Milling Tool Wear Prediction Method Based on Deep Learning Under Variable Working Conditions

Wang, Mingwei; Zhou, Jingtao; Gao, Jing; Li, Ziqiu

doi:10.1109/access.2020.3010378

Cited by 57 publications

(17 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They both solve the problems of gradient explosion, gradient disappearance, and insufficient long-term memory capacity of traditional recurrent neural networks while introducing the temporal feedback mechanism, and thus effectively utilize the previous temporal information and improve the model reliability. LSTM has been successfully used for anomaly detection in mechanical equipment [28], the authors' team [12,23] also proposed the use of LSTM to predict the tool wear state under different working conditions. Compared with the standard LSTM network, the GRU network structure is more streamlined and computationally simpler.…”

Section: Recurrent Neural Networkmentioning

confidence: 99%

“…The rapid development in the field of computer science such as machine learning, deep learning, provides new data-driven ideas for discovering patterns in machining processes from these data [11], especially for complex, dynamic and even chaotic manufacturing processes reflecting great advantages, such as applications in tool condition monitoring [12], machining accuracy prediction [13], and machining deformation prediction problems [14]. Inspired by this, this paper proposes a CNN-based feature extraction of time-varying working conditions of machining process, with GRU-based learning of dynamic time-series relationship between variable working conditions and clamping point force for clamping point force prediction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CNN-GRU network-based force prediction approach for variable working condition milling clamping points of deformable parts

Zhou

Yang

et al. 2022

Int J Adv Manuf Technol

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Recurrent Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

CNN-GRU network-based force prediction approach for variable working condition milling clamping points of deformable parts

Zhou

Yang

et al. 2022

Int J Adv Manuf Technol

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep convolutional neural networks have achieved state-of-the-art results in many imaging recognition tasks, therefore they are increasingly applied to make predictions analyzing tool wear images [ 22 , 23 , 24 ]. It could be a very efficient method to exclude relative numerical features as well [ 25 , 26 , 27 ]. However, the provided accuracy results of different ML methods vary considerably, ranging from 50% to 100% [ 18 , 19 , 21 , 28 ], depending on the derived features, experimental conditions, the prediction task (classification or regression), the parameters of the ML model and etc.…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning Approach for Wear Monitoring of End Mill by Self-Powering Wireless Sensor Nodes

Ostaševičius

Karpavicius

Paulauskaitė-Tarasevičienė

et al. 2021

Sensors

View full text Add to dashboard Cite

There are many tool condition monitoring solutions that use a variety of sensors. This paper presents a self-powering wireless sensor node for shank-type rotating tools and a method for real-time end mill wear monitoring. The novelty of the developed and patented sensor node is that the longitudinal oscillations, which directly affect the intensity of the energy harvesting, are significantly intensified due to the helical grooves cut onto the conical surface of the tool holder horn. A wireless transmission of electrical impulses from the capacitor is proposed, where the collected electrical energy is charged and discharged when a defined potential is reached. The frequency of the discharge pulses is directly proportional to the wear level of the tool and, at the same time, to the surface roughness of the workpiece. By employing these measures, we investigate the support vector machine (SVM) approach for wear level prediction.

show abstract

“…Li et al [18] developed a convolutional neural network (CNN) to capture multisource data for industrial production monitoring. Wang et al [19] proposed a novel SAE-LSTM for tool wear prediction under variable working conditions.…”

Section: Introductionmentioning

confidence: 99%

Multi-Step-Ahead Tool State Monitoring Using Clustering Feature-Based Recurrent Fuzzy Neural Networks

Yao

Zhang

2021

IEEE Access

View full text Add to dashboard Cite

Reliable and precise multi-step-ahead tool wear state prediction is significant to modern industries for maintaining part quality and reducing cost. This study proposes a Clustering Feature-based Recurrent Fuzzy Neural Network (CFRFNN) for tool wear state monitoring and remaining useful life (RUL) prediction based on K-means Clustering, Recurrent Fuzzy Neural Network (RFNN) and Genetic Algorithm (GA). K-means Clustering method is utilized to realize tool wear state definition and input signal division, which reduces the dependence on the prior knowledge of tool wear degree and improves the prediction accuracy. Then, an enhanced RFNN model is designed and applied on the clustered features to predict tool wear state. The optimized GA technique is helpful for adaptive optimization of model parameters, which significantly improves convergence rate and prediction accuracy. The experiments on tool state prediction are performed to validate superiority of CFRFNN, and the results demonstrate that the proposed network could reasonably configure the complex non-stationary tool wear process and have high prediction accuracy of tool wear state.INDEX TERMS Multi-step-ahead tool state prediction, remaining useful life (RUL), recurrent fuzzy neural network (RFNN), tool wear monitoring.

show abstract

Milling Tool Wear Prediction Method Based on Deep Learning Under Variable Working Conditions

Cited by 57 publications

References 21 publications

CNN-GRU network-based force prediction approach for variable working condition milling clamping points of deformable parts

CNN-GRU network-based force prediction approach for variable working condition milling clamping points of deformable parts

A Machine Learning Approach for Wear Monitoring of End Mill by Self-Powering Wireless Sensor Nodes

Multi-Step-Ahead Tool State Monitoring Using Clustering Feature-Based Recurrent Fuzzy Neural Networks

Contact Info

Product

Resources

About