Neural Networks for fast sensor data processing in Laser Welding
نویسندگان
چکیده
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 reconstruction and capability for classification are later compared with features, extracted by the principal component analysis. The neural network demonstrates to extract more robust and meaningful features, compared to a PCA.
منابع مشابه
First steps towards an intelligent laser welding architecture using deep neural networks and reinforcement learning
To address control difficulties in laser welding, we propose the idea of a self-learning and self-improving laser welding system that combines three modern machine learning techniques. We first show the ability of a deep neural network to extract meaningful, low-dimensional features from high-dimensional laser-welding camera data. These features are then used by a temporal-difference learning a...
متن کاملIntelligent laser welding through representation, prediction, and control learning: An architecture with deep neural networks and reinforcement learning
Laser welding is a widely used but complex industrial process. In this work, we propose the use of an integrated machine intelligence architecture to help address the significant control difficulties that prevent laser welding from seeing its full potential in process engineering and production. This architecture combines three contemporary machine learning techniques to allow a laser welding c...
متن کاملA Self-Reconstructing Algorithm for Single and Multiple-Sensor Fault Isolation Based on Auto-Associative Neural Networks
Recently different approaches have been developed in the field of sensor fault diagnostics based on Auto-Associative Neural Network (AANN). In this paper we present a novel algorithm called Self reconstructing Auto-Associative Neural Network (S-AANN) which is able to detect and isolate single faulty sensor via reconstruction. We have also extended the algorithm to be applicable in multiple faul...
متن کاملSensor Fusion to Estimate the Depth and Width of the Weld Bead in Real Time in GMAW Processes.
The arc welding process is widely used in industry but its automatic control is limited by the difficulty in measuring the weld bead geometry and closing the control loop on the arc, which has adverse environmental conditions. To address this problem, this work proposes a system to capture the welding variables and send stimuli to the Gas Metal Arc Welding (GMAW) conventional process with a con...
متن کاملArc-welding quality assurance by means of embedded fiber sensor and spectral processing combining feature selection and neural networks
A new spectral processing technique designed for its application in the on-line detection and classification of arc-welding defects is presented in this paper. A non-invasive fiber sensor embedded within a TIG torch collects the plasma radiation originated during the welding process. The spectral information is then processed by means of two consecutive stages. A compression algorithm is first ...
متن کامل