Skip to main content

Advertisement

Springer Nature Link
Log in

Sine cosine-K-means hybrid algorithm for dynamic traction load classification of high-speed rail

  • Original Research
  • Published:
Journal of Ambient Intelligence and Humanized Computing Aims and scope Submit manuscript

Abstract

Dynamic traction load classification and cluster analysis play an important guiding role in high-speed rail load forecasting. This study classifies numerous measured traction load data after analyzing the dynamic characteristics of the load during typical operation to predict the dynamic load of high-speed rail traction substations accurately. The K-means clustering method is affected by the location of the initial clustering center, which is prone to cause the problem of inaccurate clustering results. The study proposes a sine cosine-K-means (SCA-K) hybrid algorithm for dynamic traction load classification. The sine cosine algorithm (SCA) can dynamically search for the optimal global solution by simulating the outward fluctuation of the sine and cosine functions interactively. The SCA is adopted to optimize the initial classification status. The K-means algorithm is simple in structure, clear in meaning and fast in computation. A combination of the above two algorithms is applied to perform dynamic traction load classification. The case study is to classify the dynamic traction load of a traction substation and compare the classification effect with the other four algorithms. The simulation results show the silhouette coefficient, cluster center, running time, and other results of the SCA-K and the other four algorithms. The proposed SCA-K has a 1.24% higher silhouette coefficient than the best of other compared methods. Compared with the other four algorithms, SCA-K has a superior clustering effect and operational stability and can improve the classification accuracy of traction load.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

The data that support the findings of this study are available from the corresponding author upon reasonable request. Data link: https://pan.baidu.com/s/1CcSSL9GbfdOGQIsSSRS-JA

Abbreviations

\(a\) :

A constant

A(x):

Average distance of x from the remaining data within class Uk

B(x):

Minimum mean distance between x and non- Uk class distance

\(n_{1}\),\(n_{2}\),\(n_{3}\),\(n_{4}\) :

Stochastic numbers

\(N(P_{j} )\) :

Dimensions of data in the cluster center \(P_{j}\) to which it is classified

\(P\) :

Cluster of the K-means

\(p_{d}^{t}\) :

d-Dimensional optimal position

\(S\) :

Dataset of the K-means

\({\varvec{S}}_{i}\) :

i-Th data

\(SIL\) :

Silhouette coefficient

\(\overline{SIL}\) :

Mean value of \(SIL\)

\(t\) :

Current quantity of iterations

\(T\) :

Maximum quantity of iterations

\(U\) :

Clustering centers of the K-means

\({\varvec{U}}_{j}\) :

j-Th clustering center

x :

Sample data of Uk

\(x_{i,d}^{t}\) :

d-Dimensional position

GWO:

Grey wolf optimizer

GWO-K:

GWO and K-means

MFO:

Moth-flame optimization

MFO-K:

MFO and K-means

PSO:

Particle swarm optimization

PSO-K:

PSO and K-means

SCA:

Sine cosine algorithm

SCA-K:

SCA and K-means

SIL:

Silhouette coefficient

TPSS:

Traction power supply system

References

  • Abualigah L, Diabat A (2021) Advances in sine cosine algorithm: a comprehensive survey. Artif Intell Rev 54(4):2567–2608

    Google Scholar 

  • Askarovich AB (2021) Cluster methods for the development of thinking of students of informatics. Academy 3(66):13–14

    Google Scholar 

  • Berahmand K, Mohammadi M, Faroughi A, Mohammadiani R (2022) A novel method of spectral clustering in attributed networks by constructing parameter-free affinity matrix. Clust Comput 25(2):869–888

    Google Scholar 

  • Bittmann L (2021) A quantum cluster algebra approach to representations of simply laced quantum affine algebras. Math Z 298(3):1449–1485

    MathSciNet  MATH  Google Scholar 

  • Borlea ID, Precup RE, Borlea AB, Iercan D (2021) A unified form of fuzzy C-means and K-means algorithms and its partitional implementation. Knowl-Based Syst 214:106731

    Google Scholar 

  • Caldas R, Rátiva D, de Lima Neto FB (2018) Clustering of self-organizing maps as a means to support gait kinematics analysis and symmetry evaluation. Med Eng Phys 62:46–52

    Google Scholar 

  • Cao W, Feng X, Zhang H (2019) The structural and spatial properties of the high-speed railway network in China: a complex network perspective. J Rail Transport Plan Manag 9:46–56

    Google Scholar 

  • Chavent M, Kuentz-Simonet V, Labenne A, Saracco J (2018) ClustGeo: an R package for hierarchical clustering with spatial constraints. Comput Statistics 33(4):1799–1822

    MathSciNet  MATH  Google Scholar 

  • El-Khatib SA, Skobtsov YA, Rodzin SI (2021) Comparison of hybrid ACO-k-means algorithm and Grub cut for MRI images segmentation. Proc Comput Sci 186:316–322

    Google Scholar 

  • Ezugwu AE, Agushaka JO, Abualigah L, Mirjalili S, Gandomi A (2022) Prairie dog optimization algorithm. Neural Comput Appl 34(22):20017–20065

    Google Scholar 

  • Gabis AB, Meraihi Y, Mirjalili S, Cherif AR (2021) A comprehensive survey of sine cosine algorithm: variants and applications. Artif Intell Rev 54(7):5469–5540

    Google Scholar 

  • Gupta MK, Chandra P (2020) A comprehensive survey of data mining. Int J Inf Technol 12(4):1243–1257

    Google Scholar 

  • Han K, Huang T, Yin L (2021) Quantum parallel multi-layer Monte Carlo optimization algorithm for controller parameters optimization of doubly-fed induction generator-based wind turbines. Appl Soft Comput 112:107813

    Google Scholar 

  • Hatamlou A, Abdullah S, Nezamabadi-Pour H (2012) A combined approach for clustering based on K-means and gravitational search algorithms. Swarm Evol Comput 6:47–52

    Google Scholar 

  • He Z, Zheng Z, Hu H (2016) Power quality in high-speed railway systems. Int J Rail Transport 4(2):71–97

    Google Scholar 

  • Hotait H, Chiementin X, Mouchaweh MS, Rasolofondraibe L (2021) Monitoring of ball bearing based on improved real-time OPTICS clustering. J Signal Process Syst 93(2):221–237

    Google Scholar 

  • Jesper M, Pag F, Vajen K, Jordan U (2021) Annual industrial and commercial heat load profiles: modeling based on k-Means clustering and regression analysis. Energy Conversion Manag X 10:100085

    Google Scholar 

  • Joseph A, Rex ES, Christopher S, Jose J (2021) Content-based image retrieval using hybrid K-means moth flame optimization algorithm. Arab J Geosci 14(8):1–14

    Google Scholar 

  • Kaur G, Dhillon JS (2021) Economic power generation scheduling exploiting hill-climbed Sine-Cosine algorithm. Appl Soft Comput 111:107690

    Google Scholar 

  • Khotimah BK, Irhamni F, Sundarwati TRI (2016) A Genetic algorithm for optimized initial centers K-means clustering in SMEs. J Theor Appl Inf Technol 90(1):23

    Google Scholar 

  • Kim K (2021) Spatial contiguity-constrained hierarchical clustering for traffic prediction in bike sharing systems. IEEE Trans Intell Transp Syst 23(6):5754–5764

    Google Scholar 

  • Kim K, Ahn H (2008) A recommender system using GA K-means clustering in an online shopping market. Expert Syst Appl 34(2):1200–1209

    Google Scholar 

  • Kumar S, Yildiz BS, Mehta P, Panagant N, Sait SM, Mirjalili S, Yildiz AR (2022) Chaotic marine predators algorithm for global optimization of real-world engineering problems. Knowl-Based Syst 261:110192

    Google Scholar 

  • Li H, Wang J (2022) Collaborative annealing power k-means++ clustering. Knowl-Based Syst 255:109593

    Google Scholar 

  • Li Y, Zhao Y, Liu J (2021) Dynamic sine cosine algorithm for large-scale global optimization problems. Expert Syst Appl 177:114950

    Google Scholar 

  • Ma L, Gu L, Li B, Ma Y, Wang J (2015) An improved K-means algorithm based on mapreduce and grid. Int J Grid Distrib Comput 8(1):189–200

    Google Scholar 

  • Majhi SK, Biswal S (2018) Optimal cluster analysis using hybrid K-means and ant lion optimizer. Karbala Int J Modern Sci 4(4):347–360

    Google Scholar 

  • Meenakshi A, Sirmathi H, Ruth JA (2019) Cloud computing-based resource provisioning using K-means clustering and GWO prioritization. Soft Comput 23(21):10781–10791

    Google Scholar 

  • Mirjalili S (2016) SCA: a sine cosine algorithm for solving optimization problems. Knowl-Based Syst 96:120–133

    Google Scholar 

  • Narayana GS, Kolli K (2021) Fuzzy K-means clustering with fast density peak clustering on multivariate kernel estimator with evolutionary multimodal optimization clusters on a large dataset. Multimed Tools Appl 80(3):4769–4787

    Google Scholar 

  • Oguri R, Ando K (2018) Cavitation bubble nucleation induced by shock-bubble interaction in a gelatin gel. Phys Fluids 30(5):051904

    Google Scholar 

  • Oh Y, Kim Y (2019) A resource recommendation method based on dynamic cluster analysis of application characteristics. Clust Comput 22(1):175–184

    MathSciNet  Google Scholar 

  • Randriamihamison N, Vialaneix N, Neuvial P (2021) Applicability and interpretability of Ward’s hierarchical agglomerative clustering with or without contiguity constraints. J Classif 38(2):363–389

    MathSciNet  MATH  Google Scholar 

  • Ren Z, Lei H, Sun Q, Yang C (2021) Simultaneous learning coefficient matrix and affinity graph for multiple kernel clustering. Inf Sci 547:289–306

    MathSciNet  MATH  Google Scholar 

  • Shaik MA, Verma D (2021) Agent-MB-DivClues: multi agent mean based divisive clustering. Elem Educ Online 20(5):5597–5597

    Google Scholar 

  • Shen H, Jiang Y, Li T, Cheng Q, Zeng C, Zhang L (2020) Deep learning-based air temperature mapping by fusing remote sensing, station, simulation and socioeconomic data. Remote Sens Environ 240:111692

    Google Scholar 

  • Tambunan HB, Barus DH, Hartono J, Alam AS, Nugraha DA, Usman HHH (2020) Electrical peak load clustering analysis using K-means algorithm and silhouette coefficient. In: 2020 international conference on technology and policy in energy and electric power (ICT-PEP). IEEE, pp 258–262

  • Wang L, Cao Q, Zhang Z, Mirjalili S, Zhao W (2022) Artificial rabbits optimization: a new bio-inspired meta-heuristic algorithm for solving engineering optimization problems. Eng Appl Artif Intell 114:105082

    Google Scholar 

  • Wolpert DH, Macready WG (1997) No free lunch theorems for optimization. IEEE Trans Evol Comput 1(1):67–82

    Google Scholar 

  • Xie H, Zhang L, Lim CP, Yu Y, Liu C, Liu H, Walters J (2019) Improving K-means clustering with enhanced firefly algorithms. Appl Soft Comput 84:105763

    Google Scholar 

  • Xu G, Liu Y, Khan PW (2019) Improvement of the DPoS consensus mechanism in Blockchain based on vague sets. IEEE Trans Industr Inf 16(6):4252–4259

    Google Scholar 

  • Yang S, Song K, Zhu G (2019) Stochastic process and simulation of traction load for high speed railways. IEEE Access 7:76049–76060

    Google Scholar 

  • Yin L, Sun Z (2021) Multi-layer distributed multi-objective consensus algorithm for multi-objective economic dispatch of large-scale multi-area interconnected power systems. Appl Energy 300:117391

    Google Scholar 

  • Yin L, Sun Z (2022) Distributed multi-objective grey wolf optimizer for distributed multi-objective economic dispatch of multi-area interconnected power systems. Appl Soft Comput 117:108345

    Google Scholar 

  • Yin L, Wang T, Zheng B (2021) Analytical adaptive distributed multi-objective optimization algorithm for optimal power flow problems. Energy 216:119245

    Google Scholar 

  • Younus ZS, Mohamad D, Saba T, Alkawaz MH, Rehman A, Al-Rodhaan M, Al-Dhelaan A (2015) Content-based image retrieval using PSO and k-means clustering algorithm. Arab J Geosci 8(8):6211–6224

    Google Scholar 

  • Zanbouri K, Jafari NN (2020) A cloud service composition method using a trust-based clustering algorithm and honeybee mating optimization algorithm. Int J Commun Syst 33(5):e4259

    Google Scholar 

  • Zhang P, Wu X, Wang X, Bi S (2015) Short-term load forecasting based on big data technologies. CSEE J Power Energy Syst 1(3):59–67

    Google Scholar 

  • Zhang G, Zhang C, Zhang H (2018) Improved K-means algorithm based on density Canopy. Knowl-Based Syst 145:289–297

    Google Scholar 

  • Zhang L, Lu S, Hu C, Xiang D, Liu T, Su Y (2021) Superpixel generation for SAR imagery based on fast DBSCAN clustering with edge penalty. IEEE J Sel Top Appl Earth Observ Remote Sens 15:804–819

    Google Scholar 

  • Zhao W, Wang L, Mirjalili S (2022) Artificial hummingbird algorithm: a new bio-inspired optimizer with its engineering applications. Comput Methods Appl Mech Eng 388:114194

    MathSciNet  MATH  Google Scholar 

  • Zhou Y, Ren Q (2019) Fuzzy c-means clustering algorithm for performance improvement of ENN. Clust Comput 22(5):11163–11174

    Google Scholar 

  • Zhu Q, Pei J, Liu X, Zhou Z (2019) Analyzing commercial aircraft fuel consumption during descent: a case study using an improved K-means clustering algorithm. J Clean Prod 223:869–882

    Google Scholar 

  • Zou X, Cao J, Sun W, Guo Q, Wen T (2019) Flow data processing paradigm and its application in smart city using a cluster analysis approach. Clust Comput 22(2):435–444

    Google Scholar 

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China under Grant. 52107081 and the Natural Science Foundation of Guangxi Province (China) under Grant. AA22068071.

Author information

Authors and Affiliations

  1. School of Electrical Engineering, Guangxi University, Nanning, 530004, Guangxi, China

    Linfei Yin, Lichun Chen, Zhipeng Su & Yu Li

  2. School of Intelligent Manufacturing, Nanning University, Nanning, 541699, Guangxi, China

    Linfei Yin

Authors
  1. Linfei Yin
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Lichun Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Zhipeng Su
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Yu Li
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

LY: conceptualization, funding acquisition, project administration, supervision, methodology, resources, writing—review and editing. LC, ZS, YL: data curation, formal analysis, investigation, software, validation, visualization, writing—original draft.

Corresponding author

Correspondence to Linfei Yin.

Ethics declarations

Conflict of interest

The authors declare no potential conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yin, L., Chen, L., Su, Z. et al. Sine cosine-K-means hybrid algorithm for dynamic traction load classification of high-speed rail. J Ambient Intell Human Comput 14, 4515–4527 (2023). https://doi.org/10.1007/s12652-023-04569-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12652-023-04569-x

Keywords