Tool wear monitoring of TC4 titanium alloy milling process based on multi-channel signal and time-dependent properties by using deep learning

Tool wear monitoring is necessary for cost reduction and productivity improvement in the machining industry. Machine learning has been proven to be an effective means of tool wear monitoring. Feature engineering is the core of the machining learning model. In complex parts milling, cutting conditions are time-varying due to the variable engagement between cutting tool and the complex geometric features of the workpiece. In such cases, the features for accurate tool wear monitoring are tricky to select. Besides, usually few sensors are available in an actual machining situation. This causes a high correlation between the hand-designed features, leading to the low accuracy and weak generalization ability of the machine learning model. This paper presents a tool wear monitoring method for complex part milling based on deep learning. The features are pre-selected based on cutting force model and wavelet packet decomposition. The pre-selected cutting forces, cutting vibration and cutting condition features are input to a deep autoencoder for dimension reduction. Then, a deep multi-layer perceptron is developed to estimate the tool wear. The dataset is obtained with a carefully designed varying cutting depth milling experiment. The proposed method works well, with an error of 8.2% on testing samples, which shows an obvious advantage over the classic machine learning method.

Download Full-text

A Neuro-Fuzzy Approach Based Tool Condition Monitoring in AISI H13 Milling

10.20944/preprints201807.0447.v1 ◽

2018 ◽

Author(s):

Md. Shafiul Alam ◽

Maryam Aramesh ◽

Stephen Veldhuis

Keyword(s):

Tool Wear ◽

Monitoring System ◽

Condition Monitoring ◽

Manufacturing Industry ◽

Cutting Tool ◽

Milling Process ◽

Tool Condition Monitoring ◽

Tool Wear Monitoring ◽

Tool Condition ◽

Wear Monitoring

In the manufacturing industry, cutting tool failure is a probable fault which causes damage to the cutting tools, workpiece quality and unscheduled downtime. It is very important to develop a reliable and inexpensive intelligent tool wear monitoring system for use in cutting processes. A successful monitoring system can effectively maintain machine tools, cutting tool and workpiece. In the present study, the tool condition monitoring system has been developed for Die steel (H13) milling process. Effective design of experiment and robust data acquisition system ensured the machining forces impact in the milling operation. Also, ANFIS based model has been developed based on cutting force-tool wear relationship in this research which has been implemented in the tool wear monitoring system. Prediction model shows that the developed system is accurate enough to perform an online tool wear monitoring system in the milling process.

Download Full-text

Tool Wear Monitoring in Milling Processes Based on Cointegration Modeling

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.34-35.1746 ◽

2010 ◽

Vol 34-35 ◽

pp. 1746-1751 ◽

Cited By ~ 1

Author(s):

Yin Hu Cui ◽

Guo Feng Wang ◽

Dong Biao Peng

Keyword(s):

Tool Wear ◽

Milling Process ◽

Support Vector ◽

Tool Wear Monitoring ◽

Machining Processes ◽

Machine Model ◽

Force Signal ◽

Frequency Components ◽

Wear Monitoring ◽

Cointegration Relationship

Tool wear monitoring plays an important role in the automatic machining processes. Therefore, a reliable method is necessary for practical application. In this paper, a new method based on cointegration theory was introduced to extract features from the cutting force signal in the milling process. Cointegration relationship between cutting forces of different directions could be found and the corresponding cointegration vector could also be calculated. In order to improve the reliability of pattern recognition, the cointegration vectors combined with the energy of the high-frequency components of the acoustic emission signals were used as features. Once all the features are extracted, they were trained and tested through a support vector machine model. Experiments were performed to verify this method and the results showed that it could efficiently recognize the tool wear status.

Download Full-text