• Journal of the Korea Society of Computer and Information
• /
• v.27 no.4
• /
• pp.27-36
• /
• 2022

In this paper, to improve the conditions of the fish processing site, we propose a method to predict the cutting point of fish according to the target weight using AI machine vision. The proposed method performs image-based preprocessing by first photographing the top and front views of the input fish. Then, RANSAC(RANdom SAmple Consensus) is used to extract the fish contour line, and then 3D external information of the fish is obtained using 3D modeling. Next, machine learning is performed on the extracted three-dimensional feature information and measured weight information to generate a neural network model. Subsequently, the fish is cut at the cutting point predicted by the proposed technique, and then the weight of the cut piece is measured. We compared the measured weight with the target weight and evaluated the performance using evaluation methods such as MAE(Mean Absolute Error) and MRE(Mean Relative Error). The obtained results indicate that an average error rate of less than 3% was achieved in comparison to the target weight. The proposed technique is expected to contribute greatly to the development of the fishery industry in the future by being linked to the automation system.

• Journal of the Society of Naval Architects of Korea
• /
• v.37 no.3
• /
• pp.90-98
• /
• 2000

Nesting and cutting path optimization have a great effect on price competitions and improvement of productivity in various industries such as the shipbuilding, the auto, the clothing, and so on. But the theoretical approach on the development of cutting path optimization algorithm, which can be applied effectively in the shipbuilding, has not been performed enough because parts are so complex and various. In this study, a new solution has been presented to solve the cutting path problem in 2-D cutting by using improved genetic algorithm. The presented optimization algorithm can search not only the cutting sequence of parts but also the position of piercing point by applying the effective neighborhood solution generating method

• Design & Manufacturing
• /
• v.11 no.1
• /
• pp.50-54
• /
• 2017

In this study, researches were conducted as follows. First, as the basic experiment, the cutting speed, feedrate, and the depth of cut were set as the process parameters, and by setting the surface roughness as the factor of measurement for each of the combinations, and the analysis about cutting tendency of the material was conducted by proceeding the turning process of Co-Cr-Mo alloy. Second, by setting the feature of the surface roughness according to the 'turning processing condition' that was confirmed in the previous experiment, and by applying the Taguchi Method, the conditions that influence the features of the surface roughness according to the 'turning processing condition' of Co-Cr-Mo was analyzed, and also by measuring the surface roughness according to each of the 'cutting conditions', the optimal processing condition was generated. As the result of analysis, it was possible to understand that the factor that mostly affects the surface roughness was the cutting speed, followed by the dept of cutting and transfer speed, and as for the optimal processing condition, it was possible to find that the cutting speed was 5,000rpm, and the depth of cut was 0.1mm, and the feedrate was 0.003mm/rev, and the value of the surface roughness at this point is $0.197{\mu}m$.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.05a
• /
• pp.944-947
• /
• 2000

Sculptured surface machining plays a vital role in the process of bring new products to the market place. A great variety of products rely on this technology for the production of the dies and moulds used in manufacturing. And, the use of CNC machines and CAD/CAM system has become a vital parts of product development process. The propose of this study is to investigate the effect of cutting parameters on the machinability such as surface roughness and cusp generated in the machining of sculptured surface on a three-axis CNC machining center using the CAD/CAM system. Experimental result showed that: In step down cutting, as the inclined angle of surface became smaller, the cusp height appeared higher. On the other hand, in step over cutting, as the inclined angle of surface became larger, the cusp height appeared higher. In the point of precision machining, step over cutting was more effective. For the minimization of cusp height, step down cutting was effective in larger inclined surface, but step over cutting in smaller inclined surface.

• Journal of Korean Society for Geospatial Information Science
• /
• v.17 no.2
• /
• pp.11-17
• /
• 2009

Terrestrial LiDAR can measure high capacity 3D-topography coordinates and try to apply to various public works such as tunnel surveying, facility deformation surveying. This experiment is about how to calculate ground cutting volume because the stage of the earth work spend lots of money and time among civil engineering works. Surveying cutting area using Terrestrial LiDAR and then calculating cutting area in planned area comparing sectional plan before construction and planned section and LiDAR data. Also, the values of the calculating ground cutting volume by three different resolution LiDAR has are compared and analyzed.

• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.12
• /
• pp.47-54
• /
• 2008

Hard turning process can be defined as a single-point machining process carried out on "hard" materials. The process is intended to replace or limit traditional grinding operations that are expensive, environmentally unfriendly, and inflexible. The purpose of this study is to achieve a systematic understanding of machining characteristics and the effects of machining parameters on cutting force, tool wear shape and chip formation by the outer cutting of a kind of wear resistant tungsten carbide V30. Hard turning experiments were carried out on this alloy using the PCD (Poly Crystalline Diamond), cBN (cubic Boron Nitride) and PcBN (Polycrystalline cubic Boron Nitride) cutting tools. The PcBN and the usual cBN tools were used to be compare with the PCD tool and the dry turning was carried out. The PcBN is attractive as the tool material which replaces the PCD. The tool wear width and cutting force were measured, and the worn tool and chip were observed. The difference of the tool wear mechanism among the three tool materials was investigated.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.5 s.182
• /
• pp.44-50
• /
• 2006

This paper describs about the technique of ultra-precision machining for an infrared(IR) camera aspheric mirror. A 200 mm diameter aspheric mirror was fabricated by SPDTM(Single Point Diamond Turning Machine). Aluminum alloy as mirror substrates is known to be easily machined, but not polishable due to its ductility. Aspheric large reflector without a polishing process, the surface roughness of 5 nm Ra, and the form error of ${\lambda}/2\;({\lambda}=632.8\;nm)$ for reference curved surface 200 mm has been required. The purpose of this research is to find the optimum machining conditions for cutting reflector using Al6061-T651 and apply the SPDTM technique to the manufacturing of ultra precision optical components of Al-alloy aspheric reflector. The cutting force and the surface roughness are measured according to each cutting conditions feed rate, depth of cut and cutting speed, using diamond turning machine to perform cutting processing. As a result, the surface roughness is good when feed rate is 1mm/min, depth of cut $4{\mu}m$ and cutting speed is 220 m/min. We could machined the primary mirror for IR camera in diamond machine with a surface roughness within $0.483{\mu}m$ Rt on aspheric.

• Korean Journal of Computational Design and Engineering
• /
• v.1 no.1
• /
• pp.45-55
• /
• 1996

This paper presents a new approach to non-parametric modeling of cutter swept surface (CSS) for cutting simulation. Instead of explicitly modeling cutter swept volumes, silhouette curves of the cutter surface are utilized in computing the z-value of the CSS at a grid point on the x,y-plane. The non-parametric evaluation of the CSS constitutes the integral part of 3-axis cutting simulation. The proposed method is more efficient than the existing ones in the case of conventional cutters (i.e., ball-end mills and flat-end mills), and more importantly, it enables the non-parametric modeling of the CSS for the round-end mills which was not possible with the existing methods.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.12
• /
• pp.1048-1055
• /
• 2002

The problem of generating torch paths for 2D laser cutting of a stock plate nested with a set of free-formed parts is investigated. The objective is to minimize the total length of the torch path starting from a blown depot, then visiting all the given Parts, and retuning back to the depot. A torch Path consists of the depot and Piercing Points each of which is to be specified for cutting a part. The torch path optimization problem is shown to be formulated as an extended version of the standard travelling salesman problem To solve the problem, a hybrid genetic algorithm is proposed. In order to improve the speed of evolution convergence, the algorithm employs a genetic algorithm for global search and a combination of an optimization technique and a genetic algorithm for local optimization. Traditional genetic operators developed for continuous optimization problems are used to effectively deal with the continuous nature of piercing point positions. Computational results are provided to illustrate the validity of the proposed algorithm.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.4 no.3
• /
• pp.39-47
• /
• 1995

This paper suggests generalize mathematica mode for the benefit of volumetric error analysis of a multi-axis machine tool machining a sculptured surfaces. The volumetric error, in this paper, is defined as a three dimensional error at the cutting point, which is caused by the geometric errors and the kinematic errors of each axis and alignment errors of the cutting tool. The actual cutting position is analyzed based on the form shaping model including a geometric error of the moving carriage, where a form shaping model is derived from the homogeneous transformation matrix. Then the volumetric error is obtained by calculating the position difference between the actual cutting position and the ideal one calculated from a Nonuniform Rational B-Spline named as NURES. The simulation study shows the effectiveness for predicting the behavior of machining error and for the method of error compensation.