Restricted accessResearch articleFirst published online 2026
A novel predictive maintenance system for automotive industry using enhanced optimization and weighted fused feature-based cascaded deep learning network
The previous predictive maintenance (PdM) systems can summarize the required information for estimating the period of the failures in the machine, the powerful impacts of the issue, or the need to prevent production from executing the repair functionalities. But the logs for the maintenance are apt to have unbalanced distributions. In this work, a new PdM system is developed to detect equipment failures in the automotive industry using deep learning techniques. It is used to improve productivity. The data is collected from the internet. The collected data is given to the data cleaning phase to remove unwanted disruptions from the data. Then, deep feature data are extracted using restricted Boltzmann machine (RBM), autoencoder, and one-dimensional convolutional neural network (1DCNN). Then, the extracted features are given to the deep-weighted feature fusion phase. Here, the weight is optimized using the developed enhanced American zebra optimization (EAZO). Then, the deep-weighted fusion features are given to the prediction phase. The cascaded residual long short-term memory network (LSTM) with AM (CResLSTM-AM) is used to predict the equipment faults effectively. The developed PdM system in the automotive industry is contrasted with conventional models with performance measures to show accurate outcomes.
LinC-YHsiehY-MChengF-T, et al. Time series prediction algorithm for intelligent predictive maintenance. IEEE Robot Autom Lett2019; 4(3): 2807–2814.
2.
AbdennadherKVenetPRojatG, et al. A real-time predictive-maintenance system of aluminum electrolytic capacitors used in uninterrupted power supplies. IEEE Trans Ind Appl2010; 46(4): 1644–1652.
3.
GungorORosingTSAksanliB.DOWELL: diversity-induced optimally weighted ensemble learner for predictive maintenance of industrial Internet of Things devices. IEEE Internet Things J2021; 9(4): 3125–3134.
4.
NguyenKTPMedjaherK. A new dynamic predictive maintenance framework using deep learning for failure prognostics. Reliab Eng Syst Saf2019; 188: 251–262.
5.
YanJMengYLuL, et al. Industrial Big Data in an Industry 4.0 environment: challenges, schemes, and applications for predictive maintenance. IEEE Access2017; 5: 23484–23491.
6.
TeohYKGillSSParlikadAK.IoT and fog-computing-based predictive maintenance model for effective asset management in Industry 4.0 using machine learning. IEEE Internet Things J2021; 10(3): 2087–2094.
7.
PezzeDDMasieroCTosatoD, et al. FORMULA: a deep learning approach for rare alarms predictions in industrial equipment. IEEE Trans Autom Sci Eng2021; 19(3): 1491–1502.
8.
LeeHKimCOKoHH, et al. Yield prediction through the event sequence analysis of the die attach process. IEEE Trans Semicond Manuf2015; 28(4): 563–570.
9.
LiL-JChangXChaoF, et al. Self-organizing type-2 fuzzy double loop recurrent neural network for uncertain nonlinear system control. IEEE Trans Neural Netw Learn Syst2024; 36(4): 6451–6465.
10.
ChenBLiuYZhangC, et al. Time series data for equipment reliability analysis with deep learning. IEEE Access2020; 8: 105484–105493.
11.
EinabadiBMohammad-AminiMBaboliA, et al. Dashboard proposition for health monitoring of production system in the automotive industry. IFAC-PapersOnLine2021; 54(1): 780–786.
12.
BampoulaXSiaterlisGNikolakisN, et al. A deep learning model for predictive maintenance in cyber-physical production systems using LSTM autoencoders. Sensors2021; 21(3): 972.
13.
OlabiAGWilberforceTAli AbdelkareemM.Fuel cell application in the automotive industry and future perspective. Energy2021; 214: 118955.
14.
KumarRSrivastavaSGuptaJRP. Modeling and adaptive control of nonlinear dynamical systems using radial basis function network. Soft Comput2017; 21: 4447–4463.
15.
KumarR.Memory recurrent Elman neural network-based identification of time-delayed nonlinear dynamical system. IEEE Trans Syst Man Cybern Syst2022; 53(2): 753–762.
16.
FangYPercMZhangH.A game theoretical model for the stimulation of public cooperation in environmental collaborative governance. R Soc Open Sci2022; 9(11): 221148.
17.
StavropoulosPPapacharalampopoulosAAthanasopoulouL, et al. Designing a digitalized cell for remanufacturing of automotive frames. Procedia CIRP2022; 109: 513–519.
18.
MuntenPVanhammeJMaonF, et al. Addressing tensions in coopetition for sustainable innovation: insights from the automotive industry. J Bus Res2021; 136: 10–20.
19.
HakamNBenfrihaK.Enhancement of industrial information systems through AI models to simulate the vibrational and acoustic behavior of machining operations. J Ind Inf Integr2025; 43: 100744.
20.
LiHLiSMinG.Lightweight privacy-preserving predictive maintenance in 6G enabled IIoT. J Ind Inf Integr2024; 39: 100548.
21.
UysalMP.Machine learning-enabled healthcare information systems in view of industrial information integration engineering. J Ind Inf Integr2022; 30: 100382.
22.
RajeshPKManikandanNRamshankarCS, et al. Digital twin of an automotive brake pad for predictive maintenance. Procedia Comput Sci2019; 165: 18–24.
23.
DelicMEyersDR.The effect of additive manufacturing adoption on supply chain flexibility and performance: an empirical analysis from the automotive industry. Int J Prod Econ2020; 228: 107689.
24.
GopaliSSiami-NaminiSAbriF, et al. A comparative multivariate analysis of VAR and deep learning-based models for forecasting volatile time series data. IEEE Access2024; 12: 155423–155436.
25.
MohapatraANayakNKhannaA, et al. Enhancing fault detection and predictive maintenance of rotating machinery with Fiber Bragg Grating sensor and machine learning techniques. Int J Inf Technol2025; 17(2): 1225–1234.
26.
CavusMDissanayakeDBellM.Next generation of electric vehicles: AI-driven approaches for predictive maintenance and battery management. Energies2025; 18(5): 1041.
27.
KumarRSrivastavaSGuptaJRP, et al. Self-recurrent wavelet neural network-based identification and adaptive predictive control of nonlinear dynamical systems. Int J Adapt Control Signal Process2018; 32(9): 1326–1358.
28.
KumarRSrivastavaS.Externally recurrent neural network based identification of dynamic systems using Lyapunov stability analysis. ISA Trans2020; 8: 292–308.
29.
SinghMKKumarSNandanD.Faulty voice diagnosis of automotive gearbox based on acoustic feature extraction and classification technique. J Eng Res2023; 11(2): 100051.
30.
GuptaTKumarR.A novel feed-through Elman neural network for predicting the compressive and flexural strengths of eco-friendly jarosite mixed concrete: design, simulation and a comparative study. Soft Comput2024; 28(1): 399–414.
31.
ChenC.Deep learning for automobile predictive maintenance under Industry 4.0. Cardiff University Electronic Publication, 2020.
32.
ChenCLiuYSunX, et al. An integrated deep learning-based approach for automobile maintenance prediction with GIS data. Reliab Eng Syst Saf2021; 216: 107919.
33.
TheisslerAPérez-VelázquezJKettelgerdesM, et al. Predictive maintenance enabled by machine learning: use cases and challenges in the automotive industry. Reliab Eng Syst Saf2021; 215: 107864.
34.
Ben BrahimIAddoucheSAEl MhamediA, et al. Build a Bayesian network from FMECA in the production of automotive parts: diagnosis and prediction. IFAC-PapersOnLine2019; 52(13): 2572–2577.
35.
ChintaVSKethi ReddiSYarramsettyN.Optimal feature selection on Serial Cascaded deep learning for predictive maintenance system in automotive industry with fused optimization algorithm. Adv Eng Inform2023; 57: 102105.
36.
JustusVKanagachidambaresanGR.Machine learning based fault-oriented predictive maintenance in Industry 4.0. Int J Syst Assur Eng Manag2024; 15(1): 462–474.
37.
IndumathiVAshok KumarC. An Innovative deep learning-based predictive maintenance model for smart automotive system. In: 2025 International conference on multi-agent systems for collaborative intelligence (ICMSCI), Erode, India, 20–22 January 2025, pp. 1426–1433. New York: IEEE.
38.
ZebSLodhiSK.AI for predictive maintenance: reducing downtime and enhancing efficiency. Enrichment J Multidiscip Res Dev2025; 3(1): 135–150.
39.
WojtulewiczAChaberP.Industrial robot control system with a predictive maintenance module using IIoT technology. Sensors2025; 25(4): 1154.
40.
Al-SaidSFindikOAssanovaB, et al. Enhancing predictive maintenance in manufacturing: a CNN–LSTM hybrid approach for reliable component failure prediction. In: Technology-driven business innovation: unleashing the digital advantage, 2024, vol. 1, pp. 137–153. Cham: Springer Nature.
41.
LaxmiMMVidya Sri VarshiniKSandhyaB, et al. Hybrid ensemble learning for real-time predictive maintenance in vehicular engine health monitoring systems. Front Collab Res2025; 3(2): 1–11.
42.
BharatheedasanKMaityTKumaraswamidhasLA, et al. Enhanced fault diagnosis and remaining useful life prediction of rolling bearings using a hybrid multilayer perceptron and LSTM network model. Alex Eng J2025; 115: 355–369.
43.
VikramKNezafatiKStaytonE, et al. Explainable AI framework for imaging-based predictive maintenance for automotive applications and beyond. Data-Enabl Discov Appl2020; 4: 7.
44.
DashSKRajSAgarwalR, et al. Automobile predictive maintenance using deep learning. Int J Artif Intell Mach Learn2021; 11: 1–12.
45.
BaşarGDerOGuvencMA. 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: 08927057251344183.
46.
SinghSPKumarNDhimanG, et al. AI-powered metaheuristic algorithms: enhancing detection and defense for consumer technology. IEEE Consum Electron Mag2024; 14(3): 44–52.
47.
RamereMDLaseindeOT.Optimization of condition-based maintenance strategy prediction for aging automotive industrial equipment using FMEA. Procedia Comput Sci2021; 180: 229–238.
48.
PinardiDArpaLToscaniA, et al. A novel hybrid acquisition system for industrial condition monitoring and predictive maintenance. IEEE Access2024; 12: 98121–98129.
49.
UcarAKarakoseMKırımçaN.Artificial intelligence for predictive maintenance applications: key components, trustworthiness, and future trends. Appl Sci2024; 14(2): 898.
50.
AbidiMHMohammedMKAlkhalefahH.Predictive maintenance planning for Industry 4.0 using machine learning for sustainable manufacturing. Sustainability2022; 14(6): 3387.
51.
FischerLASFoggiattoJAMarcondesPVP, et al. Design for additive manufacturing (DFAM) applied in the manufacture of Master Sample for the automotive industry. Proc Inst Mech Eng B J Eng Manuf2025; 239(1–2): 6–103.
52.
HarishDRGowthamTArunachalamA, et al. Productivity improvement by application of simulation and lean approaches in an multimodel assembly line. Proc Inst Mech Eng B J Eng Manuf2024; 238(6–7): 1084–1094.
53.
BeshaARMAOjekemiOSOzT, et al. PLSCO: an optimization-driven approach for enhancing predictive maintenance accuracy in intelligent manufacturing. Processes2025; 13(9): 2707.
54.
ArularasanANGaneshkumarPAlkhatibM, et al. Harmonized integration of GWO and J-SLnO for optimized asset management and predictive maintenance in Industry 4.0. Sensors2025; 25(9): 2896.
55.
WangXGuoSShenJ, et al. Optimization of preventive maintenance for series manufacturing system by differential evolution algorithm. J Intell Manuf2020; 31(3): 745–757.
56.
MohapatraSMohapatraP.American zebra optimization algorithm for global optimization problems. Sci Rep2023; 13: 5211.
57.
KudelaJ.A critical problem in benchmarking and analysis of evolutionary computation methods. Nat Mach Intell2022; 4(12): 1238–1245.
58.
NorouziMRanjbarMMoriG. Stacks of convolutional restricted Boltzmann machines for shift-invariant feature learning. In: 2009 IEEE conference on computer vision and pattern recognition, Miami, FL, USA, 20–25 June 2009, pp. 2735–2742. New York: IEEE.
59.
MengQCatchpooleDSkillicomD, et al. Relational autoencoder for feature extraction, May2017, pp. 364–371. IEEE.
60.
AbdoliSCardinalPKoerichAL.End-to-end environmental sound classification using a 1D convolutional neural network. Expert Syst Appl2019; 136: 252–263.
61.
El WardiJBellaNLagratI, et al. The quality acceptance specifications of automotive electrical connector using combination of principal component analysis and regression statistical analysis. J Eng Res2026; 14(1): 1130–1139.
62.
KimJEl-KhamyMLeeJ.Residual LSTM: design of a deep recurrent architecture for distant speech recognition. arXiv preprint, 2017.
63.
WangHXuJYanR, et al. Intelligent bearing fault diagnosis using multi-head attention-based CNN. Procedia Manuf2020; 49: 112–118.
64.
SalimAJummarWKJasimFM, et al. Eurasian oystercatcher optimiser: new meta-heuristic algorithm. J Intell Syst2022; 31(1): 332–344.
AbualigahLAbd ElazizMSumariP, et al. Reptile search algorithm (RSA): a nature-inspired meta-heuristic optimizer. Expert Syst Appl2022; 191: 116158.
67.
ShafiIMazahirAFatimaA, et al. Internal defects detection and classification in hollow cylindrical surfaces using single shot detection and MobileNet. Measurement2022; 202: 111836.
68.
SharmaDKBrahmachariSSinghalK, et al. Data driven predictive maintenance applications for industrial systems with temporal convolutional networks. Comput Ind Eng2022; 169: 108213.
69.
DemidovaLA.Recurrent neural networks’ configurations in the predictive maintenance problems. IOP Conf Ser Mater Sci Eng2020; 714: 012005.
70.
DhinakaranDEdwin RajaSVelselviR, et al. Intelligent IoT-driven advanced predictive maintenance system for industrial applications. SN Comput Sci2025; 6(2): 151.
71.
ElkatebSMétwalliAShendyA, et al. Machine learning and IoT-based predictive maintenance approach for industrial applications. Alex Eng J2024; 88: 298–309.
72.
LiuCTangDZhuH, et al. A novel predictive maintenance method based on deep adversarial learning in the intelligent manufacturing system. IEEE Access2021; 9: 49557–49575.
73.
NasserAAl-KhazrajiH.A hybrid of convolutional neural network and long short-term memory network approach to predictive maintenance. Int J Electr Comput Eng2022; 12(1): 721–730.
