Dynamic control for LMD processes using sensor fusion and edge computing

Arejita, Beñat; Garmendia, Iker; Isaza, Juan Fernando; Zuloaga, Aitzol

doi:10.1016/j.procir.2022.08.026

Cited by 3 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Local mean decomposition (LMD) is a signal analysis method proposed by Smith S [17] for the first time. It can adaptively decompose complex multi-component signals into the sum of several product functions (PF) [18]. This method has strong adaptability to nonlinear and nonstationary signal analysis [19].…”

Section: Literature Analysismentioning

confidence: 99%

Fault Diagnosis of Mine Truck Hub Drive System Based on LMD Multi-Component Sample Entropy Fusion and LS-SVM

Xu,

Li,

Zhang

et al. 2023

Actuators

View full text Add to dashboard Cite

As the main transportation equipment in ore mining, the wheel drive system of mining trucks plays a crucial role in the transportation capacity of mining trucks. The internal components of the hub drive system are mainly composed of bearings, gears, etc. The vibration signals caused during operation are nonlinear and nonstationary complex signals, and there may be more than one factor that causes faults, which causes certain difficulties for the fault diagnosis of the hub drive system. A fault diagnosis method based on local mean decomposition (LMD) multi-component sample entropy fusion and LS-SVM is proposed to address this issue. Firstly, the LMD method is used to decompose the vibration signals in different states to obtain a finite number of PF components. Then, based on the typical correlation analysis method, the distribution characteristics and correlation coefficients of vibration signals in the frequency domain under different states are calculated, and effective PF multi-component sample entropy features are constructed. Finally, the LS-SVM multi-fault classifier is used to train and test the extracted multi-component sample entropy features to verify the effectiveness of the method. The experimental results show that, even in small-sample data, the LMD multi-component sample entropy fusion and LS-SVM method can accurately extract fault features of vibration signals and complete classification, achieving fault diagnosis of wheel drive systems.

show abstract

Section: Literature Analysismentioning

confidence: 99%

Fault Diagnosis of Mine Truck Hub Drive System Based on LMD Multi-Component Sample Entropy Fusion and LS-SVM

Xu,

Li,

Zhang

et al. 2023

Actuators

View full text Add to dashboard Cite

show abstract

“…Cao et al [12] used a commercial laser displacement sensor to study the surface topography detection of 24CrNiMo alloy steel produced by direct laser deposition. Arejita et al [13] presented a closed-loop control algorithm that dynamically controlled the melt pool size, deposition speed and standoff distance combining data from a laser line profiler and a NIT Tachyon 1024 micro-core MWIR camera.…”

Section: Introductionmentioning

confidence: 99%

In process monitoring of geometrical characteristics in laser metal deposition: A comparative study

Latte

2023

Materials Research Proceedings

View full text Add to dashboard Cite

Abstract. Although it is experiencing a wide diffusion, there are still several limits to the use of additive manufacturing (AM) for the fabrication of metal components. This includes low productivity, poor dimensional accuracy and uncertainty about the mechanical properties of the final parts. The main cause of these undesirable effects lies in the intrinsic complexity of the metal AM processes, such as Laser Metal Deposition (LMD). Accurate monitoring of the process and optimization of the process parameters are therefore of fundamental importance to ensure the overall quality of the product. Nowadays, several optical methods are under development for the monitoring of geometric characteristics and their correlation with specific process parameters, such as the standoff distance. This paper presents a comparative study between two optical in-process monitoring methods performed on AISI 316L multilayer samples produced by the LMD process. The first is a laser line section method based on a laser diode mounted on the deposition head, while the second method uses a high-resolution CMOS camera placed on the horizontal plane with a front view of the sample. In both cases, ad-hoc image processing algorithms were used to process the data, reconstruct the morphology of the component, and extract geometrical information. Results were then validated using an offline scanning system and micrographic analyses. Both proposed systems allowed the monitoring of the deposition quality using appropriate Key Performance Indicators (KPIs). The study showed a good capability of the prototype systems to detect deposition defects due to undesired variations of the process conditions and to monitor the standoff distance.

show abstract

Cross-section geometry prediction for laser metal deposition layer-based on multi-mode convolutional neural network and multi-sensor data fusion

Dong,

Kong,

Wang

et al. 2023

Journal of Manufacturing Processes

View full text Add to dashboard Cite

Dynamic control for LMD processes using sensor fusion and edge computing

Cited by 3 publications

References 14 publications

Fault Diagnosis of Mine Truck Hub Drive System Based on LMD Multi-Component Sample Entropy Fusion and LS-SVM

Fault Diagnosis of Mine Truck Hub Drive System Based on LMD Multi-Component Sample Entropy Fusion and LS-SVM

In process monitoring of geometrical characteristics in laser metal deposition: A comparative study

Cross-section geometry prediction for laser metal deposition layer-based on multi-mode convolutional neural network and multi-sensor data fusion

Contact Info

Product

Resources

About