New motor development requires high-speed load testing using dynamo equipment to calculate the efficiency of the motor. Abnormal noise and vibration may occur in the test equipment rotating at high speed due to misalignment of the connecting shaft or looseness of the fixation, which may lead to safety accidents. In this study, three single-axis vibration sensors for X, Y, and Z axes were attached on the surface of the test motor to measure the vibration value of vibration. Analog data collected from these sensors was used in classification models for anomaly detection. Since the classification accuracy was around only 93%, commonly used hyperparameter optimization techniques such as Grid search, Random search, and Bayesian Optimization were applied to increase accuracy. In addition, Response Surface Method based on Design of Experiment was also used for hyperparameter optimization. However, it was found that there were limits to improving accuracy with these methods. The reason is that the sampling data from an analog signal does not reflect the patterns hidden in the signal. Therefore, in order to find pattern information of the sampling data, we obtained descriptive statistics such as mean, variance, skewness, kurtosis, and percentiles of the analog data, and applied them to the classification models. Classification models using descriptive statistics showed excellent performance improvement. The developed model can be used as a monitoring system that detects abnormal conditions of the motor test.

In the case of a die-casting process, defects that are difficult to confirm by visual inspection, such as shrinkage bubbles, may occur due to an error in maintaining a vacuum state. Since these casting defects are discovered during post-processing operations such as heat treatment or finishing work, they cannot be taken in advance at the casting time, which can cause a large number of defects. In this study, we propose an approach that can predict the occurrence of casting defects by defect type using machine learning technology based on casting parameter data collected from equipment in the die casting process in real time. Die-casting parameter data can basically be collected through the casting equipment controller. In order to perform classification analysis for predicting defects by defect type, labeling of casting parameters must be performed. In this study, first, the defective data set is separated by performing the primary clustering based on the total defect rate obtained during the post-processing. Second, the secondary cluster analysis is performed using the defect rate by type for the separated defect data set, and the labeling task is performed by defect type using the cluster analysis result. Finally, a classification learning model is created by collecting the entire labeled data set, and a real-time monitoring system for defect prediction using LabView and Python was implemented. When a defect is predicted, notification is performed so that the operator can cope with it, such as displaying on the monitoring screen and alarm notification.

When developing a new motor, a high-speed load test is performed using dynamo equipment to calculate the efficiency of the developed motor using the collected dynamo data. When connecting the test motor and the dynamo used as a load, abnormal noise and vibration may occur in the test equipment rotating at high speed due to misalignment of the connecting shaft and looseness of the connection, which may lead to a safety accident. In this study, three vibration sensors are attached to the surface of bearing parts of the test motor to measure the vibration value, and statistics such as kurtosis, skewness, and percentiles are obtained in order to clearly express the pattern of the measurement data. With these statistics, machine learning models are developed. The developed model in this way can be used as a diagnostic system that can detect abnormal conditions of the motor test equipment through monitoring the motor vibration data during the motor test.

In the era of the 4th industrial revolution driven by the convergence of ICT(information and communication technology) and manufacturing, research on smart factories is being actively conducted. In particular, the manufacturing industry prefers smart factories that autonomously connect and analyze data. For the efficient implementation of smart factories, it is essential to have an integrated production system that vertically integrates separately operated production equipment and heterogeneous S/W systems such as ERP, MES. In addition, it is necessary to double-verify production data by using automatic data collection technology so that the production process can be traced transparently. In this study, we want to show a case of data-centered integration of a large aircraft parts processing factory that requires high precision, takes a long time, and has the characteristics of processing large raw materials. For this, the components of the data-oriented integrated production system were identified and the connection structure between them was explained. And we would like to share the experience gained through the design and implementation case. The integrated production system proposed in this study integrates internal components based on data, which is expected to serve as a basis for SMEs to develop into an advanced stage, and traces materials with RFID technology.

In the process of cutting large aircraft parts, the tool may be abnormally worn or damaged due to various factors such as mechanical vibration, disturbances such as chips, and physical properties of the workpiece, which may result in deterioration of the surface quality of the workpiece. Because workpieces used for large aircrafts parts are expensive and require strict processing quality, a maintenance plan is required to minimize the deterioration of the workpiece quality that can be caused by unexpected abnormalities of the tool and take maintenance measures at an earlier stage that does not adversely affect the machining. In this paper, we propose a method to indirectly monitor the tool condition that can affect the machining quality of large aircraft parts through real-time monitoring of the current signal applied to the spindle motor during machining by comparing whether the monitored current shows an abnormal pattern during actual machining by using this as a reference pattern. First, 30 types of tools are used for machining large aircraft parts, and three tools with relatively frequent breakages among these tools were selected as monitoring targets by reflecting the opinions of processing experts in the field. Second, when creating the CNC machining program, the M code, which is a CNC auxiliary function, is inserted at the starting and ending positions of the tool to be monitored using the editing tool, so that monitoring start and end times can be notified. Third, the monitoring program was run with the M code signal notified from the CNC controller by using the DAQ (Data Acquisition) device, and the machine learning algorithms for detecting abnormality of the current signal received in real time could be used to determine whether there was an abnormality. Fourth, through the implementation of the prototype system, the feasibility of the method proposed in this paper was shown and verified through an actual example.

In the field of optimization, many studies have been performed on various types of Vehicle Routing Problem (VRP) for a long time. A variety of models have been derived to extend the basic VRP model, to consider multiple truck terminal, multiple pickup and delivery, and time windows characteristics. A lot of research has been performed to find better solutions in a reasonable time for these models with heuristic approaches. In this paper, by considering realtime traffic characteristics in Map Navigation environment, we proposed a method to manage realistic optimal path allocation for the logistics trucks and cargoes, which are dispersed, in order to realize the realistic cargo mixing allowance and time constraint enforcement which were required as the most important points for an online logistics brokerage service company. Then we developed a prototype system that can support above functionality together with delivery status monitoring on Map Navigation environment. First, through Map Navigation system, we derived information such as navigation-based travel time required for logistics allocation scheduling based on multiple terminal multiple pickup and delivery models with time constraints. Especially, the travel time can be actually obtained by using the Map Navigation system by reflecting the road situation and traffic. Second, we made a mathematical model for optimal path allocation using the derived information, and solved it using an optimization solver. Third, we constructed the prototype system to provide the proposed method together with realtime logistics monitoring by arranging the allocation results in the Map Navigation environment.

최적화 분야에서는 VRP(Vehicle Routing Problem)에 대한 많은 연구가 오래전부터 이루어져 왔다. 기본적인 VRP 모형을 확장하여, 단일차고지와 다수차고지 특성, Pickup and Delivery 특성, Time Windows 특성 등을 고려하여 다양한 모형들을 도출되고 있으며 이들에 대한 보다 나은 해를 구하는데 초점이 맞추어져 왔다. 이들 VRP 모형들은 노드 수의 증가에 따른 NP-Hard 특성을 가지고 있기 때문에 최적화에 초점을 맞추기 보다는 Genetic Algorithms, Tabu Search, Simulated Annealing 등의 메타휴리스틱 기법 등을 이용하여 적용할 수 있는 우수한 해를 도출하려 노력을 기울이고 있다. 본 연구에서는 시간제약을 가지는 Multi-Depot Pickup and Delivery 모형을 이용하여 3자물류 기업에서 물류 트럭의 할당 및 이들에 대한 운영 상황 모니터링을 지원할 수 있는 시스템 개발에 초점을 맞추고 있다. 본 연구에서는 먼저 수요기업의 요구사항을 반영하여 가장 중점을 두고자 하는 혼적이 가능하고 시간제약을 반영한 해를 도출하고자 했으며 도출된 해를 기반으로 물류를 트럭에 할당한 후 물류 트럭에 대한 GPS기반의 모니터링 시스템을 제안하고자 한다.

The business process of global third party logistics company is defined as a network of logistics activities which involves the products that are manufactured in the developing countries, such as Vietnam, China and so on, and delivered to North or South American countries via intermediate stopover sites. The third party logistics company usually uses proprietary logistics information system to support the related logistics activities. However, each consignor sometimes may require different business process based on the customer type or characteristics of their products. Therefore, the third party logistics company need to modify their business process to reflect customer’s requirements, resulting in the modification of logistic information systems and additional costs. Therefore, a flexible mechanism is required to efficiently support the various types of requirements by the owners of the products. In this paper, first, we figured out various business rules related to third party global logistics activities. Second, we grouped the identified business rules into business processes, objects, relations, dependency, policy, representations, execution, and resources and further into precondition, postcondition, and invariant based on checking point in time. Furthermore, the categorized rules are classified into inter-activity and intra-activity rules based on the execution range. Third, we proposed a rule syntax to describe the defined rules into scripts which are understood by user and information system together. When each activity is executed, the rule manager checks whether there are rules related with the activity execution. Finally, we developed a prototype rule management system to show the feasibility of our proposed methodology and to validate it with an example.

The market size of plant projects in overseas is so large that domestic EPC project contractors are actively seeking the overseas projects and then trying to meet completion plans since successful fulfillment of these projects can provide great opportunities for them to expand into new foreign markets. International EPC projects involve all of the uncertainties common to domestic projects as well as uncertainties specific to foreign projects including marine transportation, customs, regulations, nationality, culture and so on. When overseas project gets off-schedule, the resulting uncertainty may trigger unexpected exceptions and then critical effects to the project performance. It usually require much more time and costs to encounter these exceptions in foreign sites compared to domestic project sites. Therefore, an exception handling approach is required to manage exceptions effectively for successful project progress in foreign project sites.In this research, we proposed a methodology for prediction and evaluation of exceptions caused by risks in international EPC projects based on sensitivity analysis and Bayesian Networks. First, we identified project schedule risks and related exceptions, which may meet during the fulfillment of foreign EPC projects that is performed in a sequence of engineering, procurement, preparatory manufacture, foreign shipping, construction, inspection and modification activities, and affect project performance, using literature review and expert interviews. The impact of exceptions to the schedule delay were also identified. Second, we proposed a methodology to predict the occurrence of exceptions caused by project risks and evaluate them. Using sensitivity analysis, we can identify activities that critically affect schedule delay and need to focus by priority. Then, we use Bayesian Networks to predict and evaluate exceptions. Third, we applied the proposed methodology to an international EPC project example to validate the proposed approach. Finally, we concluded the research with the further research topics. We expect that the proposed approach can be extended to apply in exception management in project management.

The project schedule risk in the engineering and facility construction industry is increasingly considered as important management factor because the risks in terms of schedule or deadline may significantly affect the project cost. Especially, the project-based operating companies attempt to find the best estimate of the project completion time for use at their proposals, and therefore, usually have much interest in accurate estimation of the duration of the projects. In general, the management of projects schedule risk is achieved by modeling project schedule with PERT/CPM techniques, and then performing risk assessment with simulation such as Monte-Carlo simulation method. However, since these approaches require the accumulated executional data, which are not usually available in project-based operating company, and, further, they cannot reflect various schedule constraints, which usually are met during the project execution, the project managers have difficulty in preparing for the project risks in advance of their occurrence in the project execution. As these constraints may affect time and cost which role as the crucial evaluation factors to the quality of the project result, they must be identified and described in advance of their occurrence in the project management. This paper proposes a Bayesian Net based methodology for estimating project schedule risk by identifying and enforcing the project risks and its response plan which may occur in storage tank engineering and construction project environment. First, we translated the schedule network with the project risks and its response plan into Bayesian Net. Second, we analyzed the integrated Bayesian Net and suggested an estimate of project schedule risk with simulation approach. Finally, we applied our approach to a storage tank construction project to validate its feasibility.

Recently as the manufacturers want competitiveness in dynamically changing environment, they are trying a lot of efforts to be efficient with their production systems, which may be achieved by diminishing unplanned operation stops. The operation stops and maintenance cost are known to be significantly decreased by adopting proper maintenance strategy. Therefore, the manufacturers were more getting interested in scheduling of exact maintenance scheduling to keep smooth operation and prevent unexpected stops. In this paper, we proposedan integrated maintenance approach in injection molding manufacturing line. It consists of predictive and preventive maintenance approach. The predictive maintenance uses the statistical process control technique with the real-time data and the preventive maintenance is based on the checking period of machine components or equipment. For the predictive maintenance approach, firstly, we identified components or equipment that are required maintenance, and then machine parameters that are related with the identified components or equipment. Second, we performed regression analysis to select the machine parameters that affect the quality of the manufactured products and are significant to the quality of the products. By this analysis, we can exclude the insignificant parameters from monitoring parameters and focus on the significant parameters. Third, we developed the statistical prediction models for the selected machine parameters. Current models include regression, exponential smoothing and so on. We used these models to decide abnormal patternand to schedule maintenance. Finally, for other components or equipment which is not covered by predictive approach, we adoptedpreventive maintenance approach. To show feasibility we developed an integrated maintenance support system in LabView Watchdog Agent and SQL Server environment and validated our proposed methodology with experimental data.

The project-based business companies usually have much interest in predicting the expected finish date and related probability of project completion to refer at their proposals for projects. In general, the management of projects schedule risk is achieved by modeling project schedule with PERT/CPM techniques, then performing risk assessment with Monte-Carlo simulation method. However, since these approaches cannot reflect various schedule constraints, the project managers cannot prepare for the project risks in advance of their. This paper proposed a methodology for predicting project schedule risk by identifying and enforcing the constraints which may occur in a storage tank engineering and construction project environment. We applied our approach to a storage tank construction project to validate its feasibility. By using the methodology proposed in this paper, the project schedule risk can be evaluated and predicted more accurately and practically than the PERT/CPM or Monte-Carlo simulation approach.

Small and medium companies have few dedicated employees for process planning and analyzing. They have many defects in their operational processes which result in less productivity. This research analyze a process of small company, which makes a hole and a round for gear parts. We found that the drilling operation is a bootle-neck operation and propose a revised general machine for drilling operation. The legacy drilling operation is performed as follows. First, a operator drills a half hole of a part and turns the part upside down. Then he drills a rest hole of the part. The operation needs more efforts than other operations. Therefore a productivity of the factory depends on that of the drilling operation. We developed a horizontal multi-drilling machine for the drilling operation. The machine has the drilling tool heads and takes three parts and makes a hole at the same time. It eliminates human operation in the middle of drilling, We also developed clamping jig for holding parts tightly. The proposed machine reduces the total operation time and enhances the productivity of the factory. The process capability index also increased from 6.8 to 9.6.