在建设全过程课程思政的大背景下,探讨多维度、全方位的"线性控制系统"课程思政的建设模式.通过挖掘、提炼课程专业知识体系中所蕴含的科学规律,使之与思政教育进行有效结合,有针对性地协同规划课程内容,进一步拓展课程的广度、深度.此外,采用多维度教学手段进行教学支撑与实现,有效利用学习强国平台等线上资源,实现线上线下,课内课外,灵活、多渠道地引导与影响学生.探索建立具有院校特色的"线性控制系统"课程思政教学结构框架,对课程内容和教学方法进行融合、补充与改善,可为其他工科类课程进行课程思政建设提供借鉴与参考.

在突发事件和大数据情景下,建立基于数据流模糊C均值聚类算法的集群式供应链应急物资需求重要度决策算法,有助于辨识集群式供应链子系统应急物资需求的重要程度.针对集群式供应链中各子供应链之间的耦合特性和预测指标的快速变化数据流特征,提出基于长短期记忆网络的集群式供应链应急物资需求动态预测算法,提取集群式供应链多个子系统应急物资需求参数的时序特征,动态地、分布地对互联大系统的应急物资需求不确定性进行系统辨识估计.仿真实验结果表明了基于长短期记忆网络的集群式供应链互联大系统应急物资需求动态预测算法的可行性和精确性.

Based on the analysis of cluster supply chain risk characteristics, starting from the analysis of technical risk dimensions, information risk dimensions, human risk dimensions, and capital risk dimensions, a cluster supply chain risk severity assessment index system is designed. The fuzzy C-means clustering algorithm based on data flow is used to cluster each supply chain, analyze the risk severity of the supply chain, and evaluate the decision of the supply chain risk severity level based on the cluster weights and cluster center range. Based on the analytic hierarchy process, the risk severity of the entire clustered supply chain is made an early warning decision, and the clustered supply chain risk severity early warning level is obtained. The results of simulation experiments verify the feasibility of the decision method for cluster supply chain risk severity, and improve the theoretical support for cluster supply chain risk severity prediction.

In order to solve the problem of optimal scheduling and reasonable allocation of limited materials in a short time after a natural disaster, a clustering supply chain emergency material distribution priority decision algorithm based on density clustering algorithm is proposed. Perform clustering as a factor indicator to determine the priority level of emergency material distribution in each supply chain in the clustered supply chain. Based on the material importance, timeliness, and gap index factors, a fuzzy C-means clustering algorithm for supply chain emergency material demand importance decision algorithm is proposed to classify a variety of emergency materials required in disaster areas when an emergency occurs., And decide the importance of each type of emergency supplies. The results of simulation experiments verify the feasibility of the emergency supply materials scheduling and importance decision-making method for the clustered supply chain. The decision results guarantee the optimal scheduling and allocation of limited supplies in the shortest possible time. And transportation programs provide theoretical support.

With changes in the social and economic environment, more and more small and medium-sized enterprises gather in the supply chain to form industrial clusters. How to customize reasonable prices and maximize the profit of products in cluster supply chain has become an important research topic. This paper is based on the clustering supply chain pricing strategy, mathematical modeling based on the pricing model of Mukhopadhyay economics, and then, the collaborative decision-making algorithm based on the double-layer adaptive genetic algorithm and particle swarm optimization algorithm is used to study the pricing scheme which can ensure the maximum profit of each supply chain and the total profit of the whole cluster supply chain. And study the impact on the optimization plan when consumer preferences change and the price elasticity of demand changes. It can be seen from the experimental results that this research has certain reference value for seeking optimal pricing for cluster supply chains.

Aiming at the unpredictability of cluster supply chain unconventional emergency, this paper proposes a case-based reasoning (CBR) emergency decision-making method for cluster supply chain unconventional emergency based on scenario analysis. In the unconventional emergency scenario, the unconventional emergency scenario knowledge representation structure is constructed based on the pressure-state-response (PSR) model, and then a Bayesian network-based cluster supply chain unconventional emergency scenario analysis network model is created to deduce the characteristic values of emergency decision-making indicators of new cases. The case retrieval algorithm based on the multidimensional cloud model is used for case matching. The weights of indexes are determined based on the entropy weight method. The simulation experiment results verify the effectiveness of the proposed method, which provides theoretical support for the emergency decision-making of unconventional emergency in the cluster supply chain.

The research of the difference measure method for risk probability distribution plays a key role in the early warning decision-making management of retail supply chain unconventional emergency. However, the common difference measure indices are established by the specific density function or distribution law of the risk probability distribution. In Knight uncertain environment, only the moments of the risk probability distribution can be obtained. This study proposes the difference moment measure method of risk probability distribution based on moment generating function and fuzzy data stream clustering for the retail supply chain unconventional emergency. The big data statistical analysis is performed on the risk assessment indices to obtain the moments of the risk probability distribution for unconventional emergency. The difference of moment generating functions for unconventional emergency risk is measured by the distance function in the real vector space of infinite dimensional moments and then the difference between the real distribution and the reference distribution of the risk probability for unconventional emergency is further measured by the moments. The main contribution of this study is that we propose a new difference measure method of risk probability distribution for unconventional emergency based on cloud model method, moment generating function theory, functional function and big data fuzzy statistics technology in Knight uncertain and big date environments, which can overcome the drawbacks of the existing difference measure methods for probability distributions.

Aiming at the composite uncertainty characteristics and high-dimensional data stream characteristics of the evaluation index with both ambiguity and randomness, this paper proposes a emergency severity assessment method for cluster supply chain based on cloud fuzzy clustering algorithm. The summary cloud model generation algorithm is created. And the multi-data fusion method is applied to the cloud model processing of the evaluation indexes for high-dimensional data stream with ambiguity and randomness. The synopsis data of the emergency severity assessment indexes are extracted. Based on time attenuation model and sliding window model, the data stream fuzzy clustering algorithm for emergency severity assessment is established. The evaluation results are rationally optimized according to the generalized Euclidean distances of the cluster centers and cluster microcluster weights, and the severity grade of cluster supply chain emergency is dynamically evaluated. The experimental results show that the proposed algorithm improves the clustering accuracy and reduces the operation time, as well as can provide more accurate theoretical support for the early warning decision of cluster supply chain emergency.

The early warning classification plays an important role in the emergency management of cluster supply chain. This paper proposed the high-dimensional datastream evolutionary clustering algorithm of early warning classification for cluster supply chain emergency based on cloud model. It solved the bottleneck problem of early warning classification of cluster supply chain emergency with the high-dimensional datastream and composite uncertainty characteristics. The cloud model generation algorithm of early warning summary is used to generate the early warning summary data based on the multiple data fusion method. The evolutionary datastream clustering algorithm of early warning classification is used to dynamically forecast the harming degree of cluster supply chain emergency based on time decaying model and sliding window model. Compared to other similar algorithms, the algorithm proposed in this paper increased the classification accuracy by 92.6% while reduced operation time by 66.7%. The algorithm can provide more accurate decision supports for design and implementation of emergency preplan of cluster supply chain emergency. The feasibility of this algorithm has been demonstrated by multiple experiments conducted on the algorithm.

Aiming at the characteristics of high dimension, dynamic condition and parameter self-adaptation for demand forecasting, the demand forecasting model of retail supply chain emergency logistics was created based on NRS-GA- SVM algorithm. The sample attribute index reduction model for emergency logistics demand forecasting was established based on NRS algorithm. The continuous data processing method was adopted. The key influencing factors were extracted more accurately. The dynamic demand forecasting model of emergency logistics was established based on nonlinear support vector machine regression theory and parameter optimization machine learning algorithm in order to get the optimal prediction effect. The numerical experiment results show that preprocessing the indexes with NRS and optimizing parameters with GA can not only improve the accuracy of the emergency logistics demand forecasting results, can but also reduce the execution time of the forecasting model, which promotes the emergency safeguard capability of retail supply chain emergency and verifies the feasibility of emergency logistics demand forecasting model for retail supply chain.

The challenges to the dispatch of emergency material distribution have been posed based on the dynamic of emergency logistics environment, the diversity of emergency material demand and the time-varying of emergency material demand and supplies in chain retail supply chain. The urgent of emergency logistics requires to furthest assure material supplies of the disaster-affected area. It is required that the distribution cost of emergency logistics is minimized in chain retail supply chain. Therefore, this paper created a nonlinear dynamic multi-objective programming model for the emergency material distribution of chain retail supply chain with multi-point rescue, multi-point disaster and multimaterial types. It proposed a robust decision-making algorithm for emergency supplies distribution in chain retail supply chain based on CS-GA to minimize the transportation costs and demand costs of emergency supplies. The feasibility and effectiveness of the models and algorithms are verified by the numerical experiments. The results of the numerical experiments show that the robust decision-making model and algorithm for emergency material distribution improve the efficiency and satisfaction rate of distribution and reduce the emergency distribution cost of chain retail supply chain.

In view of the high-dimensional data stream characteristics of Omni-Channel consumer behavior, the synopsis generation algorithm of the Omni-Channel consumer segmentation was created based on the Omni-Channel customer value. The evolutionary data stream clustering algorithm of Omni-Channel consumer segmentation was proposed based on time attenuation model and sliding window model, which deal with the high-speed flow data. The hierarchical processing framework of evolutionary data stream clustering algorithm can make quick and accurate decisions for the Omni-Channel consumer segmentation. The experiment results show that the algorithm improves the temporal and spatial efficiency, and can cluster independently, which provides decision support for the Omni-Channel retail enterprises to better develop and implement multi-channel marketing strategy.

For the deep uncertainty and large data characteristics of the retail supply chain unconventional emergency, the architecture and design issues of early warning decision-making management system for retail supply chain unconventional emergency were researched based on MAS and cloud computing technology. According to the design principles of early warning decision-making management system, the business intelligence system framework of early warning decision-making for retail supply chain unconventional emergency was created based on cloud computing technology. For the complex adaptation of early warning decision-making management system, the MAS organizational structure of early warning decision-making management system for retail supply chain unconventional emergency was constructed based on the modeling method of multi-agent complex system. In the cloud computing environment, the network topology and data warehouse system architecture were established to realize the acquisition and sharing mechanism of the scene big data in the early warning decision-making management system for retail supply chain unconventional emergency. The results of empirical experiment show that the system can improve the intelligence and accuracy of the early warning decision-making for retail supply chain unconventional emergencies.

Aiming at the profit optimization distribution problem of retail supply chain under emergencies, the retail price and revenue sharing proportion are set as the floating parameters. The profit distribution multi-objective programming model of retail supply chain is created based on revenue sharing contract under the emergency. Cooperation intentions are concluded by the dynamic negotiation. This paper presents a collaborative decision algorithm of retail supply chain profit distribution based on multi-objective symbiotic co-evolutionary genetic algorithm. The multi-objective evolutionary optimization problems of retail supply chain are well studied under emergency, by which the intelligence and precision of multi-objective collaborative decision-making are improved. The numerical experiment results show that the profit distribution multi-objective programming model of retail supply chain under emergency makes profits into balance for both sides and the entire supply chain profit loss into minimization. The feasibility of the collaborative? decision algorithm for retail supply chain profit distribution is verified under emergency.

With the layout of the omni-channel marketing strategy,the number of consumers in the omni-channel witnesses an explosive growth,and the consumer behavior of the omni-channel becomes a research hotspot.However,the consumption data of the omni-channel consumers of the chain retail supply chain is massive and high dimensional.Given the abovementioned features,we propose a co-evolution algorithm to analyze omni-channel consumer behavior in the chain retail supply chain.Taking the advantages of the particle swarm optimization algorithm and adaptive genetic algorithm,the two populations are traversed simultaneously,and the information interaction mechanism is introduced between the two populations,which makes the two populations collaboratively evolve.Empirical research proves that when the collaborative evolution algorithm is applied to association rule mining of omni-channel consumer's consumption data in the chain retail supply chain,the speed of the algorithm is faster,and it can also avoid the local optimum of the genetic algorithm when it is applied alone,and improves the quality of omni-channel consumer behavior association rule mining in the chain retail supply chain.It provides a new method for the study of the omni-channel consumer purchasing behavior.

针对连锁零售供应链多级库存资源的动态优化配置问题,提出了在上层对库存策略和下层对物流分配方案协同寻优的多级库存双层规划模型.借鉴细粒度模型遗传算法的遗传操作具有局部性的特点,模拟微观群体交互作用的局部性,基于细粒度模型遗传算法的Agent群体行为优化算法和基于复杂适应系统涌现机理的协同决策机制,进行连锁零售供应链多级库存协同决策研究.通过算例实验对模型的有效性进行了验证.仿真实验结果表明,通过连锁零售供应链微观个体Agent的群体行为优化,从系统工程的角度,实现了连锁零售供应链多级库存的动态资源优化配置和信息共享,降低了多级库存管理与运营的总成本.

从系统工程的角度定量研究供应链运作模式下多级库存需求水平的预测问题.针对零售供应链系统中事件具有时延和随机并发性的特点,建立了一种基于着色时间Petri网和Agent的零售供应链动态协同需求预测模型.分析了零售供应链中零售企业、分销商和供应商三者各自的实时库存需求预测量及其相互关系.最后以某零售供应链的相关数据对预测模型进行了验证,仿真结果表明,该预测模型可以协调供应链中的各个系统要素,实现动态协同需求预测和信息共享,从而能够为连锁零售供应链多级库存实时控制决策提供参考.

突发事件发生时,如何提高应急物流能力是连锁零售企业亟待解决的问题.将粗糙集理论引入连锁零售企业应急需求的预测中,建立基于粗糙集与支持向量机的连锁零售企业应急需求预测模型.首先利用粗糙集约减数据,剔除冗余信息,然后把它们作为支持向量机的输入矢量来预测应急需求.结果表明,与传统支持向量机模型相比,新的模型预测精度更高,更能有效预测应急需求.

采用复杂适应系统理论和复杂人Agent的行为方式,进行系统节点Agent群体之间的协同进化机制研究.以成本、质量、服务水平三个准则为目标函数,构建供应商系统节点Agent决策模型;以买方选择供应商数量最少为目标函数,构建总部配送中心系统节点Agent决策模型.提出了基于多目标共生型协同进化遗传算法的Agent群体间行为优化算法,通过系统节点Agent群体间的行为优化,巩固了连锁零售供应链上下游企业之间的关系,降低了供应链的总成本.

针对突发事件发生后,商业企业需要调整采购决策,重新进行供应商选择问题,建立了突发事件供应商评价指标体系,该指标体系中既有供应商的基本指标,又存在反映突发事件特性的指标.将层次分析法、模糊综合评判和全排列多边形图示指标法运用到突发事件供应商选择当中,建立了突发事件供应商选择模型.该模型能较好地解决评价指标难以准确统计和量化的问题,合理地解决了单级指标和多级指标同时作为评价指标的权重问题,使选择结果更准确客观.