Tool condition monitoring technique for deep-hole drilling of large components based on chatter identification in time–frequency domain

Measurement ◽  
2017 ◽  
Vol 103 ◽  
pp. 199-207 ◽  
Author(s):  
Masahiro Uekita ◽  
Yasuhiro Takaya
Keyword(s):  
Frequency Domain ◽  
Condition Monitoring ◽  
Tool Condition Monitoring ◽  
Hole Drilling ◽  
Deep Hole ◽  
Deep Hole Drilling ◽  
Time Frequency ◽  
Chatter Identification ◽  
Tool Condition ◽  
Monitoring Technique

scholarly journals Frequency and Time-Frequency Analysis of Cutting Force and Vibration Signals for Tool Condition Monitoring

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 6400-6410 ◽  
Author(s):  
Juan C. Jauregui ◽  
Juvenal R. Resendiz ◽  
Suresh Thenozhi ◽  
Tibor Szalay ◽  
Adam Jacso ◽  
...  
Keyword(s):  
Cutting Force ◽  
Condition Monitoring ◽  
Frequency Analysis ◽  
Tool Condition Monitoring ◽  
Vibration Signals ◽  
Time Frequency Analysis ◽  
Time Frequency ◽  
Tool Condition

Tool Condition Monitoring Using the Electromotive Force from the Chip-Tool Thermocouple

2015 ◽  
Vol 798 ◽  
pp. 271-275
Author(s):  
Rubens Roberto Ingraci Neto ◽  
Renan Luis Fragelli ◽  
Arthur Alves Fiocchi ◽  
Luiz Eduardo de Angelo Sanchez
Keyword(s):  
Neural Network ◽  
Condition Monitoring ◽  
Electromotive Force ◽  
Cutting Tool ◽  
Low Cost ◽  
Maximum Error ◽  
Tool Condition Monitoring ◽  
Machining Processes ◽  
Time Frequency ◽  
Tool Condition

Tool condition monitoring systems are extensively study. However, the machining processes are non-stationary and comprise many details that interfere in its monitoring. Aiming to develop a simple, low cost and efficient tool condition monitoring system, this study analyzed the electromotive force (EMF) from a chip-tool thermocouple in turning tests with AISI 1045. Since EMF comprises time and frequency variations related to machining conditions a Wavelet Packet Transform extracted the signals features from EMF. These signals features fed inputs of a neural network that aimed to evaluate the cutting tool maximum flank wear. The maximum error of the neural network was 1.88% for tested signals. Moreover, EMF showed changes that allow the detection of cutting tool breakage. Therefore, the chip-tool thermocouple may be a promising method for tool condition monitoring. This is the first report of electromotive force analysis in time-frequency domain aiming to quantify the wear of the cutting tool and evaluate its condition.

Research on Tool Condition Monitoring System in Auto-Balancing Machines

2010 ◽  
Vol 437 ◽  
pp. 497-501
Author(s):  
Ding Ding Zhao ◽  
Ping Cai
Keyword(s):  
Frequency Domain ◽  
Monitoring System ◽  
Condition Monitoring ◽  
Working Condition ◽  
Spindle Motor ◽  
Servo Motor ◽  
Time Frequency ◽  
Motor Current ◽  
Tool Condition ◽  
Condition Monitoring System

A drill set working condition monitoring system is introduced and investigated to improve the performance of auto-balancing machine. The experiment setup to acquire data of armature currents of spindle and servo motors is constructed. The features of the armature currents of both spindle motor and servo motor in time domain, frequency domain and time-frequency domain are extracted respectively, and they are fused separately by two distinct RBF ANNs to get the primary fusing results. The primary results are fused by the third RBF ANN to get a comprehensive result. Experiment results demonstrate that the servo motor current has a closer relation with drill set working condition than that of spindle motor, and two successive fusing operations can achieve more reliable recognition with a correctness up to 86.67%.

scholarly journals A Multisensor Fusion Method for Tool Condition Monitoring in Milling

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3866 ◽  
Author(s):  
Yuqing Zhou ◽  
Wei Xue
Keyword(s):  
Feature Selection ◽  
Condition Monitoring ◽  
Optimal Parameter ◽  
Tool Condition Monitoring ◽  
Numerical Control ◽  
Selection Methods ◽  
Statistical Parameters ◽  
Time Frequency ◽  
Feature Parameters ◽  
Tool Condition

Tool fault diagnosis in numerical control (NC) machines plays a significant role in ensuring manufacturing quality. Tool condition monitoring (TCM) based on multisensors can provide more information related to tool condition, but it can also increase the risk that effective information is overwhelmed by redundant information. Thus, the method of obtaining the most effective feature information from multisensor signals is currently a hot topic. However, most of the current feature selection methods take into account the correlation between the feature parameters and the tool state and do not analyze the influence of feature parameters on prediction accuracy. In this paper, a multisensor global feature extraction method for TCM in the milling process is researched. Several statistical parameters in the time, frequency, and time–frequency (Wavelet packet transform) domains of multiple sensors are selected as an alternative parameter set. The monitoring model is executed by a Kernel-based extreme learning Machine (KELM), and a modified genetic algorithm (GA) is applied in order to search the optimal parameter combinations in a two-objective optimization model to achieve the highest prediction precision. The experimental results show that the proposed method outperforms the Pearson’s correlation coefficient (PCC) based, minimal redundancy and maximal relevance (mRMR) based, and Principal component analysis (PCA)-based feature selection methods.

scholarly journals Condition Monitoring in Drilling Operation based on Vibration Signals

2019 ◽  
Vol 8 (3) ◽  
pp. 1272-1277
Keyword(s):  
Neural Network ◽  
Frequency Domain ◽  
Condition Monitoring ◽  
Time Domain ◽  
Flank Wear ◽  
Tool Condition Monitoring ◽  
Vibration Signals ◽  
Drilling Operation ◽  
Tool Condition ◽  
The Time Domain

Tool condition monitoring is the efficient process for all machining managing operation and the maintenance of machinery operation. Tool condition monitoring implies effective production cost, the rate of tool life, tool quality, dimensional accuracy in terms of tolerance and surface finish in machine shop. Here the machining operation is fully depending on the whims & fancies of the operator. So when a new person operating the machine it makes more troubles in terms to find out the tool wearing point and it make operation difficulty by the operator. To overcome this difficulty a systematic methodology required for machining operation. This paper deals with monitoring the condition on the drilling operation with the help of Accelerometer sensor a physical vibration model 8636C50 having a broad band sensitivity of Sensitivity (±5%) 100.0mV/g and resonant frequency up to 22.0 kHz and performing the drilling operation on EN 24 steel at various operation parameters and analyzing the time domain signal response and frequency domain response graph and implemented analyze the feasibility of proposed methodology for practical applications. Further, the Lab View was used to predict amplitude of work piece vibration which determines the tool condition after various experimental tests. In the time domain, the characteristic parameter during drill wear represent RMS value increase in flank wear and also shows the linear relationship between these two. In the frequency domain, the characteristic parameters during drill failure represent the magnitude of vibration amplitude and the increase in flank wear. Here multilayer Artificial Neural Network (ANN) model, Fuzzy Neural Network and Taguchi Method have been trained with the experimental data using back propagation algorithm. Condition monitoring of drilling is fully depending on the vibration signals. Based on the vibration signal the tool wear point is found out. Experiments results indicated the effect of unconditional drilling operation and detected the tool failure and proper operating condition for drilling machining.

Sign in / Sign up

Export Citation Format

Share Document