injection Molded Parts by Adjusting V/P Switchover Point and Holding Pressure[J]. Polymer, 2021, 213: 123332.
[20]
LÓPEZA, AISAJ, MARTINEZA, et al. Injection Moulding Parameters Influence on Weight Quality of Complex Parts by Means of DOE Application: Case Study[J]. Measurement, 2016, 90: 349-356.
[21]
BAIS, KOLTERJ Z, KOLTUNV. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling [J]. Arxiv Preprint Arxiv:2018.
[22]
CHUNGJ, GULCEHREC, CHOK H, et al. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling [J]. Arxiv Preprint Arxiv:2014.
[23]
HUJie, SHENLi, SUNGang. Squeeze-and-excitation Networks[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 7132-7141.
[24]
BOGEDALEL, DOERFELS, SCHRODTA, et al. Online Prediction of Molded Part Quality in the Injection Molding Process Using High-resolution Time Series[J]. Polymers, 2023, 15(4): 978.