Top Read Articles

Published in last 1 year |  In last 2 years |  In last 3 years |  All

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

An Extended Conformable Fractional Stochastic Grey Model and its Analysis in System Prediction#br# Yang Yang, Di Zhang, Xiuqin Wang The Journal of Grey System    2025, 37 (6): 1-13.   Abstract （243）            Knowledge map    Grey models are widely researched for system modelling and analysis. Considering the complexity of practical problems, grey models with both fractional and stochastic calculus can be used for mining the changing trend of the system with certain interference and uncertainty. For the simple expression and easier calculation of conformable fractional calculus, the conformable fractional stochastic grey model is proposed and discussed. The proposed model includes both random and deterministic factors, which can utilize the excellent characteristics of fractional and stochastic grey models. Several examples are used to test the performance of the proposed model. As a broader category model, conformable fractional stochastic grey one can integrate and expand the existing model with better physical meaning. The results show that new model has good performances in model analysis and short-term prediction. More novel models and application could be achieved for data mining, complex physical problems modelling and prediction. Related Articles | Metrics

Select

Forecasting ICT Service Export Trends Using Advanced Grey Models Saima Khan, Ghulam Abbas Bhatti, Muhammad Nawaz, Naiming Xie, Weiliang Zhang The Journal of Grey System    2025, 37 (6): 66-78.   Abstract （187）            Knowledge map    The study aimed to forecasts the future trends of information and communication technology (ICT) service exports in the United States of America (USA), China, India, and. By using the data obtained from the world bank, the study compares classical time series model that is exponential triple smoothing (ETS) with advanced grey-models including DGM(1,1,α), EGM(1,1), EGM(1,1,α,θ). ICT services are projected to be exponential in case of China and India, whereas for the USA, growth is projected to be approximately linear. EGM (1,1,α,θ) demonstrated superior performance in all three countries, as confirmed by the lowest mean absolute percentage error (MAPE). The additional parameters α and θ are likely to enable a more accurate representation of the underlying pattern in data, particularly in cases with significant fluctuations in data. The results have important implications for strategic planning in the digital infrastructure. Related Articles | Metrics

Select

A Novel Seasonal Grey Model with Time Power Terms for High-accuracy Quarterly Electricity Consumption Forecasting Xuexiu Fan, Keshen Jiang, Zedong Xu The Journal of Grey System    2025, 37 (6): 14-27.   Abstract （171）            Knowledge map    Quarterly electricity consumption forecasting poses significant challenges due to its inherent characteristics of periodic oscillations, nonlinear fluctuations, and temporal trends, driven by seasonal variations and macroeconomic dynamics. This study proposes a seasonal grey model with time power terms (abbreviated as SPGM(1,1)) that integrates trigonometric seasonality components and time-variant power terms into the grey system framework. We rigorously derive the model’s discrete formulation and time response sequence. To enhance the model’s efficacy, a particle swarm optimization (PSO) algorithm is adopted to calibrate the model’s nonlinear parameters. To demonstrate the effectiveness and superiority of the SPGM(1,1) model, this model is applied to simulate and predict Guangzhou’s quarterly electricity consumption data (2018Q1-2023Q4). The numerical results show that the proposed model demonstrates a better performance than the other grey models, the statistical econometric model and the machine learning model. Furthermore, to validate the robustness and stability of the new model, we trained it using datasets with varying proportions. The results demonstrate that the SPGM (1,1) model can adaptively fit and predict data sequences. Therefore, the SPGM(1,1) model is utilized to predict Guangzhou’s quarterly electricity consumption by 2025, inferring that electricity consumption will continue to exhibit a growth tendency with seasonal fluctuations. Based on the attained forecasts, several suggestions are put forward to promote the sustainable development of Guangzhou’s electricity consumption, supporting the evaluation of China’s power system reform pilot programs to derive actionable insights for optimizing energy systems in similar cities globally. Related Articles | Metrics

Select

A Novel Nonlinear Discrete Grey Bernoulli Model with Time Power Term and Its Applications#br# Changyu Cai, Wenqing Wu, Mengfan He, Lianlian Luo The Journal of Grey System    2025, 37 (6): 91-111.   Abstract （169）            Knowledge map    The nonlinear grey Bernoulli model is a powerful grey forecasting model for analyzing nonlinear small sample sequences, which receives a considerable amount of interest in recent years. However, the inconsistency between its grey basic form used for linear parameters estimation and its grey differential equation used for time response function may cause large errors in some real applications. Thus this paper designs a nonlinear discrete grey Bernoulli model with time power term, abbreviated as NDGBM(1,1, ta), to improve the model accuracy. The expressions of the time response function and the linear system parameters are derived with the linearized form of the NGBM(1,1, ta) model. The structural parameters of the new discrete model are searched by the whale optimization algorithm. Further, according to historical data of gross regional product of Shifang city and Mianzhu city in Sichuan province, different type of continuous and discrete grey forecasting models are built, and the future values of selected cities are calculated. Related Articles | Metrics

Select

A Novel Time-varying Grey Model for the NEV Sales Prediction in China Shuliang Li, Rongji Zhang, Guijun Zhang, Xun Zhang, Mingmeng Gan, Liangping Zhang The Journal of Grey System    2026, 38 (3): 1-15.   Abstract （164）            Knowledge map    Current time-varying grey models generally suffer from structural rigidity and insufficient consideration of the intervention effect. To further broaden the application scope of time-varying grey models, this paper proposes a novel fractional time-varying discrete grey model based on the intervention effect (IE-FTVDGM(1, N)). The new model reconstructs the time-varying term by introducing a fractional-order time series to construct a grey model with an adaptive time-varying structure. The reconstructed time-varying term combines integer-order and fractional-order polynomial properties, and can be flexibly adjusted by optimizing a single hyperparameter. In addition, the dual carbon policy is incorporated into the modeling framework as an intervention dummy variable to capture anomalous fluctuations.To determine the optimal hyperparameters, we select the particle swarm algorithm after comparing it with other intelligent algorithms. Finally, Monte Carlo is used to evaluate the robustness of the proposed model. When applied to forecasting China’s new energy vehicle sales, the proposed IE-FTVDGM(1, N) achieves an MAPE of 0.101% and an R2 of 0.9999. It consistently maintains an MAPE below 1% under three different noise levels, demonstrating superior accuracy and stability over all competing models. Related Articles | Metrics

Select

A Time Delayed Discrete Grey Power Model with Dynamic Background Value and Its Application in Forecasting Master's Enrollment Scale#br# Xin Lu, Yongwei Cheng, Ying Wang, Wei Meng The Journal of Grey System    2025, 37 (6): 53-65.   Abstract （158）            Knowledge map    In recent years, the "postgraduate entrance exam fever" has become a hot topic in public discourse. The contradiction between the supply of talent cultivation in higher education institutions and societal demands has become increasingly prominent. Therefore, it is crucial to guide graduates in rationally understanding the future trends of postgraduate entrance exams, and the quantity of master's enrollment is a key factor influencing whether undergraduates choose to apply. Based on the three-parameter discrete grey forecast model, this paper introduces dynamic background value and a time delayed power term to construct a time delayed discrete grey power model (TDDBGM(1,1,λ,tα). With the goal of minimizing the MAPE of total test, the PSO (Particle Swarm Optimization) algorithm is employed to globally optimize the parameters λ and α. Subsequently, this model is used to simulate and forecast the quantity of master's enrollment under the background of higher education popularization. The results demonstrate superior performance with train set error (3.28%), test set error (1.39%), and total set error (2.94%), all of which are significantly lower than those of the TDDGM(1,1,tα) model, DBGM(1,1) model, GM(1,1,t2) model, ARIMA model and SVR model. Based on the results, this study proposes relevant policy recommendations. Related Articles | Metrics

Select

Corrosion Rate Prediction of Oil and Gas Pipelines Based on VMD-KPCA-Optimized GM (1, N) Power Model#br# Donghai Yang, Mingzhang Zhuang, Jiaxu Miao The Journal of Grey System    2025, 37 (6): 40-52.   Abstract （154）            Knowledge map    At present, the data regarding oil and gas pipeline corrosion rate prediction collected in oilfields is characterized by a limited number of samples, a limited variety of types, and the absence of linear regularity. In light of these characteristics, this paper intends to adopt an improved approach for accurately predicting the corrosion rate of oil and gas pipelines. Firstly, variational mode decomposition (VMD) is utilized to decompose various pipeline corrosion factors. This method decomposes the limited pipeline corrosion factors into new variables with distinct features, thereby making effective use of the collected data. Subsequently, kernel principal component analysis (KPCA) is employed to reduce the dimensionality of the decomposed new variables of the corrosion factors, a minimizing data redundancy. Finally, the GM (1, N) power model with structural enhancements and optimized background - value calculation is used for modeling and prediction. The prediction results of the VMD - KPCA - OGM (1, N) are compared with those of the GRA - OGM (1, N), VMD - OGM (1, N), and GRA - OGM (1, N) - GABP. The results show that VMD addresses the end effect and mode mixing issues of the EMD during the decomposition of pipeline corrosion rate prediction data, enabling more effective extraction of each principal component. Simultaneously, compared to the PCA, the KPCA exhibits a more pronounced dimension - reduction effect on nonlinear data. The prediction model established by integrating these three methods demonstrates a higher training fitting degree and prediction accuracy for the corrosion rate prediction data than other models. Its Mean Absolute Percentage Error (MAPE) is 1.4856%, the lowest among the four models. Consequently, this model proves to be an effective means of reflecting the variations in the corrosion rate of pipelines. Related Articles | Metrics

Select

Occupational Hazards and Workplace Safety in Organizational Setting: Grey Relational Evaluation#br# Dongrui Xia, Mian Aziz Hussain, Xiaodong Ding, Razia Anjum, Beenish Ramzan, Muhammad Wasif Hanif The Journal of Grey System    2025, 37 (6): 112-123.   Abstract （136）            Knowledge map    With a view to improve health and safety of human resources in industry, the study aims to identify and evaluate the occupational hazards relevant to cement industry in China. Primary data were collected from the cement industry professionals based on physical, chemical, biological, process, and ergonomic and environmental hazards. The Dynamic Grey Relational Analysis (DGRA) was used to identify and rank the hazards. This method established an effective system to handle complex relations together with uncertainties found in occupational hazard information. For comparative analyses, the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) and the Grey Ordinal Priority Approach (OPA-G) were used. We found that the most significant hazard was physical cement dust in all methods. The Kruskal-Walli’s test (KWT) was also applied to investigate the significance of this hazard across different demographics groups, and found no significant differences among them. This study is the first of its kind to apply the Grey Relational Analysis methods to explore the occupational hazards of airborne contaminants in cement industry of China. This suggests the industry stakeholders to develop effective safety measures for the cement industry by correct identification and control of key hazards. Related Articles | Metrics

Select

Prioritizing Barriers and Potential Solutions for Solar Energy Development in China: A dynamic Grey Relational Analysis and TOPSIS Approach#br# Ismail Kamdar, Sifeng Liu, Weiliang Zhang The Journal of Grey System    2025, 37 (6): 28-39.   Abstract （125）            Knowledge map    Among various renewable energy sources, solar energy is particularly attractive due to its abundance in China. However, several barriers hinder the development of solar energy in the country. This study followed a systematic approach to identify country-specific barriers and corresponding solutions. A total of 17 barriers were identified and categorized into six groups: technical, economic, social, political, institutional, and environmental. To overcome these barriers, six potential solutions were proposed. The dynamic grey relational analysis (dynamic GRA) approach was then applied to evaluate and prioritize these barriers, and the technique for order of preference by similarity to ideal solution (TOPSIS) approach was used to assess the potential solutions. The dynamic GRA approach revealed that “high initial capital costs” and “energy storage challenges” in the economic and technical groups are the most significant barriers to solar energy development in China. Meanwhile, the TOPSIS approach indicated that “financial and economic incentives” and “regulatory and policy reforms” are the most effective solutions to these barriers. This study is the first to incorporate environmental factors and apply the dynamic GRA to evaluate barriers to solar energy development. The findings provide important insights and practical recommendations for energy professionals and policymakers. Related Articles | Metrics

Select

Evaluation of Renewable Energy Integration in Green Transportation Systems: Grey Systematic Approach Yi Li, Muhammad Nawaz, Muhammad Wasif Hanif The Journal of Grey System    2026, 38 (2): 1-15.   Abstract （125）            Knowledge map    Integrating renewable energy into green transportation is critical for achieving sustainable development goals. This study investigates the key factors driving the integration of renewable energy into green transportation systems. Through a comprehensive literature review and expert consultation, 11 drivers were identified and ranked using the Dynamic Grey Relational Analysis (DGRA) and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). Government Subsidies and Incentives, Electric Vehicles and Charging Infrastructure, and Energy Security and Reduced Fuel Dependency were the most important drivers. In addition, Kruskal-Wallis test was used to assess the consistency of rankings between different stakeholder groups. Although there were slight differences between the rankings produced by the DGRA and TOPSIS methods, the top five drivers for both methods remained consistent, underscoring their critical importance. The findings highlight that government interventions, such as subsidies and incentives, play a key role in promoting renewable energy adoption. The development of electric vehicles and charging infrastructure, as well as the need to enhance energy security and reduce dependence on fossil fuels, further highlights the systemic nature of these factors. This study provides a robust framework for policymakers and industry stakeholders to prioritize initiatives and efficiently allocate resources to facilitate the integration of renewable energy sources. Related Articles | Metrics

Select

An Interval Grey Number Approach to Congestion Measurement in Data Envelopment Analysis Chong Li, Xintian He, Xinru Yu The Journal of Grey System    2025, 37 (6): 79-90.   Abstract （123）            Knowledge map    Efficiency measurement in traditional Data Envelopment Analysis (DEA) models depends mainly on sampling, and the reliability of efficiency results is directly affected by the data quality of the Decision-making Units (DMUs). The interval DEA models have been developed to address the problem of inaccurate data in DEA. However, this study reveals that the existing models and approaches may lead to inaccuracies and inconsistencies in the measurement of efficiency and congestion effect. To address these shortcomings, this paper first proposes a new interval grey number envelopment model which takes into account the cross-evaluation logic between DMUs in an uncertain environment. It then proposes a novel algorithm for identifying and measuring the effects of congestion. The new method reserves the maximum possible range of efficiency values and improves the congestion identification between DMUs. Finally, the advantages and improvements of the proposed method are illustrated by several numerical examples. Related Articles | Metrics

Select

A multivariate grey Bernoulli model based on damping accumulation and its application in the high-tech industry Sandang Guo, Ruimin Xia, Xu Han, Shuaishuai Geng, Jun Wei, Xiaomeng Ma The Journal of Grey System    2026, 38 (2): 16-28.   Abstract （118）            Knowledge map    Addressing the nonlinear, fluctuating nature of system data and the insufficient sensitivity of existing grey accumulation to new information, an improved grey Bernoulli model with a damping trend factor (DANGBM(1,N)) is proposed. A damping accumulation operator is introduced, assigning greater weight to new data during preprocessing to enhance sensitivity to recent trends. Combined with the grey Bernoulli model, it better identifies nonlinear characteristics and flexibly adjusts prediction trends, overcoming limitations in existing techniques. Hyperparameters are optimized via particle swarm optimization for adaptability. Applied to China’s high-tech industry output value, the model demonstrates superior predictive performance over five benchmarks, offering an effective method for complex nonlinear small-sample forecasting. Related Articles | Metrics

Select

Integration of Grey System Theory and EEG Technology for Personalized Attention Cultivation in Primary Education Yufeng Huang, Tiffany Chang The Journal of Grey System    2026, 38 (2): 82-94.   Abstract （118）            Knowledge map    Attention has emerged as a critical determinant of learning outcomes in an increasingly digital educational landscape. Traditional assessment methods, however, inadequately capture the uncertainty and dynamic fluctuations characteristic of attention data. We developed a Dynamic Nonlinear Grey Relational Analysis (DN-GRA) model integrated with electroencephalography (EEG)neurofeedback technology to enable real-time detection and prediction of attention patterns, thereby facilitating personalized educational interventions. A 12-week randomized controlled trial with 200 primary school students (grades 3-4) revealed that the experimental group significantly outperformed controls across multiple dimensions: attention stability increased 175%, sustained attention duration improved 120%, and average attention values rose 129% (all p < 0.001). Students also demonstrated substantial gains in memory capacity (28.5%), logical reasoning (30.1%), and overall academic performance (effect size d = 0.82). Grey Relational Analysis validation confirmed the effectiveness of personalized intervention strategies, establishing a practical framework for integrating grey system theory (GST) with neurotechnology to advance educational equity and promote sustainable learning outcomes. Related Articles | Metrics

Select

A Time-delay Grey Relational Analysis Model based on Procrustes Distance Honghua Wu, Aqin Hu, Yafang Li, Xue Han, Yang Li The Journal of Grey System    2026, 38 (3): 27-35.   Abstract （117）            Knowledge map    To address the issues in existing panel data-based grey relational analysis models (PD-GRA), such as the neglect of indicator’s time delay and data transformation considerations, a time-delay grey relational analysis model (TDGRA) is proposed. First, the concepts of the sample matrix, the submatrix under time delay, and the corresponding truncation matrix are introduced. Second, singular value analysis is performed on the relevant matrices, and the optimal rotation matrix is derived. Then, an optimization model is constructed with the goal of minimizing the Procrustes distance, through which the time delays between indicators are determined. And then, a PD-GRA model is proposed based on the optimal Procrustes distance with time delay. Finally, the TDGRA model is used to identify the driving factors of AQI in the Yellow River Basin, obtaining urbanization rate (UR), carbon emissions (CE), gross domestic product (GDP), and the growth of total investments in fixed assets (GIFA) as the main drivers. The results demonstrate the rationality and effectiveness of the proposed TDGRA model, and its advantages are further highlighted through comparative analysis. Related Articles | Metrics

Select

Complex Order Damped Cumulative GM(1,1) Model Applied to Oil Trade Jie Zhang, Jinhai Guo, Yihao Gao, Lin Wang The Journal of Grey System    2026, 38 (2): 29-42.   Abstract （117）            Knowledge map    In this study, the complex-order damping accumulated GM(1,1) model (CDAGMz(1,1)) and the complex-order damping accumulated discrete GM(1,1) model (CDADGMz(1,1)) are based on the damping accumulated generating operator and the complex-order accumulated generating operator. By expanding the parameter value range from the real domain to the complex domain, these two new models can better balance the weighting between new and old information, extract more effective features from limited data, and enhance the model accuracy. The relationship between the two models and their respective application scopes was also clarified. An empirical analysis is conducted using China's oil import and export volumes from 2012 to 2024 as the research subject, verifying the applicability and effectiveness of the new models in predicting oil import and export volumes and predicting the oil import and export volumes from 2025 to 2027. Related Articles | Metrics

Select

Governance, Security, and Public Satisfaction: Evidence from Romanian and Moldovan Regions through Grey Clustering Analysis Camelia Delcea, Rafal Mierzwiak, Constantin Marius Profiroiu, Alina Georgiana Profiroiu, Bianca Cibu, Ionuț Nica, Ioana Ioanăș, Andra Sandu The Journal of Grey System    2026, 38 (4): 1-26.   Abstract （114）            Knowledge map    This study investigates how varying the analytical emphasis placed on political and security-related indicators shapes citizen satisfaction at the regional level in Romania and the Republic of Moldova. In a socio-political environment characterized by institutional transformation and evolving security challenges, identifying the combined and separate effects of these dimensions is critical for designing effective regional policies. The empirical analysis employs a grey clustering methodology to classify counties into three distinct satisfaction categories. To capture the sensitivity of outcomes to indicator prioritization, five predefined analytical configurations are constructed, reflecting different emphases on political versus security factors. The results show that under political-dominant configurations (100% or 80%), a larger share of Romanian counties (22–24 out of 42) are classified in the highest satisfaction cluster, while Moldovan counties are predominantly located in the lowest cluster. Conversely, under security-dominant configurations (80% or 100%), between 23 and 28 Moldovan counties are assigned to the highest satisfaction cluster, whereas 36–37 Romanian counties shift to the lowest cluster. These consistent structural shifts across predefined analytical configurations highlight the context-dependent role of governance and security perceptions in shaping regional satisfaction patterns. Related Articles | Metrics

Select

A New-information-prioritized Grey Bernoulli Model for Forecasting the Number of Students Enrolled in Higher Education of Chinese Provincial Administrative Regions#br# Feifei Wang, Weizhen Zuo, Weijie Zhou The Journal of Grey System    2025, 37 (6): 124-136.   Abstract （111）            Knowledge map    Accurately forecasting the number of enrollments in higher education in China can optimize the allocation of educational resources and ensure the sustainable development of the education system. Unlike existing grey prediction modeling approaches, this paper proposes a novel concept, i.e., the accumulated generating sequences preserve morphological features similar to the original data while enhancing sequence smoothness, and build a novel New-Information-Priority Grey Bernoulli Model (NIPNGBM) for predicting the number of students enrolled in higher education with different trends. Then, we use the number of students enrolled in higher education per 100,000 population from 2010 to 2021 in Beijing, Guangxi, Xizang, and Ningxia as examples, testing the adaptability of the new model to various sequence patterns, such as L-shaped, rising, inverted U-shaped, and S-shaped sequences. And the last block validation method in sample segmentation is used for hyper-parameters optimization. Results indicate that the proposed model demonstrates higher prediction accuracy and lower prediction volatility, compared against LSTM, Holt-Winters, ARIMA, LSSVR, and NGBM models. Furtherly, the new model is applied to forecast and the development trends of the number of students enrolled in higher education across 31 provinces in mainland China in the next seven years are analyzed from different time points, population thresholds, and different regions. This concept that grey prediction models balance both the shape and smoothness of the original sequence can be extended to the grey predictive modeling system, making the cumulative generation and the construction of new model more compatible, thereby expanding the application scope of the model. Related Articles | Metrics

Select

Forecasting China’s thermal power generation using a novelmultivariable time-delay grey model Youyang Ren, Yuhong Wang, Lin Xia, Wentao Huang The Journal of Grey System    2026, 38 (2): 123-137.   Abstract （109）            Knowledge map    Accurately forecasting thermal power generation is essential for China’s sustainable energy planning and green development. This paper proposes a novel multivariable time-delay grey model to forecast China’s thermal power generation from 2025 to 2030. The proposed model combines time-delay effects and dummy variables to capture the complex, nonlinear relationships between thermal power generation and economic drivers under conditions of limited data. By optimizing parameters with the Aquila Optimizer, the proposed model achieves improved adaptability and forecasting accuracy. The proposed model’s fitting MAPE is 0.58%, and the test MAPE is 0.29%, outperforming other comparison models. The forecasting results indicate that China’s thermal power generation may grow unstably through 2030. The growth rate may slow due to the increasing integration of renewable energy sources and the implementation of carbon neutrality policies. It offers referenceable and foresight insights for the Chinese government to support energy security management and future sustainable development. Related Articles | Metrics

Select

Model Selection of a Class of Discrete Grey Models Based on Connotation Research Zhicheng Jiang, Yunlian Li, Wenjing Li The Journal of Grey System    2026, 38 (1): 120-132.   Abstract （105）            Knowledge map    This paper first rewrites the first-order accumulated sequence into two distinct sequences, thereby introducing a novel research perspective. Secondly, it reveals the intrinsic relationships and geometric interpretations among the DGM(1,1), NDGM(1,1), QPDGM(1,1), and DGMP(1,1,N) models, and proposes a new criterion for determining the degree N in the DGMP(1,1,N) model. Finally, numerical examples and practical applications demonstrate the validity of the proposed theory and the operational feasibility of the method. The approach improves efficiency for applied researchers in model selection and is straightforward to implement. Related Articles | Metrics

Select

Lithium-Ion Battery Remaining Useful Life Prediction Based on a Hybrid Method of Improved GM(1,N) Model and Gaussian Process Regression Yang Cao, Min Sun, Qinqin Shen, Quan Shi The Journal of Grey System    2026, 38 (1): 28-40.   Abstract （100）            Knowledge map    Accurately predicting the remaining useful life (RUL) of lithium-ion batteries is crucial for safe operation. Grey prediction models, with advantages in handling small samples and uncertain information, offer a promising approach for RUL prediction. However, most of the existing grey prediction models focus on the degradation trend while neglecting the capacity regeneration phenomenon. To address this limitation, the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is first applied to separate the capacity degradation trend from local regeneration trends, addressing their differences in magnitude and characteristics. A hybrid prediction method, which combines an improved grey multivariate model and Bayesian-optimized Gaussian process regression, is then proposed. For the capacity degradation trend, which exhibits information heterogeneity and an exponential nonlinear trend, a variable new information priority fractional discrete grey multivariate model is proposed for prediction. The model is not only based on the ideas of variable-order accumulation and discrete grey models, but also introduces an additional nonlinear correction term. For the local regeneration trend, which is nonstationary, nonlinear, and noisy, a denoising autoencoder is employed for noise reduction and feature enrichment, followed by the Bayesian-optimized Gaussian process regression model for prediction. Finally, the predictions of each component are reconstructed to obtain the complete capacity sequence. Multidimensional evaluations on multiple NASA battery datasets, including comparisons with common baseline models and ablation studies to verify the effectiveness of each module, demonstrate that the proposed method achieves superior accuracy, stability, and generalization in capacity degradation prediction. Related Articles | Metrics