scholarly journals CNN-GRU Network-based Force Prediction Approach for Variable Working Condition Milling Clamping Points of Deformable Parts

2021 ◽  
Author(s):  
Enming Li ◽  
Jingtao Zhou ◽  
Changsen Yang ◽  
Mingwei Wang ◽  
Zeyu Li ◽  
...  
Keyword(s):  
Working Conditions ◽  
Coupling Effect ◽  
Milling Process ◽  
Machining Process ◽  
Point Force ◽  
Temporal Association ◽  
Force Prediction ◽  
Machining Conditions ◽  
Machining Deformation ◽  
Prediction Approach

Abstract Improper clamping is one of the major causes of part deformation. Improving the fixture arrangement through force analysis of clamping points is an effective means to suppress or improve machining deformation. However, the existing research focuses on the monitoring and off-line optimization of the clamping point force, which has a certain lag on the machining deformation control, and it is difficult to predict the clamping point force due to the time-varying coupling effect of multiple factors such as process parameters, cutting force and clamping point force in the machining process. Inspired by the excellent performance of convolutional neural networks and gated recurrent networks in feature extraction and learning of temporal association laws, this paper proposes a CNN-GRU-based method for predicting the force state of clamping points under variable working conditions. Firstly, a force prediction model of clamping point during milling process with variable working conditions is established. Secondly, a convolutional neural network is designed to extract the features of dynamic coupled machining conditions. Then, a network of gated recurrent units is constructed to learn the temporal correlation law between the machining conditions and the forces on the clamping points to achieve force prediction of the clamping points during machining. Finally, it was verified by the milling process of the piston skirt. The results show that CNN-GRU can effectively predict the clamping force. In addition, CNN-GRU has higher computational efficiency and accuracy compared with CNN-LSTM, CNN-RNN and CNN-BP.

Analysis and Prediction Approach to the Thin-Walled Workpiece Deformation with Thermo-Mechanical Couple Consideration

2012 ◽  
Vol 499 ◽  
pp. 15-20
Author(s):  
Xiao Hong Zhong ◽  
Guo Hua Qin ◽  
S.P. Sun ◽  
D. Lu
Keyword(s):  
Finite Element ◽  
Metal Cutting ◽  
Thermal Control ◽  
Friction Model ◽  
Machining Process ◽  
Peripheral Milling ◽  
Mechanical Coupling ◽  
Machining Deformation ◽  
Thin Walled ◽  
Prediction Approach

The metal cutting is a complexly dynamic physical process of thermal-mechanical coupling. It is difficult in analyzing the mechanism of machining deformation with the traditional calculation method. The key simulation technologies of the machining process are analyzed by means of finite element method (FEM), such as material constitutive model, chip separation criterion, tool-chip interaction and friction model, thermal control equation. During finite element simulation of the peripheral milling of the thin-walled workpiece, the contact constraints between the tool and workpiece can be effectively simplified. Thus, the tool and workpiece are considered as rigid and elastic bodies, respectively. In sequence, the unit birth and death technology is used to simulate the material removal in the milling process so that the effect of the workpiece size on machining deformation can be researched accurately. The investigation on the theory and application of the above key technologies can not only analyze and predict the deformation of thin-walled parts, but also optimize process parameters to control the machining deformation.

Optimization of turn-milling process in roughing and finishing regimes: Trade-off between productivity, cutting force and surface integrity

2021 ◽  
pp. 095440892199851
Author(s):  
Ebrahim Hosseini ◽  
Shafiqur Rehman ◽  
Ashkan Alimoradi
Keyword(s):  
Cutting Force ◽  
Desirability Function ◽  
Milling Process ◽  
Machining Process ◽  
Hybrid Machining ◽  
Trade Off ◽  
Hybrid Machining Process ◽  
Process Factors ◽  
Turn Milling ◽  
Selection Of

Turn-milling is a hybrid machining process which used benefits of interrupted cutting for proceeding of round bars. However, number of controllable parameters in the hybrid process is numerous that makes optimizing the process complicated. In the present study, an optimization work has been proposed to investigate the trade-off between production rate and cutting force in roughing regime as well surface roughness and tensile residual stress in finishing regime. Number of 43 experiments based on response surface methodology was designed and carried out to gather required data for development of quadratic empirical models. Then, the adequacy and importance of process factors were analyzed using analysis of variances. Finally, desirability function was used to optimize the process in rough and finish machining regimes. The obtained results showed that selection of eccentricity and cutter speed at their maximum working range can effectively enhance the quality characteristics in both the roughing and finishing regimes.

Milling Force Prediction for Circular Contour Machining

2014 ◽  
Vol 800-801 ◽  
pp. 243-248
Author(s):  
Kai Zhao ◽  
Zhan Qiang Liu
Keyword(s):  
Prediction Model ◽  
Milling Process ◽  
Machining Process ◽  
Curvature Radius ◽  
Force Model ◽  
Milling Force ◽  
Circular Contour ◽  
The Mean ◽  
Contour Machining ◽  
Matlab Programming

When machining the complex parts of aircraft engines, the milling force for the circular contour must be accurately predicted to reduce machining vibration. In this paper, the prediction model of the mean milling force per tooth during machining circular contour is developed. Firstly, the formulas of the entry angle, the exit angle and the equivalent feed per tooth are established through the analysis of circular contour milling process. Then, the equation of the mean milling force per tooth is deduced based on mechanistic force model during the circular contour machining process. Finally, the prediction model of mean milling force per tooth during machining circular contour is developed using MATLAB programming. The relationship between the milling force per tooth and surface curvature radius of the machined workpiece is also analyzed in this paper.

Failure time prognosis in manufacturing process using multi-dislocated time series convolutional neural network

2020 ◽  
pp. 095440892097414
Author(s):  
Bohao Li ◽  
Liping Zhao ◽  
Yiyong Yao
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Convolutional Neural Network ◽  
Manufacturing Process ◽  
Failure Time ◽  
Great Difficulty ◽  
Milling Process ◽  
Machining Process ◽  
Massive Data ◽  
The Difference

Failure time prognosis in manufacturing process plays a crucial role in guaranteeing manufacturing safety and reducing maintenance loss. However, most current prognosis methods face great difficulty when handling massive data collected from manufacturing process. Convolutional neural network (CNN) provides an effective way to extract features with massive data. Due to the difference between images and multisensory signals, CNN is not suitable for machining process. Inspired by the idea of CNN, a novel prognosis framework is proposed based on the characteristics of multisensory signals, which is called multi-dislocated time series convolutional neural network (MDTSCNN). The proposed MDTSCNN is composed of multi-dislocate layer, convolutional layer, pooling layer and fully connected layer. By adding a multi-dislocate layer, this model can learn the relationship between different signals and different intervals in periodic multisensory signals. The effectiveness of proposed method is validated by a milling process. Compared to other prognosis method, the proposed MDTSCNN shows enhanced performances in prediction accuracy.

scholarly journals Automatic Temperature Measurement and Monitoring System for Milling Process of AA6041 Aluminum Aloy using MLX90614 Infrared Thermometer Sensor with Arduino

2021 ◽  
Vol 82 (2) ◽  
pp. 1-14
Author(s):  
Agus Sudianto ◽  
Zamberi Jamaludin ◽  
Azrul Azwan Abdul Rahman ◽  
Sentot Novianto ◽  
Fajar Muharrom
Keyword(s):  
Aluminum Alloy ◽  
Temperature Measurement ◽  
Monitoring System ◽  
Measurement System ◽  
Manufacturing Process ◽  
Milling Process ◽  
Numerical Control ◽  
Machining Process ◽  
Infrared Thermometer ◽  
Temperature Measurement System

Manufacturing process of metal part requires real-time temperature monitoring capability to ensure high surface integrity is upheld throughout the machining process. A smart temperature measurement and monitoring system for manufacturing process of metal parts is necessary to meet quality and productivity requirements. A smart temperature measurement can be applied in machining processes of conventional, non-conventional and computer numerical control (CNC) machines. Currently, an infrared fusion based thermometer Fluke Ti400 was employed for temperature measurement in a machining process. However, measured temperature in the form of data list with adjustable time range setting is not automatically linked to the computer for continuous monitoring and data analysis purposes. For this reason, a smart temperature measurement system was developed for a CNC milling operation on aluminum alloy (AA6041) using a MLX90614 infrared thermometer sensor operated by Arduino. The system enables data linkages with the computer because MLX90614 is compatible and linked to Microsoft Exel via the Arduino. This paper presents a work-study on the performance of this Arduino based temperature measurement system for dry milling process application. Here, the Arduino based temperature measurement system captured the workpiece temperature during machining of Aluminum Alloy (AA6041) and data were compared with the Fluke Ti400 infrared thermometer. Measurement results from both devices showed similar accuracy level with a deviation of ± 2 oC. Hence, a smart temperature measurement system was succeesfully developed expanding the scopes of current system setup.

scholarly journals The Design and Implementation of Fan Chips as Cooling for Milling Process on Aluminum Alloy 5086 to Increase Tool Life

2021 ◽  
Vol 2 (1) ◽  
pp. 29-42
Author(s):  
Agus Sifa ◽  
Dedi Suwandi ◽  
Tito Endramawan ◽  
Alam Aulia Rachman
Keyword(s):  
Aluminum Alloy ◽  
Tool Life ◽  
Experimental Testing ◽  
Fluid Dynamic ◽  
Milling Process ◽  
Machining Process ◽  
Central Character ◽  
Spindle Rotation ◽  
Cfd Method ◽  
Increase Tool Life

In the metal machining process, especially in the milling process, the parameters that affect the quality milling process results are cooling media because it affects the tool life used. This paper aims to determine the performance of using fan chips as the coolant in the dry milling process area. The method used is the computational fluid dynamic (CFD) method and the experimental milling process on a workpiece made from aluminum alloy 5086. In experimental testing using a variation of the milling machine spindle rotation. The simulation test results on the fluid flow character on fan chips with a protector producing a central character with a small area. In contrast, fan chips without a protector make a central character with a broader area. The wind speed data in simulation testing and experimental testing produced the same trend graph. The results of the performance of fan chips after experimented with variations in spindle rotation, cooling process on area occurs when the motor spindle rotates above 1120 Rpm on the fan chips with a protector, and the engine spindle rotates above 770 Rpm on the fan chips without a protector. The effect of fan chips on tool life affects increasing tool life by 8 minutes on installing fan chips with a protector and increasing tool life by 12 minutes on installing fan chips without a protector.

An Investigation of the End Milling Process Under Varying Machining Conditions

1989 ◽  
Vol 111 (1) ◽  
pp. 27-36 ◽  
Author(s):  
B. K. Fussell ◽  
K. Srinivasan
Keyword(s):  
Adaptive Control ◽  
Feedback Loop ◽  
End Milling ◽  
Milling Process ◽  
Operating Conditions ◽  
Machining Conditions ◽  
Adaptive Control Systems ◽  
Proper Design ◽  
Process Mechanics ◽  
End Milling Process

Varying machining conditions are encountered in adaptively controlled machining situations where operating conditions such as the feedrate and spindle speed are adjusted continuously to achieve desired objectives. Proper design, of constraint-type adaptive control systems in particular, requires models of the milling process mechanics since the milling process is usually part of the feedback loop. The adequacy of available models of milling process mechanics is evaluated here experimentally for many cases of varying machining conditions, including changing axial and radial depths of cut and feedrate. Startup transients in the force as the cutter engages the workpiece are also investigated. The significance of dynamic effects in the milling process and of effects such as runout, for constraint-type adaptive control system design, is then evaluated.

The Effect of Prior Cutting Conditions on the Shear Mechanics of Orthogonal Machining

1998 ◽  
Vol 120 (1) ◽  
pp. 13-20 ◽  
Author(s):  
R. Stevenson ◽  
D. A. Stephenson
Keyword(s):  
Material Properties ◽  
Metal Cutting ◽  
Orthogonal Cutting ◽  
Rake Angle ◽  
Cnc Machining ◽  
Machining Process ◽  
Depth Of Cut ◽  
Prior History ◽  
Machining Conditions ◽  
The Difference

It has been proposed several times in the metal-cutting literature that the machining process is non-unique and that the instantaneous machining conditions depend on the prior machining conditions (e.g. depth of cut, rake angle etc.). To evaluate the validity of this concept, a series of experiments was conducted using a highly accurate CNC machining center. For these experiments, the machining conditions were changed during the course of an orthogonal cutting experiment in a repeatable manner and the measured forces compared as a function of prior history. Tests were conducted on several tempers of 1100 aluminum and commercial purity zinc to evaluate the effect of material properties on the machining response. It was found that the change in measured cutting forces which could be ascribed to prior machining history was less than 3 percent and that material properties, particularly work hardening response, had no discernible effect on the magnitude of the difference.

Study on Machining Deformation Errors in Spiral Finish Milling of Thin-Walled Blades

2011 ◽  
Vol 314-316 ◽  
pp. 1773-1777
Author(s):  
Wei Wei Liu ◽  
Pei Chen ◽  
Xiao Juan Gao ◽  
Chen Wei Shan ◽  
Min Wan
Keyword(s):  
Geometric Dimension ◽  
Beam Theory ◽  
Milling Process ◽  
Simplified Model ◽  
Machining Deformation ◽  
Proposed Model ◽  
Thin Walled ◽  
The Relationship ◽  
Torsion Deformation

In this paper, a new procedure is proposed to study the deformation errors for spiral milling process of blade, which can be simplified as a stepwise beam based on the geometry and clamping characteristics. Kirchhoff beam theory is adopted to analyze the bending and torsion deformation. The relationship between machining deformation errors and the workpiece’s geometric dimension are also established based on the simplified model. Corresponding algorithms are realized by MATLAB codes. Experiment test shows that the results predicted by the proposed model are in well agreement with measured ones.

Contribution to Computer Control and Optimization of Hydro-Abrasive Jet Machining Process

1991 ◽  
Author(s):  
Roberto Groppetti ◽  
Giuseppe Comi
Keyword(s):  
Real Time ◽  
Process Model ◽  
Wide Spectrum ◽  
Computer Control ◽  
Process Condition ◽  
Machining Process ◽  
Process Variables ◽  
Real Time Control ◽  
Machining Conditions ◽  
Abrasive Jet Machining

Abstract Hydro-Abrasive Jet Machining (HAJM) has demonstrated its suitability for several applications in the machining of a wide spectrum of materials (metals, polymers, ceramics, fibre reinforced composites, etc.). The paper is a contribution to the computer control, integration and optimization of HAJM process in order to establish a hierarchical control architecture and a platform for the implementation of a real-time Adaptive Control Optimization (ACO) module. The paper presents the approach followed and the main results obtained during the development and implementation of a HAJM cell and its computerized controller. A critical analysis of the process variables available in the literature is presented, in order to identify the process variables and to define a process model suitable for HAJM real-time control and optimization. Besides for HAJM computer control, in order to correlate process variables and parameters with machining results, a process model and an optimization procedure are necessary in order to avoid expensive and time-consuming experiments for the determination of optimal machining conditions. The paper presents the configuration of the cell and the specific components adopted in order to make possible a fully computerized control of the process, and the architecture of the controller, capable to manage the several logical and analogical signals from the different modules of the cell, for multiprogramming, process monitoring, controlling, process parameters predetermination, process condition multiobjective optimization. A prediction and an optimization model is presented allowing the identification of optimal machining conditions using multiobjective programming. This model is based on the definition of an economy function and a productivity function, with suitable constraints relevant to the required machining quality, the required kerfing depth and the available resources. A test case based on experimental results is discussed in order to validate the model.

Sign in / Sign up

Export Citation Format

Share Document