scholarly journals Artificial Intelligence-Based Hole Quality Prediction in Micro-Drilling Using Multiple Sensors

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 885 ◽  
Author(s):  
Jitesh Ranjan ◽  
Karali Patra ◽  
Tibor Szalay ◽  
Mozammel Mia ◽  
Munish Kumar Gupta ◽  
...  
Keyword(s):  
Condition Monitoring ◽  
Fuzzy Inference ◽  
Wavelet Packet ◽  
Vibration Signal ◽  
Tool Condition Monitoring ◽  
Hole Quality ◽  
Inference System ◽  
Tool Condition ◽  
Micro Drilling ◽  
Sensor Signals

The prevalence of micro-holes is widespread in mechanical, electronic, optical, ornaments, micro-fluidic devices, etc. However, monitoring and detection tool wear and tool breakage are imperative to achieve improved hole quality and high productivity in micro-drilling. The various multi-sensor signals are used to monitor the condition of the tool. In this work, the vibration signals and cutting force signals have been applied individually as well as in combination to determine their effectiveness for tool-condition monitoring applications. Moreover, they have been used to determine the best strategies for tool-condition monitoring by prediction of hole quality during micro-drilling operations with 0.4 mm micro-drills. Furthermore, this work also developed an adaptive neuro fuzzy inference system (ANFIS) model using different time domains and wavelet packet features of these sensor signals for the prediction of the hole quality. The best prediction of hole quality was obtained by a combination of different sensor features in wavelet domain of vibration signal. The model’s predicted results were found to exert a good agreement with the experimental results.

Tool Condition Monitoring Based on Radial Basis Probabilistic Neural Networks and Improved Genetic Algorithm

2010 ◽  
Vol 139-141 ◽  
pp. 2522-2526
Author(s):  
Deng Wan Li ◽  
Hong Li Gao ◽  
Yun Shou ◽  
Peng Du ◽  
Ming Heng Xu
Keyword(s):  
Genetic Algorithm ◽  
Condition Monitoring ◽  
Recognition Rate ◽  
Principal Component ◽  
Vibration Signal ◽  
Tool Condition Monitoring ◽  
Cutting Condition ◽  
Improved Genetic Algorithm ◽  
Tool Condition ◽  
Radial Basis

In order to accurately estimate tool life for milling operation, a novel tool condition monitoring system was proposed to improve classifying precision in different cutting condition. Lots of features were extracted from cutting forces signal, vibration signal and acoustic emission signal by different signal processing method, only a few features selected by principal component analysis (PCA) according to contribution rate, and constructed as input vector. The relation between tool condition and features was built by radial basis probability neural network which control parameter of kernel function and hidden central vector were optimized by improved genetic algorithm. The experimental results show that the method proposed in the paper achieves higher recognition rate, good generalization ability and better available practicality.

A New Method for Real-Time Tool Condition Monitoring in Transfer Machining Stations1

2000 ◽  
Vol 123 (2) ◽  
pp. 339-347 ◽  
Author(s):  
Ya Wu ◽  
Philippe Escande ◽  
R. Du
Keyword(s):  
Decision Making ◽  
Condition Monitoring ◽  
Wavelet Packet ◽  
Signal Reconstruction ◽  
Spindle Motor ◽  
Tool Condition Monitoring ◽  
New Method ◽  
Wavelet Packets ◽  
Tool Condition ◽  
Threshold Crossing

This paper introduces a new method for tool condition monitoring in transfer machining stations. The new method is developed based on a combination of wavelet transform, signal reconstruction, and the probability of threshold crossing. It consists of two parts: training and decision making. Training is aimed at determining the alarm threshold and it is done in six steps: (1) Calculate the wavelet packet transform of the sensor signals (spindle motor current) obtained from normal tool conditions. (2) Select feature wavelet packets that represent the principal components of the signals. (3) Reconstruct the signals from the feature wavelet packets (this removes the unwanted noises). (4) Calculate the statistics of the reconstructed signals. (5) Calculate the alarm thresholds based on the statistics of the reconstructed signals, and (6) Calculate the probability of the threshold crossing (the number of threshold crossing conforms a Poisson distribution). The decision making is done in two steps: (1) Check the threshold crossing, and (2) Calculate the number of threshold crossing to determine whether an alarm shall be given. As demonstrated using a practical example from a drilling transfer station, the new method is effective with a success rate over 90 percent. Also, it is fast (the monitoring decision can be done in milliseconds) and cost-effective (the implementation cost shall be less than $500).

scholarly journals Automatic selection of representative parts of the sensor signals for tool condition monitoring

Mechanik ◽  
2016 ◽  
pp. 1416-1417
Author(s):  
Krzysztof Błażejak ◽  
Sebastian Bombiński ◽  
Mirosław Nejman ◽  
Krzysztof Jemielniak
Keyword(s):  
Condition Monitoring ◽  
Tool Condition Monitoring ◽  
Tool Condition ◽  
Automatic Selection ◽  
Sensor Signals ◽  
Selection Of

ANFIS Building Methodology for the Task of Cutting Tool Condition Diagnosis Using Matlab Software

2013 ◽  
Vol 581 ◽  
pp. 466-471
Author(s):  
V.O. Zaloha ◽  
Ruslan M. Zinchenko ◽  
Anna V. Honshchyk
Keyword(s):  
Manufacturing Process ◽  
Cutting Tool ◽  
Fuzzy Inference ◽  
Vibration Signal ◽  
Matlab Software ◽  
Inference System ◽  
Tool Condition ◽  
Neuro Fuzzy ◽  
Tool Replacement ◽  
Condition Diagnosis

Machining of materials with cutting still covers a significant part of shapegenerating operations in manufacturing process. One of the most important tasks in research touches upon the area of cutting is the development of a method which can insure: required productivity, high accuracy of machining, optimal usage of cutting tool and machine-tool resource, automation of manufacturing process, reduction of machinetool down time and cutting tool costs. In this connection cutting tool condition diagnosis (CTCD) becomes an important requirement for the realization of computer-aided manufacturing. The real-time CTCD allows improving the efficiency of machining with the opportune cutting tool replacement and the prior prevention of its catastrophic wear or breakdown. The main goal of this investigation is the verification of the ANFIS working capacity for the description of the relation between the flank wear of cutting tool and the power of vibration signal received during CTCD in turning by means of Matlab software. Consequently, the methodology of building the adaptive neuro-fuzzy inference system (ANFISnetwork) for the task of cutting tool condition diagnosis is worked out.

Sign in / Sign up

Export Citation Format

Share Document