Research on Fault Diagnosis Based on BP-SOM Hybrid Algorithms for NC Machine

2012 ◽  
Vol 544 ◽  
pp. 32-37 ◽  
Author(s):  
Chao Deng ◽  
Wen Long Dong ◽  
Yuan Hang Wang ◽  
Yao Xiong
Keyword(s):  
Fault Diagnosis ◽  
Manufacturing Industry ◽  
Hybrid Algorithms ◽  
Basic Data ◽  
Precision Data ◽  
The Real ◽  
Simulation Output ◽  
Nc Machine

NC machines are more and more widely used in manufacturing industry. As the key equipments in the factory, NC machines should be closely monitored to avoid faults. Therefore, the research on multi-function diagnosis based on BP-SOM is discussed for NC machine in the paper. Taking the precision data as the basic data for diagnosis, the research used BP and SOM algorithms to build up diagnosis models. As a result, the research has accomplished the diagnosing process and acquires good simulation output, which resembles with the real fact.

scholarly journals VR FOR ASSEMBLY TASKS IN THE MANUFACTURING INDUSTRY – INTERACTION AND BEHAVIOUR

2020 ◽  
Vol 1 ◽  
pp. 1697-1706
Author(s):  
Y. Eriksson ◽  
M. Sjölinder ◽  
A. Wallberg ◽  
J. Söderberg
Keyword(s):  
Pilot Study ◽  
Real World ◽  
Manufacturing Industry ◽  
The Real ◽  
Assembly Tasks

AbstractA testbed was developed aiming to contribute to further knowledge on what is required from a VR application in order to be useful for planning of assembly tasks. In a pilot study the testbed was tested on students. The focus of the study was to explore the users’ behaviour, and to gain a better understanding of their experience using VR. The students experienced a gap between the real world and VR, which confirms theories that VR is not a copy or twin of an object or environment.

scholarly journals Behavior Analysis of Human Locomotion in the Real World and Virtual Reality for the Manufacturing Industry

2018 ◽  
Vol 15 (3) ◽  
pp. 1-19 ◽  
Author(s):  
Philipp Agethen ◽  
Viswa Subramanian Sekar ◽  
Felix Gaisbauer ◽  
Thies Pfeiffer ◽  
Michael Otto ◽  
...  
Keyword(s):  
Virtual Reality ◽  
Behavior Analysis ◽  
Real World ◽  
Manufacturing Industry ◽  
Human Locomotion ◽  
The Real

scholarly journals A Stacked Autoencoder-Based Deep Neural Network for Achieving Gearbox Fault Diagnosis

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Guifang Liu ◽  
Huaiqian Bao ◽  
Baokun Han
Keyword(s):  
Fault Diagnosis ◽  
Manufacturing Industry ◽  
Activation Function ◽  
Data Driven ◽  
Training Process ◽  
Training Set ◽  
Analysis Techniques ◽  
Stacked Autoencoders ◽  
Modern Manufacturing ◽  
Machinery Fault Diagnosis

Machinery fault diagnosis is pretty vital in modern manufacturing industry since an early detection can avoid some dangerous situations. Among various diagnosis methods, data-driven approaches are gaining popularity with the widespread development of data analysis techniques. In this research, an effective deep learning method known as stacked autoencoders (SAEs) is proposed to solve gearbox fault diagnosis. The proposed method can directly extract salient features from frequency-domain signals and eliminate the exhausted use of handcrafted features. Furthermore, to reduce the overfitting problem in training process and improve the performance for small training set, dropout technique and ReLU activation function are introduced into SAEs. Two gearbox datasets are employed to conform the effectiveness of the proposed method; the result indicates that the proposed method can not only achieve significant improvement but also is superior to the raw SAEs and some other traditional methods.

Research on Fault Diagnosis Monitoring System of Natural Gas Compressor

2014 ◽  
Vol 1048 ◽  
pp. 541-544
Author(s):  
Huan Huan Nie ◽  
Zhen Lu Wu ◽  
Guo Yan Yu
Keyword(s):  
Fault Diagnosis ◽  
Natural Gas ◽  
Real Time ◽  
Monitoring System ◽  
Register Data ◽  
Parameter Method ◽  
Time Requirement ◽  
The Real ◽  
Technical Framework

In this paper the structure of natural gas compressor monitoring system was designed. All the register data in PLC could be obtained to meet the real-time requirement by an instruction of PPI protocol. The technical framework of system was introduced simply, and the parameter method for measuring was put forward in fault diagnosis of natural gas compressor.

scholarly journals NC Machine Tools Fault Diagnosis Based on Kernel PCA andk-Nearest Neighbor Using Vibration Signals

2015 ◽  
Vol 2015 ◽  
pp. 1-10 ◽  
Author(s):  
Zhou Yuqing ◽  
Sun Bingtao ◽  
Li Fengping ◽  
Song Wenlei
Keyword(s):  
Fault Diagnosis ◽  
Machine Tools ◽  
Nearest Neighbor ◽  
Principal Component ◽  
Feature Space ◽  
Kernel Principal Component Analysis ◽  
Dimensional Manifold ◽  
Nc Milling ◽  
Nc Machine ◽  
Nc Machine Tools

This paper focuses on the fault diagnosis for NC machine tools and puts forward a fault diagnosis method based on kernel principal component analysis (KPCA) andk-nearest neighbor (kNN). A data-dependent KPCA based on covariance matrix of sample data is designed to overcome the subjectivity in parameter selection of kernel function and is used to transform original high-dimensional data into low-dimensional manifold feature space with the intrinsic dimensionality. ThekNN method is modified to adapt the fault diagnosis of tools that can determine thresholds of multifault classes and is applied to detect potential faults. An experimental analysis in NC milling machine tools is developed; the testing result shows that the proposed method is outperforming compared to the other two methods in tool fault diagnosis.

On Transformation and Upgrading Manufacturing Industry

2013 ◽  
Vol 340 ◽  
pp. 208-212
Author(s):  
Ying Zhu
Keyword(s):  
Manufacturing Industry ◽  
Global Finance ◽  
Reform Policy ◽  
The Real ◽  
Development Path ◽  
The Future ◽  
History Of ◽  
Great Development

During the thirty years high development of Dongguans Manufacturing Industry under open and reform policy, it has not only created Dongguan model, but also created Dongguan miracle . However, behind the great development of Dongguan manufacturing industry, it exposed much problems gradually. Especially , when the global finance crisis that crisis of sub-credit due to happened, Dongguan manufacturing industry that must transform and upgrade. Under the real circumstance of Dongguan manufacturing industry and after issuing of the 12th Five Year Plan, review on the history of it, summary of development characters of it , deeply analysis of the problems and reason of it, some theories explore about development path of Dongguans manufacturing industry in the future could be taken.

scholarly journals Worker’s behaviour in manufacturing industry: An evidence from a minimum spanning tree

2015 ◽  
Vol 8 (1) ◽  
Author(s):  
Shamshuritawati Sharif ◽  
Maman A. Djauhari
Keyword(s):  
Spanning Tree ◽  
Manufacturing Industry ◽  
Minimum Spanning Tree ◽  
Manufacturing Sector ◽  
Correlation Structure ◽  
Real Situation ◽  
Fatal Accidents ◽  
Centrality Measure ◽  
The Real ◽  
Economic Opportunities

A manufacturing industry contributes around 10% Malaysian economic. It provides economic opportunities for related industries and business. However, the number of accidents in manufacturing sector, including fatal accidents, has been increased from time to time. We analyze worker’s behaviour to understand the real situation. The method developed in econophysics has been used to transform the correlation structure into sub-dominant ultrametric structure. Its corresponding minimum spanning tree and the centrality measure are performed in order to identify the most influential variables.

scholarly journals PROBING Δ STRUCTURE WITH PION ELECTROMAGNETIC PRODUCTION

2003 ◽  
Vol 18 (02n06) ◽  
pp. 248-257 ◽  
Author(s):  
SHIN NAN YANG ◽  
SABIT S. KAMALOV
Keyword(s):  
Helicity Amplitude ◽  
Scaling Behavior ◽  
Dynamical Model ◽  
Real Photon ◽  
Pion Cloud ◽  
Precision Data ◽  
The Real ◽  
Clear Tendency ◽  
Existing Data

The Dubna-Mainz-Taipei dynamical model for pion electromagnetic production, which can describe well the existing data from threshold up to 1 GeV photon lab energy, is presented and used to analyze the recent precision data in the Δ region. We find that, within our model, the bare Δ is almost spherical while the physical Δ is oblate. The deformation is almost saturated by the pion cloud effects. We further find that up to Q2 = 4.0(GeV/c)2 the extracted helicity amplitude A3/2 and A1/2 remain comparable with each other, implying that hadronic helicity is not conserved at this range of Q2. The ratio E1+/M1+ obtained show, starting from a small and negative value at the real photon point, a clear tendency to cross zero, and to become positive with increasing Q2. This is a possible indication of a very slow approach toward the pQCD region. Finally, we find that the bare helicity amplitude A1/2 and S1/2, but not A3/2, starts exhibiting the scaling behavior at about Q2 ≥ 2.5(GeV/c)2.

Sign in / Sign up

Export Citation Format

Share Document