• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.2
• /
• pp.84-90
• /
• 2022

Machine tool state monitoring is a process that automatically detects the states of machine. In the manufacturing process, the efficiency of machining and the quality of the product are affected by the condition of the tool. Wear and broken tools can cause more serious problems in process performance and lower product quality. Therefore, it is necessary to develop a system to prevent tool wear and damage during the process so that the tool can be replaced in a timely manner. This paper proposes a method for diagnosing five tool states using a deep learning-based hierarchical convolutional neural network to change tools at the right time. The one-dimensional acoustic signal generated when the machine cuts the workpiece is converted into a frequency-based power spectral density two-dimensional image and use as an input for a convolutional neural network. The learning model diagnoses five tool states through three hierarchical steps. The proposed method showed high accuracy compared to the conventional method. In addition, it will be able to be utilized in a smart factory fault diagnosis system that can monitor various machine tools through real-time connecting.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.603-605
• /
• 2021

With the expansion of the indoor service-providing robot market and the electrification of automobiles, research on autonomous driving is being actively conducted. In general, in the case of outside, the location is mainly recognized through GPS, and location positioning is performed indoors using technologies such as WiFi, UWB (Ultra-Wide Band), VLP, LiDAR, and Vision. In this paper, we introduce a system for location-positioning using LED lights with different color temperatures in an indoor environment. After installing LED lights in a simulated environment such as a tunnel, it was shown that information about the current location can be obtained through the analysis of chromaticity values according to location. Through this, it is expected to be able to obtain information about the location of the vehicle in the tunnel and the movement of the device in a room such as a warehouse or a factory.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.150-153
• /
• 2022

This paper reports a technique that automatically extracts object shapes through Dense-Net, and subsequently, detects the objects using Mask R-CNN in a manufacturing site, in which workers and objects are mixed. It is based on the customized factory dataset by targeting workers, machines, tools, control boxes, and products as the objects. Mask R-CNN supports multi-object recognition as a well-known object recognition method, while Dense-Net effectively extracts a feature from multiple and overlapping objects. After immediate implementation using the two technologies, the object is naturally extracted from a still image of the manufacturing site to describe image. Afterwards, the result is planned to be used to detect workers' abnormal behavior by adding a label on the objects.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.75-84
• /
• 2020

Modular construction is a construction method whereby prefabricated volumetric units are produced in a factory and are installed on site to form a building block. The construction productivity can be substantially improved by the manufacturing and assembly of standardized modular units. 3D printing is a computer-controlled fabrication method first adopted in the manufacturing industry and was utilized for the automated construction of small-scale houses in recent years. Implementing 3D printing in the fabrication of modular units brings huge benefits to modular construction, including increased customization, lower material waste, and reduced labor work. Such implementation also benefits the large-scale and wider adoption of 3D printing in engineering practice. However, a critical issue for 3D printed modules is the loading capacity, particularly in response to horizontal forces like wind load, which requires a deeper understanding of the building structure behavior and the design of load-bearing modules. Therefore, this paper presents the state-of-the-art literature concerning recent achievement in 3D printing for buildings, followed by discussion on the opportunities and challenges for examining 3D printing in modular construction. Promising 3D printing techniques are critically reviewed and discussed with regard to their advantages and limitations in construction. The appropriate structural form needs to be determined at the design stage, taking into consideration the overall building structural behavior, site environmental conditions (e.g., wind), and load-carrying capacity of the 3D printed modules. Detailed finite element modelling of the entire modular buildings needs to be conducted to verify the structural performance, considering the code-stipulated lateral drift, strength criteria, and other design requirements. Moreover, integration of building information modelling (BIM) method is beneficial for generating the material and geometric details of the 3D printed modules, which can then be utilized for the fabrication.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.43-52
• /
• 2023

Rubber produced by rubber companies is subjected to quality suitability inspection through rheometer test, followed by secondary processing for automobile parts. However, rheometer test is being conducted by humans and has the disadvantage of being very dependent on experts. In order to solve this problem, this paper proposes a deep learning-based rheometer quality inspection system. The proposed system combines LSTM(Long Short-Term Memory) and CNN(Convolutional Neural Network) to take advantage of temporal and spatial characteristics from the rheometer. Next, combination materials of each rubber was used as an auxiliary input to enable quality conformity inspection of various rubber products in one model. The proposed method examined its performance with 30,000 validation datasets. As a result, an F1-score of 0.9940 was achieved on average, and its excellence was proved.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.151-161
• /
• 2024

In this paper, we develop 'the Danger Map' of a workplace to identify risk and harmful factors by analyzing images of each process within the manufacturing plant site using artificial intelligence (AI). We proposed a system that automatically derives 'the risk and safety levels' based on the frequency and intensity derived from this Danger Map in accordance with actual field conditions and applies them to similar manufacturing industries. In particular, in the traditional evaluation method of manually evaluating the risk of a workplace using Excel, the risk level for each risk and harmful factor acquired from the video is automatically calculated and evaluated to ensure safety through the system and calculate the safety level, so that the company can take appropriate actions accordingly. and measures were prepared. To automate safety calculation and evaluation, 'Heinrich's law' was used as a model, and a 5X4 point evaluation scale was calculated for risky behavior patterns. To demonstrate this system, we applied it to a casting factory and were able to save 2 people the time and labor required to calculate safety each month.

• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.6
• /
• pp.47-59
• /
• 2017

Korean Economy has been developed by the Korean Government's Support for the Large-sized Firms. This Government Policy causes the Polarization between Large-sized and Micro-sized Firms Aggravated. Micro-sized Firms are distributed over the Whole Industry Area, and can also cause the Economic Crisis If They are crashed down. Therefore Government Policy for the Micro-sized Manufacturing Industry is very Important Issue. This Paper Focused on the Analysis of Current Status for the Shoes Micro Manufacturing Industry. For the Effective Analysis, This Paper uses the Statistical Data Open to the Public and also conducts the Survey for the Micro-sized Firms in Busan. Statistical Program is used for Analyzing the Collected Data and the Major Findings are as Follows. First, Shoes Industry is led by the Micro and Small & Medium sized Firms rather than the Large-sized. And the Micro-sized Firms are getting the High Rate among the Whole Shoes Industry. Busan is heavily populated Area as the Origin of Shoes Industry. Second, even though Most of the Owner of the Micro-sized Firms have the High Technology Skill Level, Worker's Aging Phenomenon gets Worse and causes the Technology Handing down to the Next Generation Difficult. Third, Because the Factory Facility of the Micro-sized Firms is Dirt and Unstable, the Modernized Manufacturing Infrastructure such as the Apartment Factory Facility is Necessary. Forth, as the Micro-sized Firms which have the Intangible Asset such as Patent is Few, the Government Policy for Encouraging the Patent Application is strongly Needed. Fifth, Entrepreneurship and Collaboration Mind between Micro-sized Firms are Lacked, so Establishment of the Cooperative Union is required. Finally, the Effort for the Systemic Planning for the Management is lacked, and the Introduction of the Management Innovation is strongly needed. The Limitation and Future Research Direction is also discussed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.10
• /
• pp.3873-3879
• /
• 2010

Home service robot are not working in the fixed task such as industrial robot, because they are together with human in the same indoor space, but have to do in much more flexible and various environments. Most of them are developed on the base of the wheel-base mobile robot in the same method as a vehicle robot for factory automation. In these days, for holonomic system characteristics, omni-directional wheels are used in the mobile robot. A holonomicrobot, using omni-directional wheels, is capable of driving in any direction. But trajectory control for omni-directional mobile robot is not easy. Especially, azimuth control which sensor uncertainty problem is included is much more difficult. This paper develops trajectory controller of 3-wheels omni-directional mobile robot using fuzzy azimuth estimator. A trajectory controller for an omni-directional mobile robot, which each motor is controlled by an individual PID law to follow the speed command from inverse kinematics, needs a precise sensing data of its azimuth and exact estimation of reference azimuth value. It has imprecision and uncertainty inherent to perception sensors for azimuth. In this paper, they are solved by using fuzzy logic inference which can be used straightforward to perform the control of the mobile robot by means of the fuzzy behavior-based scheme already existent in literature. Finally, the good performance of the developed mobile robot is confirmed through live tests of path control task.

• Geomechanics and Engineering
• /
• v.8 no.6
• /
• pp.859-872
• /
• 2015

Pebble matrix filtration (PMF) is a water treatment technology that can remove suspended solids in highly turbid surface water during heavy storms. PMF typically uses sand and natural pebbles as filter media. Hand-made clay pebbles (balls) can be used as alternatives to natural pebbles in PMF treatment plants, where natural pebbles are not readily available. Since the high turbidity is a seasonal problem that occurs during heavy rains, the use of newly developed composite clay balls instead of pure clay balls have the advantage of removing other pollutants such as natural organic matter (NOM) during other times. Only the strength properties of composite clay balls are described here as the pollutant removal is beyond the scope of this paper. These new composite clay balls must be able to withstand dead and live loads under dry and saturated conditions in a filter assembly. Absence of a standard ball preparation process and expected strength properties of composite clay balls were the main reasons behind the present study. Five different raw materials from industry wastes: Red Mud (RM), Water Treatment Alum Sludge (S), Shredded Paper (SP), Saw Dust (SD), and Sugar Mulch (SM) were added to common clay brick mix (BM) in different proportions. In an effort to minimize costs, in this study clay balls were fired to $1100^{\circ}C$ at a local brick factory together with their bricks. A comprehensive experimental program was performed to evaluate crushing strength of composite hand-made clay balls, using uniaxial compression test to establish the best material combination on the basis of strength properties for designing sustainable filter media for water treatment plants. Performance at both construction and operating stages were considered by analyzing both strength properties under fully dry conditions and strength degradation after saturation in a water bath. The BM-75% as the main component produced optimum combination in terms of workability and strength. With the material combination of BM-75% and additives-25%, the use of Red Mud and water treatment sludge as additives produced the highest and lowest strength of composite clay balls, with a failure load of 5.4 kN and 1.4 kN respectively. However, this lower value of 1.4 kN is much higher than the effective load on each clay ball of 0.04 kN in a typical filter assembly (safety factor of 35), therefore, can still be used as a suitable filter material for enhanced pollutant removal.

• Journal of the Institute of Convergence Signal Processing
• /
• v.18 no.1
• /
• pp.13-20
• /
• 2017

In this paper, we evaluate the basic test results of the 32 Gbps observational equipment introduced as the back-end system for the wideband VLBI (Very Long Baseline Interferometry) observation of KVN (Korean VLBI Network). Radio astronomers want to make a large radio telescope that has excellent performance in order to observe the superfine structure of a celestial body, but a lot of money is needed. Therefore, in order to increase the sensitivity, the performance improvement of the receiving system and the method of observing the wide frequency bandwidth are introduced. To do this, we adopted a wideband sampling method for converting analog signals to digital with ultra-fast speeds and a wideband sampler for performing digital filtering in order to observe a wide observational frequency bandwidth. The wideband sampler (OCTAD-K) supports up to 16 Gsps-2bits sampling and supports a variety of observational bandwidth using digital filtering techniques. In particular, it is designed to support KVN's 4-frequency simultaneous observation system and VERA(VLBI Exploration of Radio Astrometry)'s 2-beam observation system. It can also support polKVN(Korean VLBI Network), KaVA(KVN and VERA Array), 32Gbps Direct Sampler, Digital Filter, Widebandarization observations and supports the standard VDIF(VLBI Data Interchange Format) format of observed data. In this paper, the performance of the system and the problem solving are described in detail after performing the factory inspection and field test before the system is introduced.