N.D. Wang

Bio: N.D. Wang is an academic researcher. The author has contributed to research in topics: Genetic algorithm. The author has an hindex of 1, co-authored 1 publications receiving 2 citations.

Optimization of disassembly line balancing using an improved multi-objective Genetic Algorithm

Abstract: Disassembly activities take place in various recovery operations including remanufacturing, recycling, and disposal. Product disassembly is an effective way to recycle waste products, and it is a necessary condition to make the product life cycle complete. According to the characteristics of the product disassembly line, based on minimizing the number of workstations and balancing the idle time in the station, the harmful index, the demand index, and the number of direction changes are proposed as new optimization objectives. So based on the analysis of the traditional genetic algorithm into the precocious phenomenon, this paper constructed the multi-objective relationship of the disassembly line balance problem. The disassembly line balance problem belongs to the NP-hard problem, and the intelligent optimization algorithm shows excellent performance in solving this problem. Considering the characteristics of the traditional method solving the multi-objective disassembly line balance problem that the solution result was single and could not meet many objectives of balance, a multi-objective improved genetic algorithm was proposed to solve the model. The algorithm speeds up the convergence speed of the algorithm. Based on the example of the basic disassembly task, by comparing with the existing single objective heuristic algorithm, the multi-objective improved genetic algorithm was verified to be effective and feasible, and it was applied to the actual disassembly example to obtain the balance optimization scheme. Two case studies are given: a disassembly process of the automobile engine and a disassembly of the computer components.

Optimization approaches for solving production scheduling problem: A brief overview and a case study for hybrid flow shop using genetic algorithms

Abstract: The aim of this paper is to investigate scheduling problems in manufacturing. After a brief introduction to the modelling approach to the scheduling problem, the study focuses on the optimization approach to the scheduling problem. Firstly, the different optimization approaches are categorised and their respective advantages and disadvantages are shown. This is followed by a detailed analysis of the characteristics and applicability of each of the commonly used optimization approaches. Finally, a case study is presented. A mathematical model is developed with the objective of minimising the maximum completion time for a mixed flow shop scheduling problem, and a genetic algorithm is used to solve the problem. The validity of the model is verified through the case study, which can provide a reasonable scheduling solution for actual manufacturing. This provides a reference for the selection and use of methods for solving scheduling problems in practical production.

Analysis of Traffic Accident Based on Knowledge Graph

Abstract: Traffic accident data include multidimensional dynamic and static factors such as “people, vehicles, roads, and environment” at the time of the accident, which is one of the important data sources for improving the traffic safety environment. Based on the case data of traffic accidents and the construction idea of knowledge graph, the knowledge demand, knowledge modeling, knowledge extraction, and knowledge storage of traffic accidents are analyzed in detail. Finally, the traffic accident knowledge graph is constructed. The visualization analysis of accident is carried out from four angles: accident portrait, accident classification, accident statistics, and accident correlation path. The visualized graphic network displayed by the traffic accident knowledge combines human cognition with machine cognition, which improves human’s ability to understand massive and complicated data. The theoretical system of constructing traffic accident knowledge graph has certain reference significance in the follow-up research on the analysis of massive traffic accident data.

Optimization approaches for solving production scheduling problem: A brief overview and a case study for hybrid flow shop using genetic algorithms

Abstract: The aim of this paper is to investigate scheduling problems in manufacturing. After a brief introduction to the modelling approach to the scheduling problem, the study focuses on the optimization approach to the scheduling problem. Firstly, the different optimization approaches are categorised and their respective advantages and disadvantages are shown. This is followed by a detailed analysis of the characteristics and applicability of each of the commonly used optimization approaches. Finally, a case study is presented. A mathematical model is developed with the objective of minimising the maximum completion time for a mixed flow shop scheduling problem, and a genetic algorithm is used to solve the problem. The validity of the model is verified through the case study, which can provide a reasonable scheduling solution for actual manufacturing. This provides a reference for the selection and use of methods for solving scheduling problems in practical production.

An Improved Q-Learning Algorithm for Solving Disassembly Line Balancing Problem Considering Carbon Emission

Abstract: The remanufacturing, recycling, and reusing of waste products are particularly important to solve the problem of the resource shortage. Disassembly is a key step in the recycling process. How to minimize the negative impact of greenhouse gases on the environment has attracted extensive attention. This paper studies the disassembly line balancing problem to minimize the carbon emissions generated in the disassembly process. A Q-learning algorithm in reinforcement learning is applied to solve the disassembly line balancing problem. Through the analysis and comparison with the state-action-reward-state’-action algorithm to address the same real-life cases, it is proved that the Q-learning algorithm has good performance in most cases. In terms of solution speed, the proposed method is faster in both small-scale and large-scale cases.