• 인터넷정보학회논문지
• /
• 제21권1호
• /
• pp.127-135
• /
• 2020

비정형 데이터의 수집, 분석 그리고 활용에 대한 필요성이 대두되고 있지만 여전히 비정형 데이터를 효과적으로 활용하지 못하고 있는 실정이다. 본 연구에서는 국내 유수 이동통신 기업의 통신 시설장비 점검 시스템에 기록된 비정형데이터를 분석하여 장비고장 대응과 예방에 적극 활용할 수 있는 기반을 만들고자 하였고, 약 220만 건의 작업일지 데이터를 텍스트 마이닝을 통해 구조화/정형화 하였다. 이를 위해 장비 고장과 관련된 4가지 분석 프레임, 고장인지, 고장원인, 고장대상, 조치결과를 구성하였고 분석 결과로는 크게 3가지의 효율화 방안과 관련한 인사이트를 얻을 수 있었다. 첫 번째로는 신속한 조치를 통한 시간 단축을 도모하고, 두 번째로는 고장장비 Unit 수요를 예측하고, 마지막으로 현장 출동의 최소화를 지원할 수 있을 것으로 기대되었다. 결론적으로, 본 사례연구는 통신시설 장비 고장 대응을 위해 데이터 분석 대상을 정형 데이터뿐만 아니라 장비일지라는 비정형 빅데이터로도 범위를 확장했으며, 이를 분석에 활용하기 위해 처음으로 텍스트 마이닝을 시도를 했다는데 의의를 가진다. 또한 N사는 정형 데이터 뿐 만아니라 년 80만 건씩 축적되던 비정형 데이터의 활용 가치를 확인할 수 있던 기회를 가졌으며, 향후 비정형 데이터의 활용 방안에 대한 발전방향 그리고 추후의 정형 데이터와의 연계 분석 방안 등에 대한 가이드를 확보할 수 있었다.

• 전기학회논문지
• /
• 제57권11호
• /
• pp.1910-1915
• /
• 2008

The load analysis for the distribution system and facilities has relied on measurement equipment. Moreover, load monitoring incurs huge costs in terms of installation and maintenance. This paper presents a new model to analyze wherein facilities load under a feeder every 15 minutes using meter reading data that can be obtained from a power consumer every 15 minute or a month even without setting up any measuring equipment. After the data warehouse is constructed by interfacing the legacy system required for the load calculation, the relationship between the distribution system and the power consumer is established. Once the load pattern is forecasted by applying clustering and classification algorithm of temporal data mining techniques for the power customer who is not involved in Automatic Meter Reading(AMR), a single-line diagram per feeder is created, and power flow calculation is executed. The calculation result is analyzed using various temporal and spatial analysis methods such as Internet Geographic Information System(GIS), single-line diagram, and Online Analytical Processing (OLAP).

• Ocean and Polar Research
• /
• 제36권4호
• /
• pp.455-463
• /
• 2014

This paper presents data from performance tests carried out to assess a manganese nodule crusher. Manganese nodules should be crushed into smaller pieces in order to assure the slurry flow of the lifting system. Both artificial nodules and real manganese nodules are used to evaluate nodule breaking ability of the crusher. The crushing performance of the crusher depends on the flow rate and pressure of the power transmission device. The size of the crushed manganese nodules also depends on the shape of the crushing drum. In this paper, several comparative tests are carried out to evaluate and improve the crushing performance and find the optimal design point of the crusher.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.94-102
• /
• 2022

Construction workers are engaged in many activities that may expose them to serious hazards, such as falling, unguarded machinery, or being struck by heavy construction equipment. Despite extensive research in building information modeling (BIM) for safety management, current approaches, detecting safety issues after design completion, may limit the opportunities to prevent predictable and potential accidents when decisions of building materials and systems are made. In this respect, this research proposes a proactive approach to detecting safety issues from the early design phase. This research aims to explore accident precursors and integrate them into BIM for tracking safety hazards during the design development process. Accident precursors can be identified from construction incident reports published by OSHA using a text mining technique. Through BIM-integrated accident precursors, construction safety hazards can be identified during the design phase. The results will contribute to supporting a successful transition from the design stage to the construction stage that considers a safe construction workplace. This will advance the body of knowledge about construction safety management by elucidating a hypothesis that safety hazards can be detected during the design phase involving decisions about materials, building elements, and equipment. In addition, the proactive approach will help the Architecture, Engineering and Construction (AEC) industry eliminate occupational safety hazards before near-miss situations appear on construction sites.

• 대한안전경영과학회지
• /
• 제2권3호
• /
• pp.129-140
• /
• 2000

Nowadays the role of information systems is getting more and more increased according to the development of information technology. In order to manage complex, various and huge data, it is vital to construct efficient information system. For this effective information system, data have properly to be stored, encoded and represented when needed. This paper presents equipment management information system using wireless application protocol. This system enables us to have remote control of data searching and data management. Also, through the technique of data mining, database resulted from this system can be utilized into expectation and analysis about life-cycle, characteristic, and failure time of equipment, pattern recognition of users, and state of movement, etc.

• Safety and Health at Work
• /
• 제7권1호
• /
• pp.12-17
• /
• 2016

Background: The mining industry is considered as one of the most dangerous and hazardous industries and the need for effective and efficient occupational health and safety management is critical to safeguard workers and the industry. Despite the dangers and hazards present in the mining industry, only few studies have focused on how occupational health and safety and turnover intentions in the mines. Method: The study suing a cross-sectional survey design collected quantitative data from the 255 mine workers that were conveniently sampled from the Ghanaian mining industry. The data collection tools were standardized questionnaires that measured occupational health and safety management and turnover intentions. These scales were also pretested before their usage in actual data collection. Results: The correlation coefficient showed that a negative relationship existed between dimensions of occupational health and safety management and turnover intention; safety leadership (r = -0.33, p < 0.01); supervision (r = -0.26, p < 0.01); safety facilities and equipment (r = -0.32, p < 0.01); safety procedure (r = -0.27, p < 0.01). Among these dimensions, safety leadership and safety facility were significant predictors of turnover intention, (${\beta}=-0.28$, p < 0.01) and (${\beta}=-0.24$, p < 0.01) respectively. The study also found that turnover intention of employees is heavily influenced by the commitment of safety leadership in ensuring the effective formulation of policies and supervision of occupational health and safety at the workplace. Conclusion: The present study demonstrates that safety leadership is crucial in the administration of occupational health and safety and reducing turnover intention in organizations.

• Geomechanics and Engineering
• /
• 제30권4호
• /
• pp.345-352
• /
• 2022

When rock burst occurs, the damaged coal, rock and other fragments can be ejected to the roadway at a speed of up to 10 m/s. It is extremely harmful to personnel and mining equipment, and seriously affects the mining activities. In order to study the energy evolution characteristics, especially kinetic energy, in the process of rock mass failure, this paper first analyzes the energy changes of the rock in different stages under uniaxial compression. The formula of the kinetic energy of rock sample considering the energy from the indenter of the testing machine is obtained. Then, the uniaxial compression tests with different stiffness ratios of the indenter and rock sample are simulated by numerical simulation. The kinetic energy U_d, elastic strain energy U_e, friction energy U_f, total input energy U and surface energy U_θ of crack cracking are analyzed. The results show that: The stiffness ratio has influence on the peak strength, peak strain, U_d, U_e, U_θ, U_f and U of rock samples. The variation trends of strength, strain and energy with stiffness are different. And when the stiffness ratio increases to a certain value, if the stiffness of the indenter continues to increase, it will have no longer effect on the rock sample.

• Geomechanics and Engineering
• /
• 제21권4호
• /
• pp.391-399
• /
• 2020

Brittleness is one of the most important properties of rock which has a major impact not only on the failure process of intact rock but also on the response of rock mass to tunneling and mining projects. Due to the lack of a universally accepted definition of rock brittleness, a wide range of methods, including direct and indirect methods, have been developed for its measurement. Measuring rock brittleness by direct methods requires special equipment which may lead to financial inconveniences and is usually unavailable in most of rock mechanic laboratories. Accordingly, this study aimed to develop a new strength-based index for predicting rock brittleness based on the obtained base form. To this end, an innovative algorithm was developed in Matlab environment. The utilized algorithm finds the optimal index based on the open access dataset including the results of punch penetration test (PPT), uniaxial compressive and Brazilian tensile strength. Validation of proposed index was checked by the coefficient of determination (R²), the root mean square error (RMSE), and also the variance for account (VAF). The results indicated that among the different brittleness indices, the suggested equation is the most accurate one, since it has the optimal R², RMSE and VAF as 0.912, 3.47 and 89.8%, respectively. It could finally be concluded that, using the proposed brittleness index, rock brittleness can be reliably predicted with a high level of accuracy.

• 기술사
• /
• 제19권4호
• /
• pp.11-21
• /
• 1986

Mine drainage from coal mines is mostly acidic, polluted and/or contaminated, even if its quantity has increased substantially during recent days. This causes two kinds of problems arising at mining districts; one is the environmental disruption and the other is insufficient water supply for living, employee's bathing and industrial purposes. In order to mitigate the aforementioned problems, a specific equipment of Korea type for mine drainage purification has been developed and its prototype manufactured, followed by its applicability tests implemented at mine site. The results of the tests indicates that the new equipment developed is much lower than and economical compared to, other existing neutralization facilities at home and abroad in capital investment at installation stage, the consumption of neutralizing chemicals at operation stage and the requirements of installation site. Whangji area where the prototype water treatment equipment is installed has been sustaining a short supply of usable water, especially in dry seasons and supplementing about 40㎥ of water brought from a location farther than 4km in distance to meet water requirements. The prototype water treatment equipment is however considered capable of providing compressor cooling water in sufficient amount from winter season In the future.

• International Journal of Contents
• /
• 제13권2호
• /
• pp.57-65
• /
• 2017

Recently, due to the significance of Industry 4.0, the manufacturing industry is developing globally. Conventionally, the manufacturing industry generates a large volume of data that is often related to process, line and products. In this paper, we analyzed causes of defective products in the manufacturing process using the decision tree technique, that is a well-known technique used in data mining. We used data collected from the domestic manufacturing industry that includes Manufacturing Execution System (MES), Point of Production (POP), equipment data accumulated directly in equipment, in-process/external air-conditioning sensors and static electricity. We propose to implement a model using C4.5 decision tree algorithm. Specifically, the proposed decision tree model is modeled based on components of a specific part. We propose to identify the state of products, where the defect occurred and compare it with the generated decision tree model to determine the cause of the defect.