Partial discharge monitoring using deep neural networks with acoustic emission

2021 ◽  
Vol 263 (3) ◽  
pp. 3312-3323
Author(s):  
Saichand Gourishetti ◽  
David Johnson ◽  
Sara Werner ◽  
András Kátai ◽  
Peter Holstein
Keyword(s):  
Partial Discharge ◽  
Network Models ◽  
Electrical Equipment ◽  
Operating Conditions ◽  
Measurement Technology ◽  
Neural Network Models ◽  
Time Frequency ◽  
Common Time ◽  
Expert Analysis ◽  
Processing Techniques

The occurrence of partial discharge (PD) indicates failures in electrical equipment. Depending on the equipment and operating conditions, each type of PD has its own acoustic characteristics and a wide frequency spectrum. To detect PD, electrical equipment is often monitored using various sensors, such as microphones, ultrasonic, and transient-earth voltage, whose signals are then analyzed manually by experts using signal processing techniques. This process requires significant expertise and time, both of which are costly. Advancements in machine learning, aim to address this issue by automatically learning a representation of the signal, minimizing the need for expert analysis. To this end, we propose a deep learning-based solution for the automatic detection of PD using airborne sound emission in the audible to the ultrasonic range. As input to our proposed model, we evaluate common time-frequency representations of the acoustic signal, such as short-time Fourier, continuous wavelet transform and Mel spectrograms. The extracted spectrum from the PD signal pulses is used to train and evaluate the proposed deep neural network models for the detection of different types of PD. Compared to the manual process, the automatic solution is seen as beneficial for maintenance processes and measurement technology.

Analysis of Fin-Tube Evaporator Performance With Limited Experimental Data Using Artificial Neural Networks

2000 ◽  
Author(s):  
Arturo Pacheco-Vega ◽  
Mihir Sen ◽  
Rodney L. McClain
Keyword(s):  
Neural Network ◽  
Heat Rate ◽  
Network Models ◽  
Activation Function ◽  
Operating Conditions ◽  
Training Data ◽  
Neural Network Models ◽  
The Neural Network ◽  
Artificial Neural ◽  
Fin Tube

Abstract In the current study we consider the problem of accuracy in heat rate estimations from artificial neural network models of heat exchangers used for refrigeration applications. The network configuration is of the feedforward type with a sigmoid activation function and a backpropagation algorithm. Limited experimental measurements from a manufacturer are used to show the capability of the neural network technique in modeling the heat transfer in these systems. Results from this exercise show that a well-trained network correlates the data with errors of the same order as the uncertainty of the measurements. It is also shown that the number and distribution of the training data are linked to the performance of the network when estimating the heat rates under different operating conditions, and that networks trained from few tests may give large errors. A methodology based on the cross-validation technique is presented to find regions where not enough data are available to construct a reliable neural network. The results from three tests show that the proposed methodology gives an upper bound of the estimated error in the heat rates.

Neural Network Models for Usage Based Remaining Life Computation

2006 ◽  
Author(s):  
Girija Parthasarathy ◽  
Sunil Menon ◽  
Kurt Richardson ◽  
Ahsan Jameel ◽  
Dawn McNamee ◽  
...  
Keyword(s):  
Neural Network ◽  
Computation Time ◽  
Network Models ◽  
Operating Conditions ◽  
Neural Network Models ◽  
Operational Conditions ◽  
Actual Operating ◽  
Critical Components ◽  
Stress Models ◽  
Work Done

In engine structural life computations, it is common practice to assign a life of certain number of start-stop cycles based on a standard flight or mission. This is done during design through detailed calculations of stresses and temperatures for a standard flight, and the use of material property and failure models. The limitation of the design phase stress and temperature calculations is that they cannot take into account actual operating temperatures and stresses. This limitation results in either very conservative life estimates and subsequent wastage of good components, or in catastrophic damage because of highly aggressive operational conditions which were not accounted for in design. In order to improve significantly the accuracy of the life prediction, the component temperatures and stresses need to be computed for actual operating conditions. However, thermal and stress models are very detailed and complex, and it could take on the order of a few hours to complete a stress and temperature simulation of critical components for a flight. The objective of this work is to develop dynamic neural network models, that would enable us to compute the stresses and temperatures at critical locations, in orders of magnitude less computation time than required by more detailed thermal and stress models. This work expands on the work done previously [1] where a linear system identification approach was developed. The current paper describes the development of a neural network model and the temperature results achieved in comparison with the original models for Honeywell turbine and compressor components. Given certain inputs such as engine speed and gas temperatures for the flight, the models compute the component critical location temperatures for the same flight in a very small fraction of time it would take the original thermal model to compute.

Efficient Image Denoising for Effective Digitization using Image Processing Techniques and Neural Networks

2016 ◽  
Vol 7 (4) ◽  
pp. 77-93 ◽  
Author(s):  
K.G. Srinivasa ◽  
B.J. Sowmya ◽  
D. Pradeep Kumar ◽  
Chetan Shetty
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Network Models ◽  
Morphological Operations ◽  
Neural Network Models ◽  
Image Processing Techniques ◽  
Optical Character ◽  
Processing Techniques

Vast reserves of information are found in ancient texts, scripts, stone tablets etc. However due to difficulty in creating new physical copies of such texts, knowledge to be obtained from them is limited to those few who have access to such resources. With the advent of Optical Character Recognition (OCR) efforts have been made to digitize such information. This increases their availability by making it easier to share, search and edit. Many documents are held back due to being damaged. This gives rise to an interesting problem of removing the noise from such documents so it becomes easier to apply OCR on them. Here the authors aim to develop a model that helps denoise images of such documents retaining on the text. The primary goal of their project is to help ease document digitization. They intend to study the effects of combining image processing techniques and neural networks. Image processing techniques like thresholding, filtering, edge detection, morphological operations, etc. will be applied to pre-process images to yield higher accuracy of neural network models.

Neural Network Models for Usage Based Remaining Life Computation

2008 ◽  
Vol 130 (1) ◽  
Author(s):  
Girija Parthasarathy ◽  
Sunil Menon ◽  
Kurt Richardson ◽  
Ahsan Jameel ◽  
Dawn McNamee ◽  
...  
Keyword(s):  
Neural Network ◽  
Computation Time ◽  
Network Models ◽  
Operating Conditions ◽  
Neural Network Models ◽  
Operational Conditions ◽  
Actual Operating ◽  
Critical Location ◽  
Critical Components ◽  
Stress Models

In engine structural life computations, it is common practice to assign a life of certain number of start-stop cycles based on a standard flight or mission. This is done during design through detailed calculations of stresses and temperatures for a standard flight, and the use of material property and failure models. The limitation of the design phase stress and temperature calculations is that they cannot take into account actual operating temperatures and stresses. This limitation results in either very conservative life estimates and subsequent wastage of good components or in catastrophic damage because of highly aggressive operational conditions, which were not accounted for in design. In order to improve significantly the accuracy of the life prediction, the component temperatures and stresses need to be computed for actual operating conditions. However, thermal and stress models are very detailed and complex, and it could take on the order of a few hours to complete a stress and temperature simulation of critical components for a flight. The objective of this work is to develop dynamic neural network models that would enable us to compute the stresses and temperatures at critical locations, in orders of magnitude less computation time than required by more detailed thermal and stress models. The current paper describes the development of a neural network model and the temperature results achieved in comparison with the original models for Honeywell turbine and compressor components. Given certain inputs such as engine speed and gas temperatures for the flight, the models compute the component critical location temperatures for the same flight in a very small fraction of time it would take the original thermal model to compute.

Monitoring and Diagnosis of Steel Reheating Burners

2008 ◽  
Author(s):  
S. M. Thai ◽  
H. S. Chong ◽  
C. K. Tan ◽  
S. J. Wilcox ◽  
J. Ward ◽  
...  
Keyword(s):  
Diagnostic System ◽  
Network Models ◽  
Pilot Scale ◽  
Operating Conditions ◽  
Neural Network Models ◽  
Flame Radiation ◽  
Excess Air ◽  
Wide Range ◽  
Modelling Techniques ◽  
Signal Processing Methods

This paper describes the development of an intelligent Flame Diagnostic System which is able to monitor the combustion characteristics of individual burners based on direct measurement and analysis of the flame radiation signals. A series of experiments were conducted on a 500 kW pilot-scale furnace fitted with both a single burner and also two burners firing in a regenerative manner. The experiments covered a wide range of burner operating conditions including variations in the burner firing-rate and excess air level. A fibre-optic based optical instrument, incorporating broad ultraviolet, visible and infrared photo diodes was developed and used to acquire the dynamic flame signals through a data acquisition system. These flame signals were then analysed off-line, using simple signal processing methods, to yield a set of flame features. Correlation of these flame features with respect to the excess air level and NOx emissions were made using neural network models. The present work indicates that the measurement of flame radiation characteristics, coupled with advanced data modelling techniques such as neural networks, provides a promising means of monitoring and optimising burner performance.

scholarly journals Physics-based neural networks for simulation and synthesis of cyclic adsorption processes

2021 ◽  
Author(s):  
Sai Gokul Subraveti ◽  
Zukui Li ◽  
Vinay Prasad ◽  
Arvind Rajendran
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Models ◽  
Operating Conditions ◽  
State Variables ◽  
Neural Network Models ◽  
Detailed Model ◽  
The Neural Network ◽  
Adsorption Processes ◽  
Cyclic Adsorption

A computationally faster and reliable modelling approach called a physics-based artificial neural network framework for adsorption and chromatography emulation (PANACHE) is developed. PANACHE uses deep neural networks for cycle synthesis and simulation of cyclic adsorption processes. The proposed approach focuses on learning the underlying governing partial differential equations in the form of a physics-constrained loss function to simulate adsorption processes accurately. The methodology developed herein does not require any system-specific inputs such as isotherm parameters. Accordingly, unique neural network models were built to fully predict the column dynamics of different constituent steps based on unique boundary conditions that are typically encountered in adsorption processes. The trained neural network model for each constituent step aims to predict the entire spatiotemporal solutions of different state variables by obeying the underlying physical laws. The proposed approach is tested by constructing and simulating four different vacuum swing adsorption cycles for post-combustion CO2 capture without retraining the neural network models. For each cycle, 50 simulations, each corresponding to a unique set of operating conditions, are carried out until the cyclic-steady state. The results demonstrated that the purity and recovery calculated from the neural network-based simulations are within 2.5% of the detailed model's predictions. PANACHE reduced computational times by 100 times while maintaining similar accuracy of the detailed model simulations.

Efficient Image Denoising for Effective Digitization Using Image Processing Techniques and Neural Networks

2018 ◽  
pp. 1091-1108
Author(s):  
K.G. Srinivasa ◽  
B.J. Sowmya ◽  
D. Pradeep Kumar ◽  
Chetan Shetty
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Network Models ◽  
Morphological Operations ◽  
Interesting Problem ◽  
Neural Network Models ◽  
Image Processing Techniques ◽  
Processing Techniques

Vast reserves of information are found in ancient texts, scripts, stone tablets etc. However due to difficulty in creating new physical copies of such texts, knowledge to be obtained from them is limited to those few who have access to such resources. With the advent of Optical Character Recognition (OCR) efforts have been made to digitize such information. This increases their availability by making it easier to share, search and edit. Many documents are held back due to being damaged. This gives rise to an interesting problem of removing the noise from such documents so it becomes easier to apply OCR on them. Here the authors aim to develop a model that helps denoise images of such documents retaining on the text. The primary goal of their project is to help ease document digitization. They intend to study the effects of combining image processing techniques and neural networks. Image processing techniques like thresholding, filtering, edge detection, morphological operations, etc. will be applied to pre-process images to yield higher accuracy of neural network models.

Sign in / Sign up

Export Citation Format

Share Document