复杂数据驱动下的质量检测、监测与运维技术研究综述

doi:10.16381/j.cnki.issn1003-207x.2024.1767

摘要/Abstract

摘要：

在制造业领域，产品质量管理是企业核心竞争力构建的关键环节。传统的质量管理手段先后关注结果质量、过程质量、全流程质量的相关方法。然而，随着21世纪后全球互联网的深度发展，以智能化、自动化为特色的“智能+”信息化技术开辟了质量管理技术新阶段，因此，数据成为了新时代质量管理的基础，贯穿于产品从设计到退役的全生命周期之中。数据的表现形式多样，涵盖了文本记录、数值指标、图像分析、视频监控等多元化形态，不仅促使数据收集手段需不断创新与丰富，以满足多样化的数据捕获需求，同时也对数据分析理论的深度、模型的适用性提出了更为严苛的要求。然而，数据的不平衡、多源异构等复杂特性为质量管理新技术的应用带来了挑战。在此背景下，本文聚焦于制造业产品生产过程，以检测、监测、运维为导向，探究了复杂数据在制造业产品生产质量管理中的前沿技术，并总结了现有挑战，展望了未来研究的发展趋势。

关键词: 复杂数据, 质量管理, 质量检测, 质量监测, 运维管理

Abstract:

In the field of manufacturing， quality management plays a critical role in enhancing companies' core competitiveness. Traditional approaches to quality management have rapidly evolved， transitioning from an emphasis on quality inspection to quality monitoring， and ultimately to full life-cycle quality management. However， with the rapid development of the global Internet in the 21st century， "smart+" technologies， characterized by intelligence and automation， have ushered in a new era of quality management techniques. Consequently， data has emerged as the cornerstone of modern quality management across every stage of the product life cycle. Data manifests in diverse forms， including text， numeric， images， video， and other formats. This diversity not only promotes the continuous innovation and data collection methods， but also imposes higher demands on the theoretical depth of data analysis and the applicability of analytical models. Complex data characteristics， such as data imbalance and multi-source heterogeneity， pose significant challenges to the quality management technologies. In this context， it focuses on the process of manufacturing， with a focus on quality inspection， monitoring， and operations and maintenance （O&M）. It summarizes the cutting-edge technologies that address complex data in quality management and provides insights into prospective research directions in this field.

Key words: complex data, quality management, quality inspection, quality monitoring, operation and maintenance management

中图分类号:

F253.3

高园园,洪铦栋,陶宝平, 等. 复杂数据驱动下的质量检测、监测与运维技术研究综述[J]. 中国管理科学, 2026, 34(2): 41-55.

Yuanyuan Gao,Xiandong Hong,Baoping Tao, et al. Review of Quality Detection, Monitoring, Operation and Maintenance Technology Driven by Complex Data[J]. Chinese Journal of Management Science, 2026, 34(2): 41-55.

图/表 1

参考文献 87

[1]	中共中央，国务院. 质量强国建设纲要［N］. 人民日报， 2023-02-07（1）.
	Central Committee of the Communist Party of China， Council State. Outline for building a quality-powered nation ［N］. People's Daily， 2023-02-07（1）.
[2]	工业和信息化部科技司. 夯实“中国制造”的质量基础［N］. 中国电子报， 2023-12-26（2）.
	Department of Science and Technology， Ministry of Industry and Information Technology. Strengthening the quality foundation of “Made in China” ［N］. China Electronics News， 2023-12-26（2）.
[3]	Gaw N， Yousefi S， Gahrooei M R. Multimodal data fusion for systems improvement： A review［J］. IISE Transactions， 2022， 54（11）： 1098-1116.
[4]	Tsung F， Zhang K， Cheng L， et al. Statistical transfer learning： A review and some extensions to statistical process control［J］. Quality Engineering， 2018， 30（1）： 115-128.
[5]	Ding Y， Zeng L， Zhou S. Phase I analysis for monitoring nonlinear profiles in manufacturing processes［J］. Journal of Quality Technology， 2006， 38（3）： 199-216.
[6]	刘心报，胡俊迎，陆少军，等. 新一代信息技术环境下的全生命周期质量管理［J］. 管理科学学报， 2022， 25（7）： 2-11.
	Liu X B， Hu J Y， Lu S J， et al. The entire life cycle quality management in the new generation of information technology environment［J］. Journal of Management Sciences in China， 2022， 25（7）： 2-11.
[7]	Sony M， Antony J， Douglas J A. Essential ingredients for the implementation of Quality 4.0： A narrative review of literature and future directions for research［J］. The TQM Journal， 2020， 32（4）： 779-793.
[8]	Antony J， McDermott O， Sony M. Quality 4.0 conceptualisation and theoretical understanding： A global exploratory qualitative study［J］. The TQM Journal， 2022， 34（5）： 1169-1188.
[9]	工业和信息化部科技司. 全面强化质量管理数字化能力加快推动制造业高质量发展［N］. 中国电子报， 2022-01-14（6）.
	Department of Science and Technology，Ministry of Industry and Information Technology. Comprehensively strengthening the digitization capability in quality management to accelerate the high-quality development for manufacturing industries［N］. China Electronics News， 2022-01-14（6）.
[10]	Avola D， Cascio M， Cinque L， et al. Real-time deep learning method for automated detection and localization of structural defects in manufactured products［J］. Computers & Industrial Engineering， 2022， 172： 108512.
[11]	Baek J， Jeong M K， Elsayed E A. Residual-based surface segmentation for monitoring topographic variations［J］. IEEE Transactions on Automation Science and Engineering， 2022， 19（1）： 280-294.
[12]	Manivannan S. Collaborative deep semi-supervised learning with knowledge distillation for surface defect classification［J］. Computers & Industrial Engineering， 2023， 186： 109766.
[13]	林时雨，闫雪娇，谢哲，等. 基于时间序列及邻域分析的管道点云障碍物检测［J］. 激光与光电子学进展， 2022， 59（22）： 2210007.
	Lin S Y， Yan X J， Xie Z， et al. Obstacle detection for a pipeline point cloud based on time series and neighborhood analysis［J］. Laser & Optoelectronics Progress， 2022， 59（22）： 2210007.
[14]	Wang F， Song G， Mao J， et al. Internal defect detection of overhead aluminum conductor composite core transmission lines with an inspection robot and computer vision［J］. IEEE Transactions on Instrumentation and Measurement， 2023， 72： 3512516.
[15]	Wang J， Li G， Bai H， et al. A hybrid deep learning-based framework for chip packaging fault diagnostics in X-ray images［J］. IEEE Transactions on Industrial Informatics， 2024， 20（9）： 11181-11191.
[16]	Arcos Jiménez A， Gómez Muñoz C Q， García Márquez F P. Dirt and mud detection and diagnosis on a wind turbine blade employing guided waves and supervised learning classifiers［J］. Reliability Engineering & System Safety， 2019， 184： 2-12.
[17]	Chabot A， Laroche N， Carcreff E， et al. Towards defect monitoring for metallic additive manufacturing components using phased array ultrasonic testing［J］. Journal of Intelligent Manufacturing， 2020， 31（5）： 1191-1201.
[18]	Ding L， Lu Q， Liu S， et al. Quality inspection of micro solder joints in laser spot welding by laser ultrasonic method［J］. Ultrasonics， 2022， 118： 106567.
[19]	Li Y， Li R. Research on construction method of knowledge graph-based on mobile phone quality detection［C］// Proceedings of 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference （ITOEC）， Chongqing， China， June 12-14， IEEE， 2020： 695-699.
[20]	Li Q， Yang B， Wang S， et al. A fine-grained flexible graph convolution network for visual inspection of resistance spot welds using cross-domain features［J］. Journal of Manufacturing Processes， 2022， 78： 319-329.
[21]	Fan C L. Defect risk assessment using a hybrid machine learning method［J］. Journal of Construction Engineering and Management， 2020， 146（9）： 04020102.
[22]	Yang Y， Chen X. Crowdsourced test report prioritization based on text classification［J］. IEEE Access， 2022， 10： 92692-92705.
[23]	Mohandas R， Mongan P， Hayes M. Ultrasonic weld quality inspection involving strength prediction and defect detection in data-constrained training environments［J］. Sensors， 2024， 24（20）： 6553.
[24]	Mosca N， Renò V， Nitti M， et al. Post assembly quality inspection using multimodal sensing in aircraft manufacturing［C］//Multimodal Sensing and Artificial Intelligence： Technologies and Applications II， Germany， June 21-26 ， SPIE， 2021： 2594104.
[25]	Chheang V， Narain S， Hooten G， et al. Enabling additive manufacturing part inspection of digital twins via collaborative virtual reality［J］. Scientific Reports， 2024， 14： 29783.
[26]	Gao Y， Feng Y， Ji S， et al. HGNN： General hypergraph neural networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2023， 45（3）： 3181-3199.
[27]	封晓斌，汤易兵，吴增源，等. 基于SRFML-Lift的流程制造产品质量状态监测［J］. 中国管理科学， 2021， 29（12）： 227-236.
	Feng X B， Tang Y B， Wu Z Y， et al. Process manufacturing product quality status monitoring based on SRFML-lift［J］. Chinese Journal of Management Science， 2021， 29（12）： 227-236.
[28]	Xu R， Huang S， Song Z， et al. A deep mixed-effects modeling approach for real-time monitoring of metal additive manufacturing process［J］. IISE Transactions， 2024， 56（9）： 945-959.
[29]	Lu Y， Wang Y. An efficient transient temperature monitoring of fused filament fabrication process with physics-based compressive sensing［J］. IISE Transactions， 2019， 51（2）： 168-180.
[30]	Zhang Z， Sahu C K， Singh S K， et al. Machine learning based prediction of melt pool morphology in a laser-based powder bed fusion additive manufacturing process［J］. International Journal of Production Research， 2024， 62（5）： 1803-1817.
[31]	Wang R， Zhang L， Chen N. Spatial correlated data monitoring in semiconductor manufacturing using Gaussian process model［J］. IEEE Transactions on Semiconductor Manufacturing， 2019， 32（1）： 104-111.
[32]	韩云霞，马义中，欧阳林寒，等. 高质量低成本视角下的参数和容差整合设计［J］. 中国管理科学， 2024， 32（8）： 159-170.
	Han Y X， Ma Y Z， Ouyang L H， et al. Integrated design of parameters and tolerances under high-quality and low-cost perspective［J］. Chinese Journal of Management Science， 2024， 32（8）： 159-170.
[33]	Wu D， Chen H， Huang Y， et al. Online monitoring and model-free adaptive control of weld penetration in VPPAW based on extreme learning machine［J］. IEEE Transactions on Industrial Informatics， 2019， 15（5）： 2732-2740.
[34]	Shui H， Jin X， Ni J. Twofold variation propagation modeling and analysis for roll-to-roll manufacturing systems［J］. IEEE Transactions on Automation Science and Engineering， 2019， 16（2）： 599-612.
[35]	王鸿鹭，蒋炜，魏来，等. 基于物联网的产品全生命周期质量管理的模式创新与展望［J］. 系统工程理论与实践， 2021， 41（2）： 475-482.
	Wang H L， Jiang W， Wei L， et al. Product lifecycle quality management based on the Internet of Things： Business model innovation and future outlook［J］. Systems Engineering-Theory & Practice， 2021， 41（2）： 475-482.
[36]	Aminzadeh M， Kurfess T R. Online quality inspection using Bayesian classification in powder-bed additive manufacturing from high-resolution visual camera images［J］. Journal of Intelligent Manufacturing， 2019， 30（6）： 2505-2523.
[37]	Zhang Y， Soon H G， Ye D， et al. Powder-bed fusion process monitoring by machine vision with hybrid convolutional neural networks［J］. IEEE Transactions on Industrial Informatics， 2020， 16（9）： 5769-5779.
[38]	Mojahed Yazdi R， Imani F， Yang H. A hybrid deep learning model of process-build interactions in additive manufacturing［J］. Journal of Manufacturing Systems， 2020， 57： 460-468.
[39]	Yin M， Zhuo S， Xie L， et al. Online monitoring of local defects in robotic laser additive manufacturing process based on a dynamic mapping strategy and multibranch fusion convolutional neural network［J］. Journal of Manufacturing Systems， 2023， 71： 494-503.
[40]	Hong Y， Yang M， Jiang Y， et al. Real-time quality monitoring of ultrathin sheets edge welding based on microvision sensing and SOCIFS-SVM［J］. IEEE Transactions on Industrial Informatics， 2023， 19（4）： 5506-5516.
[41]	Guo S， Chen M， Abolhassani A， et al. Identifying manufacturing operational conditions by physics-based feature extraction and ensemble clustering［J］. Journal of Manufacturing Systems， 2021， 60： 162-175.
[42]	Hong Y， He X， Xu J， et al. AF-FTTSnet： An end-to-end two-stream convolutional neural network for online quality monitoring of robotic welding［J］. Journal of Manufacturing Systems， 2024， 74： 422-434.
[43]	Zhou Y， Chang B， Zou H， et al. Online visual monitoring method for liquid rocket engine nozzle welding based on a multi-task deep learning model［J］. Journal of Manufacturing Systems， 2023， 68： 1-11.
[44]	Wang Z， Iquebal A S， Bukkapatnam S T S. A vision-based monitoring approach for real-time control of laser origami cybermanufacturing processes［J］. Procedia Manufacturing， 2018， 26： 1307-1317.
[45]	Segura L J， Wang T， Zhou C， et al. Online droplet anomaly detection from streaming videos in inkjet printing［J］. Additive Manufacturing， 2021， 38： 101835.
[46]	Bugatti M， Colosimo B M. Towards real-time in situ monitoring of hot-spot defects in L-PBF： A new classification-based method for fast video-imaging data analysis［J］. Journal of Intelligent Manufacturing， 2022， 33（1）： 293-309.
[47]	Yan H， Grasso M， Paynabar K， et al. Real-time detection of clustered events in video-imaging data with applications to additive manufacturing［J］. IISE Transactions， 2022， 54（5）： 464-480.
[48]	Yoder S， Morgan S， Kinzy C， et al. Characterization of topology optimized Ti-6Al-4V components using electron beam powder bed fusion［J］. Additive Manufacturing， 2018， 19： 184-196.
[49]	Nagy Z， Werner-Stark Á， Dulai T. An industrial application using process mining to reduce the number of faulty products［C］//Proceedings of European Conference on Advances in Databases and Information Systems（ADBIS），Budapest， Hungary， September 2-5 ，Springer International Publishing， 2018： 352-363.
[50]	Du Y. Introducing the visual imaging feature to the text analysis： High efficient soft computing models with Bayesian network［J］. Neural Processing Letters， 2021， 53（4）： 2403-2419.
[51]	Luftensteiner S， Praher P. Log file anomaly detection based on process mining graphs［C］//Proceedings of 2022 International Conference on Database and Expert Systems Applications （DEXA）， Vienna， Austria， August 22-24 ， Cham： Springer International Publishing， 2022： 383-391.
[52]	Rao P K， Liu J P， Roberson D， et al. Online real-time quality monitoring in additive manufacturing processes using heterogeneous sensors［J］. Journal of Manufacturing Science and Engineering， 2015， 137（6）： 061007.
[53]	Vandone A， Baraldo S， Valente A. Multisensor data fusion for additive manufacturing process control［J］. IEEE Robotics and Automation Letters， 2018， 3（4）： 3279-3284.
[54]	Akhavan J， Manoochehri S. Sensory data fusion using machine learning methods for in situ defect registration in additive manufacturing： A review［C］//Proceedings of 2022 IEEE International IOT， Electronics and Mechatronics Conference （IEMTRONICS）， Toronto， ON， Canada， June 1-4， IEEE， 2022： 1-10.
[55]	Bevans B， Barrett C， Spears T， et al. Heterogeneous sensor data fusion for multiscale， shape agnostic flaw detection in laser powder bed fusion additive manufacturing［J］. Virtual and Physical Prototyping， 2023， 18（1）： e2196266.
[56]	刘丽君，马义中，欧阳林寒. 高效的因子分类筛选方法及仿真应用［J］. 系统管理学报， 2021， 30（1）： 3-13.
	Liu L J， Ma Y Z， Ouyang L H. An efficient factor screening and classification procedure based on multi-response sequential bifurcation and applications［J］. Journal of Systems & Management， 2021， 30（1）： 3-13.
[57]	汪建均，屠雅楠，马义中. 结合SUR与因子效应原则的多响应质量设计［J］. 管理科学学报， 2020， 23（12）： 12-29.
	Wang J J， Tu Y N， Ma Y Z. Multi-response quality design integrating SUR models with factorial effect principles［J］. Journal of Management Sciences in China， 2020， 23（12）： 12-29.
[58]	Zhong S， Liu D， Lin L， et al. CAE-WANN： A novel anomaly detection method for gas turbines via search space extension［J］. Quality and Reliability Engineering International， 2022， 38（6）： 3116-3134.
[59]	An B， Wang S， Qin F， et al. Adversarial algorithm unrolling network for interpretable mechanical anomaly detection［J］. IEEE Transactions on Neural Networks and Learning Systems， 2024， 35（5）： 6007-6020.
[60]	Li W， Li C， Wang N， et al. Energy saving design optimization of CNC machine tool feed system： A data-model hybrid driven approach［J］. IEEE Transactions on Automation Science and Engineering， 2022， 19（4）： 3809-3820.
[61]	Li J Q， Du Y， Gao K Z， et al. A hybrid iterated greedy algorithm for a crane transportation flexible job shop problem［J］. IEEE Transactions on Automation Science and Engineering， 2022， 19（3）： 2153-2170.
[62]	刘虎沉，王鹤鸣，施华. 智能质量管理：理论模型、关键技术与研究展望［J］. 中国管理科学， 2024， 32（3）： 287-298.
	Liu H C， Wang H M， Shi H. Intelligent quality management： Theoretical framework， key technologies， and research prospect［J］. Chinese Journal of Management Science， 2024， 32（3）： 287-298.
[63]	Annear L M， Akhavan-Tabatabaei R， Schmid V. Dynamic assignment of a multi-skilled workforce in job shops： An approximate dynamic programming approach［J］. European Journal of Operational Research， 2023， 306（3）： 1109-1125.
[64]	Dolgui A， Kovalev S， Kovalyov M Y， et al. Optimal workforce assignment to operations of a paced assembly line［J］. European Journal of Operational Research， 2018， 264（1）： 200-211.
[65]	Giannini F， Lupinetti K， Monti M， et al. A customizable VR system supporting industrial equipment operator training［J］. Computer-Aided Design and Applications， 2022： 716-730.
[66]	Ciccarelli M， Papetti A， Cappelletti F， et al. Combining World Class Manufacturing system and Industry 4.0 technologies to design ergonomic manufacturing equipment［J］. International Journal on Interactive Design and Manufacturing （IJIDeM）， 2022， 16（1）： 263-279.
[67]	李岸达，何桢，何曙光. 基于NSGA-Ⅱ的非平衡制造数据关键质量特性识别［J］. 系统工程理论与实践， 2016， 36（6）： 1472-1479.
	Li A D， He Z， He S G. Critical to quality characteristics identification for imbalanced production data based on NSGA-Ⅱ［J］. Systems Engineering-Theory & Practice， 2016， 36（6）： 1472-1479.
[68]	Zhang Q， Qi J， Zhang X. Analysis of the application of RCM maintenance ideas in the operation and maintenance of air traffic control equipment in high altitude airports［J］. IET Conference Proceedings， 2023， 2023（9）： 482-489.
[69]	Ghosh R， Seri P， Montanari G C. Condition assessment of electrical equipment in harsh electrical environment［C］//Proceedings of 2019 IEEE 4th International Conference on Condition Assessment Techniques in Electrical Systems （CATCON）， Chennai， India， November 21-23， IEEE， 2019： 1-6.
[70]	Nie W， Cha X， Bao Q， et al. Study on dust pollution suppression of mine wind-assisted spray device based on orthogonal test and CFD simulation［J］. Energy， 2023， 263： 125590.
[71]	Evans P， Sandvig J， Churchill J， et al. Continuous measurement of methane emissions from turbines and compressors using predictive emissions monitoring （PEMS） technology-new insights from a global deployment programme［C］//Proceedings of SPE International Health， Safety， Environment and Sustainability Conference and Exhibition， DhabiAbu， UAE， September 10-12 ， Richardson： Society of Petroleum Engineers， 2024： SPE 220445-MS.
[72]	欧阳林寒，陶宝平，马妍. 基于选择性集成核高斯过程模型的质量预测研究［J］. 中国管理科学， 2023， 31（3）： 69-80.
	Ouyang L H， Tao B P， Ma Y. Research on quality prediction based on Gaussian process model with selective ensemble kernel［J］. Chinese Journal of Management Science， 2023， 31（3）： 69-80.
[73]	Qi F Q， Wang Y K， Huang H Z. Optimal maintenance policy considering imperfect switching for a multi-state warm standby system［J］. Quality and Reliability Engineering International， 2024， 40（5）： 2423-2443.
[74]	Schouten T N， Dekker R， Hekimoğlu M， et al. Maintenance optimization for a single wind turbine component under time-varying costs［J］. European Journal of Operational Research， 2022， 300（3）： 979-991.
[75]	翟翠红，汪建均，马义中，等. 基于高斯过程模型的时空响应稳健参数设计［J］. 系统工程理论与实践， 2023， 43（2）： 537-555.
	Zhai C H， Wang J J， Ma Y Z， et al. Spatio-temporal response robust parameter design based on Gaussian process model［J］. Systems Engineering —Theory & Practice， 2023， 43（2）： 537-555.
[76]	Zhang Z， Wang H， Chen H， et al. A novel IEPE AE-vibration-temperature-combined intelligent sensor for defect detection of power equipment［J］. IEEE Transactions on Instrumentation and Measurement， 2023， 72： 9506809.
[77]	Kohtz S， Zhao J， Renteria A， et al. Optimal sensor placement for permanent magnet synchronous motor condition monitoring using a digital twin-assisted fault diagnosis approach［J］. Reliability Engineering & System Safety， 2024， 242： 109714.
[78]	Dalle Pezze D， Masiero C， Tosato D， et al. FORMULA： A deep learning approach for rare alarms predictions in industrial equipment［J］. IEEE Transactions on Automation Science and Engineering， 2022， 19（3）： 1491-1502.
[79]	Liu S， Fan L. An adaptive prediction approach for rolling bearing remaining useful life based on multistage model with three-source variability［J］. Reliability Engineering & System Safety， 2022， 218： 108182.
[80]	王宁，田淑珂，刘玉敏，等. 基于PLS-Aenet的多工序制造过程关键质量特性识别［J］. 中国管理科学， 2024， 32（4）： 271-278.
	Wang N， Tian S K， Liu Y M， et al. Identification of key quality characteristics in multistage manufacturing process based on PLS-aenet［J］. Chinese Journal of Management Science， 2024， 32（4）： 271-278.
[81]	Li H， Hu G， Li J， et al. Intelligent fault diagnosis for large-scale rotating machines using binarized deep neural networks and random forests［J］. IEEE Transactions on Automation Science and Engineering， 2022， 19（2）： 1109-1119.
[82]	Wang H， Li Y F. Robust mechanical fault diagnosis with noisy label based on multistage true label distribution learning［J］. IEEE Transactions on Reliability， 2023， 72（3）： 975-988.
[83]	Xu J， Wang R， Liang Z， et al. Physics-guided， data-refined fault root cause tracing framework for complex electromechanical system［J］. Reliability Engineering & System Safety， 2023， 236： 109293.
[84]	Xia L， Zheng P， Herrera M， et al. Graph embedding-based Bayesian network for fault isolation in complex equipment［J］. IEEE Transactions on Reliability， 2025， 74（3）： 3897-3910.
[85]	Wu C H， Yang D Y， He T E. Matrix-augmentation approach for machine repair problem with generally distributed repair times during working breakdown periods［J］. Mathematics and Computers in Simulation， 2024， 225： 1019-1038.
[86]	Gan S， Song Z， Zhang L. A maintenance strategy based on system reliability considering imperfect corrective maintenance and shocks［J］. Computers & Industrial Engineering， 2022， 164： 107886.
[87]	Sony M， Antony J， Douglas J A， et al. Motivations， barriers and readiness factors for Quality 4.0 implementation： An exploratory study［J］. The TQM Journal， 2021， 33（6）： 1502-1515.