Andi Cakravastia’s research while affiliated with Bandung Institute of Technology and other places

Background: Accurate inventory management of intermittent spare parts requires precise demand forecasting. The sporadic and irregular nature of demand, characterized by long intervals between occurrences, results in a significant data imbalance, where demand events are vastly outnumbered by zero-demand periods. This challenge has been largely overlooked in forecasting research for intermittent spare parts. Methods: The proposed model incorporates the Synthetic Minority Oversampling Technique (SMOTE) to balance the dataset and uses focal loss to enhance the sensitivity of deep learning models to rare demand events. The approach was empirically validated by comparing the model’s Mean Squared Error (MSE) performance and Area Under the Curve (AUC). Results: The ensemble model achieved a 47% reduction in MSE and a 32% increase in AUC, demonstrating substantial improvements in forecasting accuracy. Conclusions: The findings highlight the effectiveness of the proposed method in addressing data imbalance and improving the prediction of intermittent spare part demand, providing a valuable tool for inventory management.

Background: Container terminal congestion is often measured by the average turnaround time for external trucks. Reducing the average turnaround time can be resolved by controlling the yard crane operation and the arrival times of external trucks (truck appointment system). Because the truck appointment system and yard crane scheduling problem are closely interconnected, this research investigates synchronization between the approaches used in truck appointment systems and yard crane scheduling strategies. Rubber-tired gantry (RTG) operators for yard crane scheduling operations strive to reduce RTG movement time as part of the container retrieval service. However, there is a conflict between individual agent goals. While seeking to minimize truck turnaround time, RTGs may travel long distances, ultimately slowing down the RTG service. Methods: We address a method that balances individual agent goals while also considering the collective objective, thereby minimizing turnaround time. An agent-based simulation is proposed to simulate scenarios for yard crane scheduling strategies and truck appointment system approaches, which are centralized and decentralized. This study explores the combined effects of different yard scheduling strategies and truck appointment procedures on performance indicators. Various configurations of the truck appointment system and yard scheduling strategies are modeled to investigate how those factors affect the average turnaround time, yard crane utilization, and CO2 emissions. Results: At all levels of truck arrival rates, the nearest-truck-first-served (NTFS) scenario tends to provide lower external truck turnaround times than the first-come-first-served (FCFS) and nearest-truck longest-waiting-time first-served (NLFS) scenario. Conclusions: The decentralized truck appointment system (DTAS) generally shows slightly higher efficiency in emission reduction compared with centralized truck appointment system (CTAS), especially at moderate to high truck arrival rates. The decentralized approach of the truck appointment system should be accompanied by the yard scheduling strategy to obtain better performance indicators.

Applying Human Action Recognition (HAR) in manufacturing site to recognize the human assembling tasks, representing as repetitions of human actions, is an emerging research area. However, human unintentional movements or actions beyond the pre-determined tasks are inevitable and cause the difficulty of applying machine learning model for training. Obviously, exhaustively listing all exceptional actions for training a model is not feasible. Therefore, when utilizing a pre-trained model or re-training a model by considering the limited number of exceptional actions leads to the low accuracy of action recognition. To overcome this challenge, in this work, an unsupervised detection framework named Entropy Signal Clustering (ESC) was proposed to detect the exceptional actions from a repetition of actions which are assumed to be basis of assembling tasks. In order to handle frame-basis detection, first, Temporal Self-similarity Matrix (TSM) from the encoder model of RepNet was constructed to represent the similarities of the pair-wise image frames extracted from a video. Second, a calculating process was re-invented to compensate the misleading similarity caused by the padding window on the edges of TSM. Then, an innovative measure of entropy was proposed to create the indication statistics of action similarity. Finally, a clustering-based time-series anomaly detection was proposed to detect the discordance representing the exceptional action in an entropy time-series data against the repetition of actions. To validate the proposed framework, a simulated videos dataset was created. The results show the proposed ESC method is able to obtain accuracies from 85 to 99% and recall of both exceptional (79–100%) and standard of procedure task (92–100%) actions across all demonstration videos comparing with Histogram, Matrix Profile, Local Recurrence Rate based Discord Search (LRRDS), and LRRDS Sampling K-means (LSK) methods.

In recent years, the use of collaborative robots in assembly lines has promised productivity improvement. It provides more alternatives for the assembly line design, which are the alternative resources of the human, robot, or human-robot collaboration (HRC), and the alternative subsets of processes, termed alternative subgraphs, taking advantage of the variety of robotic tools or end-effectors. However, more alternatives make the assembly line balancing problem more complex. This situation is encountered frequently in modern electronics and automotive assembly lines. The contribution of this study is to provide a mathematical model and solution to the assembly line balancing problem that has both HRC and alternative subgraphs, which has not been discussed as an integrated problem in previous literature. To accomplish this optimization problem, a mixed-integer linear programming (MILP) model has been developed to assign tasks to stations and determine the type of resources required while minimizing the cycle time. Practical constraints such as the available number of robots and robotic end-effector types are also considered. Owing to the complexity of the problem, the exact method for MILP is extremely time-consuming for real-world applications. Therefore, a metaheuristic algorithm based on the ant colony optimization (ACO) approach has been developed to solve the problem more efficiently. The results show that the MILP model can obtain optimal solutions for small-sized problems, whereas the ACO algorithm has proven to be a practical solution for medium- to large-sized problems, providing good solutions within an acceptable computation time. The results also show that the presence of alternative subgraphs can give opportunities for better solutions.

This study develops warranty cost models for a warranted product under the lemon laws protection. The product considered in this study is a multi-component system consisting of critical and non-critical components. The Failure of either component can cause the product to fail. The product is declared a lemon if recurrent failures of the critical component occur—i.e., the number of the failures reaches the threshold value, k (e.g., four failures). Furthermore, this study assumes that a failure of the critical component can occur naturally or induced by a failure of the non-critical component. Hence, two types of failures are considered—i.e., a natural failure and an induced failure. Whenever a lemon is declared, the customers can opt for either (i) a refund or (ii) a replacement warranty claim. Hence, this paper provides the warranty cost models for the two cases—(i) refund and (ii) replacement then encounters the optimal lemon law period that minimizes the expected warranty cost rate. The numerical examples are provided to illustrate the expected warranty cost and the optimal lemon law period.

This research is based on a case study of an automotive company with a mixed production line system facing on redesigning layout due to an additional new product in the current facilities for cost improvement. The objective of this research is twofold (i) to fulfil space required for additional machines and (ii) to redesign layout which is the best layout for producing the current and new products. Heuristic approach combining construction and improvement algorithms is used for redesigning a manufacturing mixed production line layout, and this results in four alternative layouts. The four alternative layouts are evaluated comprehensively by using MCDM (Multi Criteria Decision Making) and the multi criteria considered are material handling cost, total re-layout cost, takt time process, numbers of shutdown period for relocation and comply with management policy related with safety. The best layout is the layout fulfilling required space, 1,120 m ² for new processes, and meet with the five criteria considered.