Minmin Qiu

A Novel Approach for Process Mining Based on Event Types

Process mining aims at distilling useful knowledge from the execution logs of process models. It has become a vivid research area in recent years. In this paper, a novel approach for process mining based on two event types, i.e., START and COMPLETE, is proposed. Information about the start and completion of tasks can be used to explicitly detect parallelism. The algorithm presented in this paper overcomes some of the limitations of existing algorithms such as the a-algorithm (e.g., short-loops) and therefore enhances the applicability of process mining in practical situations. Based on the completeness of the given event log and the behavior theory of Petri nets, the correctness of the algorithm can be proved theoretically.

A low-carbon production scheduling system considering renewable energy

Climate change is becoming one of the most important challenges facing our generation. Many industries and enterprises have begun steps for carbon emissions reduction and management. Manufacturing and industrial processes produce large amounts of greenhouse gas and use more electricity than any other sector, which push manufacturing enterprises to apply renewable energy to mitigate emissions from their production and operations. This paper addresses a low-carbon production scheduling problem considering renewable energy. A low-carbon production scheduling system architecture is proposed. A mathematical model of the addressed problem is presented with the objective of minimizing the total carbon emissions during the whole planning horizon. A low-carbon production scheduling algorithm of the addressed problem is designed. Computational experiments have demonstrated the proposed low-carbon production scheduling considering renewable energy.

An introduction to IBM general business simulation environment

IBM general business simulation environment (GBSE) is a supply chain simulation tool developed by IBM China Research Lab. It can capture supply chain dynamics with finest level of granularity and provides great insights to a supply chain¿s real operations. GBSE is designed for tactical level decision making; it is proper for supply chain what-if analysis and risk analysis. GBSE implements multiple supply chain processes to considerable details, such as order handling process, inventory control process, manufacturing process, transportation process, procurement process, and planning. The environment is created as a desktop software tool based on Eclipse platform. The backbone framework consists of Presentation Layer, Controller Layer, Service Layer, and Data Layer.

A new hybrid variable-length GA and PSO algorithm in continuous facility location problem with capacity and service level constraints

This paper considers a continuous capacitated facility location problem without a priori knowledge of the desired number of facilities. The demand locations and volume are known to the decision maker. A new hybrid evolutionary algorithm combining variable-length GA (Genetic Algorithm) and PSO (Particle Swarm Optimization) together is proposed to solve the problem. For variable-length GA, the chromosome in the population varies with the number of facilities to be located, and special crossover and mutation operators are designed. For PSO algorithm, it is combined with ATL (Alternative Transporting Location) method to attain the appropriate location of each facility. Furthermore, an external population is adopted to gather the inferior solutions instead of abandoning them simply. This work has been developed as an Eclipse RCP tool and applied in business cases.

A Method and Tool for Process-Centric Supply Chain Transformation

Supply chain transformation is an emerging service area in the market which is offered to help companies in maximizing the performance of their supply chain operations while reducing costs. An end-to-end supply chain transformation includes the improvement from strategic and tactical level, operational level, execution level and implementation level. Business process is the foundation and linkage of the whole supply chain transformation lifecycle. In this paper, we introduce an effort in IBM China Research Lab named On-demand Supply Chain Analytics Resource (OSCAR), which provides comprehensive methodology and tool support for supply chain transformation from a process-centric point of view. The tool provides an end-to-end support for supply chain transformation, which includes business process modeling, business process diagnosis, strategic and tactical decision making, etc. It has been successfully applied in several supply chain transformation projects for validation and hardening.

Impact of Business Service Modes on Distribution Systems: A Reinforcement Learning Approach

In this paper we identify several typical business service modes in a general distribution system composed of a single distributor and multiple retailers. For different service models, the business process can be different and each member of the distribution system may observe different level of information. Each member makes decisions to minimize its long-run-average cost or maximize its profit. A reinforcement learning algorithm is applied to obtain the decision policies and system costs. By comparing the system costs in various business service modes, we show numerically the impact of different business service modes on the distribution system. The results provide managerial insights into actual decision making in distribution systems.

Evaluating the value of collaboration in supply chain through business process simulation

In the background of flat world and widely international collaborations, it becomes critical for supply chain members to collaborate with each other. In this paper, we try to quantify the value of collaboration by improving business processes from the simulation point of view. We discuss different kinds of business process improvement manners, create simulation scenarios with or without collaboration, and analyze the simulation results. With the power of business process simulation, we have the capability to evaluate the benefits of collaboration with consideration of the details of operations and stochastic characters.

A myopic policy based simulation optimization framework in a general decentralized supply chain

Decentralized multi-echelon supply chains are often computationally intractable and difficult to analyze due to the complex network structure and various decision makings. This paper develops a simulation optimization framework for a general decentralized supply chain composed of sup-pliers, plants, distributors and customers. Each facility in the network is under local control and makes decisions based on a myopic policy. The simulation optimization framework is composed of an event simulator, an optimization engine, a system updater and a process controller. The simulation test bed can help the network facilities asymptotically optimize their decisions based on the feed-back during the simulation process, and evaluate the performance of each facility.

Event-driven monitoring and scheduling in express and logistics industry

Express delivery industry is growing rapidly as the result of an explosive growth in the e-commerce, telemarketing and TV home-shopping, especially in developing countries. On the other hand parcel delay, loss and damage become the major challenges of the excessive number of express companies. In this paper we introduce an event-driven shipment monitoring and scheduling system, which utilizes the information flow and material flow together to monitor the events during the shipment lifecycle and detect any exception event. A centralized scheduling engine will generate dynamic routing for the shipment in case of exception. The system can efficiently avoid parcel loss and guarantee parcel service quality.

Quantifying the value of collaboration in supply chain management through business process simulation

In the background of flat world and widely international collaborations, it becomes critical for supply chain members to collaborate with each other. In this paper, we try to quantify the value of collaboration by improving business processes from the simulation point of view. We discuss different kinds of business process improvement manners, create simulation scenarios with or without collaboration, and analyze the simulation results. With the power of business process simulation, we have the capability to evaluate the benefits of collaboration with consideration of details of operations and stochastic characters.