Search results

Quality management of products is an important part of manufacturing process. One way to manage and assure product quality is to use machine learning algorithms based on relationship among various process steps. The purpose of this paper is to integrate manufacturing, inspection and after-sales service data to make full use of machine learning algorithms for estimating the products’ quality in a supervised fashion. Proposed frameworks and methods are applied to actual data associated with heavy machinery engines.

By following Lenzerini’s formula, manufacturing, inspection and after-sales service data from various sources are integrated. The after-sales service data are used to label each engine as normal or abnormal. In this study, one-class classification algorithms are used due to class imbalance problem. To address multi-dimensionality of time series data, the symbolic aggregate approximation algorithm is used for data segmentation. Then, binary genetic algorithm-based wrapper approach is applied to segmented data to find the optimal feature subset.

By employing machine learning-based anomaly detection models, an anomaly score for each engine is calculated. Experimental results show that the proposed method can detect defective engines with a high probability before they are shipped.

Through data integration, the actual customer-perceived quality from after-sales service is linked to data from manufacturing and inspection process. In terms of business application, data integration and machine learning-based anomaly detection can help manufacturers establish quality management policies that reflect the actual customer-perceived quality by predicting defective engines.

The weapon system of The Navy is the small quantity producing system on multiple kinds. It is consisted of various equipment and the subordinate parts of those which can repair the damaged part. The operating procedure concerning warship's repair parts managed under these systems is as follows. Firstly, if demand of repair parts occurs from warship which is the operating unit of weapon, then the Fleet(the repair & supply support battalion) is in charge of dealing with these requests. If certain request from warship is beyond the battalion's capability, it is delivered directly to the Logistic Command. In short, the repair and supply support system of repair parts can be described as the multi-level support system. The various theoretical researches on inventory management of Navy's repair parts and simulation study that reflects reality in detail have been carried out simultaneously. However, the majority of existing research has been conducted on aircraft and tank's repairable items, in that, the studies is woefully deficient in the area concerning Navy's inventory management. For that reason, this paper firstly constructs the model of consumable items that is frequently damaged reflecting characteristics of navy's repair parts inventory management using ARENA simulation. After that, this paper is trying to propose methodology to analyze optimal inventory level of each supply unit through OptQuest, the optimization program of ARENA simulation.