This study presents an intelligent, digital-twin-driven device that leverages computer vision, machine learning (ML), and genetic algorithms as a cyber-physical system (CPS) to achieve high-quality products—benchmarks that companies must strive for in the current competitive milieu. For precision and quality manufacturing, companies have the opportunity to exploit the advantages of such digitalization to prevent errors in line with zero-defect strategies. The proposed design is for a flow-production environment, where feature data is retrieved contactlessly through a system comprising both hardware and software. The hardware module captures product images and stores them on an edge computing device, while the software extracts image-feature data, identifies patterns, and determines correlations between the feature data and production-process parameters using ML. Overall, the designed system has the potential to revolutionize product quality assurance in the era of Industry 4.0 by providing an efficient, reliable, and cost-effective solution, that is, also customizable for product manufacturing. The proposed model is further validated in an automotive component CPS factory. The system operates on a two-stage intelligence principle: (1) a real-time pass/fail classification based on surface-quality thresholds and (2) a root-cause analysis and prevention loop that uses a hybrid AI pipeline (GLCM feature extraction, KSOM validation, and GA optimization) to derive and feedback optimal process parameters to the production line. The novelty of the CPS solution lies in its integrated, low-cost AI, which drastically reduces the cost burden of the inspection vision system, making it suitable for manufacturing on varied scales, and hence, bestowing potential and possibility for widespread adoption.
EleftheriadisRJMyklebustO. A quality pathway to digitalization in manufacturing thru Zero Defect Manufacturing practices. In: Proceedings of the 6th international workshop of advanced manufacturing and automation, Atlantis Press, 2016.
2.
KambleSSGunasekaranAGawankarSA.Achieving sustainable performance in a data-driven agriculture supply chain: a review for research and applications. Int J Prod Econ2020; 219: 179–194.
3.
MittalSKhanMARomeroD, et al. Smart manufacturing: characteristics, technologies and enabling factors. Proc Inst Mech Eng B J Eng Manuf2019; 233: 1342–1361.
4.
Villalba-DiezJSchmidtDGeversR, et al. Deep learning for industrial computer vision quality control in the printing Industry 4.0. Sensors2019; 19(18): 3987.
5.
KumarSGopiTHarikeerthanaN, et al. Machine learning techniques in additive manufacturing: a state of the art review on design, processes and production control. J Intell Manuf2023; 34: 21–55.
6.
ZhangYZhangGLiuY.Deep learning-based defect detection for industrial quality control: challenges and solutions. IEEE Trans Ind Inform2022; 18: 3421–3432.
ZhengPWangHSangZ, et al. Smart manufacturing systems for Industry 4.0: conceptual framework, scenarios, and future perspectives. Front Mech Eng2018; 13: 137–150.
10.
MagnaniniMCTolioTAM. A model-based digital twin to support responsive manufacturing systems. CIRP Ann2021; 70: 353–356.
LeberruyerNBruchJAhlskogM, et al. Toward Zero Defect Manufacturing with the support of artificial intelligence—insights from an industrial application. Comput Ind2023; 147: 103877.
13.
PowellDMagnaniniMCColledaniM, et al. Advancing Zero Defect Manufacturing: a state-of-the-art perspective and future research directions. Comput Ind2022; 136: 103596.
14.
MoktadirMADwivediAKhanNS, et al. Analysis of risk factors in sustainable supply chain management in an emerging economy of leather industry. J Clean Prod2021; 283: 124641.
15.
TaoFQiQWangL, et al. Digital twins and cyber–physical systems toward smart manufacturing and Industry 4.0: correlation and comparison. Engineering2019; 5: 653–661.
16.
MattDTModrákVZsifkovitsH (eds.) Industry 4.0 for SMEs. 2020th ed.Springer Nature, 2020.
17.
CaiazzoBDi NardoMMurinoT, et al. Towards Zero Defect Manufacturing paradigm: a review of the state-of-the-art methods and open challenges. Comput Ind2022; 134: 103548.
LiuYGuoLGaoH, et al. Machine vision based condition monitoring and fault diagnosis of machine tools using information from machined surface texture: a review. Mech Syst Signal Process2022; 164: 108068.
20.
PalaniSNatarajanU.Prediction of surface roughness in CNC end milling by machine vision system using artificial neural network based on 2D Fourier transform. Int J Adv Manuf Technol2011; 54: 1033–1042.
21.
ManishRVenkateshADenis AshokS.Machine vision based image processing techniques for surface finish and defect inspection in a grinding process. Mater Today2018; 5: 12792–12802.
22.
PatelDRKiranMB.A non-contact approach for surface roughness prediction in CNC turning using a linear regression model. Mater Today2020; 26: 350–355.
23.
ArunachalamNRamamoorthyB.Texture analysis for grinding wheel wear assessment using machine vision. Proc Inst Mech Eng B J Eng Manuf2007; 221: 419–430.
24.
KumarBMRatnamMM.Machine vision method for non-contact measurement of surface roughness of a rotating workpiece. Sens Rev2015; 35: 10–19.
25.
SchmittRFürtjesTAbbasB, et al. Real-time machine vision system for an automated quality monitoring in mass production of multiaxial non-crimp fabrics. IFAC-PapersOnLine2015; 48: 2393–2398.
26.
DuanJZhuangLZhangQ, et al. Vision-based robotic grasping using faster R-CNN–GRCNN dual-layer detection mechanism. Proc Inst Mech Eng B J Eng Manuf2024; 239(6–7): e249217.
27.
BaleaniAPaoneNGladinesJ, et al. Design and metrological analysis of a Backlit vision system for surface roughness measurements of turned parts. Sensors2023; 23(3): 1584.
28.
BalasundaramMKRatnamMM.In-process measurement of surface roughness using machine vision with sub-pixel edge detection in finish turning. Int J Precis Eng Manuf2014; 15: 2239–2249.
29.
MassaroAManfredoniaIGalianoA, et al. Inline image vision technique for tires Industry 4.0: quality and defect monitoring in tires assembly. In: 2019 II workshop on metrology for Industry 4.0 and IoT (MetroInd4.0&IoT), Naples, Italy, 4–6 June 2019. New York: IEEE.
30.
FrustaciFPerriSCocorulloG, et al. An embedded machine vision system for an in-line quality check of assembly processes. Procedia Manuf2020; 42: 211–218.
31.
AyonSTKSirajFMUddinJ. Steel surface defect detection using learnable memory vision transformer. Comput Mater Contin2025; 82: 499–520.
32.
EraIZZhouFRaihanAS, et al. In-situ melt pool characterization via thermal imaging for defect detection in Directed Energy Deposition using Vision Transformers. J Manuf Process2025; 145: 11–21.
33.
TaoFXiaoBQiQ, et al. Digital twin modeling. J Manuf Syst2022; 64: 372–389.
34.
BhandalRMeritonRKavanaghRE, et al. The application of digital twin technology in operations and supply chain management: a bibliometric review. Supply Chain Manag2022; 27: 182–206.
35.
RajPSurianarayananC.Digital twin: the industry use cases. Adv Comput2020; 285–320.
36.
PsarommatisFMayG. A literature review and design methodology for digital twins in the era of Zero Defect Manufacturing. Int J Prod Res2022; 61(5): 1–21.
37.
LvZGuoJLvH.Safety Poka Yoke in zero-defect manufacturing based on digital twins. IEEE Trans Ind Inform2023; 19: 1176–1184.
38.
WangQJiaoWZhangY.Deep learning-empowered digital twin for visualized weld joint growth monitoring and penetration control. J Manuf Syst2020; 57: 429–439.
39.
XuJJiZJingX, et al. Digital twin based intelligent coating film thickness monitoring system. Proc Inst Mech Eng B J Eng Manuf2025; 2025: 4428.
40.
MaYKasslerAAhmedBS, et al. Using deep reinforcement learning for zero defect smart forging. Adv Transdiscipl Eng2022; 21: 701–712.
41.
RuizJCSBruJMEscotoRP. Smart digital twin for ZDM-based job-shop scheduling. In: 2021 IEEE international workshop on metrology for Industry 4.0 & IoT (MetroInd4.0&IoT), Rome, Italy, 7–9 June 2021. New York: IEEE.
42.
LiXLiuHWangW, et al. Big data analysis of the Internet of Things in the digital twins of smart city based on deep learning. Future Gener Comput Syst2022; 128: 167–177.
43.
WagnerUAlGeddawyTElMaraghyH, et al. The state-of-the-art and prospects of learning factories. Procedia CIRP2012; 3: 109–114.
44.
AbeleEChryssolourisGSihnW, et al. Learning factories for future oriented research and education in manufacturing. CIRP Ann2017; 66: 803–826.
45.
TischMAbeleEMetternichJ.Overview on potentials and limitations of existing learning factory concept variations. In: AbeleEMetternichJTischM, et al. (eds) Learning factories. Springer International Publishing, 2024, pp.289–321.
ChenBWanJCelestiA, et al. Edge computing in IoT-based manufacturing. IEEE Commun Mag2018; 56: 103–109.
48.
ShiJYTaifiMKhreishahA, et al. Sustainable GPU computing at scale. In: 2011 14th IEEE international conference on computational science and engineering, Dalian, China, 24–26 August 2011. New York: IEEE.
49.
BhargavaAKumarA.Arduino controlled robotic arm. In: 2017 International conference of electronics, communication and aerospace technology (ICECA), Coimbatore, India, 20–22 April 2017. New York: IEEE.
50.
PurSFSagirogluS. A novel approach to fashion-based analysis and analytics using an intelligent in-store camera system. In: 2020 5th International conference on computer science and engineering (UBMK), Diyarbakir, Turkey, 9–11 September 2020. New York: IEEE.
51.
PfisterTLiXZhaoG, et al. Recognising spontaneous facial micro-expressions. In: 2011 international conference on computer vision, Barcelona, Spain, 6–13 November 2011. New York: IEEE.
52.
GhoshTWangYMartinsenK, et al. A surrogate-assisted optimization approach for multi-response end milling of aluminum alloy AA3105. Int J Adv Manuf Technol2020; 111: 2419–2439.
53.
ChakrabortySChakrabortyS.A scoping review on the applications of MCDM techniques for parametric optimization of machining processes. Arch Comput Methods Eng2022; 29: 4165–4186.
54.
NatarajMBalasubramanianK.Parametric optimization of CNC turning process for hybrid metal matrix composite. Int J Adv Manuf Technol2017; 93: 215–224.
55.
SahooAKJeetSBagalDK, et al. Parametric optimization of CNC-drilling of Inconel 718 with cryogenically treated drill-bit using Taguchi–Whale optimization algorithm. Mater Today2022; 50: 1591–1598.
56.
LiLLiCTangY, et al. An integrated approach of process planning and cutting parameter optimization for energy-aware CNC machining. J Clean Prod2017; 162: 458–473.
57.
LessmannSStahlbockRCroneSF. Genetic algorithms for support vector machine model selection. In: The 2006 IEEE international joint conference on neural network proceedings, Vancouver, BC, Canada, 30 October 2006. New York: IEEE.
58.
VermaAKDixitVS. An outlier accuracy improvement in shilling attacks using KSOM. In: Advances in intelligent systems and computing, pp.353–365. Singapore: Springer Singapore.
59.
YuDHuJSongX, et al. Supervised kernel self-organizing map. In: Intelligent science and intelligent data engineering, pp.246–253. Berlin/Heidelberg: Springer.
FisherRA.The genetical theory of natural selection. Oxford: At The Clarendon Press, 1930.
62.
MadhavaPReddyKD.Optimization of laser beam cutting process parameters using response surface methodology & genetic algorithm. Int J Mech Eng Technol2025; 16: 63–88.
63.
SenthilKumarVNagadeepanAHubert Tony RajL, et al. Optimization of aluminum alloy by CO2 laser cutting using genetic algorithm to achieve surface quality. IOP Conf Ser Mater Sci Eng2021; 1055: 012123.
64.
BasarGDerOGuvencMA.AI-powered hybrid metaheuristic optimization for predicting surface roughness and kerf width in CO2 laser cutting of 3D-printed PLA-CF composites. J Thermoplast Compos Mater2025; 38: 2688–2717.
65.
DerOBaşarG.TOPSIS-based multi-response optimization for improving CO2 laser cutting quality of 3D printed PLA. Int Adv Res Eng J2025; 9: 118–129.
66.
DerO.Multi-output prediction and optimization of CO2 laser cutting quality in FFF-printed ASA thermoplastics using machine learning approaches. Polymers2025; 17: 1910.
67.
HimmetoğluSDeliceYKızılkaya AydoğanE, et al. Green building envelope designs in different climate and seismic zones: multi-objective ANN-based genetic algorithm. Sustain Energy Technol Assess2022; 53: 102505.
68.
MahmoodSSunHAli AlhussanA, et al. Active learning-based machine learning approach for enhancing environmental sustainability in green building energy consumption. Sci Rep2024; 14: 19894.
69.
ChenLDebKLiuH-L, et al. Effect of objective normalization and penalty parameter on penalty boundary intersection decomposition-based evolutionary many-objective optimization algorithms. Evol Comput2021; 29: 157–186.
BhattacharjeeDGhoshTBholaP, et al. Data-driven surrogate assisted evolutionary optimization of hybrid powertrain for improved fuel economy and performance. Energy2019; 183: 235–248.
72.
ChengJXieZ.Genetic algorithm applications in RF broadband matching circuits design. In: SoutheastCon 2022, Mobile, AL, USA, 26 March–03 April 2022. New York: IEEE.
73.
DhafrNAhmadMBurgessB, et al. Improvement of quality performance in manufacturing organizations by minimization of production defects. Robot Comput Integr Manuf2006; 22: 536–542.
LiMWenQZhangY, et al. New insights into the transformation of effluent organic matter during Fe(II)-assisted advanced oxidation processes: parallel factor analysis coupled with self-organizing maps. Water Res2022; 221: 118789.
HimbergJAholaJAlhoniemiE, et al. The self-organizing map as a tool in knowledge engineering. In: MikiT (ed.) Pattern recognition in soft computing paradigm. World Scientific, 2001, pp.38–65.
