基于并行混合神经网络的碾米机故障诊断方法

doi:10.13733/j.jcam.issn.2095-5553.2025.06.033

摘要/Abstract

摘要：

为能够对碾米机故障进行快速诊断，提出一种基于并行混合神经网络的碾米机故障诊断方法。搭建碾米机故障采集系统，主要由供电端、故障端、数据采集端和数据处理端4个部分组成，其中数据采集端用于采集碾米机故障信号，数据处理端则主要负责接收并处理碾米机的故障数据，将故障数据集带入具有全局均值池化（GAP）的并行混合神经网络中进行特征提取和故障分类，获取故障诊断结果，并与其他最新的故障诊断模型进行比较。试验结果表明，该方法能够将碾米机的故障诊断精度提升至90.72%，与其他模型相比诊断性能更加优越，对碾米机故障实现快速诊断具有重要意义。

关键词: 碾米机, 故障诊断, 门控循环单元, 并行混合神经网络, 全局均值池化

Abstract:

In order to enable rapid diagnosis of rice mill machine faults, a rice mill machine fault diagnosis method based on parallel hybrid neural networks was proposed in this paper. To achieve this, a rice mill machine fault acquisition system was constructed, consisting of four components such as power supply end, fault end, data acquisition end and data processing end. The data acquisition end was utilized for collecting fault signals from the rice mill machine, while the data processing end was primarily responsible for receiving and processing the fault data of the rice mill machine. The fault data set was then input into a parallel hybrid neural network with global average pooling (GAP) for feature extraction and fault classification, and the fault diagnosis results were compared with other state‑of‑the‑art fault diagnosis models. The experimental results demonstrated that this method improved the fault diagnosis accuracy of the rice mill machine to 90.72%. Compared with other models, it exhibits superior diagnostic performance, which is of significant importance for achieving rapid diagnosis of rice mill machine faults.

Key words: rice mill, fault diagnosis, gated recurrent unit, parallel hybrid neural network, global average pooling

中图分类号:

孙秋, 蔡华锋. 基于并行混合神经网络的碾米机故障诊断方法[J]. 中国农机化学报, 2025, 46(6): 221-227.

Sun Qiu, Cai Huafeng. Fault diagnosis method of rice mill based on parallel hybrid neural network[J]. Journal of Chinese Agricultural Mechanization, 2025, 46(6): 221-227.

参考文献

[ 1 ] 程维彪. 农村小型碾米机的使用与调整[J]. 中国农机装备, 2023(8): 97-101.

Cheng Weibiao. Use and adjustment of small rice mill in rural areas [J]. China Agricultural Machinery Equipment, 2023(8): 97-101.

[ 2 ] 江法霖. 基于追溯评价体系的稻谷加工企业的损耗评价及影响因素分析[D]. 武汉: 武汉轻工大学, 2021.

[ 3 ] 郭亚丽, 程科, 周娜, 等. 碾米机智能运维体系研究[J]. 粮食科技与经济, 2022, 47(4): 114-116.

[ 4 ] Takaoka M, Inohata K, Miyake T, et al. Development of trouble diagnosis technology of 50-W-grade micro wind turbine generator [J]. Electrical Engineering in Japan, 2011, 17(1): 33-39.

[ 5 ] Wang H C, Du W L. Intelligent diagnosis of rolling bearing compound faults based on device state dictionary set sparse decomposition feature extraction‑hidden Markov model [J]. Advances in Mechanical Engineering, 2020, 12(6): 1-12.

[ 6 ] Lu J, Yin Q, Li S. Rolling bearing composite fault diagnosis method based on enhanced harmonic vector analysis [J]. Sensors, 2023, 23(11): 5115.

[ 7 ] Audigier R, Lotufo R D A. Relationships between some watershed definitions and their tie‑zone transforms [J]. Image and Vision Computing, 2010, 28(10): 1472-1482.

[ 8 ] Liu F, Shang Z, Gao M, et al. Bearing failure diagnosis at time‑varying speed based on adaptive clustered fractional Gabor transform [J]. Measurement Science and Technology, 2023, 34(9): 95002.

[ 9 ] Li M, Xu D, Zhang D. The seeding algorithms for spherical k‑means clustering [J]. Journal of Global Optimization, 2020, 76(4): 695-708.

[10] Qin Y, Shi X. Fault diagnosis method for rolling bearings based on two‑channel CNN under unbalanced datasets [J]. Applied Sciences‑Basel, 2022, 12(17): 8474.

[11] Tian H, Wang A. A novel fault diagnosis system for blast furnace based on support vector machine ensemble [J]. ISIJ International, 2010, 50(5): 738-742.

[12] Ma C, Dai G, Zhou J. Short‑term traffic flow prediction for urban road sections based on time series analysis and LSTM_BiLSTM method [J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(6): 5615-5624.

[13] Ni X, Xiong Q, Kong Q, et al. Deep HystereticNet to predict hysteretic performance of RC columns against cyclic loading [J]. Engineering Structures, 2022, 273: 115103.

[14] Wang J, Guo J, Wang L, et al. A hybrid intelligent rolling bearing fault diagnosis method combining WKN—BiLSTM and attention mechanism [J]. Measurement Science and Technology, 2023, 34(8): 85106.

[15] Jin Y, Chen C, Zhao S. Multisource data fusion diagnosis method of rolling bearings based on improved multiscale CNN [J]. Journal of Sensors, 2021, 9(12): 1-17.

[16] 王晓芳, 李林轩. 碾米机的操作管理与故障分析处理[J]. 粮食加工, 2013, 38(6): 34-37.

[17] 谢佩霞. 碾米机的故障与排除[J]. 广西农业机械化, 1994(6): 34.

[18] Xue T, Wang H, Wu D. MobileNetV2 combined with fast spectral kurtosis analysis for bearing fault diagnosis [J] Electronics, 2022, 11(19): 3176.

[19] Sun J, Wen J, Yuan C, et al. Bearing fault diagnosis based on multiple transformation domain fusion and improved residual dense networks [J]. IEEE Sensors Journal, 2022, 22(2): 1541-1551.

[20] Ma J, Wang X. Compound fault diagnosis of rolling bearing based on ACMD Gini index fusion and AO—LSTM [J]. Symmetry, 2021, 13(12): 2386.

[21] Yang M, Liu W, Zhang W, et al. Bearing vibration signal fault diagnosis based on LSTM—Cascade CatBoost [J]. Journal of Internet Technology, 2022, 23(5): 1155-1161.

[22] Che C, Wang H, Ni X, et al. Hybrid multimodal fusion with deep learning for rolling bearing fault diagnosis [J]. Measurement, 2020, 173(7): 108655.

[1]	沈伟杰, 肖茂华, 宋新民, 项腾飞. 基于连续小波变换的CNN—SVM农机滚动轴承故障诊断#br#[J]. 中国农机化学报, 2025, 46(4): 254-264.
[2]	杨宁, , , 杨林楠, , , 陈健, , . 面向联合收割机故障诊断领域知识图谱的构建技术及其问答应用[J]. 中国农机化学报, 2024, 45(6): 170-177.
[3]	李星逸, 付波, 范秀香, 权轶. 基于改进对抗蒸馏的轴承故障分类方法[J]. 中国农机化学报, 2024, 45(6): 178-183.
[4]	范卫强, , , 柳平增, , , 朱珂, , , 孟宪勇, , , 刘力宁, , . 基于主元分析的温室物联网空气温湿度传感器故障诊断[J]. 中国农机化学报, 2024, 45(5): 69-78.
[5]	邢清桂, 吴凯, 周洪斌. 基于分层特征注意力解耦的农机轴承故障诊断[J]. 中国农机化学报, 2024, 45(5): 140-146.
[6]	祝玉华, , 张钰涵, , 李智慧, , 甄彤, . 基于TCN-BiGRU结合自注意力机制的储粮温度预测研究[J]. 中国农机化学报, 2024, 45(12): 133-139.
[7]	任彬, 白东, 谢虎, 韩柏和, 肖苏伟. 基于粗糙遗传算法在打捆机齿轮箱故障诊断中的应用^*[J]. 中国农机化学报, 2021, 42(11): 103-109.
[8]	姜世腾;李军伟;聂林同;阚辉玉;孙宾宾;李德芳;. 重型拖拉机故障诊断系统开发[J]. 中国农机化学报, 2020, 41(6): 143-148.
[9]	高霞;. 基于改进SOM神经网络的农机液压系统故障诊断方法[J]. 中国农机化学报, 2019, 40(3): 128-132.
[10]	唐敏;宋云艳;. 基于专家系统和稀疏编码的农机液压系统故障诊断[J]. 中国农机化学报, 2019, 40(12): 130-135.