Abstract
[Objective] To address the issue of bearing failure in fruit puree packaging machines operating in complex work environments. [Methods] This study proposes a method of bearing fault detection of fruit puree packing machine based on multi-channel depth residual graph neural network. First, it uses the Cmor wavelet to complete signal preprocessing, and converts the original one-dimensional bearing fault signal samples into two-dimensional time-frequency graph signals. Second, the study designs the multi-channel feature extraction module, which reduces the number of parameters and enhances the data interaction between each channel, so as to effectively extract the two-dimensional time-frequency spectrum information of the bearing fault signal of the fruit puree packaging machine. Third, it proposes the residual graph neural network to fully learn the bearing fault characteristics from the two-dimensional time-frequency domain data of the bearing fault signal of the fruit puree packaging machine. Finally, the study completes the sample classification of faulty bearings by using the bearing fault classification part. The accuracy, visualization, experimental comparison, and performance analysis under variable conditions and noise are conducted on the proposed method and the comparison method. [Results] The overall bearing fault accuracy of the proposed method reaches 96.95%, which is higher than 86.43% of WSVMD-net and 91.9% of OSCFD-net. When the signal-to-noise ratio (SNR) decreases from 12 to −4 dB, the bearing fault diagnosis rate of the proposed method only decreases from 95.24% to 91.35%. [Conclusion] Compared with WSVMD-net and OSCFD-net, the proposed method is more suitable for variable conditions and noisy environment, obtaining higher accuracy and lower loss value.
Publication Date
5-13-2026
First Page
63
Last Page
70
DOI
10.13652/j.spjx.1003.5788.2024.80255
Recommended Citation
Shengli, YAN; Hui, FU; and Hao, LI
(2026)
"Bearing fault detection of fruit puree packing machine based on multi-channel depth residual graph neural network,"
Food and Machinery: Vol. 42:
Iss.
3, Article 9.
DOI: 10.13652/j.spjx.1003.5788.2024.80255
Available at:
https://www.ifoodmm.cn/journal/vol42/iss3/9
References
[1] 左 斌,王 仁 忠,王 敏.基 于 AHP/AD/TRIZ 的 球 形 水 果 包 装 机设计 [J].食品与机械,2023,39(9):103-109,161.ZUO B,WANG R Z,WANG M.Design of spherical fruit packing machine based on AHP/AD/TRIZ [J].Food & Machinery,2023,39(9):103-109,161.
[2] 单迪,杨欢,谢利,等.杀菌技术在提升预制菜质量安全中的应用研究 [J].包装工程,2023,44(9):18-27.SHAN D,YANG H,XIE L,et al.Application of sterilization technology in improving the quality and safety of prepared food[J].Packaging Engineering,2023,44(9):18-27.
[3] 鲁国阳,王玉芳,胡鸿宣,等.基于极端学习机的切丝机轴承故障诊断 [J].包装工程,2023,44(S2):97-101.LU G Y,WANG Y F,HU H X,et al.Fault diagnosis of cutter bearing based on extreme learning machine [J].PackagingEngineering,2023,44(S2):97-101.
[4] ZHOU J M,YANG X T,LIU L L,et al.Fuzzy broad learning system combined with feature-engineering-based fault diagnosis for bearings [J].Machines,2022,10(12):1 229.
[5] KUANG J C,XU G H,TAO T F,et al.Domain conditioned joint adaptation network for intelligent bearing fault diagnosis across different positions and machines [J].IEEE Sensors Journal,2023,23(4):4 000-4 010.
[6] 孙佳韵,战卫侠,孙显彬,等.基于卷积神经网络的端到端低速 重 载 轴 承 故 障 诊 断 方 法 [J].制 造 业 自 动 化,2023,45(12):194-198.SUN J Y,ZHAN W X,SUN X B,et al.Fault diagnois method of end-to-end low speed and heavy-load bearing based on convolutional neural network [J].Manufacturing Automation,2023,45(12):194-198.
[7] 孙康,金江涛,李春,等.优化变分模态分解与深度学习融合的 滚 动 轴 承 故 障 诊 断 策 略 [J].动 力 工 程 学 报,2023,43(6):749-758.SUN K,JIN J T,LI C,et al.Fault diagnosis strategy for rolling bearing based on optimal fusion of variational modal decomposition and deep learning [J].Journal of Chinese Society of Power Engineering,2023,43(6):749-758.
[8] JIANG T Y,LI Y K,LI S.Multi-fault diagnosis of rolling bearing using two-dimensional feature vector of WP-VMD and PSO-KELM algorithm [J].Soft Computing,2023,27(12):8 175-8 187.
[9] CHEN X X,SUN S L.Resonance detection method and realization of bearing fault signal based on kalman filter and spectrum analysis [J].Applied Sciences-Basel,2023,13(3):1 472.
[10] JHANG J Y,LIN C J,KUO S W.Convolutional takagi-sugeno-kang-type fuzzy neural network for bearing fault diagnosis [J].Sensors and Materials,2023,35(7):2 355-2 370.
[11] HAN S J,FENG Z P.Deep subclass alignment transfer network based on time-frequency features for intelligent fault diagnosis of planetary gearboxes under time-varying speeds [J].Measurement Science and Technology,2022,33(10):105010.
[12] WEI M H,JIANG L X,ZHANG D,et al.Bearing fault feature extraction method based on variational mode decomposition of fractional fourier transform [J].Russian Journal of Nondestructive Testing,2022,58(3):221-235.
[13] 杨岗,秦礼目,吕琨,等.基于连续交叉小波相干分析和自适应CYCBD 的 轴 承 故 障 诊 断 [J].振 动 与 冲 击,2023,42(21):17-28.YANG G,QIN L M,LU K,et al.Bearing fault diagnosis based on continuous cross wavelet coherence analysis and adaptive CYCBD [J].Journal of Vibration and Shock,2023,42(21):17-28.
[14] ABDELMAKSOUD M,TORKI M,EL-HABROUK M,et al.Convolutional-neural-network-based multi-signals fault diagnosis of induction motor using single and multi-channels datasets [J].Alexandria Engineering Journal,2023,73:231-248.
[15] 侯 东 晓,周 子 安,程 荣 财,等.基 于 GADF-TL-ResNeXt 的 滚动 轴 承 故 障 诊 断 方 法 [J].计 量 学 报,2023,44(10):1 534-1 542.HOU D X,ZHOU Z A,CHENG R C,et al.Based on the GADF-TL-ResNetXt rolling bearing fault diagnosis method[J].Acta Metrologica Sinica,2023,44(10):1 534-1 542.
