• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2001년도 춘계학술대회 논문집(한국공작기계학회)
• /
• pp.376-381
• /
• 2001

This paper presents a methodology of machining error compensation by using Artificial Neural Network(ANN) model based on the inspection database of On-Machine-Measurement(OMM) system. First, the geometric errors of the machining center and the probing errors are significantly reduced through compensation processes. Then, we acquire machining error distributions from a specimen workpiece. In order to efficiently analyze the machining errors, we define two characteristic machining error parameters. These can be modeled by using an ANN model, which allows us to determine the machining errors in the domain of considered cutting conditions. Based on this ANN model, we try to correct the tool path in order to effectively reduce the errors by using an iterative algorithm. The iterative algorithm allows us to integrate changes of the cutting conditions according to the corrected tool path. Experimentation is carried out in order to validate the approaches proposed in this paper.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2005년도 춘계학술대회 논문집
• /
• pp.300-306
• /
• 2005

This paper presents the methodology for measuring eccentricity of the machined cylindrical part using CCS(cylindrical capacitance spindle sensor) signal in the CNC turning process. We use capacitance type sensor to take full advantage of averaging effect by using large capacitance area to encompass the whole side of a sensor. The intentionally proposed initial eccentricity is applied to the experimental testpieces, and their resultant relationships between CCS orbits and eccentricities are investigated. As a result, the possibility as a automatic detection apparatus for the CNC lathe is considered based on the linearities of CCS signal and magnitude of eccentricity of machined cylindrical surfaces.

• 대한기계학회논문집A
• /
• 제21권2호
• /
• pp.189-198
• /
• 1997

This paper presents development of a practical tool deflection compensation system in order to reduce the machining error from the tool deflection compensation system in order to reduce the machining error from the tool deflection in the end-milling process. The devised system is a tool adapter which includes 1-axes force sensor for detecting tool deflection and 2-axes tool tilting device for adjusting tool position through computer interface on line process. Experimental in investigations for typical shaped workpieces representing various end milling situations are performed to verify the ability of the system to suppress the surface errors due to tool deflections. With the system, it is possible to get precise machining surface without any excessive machining error due to increased cutting force in more productive machining conditions.

• 한국정밀공학회지
• /
• 제18권11호
• /
• pp.74-79
• /
• 2001

In this two-part paper, a virtual machine tool (VMT) is presented. In part 1, the analytical foundation of a virtual machining system, envisioned as the foundation for a comprehensive simulation environment capable of predicting the outcome of cutting processes, is developed. The VMT system purposes to experience the pseudo-real machining before real cutting with a CNC machine tool, to provide the proper cutting conditions for process planners, and to compensate or control the machining process in terms of the productivity and attributes of products. The attributes can be characterized with the machined surface error, dimensional accuracy, roughness, integrity and so forth. The main components of the VMT are cutting process, application, thermal behavior and feed drive modules. In part 1, the cutting process module is presented. The proposed models were verified experimentally and gave significantly better prediction results than any other method. The thermal behavior and feed drive modules are developed in part 2 paper. The developed models are integrated as a comprehensive software environment in part 2 paper.

• 한국기계가공학회지
• /
• 제20권11호
• /
• pp.36-42
• /
• 2021

This study was conducted to analyze the effect of the gear specification and gear quality corresponding to the macro geometry on the gear transmission error. The two pairs of gears with large and small transmission errors were selected for calculation, and two pairs of gears were manufactured with different gear quality. The test gears were manufactured by two different gear specifications with ISO 5 and 8 gear quality, respectively. The transmission error measurement system consists of an input motor, reducer, encoders, gearbox, torque meter, and powder brake. To confirm the repeatability of the test results, repeatability was confirmed by performing three repetitions under all conditions, and the average value was used to compare the transmission error results. The transmission errors of the gears were analyzed and compared with the test results. When the gear quality was high, the transmission error was generally low depending on the load, and the load at which the decreasing transmission error phenomenon was completed was also lower. Even when the design transmission error according to the gear specification was different, the difference of the minimum transmission error was not large. The transmission error at the load larger than the minimum transmission error load increased to a slope similar to the slope of the analysis result.

• 한국산학기술학회논문지
• /
• 제19권11호
• /
• pp.338-343
• /
• 2018

최근 금형산업과 다양한 산업에서 사용되고 있는 CNC 공작기계는 제품 공정 증가에 따라 작업효율, 생산 품질과 작업자의 안전성이 중요해지고 있다. 특히 4차 산업으로 산업구조가 바뀜에 따라 CNC 공작기계는 기존의 고정밀, 고능률화를 넘어 ICT 스마트 가공에 대한 다양한 연구가 진행되고 있다. 이에 CNC 절삭가공 시 생산제품의 품질을 균일하게 하고 재현성을 향상시키기 위한 다양한 공구 수명 예측 연구가 진행되어 왔다. 이러한 과정에서 기존의 확장된 Taylor 공구 수명식을 이용하여 공구 수명을 예측하였을 경우 예측결과와 실제 실험 결과와의 오차가 상당하다. 이에 본 논문에서는 공구 수명 관련 가공 실험을 통해 공구 수명에 대한 데이터를 확보 한 후 이를 기초로 유전알고리즘을 이용하여 최적의 공구 수명 매개변수를 추정하였다. 이때 공구 수명에 관련하여 공구 마모 관련 정보를 삽입하여 공구 마모량에 따른 공구 수명을 정확하게 예측할 수 있도록 구성하였으며, 이를 통해 공구 수명식을 보다 정확하게 최적화할 수 있도록 하였다.

• 한국항행학회논문지
• /
• 제27권1호
• /
• pp.111-118
• /
• 2023

스마트팩토리의 구축을 위해서는 제조환경에서 여러 센서 및 기기 등을 연결하여 데이터를 수집하고, 데이터 분석을 통해 생산설비 등의 장애를 진단하거나 예측하여야 한다. 본 논문에서는 공작기계에서 제품을 가공하기 위해 사용되는 절삭용 인서트의 잔여 유효 수명을 예측하기 위해 진동 신호를 기반으로 한 가중화 k-최근접이웃(Weighted k-NN) 알고리즘, 의사결정나무(Decision Tree), 서포트벡터회귀(SVM), XGBoost, 랜덤포레스트(Random forest), 1차원 합성곱신경망(1D-CNN), 그리고 진동 신호를 FFT한 주파수 스펙트럼에 대해 알아보았다. 연구결과, 주파수 스펙트럼으로는 잔여 유효수명의 정확한 예측에 대해서는 신빙성있는 기준을 제공하지 못한다는 것을 알수 있었고, 예측 모델 중 가중화 k-최근접이웃 알고리즘이 MAE가 0.0013, MSE가 0.004, RMSE가 0.0192로 가장 우수한 성능을 나타내었다. 이는 가중화 k-최근접이웃 알고리즘에 의해 예측되는 인서트의 잔여 유효 수명의 오차가 0.001초 수준으로 평가되어, 실제 산업현장에 적용이 가능한 수준으로 사료된다.

• 한국정밀공학회지
• /
• 제27권4호
• /
• pp.20-26
• /
• 2010

Any relative deformation between the cutting tool and the workpiece at the machining point, results directly in form and dimensional errors. The source of relative deformations between the cutting tool and the workpiece at the contact point may be due to thermal, weight, and cutting forces. This paper presents an investigation into dry and fluid machining with the objective of evaluating shape accuracy effect for the turning process of Al6061. The thermal distribution of cutting tool and cutting force was predicted using finite element method after measuring the temperature of the tool holder. To reach this goal, shape accuracy turning experiments are carried out according to cutting conditions with dry and fluid machining methods. The variable cutting conditions are cutting speed, depth of cutting and feed rate.

• 한국생산제조학회지
• /
• 제19권4호
• /
• pp.498-503
• /
• 2010

The main purpose of this study strongly concerned micro machining error estimation by using FEM analysis of tool deflection shapes in micro flat end-milling process. For the precision micro flat end-milling process, analysis of micro cutting errors is mandatory. In general, tool deflection is a major factor which causes cutting error and limits realization of the high-precision cutting process. Especially, in micro end-milling process, micro tool deflection generates very serious problems in contrast to macro tool deflection. Methods which deal with compensation of cutting error by tool deflection in macro end-milling process have been studied plentifully but, few researches transact with micro scaled cutting tool deflection in micro cutting process. Therefore, the trend of micro tool deflection was estimated by using FEM analysis in this paper. Cutting forces were acquired by micro dynamometer and these were utilized in FEM analysis. In order to verify FEM analysis results, micro machining processes were carried out and real machined profiles were compared with FEM results. Finally through the proposed approach well suited FEM results were obtained.

• 한국생산제조학회지
• /
• 제21권3호
• /
• pp.387-393
• /
• 2012

It is very difficult to determine suitable cutting conditions in order to obtain accurate cutting profiles because machining errors caused by tool deflection depend upon cutting conditions. In this study the relationship between real cutting profiles (inclined shapes and machining errors) and cutting conditions was modeled in order to fabricate draft angle on micro molds. CCD (Central Composite Design) of DOE (Design Of Experiment) and RSM (Response Surface Method) were applied in order to model the relationship between cutting conditions and machining errors. In order to use CCD the range of radial depth of cut was chosen by $10-90{\mu}m$ and the range of feedrate was chosen by 200-300mm/min, and 9 points of cutting conditions were chosen inside determined ranges. Then, actual cutting processes were carried out as respect to 9 points of cutting conditions, draft angles and real cutting profiles were measured on cutting profiles, each response surface function was determined by conducting response surface analysis and the functions were represented by 3-dimensional graphs, contour lines and $101{\times}101$ matrices. Consequently it is possible to determine suitable cutting conditions in order to obtain arbitrary given draft angles and cutting profiles by using modeling. To validate proposed approach in this study suitable cutting conditions were determined by modeling in order to obtain arbitrary given draft angle and cutting profile, and actual cutting processes were carried out. About 95% of good agreement between predicted and measured values was obtained.