A multi-access edge computing enabled framework for the construction of a knowledge-sharing intelligent machine tool swarm in Industry 4.0

Zhang, Chao; Zhou, Guanghui; Li, Jingjing; Chang, Fengtian; Ding, Kai; Ma, Dongxu

doi:10.1016/j.jmsy.2022.11.015

Cited by 47 publications

(14 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [5], the authors explore the use of digital twins in healthcare and provide a paradigm of digitally twinned everything as a healthcare service. This is consistent with the digital twining as a service paradigm and the Internet of Things as a Service idea supporting Industry 4.0 [6]. [7] offers a systematic evaluation of the literature on DT technology and its implementa-tion difficulties in critical engineering domains.…”

Section: Introductionsupporting

confidence: 69%

Emotion Recognition for Affective Human Digital Twin by Means of Virtual Reality Enabling Technologies

Amara¹,

Kerdjidj

Ramzan

2023

IEEE Access

View full text Add to dashboard Cite

Digital Twin is the seamless data integration between a physical and virtual machine in either direction. Emotion recognition in healthcare is becoming increasingly important due to recent developments in Machine Learning methods. However, it may face technical problems such as limited datasets, occlusion and lighting issues, identifying key features, incorrect emotion classification, high implementation costs, head posture, and a person's cultural background. This paper proposes a novel approach based on facial expression and body movement recognition for emotion recognition. It uses three devices (Kinect 1, Kinect 2, and RGB HD camera) to construct a new bi-modal database containing 17 participants' performances of six emotional states. Two mono-modal classifiers have been developed to obtain sufficient state information based on facial expression and body motion analysis. The system's performance is assessed using three algorithms: Bagged Trees, k-Nearest Neighbors (k-NN), and Support Vector Machine (Linear and Cubic). The acquired findings demonstrate the excellent performance of the suggested method and the effectiveness of the proposed features, particularly the combination of 3D distance and 3D angle, in characterising and identifying emotions. Results obtained using Kinect 2 marginally surpass those with Kinect 1. Comparing 2D RGB and RGB-D data reveals that the depth information significantly raises the recognition rate. RGB-D features can be used to represent emotions, but there are discrepancies between RGB and RG-D data.

show abstract

Section: Introductionsupporting

confidence: 69%

Emotion Recognition for Affective Human Digital Twin by Means of Virtual Reality Enabling Technologies

Amara¹,

Kerdjidj

Ramzan

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…36 Digital twins are seen as an efficient way to achieve the interactive integration of the industrial information world and the physical world, particularly in the field of intelligent manufacturing. 37 The open integral micro impeller’s multi-axis CNC finishing path has been identified previously. To investigate the impact of two distinct finishing pathways and varying cutting parameters on blade surface roughness, a multi-physical field coupling model was developed for blade finishing, and numerical simulation was conducted from a mathematical model construction standpoint.…”

Section: Surface Roughness Acquisition and Experimental Verification ...mentioning

confidence: 99%

Multi-axis CNC finishing and surface roughness prediction of TC11 titanium alloy open integral micro impeller

Zhao,

Cao,

Guo

et al. 2024

Advances in Mechanical Engineering

View full text Add to dashboard Cite

The titanium alloy open integral micro impeller has a strong material strength and high removal rate in the field of multi-axis CNC machining. The flow channel is tiny and the blades are thin and highly twisted. It is difficult to control the surface accuracy and prone to overcutting and undercutting. The NX2212 software post-processing module plans two distinct blade finishing process routes and verifies them using virtual machine tool simulation, taking into account the technical challenges of micro impeller machining. Following verification, the tool path machining code is imported into MATLAB for data fitting. The workpiece surface working condition is determined based on the simulation findings, the blade surface roughness value is calculated, and a physical simulation model of blade finishing is created in the finite element analysis software. The outcomes demonstrate how well the “segmented and sub-regional cutting” processing method may raise blade accuracy. The leading and trailing edges of the blade both had surface roughness increases of 4.86% and 4.19%. The surface morphology of the micro impeller is measured using a white light interferometer, and it is CNC machined using two distinct process methods. The findings demonstrate that there is a significant difference between the value calculated by the finite element analysis software and the surface roughness value measured experimentally which together make up less than 5%. An investigation of the impact of cutting parameters on the surface roughness of micro-structure components is carried out using a three factor, three-level BBD experiment that is founded on the second-order response surface method. The findings indicate that the feed per tooth influences surface roughness more significantly than cutting depth and cutting speed for a reasonable range of cutting parameters; Surface roughness will rise with lower or higher cutting speeds; Raising the feed per tooth and the cutting speed simultaneously may reduce surface roughness; Surface roughness can be accurately predicted and controlled using the second-order response surface method.

show abstract

“…Data collection, feature removal, a prediction model, cloud storage, and analysis are all parts of the decision support system (DSS) proposed by Rosati et al [16] Unlike previous studies, our approach uses data from both the lower and higher tiers of the production scheme to fuel a feature extraction approach and ML prediction model, which is a significant departure from the status quo. Predictive performance (mean absolute error (MAE): 0.089) and computational effort (average latency of quality) were all found to be optimal by the experiments.…”

Section: Related Workmentioning

confidence: 99%

Developing an Integrated IoT Cloud Based Predictive Conservation Model for Asset Management in Industry 4.0

Shanmugam,

Satyam,

Reddy

2023

J. Soc. Comput.

View full text Add to dashboard Cite

With the advent of Industry 4.0 (I4.0), predictive maintenance (PdM) methods have been widely adopted by businesses to deal with the condition of their machinery. With the help of I4.0, digital transformation, information techniques, computerised control, and communication networks, large amounts of data on operational and process conditions can be collected from multiple pieces of equipment and used to make an automated fault detection and diagnosis, all with the goal of reducing unscheduled maintenance, improving component utilisation, and lengthening the lifespan of the equipment. In this paper, we use smart approaches to create a PdM planning model. The five key steps of the created approach are as follows: (1) cleaning the data,(2) normalising the data, (3) selecting the best features, (4) making a decision about the prediction network, and (5) producing a prediction. At the outset, PdM-related data undergo data cleaning and normalisation to get everything in order and within some kind of bounds. The next step is to execute optimal feature selection in order to eliminate unnecessary data. This research presents the golden search optimization (GSO) algorithm, a powerful population-based optimization technique for efficient feature selection. The first phase of GSO is to produce a set of possible solutions or objects at random. These objects will then interact with one another using a straightforward mathematical model to find the best feasible answer. Due to the wide range over which the prediction values fall, machine learning and deep learning confront challenges in providing reliable predictions. This is why we recommend a multilayer hybrid convolution neural network (MLH-CNN).While conceptually similar to VGGNet, this approach uses fewer parameters while maintaining or improving classification correctness by adjusting the amount of network modules and channels. The projected perfect is evaluated on two datasets to show that it can accurately predict the future state of components for upkeep preparation.

show abstract

A multi-access edge computing enabled framework for the construction of a knowledge-sharing intelligent machine tool swarm in Industry 4.0

Cited by 47 publications

References 29 publications

Emotion Recognition for Affective Human Digital Twin by Means of Virtual Reality Enabling Technologies

Emotion Recognition for Affective Human Digital Twin by Means of Virtual Reality Enabling Technologies

Multi-axis CNC finishing and surface roughness prediction of TC11 titanium alloy open integral micro impeller

Developing an Integrated IoT Cloud Based Predictive Conservation Model for Asset Management in Industry 4.0

Contact Info

Product

Resources

About