To address the problem that fluctuation caused by multi-dimensional quality-related process variables is difficult to evaluate, this paper proposes a quality spectra-based support vector data description (SVDD) method for multi-dimensional quality fluctuation evaluation in complex industrial process. Firstly, based on quality spectra modelling, a multi-dimensional state feature vector of quality fluctuation is constructed from the perspective of quality spectra and statistical distribution, which is used to characterize the difference between normal and abnormal fluctuation. Then the quality fluctuation evaluation model is established based on SVDD algorithm. On this basis, the spherical distance between the sample to be evaluated and the quality evaluation model is calculated to measure the quality fluctuation degree. Finally, a case for TE process data sets is used to verify the quality fluctuation evaluation approach, it reveals that the proposed method could evaluate the degree of quality fluctuation, which could provide some theoretical guides for quality stability control.
OalaLMurchisonAGBalachandranP, et al.Machine learning for health: algorithm auditing & quality control. J Med Syst2021; 45: 105–105.
2.
AbioABonadaFPujanteJ, et al.Machine learning-based surrogate model for press hardening process of 22MnB5 sheet steel simulation in industry 4.0. Materials (Basel)2022; 15: 3647–3647.
3.
ZhangGRanYWangY, et al.Composite error prediction of multistage machining processes based on error transfer mechanism. Int J Adv Manuf Technol2015; 76: 271–280.
4.
Peter HeQWangJ. Statistical process monitoring as a big data analytics tool for smart manufacturing. J Process Control2018; 67: 35–43.
5.
HuSZhaoLPYaoYY, et al.A variance change point estimation method based on intelligent ensemble model for quality fluctuation analysis. Int J Prod Res2016; 54: 5783–5797.
6.
LiuSQSuQLiP. QUALITY PAPER. Research on the quality stability evaluation and monitoring based on the pre-control chart. Int J Qual Reliab Manag2014; 31: 966–982.
7.
ZhengWJLiuYGaoZL, et al.Just-in-time semi-supervised soft sensor for quality prediction in industrial rubber mixers. Chemom Intell Lab Syst2018; 180: 36–41.
8.
DasA. Multivariate statistical monitoring strategy for an automotive manufacturing part facility. Mater Today Proc2020; 27: 2914–2917.
9.
GuoLLWuPLouSW, et al.A multi-feature extraction technique based on principal component analysis for nonlinear dynamic process monitoring . J Process Control2020; 85: 159–172.
10.
AslamMAzamMKimK-J, et al.Designing of an attribute control chart for two-stage process. Meas Control2018; 51: 285–292.
11.
ZanTLiuZHWangH, et al.Control chart pattern recognition using the convolutional neural network. J Intell Manuf2020; 31: 703–716.
12.
XieJTGaoJMGaoZY, et al.Application research of multivariate linkage fluctuation analysis on condition evaluation in process industry. Sci China Technol Sci2018; 61(03): 397–407.
13.
SunKGaoJMGaoZY, et al.Plant-wide quantitative evaluation of a process industry system’s operating state based on color-spectrum. Mech Syst Signal Process2015; 60–61: 644–655.
14.
LiuYMZhouHFTsungF, et al.Real-time quality monitoring and diagnosis for manufacturing process profiles based on deep belief networks. Comput Ind Eng2019; 136: 494–503.
15.
HuSDongBC. A multidimensional data flow driven-based quality fluctuation evaluation for manufacturing process. Math Probl Eng2021; 5514056: 1–9.
16.
ZhaoLPHuSYaoYY. A quality-driven stability analysis framework based on state fluctuation space model for manufacturing process. Proc Inst Mech Eng E J Process Mech Eng2019; 233: 436–447.
17.
ZhuJShiHSongB, et al.Information concentrated variational auto-encoder for quality-related nonlinear process monitoring. J Process Control2020; 94: 12–25.
18.
SvenKSebastianSDirkB. Quality prediction of honed bores with machine learning based on machining and quality data to improve the honing process control. Proc CIRP2020; 93: 1322–1327.
19.
BaiYSunZZZengB, et al.A comparison of dimension reduction techniques for support vector machine modeling of multi-parameter manufacturing quality prediction. J Intell Manuf2019; 30: 2245–2256.
20.
HuZLZhaoQWangJ. The prediction model of worsted yarn quality based on CNN–GRNN neural network. Neural Comput Appl2019; 31: 4551–4562.
21.
GhanmiHGhithABenameUT. Prediction of rotor-spun yarn quality using hybrid artificial neural network-fuzzy expert system model. Indian J Fibre Text Res2019; 44: 31–38.
22.
BesenhardMOScheibelhoferOFrançoisK, et al.A multivariate process monitoring strategy and control concept for a small-scale fermenter in a PAT environment. J Intell Manuf2018; 29: 1501–1514.
23.
LiDYWangKB. A multisource domain adaptation method for quality prediction in small-batch production systems. Int J Prod Res2022; 60: 6268–6281.
24.
LiYXMuHCJosephP, et al.Towards intelligent monitoring system in wire arc additive manufacturing: a surface anomaly detector on a small dataset. Int J Adv Manuf Technol2022; 120: 5225–5242.
25.
LiYRZangWL. Prediction and analysis of slab quality based on neural network combined with particle swarm optimization (PSO). Metalurgija2021; 60: 15–18.
26.
MyrsiniNSpyridonPAnastasiosK, et al.Infrastructure monitoring and quality diagnosis in CNC machining: a review. CIRP J Manuf Sci Technol2022; 38: 631–649.
27.
ThiedeSTuretskyyAKwadeA, et al.Data mining in battery production chains towards multi-criterial quality prediction. CIRP Ann2019; 68: 463–466.
28.
JihyeJTaiWooCSungbumJ. Quality prediction and yield improvement in process manufacturing based on data analytics. Process2020; 8: 1068–1086.
29.
HuSLiZZhangSJ. Quality spectra fluctuation modeling for manufacturing process based on deep transfer learning. J Phys Conf Ser2021; 1983: 012101 (7pp).
30.
ChristopherRMuratKOleR. An extended Tennessee Eastman simulation dataset for fault-detection and decision support systems. Comput Chem Eng2021; 149: 1–11.
31.
MyasnikovE. A feature fusion technique for dimensionality reduction. Pattern Recognit Image Anal2022; 32: 607–610.
