多階段製造過程中防止缺陷的新方法: 多階段參數優化規則生成法 (MPORG)

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：42

、訪客IP：18.222.108.185

姓名

王伊妲(Ida Wahyuni) 查詢紙本館藏

畢業系所

資訊工程學系

論文名稱

多階段製造過程中防止缺陷的新方法: 多階段參數優化規則生成法 (MPORG)
(MPORG: Multistage Parameter Optimization for Rule Generation to Prevent Defects in Multistage Manufacturing Processes)

相關論文

★ 基於最大期望算法之分析陶瓷基板機器暗裂破片率	★ 基於時間序列預測的機器良率預測
★ 基於OpenPose特徵的行人分心偵測	★ 建構深度學習CNN模型以正確分類傳統AOI模型之偵測結果
★ 一種結合循序向後選擇法與回歸樹分析的瑕疵肇因關鍵因子擷取方法與系統－以紡織製程為例	★ 融合生成對抗網路及領域知識的分層式影像擴增
★ 針織布異常偵測方法研究	★ 基於工廠生產資料的異常機器維修預測
★ 萃取駕駛人在不同環境之駕駛行為方法	★ 基於刮痕瑕疵資料擴增的分割拼接影像生成
★ 應用卷積神經網路於航攝影像做基於坵塊的水稻判釋之研究	★ 採迴歸樹進行規則探勘以有效同時降低多種紡織瑕疵
★ 應用增量式學習於多種農作物判釋之研究	★ 應用自動化測試於異質環境機器學習管道之 MLOps 系統
★ 農業影像二元分類：坵塊分離的檢測	★ 應用遷移學習於胚布瑕疵檢測

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

至系統瀏覽論文 (2027-1-31以後開放)

摘要(中)

多階段製造工藝 (MMP) 中缺陷的出現是不可避免的，並且是一個持續存在的問題，會降低產品價值和製造商利潤。因此，在一定範圍內調整 MMP 參數對於預防缺陷、動態精度和適應製造公差至關重要。然而，之前的研究主要集中在單個MMP製造階段的優化，例如織物製造中的織造階段。此外，當前的方法針對單個數字而不是範圍進行優化。因此，本研究提出了一種稱為 Multistage Parameter Optimization for Rule Generation (MPORG) 的方法來防止 MMP 中出現缺陷。在所提出的方法中，識別MMP關鍵參數，然後找到每個關鍵參數和缺陷類型的最佳值範圍，然後合併獲得的結果。本研究的結果為製造工程師在MMP中調整特定產品類型的關鍵參數提供了相關條件（即一組最佳值範圍）。所提出的方法提供了範圍值優化，在 MMP 參數調整期間為製造工程師提供了靈活的值範圍，這是線性迴歸方法無法提供的。實驗結果表明，使用真實世界 I-Manufacturing 數據集驗證的 MPORG 方法可以防止單一類型或多類型缺陷的發生，效率約為 89%。此外，實驗結果表明，在缺陷預防方面，所提出的方法在 MMP 中優於分類迴歸樹 (CART) 和多響應 CART (MR-CART) 方法。

摘要(英)

Defects occurring in multistage manufacturing processes (MMPs) are inevitable and a persistent problem that decreases product value and manufacturer profits. As a result, MMP parameter tuning in a range is critical for defect prevention, dynamic precision, and accommodating manufacturing tolerances. Nevertheless, earlier studies primarily concentrated on optimizing single stages MMP, such as the weaving stage in the context of fabric manufacturing. Moreover, current studies focus on optimizing for a single value rather than a range. Therefore, this study introduced an approach named Multistage Parameter Optimization for Rule Generation (MPORG) and aimed at preventing the occurrence of defects in MMPs. In the proposed approach, the MMPs key parameters are identified, following which the optimal value range for each key parameter and defect type is found, and the obtained results are then merged. The results of this study indicate relevant conditions (i.e., a set of the optimal value range) for manufacturing engineers in adjusting the key parameters of a particular product type in an MMP. The proposed approach provides range-value optimization that gives a flexible range of values for manufacturing engineers during the MMPs parameters adjustments, which cannot be provided by the linear regression method. The results from the experiments indicated that the MPORG approach, validated with the real-world I-Manufacturing dataset, can reduce the occurrence of both single-type and multiple-type defects by approximately 89%. Furthermore, the experimental outcomes show that the proposed approach surpasses the performance of both the classification and regression tree (CART) and multiresponse CART (MR-CART) methods in preventing defects within MMP.

關鍵字(中)

★ 布料製造
★ 工業資料探勘
★ 多階段製造工藝
★ 多類型缺陷
★ 某個取值範圍內的參數最佳化

關鍵字(英)

★ fabric manufacturing
★ industrial data mining
★ multistage manufacturing processes
★ multitype defects
★ parameter optimization in value range

論文目次

摘要 i
Abstract ii
Table of Contents iii
List of Figures v
List of Tables vi
Explanation of Symbols vii
1 Introduction 1
1-1 Challenges in Multistage Manufacturing Process 1
1-2 Proposed MPORG 4
1-3 Research Limitations and Assumptions 5
1-4 Contributions 5
2 Background 7
2-1 Fabric Manufacturing Process 7
2-2 Sequential Backward Selection (SBS) 7
2-3 Classification and Regression Tree (CART) 8
3 Related Works 13
3-1 Defect Prevention in The Fabric Manufacturing Industry 13
3-2 Advantages and Limitations of the CART Algorithm 14
4 Proposed Approach 15
4-1 Problem Formulation 15
4-2 Data Collection 18
4-3 Data Preprocessing 19
4.3.1 Data Integration 19
4.3.2 Data Transformation 20
4.3.3 Data Cleaning 21
4.3.4 Parameter Selection 22
4-4 MPORG Method 22
4.4.1 Finding Key Parameters and Value Range 23
4.4.2 The Merging Methods 26
5 Experiment Results and Discussion 28
5-1 Datasets 28
5-2 Experiment Setting 30
5.2.1 Experiment Scenario 31
5.2.2 Evaluation Metrics 31
5-3 Sensitivity Analysis on Merging Method 32
5-4 Multistage Experiments 32
5.4.1 MPORG using Union Operation 33
5.4.2 MPORG using Intersection Operation 35
5.4.3 Baseline CART Method 37
5.4.4 Baseline MR-CART Method 38
5.4.5 Baseline SBS-MR-CART Method 38
5-5 Single-stage Experiments 39
5-6 Discussions 40
6 Conclusions 42
7 Future Work 43
7-1 Limitation of Current Work 43
7-2 SBS-MR-CART Method 43
7-3 Problem Formulation 45
7-4 Experiment Design 48
7.4.1 Experimental Motivation and Purpose 48
7.4.2 Synthetic Datasets 48
References 51

參考文獻

[1] D. Zhang, Z. Liu, W. Jia, H. Liu, and J. Tan, “Path Enhanced Bidirectional Graph Attention Network for Quality Prediction in Multistage Manufacturing Process,” IEEE Trans. Ind. Informatics, vol. 18, no. 2, pp. 1018–1027, 2022, doi: 10.1109/TII.2021.3076803.
[2] M. Papananias, T. E. McLeay, M. Mahfouf, and V. Kadirkamanathan, “A Bayesian framework to estimate part quality and associated uncertainties in multistage manufacturing,” Comput. Ind., vol. 105, pp. 35–47, 2019, doi: 10.1016/j.compind.2018.10.008.
[3] K. Wang, G. Li, S. Du, L. Xi, and T. Xia, “State space modeling of variation propagation in multistage machining processes for variable stiffness structure workpieces,” Int. J. Prod. Res., vol. 59, no. 13, pp. 4033–4052, 2021, doi: 10.1080/00207543.2020.1757173.
[4] L. Ma, J. Dong, K. Peng, and C. Zhang, “Hierarchical Monitoring and Root-Cause Diagnosis Framework for Key Performance Indicator-Related Multiple Faults in Process Industries,” IEEE Trans. Ind. Informatics, vol. 15, no. 4, pp. 2091–2100, 2019, doi: 10.1109/TII.2018.2855189.
[5] S. Chakraborty, M. Moore, and L. Parrillo-Chapman, “Automatic Printed Fabric Defect Detection Based on Image Classification Using Modified VGG Network,” in Advances in Simulation and Digital Human Modeling, vol. 1206, 2021, pp. 384–393.
[6] D. Mo, W. K. Wong, Z. Lai, and J. Zhou, “Weighted Double-Low-Rank Decomposition with Application to Fabric Defect Detection,” IEEE Trans. Autom. Sci. Eng., vol. 18, no. 3, pp. 1170–1190, 2021, doi: 10.1109/TASE.2020.2997718.
[7] P. Arora and M. Hanmandlu, “Detection of defects in fabrics using information set features in comparison with deep learning approaches,” J. Text. Inst., vol. 113, no. 2, pp. 266–272, 2022, doi: 10.1080/00405000.2020.1870326.
[8] F. Psarommatis and D. Kiritsis, “A hybrid Decision Support System for automating decision making in the event of defects in the era of Zero Defect Manufacturing,” J. Ind. Inf. Integr., vol. 26, p. 100263, 2022, doi: 10.1016/j.jii.2021.100263.
[9] Y. Peng et al., “Joint Scanning Electromagnetic Thermography for Industrial Motor Winding Defect Inspection and Quantitative Evaluation,” IEEE Trans. Ind. Informatics, vol. 17, no. 10, pp. 6832–6840, 2021, doi: 10.1109/TII.2020.3045784.
[10] F. Kong, J. Li, B. Jiang, H. Wang, and H. Song, “Integrated Generative Model for Industrial Anomaly Detection via Bi-directional LSTM and Attention Mechanism,” IEEE Trans. Ind. Informatics, 2021, doi: 10.1109/TII.2021.3078192.
[11] D. Powell, M. C. Magnanini, M. Colledani, and O. Myklebust, “Advancing zero defect manufacturing: A state-of-the-art perspective and future research directions,” Comput. Ind., vol. 136, pp. 1–11, 2022, doi: 10.1016/j.compind.2021.103596.
[12] Z. Lv, J. Guo, and H. Lv, “Safety Poka Yoke in Zero-Defect Manufacturing Based on Digital Twins,” IEEE Electron Device Lettres, vol. 38, no. 5, pp. 2–10, 2017, doi: 10.1109/TII.2021.3139897.
[13] F. T. Cheng, C. Y. Lee, M. H. Hung, L. Monch, J. R. Morrison, and K. Liu, “Special Issue on Automation Analytics Beyond Industry 4.0: From Hybrid Strategy to Zero-Defect Manufacturing,” IEEE Trans. Autom. Sci. Eng., vol. 19, no. 3, pp. 1472–1476, 2022, doi: 10.1109/TASE.2022.3180525.
[14] M. Dema, C. Turner, H. Sari-Sarraf, and E. Hequet, “Machine Vision System for Characterizing Horizontal Wicking and Drying Using an Infrared Camera,” IEEE Trans. Ind. Informatics, vol. 12, no. 2, pp. 493–502, 2016, doi: 10.1109/TII.2016.2516441.
[15] R. Furferi, L. Governi, and Y. Volpe, “Modelling and simulation of an innovative fabric coating process using artificial neural networks,” Text. Res. J., vol. 82, no. 12, pp. 1282–1294, 2012, doi: 10.1177/0040517512436828.
[16] S. Dong, M. Liu, and S. Zhang, “Association Rule Mining of Silk Relics Database with the RCFP-growth Algorithm,” in Proceedings of the 38th Chinese Control Conference, 2019, pp. 7804–7809.
[17] A. Mukhopadhyay, V. K. Midha, and N. C. Ray, “Multi-objective optimization of parametric combination of injected slub yarn for producing knitted and woven fabrics with least abrasive damage,” Res. J. Text. Appar., vol. 21, no. 2, pp. 111–133, 2017, doi: 10.1108/RJTA-10-2016-0024.
[18] J.-Y. Drean and M. Decrette, “Weaving Preparation,” in Advanced Weaving Technology, Y. Kyosev and F. Boussu, Eds. France: Springer Nature Switzerland, 2022, pp. 3–80.
[19] A. Djuraev, S. Madrakhimov, and M. Erkinov, “Development of the design and justification of the parameters of the guide rapier of the weaving machine,” in Journal of Physics: Conference Series, 2021, vol. 2094, pp. 1–6, doi: 10.1088/1742-6596/2094/4/042029.
[20] Y. Zhang, S. Li, X. Qian, and J. Wang, “A fuzzy neural network based on non-euclidean distance clustering for quality index model in slashing process,” Math. Probl. Eng., vol. 2015, pp. 1–9, 2015, doi: 10.1155/2015/513039.
[21] S. V. Nejat, S. A. Darestani, M. Omidvari, and M. A. Adibi, “Evaluation of green lean production in textile industry: a hybrid fuzzy decision-making framework,” Environ. Sci. Pollut. Res., vol. 29, no. 8, pp. 11590–11611, 2022, doi: 10.1007/s11356-021-16211-4.
[22] Y. Li, J. Ai, and C. Sun, “Online fabric defect inspection using smart visual sensors,” Sensors (Switzerland), vol. 13, no. 4, pp. 4659–4673, 2013, doi: 10.3390/s130404659.
[23] X. Long, B. Fang, Y. Zhang, G. Y. Luo, and F. Sun, “Fabric defect detection using tactile information,” in IEEE International Conference on Robotics and Automation (ICRA 2021), 2021, vol. 2021, no. May, pp. 11169–11174, doi: 10.1109/ICRA48506.2021.9561092.
[24] A. Fallah, E. Jabbari, and R. Babaee, “Development of the Kansa method for solving seepage problems using a new algorithm for the shape parameter optimization,” Comput. Math. with Appl., vol. 77, no. 3, pp. 815–829, 2019, doi: 10.1016/j.camwa.2018.10.021.
[25] W. Wei, D. Deng, L. Zeng, and C. Zhang, “Real-time implementation of fabric defect detection based on variational automatic encoder with structure similarity,” J. Real-Time Image Process., vol. 18, no. 3, pp. 807–823, 2020, doi: 10.1007/s11554-020-01023-5.
[26] B. Wei, K. Hao, X. S. Tang, and L. Ren, “Fabric defect detection based on faster RCNN,” in Advances in Intelligent Systems and Computing, vol. 849, Springer International Publishing, 2019, pp. 45–51.
[27] S. Dlamini, C.-Y. Kao, S.-L. Su, and C.-F. J. Kuo, “Development of a real-time machine vision system for functional textile fabric defect detection using a deep YOLOv4 model,” Text. Res. J., vol. 92, no. 5–6, pp. 675–690, 2022, doi: 10.1177/00405175211034241.
[28] S. E. G. Jeguirim, M. Sahnoun, A. B. Dhouib, M. Cheickrouhou, L. Schacher, and D. Adolphe, “Predicting compression and surfaces properties of knits using fuzzy logic and neural networks techniques,” Int. J. Cloth. Sci. Technol., vol. 23, no. 5, pp. 294–309, 2011, doi: 10.1108/09556221111166239.
[29] G. Yao, J. Guo, and Y. Zhou, “Predicting the Warp Breakage Rate in Weaving by Neural Network Techniques,” Text. Res. J., vol. 75, no. 3, pp. 274–278, 2005, doi: 10.1177/004051750507500314.
[30] E. S. Namlıgöz, S. Çoban, and P. G. Ünal, “Prediction of various functional finishing treatments using artificial neural networks,” Fibers Polym., vol. 12, no. 3, pp. 414–421, 2011, doi: 10.1007/s12221-011-0414-8.
[31] I. Hossain, I. A. Choudhury, A. Bin Mamat, and A. Hossain, “Predicting the color properties of viscose knitted fabrics using soft computing approaches,” J. Text. Inst., vol. 108, no. 10, pp. 1689–1699, 2017, doi: 10.1080/00405000.2017.1279004.
[32] Z. A. Malik, M. H. Malik, T. Hussain, and A. Tanwari, “Predicting strength transfer efficiency of warp and weft yarns in woven fabrics using adaptive neuro-fuzzy inference system,” Indian J. Fibre Text. Res., vol. 35, no. 4, pp. 310–316, 2010.
[33] T. Hussain, A. Jabbar, and S. Ahmed, “Comparison of regression and adaptive neuro-fuzzy models for predicting the compressed air consumption in air-jet weaving,” Fibers Polym., vol. 15, no. 2, pp. 390–395, 2014, doi: 10.1007/s12221-014-0390-x.
[34] S. A. Malik et al., “Analysis and prediction of air permeability of woven barrier fabrics with respect to material, fabric construction, and process parameters,” Fibers Polym., vol. 18, no. 10, pp. 2005–2017, 2017, doi: 10.1007/s12221-017-7241-5.
[35] G. J. Vachtsevanos, J. L. Dorrity, A. Kumar, and S. Kim, “Advanced Application Of Statistical And Fuzzy Control To Textile Processes,” IEEE Trans. Ind. Appl., vol. 30, no. 3, pp. 510–516, 1994, doi: 10.1109/28.293693.
[36] I. Hossain et al., “Color fastness modeling of viscose dyed fabrics using fuzzy expert system,” in 10th International Conference on Mechanical Engineering, ICME, 2013, no. 2014, pp. 1–6.
[37] I. Hossain, A. Hossain, and I. A. Choudhury, “Color strength modeling of viscose/Lycra blended fabrics using a fuzzy logic approach,” J. Eng. Fiber. Fabr., vol. 10, no. 1, pp. 158–168, 2015, doi: 10.1177/155892501501000117.
[38] M. Sentilkumar and N. Selvakumar, “Achieving expected depth of shade in reactive dye application using artificial neural network technique,” Dye. Pigment., vol. 68, no. 2–3, pp. 89–94, 2006, doi: 10.1016/j.dyepig.2004.12.016.
[39] C. F. J. Kuo and C. C. Fang, “Optimization of the processing conditions and prediction of the quality for dyeing nylon and lycra blended fabrics,” Fibers Polym., vol. 7, no. 4, pp. 344–351, 2006, doi: 10.1007/BF02875765.
[40] A. A. Almetwally, “Multi-objective Optimization of Woven Fabric Parameters Using Taguchi–Grey Relational Analysis,” J. Nat. Fibers, vol. 17, no. 10, pp. 1468–1478, 2020, doi: 10.1080/15440478.2019.1579156.
[41] J. L. Dorrity and G. Vachtsevanos, “On-line defect detection for weaving systems,” in IEEE Textile, Fiber and Film Industry Conference, Atlanta 1996, 1996, pp. 1–6, doi: 10.1109/texcon.1996.506352.
[42] M. C. Kayacan, M. Dayik, O. Colak, and M. Kodaloglu, “Velocity control of weft insertion on air jet looms by fuzzy logic,” Fibres Text. East. Eur., vol. 12, no. 3, pp. 29–33, 2004.
[43] S. Kim and G. J. Vachtsevanos, “An intelligent approach to integration and control of textile processes,” Inf. Sci. (Ny)., vol. 123, no. 3, pp. 181–199, 2000, doi: 10.1016/S0020-0255(99)00130-9.
[44] R. A. Jelil, X. Zeng, L. Koehl, and A. Perwuelz, “Modeling plasma surface modification of textile fabrics using artificial neural networks,” Eng. Appl. Artif. Intell., vol. 26, no. 8, pp. 1854–1864, 2013, doi: 10.1016/j.engappai.2013.03.015.
[45] T. Lin, O. A. Zargar, A. M. Mallillin, S. C. Hu, and G. Leggett, “Parametric Optimization for Moisture Infiltration Prevention into a FOUP (Front Opening Unified Pod),” IEEE Trans. Semicond. Manuf., vol. 35, no. 1, pp. 118–127, 2022, doi: 10.1109/TSM.2021.3137798.
[46] G. Cavone, A. Bozza, R. Carli, and M. Dotoli, “MPC-Based Process Control of Deep Drawing: An Industry 4.0 Case Study in Automotive,” IEEE Trans. Autom. Sci. Eng., vol. 19, no. 3, pp. 1586–1598, 2022, doi: 10.1109/TASE.2022.3177362.
[47] B. Caiazzo, M. Di Nardo, T. Murino, A. Petrillo, G. Piccirillo, and S. Santini, “Towards Zero Defect Manufacturing paradigm: A review of the state-of-the-art methods and open challenges,” Comput. Ind., vol. 134, p. 103548, 2022, doi: 10.1016/j.compind.2021.103548.
[48] P. Li, P. Jiang, and W. Guo, “Modeling of Machining Errors’ Accumulation Driven by RFID Graphical Deduction Computing in Multistage Machining Processes,” IEEE Trans. Ind. Informatics, vol. 17, no. 6, pp. 3971–3981, 2021, doi: 10.1109/TII.2020.3014950.
[49] Z. He, K. P. Tran, S. Thomassey, X. Zeng, J. Xu, and C. Yi, “Multi-objective optimization of the textile manufacturing process using deep-Q-network based multi-agent reinforcement learning,” J. Manuf. Syst., vol. 62, no. January 2022, pp. 939–949, 2022, doi: 10.1016/j.jmsy.2021.03.017.
[50] S. Du, R. Xu, and L. Li, “Modeling and Analysis of Multiproduct Multistage Manufacturing System for Quality Improvement,” IEEE Trans. Syst. Man, Cybern. Syst., vol. 48, no. 5, pp. 801–820, 2018, doi: 10.1109/TSMC.2016.2614766.
[51] Z. He, J. Xu, K. P. Tran, S. Thomassey, X. Zeng, and C. Yi, “Modeling of textile manufacturing processes using intelligent techniques: a review,” Int. J. Adv. Manuf. Technol., vol. 116, no. 1–2, pp. 39–67, 2021, doi: 10.1007/s00170-021-07444-1.
[52] S. Zhou, Q. Huang, and J. Shi, “State space modeling of dimensional variation propagation in multistage machining process using differential motion vectors,” IEEE Trans. Robot. Autom., vol. 19, no. 2, pp. 296–309, 2003, doi: 10.1109/TRA.2003.808852.
[53] P. P. Phyo and C. Jeenanunta, “Daily Load Forecasting Based on a Combination of Classification and Regression Tree and Deep Belief Network,” IEEE Access, vol. 9, pp. 152226–152242, 2021, doi: 10.1109/ACCESS.2021.3127211.
[54] J. M. Hawes, “Triple Layer Papermaking Fabric Including Top and Bottom Weft Yarns Interwoven With a Warp Yarn System,” 5,454,405, 1995.
[55] B. C. Goswami, R. D. Anandjiwala, and D. Hall, Textile Sizing. 2004.
[56] Q. Huang, D. Tao, X. Li, L. Jin, and G. Wei, “Exploiting Local Coherent Patterns for Unsupervised Feature Ranking,” IEEE Trans. Syst. Man. Cybern., vol. 41, no. 6, pp. 1471–1482, 2011.
[57] W. Jiang, G. Liu, X. Zhao, and F. Yang, “Cross-Subject Emotion Recognition with a Decision Tree Classifier Based on Sequential Backward Selection,” in 11th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC, 2019, vol. 1, pp. 309–313, doi: 10.1109/IHMSC.2019.00078.
[58] J. Bemister-Buffington, A. J. Wolf, S. Raschka, and L. A. Kuhn, “Machine learning to identify flexibility signatures of class a GPCR inhibition,” Biomolecules, vol. 10, no. 3, pp. 1–22, 2020, doi: 10.3390/biom10030454.
[59] L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone, Classification And Regression Trees (1st ed.). 1984.
[60] D. H. Lee, S. H. Kim, E. S. Kim, K. J. Kim, and Z. He, “MR-CART: Multiresponse optimization using a classification and regression tree method,” Qual. Eng., vol. 33, no. 3, pp. 457–473, 2021, doi: 10.1080/08982112.2021.1888120.
[61] D. Steinberg, “CART: Classification and Regression Trees,” in The Top Ten Algorithms in Data Mining, vol. 1, X. Wu and V. Kumar, Eds. New York: CRC Press - Taylor & Francis Group, 2009, pp. 179–201.
[62] K. Y. Fung, C. K. Kwong, K. W. M. Siu, and K. M. Yu, “A multi-objective genetic algorithm approach to rule mining for affective product design,” Expert Syst. Appl., vol. 39, no. 8, pp. 7411–7419, 2012, doi: 10.1016/j.eswa.2012.01.065.
[63] K. Chikaoka and R. Shintani, “Weaving Machine,” J. Text. Mach. Soc. Japan, vol. 23, no. 3, pp. 68–72, 1977, doi: 10.2115/fiber.48.3_P116.
[64] C. K. H. Lee et al., “Using fuzzy-based association rule mining to improve production systems for chemical product development,” Int. J. Product. Qual. Manag., vol. 26, no. 4, pp. 446–468, 2019, doi: 10.1504/IJPQM.2019.099624.
[65] H. Li, J. Sun, and J. Wu, “Predicting business failure using classification and regression tree: An empirical comparison with popular classical statistical methods and top classification mining methods,” Expert Syst. Appl., vol. 37, no. 8, pp. 5895–5904, 2010, doi: 10.1016/j.eswa.2010.02.016.
[66] E. Trillas and A. R. De Soto, “On the Search of Speculations,” New Math. Nat. Comput., vol. 18, no. 01, pp. 9–18, 2022, doi: 10.1142/S1793005722500028.
[67] K. Wang, Y. Yin, S. Du, and L. Xi, “Variation management of key control characteristics in multistage machining processes considering quality-cost equilibrium,” J. Manuf. Syst., vol. 59, pp. 441–452, 2021, doi: https://doi.org/10.1016/j.jmsy.2021.03.013.
[68] W. Ren, D. Ma, and M. Han, “Multivariate Time Series Predictor With Parameter Optimization and Feature Selection Based on Modified Binary Salp Swarm Algorithm,” IEEE Trans. Ind. Informatics, vol. 19, no. 4, pp. 6150–6159, 2023, doi: 10.1109/TII.2022.3198465.
[69] S. Parvandeh, H. W. Yeh, M. P. Paulus, and B. A. McKinney, “Consensus features nested cross-validation,” Bioinformatics, vol. 36, no. 10, pp. 3093–3098, 2020, doi: 10.1093/bioinformatics/btaa046.

指導教授

梁德容(Deron Liang)

審核日期

2024-1-25

推文