Product quality prediction based on RBF optimized by firefly algorithm

doi:10.23919/JSEE.2023.000061

Journal of Systems Engineering and Electronics ›› 2024, Vol. 35 ›› Issue (1): 105-117.doi: 10.23919/JSEE.2023.000061

• SYSTEMS ENGINEERING • Previous Articles

Product quality prediction based on RBF optimized by firefly algorithm

Huihui HAN(), Jian WANG(), Sen CHEN(), Manting YAN()

¹ College of Electronics and Information Engineering, Tongji University, Shanghai 201804, China

Received:2021-06-21 Online:2024-02-18 Published:2024-03-05
Contact: Huihui HAN E-mail:hanhuihui@tongji.edu.cn;jwang@tongji.edu.cn;1910067@tongji.edu.cn;2011618@tongji.edu.cn
About author:
HAN Huihui was born in 1993. She received her M.S. degree from Hefei University of Technology in 2020. She is currently pursuing her Ph.D. degree in control science and engineering at Tongji University, Shanghai, China. From 2020 until now, she is working with the team of the CIMS Research Center at Tongji University, and her research interests are deep learning, data mining, and knowledge graph. E-mail: hanhuihui@tongji.edu.cn

WANG Jian was born in 1962. He is the director of the CIMS Research Center of Tongji University, and has been long engaged in research and development in the field of automatic control. In recent years, he has been mainly engaged in enterprise informatization, CIMS, business process management, workflow technology, energy and transportation systems, networked manufacturing and system integration. His research interests are deep learning, data mining, and knowledge graph. E-mail: jwang@tongji.edu.cn

CHEN Sen was born in 1978. He received his M.S. degree from Donghua University, Shanghai. He is currently pursuing his Ph.D. degree in control science and engineering at Tongji University, Shanghai, China. From 2019 until now, he is working with the team of the CIMS Research Center at Tongji University. His research interests are deep learning, data mining, and knowledge graph. E-mail: 1910067@tongji.edu.cn

YAN Manting was born in 1995. She received her M.S. degree from Shenyang University of Technology, Shenyang, in 2020. She is currently pursuing her Ph.D. degree in electronic information at Tongji University, Shanghai, China. Her research interests are deep learning, data mining, and knowledge graph. E-mail: 2011618@tongji.edu.cn
Supported by:
This work was supported by the National Science and Technology Innovation 2030 Next-Generation Artifical Intelligence Major Project (2018AAA0101801) and the National Natural Science Foundation of China (72271188).

Abstract

Abstract:

With the development of information technology, a large number of product quality data in the entire manufacturing process is accumulated, but it is not explored and used effectively. The traditional product quality prediction models have many disadvantages, such as high complexity and low accuracy. To overcome the above problems, we propose an optimized data equalization method to pre-process dataset and design a simple but effective product quality prediction model: radial basis function model optimized by the firefly algorithm with Levy flight mechanism (RBFFALM). First, the new data equalization method is introduced to pre-process the dataset, which reduces the dimension of the data, removes redundant features, and improves the data distribution. Then the RBFFALFM is used to predict product quality. Comprehensive experiments conducted on real-world product quality datasets validate that the new model RBFFALFM combining with the new data pre-processing method outperforms other previous methods on predicting pro-duct quality.

Key words: product quality prediction, data pre-processing, radial basis function, swarm intelligence optimization algorithm

Huihui HAN, Jian WANG, Sen CHEN, Manting YAN. Product quality prediction based on RBF optimized by firefly algorithm[J]. Journal of Systems Engineering and Electronics, 2024, 35(1): 105-117.

Figures/Tables 12

Fig 1

Fig 2

Fig 3

Table 1

Fig 4

Fig 5

Table 2

Fig 6

Fig 7

Table 3

Fig 8

Fig 9

References 40

1	MAJERNIK M, DANESHJO N, MALEGA P, et al Sustainable development of the intelligent industry from industry 4.0 to industry 5.0. Advances in Science and Technology-Research Journal, 2022, 16 (2): 12- 18.
2	CHAUHAN R, YAFI E. Applicability of classifier to discovery knowledge for future prediction modelling. Journal of Ambient Intelligence and Humanized Computing, 2022. DOI: 10.1007/s12652-022-03694-3.
3	ZHANG Q C, YANG L T, CHEN Z K, et al PPHOPCM: privacy-preserving high-order possibilistic c-means algorithm for big data clustering with cloud computing. IEEE Trans. on Big Data, 2022, 8 (1): 25- 34. doi: 10.1109/TBDATA.2017.2701816
4	DU X P, MA X L, TANG S W, et al A fast algorithm for mining of association rules. Computer Engineering and Application, 2002, 38 (11): 1- 4.
5	PACHECO C, ERNST M D Eclat: automatic generation and classification of test inputs. Lecture Notes in Computer Science, 2005, 3586, 504- 527.
6	HAN J W, PEI J, YIN Y W Mining frequent patterns without candidate generation. ACM Sigmod Record, 2000, 29 (2): 1- 12. doi: 10.1145/335191.335372
7	MAO J, CHEN D J, ZHANG L Q Mechanical assembly quality prediction method based on state space model. International Journal of Advanced Manufacturing Technology, 2016, 86 (1/4): 107- 116. doi: 10.1007/s00170-015-8122-y
8	YEH C H, FAN Y C, PENG W C. Interpretable multi-task learning for product quality prediction with attention mechanism. Proc. of the IEEE 35th International Conference on Data Engineering, 2019: 1910−1921.
9	YAO L, SHAO W M, GE Z Q Hierarchical quality monitoring for large-scale industrial plants with big process data. IEEE Trans. on Neural Networks and Learning Systems, 2021, 32 (8): 3330- 3341. doi: 10.1109/TNNLS.2019.2958184
10	YANG F, LI X, BAI J J, et al Nonlinear process quality prediction using wavelet denoising OSC-SVM-PLS. Industrial & Engineering Chemistry Research, 2020, 59 (13): 6021- 6032.
11	REN L, MENG Z H, WANG X K, et al A data-driven approach of product quality prediction for complex production systems. IEEE Trans. on Industrial Informatics, 2021, 17 (9): 6457- 6465. doi: 10.1109/TII.2020.3001054
12	HU J Y, QIAN X F, PEI J, et al. A novel quality prediction method based on feature selection considering high dimensional product quality data. Journal of Industrial and Management Optimization, 2021. DOI: 10.3934/jimo.2021099.
13	THOMSPSON R Radical basis function modelling and prediction of time series. ACS Nano, 1996, 6 (10): 8857- 8867.
14	YANG X S. Firefly algorithms for multimodal optimization. Lecture Notes in Computer Science, 2009, 5792: 169−178.
15	TANG Y T, DUAN Y Q, WEN J Study on nuclear class piping hanger and support root intelligent selection based on SOM clustering algorithm. Nuclear Power Engineering, 2020, 41 (3): 193- 196.
16	ABD EL-MONEIM S, EL-RABAIE ESM, NASSAR M A, et al. Speaker recognition based on pre-processing approaches. International Journal of Speech Technology, 2020, 23(2): 435−442.
17	YAN Y J, WU G X, DONG Y, et al An improved MSR-based data-driven detection method using smoothing pre-processing. IEEE Signal Processing Letters, 2021, 28, 444- 448. doi: 10.1109/LSP.2021.3058008
18	WANG S H, CHOU T I, CHIU S W, et al Using a hybrid deep neural network for gas classification. IEEE Sensors Journal, 2021, 21 (5): 6401- 6407. doi: 10.1109/JSEN.2020.3038304
19	NICKOLAS S, SHOBHA K Efficient pre-processing techniques for improving classifiers performance. Journal of Web Engineering, 2022, 21 (2): 203- 228.
20	BEZIN Y, SAMBO B, COSTA J N. Challenges and methodology for pre-processing measured and new rail profiles to efficiently simulate wheel-rail interaction in switches and crossings. Vehicle System Dynamics, 2022. DOI: 10.1080/00423114.2021.2014897.
21	BARALDI A, ALPAYDIN E. Constructive feedforward ART clustering networks - Part II. IEEE Trans. on Neural Networks, 2002, 13(3): 662−677.
22	HOU J, QIAO J H, HAN X L Energy-saving clustering routing protocol for wireless sensor networks using fuzzy inference. IEEE Sensors Journal, 2022, 22 (3): 2845- 2857. doi: 10.1109/JSEN.2021.3132682
23	MZAO L, YUAN C A, QIN X Wireless sensor target tracking algorithm based on improved adaptive clustering. Fire Control & Command Control, 2022, 47 (1): 57- 64.
24	KOU L, DING S S, RAO Y, et al. A lightweight intrusion detection model for 5G-enabled industrial internet. Mobile Networks & Applications, 2022. DOI: 10.1007/s11036-021-01891-6.
25	HOODA H, VERMA O P. Fuzzy clustering using gravitational search algorithm for brain image segmentation. Multimedia Tools and Applications, 2022. DOI: 10.1007/s11042-022-12336-x.
26	SHAIKH P W, EL-ABD M, GAO K Z A review on swarm intelligence and evolutionary algorithms for solving the traffic signal control problem. IEEE Trans. on Intelligent Transportation Systems, 2022, 23 (1): 48- 63. doi: 10.1109/TITS.2020.3014296
27	KUMAZAWA T, TAKIMOTO M, KAMBAYASHI Y. Exploration strategies for balancing efficiency and comprehensibility in model checking with ant colony optimization. Journal of Information and Telecommunication, 2022. DOI: 10.1080/24751839.2022.2047470.
28	XU X L, YAN F Random walk autonomous groups of particles for particle swarm optimization. Journal of Intelligent & Fuzzy Systems, 2022, 42 (3): 1519- 1545.
29	YUAN M F, KAN X, CHI C H, et al An adaptive simulated annealing and artificial fish swarm algorithm for the optimization of multi-depot express delivery vehicle routing. Intelligent Data Analysis, 2022, 26 (1): 239- 256. doi: 10.3233/IDA-205693
30	NESHAT M, SEPIDNAM G, SARGOLZAEI M Swallow swarm optimization algorithm: a new method to optimization. Neural Computing & Applications, 2013, 23 (2): 429- 454.
31	RAHUL K, BANYAL R K Firefly algorithm: an optimization solution in big data processing for the healthcare and engineering sector. International Journal of Speech Technology, 2021, 24 (3): 581- 592. doi: 10.1007/s10772-020-09783-y
32	WU Z B, WU L J, XU L Bilateral matching optimization of industrial chain financial products based on 0-1 knapsack strategy and improved discrete particle swarm optimization algorithm. Computer Integrated Manufacturing Systems, 2019, 25 (12): 3279- 3288.
33	BHAGAVATHI H, RATHINAVELAYATHAM S, SHANMUGAIAH K, et al. Improved beetle swarm optimization algorithm for energy efficient virtual machine consolidation on cloud environment. Concurrency and Computation-Practice & Experience, 2022. DOI: 10.1002/cpe.6828.
34	DUTTA T, DEY S, BHATTACHARYYA S, et al. Quantum fractional order Darwinian particle swarm optimization for hyperspectral multi-level image thresholding. Applied Soft Computing, 2021. DOI: 10.1016/j.asoc.2021.107976.
35	MUKHERJEE S, ASNANI H, LIN E, et al ClusterGAN: latent space clustering in generative adversarial networks. Proc. of the AAAI Conference on Artificial Intelligence, 2019, 33, 4610- 4617. doi: 10.1609/aaai.v33i01.33014610
36	LOBATO F, SALES C, ARAUJO I, et al Multi-objective genetic algorithm for missing data imputation. Pattern Recognition Letters, 2015, 68, 126- 131. doi: 10.1016/j.patrec.2015.08.023
37	TORRES F R, CARRASCO-OCHOA J A, MARTINEZ-TRINIDAD J F, et al SMOTE-D a deterministic version of SMOTE. Lecture Notes in Computer Science, 2016, 9703, 177- 188.
38	BABAR V, ADE R. MLP-based undersampling technique for imbalanced learning. Proc. of the International Conference on Automatic Control and Dynamic Optimization Techniques, 2016: 142−147.
39	WHITLEY D A genetic algorithm tutorial. Statistics and Computing, 1994, 4 (2): 65- 85.
40	VENTER G, JAROSLAW S S Particle swarm optimization. AIAA Journal, 2003, 41 (8): 129- 132.

Method	Accuracy/ %	Precision/ %	Recall/ %	F1-score/ %	ROC_ AUC/ %	Time/ s
BP	74.65	89.10	73.20	80.37	86.32	13
SVM	79.36	88.32	74.19	80.64	85.71	10
LeNet	85.31	90.04	81.74	85.69	89.68	18
RBF	84.65	90.19	82.65	86.25	89.32	6
RF	88.91	92.34	90.54	91.43	93.44	7
RBFFALFM	91.89	96.12	92.30	94.17	96.23	8

Method	Accuracy	Precision	Recall	F1-score	ROC_AUC
LDA + RBFFALFM	86.48	90.16	87.90	89.01	91.97
MOGAImp + RBFFALFM	87.21	91.62	88.59	90.08	92.71
SMOTE-D + RBFFALFM	88.41	93.08	89.35	91.38	92.79
MLPUS + RBFFALFM	89.45	93.17	90.82	91.98	94.47
ODEM + RBFFALFM	91.89	96.12	92.30	94.17	96.23

Method	Accuracy	Precision	Recall	F1-score	ROC_AUC
RBF	84.65	89.19	83.32	86.15	88.99
RBF + SSO	87.63	92.15	86.14	89.04	94.71
RBF + GA	88.31	94.04	88.26	91.05	92.41
RBF + PSO	88.96	92.19	89.34	90.74	94.14
RBF + FA	89.65	95.04	90.10	92.50	94.62
RBFFALFM	91.89	96.12	92.30	94.17	96.23

[1]	Fan WANG, Pengfei FAN, Yonghua FAN, Bin XU, Jie YAN. Robust adaptive control of hypersonic vehicle considering inlet unstart [J]. Journal of Systems Engineering and Electronics, 2022, 33(1): 188-196.
[2]	Zhifei XI, An XU, Yingxin KOU, Zhanwu LI, Aiwu YANG. Target maneuver trajectory prediction based on RBF neural network optimized by hybrid algorithm [J]. Journal of Systems Engineering and Electronics, 2021, 32(2): 498-516.
[3]	Yang LI, Mingyong LIU, Xiaojian ZHANG, Xingguang PENG. Global approximation based adaptive RBF neural network control for supercavitating vehicles [J]. Journal of Systems Engineering and Electronics, 2018, 29(4): 797-804.
[4]	Li Zhou, Shumin Fei, and Changsheng Jiang. Adaptive integral dynamic surface control based on fully tuned radial basis function neural network [J]. Journal of Systems Engineering and Electronics, 2010, 21(6): 1072-1078.
[5]	Zeng Delu, Zhou Zhiheng & Xie Shengli. Construction of compact RBF network by refining coarse clusters and widths? [J]. Journal of Systems Engineering and Electronics, 2009, 20(6): 1309-1315.
[6]	Xue Yali & Jiang Changsheng. Trajectory linearization control of an aerospace vehicle based on RBF neural network [J]. Journal of Systems Engineering and Electronics, 2008, 19(4): 799-805.
[7]	Zhang Chunmei, Liu Heping, Chen Shujin & Wang Fangjun. Application of neural networks for permanent magnet synchronous motor direct torque control [J]. Journal of Systems Engineering and Electronics, 2008, 19(3): 555-561.
[8]	Ren Haipeng & Liu Ding. Synchronization of chaos using radial basis functions neural networks [J]. Journal of Systems Engineering and Electronics, 2007, 18(1): 83-88.

Product quality prediction based on RBF optimized by firefly algorithm

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 12

References 40

Related Articles 8

Recommended Articles

Metrics

Comments