A design method of the network for automated transporters mounted on rails is addressed for automated container terminals. In the network design, the flow directions of some path segments as well as routes of transporters for each flow requirement must be determined, while the total transportation and waiting times are minimized. This study considers, for the design of the network, the waiting times of the transporters during the travel on path segments, intersections, transfer points below the quay crane (QC), and transfer points at the storage yard. An algorithm, which is the combination of a modified Dijkstra's algorithm for finding the shortest time path and a queuing theory for calculating the waiting times during the travel, is proposed. The proposed algorithm can solve the problem in a short time, which can be used in practice. Numerical experiments showed that the proposed algorithm gives solutions better than several simple rules. It was also shown that the proposed algorithm provides satisfactory solutions in a reasonable time with only average 7.22% gap in its travel time from those by a genetic algorithm which needs too long computational time. The performance of the algorithm is tested and analyzed for various parameters.

In a semiconductor fab, wafer lots are processed in complex sequences with re-entrants and parallel machines. It is necessary to ensure smooth wafer lot flows by detecting potential disturbances in a real-time fashion to satisfy the wafer lots' demands. This study aims to identify production factors that significantly affect the system’s throughput level and find the best prediction model. The contributions of this study are as follows: (1) this is the first study that applies machine learning techniques to identify important real-time factors that influence throughput in a semiconductor fab; (2) this study develops a test bed in the Anylogic software environment, based on the Intel minifab layout; and (3) this study proposes a data collection scheme for the production control mechanism. As a result, four models (adaptive boosting, gradient boosting, random forest, decision tree) with the best accuracies are selected, and a scheme to reduce the input data types considered in the models is also proposed. After the reduction, the accuracy of each selected model was more than 97.82%. It was found that data related to the machines’ total idle times, processing steps, and machine E have notable influences on the throughput prediction.

In a factory of automobile component primer painting, various automobile parts are attached to overhead hangers in a conveyor line and undergo a series of coating processes. Thereafter, the components are wrapped at a packaging station. The packaging process should be fully balanced by an appropriate sequence of components to prevent the bottleneck effect because each component requires different packaging times and materials. An overhead hanger has a capacity limit and can hold varying numbers of components depending on the component type. Capacity loss can occur if the hanger capacity is not fully utilized. To increase hanger utilization, companies sometimes mix two or more component types on the same hangers, and these hangers are called mixed hangers. However, mixed hangers generally cause heavy workload because different items require additional setup times during hanging and packing processes. Hence, having many mixed hangers is not recommended. A good production schedule requires a small number of mixed hangers and maximizes hanger utilization and packaging workload balance. We show that the scheduling problem is NP-hard and develop a mathematical programming model and efficient solution approaches for the problem. When applying the methods to solve real problems, we also use an initial solution-generating method that minimizes the mixing cost, set a rule for hanging the items on hangers considering eligibility constraint, and decrease the size of tabu list in proportion to the remaining computational time for assuring intensification in the final iterations of the search. Experimental results demonstrate the effectiveness of the proposed approaches.

Our study introduces a drone routing problem in which drones fly to capture photos for surveillance purposes after a disaster. The drones perform observations on nodes and edges representing populated areas and road segments of a network from multiple altitudes. Each target node and edge requires observation at least once with a certain required quality. When the drones fly at a relatively high altitude, they can simultaneously capture low-quality photos and a large number of observed target nodes and edges. However, high-quality photos and narrow observation areas can be captured from a relatively low altitude. Each drone has a limited battery capacity and thus must return to the depot for battery replacement. This study routes the drones to satisfy the required photo quality of all target nodes and edges while minimizing the makespan of the surveillance by all drones. Our study is the first to examine a multiple-drone routing problem while considering flight altitude-dependent observation quality, battery replacement, node and edge combination, and minimizing the makespan. Our problem is formulated as a mixed integer linear programming (MILP) model. Firefly and adaptive-reactive tabu search algorithms are proposed. The latter outperforms the former and obtains better solutions than those in the MILP model for small-sized instances within a given short computation time. INDEX TERMS Adaptive-reactive tabu search, altitude, battery replacement, drone routing, firefly algorithm, photo quality, surveillance.

A fast and huge COVID-19 outbreak causes the necessity for conducting massive testing of potential patients in many areas. The current testing capacities for each hospital are limited by the number of testing kit supplies and working hours of the health officers. Indonesian government states the necessity to deploy mobile laboratories that are equipped with the testing capability to handle the over-demand situation. In our study, we solve the routing problem of several mobile laboratories to maximize the total number of tested persons. Given a network of hospitals, target persons, and dynamic positions of the mobile laboratories, persons are assumed to be able to reach testing locations (hospitals or mobile laboratories) if the distance is within a certain threshold. An assignment rule combined with the transportation problem model is combined to generate effective routes and schedules of the mobile laboratories.