一种稳态库存链的灰色辨别方法

定义了供应链节点企业及整个供应链的“库存变异系数”，并且建立了供应链库存变异的灰色系统模型和“稳态库存链”的判别方法。     

基于改进GM(1,1)-Markov模型的国内生产安全事故预测研究

为准确预测我国生产安全事故发展趋势,本文在传统GM(1,1)模型和马尔科夫模型的基础上,结合二者优点提出改进灰色马尔科夫预测模型,并以2005—2018年全国生产安全事故起数为原始序列探讨了改进模型的实际应用。区别于传统灰色残差修正理论,选取灰色模型预测结果的相对误差作为修正指标,2次应用马尔科夫模型对相对误差状态和误差符号状态进行优化预测,并使用平均相对误差和小概率误差对模型进行精度检验。结果表明,改进GM(1,1)-Markov模型预测结果的相对误差为3.0%,较单一灰色预测模型预测误差减少19.5%,预测精度显著提高,同时预测得到2019年我国生产安全事故起数为479。     

库存路径问题的研究综述

在简要介绍库存路径问题(the inventory routing problem,IRP)的理论与实践意义的基础上,给出IRP问题的定义,并对IRP问题进行描述.通过分析IRP问题具备的特征,将其按照不同的特性进行分类,总结以往国外及国内学者们在求解这一问题时典型的建立模型和求解的方法,并指出该领域目前存在的问题,提出可能的解决办法及其未来的发展方向.     

一种组合预测模型及预测值的模糊分级

基于多元线性回归模型及GM（1，n)模型，给出了一种组合预测模型，进行了组合预测的精度分析及预测值的等级分类，并讨论了其在实际问题中的应用。     

供应链管理环境下的单周期库存控制建模及优化

传统的库存控制理论已经不能够适应供应链管理的要求。在建立了供应链库存成本的组成模型的基础上对供应链管理中的单周期库存控制过程进行了深入的分析，建立了相应的数学模型，求出了最优解。     

基于VMI的供需双方利益分配模型

针对解决实施供应商管理库存策略短期内合作双方的责任与利益不统一的问题,在分析库存成本模型,证明该策略能够降低供应链库存成本的基础上,根据双方优势地位的不同,建立了短期内供需双方利益分配模型,并进行了实证研究.该模型对于建立供应商零售商双方稳定的合作关系具有重要的理论与现实意义.     

基于机器学习的电喷印精度预测方法研究

目的 节省电流体喷射打印精度预测的时间和解决电流体工艺参数的选择问题,达到提高电流体打印的质量和效率的目的。方法 为了对电流体喷射打印精度进行预测,提出有限元模型与机器学习相结合的方法。基于线性回归、支持向量回归和神经网络等机器学习算法建立4种参数与射流直径的关系模型。结果 算法结果表明:支持向量回归和神经网络预测模型的决定系数R²能达到0.9以上,表示模型可信度高;支持向量回归和神经网络预测模型指标都比线性回归预测模型的小。结论 机器学习算法可对电喷印打印精度进行有效预测,预测效率提高了十几倍,节省了精度预测的时间。     

基于GMDH—GM（1，N）的模型对工业增加值预测

工业增加值的准确预测对于政府部制定工业发展政策有重要的作用。本文分别建立了四川省工业增加值的GMDH模型和GM（1,N）模型,并把两者结合起来建立基于GMDH—GM（1,N）的组合预测模型。将组合预测的结果与实际值以及单一的GMDH模型、GM（1,N）模型的结果进行了分析和比较,实证分析结果表明组合预测模型能够提高预测精度,从而为宏观经济预测提供了参考。     

生产制造业物流模型研究

以生产制造业的物流过程为对象，进行了物流管理技术的研究，提出了相应的物流管理模型，该模型对企业物流系统建立有重要的参考价值。     

基于VPMELM的滚动轴承劣化状态辨识方法

针对变量预测模型模式识别方法(VPMCD)仅仅包含几种简单数学模型的问题,所建立的预测模型不足以反映特征值之间的复杂关系;极限学习机(ELM)回归模型是一种复杂且被广泛应用的模型,其模型可以反映特征之间的相互关系。结合极限学习机回归模型和VPMCD方法的优点,提出了一种基于极限学习机的变量预测模型(VPMELM)模式识别方法,并将该方法应用于滚动轴承劣化状态实验中。实验表明,基于VPMELM的辨识方法可以有效地对滚动轴承的劣化状态进行识别。     

Bayesian Approach to Inventory Control of New Parts

The specific real world problem of concern is the inventory control of repair parts for new weapon systems. The initial forecast of demand is based on engineering estimates. This forecast is updated as demand experience accrues. An algorithm implementing a dynamic programming formulation is developed and used as a research tool to obtain insights into how the opportunity to improve the demand forecast impacts the optimum inventory control parameters.     

Rolling horizon,multi-product production planning with chance constraints and forecast evolution for wafer fabs

In this paper, we study production planning models for semiconductor wafer fabrication facilities (wafer fabs) that consider both safety stocks at the finished goods inventory level and workload-dependent lead times. The evolution of demand forecasts over time follows the multiplicative Martingale Model of Forecast Evolution (MMFE) for multiple products and is incorporated into the planning models via shortfall-based chance constraints, permitting the simultaneous determination of production quantities and safety stocks. We study two variants of this formulation, one that considers forecast updates and one that does not. A planning model with workload-dependent lead times that does not consider safety stocks is used for comparison. The performance of the planning models is assessed in a rolling horizon environment using a simulation model of a scaled-down wafer fab. We find that the chance-constrained model with forecast updates outperforms the one without forecast updates with respect to expected service level and profit. Both chance-constrained models outperform the model without safety stocks. These results indicate that considering forecast evolution in production planning models can lead to improved performance by exploiting the advance demand information provided by the forecast updates.     

A stochastic production planning model under uncertain seasonal demand and market growth

This paper proposes a stochastic production planning model for an international enclosure manufacturing company with seasonal demand and market growth uncertainty. The company purchases material and subassembly from overseas and long lead times have been observed. To prevent excess inventory and stockout, the company is required to forecast its demand and project its purchasing decisions and production load to its key suppliers in an effort to reduce risks for both parties. To assist purchasing and production decisions, a two-stage stochastic production planning model that explicitly includes uncertainty is developed with the goal of minimising the total production, inventory, and overtime costs under all scenarios. The model is solved using real data from the company and results have demonstrated the effectiveness of the model compared with various deterministic models. Parametric analyses are performed to derive managerial insights related to issues such as overtime usage, inventory holding costs and the proper selection of scenarios under pessimist, neutral, and optimist outlooks. The model has been implemented and an annual saving of more than $400,000 in inventory cost has been achieved.     

Inventory misplacement and demand forecast error in the supply chain: profitable RFID strategies under wholesale and buy-back contracts

We investigate RFID adoption strategies under wholesale price and buy-back contracts in a supply chain with one manufacturer and one retailer who faces inventory misplacement and demand forecast error. RFID can alleviate the misplacement problem, and can reduce demand forecast error by shortening order lead time. By a newsvendor model, we characterise the optimal contract terms in the supply chain without and with RFID adoption, respectively. We further analyse how the contract terms depend on RFID-related parameters (e.g. salable rate and demand forecast error). We find that both without and with RFID, the wholesale price contract will lead to the double marginalisation problem, while the buy-back contract can coordinate the supply chain. We show that the supply chain adopts RFID if and only if the tagging cost is below a threshold; the threshold is in negative correlation to the demand forecast error. The supply chain is more willing to adopt RFID under the buy-back contract than under the wholesale price contract. RFID adoption can sometimes lessen the double marginalisation problem under the wholesale price contract, improving the supply chain efficiency. A smaller RFID tagging cost or a reduced forecast error do not necessarily lead to higher supply chain efficiency.     

Application of control theoretic principles to manage inventory replenishment in a supply chain

Using uncertain real-time information to update supply chain operational policies creates a need for developing dynamic supply chain management capabilities that increase responsiveness to demand and decrease volatility of the replenishment process (popularly known as the Bullwhip Effect). To this end, we explore the use of control theoretic principles to manage the inventory replenishment process in a supply chain under different forecast situations. We study the use of proportional, proportional-integral and proportional-derivative control schemes to determine the conditions under which specific control actions are beneficial. Analytical models and simulation runs are used to study the trade-off between responsiveness to demand and volatility. Our analysis indicates that using proportional control to manage inventory replenishment is suitable for high forecast error situations. Proportional control along with integral control works well in situations where the forecast bias is relatively higher than the forecast error. Proportional control along with derivative control works best in situations with moderate forecast errors.     

DETERMINISTIC APPROXIMATIONS FOR INVENTORY MANAGEMENT AT SERVICE FACILITIES

We consider the problem of finding optimal inventory policies for a service facility where the demand for inventory occurs during the provision of service (e.g., fixing a car in a repair shop). The paper formulates a model where both the demand and service rates are assumed to be constant and deterministic. Consequently a queue forms only during stockouts. In the first of two models analyzed, the service rate is assumed to be fixed and cannot be controlled by the service facility. The ability to use this simple, deterministic model to approximate systems with probabilistic arrival and/or service distributions is also analyzed. The second model relaxes the assumption of a fixed service rate. Optimal inventory policies are derived under linear costs over ordering, inventory holding, customer waiting, and the service rate.     

Evaluating long-term service performance under short-term forecast updates

Managing product availability in a cost-effective way has always been a major challenge faced by inventory managers. We study the problem of a firm selling a perishable product with short-term demand patterns and a long-term service target using the newsvendor framework. The newsvendor determines his long-term order at the first stage, and revises the order according to a short-term forecast update at the second stage. He also evaluates a long-term service target for his overall performance on product availability across all possible forecast updates. We characterise his optimal inventory policy that minimises the expected inventory cost while meeting the long-term service target. Both in-stock rate and fill rate targets are examined.     

基于极大熵的单周期产品库存模型

研究具有自由需求分布的单周期问题。建立基本库存模型,给出期望利润表达式,运用极大熵准则确定需求的最可几分布,从而建立单周期产品库存模型,并得出最优订货批量。利用算例将该模型与Scarf订货规则和正态分布假设进行比较。结果表明,基于极大熵准则的库存模型能够获得更多的期望利润。     

A stochastic inventory model for an immediate liquidation and price-promotion decision under price-dependent demand

We consider a periodic review stochastic inventory system where the current on-hand inventory exceeds the maximum supply needs in the future. Consequently, one must make an immediate inventory liquidation decision on the liquidation quantity and promotional price with the goal of maximising the overall profit where the demand during the liquidation period (DDLP) is a random variable whose distribution depends on the promotional price. We develop a price-dependent DDLP model and an inventory model for optimising the liquidation quantity and unit promotional price. The model is applicable for general distributions of the DDLP and regular demand (i.e. demand during the future periods following the promotion period). We also investigate four special cases where the DDLP and regular demand are assumed to be either exponential or uniform random variables. The two models that assume the exponential distribution for regular demand can be examined analytically and simplified using the mathematical properties we derive. The additional two models that assume the uniform distribution for regular demand do not have closed-form expressions but can be solved numerically. Some numerical examples are presented for further elaboration of the models and to demonstrate their practical use.     

An efficient procedure for non-stationary inventory control

We present an efficient solution method - Direct Derivative Estimation (DDE) - for computing optimal order-up-to levels for a discrete time non-stationary inventory control model. We generalize a number of non-stationary inventory control models (which underlie larger models of supply chains) that include forecast updates, seasonality, information sharing, and exchange-rate fluctuations. This procedure is different from the existing ones in that it computes, in a recursive manner, the derivative of the cost function and not the cost function itself. It can also handle a much wider variety of fluctuations in the problem parameters. In our computational testing it was found to be considerably faster than Dynamic Programming and Infinitesimal Perturbation Analysis.