| 1. |
- Li, Xuebing, et al.
(författare)
-
A data-driven approach for tool wear recognition and quantitative prediction based on radar map feature fusion
- 2021
-
Ingår i: Measurement. - : Elsevier BV. - 0263-2241 .- 1873-412X. ; 185
-
Tidskriftsartikel (refereegranskat)abstract
- Tool wear monitoring during the cutting process is crucial for ensuring part quality and productivity. A datadriven monitoring approach based on radar map feature fusion is proposed for tool wear recognition and quantitative prediction, aiming at tracking the evolution of tool wear comprehensively. Specifically, the sensitive features from multi-source signals are fused by a radar map, and health indicators capable of characterizing the tool wear evolution are obtained. For the recognition of tool wear state and the quantitative prediction of tool wear values, the Adaboost Decision Tree (Adaboost-DT) ensemble learning model and stacked bi-directional long short-term memory (SBiLSTM) deep learning network are established, respectively. Experimental results demonstrated that the proposed approach could recognize the current wear state quickly and accurately whilst predicting wear values based on limited historical data available. Combining tool wear recognition and prediction results contributes to making a more flexible tool replacement decision in intelligent manufacturing processes.
|
|
| 2. |
- Liu, Zhibo, et al.
(författare)
-
Research on Tool Wear Based on 3D FEM Simulation for Milling Process
- 2020
-
Ingår i: JOURNAL OF MANUFACTURING AND MATERIALS PROCESSING. - : MDPI AG. - 2504-4494. ; 4:4
-
Tidskriftsartikel (refereegranskat)abstract
- In the process of metal cutting, the anti-wear performance of the tool determines the life of the tool and affects the surface quality of the workpiece. The finite element simulation method can directly show the tool wear state and morphology, but due to the limitations of the simulation time and complex boundary conditions, it has not been commonly used in tool life prediction. Based on this, a tool wear model was established on the platform of a finite element simulation software for the cutting process of titanium alloy TC4 by end milling. The key technique is to embed different types of tool wear models into the finite element model in combination with the consequent development technology. The effectiveness of the tool wear model was validated by comparing the experimental results with the simulation results. At the same time, in order to quickly predict the tool life, an empirical prediction formula of tool wear was established, and the change course of tool wear under time change was obtained.
|
|
| 3. |
- Yang, Shucai, et al.
(författare)
-
A novel method of experimental evaluation on BTA tool geometries
- 2017
-
Ingår i: The International Journal of Advanced Manufacturing Technology. - : Springer London. - 0268-3768 .- 1433-3015. ; 91:9-12, s. 4253-4261
-
Tidskriftsartikel (refereegranskat)abstract
- Towards the problem of closed space of Boring and Trepanning Association (BTA) drill, this paper presents a novel experimental method to evaluate BTA tool geometries, and a turning-based test is conducted to simulate drilling. The three inserts of BTA drill are replaced by the three turning inserts, the rotation of BTA drill is transformed by workpiece rotation in turning, the feed of BTA drill changes into the feed of turning inserts, and the cutting area per BTA insert is simulated by the cutting depth in turning. To implement the approach, three angles, consisting of edge inclination, flank angle and edge declination, are organised by a three-factor and three-level Taguchi experiment for each BTA insert, e.g. outside insert, centre insert and middle insert. Cutting force, chip patterns and chip curl radius are observed and measured to evaluate the insert geometries.
|
|
| 4. |
- Zhang, Bowen, et al.
(författare)
-
An imbalanced data learning approach for tool wear monitoring based on data augmentation
- 2023
-
Ingår i: Journal of Intelligent Manufacturing. - : Springer Nature. - 0956-5515 .- 1572-8145.
-
Tidskriftsartikel (refereegranskat)abstract
- During cutting operations, tool condition monitoring (TCM) is essential for maintaining safety and cost optimization, especially in the accelerated tool wear phase. Due to the safety constraints of the actual production environment and the tool's properties, the data for each wear stage is usually unbalanced, and these unbalances lead to difficulties in failure monitoring. To this end, a novel TCM method based on data augmentation is proposed, which uses generative adversarial networks (GANs) to generate valuable artificial samples for a few classes to balance the data distribution. Unlike the traditional GANs, the proposed Conditional Wasserstein GAN-Gradient Penalty (CWGAN-GP) avoids pattern collapse and training instability and simultaneously generates more realistic data and signal samples with labels for different wear states. To evaluate the quality of the generated data, an evaluation index is proposed to evaluate the generated data while further screening the samples to achieve effective oversampling. Finally, the continuous wavelet transform (CWT) is combined with the convolutional neural network (CNN) architecture of Inception-ResNet-v2 for TCM, and it is demonstrated that data augmentation can effectively improve the performance of training classification models for unbalanced data by comparing three classification methods with two data augmentation experiments, and the proposed method has a better monitoring performance.
|
|
| 5. |
- Chen, Zhan, et al.
(författare)
-
Iteration based calculation of position and orientation of grinding wheel for solid cutting tool flute grinding
- 2018
-
Ingår i: JOURNAL OF MANUFACTURING PROCESSES. - : ELSEVIER SCI LTD. - 1526-6125. ; 36, s. 209-215
-
Tidskriftsartikel (refereegranskat)abstract
- End mill cutting tools are widely used in machining of curved surface parts in many areas, e.g. aerospace, automobile, and energy. The parameters of helical groove cross section, influencing chip removal capacity, include rake angle, core radius and edge width. Towards a parametrical control algorithm of the cutting tool flute, this paper proposed an iteration based method. Within the context, the cutting tool parameters and grinding wheel are set firstly. Then, three angle parameters, alpha, beta, and theta in the grinding coordinate system, are looped. In each loop, one of the target flute parameters is compared with the pre-set values, and if the parameter is within the range, the calculation goes the next loop until the parameters are in the target range. Since the loop number is so high that the computing time is too long, the patterns between the flute parameters and looped parameters are used to improve the calculation speed. The method is implemented by using C#, and validated by a set of numeric simulation based on Matlab (R).
|
|
| 6. |
- Du, Jianbiao, et al.
(författare)
-
Transient Temperature Field Model of Wear Land on the Flank of End Mills : A Focus on Time-Varying Heat Intensity and Time-Varying Heat Distribution Ratio
- 2019
-
Ingår i: Applied Sciences. - : MDPI. - 2076-3417. ; 9:8
-
Tidskriftsartikel (refereegranskat)abstract
- Modelling methods for the transient temperature field of wear land on the flank of end mills have been proposed to address the challenges of inaccurate prediction in the temperature field of end mills during the high-speed peripheral milling of Ti6Al4V that is a titanium alloy. A transient temperature rise model of wear land on the flank of end mills was constructed under the influence of heat sources in the primary shearing zone (PSZ), rake-chip zone (RCZ), flank-workpiece zone (FWZ), and dissipating heat source. Then the transient temperature field model of wear land on the flank of end mills was constructed. Finally, the transient temperature field model of wear land on the flank of end mills was constructed. Comparison of simulation result and experimental data verified the accuracy of the model. In sum, the proposed model may provide a temperature model support for future studies of flank wear rate in end mill modeling.
|
|
| 7. |
- Hao, Xiaole, et al.
(författare)
-
Modeling of Convex Surface Topography in Milling Process
- 2020
-
Ingår i: Metals. - : MDPI AG. - 2075-4701. ; 10:9
-
Tidskriftsartikel (refereegranskat)abstract
- Cr12MoV die steel is a typical high-strength and high-hardness material. Because of the high hardness of Cr12MoV die steel, which is approximately 50-65 HRC after quenching, and the tool's weak rigidity, cutting vibration, and tool deformation are inevitable during the cutting process. In this paper, a model for predicting the surface topography of a convex curved die steel machined by a ball-end milling cutter was established. In addition, the surface springback of the workpiece is considered. According to the surface characteristics of the convex curved workpiece, the vector algorithm and transformation matrix are applied to calculate the milling cutter motion trajectory equation. Then, the influence of dynamic factors on the tool path is calculated, and finally the surface topography of the workpiece is simulated through the Z-map model. The simulation error of three-dimensional surface roughnessSaat different positions of the curved surface is between 10% and 16%. After considering the dynamic factors, the simulation error is reduced by about 50%.
|
|
| 8. |
- Ji, Wei, et al.
(författare)
-
A reachability based approach for machining feature sequencing
- 2016
-
Ingår i: Journal of manufacturing systems. - : Elsevier. - 0278-6125 .- 1878-6642. ; 40, s. 96-104
-
Tidskriftsartikel (refereegranskat)abstract
- Small and medium-sized enterprises (SMEs) are involved in highly personalised machining equipment and customised products. The trend in manufacturing systems towards higher degree of adaptability and automation has urged SMEs to seek new adaptable approaches for production, especially in the area of machining and process planning. In these areas, Cloud-DPP concept and machining feature (MF) based process sequencing have been proposed for increasing adaptability, and have gained attention recently. Both cutting tool conditions and product requirements are required in MF sequencing. In response to this fact, this paper proposes a reachability based method for MF sequencing which aims to reduce the number of tool changes and to meet specific machining requirements. This method is based on an MF path graph, an adjacency matrix, and a reachability matrix. MF path graph is mapped based on four types of mapping principles (MPs). Here, a basic MP is associated with MF sequencing rules, particular requirement MPs are relevant to machining requirements, and cutting tool MPs refer to MF machining strategies. According to MF path graph, adjacency matrix can be determined, which provides a basic matrix for calculating the reachability matrix. This method can be applied to cross-setup MF sequencing (using cross-setup MP) while making adaptive decisions along with unexpected changes of cutting tools. Finally, the results of the machined test part validate that the method can reduce the number of tool changes compared to the current MF sequencing methods.
|
|
| 9. |
- Ji, Wei, et al.
(författare)
-
An enriched machining feature based approach to cutting tool selection
- 2018
-
Ingår i: International journal of computer integrated manufacturing (Print). - : Taylor & Francis. - 0951-192X .- 1362-3052. ; 31:1, s. 1-10
-
Tidskriftsartikel (refereegranskat)abstract
- Cutting tools, considered as a basic prerequisite machining resource, are generally selected according to the selected machining methods, which cannot fit in the current manufacturing environment where small- and medium-sized enterprises (SMEs) are the major manufacturers. For the survival of SMEs, it is critical to develop methods for selecting proper cutting tools and reducing machining cost according to product data. Therefore, this study proposes an enriched machining feature (MF)-based approach towards adaptive cutting tool and machining method selection, in which both machinability and machining cost of MF are considered. It includes a two-step workflow: filtering and optimisation. In the filtering process, cutting tools are filtered according to workpiece materials, geometries of MFs and cutting tool inventory, respectively. Here, MF geometries depend on Machining Limit Value decided by sizes and interference relationships of MFs. Also, the client is suggested to choose proper new cutting tools. In the optimisation process, the filtered cutting tools are considered for all the MFs, and machining costs are calculated for each option, in order to select the cheapest one. In particular, if similar cutting tools are required for different MFs, the cutting tool selection for these MFs should be performed altogether.
|
|
| 10. |
- Ji, Wei, et al.
(författare)
-
Experimental evaluation of polycrystalline diamond (PCD) tool geometries at high feed rate in milling of titanium alloy TC11
- 2015
-
Ingår i: The International Journal of Advanced Manufacturing Technology. - : Springer Science and Business Media LLC. - 0268-3768 .- 1433-3015. ; 77:9-12, s. 1549-1555
-
Tidskriftsartikel (refereegranskat)abstract
- Titanium alloys are widely used in aerospace industrial components characterised by high material removal rate, of which the machining efficiency is a big issue. Targeting the problem, this paper presents the experimental findings of milling of titanium alloy TC11 using polycrystalline diamond (PCD) cutting tool at high feed rate. First, in order to verify the capability of PCD in finish milling of titanium alloys at high feed rate, the surface roughness R-a is investigated under different PCD tool geometries (radial rake angle, axial rake angle and insert sharp radius), and the results indicate that its range is from 0.821 to 1.562 mu m, which is suitable to titanium components. Also, the main tool failure patterns, cutting edge fracture and flank face wear, are observed and classified. Based on the tool failure patterns, the relationship between tool life and tool geometries is established. In order to explain the reasons of tool failures, the relationships between cutting forces and the tool geometries are made clear. Finally, the processes of flank face wear and rake face wear of PCD insert are proposed to show its wear evaluations.
|
|
