This study presents a unified End-of-Line (EOL) Noise–Vibration–Harshness (NVH) diagnostic framework that integrates three complementary analytical modules—Cross-Power Order Health Index (CPO-HI), Domain-Adaptive Quantile Thresholding (DAQT), and Multi-Reference Synchronous Coherence (MRSC). Unlike amplitude-only or manually tuned spectral methods, the approach consolidates order-domain cross-spectral information, data-driven acceptance bands, and coherence-weighted filtering to deliver objective and cycle-time-neutral screening. The framework is evaluated on two heterogeneous automotive subsystems—alternators and steering racks—using near-field acoustics with electrical and speed references. Explicit mathematical definitions, signal-processing parameters, and statistical analyses are provided to substantiate reproducibility. Defective alternators exhibited CPO-HI values above 1.5 relative to 0.75–0.9 for healthy units, while defective steering racks displayed inner-race order-band energies near 5.5 compared with 1.8 for nominal samples. Quantitative validation demonstrates >53% noise suppression relative to amplitude-based baselines and ROC-AUC values above 0.92 for defect classification. Cross-asset generalization was confirmed through Kolmogorov–Smirnov significance tests. The results establish a transferable and computationally lightweight NVH screening system capable of supporting intelligent, data-driven EOL operations.
KlippelW. End-of-line testing. In: GrzechcaW (ed.) Assembly line: theory and practice. IntechOpen, 2011, pp. 181–206.
2.
PsarommatisFMayGDreyfusPA, et al. Zero defect manufacturing: state-of-the-art review, shortcomings and future directions in research. Int J Prod Res2020; 58(1): 1–17.
3.
PsarommatisFSousaJMendonçaJP, et al. Zero-defect manufacturing: the approach for higher manufacturing sustainability in the era of Industry 4.0. Int J Prod Res2022; 60(1): 73–91.
4.
AzamfireiVPsarommatisFLagrosenY. Application of automation for in-line quality inspection, a zero-defect manufacturing approach. J Manuf Syst2023; 67: 1–22.
5.
EgerFCoupekDCaputoD, et al. Zero defect manufacturing strategies for reduction of scrap and inspection effort in multi-stage production systems. Procedia CIRP2018; 67: 368–373.
6.
WulleFCoupekDSchäffnerF, et al. Workpiece and machine design in additive manufacturing for multi-axis fused deposition modeling. Procedia CIRP2017; 60: 229–234.
7.
Rio-TortoICampanicoATPinhoP, et al. Hybrid quality inspection for the automotive industry: replacing the paper-based conformity list through semi-supervised object detection and simulated data. Appl Sci2022; 12(11): 5687.
8.
ScorpioMCiampiGRosatoA, et al. Electric-driven windows for historical buildings retrofit: energy and visual sensitivity analysis for different control logics. J Build Eng2020; 31: 101398.
9.
IrrgangSKlippelW. Self-testing of car audio systems. In: 2019 AES international conference on automotive audio. Audio Engineering Society, 2019, pp. 1–7.
10.
WangYChaoWLGargD, et al. Pseudo-LiDAR from visual depth estimation: bridging the gap in 3D object detection for autonomous driving. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), Long Beach, CA, USA, 15–20 June 2019, pp. 8445–8453. New York: IEEE.
11.
DiamondDHHeynsPSOberholsterAJ. Online shaft encoder geometry compensation for arbitrary shaft speed profiles using Bayesian regression. Mech Syst Signal Process2016; 81: 402–418.
12.
LaterraM. Noise and vibration sources in electric motor industrial applications. PhD Thesis, Politecnico di Torino, Italy, 2019.
13.
WangXJiangSHuW, et al. Quantitatively determining surface-adsorbate properties from vibrational spectroscopy with interpretable machine learning. J Am Chem Soc2022; 144(35): 16069–16076.
14.
QinZWuYTEizadA, et al. A study on simulation-based validation of optimized design of high precision rotating unit for processing machinery. Int J Precis Eng Manuf2019; 20(9): 1601–1609.
15.
QinZZhangQWuYT, et al. Experimentally validated geometry modification simulation for improving noise performance of CVT gearbox for vehicles. Int J Precis Eng Manuf2019; 20(11): 1969–1977.
16.
MuhrDTripathiSJodlbauerH. Divide and conquer anomaly detection: a case study predicting defective engines. Procedia Manuf2020; 42: 57–61.
17.
SuLMaLQinN, et al. Fault diagnosis of high-speed train bogie by residual-squeeze net. IEEE Trans Industr Inform2019; 15(7): 3856–3863.
18.
QinNYouYHuangD, et al. AttGAN-DPCNN: an extremely imbalanced fault diagnosis method for complex signals from multiple sensors. IEEE Sens J2024; 24: 38270–38285.
19.
SharmaVPareyA. Use of cyclostationarity-based condition indicators for gear fault diagnosis under fluctuating speed condition. In: ChaariFLeskowJNapolitanoA, et al. (eds) Cyclostationarity: theory and methods III. Springer, 2017, pp. 241–257.
20.
SharmaVPareyA. Frequency domain averaging based experimental evaluation of gear fault without tachometer for fluctuating speed conditions. Mech Syst Signal Process2017; 85: 278–295.
21.
SharmaVPareyA. Gearbox fault diagnosis using RMS probability density function and entropy measures for fluctuating speed conditions. Struct Health Monit2017; 16(6): 682–695.
22.
AndhaleYPareyA. Enhanced CEEMDAN-based deep hybrid model for automated gear crack detection. J Vib Eng Technol2024; 12(Suppl 2): 2229–2251.
23.
AndhaleYPareyA. Modified LinkNet and DenseNet-based hybrid architecture for combined fault detection in an electromechanical system. J Vib Eng Technol2025; 13(1): 7.
24.
TadžijevasABarzdaitisVMažeikaP, et al. Influence of imbalance force angular position on vertical and horizontal rotors rolling bearings defects diagnostics. J Vibroeng2014; 16(3): 1475–1482.
25.
TadžijevasABarzdaitisVDidžiokasR, et al. Diagnostics specificity of variable vertical axis rotor with damaged bearings. In: IFToMM world congress 2015 proceedings, Taipei, Taiwan, 25–30 October 2015.
26.
KartašovasVBarzdaitisVMažeikaP. Modeling and simulation of variable inertia rotor. J Vibroeng2012; 14(4): 1745–1750.
27.
AnsariAIChauhanSJKhaireP. Effect of crack on natural frequency in rotor system. AIP Conf Proc2017; 1859(1): 020101.
28.
PasiDKChoukseyMTiwariA. A finite element model-based approach for rotor unbalance detection and balancing. J Inst Eng India Ser C2023; 104(3): 479–494.
29.
UdmaleSSNathAGSinghD, et al. An optimized extreme learning machine-based novel model for bearing fault classification. Expert Syst2024; 41(2): e13432.
30.
PatilSJalanAK. Ensemble subspace discriminant classifiers for misalignment fault classification using vibro-acoustic sensor data fusion. J Vib Eng Technol2022; 10(8): 3169–3178.
31.
PatilSJalanAKMaratheAM. Support vector machine for misalignment fault classification under different loading conditions using vibro-acoustic sensor data fusion. Exp Tech2022; 46(6): 957–971.
32.
KumariS. Vibration measurement using accelerometer sensor and fast Fourier transform. In: ChakrabortyMJhaRKBalasVE, et al. (eds) Trends in wireless communication and information security: proceedings of EWCIS 2020. Springer, 2021, pp. 273–280.
33.
ThirumalaKUmarikarACJainT. An improved adaptive filtering approach for power quality analysis of time-varying waveforms. Measurement2019; 131: 677–685.
34.
Du ToitRGDiamondDHHeynsPS. A stochastic hybrid blade tip timing approach for the identification and classification of turbomachine blade damage. Mech Syst Signal Process2019; 121: 389–411.
35.
RaghavMSTiwariRSharmaRB. Fault detection in bevel gear using condition indicators. In: RakeshPKSharmaAKSinghI (eds) Advances in engineering design: ICOIED 2020. Springer, 2021, pp. 403–416.
36.
SinhaPJalanAKKumarA, et al. Diagnosis and prognosis of oil whirl in journal bearing using acoustical measurement. J Tribol2026; 148(1): 014104.
37.
GawandeSHPagarND. A combined numerical and experimental investigation on the effect of dynamics characteristics of metal expansion bellows. J Vib Eng Technol2018; 6(5): 401–416.
38.
BarshikarRRGhongadeHPBhadreAA, et al. Defect categorization of ribbon blender worm gearbox worm wheel and bearing based on artificial neural network. Eksploat Niezawodn2024; 26(2): 185371.
39.
KurtulusOYavuzC. Examining the modular end of line control unit design criteria for vehicle sliding door system track profile. Int J Mech Aerosp Ind Mechatron Manuf Eng2015; 9(10): 1753–1759.
40.
XueZWangBMaH, et al. Research on transformer fault diagnosis and maintenance strategy generation based on TransQwen model. Processes2025; 13(7): 1977.
41.
DubeyPDubeyPBokoroPN. Transformer-driven fault detection in self-healing networks: a novel attention-based framework for adaptive network recovery. Mach Learn Knowl Extr2025; 7(3): 67.
