An optimization model for reverse logistics network under stochastic environment by using genetic algorithm

Recovery of used products has become increasingly important recently due to economic reasons and growing environmental or legislative concern. Product recovery, which comprises reuse, remanufacturing and materials recycling, requires an efficient reverse logistic network. One of the main characteristics of reverse logistics network problem is uncertainty that further amplifies the complexity of the problem. The degree of uncertainty in terms of the capacities, demands and quantity of products exists in reverse logistics parameters. With consideration of the factors noted above, this paper proposes a probabilistic mixed integer linear programming model for the design of a reverse logistics network. This probabilistic model is first converted into an equivalent deterministic model. In this paper we proposed multi-product, multi-stage reverse logistics network problem for the return products to determine not only the subsets of disassembly centers and processing centers to be opened, but also the transportation strategy that will satisfy demand imposed by manufacturing centers and recycling centers with minimum fixed opening cost and total shipping cost. Then, we propose priority based genetic algorithm to find reverse logistics network to satisfy the demand imposed by manufacturing centers and recycling centers with minimum total cost under uncertainty condition. Finally, we apply the proposed model to a numerical example.     

Strategic network design for reverse logistics and remanufacturing using new and old product modules

Establishment of reverse logistics (RL) networks for various original equipment manufacturers (OEM’s) is gaining significant importance. Various green legislations are forcing OEMs to take back their used, end-of-lease or end-of-life products, or products under warranty to minimize wastes and conserve resources. Therefore OEMs have turned to a better design of their products for maximum reuse and recycling and to retrieve back the used products through a network for reuse, remanufacture, recycle or disposal, so that maximum value can be achieved from their used products. However, designing of network points and assigning capacities to them depend not only on the volume of returned products but also on the demand for remanufactured products and the parts of used products. If OEMs are not able to add value to the used product, there would be no incentive to design a complex network.In this paper, a mathematical model for the design of a RL network is proposed. It is assumed that the returned products need to be consolidated in the warehouse before they are sent to reprocessing centres for inspection and dismantling. Dismantled parts are sent for remanufacturing or to the secondary market as spare parts. Recycling and disposal of these modules are also considered in the model. The use of the model is shown through its application in a numerical example.     

碳税影响下再制造物流网络鲁棒优化模型

为了解决不确定环境下低碳再制造物流网络设计的问题,在政府征收企业碳税的情况下,综合考虑网络中再制造产品需求量和废旧产品质量的不确定性以及设施选址和节点间运输路线的决策问题,采用鲁棒优化方法,以碳税成本和物流成本之和最小化为目标,建立了再制造物流网络鲁棒混合线性规划模型。通过案例验证了鲁棒模型的可行性,就税率和不确定参数的变化进行分析,表明鲁棒模型的决策具有实用性和有效性。     

Location based treatment activities for end of life products network design under uncertainty by a robust multi-objective memetic-based heuristic approach

Rapid growth in world population and recourse limitations necessitate remanufacturing of products and their parts/modules. Managing these processes requires special activities such as inspection, disassembly, and sorting activities known as treatment activities. This paper proposes a capacitated multi-echelon, multi-product reverse logistic network design with fuzzy returned products in which both locations of the treatment activities and facilities are decision variables. As the obtained nonlinear mixed integer programming model is a combinatorial problem, a memetic-based heuristic approach is presented to solve the resulted model. To validate the proposed memetic-based heuristic method, the obtained results are compared with the results of the linear approximation of the model, which is obtained by a commercial optimization package. Moreover, due to inherent uncertainty in return products, demands of these products are considered as uncertain parameters and therefore a fuzzy approach is employed to tackle this matter. In order to deal with the uncertainty, a stochastic simulation approach is employed to defuzzify the demands, where extra costs due to opening new centers or extra transportation costs may be imposed to the system. These costs are considered as penalty in the objective function. To minimize the resulting penalties during simulation's iterations, the average of penalties is added to the objective function of the deterministic model considered as the primary objective function and variance of penalties are considered as the secondary objective function to make a robust solution. The resulted bi-objective model is solved through goal programming method to minimizing the objectives, simultaneously.     

基于集成定位-运输路线安排问题的废旧家电逆向回收物流网络优化

针对废旧家电逆向回收物流成本高、效益差而导致其回收率低的问题,提出一种应用离散微粒群智能算法优化废旧家电逆向回收物流网络模型的方法。在系统分析废旧家电逆向回收物流网络结构与要素基础上,构建基于集成定位-运输路线安排问题的废旧家电逆向回收物流网络优化模型,引入随机交换序与部分映射交叉(PMX)算子使离散微粒群优化(DPSO)算法具备良好的全局及局部搜索能力,来对该模型进行智能优化与求解。实例仿真结果表明,通过该优化模型及算法得到的全局最优解具有良好的收敛性和有效性;同时,能有效降低废旧家电逆向回收物流运作总成本。     

Integration of similarity measurement and dynamic SVM for electrically evoked potentials prediction in visual prostheses research

Electrical evoked potentials (EEPs) time series prediction is a novel topic concentrating on reducing the cost of the visual prostheses research. Support vector machine (SVM), a superior neural network algorithm, is a powerful tool for time series forecasting but is insensitive to multivariate analysis. Meanwhile, similarity measurement (SM), a key technology in case-based reasoning, has been applied in a wide variety of fields but is only limited to the point-to-point computation. This paper firstly attempts to take the advantages of SM and SVM to generate a high performance EEPs predictor. Four independent SM metrics, i.e. fuzzy SM, numeric SM, textual SM and interval SM are employed to calculate the similarities between input variables (including electrical stimulation parameter and spatial parameter) and corresponding experimental values. Then SVM is utilized to predict EEPs behavior in terms of the temporal input. Furthermore, we add the similarities and temporal weights into SVM to indicate that recent data from similar experimental cases could provide more information than distant data from dissimilar ones. Due to the dynamic property, the new SVM is called dynamic SVM, i.e. DSVM and the predictor is named SM-DSVM. How to implement the hybrid predictor with grid-search for parameter optimization is illustrated in detail. In the empirical comparison, the predictive performances on 30 hold-out data are used to make comparisons between SM-DSVM and other comparative predictors. Empirical results show that SM-DSVM is feasible and validated for EEPs prediction in visual prostheses research.     

Generalized Sequence-Based and Reverse Sequence-Based Models for Broadcasting Hot Videos

It has been well recognized as an efficient approach for broadcasting popular videos by partitioning a video data stream into multiple segments and launching each segment through an individual channel simultaneously and periodically. Based on the design premises, some recent studies, including skyscraper broadcasting (SkB), client-centric approach (CCA), greedy disk-conserving broadcasting (GDB), and reverse fast broadcasting (RFB) schemes, etc., have been reported. To study the client segment downloading process, this paper first introduces an applicable sequence-based broadcasting model that can be used to minimize the required buffer size. By extending RFB, this paper further proposes a reverse sequence-based broadcasting model, which can generally improve the existing schemes such as SkB, CCA, GDB, and FB in terms of the relaxed client buffer size. To have a deeper understanding on the proposed reverse model, the upper bound of the client buffer requirement is obtained through a comprehensive analysis, which is proved to be much smaller than the conventional sequence model by 25% to 50%. Based on the proposed reverse model, a reverse sequence-based broadcasting scheme is developed for achieving smaller delay than CCA and GDB.     

Developing a bi-objective model of the closed-loop supply chain network with green supplier selection and disassembly of products: The impact of parts reliability and product greenness on the recovery network

Closed-loop supply chain network (CLSCN) design aims to incorporate environmental considerations into the traditional supply chain design by including recycling, disassembly and reuse activities. A CLSCN incorporates the use and reuse of environmentally friendly products and materials supported by the design of an appropriate recovery, disassembly, and refurbishing network. In the design process, a trade-off must often be made between the need to maximize profit and maximize greenness. The latter is considered for several reasons including regulatory requirements, corporate responsibility and corporate image. In this paper, a bi-objective mixed integer programming model is developed and solved for a forward/reverse logistic network including three echelons in the forward direction (suppliers, assembly centers and customer zones) and two echelons in the reverse direction (disassembly and recycling center). A set of Pareto optimal solutions is obtained to show the trade-off between the profit and the greenness objectives. Some useful managerial insights are developed through various computational experiments.     

Business case Roteb: recovery strategies for monitors

Due to the introduction of extended producer responsibility, European Original Equipment Manufacturers (OEMs) are forced to set up a reverse logistic system for their discarded products. As part of this set-up, OEMs or their service providers have to determine strategies for the recovery of these products. This involves determining an optimal degree of disassembly and assigning optimal recovery and disposal options. In this paper, optimisation models presented in some of our earlier work, are applied in a business case. The case concerns the recycling of PC-monitors and was part of a broader pilot project at Roteb (the municipal waste company of Rotterdam, The Netherlands). By using the models, it is shown that the recycling costs can be reduced by about 25%. Additional cost savings are also indicated, resulting in overall savings up to 40%. Also, modelling issues are discussed in relation to models that can be found in the literature and finally directions for further research are pointed out.     

Reverse logistics network design for product reuse,remanufacturing, recycling and refurbishing under uncertainty

With the improvement of the quality of life in human society, the need to use more natural resources is felt more than ever. In this regard, much research has been done on restoring depreciated and consumed products to the supply chain; many factors, including the quality of returned products, can significantly impact how the reverse logistics network will be used. The two-stage stochastic mixed-integer programming model proposed in this paper considers various processes of recovering recyclable products, including reuse, refurbishing, remanufacturing, recycling, and selling spare parts. Also, considering uncertainty on quality and quantity of returned products, product variety, and bill of material are model features. Due to the computational complexity of large-scale problems, such problems require considerable time to solve. To tackle this issue, a hybrid algorithm constructed by a genetic algorithm and branch and cut algorithm (with CPLEX solver) has been introduced, which can significantly reduce the solution time. Finally, the algorithm is applied to a real-world problem to design a reverse logistics network for a small-size laboratory equipment manufacturer.     

Capacitated closed-loop supply chain network design under uncertainty

This study optimizes the design of a closed-loop supply chain network, which contains forward and reverse directions and is subject to uncertainty in demands for new & returned products. To address uncertainty in decision-making, we formulate a two-stage stochastic mixed-integer non-linear programming model to determine the distribution center locations and their corresponding capacity, and new & returned product flows in the supply chain network to minimize total design and expected operating costs. We convert our model to a conic quadratic programming model given the complexity of our problem. Then, the conic model is added with certain valid inequalities, such as polymatroid inequalities, and extended with respect to its cover cuts so as to improve computational efficiency. Furthermore, a tabu search algorithm is developed for large-scale problem instances. We also study the impact of inventory weight, transportation weight, and marginal value of time of returned products by the sensitivity analysis. Several computational experiments are conducted to validate the effectiveness of the proposed model and valid inequalities.     

再制造/制造系统集成物流网络模糊机会约束规划模型

在再制造/制造(R/M)系统集成物流网络中,回收产品的数量具有不确定性.根据这一特点,将各消费区域废旧产品的回收数量看成是模糊参数,提出了该集成物流网络的模糊机会约束规划模型.通过把模型中模糊机会约束清晰化,将模型转化为确定性的混合整数规划模型.利用实例数据,针对不同的置信水平对模型进行分析,其结果为该集成物流网络的设计提供了依据.     

An integrated model for closed-loop supply chain configuration and supplier selection: Multi-objective approach

Reverse logistics consists of all operations related to the reuse of products. External suppliers are one of the important members of reverse logistics and closed loop supply chain (CLSC) networks. However in CLSC network configuration models, suppliers are assessed based on purchasing cost and other factors such as on-time delivery are ignored. In this research, a general closed loop supply chain network is examined that includes manufacturer, disassembly, refurbishing, and disposal sites. Meanwhile, it is managed by the manufacturer. We propose an integrated model which has two phases. In the first phase, a framework for supplier selection criteria in RL is proposed. Besides, a fuzzy method is designed to evaluate suppliers based on qualitative criteria. The output of this stage is the weight of each supplier according to each part. In the second phase, we propose a multi objective mixed-integer linear programming model to determine which suppliers and refurbishing sites should be selected (strategic decisions), and find out the optimal number of parts and products in CLSC network (tactical decisions). The objective functions maximize profit and weights of suppliers, and one of them minimizes defect rates. To our knowledge, this model is the first effort to consider supplier selection, order allocation, and CLSC network configuration, simultaneously. The mathematical programming model is validated through numerical analysis.     

基于会话关联的软件网络通信行为分析技术

针对软件网络通信过程,提出一种基于会话关联的逆向分析方法,该方法首先对软件产生的网络通信流量和软件执行的应用程序编程接口(API)序列分别进行会话还原,再对还原的会话进行会话关联,为软件网络行为分析中的基于网络流量的分析方法和基于执行轨迹的分析方法建立了直接映射。设计并实现了相关的会话关联系统,并在此系统上进行了函数调用链的提取,使针对软件网络通信过程的分析更快捷。     

不确定环境下的再制造闭环物流网络优化

考虑废旧产品回收数量、回收质量、再生产品需求量的不确定性以及废弃处理中心的选址等多重因素,构建单产品、多周期的再制造闭环物流网络优化设计模型,运用云遗传算法来确定物流网络中各设施的数量、位置、规模以及各设施间的合理物流分配量,使得在整个运营周期的净收益最大。通过算例来验证该模型的有效性。     

Variable neighborhood search for the bi-objective post-sales network design problem: A fitness landscape analysis approach

Post-sales services are important markets in electronics industry due to their impact on marginal profit, market share, and their ability to retain customers. In this study, designing a multi-product four-layer post-sales reverse logistics network operated by a 3PL is investigated. A bi-objective MILP model is proposed to minimize network design costs as well as total weighted tardiness of returning products to customers. To solve the proposed model, a novel multi-start variable neighborhood search is suggested that incorporates nine neighborhood structures and three new encoding–decoding mechanisms. In particular, a fitness landscape measure is employed to select an effective neighborhood order for the proposed VNS. Extensive computational experiments show the effectiveness of the proposed heuristic and the three encoding–decoding mechanisms. The proposed method finds significantly better Pareto optimal sets in comparison with the original Priority method based on the number and the quality of obtained Pareto optimal solutions. In addition, it shows high efficiency by finding near-optimal solutions for the single objective versions of the problem.     

Sentiment analysis of tweets using a unified convolutional neural network‐long short‐term memory network model

Sentiment analysis focuses on identifying and classifying the sentiments expressed in text messages and reviews. Social networks like Twitter, Facebook, and Instagram generate heaps of data filled with sentiments, and the analysis of such data is very fruitful when trying to improve the quality of both products and services alike. Classic machine learning techniques have a limited capability to efficiently analyze such large amounts of data and produce precise results; they are thus supported by deep learning models to achieve higher accuracy. This study proposes a combination of convolutional neural network and long short‐term memory (CNN‐LSTM) deep network for performing sentiment analysis on Twitter datasets. The performance of the proposed model is analyzed with machine learning classifiers, including the support vector classifier, random forest (RF), stochastic gradient descent (SGD), logistic regression, a voting classifier (VC) of RF and SGD, and state‐of‐the‐art classifier models. Furthermore, two feature extraction methods (term frequency‐inverse document frequency and word2vec) are also investigated to determine their impact on prediction accuracy. Three datasets (US airline sentiments, women's e‐commerce clothing reviews, and hate speech) are utilized to evaluate the performance of the proposed model. Experiment results demonstrate that the CNN‐LSTM achieves higher accuracy than those of other classifiers.     

A gray correlation based Bayesian network model for fault source diagnosis of multistage process – Small sample manufacturing system

Fault source diagnosis methodology is one of the key technologies of quality control and assurance for multi-source & multi-stage manufacturing processes, especially in small sample manufacturing systems. By analyzing the existing research on fault source diagnosis methods, a Bayesian network-based methodology is proposed. Gray correlation theory and mechanism analysis method are used in the process of Bayesian network model construction to reduce the dependence of sample data size for structure learning in the process of small sample manufacturing of complex products. In addition, two fault source diagnosis methods based on manufacturing principle analysis and reverse Bayesian network respectively are proposed. The strategy of the combined use of the two methods in the actual manufacturing scenes is given to cope with the fault source diagnosis scenario in the real manufacturing process. In the end, an example from an actual factory is provided to validate the effectiveness and efficiency of the proposed model and methodologies.     

Synthesis and optimization of the recovery route for residual products under uncertain product demand

The present work describes an optimization model for managing the recovery of residual products that originate at industrial plants. The framework for the proposed general network superstructure, where all possible process transformations, storage, transports and auxiliary operations are accounted for, is modeled using a maximal state task network representation. This framework is combined with the evaluation of a set of environmental impacts, quantified by metrics (for air, water pollution, etc.) through the minimum environment impact analysis methodology and is associated with waste generation at utility production and transportation levels. The final model is described as a mixed-integer linear programming model, which, once solved, is able to suggest the optimal processing and transport routes, while optimizing a given objective function and meeting design and environmental constraints. For each solution obtained, a stochastic flexibility index is computed, allowing for the drawing of trade-off curves for investment decision support.     

A bi-objective reverse logistics network analysis for post-sale service

Reverse logistics, induced by various forms of return, has received growing attention throughout this decade. Reverse logistics network design is a major strategic issue. This paper addresses the analysis of reverse logistic networks that deal with the returns requiring repair service. A problem involving a manufacturer outsourcing to a third-party logistics (3PLs) provider for its post-sale services is proposed. First, a bi-objective optimization model is developed. Two objectives, minimization of the overall costs and minimization of the total tardiness of cycle time, are addressed. The facility capacity option at each potential location is treated as a discrete parameter. The purpose is to find a set of non-dominated solutions to the facility capacity arrangement among the potential facility locations, as well as the associated transportation flows between customer areas and service facilities. Then, a solution approach is designed for solving this bi-objective optimization model. The solution approach consists of a combination of three algorithms: scatter search, the dual simplex method and the constraint method. Finally, computational analyses are performed on trial examples. Numerical results present the trade-off relationship between the two objectives. The numerical results also show that the optimization for the first objective function leads to a centralized network structure; the optimization for the second objective function results in a decentralized network structure.