Grey Dynamic Model Research Articles

Temporal and Spatial Evolution of Public–Private Partnership (PPP) Project Risks in China: 2003–2019

The implementation of public–private partnership (PPP) is perturbed by multiple factors, and it is difficult for the Chinese government to fully control the risks of PPP projects. Based on the DPSIR model, this study constructed the PPP projects risk evaluation index system by using the TOPSIS method. Then the spatial variation, standard deviation ellipse, and gray dynamic model were used to analyze the spatial–temporal dynamic evolution characteristics of the risk level of PPP projects from 2003 to 2019 and to make reasonable predictions of the future spatial distribution pattern. This study yielded the following five results: (1) the average risk level of China’s PPP projects is 0.722, with a decreasing trend of fluctuation and relatively stable risk; (2) high-risk provinces for PPP projects decrease, medium-risk provinces increase; (3) the spatial variability of risk is increasing, and the spatial differentiation is significant, showing a spatial evolution pattern of “west > central > east,” but areas with low-risk values are clearly migrating to the east; (4) the spatial distribution pattern of risk has a north-easterly orientation, with a “north-west to north-east” trend in the path of movement; (5) There are differences in the spatial distribution patterns in the east–west and north–south directions, and the spatial spillover effect is not obvious. Based on the above results, the risk center of China’s PPP projects will be shifted to the northeast in 2025–2035. Our study captures the evolution of PPP project risks in China in both temporal and spatial dimensions, which can provide lessons for optimizing global PPP project risk management.

Dynamic multi-attribute grey target group decision model based on quantum-like Bayesian networks

PurposeGrey target decision-making serves as a pivotal analytical tool for addressing dynamic multi-attribute group decision-making amidst uncertain information. However, the setting of bull's eye is frequently subjective, and each stage is considered independent of the others. Interference effects between each stage can easily influence one another. To address these challenges effectively, this paper employs quantum probability theory to construct quantum-like Bayesian networks, addressing interference effects in dynamic multi-attribute group decision-making.Design/methodology/approachFirstly, the bull's eye matrix of the scheme stage is derived based on the principle of group negotiation and maximum satisfaction deviation. Secondly, a nonlinear programming model for stage weight is constructed by using an improved Orness measure constraint to determine the stage weight. Finally, the quantum-like Bayesian network is constructed to explore the interference effect between stages. In this process, the decision of each stage is regarded as a wave function which occurs synchronously, with mutual interference impacting the aggregate result. Finally, the effectiveness and rationality of the model are verified through a public health emergency.FindingsThe research shows that there are interference effects between each stage. Both the dynamic grey target group decision model and the dynamic multi-attribute group decision model based on quantum-like Bayesian network proposed in this paper are scientific and effective. They enhance the flexibility and stability of actual decision-making and provide significant practical value.Originality/valueTo address issues like stage interference effects, subjective bull's eye settings and the absence of participative behavior in decision-making groups, this paper develops a grey target decision model grounded in group negotiation and maximum satisfaction deviation. Furthermore, by integrating the quantum-like Bayesian network model, this paper offers a novel perspective for addressing information fusion and subjective cognitive biases during decision-making.

Novel grey dynamic trend relational analysis models with different types of accumulation delay effects for time-delay systems

In order to analyze the unknown accumulation delay relationship between the given inputs and outputs, one basic model and four extended models are proposed to simulate the different accumulation delay processes. The basic model called grey dynamic trend relational analysis model calculates the similarity between two sequences based on their trends. On the basis of the basic model, four extended models are developed to simulate the different accumulation delay effects. Two types of the accumulation delay effects, called driven-type and yielded-type accumulation delay effects, are put forward for different time-delay relationships. Each type of the accumulation delay effects designs two weight distributions for analyzing the different time-delay processes. Two optimization models based on grid-search are given to determine the lag parameters in the four extended models. The pseudo-codes of intelligent algorithms are provided for the optimization problems. To explain how it can be employed in practice, the new approaches for the time-delay systems are applied to analyze the relationships between the air pollution and its driven factors and results in the Yangtze River Economic Belt. The comparing results show that the novel models can handle the time-delay systems with accumulation delay effects and can determine the delay processes.

Design of an Energy Supply and Demand Forecasting System Based on Web Crawler and a Grey Dynamic Model

An energy supply and demand forecasting system can help decision-makers grasp more comprehensive information, make accurate decisions and even plan a carbon-neutral future when adjusting energy structure, developing alternative energy resources and so on. This paper presents a hierarchical design of an energy supply and demand forecasting system based on web crawler and a grey dynamic model called GM(1,1) which covers all the process of data collection, data analysis and data prediction. It mainly consists of three services, namely Crawler Service (CS), Algorithm Service (AS), Data Service (DS). The architecture of multiple loose coupling services makes the system flexible in more data, and more advanced prediction algorithms for future energy forecasting works. In order to make higher prediction accuracy based on GM(1,1), this paper illustrates some basic enhanced methods and their combinations with adaptable variable weights. An implementation for testing the system was applied, where the model was set up for coal, oil and natural gas separately, and the enhanced GM was better with relative error about 9.18% than original GM on validation data between 2010 and 2020. All results are available for reference on adjusting of energy structure and developing alternative energy resources.

Selection and Optimization of Regional Economic Industrial Structure Based on Fuzzy k-Means Clustering Algorithm.

Learning about the regional business model is essential for the sustainable development of the regional economy. From the perspective of urban renewable energy, city A is the product of energy development. This paper analyzes the current situation and existing problems of the industrial model of city A through fuzzy k-means clustering algorithm. The results show that although the optimization of industrial structure in city A has achieved some results, the more intuitive problems mainly include low labor productivity of the primary industry, strong resource dependence, insufficient extension of industrial chain, and slow development of technology intensive industries. This paper uses fuzzy k-means clustering algorithm to select the leading industries from the perspective of the current situation of leading industries, urban development pattern, and regional policies in city A. The results show that, as a renewable resource-based city, the leading industries suitable for the current development of city A include manufacturing, power, alkali gas and water production and supply, transportation, warehousing and postal industry, leasing, and business services. The results of fuzzy k-means clustering algorithm are quite excellent, and the accuracy rate is 93.3%. This paper uses the grey dynamic linear programming model to predict the future development of the Urban A business model and combines the selection of key functions to obtain the best business model: deep and efficient technical equipment as a good goal, achieved through regional logistics, transportation, new services, etc., to enhance the output value of the tertiary industry in city A and optimize the internal structure of the secondary industry in city A.

Spatial and Temporal Evolution of Tourism Ecological Security in the Old Revolutionary Region of the Dabie Mountains from 2001 to 2020

Tourism ecological security is an important basis for measuring the realization of the “double carbon” goal of regional tourism. Based on the drivers, pressures, state, impact and response model of intervention (DPSIR), an evaluation index system of tourism ecological security in the old revolutionary region of the Dabie Mountains is constructed. The entropy technique for order of preference by similarity to ideal solution (TOPSIS) method, spatial variation model, standard deviation ellipse model and gray dynamic model are used to explore the spatial and temporal evolution characteristics of the tourism ecological security level in the old revolutionary region of the Dabie Mountains from 2001 to 2020, and to forecast its future spatial development pattern. The study shows that (1) the average value in tourism ecological security in that region is 0.3153. Moreover, the comprehensive index increased from 0.2296 in 2001 to 0.4302 in 2020, which shows a steady improvement. The security status has improved from insecure to critically secure; (2) the number of municipalities that are insecure or relatively insecure in the region is gradually decreasing, while the number of municipalities that are located within critically secure and relatively secure cities and towns in the region is gradually decreasing. Moreover, an increasing number of cities and towns are critically secure and safe, and the whole region is now in the critical transition period between an average to low level to an average to high level of tourism ecological security; (3) the degree of spatial variation in tourism ecological security is increasing, the features of spatial differentiation are more obvious, and the overall spatial pattern of “Hubei > Henan > Anhui” is presented. (4) The spatial distribution pattern for tourism ecological security is “southeast-northwest”, and the spatial distribution range has undergone the process of “convergence to diffusion”. (5) The spatial distribution pattern in tourism ecological security is “southeast-northwest”, and the spatial distribution range has undergone a process of “convergence to diffusion”. This shows expansion toward the southeast that reflects a certain spatial spillover effect and “convergence” toward the northwest, with no obvious spatial spillover effect.

Measurement and Forecasting of China's Financial Stress Index in the A-E-G Coupling Perspective

After the outbreak of the global financial crisis in 2008, many scholars began to quantify financial risks and find alternative variables to reflect financial risks better. The financial stress index is a good alternative. In this paper, nine important factors of economic aggregate, economic benefit, and economic structure are selected to construct China's Financial Stress Index (CFSI). Then, the coupling identification of AHP and entropy weight method (A-E) is carried out, and the CFSI and its fluctuation are predicted by the grey dynamic prediction model GM(1, N). The results show that the CFSI constructed by a-E coupling weight can measure the pressure of China's financial system more accurately, and the CFSI is predicted to show A gentle decline trend from 2022 to 2024. Inspired by previous studies by scholars, this paper tries to construct and predict CFSI from the perspective of A-E-G coupling, combining subjective and objective, and hoping to open new ideas on CFSI construction and prediction.

The research on modeling and application of dynamic grey forecasting model based on energy price-energy consumption-economic growth

The unbalanced development among energy price, energy consumption, and economic growth will destroy the stability of the energy market. The nonlinear differential equations among several factors are established based on the actual situation of energy market changes and the causal relationship between energy price and economic growth in an economic stage and discuss the relationship among the factors. The nonlinear grey prediction model group of energy price-energy consumption-economic growth is established by using grey difference information. The least-square method is utilized to give the parameter estimation formula of the prediction model group, and the approximate time response formula of the model is obtained by recursive relation transformation. Finally, the new models are applied to the prediction of coal price and coal consumption in China, and the effectiveness of the two models analyzes the same data set. It shows that the prediction results of coal price and coal consumption are better than the other three classical grey prediction models, and it can effectively predict the coal price and consumption in China from 2021 to 2025. The prediction results can provide adequate information for China's energy system and have theoretical and practical significance for the stability of the energy system.

Variable Weight-Projection Gray Target Evaluation Model of Degree of Protection of Protective Layer Mining

In order to quantitatively evaluate the degree of protection in protective layer mining and provide guidance for the design of a secondary outburst elimination scheme, a variable weight-projection gray target dynamic evaluation model for the effectiveness of protective layer mining is established. The improved order relation analysis method was used to determine the subjective weight of each index toward the decision-making goal based on numerical diversity characteristics, and the initial fixed-weight calculation for mixed multi-attribute metrics was processed through the degree of index action. The variable weight function was used to dynamically adjust the fixed weight through the penalty and incentive index methods. Four indexes (gas content, gas pressure, coal seam permeability coefficient, and expansion deformation) were selected, the outburst elimination and anti-reflection were taken as the guide, and the critical value of each index for eliminating burst and the critical value of pressure relief were taken as the positive and negative bullseyes. Based on the variable weight-projection gray target decision model, the distance between the two target centers of each scheme was calculated; at the same time, the variable weight vector changed dynamically with the evaluation scheme to achieve the dynamic quantitative evaluation of the degree of protection. Additionally, compared with the calculation results of fixed weights, it was found that the variable weight-projection bullseye distance can more accurately reflect the dynamic control effect of differences in numerical combinations of multi-attribute indexes in different decision schemes based on the degree of protection of protective layer mining. Taking a mine in PingMei as the engineering background, Ding protected the Wu area, and the degree of protection in the Wu group coal seam reached 116.29%, eliminating the outburst risk of the coal seam. The Wu protected the Ji group coal seam, with the degree of outburst risk in the Ji group being reduced by 14.27, and the Ding + Wu group protected the Ji group coal seam, with the degree of outburst risk of the Ji group being reduced by 20.71%, but not eliminated. The evaluation model quantifies the degree of protection of protective layer mining, and provides a theoretical basis for further assessing whether the working face should strengthen the enhancing permeability or whether it needs to be used in tandem with high-strength outburst elimination methods.

Evaluation of High-Quality Development of Manufacturing Industry Using a Novel Grey Dynamic Double Incentive Decision-Making Model

This paper proposes a novel grey dynamic double incentive decision-making model to evaluate the high-quality development of manufacturing industry. First, we define the concepts of the improved grey incidence analysis and power weight Heronian aggregation (PWHA) operator. Then, we present the double incentive factors and determine incentive static evaluation values. In addition, we construct the weight vector of the time series. Guided by the incentive static evaluation values and weight vector of the time series, the dynamic evaluation values are produced. Finally, a practical example of the manufacturing industry in the Yangtze River Delta (YRD) demonstrates the effectiveness and application of the proposed model.

Yield Dynamic Gray Model and Its Stability Under Different Rotations and Fertilization Systems on Vegetable Fields

Yield Dynamic Gray Model and Its Stability Under Different Rotations and Fertilization Systems on Vegetable Fields

Research on a grey prediction model based on energy prices and its applications

Energy is the material basis on which human beings depend for survival and development and a strong guarantee for the sustainable development of national economies. Accurately predicting energy prices can better regulate the allocation of energy markets, improve the level of scientific energy control for energy users, and promote the sound and healthy development of the energy economy. Based on the existing market economic model of energy prices, this paper first studies the relationship between the energy supply and demand and its price and establishes a dynamic differential equation. According to the difference information from the differential equation and difference equation, a dynamic grey prediction model of the energy price is established. Then, the parameter estimation and approximate reduction formula of the model are studied. To improve the accuracy of the model, the particle swarm optimization algorithm is used to optimize the background value of the novel model, establish the optimized grey forecast model of energy prices, and obtain the modelling process of the optimized model. Finally, the model is applied to the prediction of fuel prices in three typical regions: Singapore, the Mediterranean Sea and the Arabian Gulf. Three kinds of grey prediction models are selected for comparative analysis, and five criteria are used for evaluation. The results show that the average relative errors of the simulations and predictions of the three actual cases are all less than 2%; the five evaluation criteria also basically indicate that the novel model is better than the other three grey prediction models.

Dynamic interpretation of the factors causing dam deformation with hybrid grey dynamic incidence model

Deformation measured from various measuring points within and on a dam provides important information on the structural behaviour. The effective analysis of the development trend of factors causing deformation is a significant prerequisite for the structural health monitoring of dams. However, the existing research, focuses on qualitative analysis without distinguishing the difference in the contribution of deformation-influencing factors and revealing their dynamic evolution. Additionally, the quantitative analyses concentrated on single-point information cannot reflect the global correlation between the overall deformation and environmental factors, and the correlation cannot be fully characterised either by the fluctuation range or changing trend of monitoring data series. To overcome these issues, a novel hybrid grey dynamic incidence model is designed by integrating the Deng’s grey incidence model and grey dynamic trend incidence model to dynamically analyse the factors causing dam deformation. In particular, the classic grey incidence models are improved through dimensional expansion for multi-point monitoring environment. Moreover, considering the effect of fluctuation range and changing trend, the hybrid grey dynamic incidence degree is defined to improve the interpretability of the influencing variables. Hence, the proposed model is applied to dynamically quantify the global connections of environmental factors against the deformation of an arch dam. The results are verified to be effective in improving the prediction accuracy in the structural safety of a dam and can be used to diagnose the working state of individual instrument location.

ATPS: an adaptive trajectory prediction system based on semantic information for dynamic objects

Obstacle trajectory prediction is a task in mobile robot dynamic obstacle avoidance. One of the most critical issues of dynamic obstacle trajectory prediction is how the robot can accurately and timely perceive and predict trajectories of all obstacles in the same scene when their motion states are different. This study presents an adaptive trajectory prediction system (ATPS) to answer the question. First, we propose a semantic-based dynamic object classification benchmark to distinguish objects in different motion states. Second, this article proposes a dynamic strategy which adaptively selects suitable trajectory prediction methods for different types of dynamic objects. Finally, we develop an improved dynamic gray model (DGM) and apply it to the system to obtain higher prediction accuracy and efficiency. We conduct experiments on different public datasets and real scenes to verify the effectiveness and superiority of the ATPS. We first conduct an evaluation of the DGM’s performance. The results show that the prediction accuracy of the DGM is improved compared with the traditional gray model, and the prediction efficiency is improved by about 25%. Second, we conduct a strategy evaluation experiment. The results show that the dynamic strategy proposed in this study improves prediction efficiency for regularly moving objects and improves the stability of prediction accuracy for randomly moving objects. Finally, we compared the ATPS with other advanced algorithms such as Long Short-Term Memory (LSTM) and Particle Swarm Optimization—Autoregressive Integrated Moving Average (PSO-ARIMA). Our system has the highest prediction accuracy and the most stable prediction efficiency.

1998年以来长江经济带旅游生态安全时空格局演化及趋势预测

PDF HTML阅读 XML下载 导出引用 引用提醒 1998年以来长江经济带旅游生态安全时空格局演化及趋势预测 DOI: 10.5846/stxb201912022599 作者: 作者单位: 作者简介: 通讯作者: 中图分类号: 基金项目: 国家自然科学基金项目（41771162）；湖南省国内一流培育学科建设项目资助（地理学-5010002） Spatio-temporal pattern evolution and trend prediction of tourism ecological security in the Yangtze River Economic Belt since 1998 Author: Affiliation: Fund Project: 摘要 | 图/表 | 访问统计 | 参考文献 | 相似文献 | 引证文献 | 资源附件 | 文章评论 摘要:旅游生态安全是旅游业可持续发展的基础。基于DPSIR （驱动力-压力-状态-影响-响应，Driving force-Pressure-State-Impact-Response）模型，构建长江经济带旅游生态安全评价指标体系，综合采用熵权TOPSIS （逼近理想解排序法，Technique for Order Preference by Similarity to an Ideal Solution）法、空间变差模型、标准差椭圆模型、灰色动态模型等方法分析长江经济带1998-2017年旅游生态安全水平的时空动态演变特征，并对其未来空间分布格局进行合理预测。研究发现：（1）长江经济带旅游生态安全水平均值为0.305，综合指数由0.207上升至0.439，呈稳步提升态势，安全状态由较不安全级上升至临界安全级；（2）经济带旅游生态安全为不安全级和较不安全级的省区数量逐渐减少，而处于临界安全级的省区数量持续增加，整体正介于由中低级向高级过渡的关键阶段；（3）旅游生态安全空间变异程度不断增强，空间分异特征显著，整体呈现出"东部 > 西部 > 中部"的空间演变格局，同时低值区域具有明显的西南迁移现象；（4）旅游生态安全空间分布格局呈东北-西南走向，移动路径呈"西北→东北→东南"变化趋势，空间分布范围经历了"分散-集聚"的过程。预测结果显示：2018-2030年旅游生态安全重心将向东北方向移动，空间分布格局在东西和南北方向上均呈敛缩态势，空间溢出效应不明显。 Abstract:Tourism ecological security is the basis of sustainable development of tourism. Based on Driving force-Pressure-State-Impact-Response (DPSIR) model, an evaluation index system for tourism ecological security in the Yangtze River Economic Belt is constructed. Meanwhile, a combination of entropy weight TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution) method, spatial variation model, standard deviation ellipse model, grey dynamic model and other methods is adopted to analyze and characterize the spatio-temporal dynamics of security level for tourism ecology along the Yangtze River Economic Belt during the period between 1998 and 2017, further with which a sensible prediction is made for its future pattern of spatial distribution. The results are as follows: (1) The average level of tourism ecological security in the Yangtze River Economic Belt is 0.305, with the comprehensive indicator increases from 0.207 to 0.439 in a status of stable improving. The security level raises from less safety grade to critical safety grade. (2) The number of provinces with unsafe grade and less safe grade for tourism ecological security gradually decreases while that with critical safety grade increases. Overall, it is at the critical stage of transition from middle and low level to high level. (3) The spatial variation degree of tourism ecological security keeps increasing with prominently spatial difference features. The overall spatial evolution pattern appears eastern > western > central tendency. At the same time, the low value area obviously migrates to the southwest. (4) The spatial distribution of tourism ecological security indicates northeast-southwest tendency, while the trajectory of gravity center presents the variational tendency of northwest→northeast→southeast. Spatial distribution range is distributed first and then gathered. The prediction results show that the gravity center of tourism ecological security will move to the northeast while the spatial distribution range will shrink in the east-west and north-south directions in 2018-2030. Therefore, the spatial spillover effect is not obvious. 参考文献 相似文献 引证文献

Study on the Measurement of Industrial Structure “Sophistication, Rationalization and Ecologicalization” Based on the Dynamic Analysis of Grey Relations — A Case Study of Beijing-Tianjin-Hebei

AbstractThe Beijing-Tianjin-Hebei region is one of the regions with the most dynamic economies, highest degrees of openness, strongest innovation capacities and largest populations, as well as an important engine driving China’s economic development. Currently, the development of the Beijing-Tianjin-Hebei region faces many difficulties, including an inefficient distribution of regional functions, imbalance in industrial structure, low sophistication, and serious overburdening of resources and the environment. Promoting the overall coordinated development of the region has become an urgent challenge. In this paper, according to the conventions of industrial structure optimization, the three core indicators of regional industrial structure rationalization, sophistication and ecologicalization are constructed. With the help of the grey dynamic correlation model, the three indicators are coupled with the economic growth rate, and the industrial structure optimization index of the Beijing-Tianjin-Hebei region is comprehensively measured. The study shows that rationalization of the industrial structure in the Beijing-Tianjin-Hebei region is increasing but that this trend is not obvious; sophistication of the industrial structure is relatively high and has also been operating at a high level; however, the overall ecological level of the industrial structure in the Beijing-Tianjin-Hebei region is not high and presents the characteristics of high in the middle and low at both ends. In terms of the relationship between industrial structure and economic growth in the Beijing-Tianjin-Hebei region, ecologicalization of the industrial structure has the greatest influence on economic growth, followed by sophistication of the industrial structure, and rationalization of the industrial structure has the weakest influence.

Forecasting China’s per capita energy consumption using dynamic grey model based on ARIMA model

Energy is the cornerstone of social progress, and energy consumption is an important reference data when the government makes energy policies. Therefore, prediction of energy consumption can provide a basis for the formulation of policies. In the traditional grey system theory, the grey input is always regarded as an invariant after determined by the least square method. However, the grey input would be changed along with the change of the internal information in the grey system. As a result, the performance and accuracy of the grey model would be affected by it.Therefore, this paper proposes the ARIMA-b-GM (1,1) model, which uses the ARIMA prediction model to fit and predict the grey input and realize the dynamic change of the grey input. Then the time response sequence of the ARIMA-b-GM (1,1) model is deduced by changing the form of grey differential equation. Finally, the ARIMA-b-GM (1,1) model is applied to predict the per capita energy consumption in China. The results exhibit that ARIMA-b-GM (1,1) model has higher prediction accuracy than GM (1,1) model, NGM (1,1) model and SAIGM (1,1) model.

Forecast of short-term wind power based on a novel hybrid method

Short-term wind power forecasting plays an important role in power generation, because it prevents the power system operation from its uncertain and intermittent nature. This article proposes a novel method for short-term wind power forecasting, which combines the wavelet transform, particle swarm optimization dynamic gray model and Lyapunov exponent prediction method. First, the approach decomposes the wind power curve into the high-frequency and low-frequency curves by wavelet transform, which represent the detail and tendency signals, respectively. Then, we use the proposed particle swarm optimization dynamic gray model to forecast the low-frequency curve with its smooth and periodic outline. Moreover, Lyapunov exponent prediction method is used to predict high-frequency curves, which possess the chaos characteristics. Finally, we obtain the wind power forecasting result from the combination of the predicted low and high frequencies. The experiment of four seasons in an US wind farm validates that the proposed method is effective in solving the short-term wind power forecasting problem. The obtained results, discussed comprehensively, show that the hybrid method has better prediction accuracy than the other methods, such as artificial neural network, persistence, and autoregressive integrated moving average model, with the lowest average mean absolute percentage error is 8.07% and the average root mean square error is 0.8164 over four seasons.

Research on navigation for underwater unmanned vehicle based on dynamic gray filtering method

According to the problem of large platform noise and external disturbance influence and the data may have outliers for UUV navigation, a dynamic grey filtering method based on fractional order operator is proposed. This method does not require prior knowledge and noise statistical properties of UUV system while establishing a dynamic grey model based on fractional operator according to navigation data. The deviation between the grey prediction value and the next navigation sample value is calculated and the data is fused according to the deviation to realize the real-time filtering. The simulation results show that the method is effective and feasible.

Study on Prediction Methods for the Fault State of Rotating Machinery Based on Dynamic Grey Model and Metabolism Grey Model

Rotors and bearings are the key parts of rotating machinery. Mechanical faults will occur easily when rotors and bearings are running for a long time in the condition of high speed and full load. In this paper, first the dynamic grey model and metabolism grey model (MGM) are respectively used to predict the trend of the vibration amplitude of rotors and bearings, and the prediction results are compared. Then based on the root mean square value of the vibration amplitude of rotors and bearings, a back propagation network prediction model of fault feature information is established, which can predict the fault of rotors and bearings in advance. Experiments show that the dynamic grey model can predict both the rising and comprehensive growth trends of the vibration signal amplitude of rotors and bearings. However, the prediction error will increase with an increase of vibration amplitude. Experiments also indicate that the accuracy of prediction based on the MGM is higher than that of dynamic grey model.