An adaptive, artificial intelligence-based chatter detection method for milling operations

Stavropoulos, Panagiotis; Souflas, Thanassis; Papaioannou, Christos; Bikas, Harry; Mourtzis, Dimitris

doi:10.1007/s00170-022-09920-8

Cited by 24 publications

(11 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method decomposes the vibration signal to extract features in different simultaneous frequency domains and uses support vector machines to make predictions about system stability. The method was tested to achieve a classification accuracy of 93 % and a detection time of only 26.1 ms [8]. In order to quickly and correctly detect chatter, Gao and his team suggested a multi-sensor signal fusion-based chatter detection approach.…”

Section: Related Workmentioning

confidence: 99%

Frequency monitoring analysis of milling edge chatter in composites using WPD for frequency band selection

Liu

2024

J. vibroeng.

View full text Add to dashboard Cite

In the milling process of composite materials, the initial chatter frequency is not obvious and is easily swamped by the rest of the signals, making frequency monitoring difficult, so the study proposes a chatter frequency monitoring method based on frequency cancellation algorithms and wavelet packet decomposition. The results of the experiments shown that the frequency cancellation algorithm can successfully remove invalid signals, such as spindle rotation frequency and cutter tooth frequency, and only keep the necessary signals, at which point the chattering frequency may be observed at a frequency of roughly 1333 Hz. The influence of the frequency bands s5, s9, s10, s12, and s13 after de-frequency removal should be avoided because they all have a low energy share of roughly 23 %, 0.9 %, 5 %, 10 %, and 16 %, respectively, and are less sensitive to chatter. For milling edge depths of 0.5 mm, 2 mm, and 4 mm, the average chatter thresholds were around 3.27, 2.9, and 2.89, respectively. It was challenging to pinpoint the chatter of the system because the empirical modal decomposition observed an average chatter energy entropy of just 1.55 and found that its fluctuations at the milling edge depth junction were insignificant. On the other hand, the chattering could be plainly seen since the energy entropy experienced a substantial and dramatic fluctuation at the intersection of the milling edge depth when it was about 2.9, 2.6, and 2.5, respectively. The experimental findings demonstrated that the frequency cancellation technique and wavelet packet decomposition-based chattering frequency monitoring approach can precisely track the chattering state of the system.

show abstract

Section: Related Workmentioning

confidence: 99%

Frequency monitoring analysis of milling edge chatter in composites using WPD for frequency band selection

Liu

2024

J. vibroeng.

View full text Add to dashboard Cite

show abstract

“…The sensor output will be used for control actions [26]. The literature compared data-driven choices vs. simulation-based solutions [27][28][29].…”

Section: Modelingmentioning

confidence: 99%

“…The sensor output will be used for control actions [26]. The literature compared data-driven choices vs. simulation-based solutions [27][28][29]. The specific beam model simulated with two-dimensional finite elements has been chosen because it can be modeled and advanced control techniques can be applied to it that take into account modeling essentials such as unknown disturbances and Vibration 2023, 6, FOR PEER REVIEW 3 positions 3 and 4, i.e., in the second half.…”

Section: Modelingmentioning

confidence: 99%

“…The sensor output will be used for control actions [26]. The literature compared data-driven choices vs. simulation-based solutions [27][28][29]. The specific beam model simulated with two-dimensional finite elements has been chosen because it can be modeled and advanced control techniques can be applied to it that take into account modeling essentials such as unknown disturbances and The specific beam model simulated with two-dimensional finite elements has been chosen because it can be modeled and advanced control techniques can be applied to it that take into account modeling essentials such as unknown disturbances and uncertainties of modeling.…”

Section: Modelingmentioning

confidence: 99%

See 1 more Smart Citation

Optimal Placement and Active Control Methods for Integrating Smart Material in Dynamic Suppression Structures

Moutsopoulou,

Stavroulakis,

Petousis

et al. 2023

Vibration

View full text Add to dashboard Cite

To simulate a lightweight structure with integrated actuators and sensors, two-dimensional finite elements are utilized. The study looks at the optimal location and active vibration control for a piezoelectric smart flexible structure. Intelligent applications are commonly used in engineering applications. In computational mechanics, selecting the ideal position for actuators to suppress oscillations is crucial. The structure oscillates due to dynamic disturbance, and active control is used to try to reduce the oscillation. Utilizing an LQR and Hinfinity controller, optimization is carried out to determine the best controller weights, which will dampen the oscillation. Challenging issues arise in the design of control techniques for piezoelectric smart structures. Piezoelectric materials have been investigated for use in distributed parameter systems (for example airplane wings, intelligent bridges, etc.) to provide active control efficiently and affordably. Still, no full suppression of the oscillation with this approach has been achieved so far. The controller’s order is then decreased using optimization techniques. Piezoelectric actuators are positioned optimally according to an enhanced optimization method. The outcomes demonstrate that the actuator optimization strategies used in the piezoelectric smart single flexible manipulator system have increased observability in addition to good vibration suppression results.

show abstract

“…The mechanism of the surface microroughness formation , alongside with numerous uncontrolled factors of the technological process, makes it practically impossible to directly solve the forecasting problem at the stage of developing the technological process [28][29][30]. The most common approach [31] to achieve a required roughness involves the assignment of low milling modes, which do not guarantee either the require surface quality or high material removal rates. There exist approaches based on the theory of shaping and cutting [32,33], the theoretical justification of which is based on the kinematics of the process, the geometric parameters of the cutting tool and the mechanism of chip formation Algorithms and methods of computer-aided design (CAD) are used to achieve the connection of graphic models of cutter during the formation of the initial tool surface, which can simulate the creation of a topography on the surface being machined, thereby serving as the main data set for predicting and evaluating the workpiece surface roughness of under certain operational conditions [34].…”

Section: Introductionmentioning

confidence: 99%

New optical imaging system for determining wear criteria for cutting inserts

Pivkin¹,

Гречишников²,

Ershov³

et al. 2022

Optical Metrology and Inspection for Industrial Applications IX

View full text Add to dashboard Cite

In mechanical engineering, cutting tool wear is a major factor in the functional and parametric failure of a cutting tool. The loss of tool performance causes failures in the production of suitable products, as well as machine downtime. In this connection, accurate measurement of wear of the cutting wedge at various stages of the technological process is extremely important. The article proposes a method for recognizing wear zones on the back surfaces of cutting inserts by image processing. Indicators have been formed for assigning a failure criterion for various quality factors. For the formation of a measurement system, a three-stage control method with the rationale for operational recommendations is proposed. The correlation of wear by image processing has been compared with the optical method currently applied in manual mode, which greatly reduces the efficiency of production quality control.

show abstract

An adaptive, artificial intelligence-based chatter detection method for milling operations

Cited by 24 publications

References 45 publications

Frequency monitoring analysis of milling edge chatter in composites using WPD for frequency band selection

Frequency monitoring analysis of milling edge chatter in composites using WPD for frequency band selection

Optimal Placement and Active Control Methods for Integrating Smart Material in Dynamic Suppression Structures

New optical imaging system for determining wear criteria for cutting inserts

Contact Info

Product

Resources

About