The Journal of Grey System ›› 2025, Vol. 37 ›› Issue (4): 79-90.

Previous Articles     Next Articles

An Improved Conformable Fractional Grey Multivariate Model and Its Application

  

  1. 1.Key Laboratory of Data Science and Smart Education, Hainan Normal University, Ministry of Education, Haikou, Hainan, 571158, P.R. China
    2.Key Laboratory of Computational Science and Application of Hainan Province, Hainan Normal University, Haikou, Hainan, 571158, P.R. China
    3.School of Transportation and Civil Engineering, Nantong University, Nantong, Jiangsu, 226019, P.R. China
  • Online:2025-08-15 Published:2025-07-31
  • Supported by:
    This work is supported by the National Natural Science Foundation of China (No. 12471354), Key Laboratory of Data
    Science and Intelligence Education (Hainan Normal University), Ministry of Education (No. DSIE202407), Key Laboratory of
    Computational Science and Application of Hainan Province (No. JSKX202402), the Science and Technology Project of Nantong
    City (No. JC2024043) and Postgraduate Research & Practice Innovation Program of Jiangsu Province (No. SJCX25_2054).

Abstract:

The conformable fractional accumulation generating operator (CF-AGO) can effectively handle information differences and deeply
explore the laws of information development. Nevertheless, the CF-AGO fails to satisfy the highly crucial new information priority
(NIP) principle. In this paper, a novel conformable fractional accumulation generating operator (NCF-AGO), which meets the NIP
principle under certain conditions, is introduced firstly. Then an improved conformable fractional grey multivariate model with
variable NCF-AGO is constructed. Both linear and nonlinear correction terms are considered in the model structure to fit data
sequences with different features. The quantum particle swarm optimization algorithm is adopted to obtain the optimal accumulation
orders and the optimal power exponent of the nonlinear correction term. In order to avoid the situation where overfitting of the model leads to poor prediction results, the Tikhonov regularization method, which includes the conventional least squares method as a special case, is proposed solve the involved model parameters. Finally, a case study from bending strength of concrete is given to show the effectiveness of the proposed model and its advantages over the well-known GM(1,N) model and several existing grey multivariate models.

Key words: