摘要
为实现工业产能过剩的精准判别与调控,提出了一种基于替代数据法与多重分形去趋势波动分析的合意工业产能利用率区间估计方法。首先判断原始时序的长程相关性和多重分形特征;然后采用替代数据法与多重分形去趋势波动分析计算出所有重排序列的Hurst指数,据此确定指数序列收敛情况和合意产能利用率区间;最后以煤炭行业为例验证了模型的有效性。结果表明:该方法能够从数据自身演化规律中自适应确定阈值,有效克服了传统统计与经验方法的主观性和缺乏理论依据的局限性;我国煤炭行业的合意产能利用率区间为73.73%~86.23%。该研究为工业产能过剩风险监测与判别提供了量化分析工具,为深化煤炭产能过剩治理提供了决策依据。
To achieve precise identification and control of industrial overcapacity, an estimation method of consensual industrial capacity utilization interval based on Surrogate Data method and Multifractal Detrended Fluctuation Analysis is proposed. Firstly, the long-range correlation and multifractal characteristics of the original time series are judged.Secondly, the Hurst index of all rearranged sequences is calculated by Surrogate Data and Multifractal Detrended Fluctuation Analysis method, and then the consensual industrial capacity utilization interval is determined according to the convergence of exponents. Finally, the coal industry is taken as an example to verify the model. The results show that the method can adaptively determine the threshold value from the evolution law of data itself, and effectively overcome limitations of subjectivity and lack of theoretical basis of the traditional statistical and empirical methods;the consensual capacity utilization interval of China’s coal industry is 73.73%~86.23%. This study provides a quantitative analysis tool for the monitoring and identification of industrial overcapacity risks and provides a decision-making basis for deepening the governance of coal overcapacity.
作者
毛锦琦
王德鲁
Xunpeng Shi
MAO Jinqi;WANG Delu;Xunpeng Shi(School of Economics and Management,China University of Mining and Technology,Xuzhou 221116,China;Ustralia-China Relations Institute,University of Technology Sydney,Ultimo,NSW 2007,Australia)
出处
《运筹与管理》
CSSCI
CSCD
北大核心
2023年第1期233-239,共7页
Operations Research and Management Science
基金
国家自然科学基金资助项目(72074210)
江苏省研究生科研与实践创新计划资助(KYCX22_2683)
中国矿业大学未来科学家计划资助(2022WLKXJ085)。
关键词
产能利用率
合意区间
多重分形去趋势波动分析
替代数据法
capacity utilization
consensual interval
multifractal detrended fluctuation analysis
surrogate data