During the shift from gasoline vehicles to electric ones, auto parts manufacturing companies have realized the importance of improvement in the manufacturing process that does not require any layout changes nor extra investments, while maintaining their current production rate. Due to these reasons, for the auto part manufacturing company, I-company, this study has developed the simulation model of the PUSH system to conduct a process analysis in terms of production rate, WIP level, and logistics work’s utilization rate. In addition, this study compares the PUSH system with other three manufacturing systems -KANBAN, DBR, and CONWIP- to compare the performance of these production systems, while satisfying the company’s target production rate. With respect to lead-time, the simulation results show that the improvement of 77.90% for the KANBAN system, 40.39% for the CONWIP system, and 69.81% for the DBR system compared to the PUSH system. In addition, with respect to WIP level, the experimental results demonstrate that the improvement of 77.91% for the KANBAN system, 40.41% for the CONWIP system, and 69.82% for the DBR system compared to the PUSH system. Since the KANBAN system has the largest impacts on the reduction of the lead-time and WIP level compared to other production systems, this study recommends the KANBAN system as the proper manufacturing system of the target company. This study also shows that the proper size of moving units is four and the priority allocation of bottleneck process methods improves the target company’s WIP and lead-time. Based on the results of this study, the adoption of the KANBAN system will significantly improve the production process of the target company in terms of lead-time and WIP level.

The important thing in the field of deep learning is to find out the appropriate hyper-parameter for image classification. In this study, the main objective is to investigate the performance of various hyper-parameters in a convolutional neural network model based on the image classification problem. The dataset was obtained from the Kaggle dataset. The experiment was conducted through different hyper-parameters. For this proposal, Stochastic Gradient Descent without momentum (SGD), Adaptive Moment Estimation (Adam), Adagrad, Adamax optimizer, and the number of batch sizes (16, 32, 64, 120), and the number of epochs (50, 100, 150) were considered as hyper-parameters to determine the losses and accuracy of a model. In addition, Binary Cross-entropy Loss Function (BCLF) was used for evaluating the performance of a model. In this study, the VGG16 convolutional neural network was used for image classification. Empirical results demonstrated that a model had minimum losses obtain by Adagrad optimizer in the case of 16 batch sizes and 50 epochs. In addition, the SGD with a 32 batch sizes and 150 epochs and the Adam with a 64 batch sizes and 50 epochs had the best performance based on the loss value during the training process. Interestingly, the accuracy was higher while performing the Adagrad and Adamax optimizer with a 120 batch sizes and 150 epochs. In this study, the Adagrad optimizer with a 120 batch sizes and 150 epochs performed slightly better among those optimizers. In addition, an increasing number of epochs can improve the performance of accuracy. It can help to create a broader scope for further experiments on several datasets to perceive the suitable hyper-parameters for the convolutional neural network. Dataset: https://www.kaggle.com/c/dogs-vs-cats/data

This paper develops an algorithm to determine the batch size of the batch process in real time for improving production and efficient control of production system with multiple processes and batch processes. It is so important to find the batch size of the batch process, because the variability arising from the batch process in the production system affects the capacity of the production. Specifically, batch size could change system efficiency such as throughput, WIP (Work In Process) in production system, batch formation time and so on. In order to improve the system variability and productivity, real time batch size determined by considering the preparation time and batch formation time according to the number of operation of the batch process. The purpose of the study is to control the WIP by applying CONWIP production system method in the production line and implements an algorithm for a real time batch size decision in a batch process that requires long work preparation time and affects system efficiency. In order to verify the efficiency of the developed algorithm that determine the batch size in a real time, an existed production system with fixed the batch size will be implemented first and determines that batch size in real time considering WIP in queue and average lead time in the current system. To comparing the efficiency of a system with a fixed batch size and a system that determines a batch size in real time, the results are analyzed using three evaluation indexes of lead time, throughput, and average WIP of the queue.

This paper deals with the picking batch size which a bi-directional carousel system can be feasible. The items that customers order are retrieved from the bins of carousel with batch size. The mathematical equations representing rotary travel distance and retrieval lead time to pick a given batch size are derived. Rotary travel distance represents the distance which carousel system rotates to retrieve items in a batch. The bi-directional carousel system rotates to minimize the travel distance in retrieving the items in a batch. Rotary travel distance and retrieval lead time are analyzed for the batch size through the simulation approach. From the simulation, the retrieval batch size that carousel system can be feasible is obtained. A numerical example is shown to explain the solution procedure.

This paper is to analyze the picking lead time for picking batch size in a warehouse system and to get minimum picking batch size that is the warehouse system feasible. The warehouse system consists of aisles and racks, which two racks face each other through aisle. The products are picked from the storage locations by batch size. The probability that items are picked in the each row of the rack in the aisle for order picking activity is derived. The picking lead time for picking batch size is the time passed from the first picking location to arrival at starting location in aisle picking all items included in a batch size. The picking lead time for picking batch size in an aisle is analyzed. The picking lead time for picking batch size in the whole warehouse system is obtained. The warehouse system is feasible if all items that customers order are picked from the storage locations for same period. The picking batch size that is the warehouse system feasible is obtained. The problem is analyzed, a solution procedure is developed, and a numerical example is shown to explain the problem.