scholarly journals Unsupervised Machine Learning for Advanced Tolerance Monitoring of Wire Electrical Discharge Machining of Disc Turbine Fir-Tree Slots

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3359 ◽  
Author(s):  
Jun Wang ◽  
Jose Sanchez ◽  
Izaro Ayesta ◽  
Jon Iturrioz
Keyword(s):  
Machine Learning ◽  
Electrical Discharge ◽  
Electrical Discharge Machining ◽  
Short Circuit ◽  
Coordinate Measuring Machine ◽  
Wire Electrical Discharge Machining ◽  
Unsupervised Machine Learning ◽  
Measuring Machine ◽  
Wedm Process ◽  
Tolerance Monitoring

Manufacturing more efficient low pressure turbines has become a topic of primary importance for aerospace companies. Specifically, wire electrical discharge machining of disc turbine fir-tree slots has attracted increasing interest in recent years. However, important issues must be still addressed for optimum application of the WEDM process for fir-tree slot production. The current work presents a novel approach for tolerance monitoring based on unsupervised machine learning methods using distribution of ionization time as a variable. The need for time-consuming experiments to set-up threshold values of the monitoring signal is avoided by using K-means and hierarchical clustering. The developments have been tested in the WEDM of a generic fir-tree slot under industrial conditions. Results show that 100% of the zones classified into Clusters 1 and 2 are related to short-circuit situations. Further, 100% of the zones classified in Clusters 3 and 5 lie within the tolerance band of ±15 μm. Finally, the 9 regions classified in Cluster 4 correspond to situations in which the wire is moving too far away from the part surface. These results are strongly in accord with tolerance distribution as measured by a coordinate measuring machine.

scholarly journals Geometrical Defect Detection in the Wire Electrical Discharge Machining of Fir-Tree Slots Using Deep Learning Techniques

2018 ◽  
Vol 9 (1) ◽  
pp. 90 ◽  
Author(s):  
Jun Wang ◽  
Jose Sanchez ◽  
Jon Iturrioz ◽  
Izaro Ayesta
Keyword(s):  
Deep Learning ◽  
Defect Detection ◽  
Electrical Discharge ◽  
Electrical Discharge Machining ◽  
Absolute Error ◽  
Critical Issue ◽  
Wire Electrical Discharge Machining ◽  
Measuring Machine ◽  
The Wire ◽  
Wedm Process

Traceability is a critical issue in the manufacturing of aerospace components. However, extracting understandable information from huge amounts of data from manufacturing processes may become a very difficult task. In this paper, a novel proposal for geometrical defect detection in the manufacturing of fir-tree slots for disk turbines using wire electrical discharge machining is presented. Useful data about the wire Electrical Discharge Machining (WEDM) process are collected every 5 ms and each single discharge is classified as a function of ignition delay time. Information from this large amount of data is extracted by using a deep neural network, which includes two hidden dense layers, each with 64 units and Relu activation, and it ends with a single unit with no activation. The average of the per-epoch absolute error (MAE) scores has been used to decide the optimum training situation for the deep learning network. Validation of the method has been carried out by machining a high-precision fir-tree slot for a disk turbine under industrial conditions. Results show that even though a strict tolerance band of ±5 µm has been applied, as many as 80% of the predictions from the network match the results of the conventional measuring method (coordinate measuring machine).

Investigation of the Spark Cycle Effect on Material Removal Rate in Wire Electrical Discharge Machining

Manufacturing ◽  
2003 ◽  
Author(s):  
Scott F. Miller ◽  
Albert J. Shih
Keyword(s):  
Process Parameters ◽  
Material Removal Rate ◽  
Electrical Discharge ◽  
Material Removal ◽  
Electrical Discharge Machining ◽  
Removal Rate ◽  
Short Circuit ◽  
Wire Electrical Discharge Machining ◽  
Time Duration ◽  
Edm Process

The development of new, advanced engineering materials and the needs for precise and flexible prototype and low-volume production have made wire electrical discharge machining (EDM) an important manufacturing process to meet such demand. This research investigates the effect of spark on-time duration and spark on-time ratio, two important EDM process parameters, on the material removal rate (MRR) and surface integrity of four types of advanced material: porous metal foams, metal bond diamond grinding wheels, sintered Nd-Fe-B magnets, and carbon-carbon bipolar plates. An experimental procedure was developed. During the wire EDM, five types of constraints on the MRR due to short circuit, wire breakage, machine slide speed limit, and spark on-time upper and lower limits have been identified. An envelope of feasible EDM process parameters is created and compared across different work-materials. Applications of such process envelope to select process parameters for maximum MRR and for machining of micro features are presented.

Cutting Characteristics of Titanium Graphite Composite by Wire Electrical Discharge Machining

2012 ◽  
Vol 630 ◽  
pp. 114-120 ◽  
Author(s):  
Mamidala Ramulu ◽  
Mathew Spaulding ◽  
P. Laxminarayana
Keyword(s):  
Composite Laminates ◽  
Electrical Discharge ◽  
Electrical Discharge Machining ◽  
Hybrid Composites ◽  
Removal Rate ◽  
Wire Electrical Discharge Machining ◽  
Metal Composite ◽  
Workpiece Material ◽  
Graphite Composite ◽  
Wedm Process

To improve strength to weight ratios, the fiber reinforced polymer composite materials are often used in conjunction with another material, like metals, to form hybrid structure. This paper reports the feasibility of using wire electrical discharge machining (WEDM) for cutting Titanium/Graphite Hybrid Composites (TiGr). Slit and slot cuts with WEDM process has been performed. Cutting times and process parameters were recorded, and cut surface characteristics were evaluated both with an optical and scanning electron microscopy (SEM). The results in terms of cutting time, workpiece material removal rate, and damage were presented and discussed. It was found that use of WEDM is possible for machining advanced hybrid metal composite laminates with appropriate machine settings.

STEP-NC compliant information modelling for wire electrical discharge machining component manufacture

2005 ◽  
Vol 219 (10) ◽  
pp. 777-784 ◽  
Author(s):  
K H Ho ◽  
S T Newman ◽  
R D Allen
Keyword(s):  
Data Model ◽  
Electrical Discharge ◽  
Electrical Discharge Machining ◽  
Database Management System ◽  
Numerical Control ◽  
Wire Electrical Discharge Machining ◽  
Computer Aided Process Planning ◽  
Information Models ◽  
Computer Aided ◽  
Wedm Process

Over the last five years, a great deal of research effort has been concentrated on the development of a new data model ISO 14649, informally known as STEP-NC. It has been strongly argued that STEP-NC has huge implications on the integration of the computer-aided design/computer-aided process planning/computer-aided manufacture (CAD/CAPP/CAM) (CAx) systems, giving the opportunity to realize interoperable computer numerical control (CNC) manufacturing. This is largely owing to the data model, which provides the capability to revolutionize the current state of the art in CNC manufacturing by offering a bi-directional interface with a high-level description of the geometrical and manufacturing information. This paper provides a view of how these STEP-NC compliant information models can be used to support the wire electrical discharge machining (WEDM) CAD to the CNC process chain. The models are based on part 13 of the ISO 14649 standard, which is dedicated to the WEDM process, together with part 10 of the standard, which specifies the general machining information. The information models have been identified and their structures have been defined and modelled using the unified modelling language (UML). A STEP-NC compliant WEDM CAx prototype system, based on the Java and the object-oriented database management system (DBMS) ObjectStore, has been constructed with an example case study to demonstrate the information models.

scholarly journals Optimasi Multirespon Proses Wire Electrical Discharge Machining untuk Pengerjaan Komponen Punch and Dies Bracket Konstruksi Kapal Alumunium

2019 ◽  
Vol 12 (2) ◽  
pp. 107
Author(s):  
Fipka Bisono ◽  
Dhika Aditya P.
Keyword(s):  
Surface Roughness ◽  
Electrical Discharge ◽  
Electrical Discharge Machining ◽  
White Layer ◽  
Performance Characteristics ◽  
Machining Process ◽  
Wire Electrical Discharge Machining ◽  
Process Variables ◽  
Relational Analysis ◽  
Wedm Process

Wire electrical discharge machining(WEDM) banyak digunakan untuk proses pembuatan punch and dies. Dimana material yang digunakan memiliki tingkat kekerasan yang sangat tinggi. Parameter pemesinan yang kurang tepat dapat menyebabkan hasil pemotongan yang tidak optimal. Penelitian ini dilakukan untuk mengoptimalkan beberapa karakteristik hasil proses pemesinan secara serentak dengan cara mevariasikan variabel-variabel proses pemesinan WEDM. Karakteristik hasil proses yang diteliti antara lain adalah lebar pemotongan, kekasaran permukaan, dan tebal lapisan white layer. Proses pemesinan dilakukan pada material tool steel SKD 11. Arc on time, on time, open voltage dan servo voltage merupakan variabel-variabel proses yang akan divariasikan. Rancangan percobaan dilakukan menggunakan metode Taguchi dengan matriks ortogonal L18(21x33) dengan dua kali replikasi. Sedangkan langkah yang digunakan untuk mengoptimasi karakteristik hasil proses pemesinan yang diteliti secara serentak adalah menggunakan metode grey relational analysis (GRA). Lebar pemotongan, kekasaran permukaan dan tebal lapisan white layer memiliki performance characteristics “smaller-is-better.” Hasil dari penelitian menunjukkan nilai variabel-variabel proses pemesinan yang menghasilkan kualitas karakteristik yang paling optimum adalah sebagai berikut: arc on time (1A), on time (4?s), open voltage (70V), dan servo voltage (40V). Dengan persentase kontribusi variabel proses dari yang terbesar berturut-turut adalah on time (65,09%), open voltage (11,35%), arc on time (7,71%), dan servo voltage (5,61%). Wire electrical discharge machining (WEDM) process is commonly used to make punch and dies. WEDM services are typically used to cut hard metals. Inappropriate machining parameters can cause suboptimal cutting results. This research was conducted to optimize several characteristics of the machining process simultaneously by varying WEDM machining process variables. Performance characteristics of the WEDM process include the kerf, surface roughness and thickness of the white layer. The machining process is carried out on SKD 11 tool steel material.  Arc on time, on time, open voltage and servo voltage are process variables that will be varied. The experimental matrix design was carried out using the Taguchi method L18 (21x33) orthogonal array with two replications. Then to optimize the performance characteristics of the machining process simultaneously is using the Gray Relational Analysis (GRA) method. Performance characteristics of kerf, surface roughness, and thickness of the white layer is "smaller-is-better". The results of the experiment indicate the value of the machining process variables that produce the most optimum quality performance characteristics are as follows: arc on time (1A), on time (4?s), open voltage (70V), and servo voltage (40V). And the percentage of contribution of the process variables from the largest to smallest are as follows: on time (65,09%), open voltage (11,35%), arc on time (7,71%), and servo voltage (5,61%).

scholarly journals Modeling and Optimization of Fractal Dimension in Wire Electrical Discharge Machining of EN 31 Steel Using the ANN-GA Approach

Materials ◽  
2019 ◽  
Vol 12 (3) ◽  
pp. 454 ◽  
Author(s):  
Arkadeb Mukhopadhyay ◽  
Tapan Barman ◽  
Prasanta Sahoo ◽  
J. Davim
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Fractal Dimension ◽  
Process Parameters ◽  
Electrical Discharge ◽  
Electrical Discharge Machining ◽  
Wire Electrical Discharge Machining ◽  
Machining Parameters ◽  
Machined Surface ◽  
Wedm Process

To achieve enhanced surface characteristics in wire electrical discharge machining (WEDM), the present work reports the use of an artificial neural network (ANN) combined with a genetic algorithm (GA) for the correlation and optimization of WEDM process parameters. The parameters considered are the discharge current, voltage, pulse-on time, and pulse-off time, while the response is fractal dimension. The usefulness of fractal dimension to characterize a machined surface lies in the fact that it is independent of the resolution of the instrument or length scales. Experiments were carried out based on a rotatable central composite design. A feed-forward ANN architecture trained using the Levenberg-Marquardt (L-M) back-propagation algorithm has been used to model the complex relationship between WEDM process parameters and fractal dimension. After several trials, 4-3-3-1 neural network architecture has been found to predict the fractal dimension with reasonable accuracy, having an overall R-value of 0.97. Furthermore, the genetic algorithm (GA) has been used to predict the optimal combination of machining parameters to achieve a higher fractal dimension. The predicted optimal condition is seen to be in close agreement with experimental results. Scanning electron micrography of the machined surface reveals that the combined ANN-GA method can significantly improve the surface texture produced from WEDM by reducing the formation of re-solidified globules.

Multi-Objective Optimization of Wire Electrical Discharge Machining (WEDM) Process Parameters Using Weighted Sum Genetic Algorithm Approach

2016 ◽  
Vol 15 (02) ◽  
pp. 85-100 ◽  
Author(s):  
P. C. Padhi ◽  
S. S. Mahapatra ◽  
S. N. Yadav ◽  
D. K. Tripathy
Keyword(s):  
Genetic Algorithm ◽  
Electrical Discharge ◽  
Electrical Discharge Machining ◽  
Wire Electrical Discharge Machining ◽  
Weighted Sum ◽  
Multi Objective ◽  
Pulse On Time ◽  
Pulse Off Time ◽  
Machining Parameter ◽  
Wedm Process

The present work is aimed at optimizing the cutting rate (CR), surface roughness (Ra) and dimensional deviation (DD) in wire electrical discharge machining (WEDM) of EN-31 steel considering various input parameters such as pulse-on-time, pulse-off-time, wire tension, spark gap set voltage and servo feed. A face centered central composite design of response surface methodology (RSM) has been adopted to develop the empirical model for the responses. It is often desired to obtain a single parameter setting that can decrease Ra and DD and increase CR simultaneously. Since the responses are conflicting in nature, it is difficult to obtain a single combination of cutting parameters satisfying all the objectives in any one solution. The optimum search of the machining parameter values for maximization of CR and minimization of Ra and DD are formulated as a multi-objective, multi-variable, nonlinear optimization problem using genetic algorithm weighted sum method to evaluate the performance.

Sign in / Sign up

Export Citation Format

Share Document