Association
|
1 |
NO |
100% Classification |
- Counting transparency |
- Depend on the human factor |
100% Confidence |
- Garment industry |
- Lee et al. (2013)Lee, C. K. H., Choy, K. L., Ho, G. T. S., Chin, K. S., Law, K. M. Y., & Tse, Y. K. (2013). A hybrid OLAP-association rule mining based quality management system for extracting defect patterns in the garment industry. Expert Systems with Applications, 40(7), 2435-2446. http://dx.doi.org/10.1016/j.eswa.2012.10.057. http://dx.doi.org/10.1016/j.eswa.2012.10...
|
- Too many generated combinations |
- Long run time |
Bayes network
|
2 |
NO |
100% Detection |
- High robustness |
- Low interpretability |
94.31% |
- Textile manufacturing |
- Romli et al. (2021)Romli, I., Pardamean, T., Butsianto, S., Wiyatno, T. N., & Mohamad, E. (2021). Naive bayes algorithm implementation based on particle swarm optimization in analyzing the defect product. Journal of Physics: Conference Series, 1845(1), 012020. http://dx.doi.org/10.1088/1742-6596/1845/1/012020. http://dx.doi.org/10.1088/1742-6596/1845...
|
- Simple to implement |
- Low learning ability |
- Yapi et al. (2017)Yapi, D., Allili, M. S., & Baaziz, N. (2017). Automatic fabric defect detection using learning-based local textural distributions in the contourlet domain. IEEE Transactions on Automation Science and Engineering, 15(3), 1017-1026. |
- Great computational efficiency |
- Long run time |
|
|
- Requires a vast number of records |
|
Clustering
|
5 |
YES |
60% Classification/ Pattern recognition |
- Well suited for multimodal classes |
- Location solution |
92.55% |
- Semiconductor manufacturing |
- Taha et al. (2018)Taha, K., Salah, K., & Yoo, P. D. (2018). Clustering the dominant defective patterns in semiconductor wafer maps. IEEE Transactions on Semiconductor Manufacturing, 31(1), 156-165. http://dx.doi.org/10.1109/TSM.2017.2768323. http://dx.doi.org/10.1109/TSM.2017.27683...
|
40% Detection |
- Zero costs of the learning process |
- Sensitive to noisy or irrelevant attributes |
- IC manufacturing |
- Hsu (2015)Hsu, C.-Y. (2015). Clustering ensemble for identifying defective wafer bin map in semiconductor manufacturing. Mathematical Problems in Engineering, 2015, 1-11. http://dx.doi.org/10.1155/2015/707358. http://dx.doi.org/10.1155/2015/707358...
|
|
|
- Performance of the algorithm depends on the number of dimensions used |
|
- Ooi et al. (2013)Ooi, M., Sok, H. K., Kuang, Y. C., Demidenko, S., & Chan, C. (2013). Defect cluster recognition system for fabricated semiconductor wafers. Engineering Applications of Artificial Intelligence, 26(3), 1029-1043. http://dx.doi.org/10.1016/j.engappai.2012.03.016. http://dx.doi.org/10.1016/j.engappai.201...
|
|
|
|
|
- Yuan et al. (2011)Yuan, T., Kuo, W., & Bae, S. J. (2011). Detection of spatial defect patterns generated in semiconductor fabrication processes. IEEE Transactions on Semiconductor Manufacturing, 24(3), 24. http://dx.doi.org/10.1109/TSM.2011.2154870. http://dx.doi.org/10.1109/TSM.2011.21548...
|
|
|
|
|
- Yuan et al. (2010)Yuan, T., Bae, S. J., & Park, J. I. (2010). Bayesian spatial defect pattern recognition in semiconductor fabrication using support vector clustering. International Journal of Advanced Manufacturing Technology, 51(5-8), 671-683. http://dx.doi.org/10.1007/s00170-010-2647-x. http://dx.doi.org/10.1007/s00170-010-264...
|
Decision trees
|
3 |
YES |
100% Classification/ Pattern recognition |
- High Interpretability |
- Low robustness |
98.50% |
- Steel parts manufacturing |
- Chien et al. (2020)Chien, J., Wu, M., & Lee, J. (2020). Inspection and classification of semiconductor wafer surface defects using CNN deep learning networks. Applied Sciences, 10(15), 5340. http://dx.doi.org/10.3390/app10155340. http://dx.doi.org/10.3390/app10155340...
|
- Fast training |
- Low learning ability |
- Semiconductor manufacturing |
- Mao et al. (2018)Mao, Q., Ma, H., Zhang, X., & Zhang, G. (2018). An improved skewness decision tree svm algorithm for the classification of steel cord conveyor belt defects. Applied Sciences, 8(12), 2574. http://dx.doi.org/10.3390/app8122574. http://dx.doi.org/10.3390/app8122574...
|
- Easy to understand |
|
|
- Radhika et al. (2013)Radhika, N., Senapathi, S. B., Subramaniam, R., Subramany, R., & Vishnu, K. N. (2013). Pattern recognition based surface roughness prediction in turning hybrid metal matrix composite using random forest algorithm. Industrial Lubrication and Tribology, 65(5), 311-319. http://dx.doi.org/10.1108/ILT-02-2011-0015. http://dx.doi.org/10.1108/ILT-02-2011-00...
|
- High accuracy |
|
|
|
- Proper handling of missing values |
|
|
|
- Robustness to outliers in input space |
|
|
|
Genetic algorithm
|
2 |
YES |
100% Classification |
- Superior classification performance |
- Time-consuming iterations |
97.50% |
- Steel parts manufacturing |
- Song et al. (2019)Song, J., Kim, Y., & Park, T. (2019). SMT defect classification by feature extraction region optimization and machine learning. International Journal of Advanced Manufacturing Technology, 101(5-8), 1303-1313. http://dx.doi.org/10.1007/s00170-018-3022-6. http://dx.doi.org/10.1007/s00170-018-302...
|
- Good compatibility with other methods |
- No global optimum |
- PCB manufacturing |
|
|
|
|
- Chondronasios et al. (2016)Chondronasios, A., Popov, I., & Jordanov, I. (2016). Feature selection for surface defect classification of extruded aluminum profiles. International Journal of Advanced Manufacturing Technology, 83(1-4), 33-41. http://dx.doi.org/10.1007/s00170-015-7514-3. http://dx.doi.org/10.1007/s00170-015-751...
|
|
|
|
|
Neural network
|
38 |
NO |
18% Classification |
- High robustness |
- Low interpretability |
93.47% |
- Automotive industry |
- Jeong et al. (2021)Jeong, E., Kim, J., Jang, W., Lim, H., Noh, H., & Choi, J. (2021). A more reliable defect detection and performance improvement method for panel inspection based on artificial intelligence. Journal of Information Display, 22(3), 127-136. http://dx.doi.org/10.1080/15980316.2021.1876174. http://dx.doi.org/10.1080/15980316.2021....
|
82% Detection |
- High accuracy |
- Time inefficiency |
- Steel parts manufacturing |
- Zhu et al. (2021)Zhu, Y., Yang, R., He, Y., Ma, J., Guo, H., Yang, Y., & Zhang, L. (2021). A Lightweight multiscale attention semantic segmentation algorithm for detecting laser welding defects on safety vent of power battery. IEEE Access : Practical Innovations, Open Solutions, 9, 39245-39254. http://dx.doi.org/10.1109/ACCESS.2021.3064180. http://dx.doi.org/10.1109/ACCESS.2021.30...
|
|
- Fault tolerance |
- Lack of explanatory power |
- Semiconductor manufacturing |
- Zhao et al. (2020b) Zhao, S., Yin, L., Zhang, J., Wang, J., & Zhong, R. (2020b). Real-time fabric defect detection based onmulti-scale convolutional neural network. IET Collaborative Intelligent Manufacturing, 2(4), 189-196. http://dx.doi.org/10.1049/iet-cim.2020.0062. http://dx.doi.org/10.1049/iet-cim.2020.0...
|
|
- Versatility of use |
- Not easy to understand |
- Concrete products |
- Huang et al. (2020)Huang, Y., Qiu, C., Wang, X., Wang, S., & Yuan, K. (2020). A compact convolutional neural network for surface defect inspection. Sensors, 20(7), 1974. http://dx.doi.org/10.3390/s20071974. PMid:32244764. http://dx.doi.org/10.3390/s20071974...
|
|
- Able to handle noisy data |
- Approximation errors |
- PCB manufacturing |
- Chen et al. (2020b) Chen, X., Chen, J., Han, X., Zhao, C., Zhang, D., Zhu, K., & Su, Y. (2020b). A light-weighted CNN model for wafer structural defect detection. IEEE Access: Practical Innovations, Open Solutions, 8, 24006-24018. http://dx.doi.org/10.1109/ACCESS.2020.2970461. http://dx.doi.org/10.1109/ACCESS.2020.29...
|
|
|
- Slow learning |
- IC manufacturing |
- Shin et al. (2020)Shin, S., Jin, C., Yu, J., & Rhee, S. (2020). Real-time detection of weld defects for automated welding process base on deep neural network. Metals, 10(3), 389. http://dx.doi.org/10.3390/met10030389. http://dx.doi.org/10.3390/met10030389...
|
|
|
- Over-fitting |
- Textile manufacturing |
- Shi et al. (2020b)Shi, W., Zhang, L., Li, Y., & Liu, H. (2020b). Adversarial semi-supervised learning method for printed circuit board unknown defect detection. Journal of Engineering, 2020(13), 505-510. http://dx.doi.org/10.1049/joe.2019.1181. http://dx.doi.org/10.1049/joe.2019.1181...
|
|
|
- Local minima |
|
- Ma et al. (2019)Ma, L., Xie, W., & Zhang, Y. (2019). Blister defect detection based on convolutional neural network for polymer lithium-ion battery. Applied Sciences, 9(6), 1085. http://dx.doi.org/10.3390/app9061085. http://dx.doi.org/10.3390/app9061085...
|
|
|
|
|
- Mei et al. (2018)Mei, S., Wang, Y., & Wen, G. (2018). Automatic fabric defect detection with a multi-scale convolutional denoising autoencoder network model. Sensors, 18(4), 1064. http://dx.doi.org/10.3390/s18041064. PMid:29614813. http://dx.doi.org/10.3390/s18041064...
|
|
|
|
|
- Kholief et al. (2017)Kholief, E. A., Darwish, S. H., & Fors, M. N. (2017). Detection of steel surface defect based on machine learning using deep auto-encoder network. In Proceedings of the International Conference on Industrial Engineering and Operations Management. Rabat, Morocco, IEOM. |
|
|
|
|
- Etc. |
Regression
|
1 |
YES |
100% Detection |
- Good computation speed |
- Approximation errors |
91.30% |
- Automotive industry |
- Jiang et al. (2014)Jiang, Y., Wu, J., & Zong, C. (2014). An effective diagnosis method for single and multiple defects detection in gearbox based on nonlinear feature selection and kernel-based extreme learning machine. Journal of Vibroengineering, 16(1), 499-512. |
- Low false alarm rate |
- Poor parameter estimates due to data sparsity, overfitting, missing or incomplete data |
- Easy to interpret |
|
Support Vector Machine
|
9 |
YES |
33% Classification |
- High classification accuracy |
- Low interpretability |
95.66% |
- Automotive industry |
- Hoang & Nguyen (2020)Hoang, N., & Nguyen, Q. (2020). A novel approach for automatic detection of concrete surface voids using image texture analysis and history-based adaptive differential evolution optimized support vector machine. Advances in Civil Engineering, 2020, 1-15. http://dx.doi.org/10.1155/2020/4190682. http://dx.doi.org/10.1155/2020/4190682...
|
- GA-SVM |
67% Detection |
- High robustness |
- High complexity |
- Semiconductor manufacturing |
- Bumrungkun (2019)Bumrungkun, P. (2019). Defect detection in textile fabrics with snake active contour and support vector machines. Journal of Physics: Conference Series, 1195, 012006. http://dx.doi.org/10.1088/1742-6596/1195/1/012006. http://dx.doi.org/10.1088/1742-6596/1195...
|
- DT-SVM |
|
- Generalization ability |
|
- Concrete products |
- Jingzhong et al. (2018)Jingzhong, H., Kewen, X., Fan, Y., & Baokai, Z. (2018). Strip steel surface defects recognition based on socp optimized multiple kernel RVM. Mathematical Problems in Engineering, 2018, 1-8. http://dx.doi.org/10.1155/2018/9298017. http://dx.doi.org/10.1155/2018/9298017...
|
- CNN-SVM |
|
- Stability |
|
- PCB manufacturing |
- Takada et al. (2017)Takada, Y., Shiina, T., Usami, H., Iwahori, Y., & Bhuyan, M. K. (2017). Defect detection and classification of electronic circuit boards using keypoint extraction and CNN features. In The Ninth International Conferences on Pervasive Patterns and Applications. Athens, Greece: Iaria. |
|
|
- Ability to extract a linear combination of features |
|
|
- Wang et al. (2015)Wang, L., Törngren, M., & Onori, M. (2015). Current status and advancement of cyber-physical systems in manufacturing. Journal of Manufacturing Systems, 37(2), 517-527. http://dx.doi.org/10.1016/j.jmsy.2015.04.008. http://dx.doi.org/10.1016/j.jmsy.2015.04...
|
|
|
- Predictive power |
|
|
- Etc. |