In industrial big data, noise significantly impacts product quality prediction and analysis. Traditional denoising methods often suffer from key information loss and residual complex noise. To address these challenges, this paper proposes a multi-layer denoising method that retains key information and eliminates residual noise, improving data quality and prediction accuracy. First, time-frequency analysis identifies noise types in the raw data. Next, multiple denoising methods are applied to target specific information (trends and key characteristics), and the results are weighted based on multi-dimensional performance evaluation (MDPE), with T-Pearson used to assess trend extraction. The weighted results are fused to obtain preliminary denoised data. This data is then processed by a GWO-DAE model, enhanced by a loss function constrained by key information retention and complex noise elimination. The final denoised data, obtained through reconstruction, offers higher quality and reliability. Experimental results from a tobacco moisture regain machine show a reconstruction error of 0.21, a processing time of 22.83 s, and improved prediction accuracy, with an average absolute error of 0.29 in product quality predictions.
ZhaoZLyuJChuY, et al. Toward generalizable robot vision guidance in real-world operational manufacturing factories: a semi-supervised knowledge distillation approach. Robot Comput Manuf2024; 86: 102639.
2.
JiaSMaBGuoW, et al. A sample entropy based prognostics method for lithium-ion batteries using relevance vector machine. J Manuf Syst2021; 61: 773–781.
3.
ChenBQiJZhangD. An adaptive parameters adjustment and planning method for robotic belt grinding using modified quality model. Proc Inst Mech Eng B J Eng Manuf2021; 235(4): 605–615.
4.
LiuDWangYLiuC, et al. Data mode related interpretable transformer network for predictive modeling and key sample analysis in industrial processes. IEEE Trans Ind Inform2023; 19(9): 9325–9336.
5.
GuoHWangLLiuX, et al. Trend-based granular representation of time series and its application in clustering. IEEE Trans Cybern2022; 52(9): 9101–9110.
6.
GuptaPChodingalaPKPatilHA. Replay spoof detection using energy separation based instantaneous frequency estimation from quadrature and in-phase components. Comput Speech Lang2023; 77: 101423.
7.
MaYChengJ. A novel joint denoising method for gear fault diagnosis with improved quaternion singular value decomposition. Measurement2024; 226: 114165.
8.
YuHGaoHHeY, et al. A novel motor fault diagnosis method based on principal component analysis (PCA) with a discrete belief rule base (DBRB) system. Meas Sci Technol2023; 34(3): 035012.
9.
McCallanNDavidsonSNgKY, et al. Seizure classification of EEG based on wavelet signal denoising using a novel channel selection algorithm. In: 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2021, pp. 1269–1276.
10.
LiQLiuSLinC. A moving average denoise operator and grey discrete production process quality prediction model. Grey Syst Theory Appl2023; 13(1): 34–57.
11.
ShanZYangJSanjuánMAF, et al. A novel adaptive moving average method for signal denoising in strong noise background. Eur Phys J Plus2022; 137(1): 50.
12.
EscalonaOCullenNWeliI, et al. Robust arm impedocardiography signal quality enhancement using recursive signal averaging and multi-stage wavelet denoising methods for long-term cardiac contractility monitoring armbands. Sensors2023; 23(13): 5892.
13.
ChenJKongYZhangD, et al. Two-dimensional phase unwrapping based on U(2)-Net in complex noise environment. Opt Express2023; 31(18): 29792–29812.
14.
ZhangYLiCTangY, et al. A novel fault early warning method for centrifugal blowers based on stacked denoising autoencoder and transfer learning. J Manuf Syst2024; 76: 443–456.
15.
LiYWangHDongX. The denoising of desert seismic data based on cycle-GAN with unpaired data training. IEEE Geosci Remote Sens Lett2021; 18(11): 2016–2020.
16.
FrusqueGFinkO. Robust time series denoising with learnable wavelet packet transform. Adv Eng Inform2024; 62: 102669.
17.
GuoXZhuSWuJ. A hybrid seasonal autoregressive integrated moving average and denoising autoencoder model for atmospheric temperature profile prediction. Big Data2022; 10(6): 493–505.
18.
ZhaRZhangLLiS, et al. Scaling up multivariate time series pre-training with decoupled spatial-temporal representations. In: 2024 IEEE 40th International Conference on Data Engineering (ICDE). IEEE, 2024, pp. 667–678.
19.
KongXTangQLuoK, et al. Vehicle Response-based bridge modal identification using different time–frequency analysis methods. Int J Struct Stab Dyn2025; 25(06): 2550062.
20.
Ben AsherTRavehDE. Aeroelastic system identification for flutter prediction via multi-output autoregressive modeling. J Aircr2024; 61(2): 470–484.
21.
AnYZhangKChaiY, et al. Gaussian mixture variational-based transformer domain adaptation fault diagnosis method and its application in bearing fault diagnosis. IEEE Trans Ind Inform2024; 20(1): 615–625.
22.
LiHQiuLWangZ, et al. An assembly precision prediction method for customized mechanical products based on GAN-FTL. Proc Inst Mech Eng B J Eng Manuf2022; 236(3): 160–173.
23.
WeiXLiuXYueC, et al. Tool wear state recognition based on feature selection method with whitening variational mode decomposition. Robot Comput Manuf2022; 77: 102344.
24.
HuangYZhangYZhaoY, et al. A novel robust Gaussian–student’s t mixture distribution based Kalman filter. IEEE Trans Signal Process2019; 67(13): 3606–3620.
25.
CaoXWangWJiaX, et al. Residual stress distribution model of high strength steel welded channel section. In: Structures. Elsevier, 2024. Vol. 60, p.105944.
26.
FangWShaoYLovePED, et al. Detecting anomalies and de-noising monitoring data from sensors: a smart data approach. Adv Eng Inform2023; 55: 101870.
27.
GuanYZhangJShiZ, et al. Formalization of continuous Fourier transform in verifying applications for dependable cyber-physical systems. J Syst Archit2020; 106: 101707.
28.
ChauhanSSinghMAggarwalAK. Designing of optimal digital IIR filter in the multi-objective framework using an evolutionary algorithm. Eng Appl Artif Intell2023; 119: 105803.
29.
GuTHuCTangD, et al. An α-moving total least squares fitting method for measurement data. Proc Inst Mech Eng B J Eng Manuf2021; 235(1–2): 65–72.
30.
GaoYLinTZhangY, et al. Robust principal component analysis based on discriminant information. IEEE Trans Knowl Data Eng2022; 35(2): 1991–2003.
31.
LiWZhangHWangG, et al. Deep learning based online metallic surface defect detection method for wire and arc additive manufacturing. Robot Comput Manuf2023; 80: 102470.
32.
GaoLGanYShiJ. A novel intelligent denoising method of ECG signals based on wavelet adaptive threshold and mathematical morphology. Appl Intell2022; 52(9): 10270–10284.
33.
ZhaoZWangSWongD, et al. Robust enhanced trend filtering with unknown noise. Signal Process2021; 180: 107889.
34.
ZhangMLiWZhangL, et al. A Pearson correlation-based adaptive variable grouping method for large-scale multi-objective optimization. Inf Sci2023; 639: 118737.
BenestyJChenJHuangY, et al. Pearson correlation coefficient. In: Noise reduction in speech processing. Heidelberg: Springer Berlin Heidelberg, 2009, pp.1–4.
37.
BenestyJChenJHuangY. On the importance of the Pearson correlation coefficient in noise reduction. IEEE Trans Audio Speech Lang Process2008; 16(4): 757–765.
38.
PengYZhangSZhouZ, et al. Full mean-square analysis of affine combination of two complex-valued LMS filters for second-order non-circular inputs. IEEE Signal Process Lett2022; 29: 1157–1161.
39.
SahuPKRaiRN. LSTM-based deep learning approach for remaining useful life prediction of rolling bearing using proposed C-MMPE feature. J Mech Sci Technol2024; 38: 2197–2209.
40.
ZhangYDingXLiG, et al. Offline real-world wireless interference signal classification algorithm utilizing denoising diffusion probability model. IEEE Signal Process Lett2023; 30: 1132–1136.
41.
LiWZhangXWangS, et al. Distributed deep learning enabled prediction on cutting tool wear and remaining useful life. Proc Inst Mech Eng B J Eng Manuf2023; 237(14): 2203–2213.
42.
YaoXZhuJJiangQ, et al. RUL prediction method for rolling bearing using convolutional denoising autoencoder and bidirectional LSTM. Meas Sci Technol2024; 35(3): 035111.
43.
ZouZGaoXLeiS, et al. Development of tool wear condition on-line monitoring method for impeller milling based on new data processing approach and DAE-BP-ANN-integrated modeling. Proc Inst Mech Eng B J Eng Manuf2024; 238(1-2): 124–136.
44.
ColinKJuYBomboisX, et al. A bias-variance perspective of data-driven control. IFAC-PapersOnLine2024; 58(15): 85–90.
45.
LuLRenWXWangSD. Fractional Fourier transform: time-frequency representation and structural instantaneous frequency identification. Mech Syst Signal Process2022; 178: 109305.
46.
WangJChenPZhengN, et al. Associations between MSE and SSIM as cost functions in linear decomposition with application to bit allocation for sparse coding. Neurocomputing2021; 422: 139–149.
47.
WangEXiaJLiJ, et al. Parameters exploration of SOFC for dynamic simulation using adaptive chaotic grey wolf optimization algorithm. Energy2022; 261: 125146.
48.
SuTLiuYZhaoJ, et al. Probabilistic stacked denoising autoencoder for power system transient stability prediction with wind farms. IEEE Trans Power Syst2021; 36(4): 3786–3789.
49.
KaurGLiuFPhoebe ChenYP. The integration of knowledge graph convolution network with denoising autoencoder. Eng Appl Artif Intell2024; 135: 108792.
50.
RajputSS. S-GWO-FH: sparsity-based grey wolf optimization algorithm for face hallucination. Soft Comput2022; 26(18): 9323–9338.
51.
LiYJLiSBLiW. Abnormal diagnosis method of self-powered power supply system based on improved GWO-SVM. J Contr Sci Eng2023; 2023(1): 1–12.
52.
LiTQianZHeT. Short-term load forecasting with improved CEEMDAN and GWO-Based multiple kernel ELMComplexity2020; 2020(1): 1–20.
53.
DalmazHErdalEMurat ÜnverH. A new hybrid approach using GWO and MFO algorithms to detect network attack. Comput Model Eng Sci2023; 136(2): 1277–1314.
54.
ZhouYWangSXieY, et al. Remaining useful life prediction and state of health diagnosis of lithium-ion batteries with multiscale health features based on optimized CatBoost algorithm. Energy2024; 300: 131575.
55.
LiuJXuLXieY, et al. Toward robust fault identification of complex industrial processes using stacked sparse-denoising autoencoder with SoftMax classifier. IEEE Trans Cybern2023; 53(1): 428–442.
56.
EswaranMBahubalendruniMV. Challenges and opportunities on AR/VR technologies for manufacturing systems in the context of industry 4.0: a state of the art review. J Manuf Syst2022; 65: 260–278.
57.
EswaranMGulivindalaAKInkuluAK, et al. Augmented reality-based guidance in product assembly and maintenance/repair perspective: a state of the art review on challenges and opportunities. Expert Syst Appl2023; 213: 118983.
