Corpus ID: 31374335

Neural Networks for fast sensor data processing in Laser Welding

@inproceedings{Gnther2014NeuralNF,
  title={Neural Networks for fast sensor data processing in Laser Welding},
  author={J. G{\"u}nther and Hao Shen and K. Diepold},
  year={2014}
}
To address the need for robust and fast representation, we introduce deep learning neural networks and parallel programming techniques for laser welding. In order to deal with high-dimensional data within real-time constraints, we use a deep autoencoder to extract robust, meaningful and low dimensional features. The implementation is then optimized, using parallel programming techniques and shown to perform within the real-time requirements for laser welding. The performance, in terms of… Expand
1 Citations
Evaluation of the Potential of Deep Learning for Manufacturing Process Analytics
TLDR
A new approach is introduced to alleviate weaknesses in current approaches which include insufficient signal selection, requirement of large amount of training data or neglection of the physical nature of the system. Expand

References

SHOWING 1-10 OF 17 REFERENCES
Cellular Neural Network (CNN) based control algorithms for omnidirectional laser welding processes: Experimental results
The high dynamics of laser beam welding (LBW) in several manufacturing processes ranging from automobile production to precision mechanics requires the introduction of new fast real time controls. InExpand
Multiple sensors and Artificial Neural Networks in a cognitive technical system for laser welding
TLDR
Multiple sensors, such as an intelligently focusing camera, acoustic sensors and photodiodes, are integrated into a cognitive technical system using Artificial Neural Networks and other techniques for learning how to monitor and control the processing systems. Expand
Automated Inspection of Micro Laser Spot Weld Quality Using Optical Sensing and Neural Network Techniques
  • J. Shao, Yong Yan
  • Computer Science
  • 2006 IEEE Instrumentation and Measurement Technology Conference Proceedings
  • 2006
TLDR
An approach to the automated inspection of laser spot welding processes using optical sensing and neural network techniques is presented, showing that this approach can be used to inspect the laser welding quality for the microelectronics industry. Expand
Sputter Tracking for the Automatic Monitoring of Industrial Laser-Welding Processes
TLDR
This paper investigates a novel classification method to automatically analyze the recorded welding sequences and robustly find the abnormal error events and shows that the material particles can be tracked accurately. Expand
Development of automatic control system for laser welding using neural network technology
Neural network technology applications in automatic control system for laser welding are considered. Fundamental concepts of neural network are outlined. Attention is drawn to the design of adaptiveExpand
Practical Recommendations for Gradient-Based Training of Deep Architectures
  • Yoshua Bengio
  • Computer Science
  • Neural Networks: Tricks of the Trade
  • 2012
TLDR
Overall, this chapter describes elements of the practice used to successfully and efficiently train and debug large-scale and often deep multi-layer neural networks and closes with open questions about the training difficulties observed with deeper architectures. Expand
Reducing the Dimensionality of Data with Neural Networks
TLDR
This work describes an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data. Expand
Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
TLDR
This work clearly establishes the value of using a denoising criterion as a tractable unsupervised objective to guide the learning of useful higher level representations. Expand
Representation Learning: A Review and New Perspectives
TLDR
Recent work in the area of unsupervised feature learning and deep learning is reviewed, covering advances in probabilistic models, autoencoders, manifold learning, and deep networks. Expand
Learning Deep Architectures for AI
TLDR
The motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer modelssuch as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks are discussed. Expand
...
1
2
...