•VMD is an effective method for extracting time–frequency feature of chatter.•When the kurtosis of reconstruction signal is the biggest, the VMD’s parameters at this moment are the best ...parameters.•Chatter frequency is not equal to the domain frequency and the multiple frequency but has larger amplitude.•The best IMF is not the biggest energy entropy, but is the IMF except the domain and multiple frequency bands.•The instantaneous frequency analysis can judge whether the IMF includes the chatter frequencies.
This paper presents a novel approach to detect the milling chatter based on Variational Mode Decomposition (VMD) and energy entropy. VMD has already been employed in feature extraction from non-stationary signals. The parameters like number of modes (K) and the quadratic penalty (α) need to be selected empirically when raw signal is decomposed by VMD. Aimed at solving the problem how to select K and α, the automatic selection method of VMD’s based on kurtosis is proposed in this paper. When chatter occurs in the milling process, energy will be absorbed to chatter frequency bands. To detect the chatter frequency bands automatically, the chatter detection method based on energy entropy is presented. The vibration signal containing chatter frequency is simulated and three groups of experiments which represent three cutting conditions are conducted. To verify the effectiveness of method presented by this paper, chatter feather extraction has been successfully employed on simulation signals and experimental signals. The simulation and experimental results show that the proposed method can effectively detect the chatter.
During metal cutting, chatter is prone to the effects of poor surface quality and tool wear. Therefore, chatter detection is becoming more and more important. The current hot methods are effective, ...but they also have limitations, such as the interference of human experience on the results, the need to label the data, and it takes a long time. This paper proposes an unsupervised milling chatter detection method based on a large number of unlabeled dynamic signals. The method does not depend on processing parameters and environment, does not require labels, and has strong stability. Based on auto-encode, each segment of the signal is compressed into two dimensions, and the feasibility of the reconstruction scheme is verified by numerical analysis. In the normalization algorithm, the similarity between the raw signal and the reconstructed signal is the highest, and the reconstruction effect is the best. Then, the compressed signals are clustered based on a hybrid clustering method combining GMM and K-means. Under the six evaluation indicators, compared with GMM, the clustering results of this scheme have been significantly improved. The evaluation metrics show that GMM-K-means is not only more stable but also has better result compared to K-means in chatter detection. The results show that the proposed method outperforms GMM and K-means in all six typical unsupervised evaluation metrics, and can detect chatter effectively.
Display omitted
•The ILR-DNN is an effective approach for online chatter detection considering the beat effect.•The LSTM branch can capture the amplitude modulation characteristic induced by the beat ...effect.•The Inception branch helps to extract multiscale features concerning different machining states.•Results show the ILR-DNN achieves the detection accuracy as high as 97.29%.
Chatter is an unstable and self-excited vibration that adversely affects part quality and tool life in various machining processes. To achieve high-performance machining, chatter identification has attracted considerable interest from many researchers in recent decades. Nevertheless, most existing chatter detection approaches fail to consider the presence of the beat effect, which is an interference pattern caused by slightly different chatter frequencies. The neglect of the beat effect would seriously degrade the effectiveness of these methods and even result in false alarms. In this paper, a novel deep neural network combining the Inception module, long short-term memory (LSTM) and residual networks (ILR-DNN) is proposed for online chatter detection considering the presence of the beat effect. The ILR-DNN automatically extracts insightful features from two branches. One branch is a two-layer LSTM network that can capture temporal characteristics of the chatter development process from the raw cutting force. In the other branch, a two-layer Inception network consisting of multiple convolutional kernel size filters extracts multiscale features from the FFT spectrum of the cutting force. Afterwards, the extracted features are concatenated and go through a residual network to alleviate the gradient disappearing during deep-layer network training. Finally, the fully-connected and softmax layers are employed to make a final classification. Machining tests are carried out, and cutting forces are collected to validate the feasibility and effectiveness of the proposed chatter detection method. Results show that the proposed ILR-DNN achieves much better performance than other methods in distinguishing machining states, i.e., stable machining, chatter with the beat effect, and chatter without the beat effect.
•The proposed method can simultaneously identify chatter and tool wear failure coupled condition.•The complexity of multi-sensor features is reduced by upgraded principal component analysis ...algorithm.•The identification accuracy of multi-condition can be improved by a new extracted signal feature.•The experimental efficiency is improved by the design of process parameters.•The identification accuracy of the proposed method is much higher than that of traditional methods.
Chatter and tool wear always coexist during the milling of Ti-6Al-4V thin-walled parts, while the boundary characteristics, time-varying, modal coupling, and position dependence characteristics in milling thin-walled parts lead to the variable spatial time–frequency distribution of the signal features related to milling conditions. As a result, the existing milling monitoring methods can only identify single chatter or tool wear while ignoring another condition. Therefore, in order to identify the chatter and tool wear simultaneously, a multi-condition identification method based on sensor fusion is proposed by fusing multi-source heterogeneous data with different spatial time–frequency distributions. Multi-sensor features of the milling process are extracted from sound, acceleration, and cutting bending moment signals. To reduce the complexity of the original feature dataset, an upgraded principal component analysis (UPCA) algorithm is proposed by screening sensor features in specific frequency bands. Moreover, a new signal feature considering energy proportion is extracted to improve the identification accuracy of multiple conditions. The process parameters are designed according to the stability lobe diagram (SLD) to improve the experimental efficiency. The experimental results show that the proposed method can identify the multi-milling condition composed of chatter and tool wear failure. With the help of UPCA and energy proportion, the computational efficiency is also improved, and the identification accuracy of the proposed method reaches 93.75%, which is much higher than the accuracy of classifiers with traditional data processing methods.
Chatter is one of the most unexpected and uncontrollable phenomenon during the milling operation. It is very important to develop an effective monitoring method to identify the chatter as soon as ...possible, while existing methods still cannot detect it before the workpiece has been damaged. This paper proposes an energy aggregation characteristic-based Hilbert–Huang transform method for online chatter detection. The measured vibration signal is firstly decomposed into a series of intrinsic mode functions (IMFs) using ensemble empirical mode decomposition. Feature IMFs are then selected according to the majority energy rule. Subsequently Hilbert spectral analysis is applied on these feature IMFs to calculate the Hilbert time/frequency spectrum. Two indicators are proposed to quantify the spectrum and thresholds are automatically calculated using Gaussian mixed model. Milling experiments prove the proposed method to be effective in protecting the workpiece from severe chatter damage within acceptable time complexity.
•Signal energy distribution transition when chatter develops is analyzed.•The energy aggregation process is adopted as the basis of the detection method.•A revised Hilbert-Huang transform is proposed to process the signal.•Two indicators are proposed to quantify the spectrum.•Thresholds are automatically determined using Gaussian mixed model.•Comparisons are made with existing wavelet method.•Experiments prove the method to be effective within acceptable time complexity.
Chatter in robotic milling is closely related to robot postures and cutting parameters. The chatter frequency varies over a wide range compared with that in the milling process using traditional ...machine tools. These features pose a significant challenge to chatter detection in robotic milling. The objective of this paper is to propose a novel approach for early and reliable chatter detection in robotic milling under variable robot postures and cutting parameters. First, the inertance frequency response function under each robot posture is used to filter the corresponding vibration signals. This minimizes the influence of robot postures on the measured vibration signals. Second, based on the filtered vibration data, a dual-tree complex wavelet packet transform is applied to extract the energy of different frequency bands, from which the fractional energy entropy is obtained to characterize the chatter state. Therefore, the chatter state can be characterized as independent of the variable cutting parameters and chatter frequencies. Third, online chatter detection is achieved using the sequential probability ratio test, with which significance tests for the chatter states are conducted. Consequently, the detection threshold does not need to be manually set. Extensive case studies demonstrate that the proposed approach can realize early and reliable chatter detection in robotic milling under variable robot postures and cutting parameters.
•The inertance FRF is used as a special filter to filter the vibration signals.•The DTCWPT is used to decompose the signals into multiple sub-bands.•A probabilistic model of energy entropy for chatter detection is developed.
Chatter is a self-excited vibration phenomenon occurring in the cutting process, and the onset of chatter will result in the worse machined surface and the redistribution of frequency and energy. ...Although the exploration of chatter has been continued for many years, there are still some problems to be researched in detail. The early researches are mainly focused on the prediction of stability with the aid of dynamic model, which is an off-line means. With the advancement of sensor technology, the on-line chatter detection has been investigated extensively. For the detection of chatter, it can be divided into four steps. First, the experiment data are obtained with various sensors, such as dynamometer, accelerometer and microphone. Second, the acquired signal is processed by some theoretical methods including time domain method, frequency domain method and time-frequency domain method. Third, different features are calculated and selected to indicate the cutting status. Finally, a decision is made based on the threshold method or intelligent recognition algorithm. This article comprehensively reviews the state of the art on the detection methods of the machining chatter.
This paper introduces a newly developed multi-sensor data fusion for the milling chatter detection with a cheap and easy implementation compared with traditional chatter detection schemes. The ...proposed multi-sensor data fusion utilizes microphone and accelerometer sensors to measure the occurrence of chatter during the milling process. It has the advantageous over the dynamometer in terms of easy installation and low cost. In this paper, the wavelet packet decomposition is adopted to analyze both measured sound and vibration signals. However, the parameters of the wavelet packet decomposition require fine-tuning to provide good performance. Hence the result of the developed scheme has been improved by optimizing the selection of the wavelet packet decomposition parameters including the mother wavelet and the decomposition level based on the kurtosis and crest factors. Furthermore, the important chatter features are selected using the recursive feature elimination method, and its performance is compared with metaheuristic algorithms. Finally, several machine learning techniques have been adopted to classify the cutting stabilities based on the selected features. The results confirm that the proposed multi-sensor data fusion scheme can provide an effective chatter detection under industrial conditions, and it has higher accuracy than the traditional schemes.
•Introducing a cost-effective multi-sensor data fusion for the milling chatter detection.•The WPD is utilized and tuned based on the kurtosis and crest factors.•The irrelevant features are identified and eliminated utilizing the RFE method.•Several machine learning techniques have been adopted to identify chatter vibration.
This paper presents a novel approach to detect the milling chatter based on energy entropy. By using variational mode decomposition and wavelet packet decomposition, the cutting force signal is ...decomposed into two group of sub-signals respectively, and each component has limited bandwidth in spectral domain. Since milling chatter is characterized by the change of frequency and energy distribution. Therefore the energy features extracted from the two group of sub-signals are considered and the energy entropies are obtained, which can be utilized to demonstrate the condition of the milling system synthetically. Several milling tests are conducted and the results show that the proposed method can effectively detect the chatter at an early stage.
•A new approach is presented to detect milling chatter in peripheral milling.•The non-stationary chatter signal is decomposed based on the VMD and WPD.•Energy entropy are utilized to demonstrate the condition of milling system.•The method has an excellent performance for chatter identification.
•Optimized variational mode decomposition is proposed to adaptively decompose a chatter signal.•The novel chatter monitoring method proposed is suitable for intermittent chatter detection.•A relative ...threshold, rather than an absolute threshold, is adopted due to the multi-working conditions in the cutting process.
In the milling process, chatter, which results in poor surface quality, dimensional errors, and reduced cutter and machine life, is one of the main limitations on performance. Consequently, a reliable, real-time detection method is desired to recognize chatter while it is developing. This study develops a novel method of online chatter identification for milling processes. In this method, optimized variational mode decomposition (OVMD) is used to decompose cutting force measurements, and the sub-components containing chatter information are extracted using a simulated annealing (SA) algorithm. The approximate entropy and the sample entropy are used to detect the onset of chatter. To evaluate the effectiveness of the proposed method, milling operations were performed and force measurements were collected for five types of operating conditions. The results show that the proposed method is suitable for detecting both continuous and intermittent chatter. Rather than establishing an absolute threshold for chatter detection, the onset of chatter is identified from relative changes in the entropy with time that occur under the various cutting conditions. The proposed method is shown to have greater sensitivity and stability than empirical mode decomposition (EMD).