Identification of Cutting Workpiece Surface Defects Based on an Improved Single Shot Multibox Detector

Abstract

In the mechanical cutting process, the surface defects of the workpiece are an important indicator of cutting quality and also reflect the condition of both the machine tool and the cutting tool. Effective detection of defects on the surface of the workpiece plays an important role in adjusting the processing conditions promptly, reducing losses, improving the utilization rate of the workpiece, and maintaining the normal operation of the equipment. To address the challenge of detecting surface defects on workpieces, an inspection method based on an improved Single Shot Multibox Detector (SSD) model is proposed. The method simplifies the detection model and reduces the computation by proposing a DH-MobileNet network instead of a VGG16 network in the SSD structure. The inverse residual structure is also used for position prediction, and null convolution is used instead of a down-sampling operation to avoid information loss. A scanning electron microscope was used to obtain the surface image of the workpiece. A dataset of workpiece surface defects was constructed and expanded, then used to train and test the model for detecting three common types of high-frequency defects: peel-off, chip adhesion, and scratches. The effect was compared with YOLO, Faster R-CNN, and the original SSD model. The detection results show that the method can detect the defects on the surface of the workpiece more accurately and quickly, which provides a new idea for defect detection in real industrial scenarios.

Keywords

Cutting machining / Workpiece surface defects / SSD / DH-MobileNet

Author Contributions

Z.D.: Preparation, Experiment, Writing. S.X.: Programming, Writing. S.W.: Visualization. Z.W.: Visualization. P.B.: Project administration. C.L.: Methodology. J.S.: Formal analysis. X.L.: Funding acquisition, Supervision, Resources.

Ethics Statement

Not applicable.

Informed Consent Statement

Not applicable.

Funding

This research was funded by [Fundamental Research Funds for the Central Universities] grant number [DUT19ZD202] and [National Natural Science Foundation of China] grant number [52475430].

Declaration of Competing Interest

The authors declare that they have no known competing interests or personal relationships that may affect the work reported in this paper.

References

[1] Yang M, Hao JC, Wu WT, Li ZH, Ma YQ, Zhou ZM, et al. Critical cutting thickness model considering subsurface damage of zirconia grinding and friction—Wear performance evaluation applied in simulated oral environment. Tribol. Int. 2024, 198, 109881. doi:10.1016/j.triboint.2024.109881.

[2] Liu MZ, Li CH, Yang M, Gao T, Wang XM, Cui X, et al. Mechanism and enhanced grindability of cryogenic air combined with biolubricant grinding titanium alloy. Tribol. Int. 2023, 187, 108704. doi:10.1016/j.triboint.2023.108704.

[3] Duan ZJ, Li CH, Zhang YB, Dong L, Bai XF, Yang M, et al. Milling surface roughness for 7050 aluminum alloy cavity influenced by nozzle position of nanofluid minimum quantity lubrication. Chin. J. Aeronaut. 2021, 34, 33-53. doi:10.1016/j.cja.2020.04.029.

[4] Cao Y, Ding WF, Zhao BA, Wen XB, Li SP, Wang JZ. Effect of intermittent cutting behavior on the ultrasonic vibration-assisted grinding performance of Inconel718 nickel-based superalloy. Precis. Eng. 2022, 78, 248-260. doi:10.1016/j.precisioneng.2022.08.006.

[5] Cao Y, Yin JF, Ding WF, Xu JH. Alumina abrasive wheel wear in ultrasonic vibration-assisted creep-feed grinding of Inconel 718 nickel-based superalloy. J. Mater. Process Tech. 2021, 297, 117241. doi:10.1016/j.jmatprotec.2021.117241.

[6] Qu SS, Yao P, Gong YD, Chu DK, Yang YY, Li CW, et al. Environmentally friendly grinding of C/SiCs using carbon nanofluid minimum quantity lubrication technology. J. Clean. Prod. 2022, 366, 132898. doi:10.1016/j.jclepro.2022.132898.

[7] Liu MZ, Li CH, Zhang YB, Yang M, Gao T, Cui X, et al. Analysis of grain tribology and improved grinding temperature model based on discrete heat source. Tribol. Int. 2023, 180, 108196. doi:10.1016/j.triboint.2022.108196.

[8] Wang HJ, Mo H, Lu SL,Zhao XM. Electrolytic capacitor surface defect detection based on deep convolution neural network.

[9] J. King Saud Univ. -Comput. Inf. Sci. 2024, 36, 101935. doi:10.1016/j.jksuci.2024.101935.

[10] He T, Liu NC, Xia HZ, Wu L, Zhang Y, Li DG, et al. Progress and trend of minimum quantity lubrication (MQL): A comprehensive review. J. Clean. Prod. 2023, 386, 135809. doi:10.1016/j.jclepro.2022.135809.

[11] Sarikaya M, Gupta MK, Tomaz I, Danish M, Mia M, Rubaiee S, et al. Cooling techniques to improve the machinability and sustainability of light-weight alloys: A state-of-the-art review. J. Manuf. Process. 2021, 62, 179-201. doi:10.1016/j.jmapro.2020.12.013.

[12] Duan ZJ, Wang SS, Wang ZH, Li CH, Li YH, Song JL, et al. Tool wear mechanisms in cold plasma and nano-lubricant multi-energy field coupled micro-milling of Al-Li alloy. Tribol. Int. 2024, 192, 109337. doi:10.1016/j.triboint.2024.109337.

[13] Duan ZJ, Wang SS, Li CH, Wang ZH, Bian P, Sun J, et al. Cold plasma and different nano-lubricants multi-energy field coupling-assisted micro-milling of Al-Li alloy 2195-T8 and flow rate optimization. J Manuf Process. 2024, 127, 218-237. doi:10.1016/j.jmapro.2024.07.146.

[14] Zhang Y, Li L, Cui X, An Q, Xu P, Wang W, et al. Lubricant activity enhanced technologies for sustainable machining: Mechanisms and processability. Chin. J. Aeronaut. 2024, doi:10.1016/j.cja.2024.08.034.

[15] Jia DZ, Zhang YB, Li CH, Yang M, Gao T, Said Z, et al. Lubrication-enhanced mechanisms of titanium alloy grinding using lecithin biolubricant. Tribol. Int. 2022, 169, 107461. doi:10.1016/j.triboint.2022.107461.

[16] Jia DZ, Li CH, Liu JH, Zhang YB, Yang M, Gao T, et al. Prediction model of volume average diameter and analysis of atomization characteristics in electrostatic atomization minimum quantity lubrication. Friction 2023, 11, 2107-2131. doi:10.1007/s40544-022-0734-2.

[17] Cönger DB, Yapan YF, Emiroglu U, Uysal A, Altan E. Influence of singular and dual MQL nozzles on sustainable milling of Al6061-T651 in different machining environments. J. Manuf. Process. 2024, 109, 524-536. doi:10.1016/j.jmapro.2023.12.043.

[18] Krishnan GP, Raj DS. Machinability and tribological analysis of used cooking oil for MQL applications in drilling AISI 304 using a low-cost pneumatic operated MQL system. J. Manuf. Process. 2023, 104, 348-371. doi:10.1016/j.jmapro.2023.09.028.

[19] Li JH, Shi WT, Lin YX, Li J, Liu S, Liu B. Comparative study on MQL milling and hole making processes for laser beam powder bed fusion (L-PBF) of Ti-6Al-4V titanium alloy. J. Manuf. Process. 2023, 94, 20-34. doi:10.1016/j.jmapro.2023.03.055.

[20] Cui X, Li CH, Zhang YB, Said Z, Debnath S, Sharma S, et al. Grindability of titanium alloy using cryogenic nanolubricant minimum quantity lubrication. J. Manuf. Process. 2022, 80, 273-286. doi:10.1016/j.jmapro.2022.06.003.

[21] Khanna N, Agrawal C, Pimenov DY, Singla AK, Machado AR, da Silva LRR, et al. Review on design and development of cryogenic machining setups for heat resistant alloys and composites. J. Manuf. Process. 2021, 68, 398-422. doi:10.1016/j.jmapro.2021.05.053.

[22] Wang XM, Li CH, Zhang YB, Said Z, Debnath S, Sharma S, et al. Influence of texture shape and arrangement on nanofluid minimum quantity lubrication turning. Int. J. Adv. Manuf. Tech. 2022, 119, 631-646. doi:10.1007/s00170-021-08235-4.

[23] Kishore K, Chauhan SR, Sinha MK. A comprehensive investigation on eco-benign grindability improvement of Inconel 625 using nano-MQL. Precis. Eng. 2024, 90, 81-95. doi:10.1016/j.precisioneng.2024.08.004.

[24] Li D, Duan Z, Hu X, Zhang D, Zhang Y.Automated classification and detection of multiple pavement distress images based on deep learning. J. Traffic Transp. Eng. 2023, 10, 276-290. doi:10.1016/j.jtte.2021.04.008.

[25] Lu HZ, Li CF, Chen WM, Jiang ZJ. A single shot multibox detector based on welding operation method for biometrics recognition in smart cities. Pattern Recogn. Lett. 2020, 140, 295-302. doi:10.1016/j.patrec.2020.10.016.

[26] Zhuang XL, Zhang TM. Detection of sick broilers by digital image processing and deep learning. Biosyst. Eng. 2019, 179, 106-116. doi:10.1016/j.biosystemseng.2019.01.003.

[27] Amemiya S, Takao H, Kato S, Yamashita H, Sakamoto N, Abe O. Automatic detection of brain metastases on contrast-enhanced CT with deep-learning feature-fused single-shot detectors. Eur. J. Radiol. 2021, 136, 109577. doi:10.1016/j.ejrad.2021.109577.

[28] Liu JM, Prabuwono AS, Abulfaraj AW, Miniaoui S, Taheri N. Cognitive cloud framework for waste dumping analysis using deep learning vision computing in healthy environment. Comput. Electr. Eng. 2023, 110, 108814. doi:10.1016/j.compeleceng.2023.108814.

[29] Xie LF, Xiang X, Xu HN, Wang L, Lin LJ, Yin GF. FFCNN: A Deep Neural Network for Surface Defect Detection of Magnetic Tile. IEEE T Ind. Electron. 2021, 68, 3506-3516. doi:10.1109/Tie.2020.2982115.

[30] Tabernik D, Sela S, Skvarc J, Skocaj D.Segmentation-based deep-learning approach for surface-defect detection. J. Intell. Manuf. 2020, 31, 759-776. doi:10.1007/s10845-019-01476-x.

[31] Neuhauser FM, Bachmann G, Hora P. Surface defect classification and detection on extruded aluminum profiles using convolutional neural networks. Int. J. Mater. Form. 2020, 13, 591-603. doi:10.1007/s12289-019-01496-1.

[32] Le HF, Zhang LJ, Liu YX. Surface Defect Detection of Industrial Parts Based on YOLOv5. IEEE Access. 2022, 10, 130784-130794. doi:10.1109/Access.2022.3228687.

[33] Niu SL, Peng YR, Li B, Qiu YH, Niu TZ, Li WF. A novel deep learning motivated data augmentation system based on defect segmentation requirements. J. Intell. Manuf. 2024, 35, 687-701. doi:10.1007/s10845-022-02068-y.

[34] Yu RY, Guo BY, Yang K. Selective Prototype Network for Few-Shot Metal Surface Defect Segmentation. IEEE T Instrum. Meas. 2022, 71, 3196447. doi:10.1109/Tim.2022.3196447.

[35] Qian W, Zhu Z, Zhu C, Luo W, Zhu Y. Efficient deployment of Single Shot Multibox Detector network on FPGAs. Integration 2024, 99, 102255. doi:10.1016/j.vlsi.2024.102255.

[36] Cai J, Makita Y, Zheng Y, Takahashi S, Hao W, Nakatoh Y. Single shot multibox detector for honeybee detection. Comput. Electr. Eng. 2022, 104, 108465. doi:10.1016/j.compeleceng.2022.108465.

[37] Qiang J, Liu W, Li X, Guan P, Du Y, Liu B, et al. Detection of citrus pests in double backbone network based on single shot multibox detector. Comput. Electron. Agric. 2023, 212, 108158. doi:10.1016/j.compag.2023.108158.

[38] Zhu W, Zhang H, Eastwood J, Qi X, Jia J, Cao Y. Concrete crack detection using lightweight attention feature fusion single shot multibox detector. Knowl. -Based Syst. 2023, 261, 110216. doi:10.1016/j.knosys.2022.110216.

[39] Sun H, Xu H, Liu B, He D, He J, Zhang H, et al. MEAN-SSD: A novel real-time detector for apple leaf diseases using improved light-weight convolutional neural networks. Comput. Electron. Agric. 2021, 189, 106379. doi:10.1016/j.compag.2021.106379.

[40] Shen YF, Zhou HL, Li JT, Jian FJ, Jayas DS. Detection of stored-grain insects using deep learning. Comput. Electron. Agr. 2018, 145, 319-325. doi:10.1016/j.compag.2017.11.039.

[41] Erhan D, Szegedy C, Toshev A, Anguelov D.Scalable Object Detection Using Deep Neural Networks. IEEE. 2013. Available online: https://arxiv.org/pdf/1312.2249 (accessed on 21 August 2024).

[42] Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, et al. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv 2017, arXiv:1704.04861.

[43] Yu F, Koltun V, Funkhouser T. Dilated Residual Networks. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21-26 July 2017. doi:10.48550/arXiv.1705.09914.

[44] Ioffe S, Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Int. Conf. Mach. Learn. 2015, 37, 448-456. doi:10.48550/arXiv.1502.03167.