基于TSO-LS-SVM模型的电煤库存风险评价研究

doi:10.16381/j.cnki.issn1003-207x.2023.1065

Abstract

Abstract:

In the current international pattern characterized by significant changes， adaptations and reorganization， energy issues are no longer simply matters of supply or development， but a comprehensive consideration involving national security and international strategy. However， the recent years' local disparities in energy supply and demand， coupled with electricity shortages in China's energy market， have laid bare the deficiencies in China's coal management. At present， these shortcomings primarily manifest in three key areas： firstly， as a large thermal power generation country， China's electric coal supply risk prevention awareness and response ability is insufficient； secondly， the electric coal stockpile reserve mechanism is not perfect； thirdly， there is a deficiency in suitable risk assessment models. Therefore， to improve China's risk control level in electric coal risk control， especially in electric coal inventory， in addition to strengthening the risk prevention awareness， appropriate risk assessment models should also be constructed and the mechanism for electric coal inventory reserve should be improved. Therefore， the thermal power plant is taken as the research object in this paper， and the risk assessment indexes are established considers the risk factors affecting the management of electric coal inventory from three levels of macro-environment （policy， economy， natural environment and market）， meso-environment （information transmission and enterprise cooperation） and micro-environment （business operation and coal yard condition）. On this basis， by analyzing the advantages and disadvantages of the SVM assessment model， the regularization parameter $λ$ is introduced to prevent the overfitting problem， and the tuna swarm optimization algorithm（TSO）is used to optimize the model regularization parameter $λ$ ， the kernel function parameter $σ$ and other related parameters， and thus the risk combination evaluation model of the tuna swarm optimization algorithm and the least-squares support vector machine （TSO-LS-SVM） is proposed. Finally， the proposed model is applied to 200 electric coal enterprises in China to analyze the examples in the context of reality， and the specific research results are as follows. （1）The indicators are selected from four aspects considering the digitalization background： information effectiveness， information sharing degree， information symmetry and vulnerability of information transmission mechanism， and a combination of quantitative and qualitative methods is used to construct the inventory risk assessment index system of electric coal enterprises. （2） The applicability of the proposed TSO-LS-SVM model in the assessment of electric coal inventory risk is verified through case analysis. The superiority of the proposed method is verified by comparing TSO， whale optimization algorithm （WOA） and particle swarm optimization （PSO）， for it has faster convergence speed， higher accuracy， smaller mean square error， and the best performance in the assessment of coal inventory risk. （3） Sensitivity analysis is conducted on risk factors， and it is found that the top five risk indicators are coal loss， policy opportunities， facility construction， employee quality and information transmission， providing scientific guidance and basis for the proposal of electric coal risk control strategy. Based on the conclusions above， certain management insights are provided for enhancing the risk management and control level of electric coal enterprises， improving the electric coal stockpile reserve mechanism， and ensuring the stable supply of energy.

Key words: electric coal inventory risk, risk assessment, support vector machine（SVM）, tuna swarm optimization algorithm（TSO）

CLC Number:

F272

Yunfeng Chen,Xue Yu,Jicheng Liu, et al. Research on Electric Coal Inventory Risk Assessment Based on TSO-LS-SVM Model[J]. Chinese Journal of Management Science, 2026, 34(2): 164-175.

Figures/Tables 11

混淆矩阵		真实值
混淆矩阵		$X 5$	$X 5 ¯$
预测值	$X 5$	TP=7	FP=0
预测值	$X 5 ¯$	FN=1	TN=32

References 37

[1]	Roberts D， Graves R. Risk assessment myth busters： Defining risk management processes and terminology［J］. IEEE Industry Applications Magazine， 2020， 26（3）： 22-28.
[2]	Hamdi F， Ghorbel A， Masmoudi F. Optimization of supply portfolio in context of supply chain risk management： Literature review［C］//Proceedongs of 2014 International Conference on Advanced Logistics and Transport （ICALT）， Hammamet， Tunisia， May 1-3， IEEE， 2014： 374-379.
[3]	王倩倩. 基于系统动力学的电煤供应链风险管理研究［D］. 北京：华北电力大学， 2020.
	Wang Q Q. Research on risk management of electric-coal supply chain based on System dynamics［D］. Beijing： North China Electric Power University， 2020.
[4]	莫聪颖. 基于CSCOR-RS的煤炭供应链风险识别和评价研究［D］. 淮南：安徽理工大学， 2017.
	Mo C Y. Research on risk identification and evaluation of coal supply chain based on CSCOR-RS［D］. Huainan： Anhui University of Science & Technology， 2017.
[5]	孙林辉，李勋，王新平. 基于AHP-ABC法的煤炭产业链供应链煤源环节风险因素分析［J］. 中国煤炭， 2023， 49（2）： 18-28.
	Sun L H， Li X， Wang X P. Risk factors analysis of coal source link in supply chain of coal industry chain based on AHP-ABC method［J］. China Coal， 2023， 49（2）： 18-28.
[6]	刘平阔. 煤电能源供应链交易稳定匹配及风险管理研究［D］. 北京：华北电力大学， 2016.
	Liu P K. Research on coal-thermal plant transactions stable matching and energy supply chain risk management［D］. Beijing： North China Electric Power University， 2016.
[7]	左晨. 基于电商平台的煤炭供应链金融风险管理研究——以易煤网为例［D］. 南昌：华东交通大学， 2021.
	Zuo C. Research on financial risk management of coal supply chain based on E-commerce platform［D］. Nanchang： East China Jiaotong University， 2021.
[8]	王淑莉，罗国甘，许世朋.火电厂锅炉补给水处理系统调试安全风险防控［J］.江西电力，2022，46（9）： 50-52.
	Wang S L， Luo G G， Xu S P. Prevention and control of safety risk in commissioning of boiler make-up water treatment system in thermal power plant［J］. Jiangxi Electric Power， 2022， 46（9）： 50-52.
[9]	韩威. 火电厂安全风险的精细化管理［J］. 中国设备工程， 2022（21）： 65-67.
	Han W. Refined management of safety risks in thermal power plants［J］. China Plant Engineering， 2022（21）： 65-67.
[10]	柏梦媛. ZB火力发电厂建设项目风险管理研究［D］. 西安：西安电子科技大学， 2021.
	Bai M Y. Study on risk management of ZB thermal power plant construction project［D］. Xi’an： Xidian University， 2021.
[11]	施琦皓，滕舒帆，郭钰渲，等. 基于SPA和Markov的危险化学品道路运输企业风险评价方法研究［J］. 化工安全与环境， 2023， 36（4）： 18-21.
	Shi Q H， Teng S F， Guo Y X， et al. Research on risk assessment method of dangerous chemicals road transportation enterprises based on SPA and Markov［J］. Chemical Safety & Environment， 2023， 36（4）： 18-21.
[12]	杨蕴华，尹冰冰，游春，等. 基于AHP法和灰色关联度法的电网生产技改项目投资风险评价模型研究［J］. 电工技术， 2023（3）： 40-44.
	Yang Y H， Yin B B， You C， et al. Research on investment risk evaluation model of power grid production technical transformation project based on AHP method and grey correlation degree method［J］. Electric Engineering， 2023（3）： 40-44.
[13]	余思勤，刘仲敏. 基于FA-KM-GAHP模型的授信供应商风险的群体共识评价［J］. 上海大学学报（自然科学版）， 2022， 28（6）： 1008-1021.
	Yu S Q， Liu Z M. Risk consensus assessment of credit suppliers based on the FA-KM-GAHP model［J］. Journal of Shanghai University （Natural Science Edition）， 2022， 28（6）： 1008-1021.
[14]	刘平山，曾梓铭. 基于GBDT的医药供应链金融信用风险评价［J］. 会计之友， 2021（16）： 24-31.
	Liu P S， Zeng Z M. Financial credit risk evaluation of pharmaceutical supply chain based on GBDT［J］. Friends of Accounting， 2021（16）： 24-31.
[15]	Dong J， Huo H J. Research on the risk factors of power coal supply in China's shanxi province based on ISM［J］. Journal of Investment and Management， 2015， 4（6）： 363-368.
[16]	Yang S X， Li R Y， Liu Y L， et al. Analysis on electricity-coal quality problems based on trust game model［J］. Applied Mechanics and Materials， 2014， 521： 777-781.
[17]	姚力，郑海峰，单葆国，等. 基于数据驱动机会约束的发电企业电煤采购及库存优化模型［J］. 中国电力， 2023， 56（6）： 176-184.
	Yao L， Zheng H F， Shan B G， et al. An optimization coal procurement and inventory model for power generation enterprises based on data-driven chance constraints［J］. Electric Power， 2023， 56（6）： 176-184.
[18]	刘涛. 电力市场环境下燃煤电厂电煤库存优化的CVaR模型［J］.信息记录材料，2018，19（6）： 189-190.
	Liu T. CVaR model for optimization of coal inventory in coal-fired power plants under electricity market environment［J］. Information Recording Materials， 2018， 19（6）： 189-190.
[19]	贾政豪，朱茳，刘芳，等. 电煤价格波动特性对火力发电行业影响研究——基于多重分形消除趋势分析法的实证研究［J］. 价格理论与实践， 2017（4）： 147-150.
	Jia Z H， Zhu J， Liu F， et al. Effect of coal price factual features on thermal power industry development： A case study based on MF-DFA method［J］. Price （Theory & Practice）， 2017（4）： 147-150.
[20]	Hanczar P， Wawrzyniak D. Operational risk assessment for blockchain solutions in supply chains： A conceptual framework［C］//Proceedings of 35th International Business Information Management Association Conference （IBIMA）， Seville， Spain， April 01-02， 2020.
[21]	Pan W， Miao L. Dynamics and risk assessment of a remanufacturing closed-loop supply chain system using the internet of things and neural network approach［J］. The Journal of Supercomputing， 2023， 79（4）： 3878-3901.
[22]	Brandtner P. Predictive analytics and intelligent decision support systems in supply chain risk management—Research directions for future studies［C］//Proceedings of Seventh International Congress on Information and Communication Technology， London， Singapore，February 21–24， Springer， 2023： 549-558.
[23]	Paul S K， Riaz S， Das S. A conceptual architecture for AI in supply chain risk management［C］//Proceedings of TENCON 2022-2022 IEEE Region 10 Conference （TENCON）. Hong Kong， China，November 1-4， IEEE， 2022： 1-5.
[24]	王静. 协同驱动提升产业链供应链现代化水平的形成机制研究——基于BP-SVM联合优化模型［J］. 中国管理科学， 2023， 31（6）： 196-206.
	Wang J. Study on the formation mechanism of synergistic drive to upgrade the modernization level of industrial chain and supply chain： Based on BP-SVM joint optimization model［J］. Chinese Journal of Management Science， 2023， 31（6）： 196-206.
[25]	杨莲，石宝峰. 基于Focal Loss修正交叉熵损失函数的信用风险评价模型及实证［J］. 中国管理科学， 2022， 30（5）： 65-75.
	Yang L， Shi B F. Credit risk evaluation model and empirical research based on focal loss modified cross-entropy loss function［J］. Chinese Journal of Management Science， 2022， 30（5）： 65-75.
[26]	杨怀珍，胡葛君. 基于事故树与贝叶斯网络的农产品供应链风险评估［J］. 江苏农业科学， 2020， 48（5）： 304-310.
	Yang H Z， Hu G J. Risk assessment of agricultural product supply chain based on fault tree and Bayesian network［J］. Jiangsu Agricultural Sciences， 2020， 48（5）： 304-310.
[27]	秦华礼，祝艺露. 基于RF-1D-CNN的城市地下综合管廊施工安全风险评估［J］. 安全与环境学报， 2023， 23（7）： 2184-2190.
	Qin H L， Zhu Y L. Safety risk assessment of urban underground integrated pipe gallery construction based on RF-1D-CNN［J］. Journal of Safety and Environment， 2023， 23（7）： 2184-2190.
[28]	王宁，田家英，董宁，等. 基于改进SVM的智能电网调控系统实时风险评估与预警技术［J］. 沈阳工业大学学报， 2022， 44（1）： 7-13.
	Wang N， Tian J Y， Dong N， et al. Real-time risk-assessment and early-warning technology of smart grid regulation system based on improved SVM［J］. Journal of Shenyang University of Technology， 2022， 44（1）： 7-13.
[29]	谭海燕. 电煤供应链风险评价研究［J］. 现代商贸工业， 2019， 40（11）： 58-61.
	Tan H Y. Study on risk assessment of coal supply chain［J］. Modern Business Trade Industry， 2019， 40（11）： 58-61.
[30]	崔树银，高攀. 基于层次分析法的电煤供应链风险评估研究［J］.上海电力学院学报，2016，32（1）：51-55+72.
	Cui S Y， Gao P. Research on risk assessment of electricity coal supply chain based on AHP approach［J］. Journal of Shanghai University of Electric Power， 2016， 32（1）： 51-55+72.
[31]	庞景文. “一带一路”背景下中国资源型企业跨国并购风险评价与防控研究［D］. 重庆：重庆大学， 2022.
	Pang J W. Study on the evaluation and prevention and control of cross-border M&A risks of Chinese resource-based enterprises in the context of “the Belt and Road”［D］. Chongqing： Chongqing University， 2022.
[32]	陈洁，吕靖，王尧. 供应链环节划分下的电煤物流风险评估和管控研究［J］. 中国安全科学学报， 2011， 21（2）： 159-164.
	Chen J， Lv J， Wang Y. Risk assessment and control of thermal coal logistics under supply chain link division［J］. China Safety Science Journal， 2011， 21（2）： 159-164.
[33]	马立伟. 基于商务智能中心的煤电联盟协同决策研究［D］. 北京：华北电力大学， 2010.
	Ma L W. Research on collaborative decision-making of coal and power alliance based on business intelligence center［D］. Beijing： North China Electric Power University， 2010.
[34]	Zhou X， Lu H， Ye S. The information transmission and risk contagion effect between green bond market and government bond market in China［J］. Frontiers in Environmental Science， 2023， 11： 1091203.
[35]	董鑫. 燃煤发电企业煤炭供应风险控制方法研究［D］. 北京：华北电力大学， 2014.
	Dong X. Research on risk control methods of coal supply for［D］. Beijing： North China Electric Power University， 2014.
[36]	Guo Y， Mauzerall D L， Lyu Y， et al. Benefits of infrastructure symbiosis between coal power and wastewater treatment［J］. Nature Sustainability， 2022， 5（12）： 1070-1079.
[37]	赵梓州. 电煤库存与船运调度两阶段模型研究［D］. 大连：大连海事大学， 2021.
	Zhao Z Z. A study on two-stage model of electric coal inventory and ship scheduling［D］. Dalian： Dalian Maritime University， 2021.

	一级风险指标	二级风险指标	三级风险指标	指标性质	正向/逆向
电煤库存风险	A₁宏观风险	B₁政策风险	C₁政策亲和度^[29]	定性	－
		B₁政策风险	C₂产业结构调整^[30]	定性	＋
		B₂经济风险	C₃经济增速^[29]	定量	＋
			C₄利率波动幅度^[31]	定量	＋
			C₅外汇波动幅度^[32]	定量	＋
		B₃环境风险	C₆灾害影响程度^[29]	定量	＋
		B₄市场风险	C₇电煤市场价格波动^[30]	定量	＋
			C₈燃油价格波动^[32]	定量	＋
			C₉电煤需求波动^[30]	定量	＋
	A₂中观风险	B₅信息风险	C₁₀信息有效性^[33]	定性	－
			C₁₁信息共享度^[33]	定性	－
			C₁₂信息对称性^[3]	定性	－
			C₁₃信息传导机制脆弱性^[34]	定性	＋
		B₆合作风险	C₁₄合作意愿^[3]	定性	－
			C₁₅合作执行力^[3]	定性	－
			C₁₆企业间信用程度^[33]	定量	－
	A₃微观风险	B₇管理风险	C₁₇库存短缺程度^[29]	定量	＋
			C₁₈煤炭损耗率^[35]	定量	＋
			C₁₉库存计划合理度^[29]	定量	－
			C₂₀设施损坏度（故障率）^[29]	定量	＋
			C₂₁基础设施建设^[36]	定量	－
			C₂₂装卸设备匹配度^[29]	定量	－
			C₂₃库存调度可控性^[37]	定量	－
			C₂₄资金充足度^[3]	定量	－
		B₈煤场风险	C₂₅堆放条件（储存环境）^[29]	定性	－
			C₂₆煤场储量面积^[32]	定量	－
			C₂₇煤场通用性^[32]	定量	－
			C₂₈电厂分布均衡性^[35]	定量	－
			C₂₉煤种分布合理性^[35]	定量	－

模型参数	参数设置
初始种群数量	50
最大迭代次数	50
参数目标上限	[100，100]
参数目标下限	[0.1，0.1]
金枪鱼在初始阶段跟随最佳个体和前一个体的概率	0.7
金枪鱼变异概率	0.05
SVM的核函数	RBF核函数

种群数量	准确率（%）	最低均方误差	最低误差迭代次数
30	82.5	0.1688	50
40	80.0	0.1750	18
50	82.5	0.1610	10
60	80.0	0.1625	22
70	80.0	0.2000	7

模型参数	最优参数设置
初始种群数量	50
最大迭代次数	50
参数目标上限	[300，300]
参数目标下限	[0.1，0.1]
跟随最佳个体和前一个体概率	0.75
变异概率	0.05

风险指标	准确率（%）	最低均方误差	最低误差迭代次数	准确率与原精度差异	均方误差与原精度差异	重要性排序
C1	70.0	0.2437	10	12.5	0.1375	2
C2	82.5	0.1875	44	0.0	0.0813	28
C3	80.0	0.1938	10	2.5	0.0876	23
C4	77.5	0.2250	11	5.0	0.1188	15
C5	77.5	0.2062	35	5.0	0.1000	17
C6	72.5	0.2062	27	10	0.1000	7
C7	80.0	0.2875	28	2.5	0.1813	19
C8	82.5	0.2500	30	0.0	0.1438	25
C9	82.5	0.2125	13	0.0	0.1063	27
C10	75.0	0.2188	21	7.5	0.1126	11
C11	82.5	0.1750	28	0.0	0.0688	29
C12	82.5	0.2687	17	0.0	0.1625	24
C13	70.0	0.2125	38	12.5	0.1063	5
C14	90.0	0.1625	33	7.5	0.0563	12
C15	77.5	0.2125	20	5.0	0.1063	16
C16	75.0	0.2375	25	7.5	0.1313	9
C17	75.0	0.2375	15	7.5	0.1313	10
C18	62.5	0.2813	8	20	0.1751	1
C19	70.0	0.2250	34	12.5	0.1188	4
C20	80.0	0.2125	17	2.5	0.1063	22
C21	70.0	0.2313	10	12.5	0.1251	3
C22	72.5	0.1625	19	10.0	0.0563	8
C23	77.5	0.2313	31	5.0	0.1251	13
C24	72.5	0.2375	28	10	0.1313	6
C25	87.5	0.1625	46	5.0	0.0563	18
C26	87.5	0.2313	20	5.0	0.1251	14
C27	80.0	0.2813	30	2.5	0.1751	20
C28	85.0	0.2437	29	2.5	0.1375	21
C29	82.5	0.2188	42	0.0	0.1126	26

Research on Electric Coal Inventory Risk Assessment Based on TSO-LS-SVM Model

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 37

Related Articles 7

Metrics

Comments

Recommended 0

关键风险因子	因子重要性排序	风险指标	管控措施
C18	1	煤炭损耗率	降低煤炭损耗
C1	2	政策亲和度	抓住政策机遇
C21	3	基础设施建设	加强设施建设
C19	4	库存计划合理度	提高员工素养
C13	5	信息传导机制脆弱性	强化信息传导

[1]	Zhaoge Liu, Xiangyang Li, Xiaohan Zhu. Risk Assessment Model Construction of Urban Rainstorm Cascading Events Based on Risk Feature Tracing [J]. Chinese Journal of Management Science, 2026, 34(1): 268-281.
[2]	Chao Jiang, Tianyuan Zhang, Xiaohua Xia. Multi Cycle Investment and Pricing Joint Decision-making of Real Estate Enterprises in A Stochastic Environment [J]. Chinese Journal of Management Science, 2025, 33(4): 82-94.
[3]	Hao Ding, Yu Su, Dequn Zhou, Siqi Zhao, Yining Zhang. 'Identification-Assessment-Alert' Integration Model of Investment Risks in Renewable Energy Projects: Cases of Belt and Road Countries [J]. Chinese Journal of Management Science, 2025, 33(11): 345-356.
[4]	Xiao-sheng WANG, Xiao-jie AN, Hai-ying GUO. Analysis of Investment Risk of Benefit-sharing Water Saving Management Contract Project [J]. Chinese Journal of Management Science, 2023, 31(9): 196-204.
[5]	DONG Lu-an, YE Xin. Interpretable Credit Risk Assessment Modeling Based on Improved Pedagogical Method [J]. Chinese Journal of Management Science, 2020, 28(9): 45-53.
[6]	LIU Jing-li, LI Jian-ping, XU Wei-xuan, SHI Yong. A Robust Weighted Adaptive L_p LS-SVM Method for Credit Risk Assessment [J]. Chinese Journal of Management Science, 2010, 18(5): 28-33.
[7]	YU Rui-feng, REN Yan-min, WANG Yu, LIU Li-wen. Research on Risk Assessment of Corporate Credit Based on Supply Chain [J]. Chinese Journal of Management Science, 2007, 15(3): 85-92.