Real-Time predicting internal temperature of heat generating cylinder from surrounding coolant temperature measurements using neural network

2021 ◽  
pp. 100910
Author(s):  
Sandeep Patil ◽  
Siddarth Chintamani ◽  
Brian H. Dennis ◽  
Ratan Kumar
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Temperature Measurements ◽  
Coolant Temperature ◽  
Internal Temperature

Application of Artificial Neural Network as Digital Filter for Online Heat Flux Estimation

2014 ◽  
Author(s):  
Hamidreza Najafi ◽  
Keith A. Woodbury
Keyword(s):  
Neural Network ◽  
Heat Flux ◽  
Artificial Neural Network ◽  
Real Time ◽  
Digital Filter ◽  
Temperature Measurements ◽  
Flux Boundary Condition ◽  
Heat Flux Estimation ◽  
Flux Estimation ◽  
Artificial Neural

Online heat flux measurement can greatly enhance the controllability in several industrial processes. Using heat flux estimation techniques based on temperature measurements is the best approach in many cases. Estimating the unknown heat flux (boundary condition) at the surface when temperature measurements are available in the interior points of the medium is an inverse heat conduction problem (IHCP). Several IHCP solution methods need the whole time domain data for the analysis and cannot be applied for real-time applications. Digital filter representation is one of the methods which can be used for near real-time heat flux estimation by using available temperature measurements. The idea of the filter algorithm is that the solution for the heat flux at any time is only affected by the recent temperature history and a few future time steps. Artificial Neural Network (ANN) is utilized in this study as a digital filter, for near real-time heat flux estimation by using temperature measurements. The performance of the ANN is compared with the digital filter coefficient method. ANN consists of a set of interconnected neurons that can evaluate outputs from inputs by feeding information through the network and adjusting the weights. Considering temperatures as the inputs and heat flux as the output, the weights can be interpreted as the filter coefficients. In using ANN, calculation of sensitivity coefficients is not needed which can lead to less computational cost. It is showed that the ANN method can estimate the heat flux closer to real-time comparing with digital filter approach. The developed method is tested through several numerical test cases using exact solutions.

Cooling Effectiveness Measurements With Thermal Radiometry in a Turbine Cascade

2000 ◽  
Author(s):  
H. K. Moon ◽  
R. Jaiswal
Keyword(s):  
Heat Transfer ◽  
Temperature Distribution ◽  
Real Time ◽  
Background Radiation ◽  
Temperature Measurements ◽  
Coolant Temperature ◽  
Turbine Cascade ◽  
Temperature Ratio ◽  
Cooling Effectiveness ◽  
Engine Condition

Airfoil temperature measurements in a hot cascade were traditionally conducted with thermocouples in spite of their limitations. In the present work, a real-time full imaging of the airfoil temperature distribution is demonstrated in a turbine cascade using a thermal radiometry system. Two synthetic sapphire windows provided infrared (IR)-viewing access from the outside. The apparent emissivity of the test airfoil was calibrated with thermocouples buried flush into the wall. The turbine cascade, fabricated with actual engine hardware, provided heat transfer similarity by matching Re, Ma, and Tu. The effect of gas to coolant temperature ratio (Tg/Tc) on the cooling effectiveness was investigated. Heating (“reverse” cooling) of the test airfoil in a relatively cold mainstream air resulted in a much more detailed temperature image than the normal (forward) cooling case, as it significantly reduced the background radiation. A methodology to correct the cooling effectiveness obtained at different gas to coolant temperature ratios than the engine condition was developed and has been experimentally validated.

Real-time Detection of Aortic Valve in Echocardiography using Convolutional Neural Networks

2020 ◽  
Vol 16 (5) ◽  
pp. 584-591 ◽  
Author(s):  
Muhammad Hanif Ahmad Nizar ◽  
Chow Khuen Chan ◽  
Azira Khalil ◽  
Ahmad Khairuddin Mohamed Yusof ◽  
Khin Wee Lai
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Heart Disease ◽  
Aortic Valve ◽  
Real Time ◽  
Convolutional Neural Networks ◽  
Valvular Heart Disease ◽  
Detection System ◽  
Processing Unit ◽  
Real Time Detection

Background: Valvular heart disease is a serious disease leading to mortality and increasing medical care cost. The aortic valve is the most common valve affected by this disease. Doctors rely on echocardiogram for diagnosing and evaluating valvular heart disease. However, the images from echocardiogram are poor in comparison to Computerized Tomography and Magnetic Resonance Imaging scan. This study proposes the development of Convolutional Neural Networks (CNN) that can function optimally during a live echocardiographic examination for detection of the aortic valve. An automated detection system in an echocardiogram will improve the accuracy of medical diagnosis and can provide further medical analysis from the resulting detection. Methods: Two detection architectures, Single Shot Multibox Detector (SSD) and Faster Regional based Convolutional Neural Network (R-CNN) with various feature extractors were trained on echocardiography images from 33 patients. Thereafter, the models were tested on 10 echocardiography videos. Results: Faster R-CNN Inception v2 had shown the highest accuracy (98.6%) followed closely by SSD Mobilenet v2. In terms of speed, SSD Mobilenet v2 resulted in a loss of 46.81% in framesper- second (fps) during real-time detection but managed to perform better than the other neural network models. Additionally, SSD Mobilenet v2 used the least amount of Graphic Processing Unit (GPU) but the Central Processing Unit (CPU) usage was relatively similar throughout all models. Conclusion: Our findings provide a foundation for implementing a convolutional detection system to echocardiography for medical purposes.

Neural network for real-time synthesis of FIR filters

1989 ◽  
Vol 25 (17) ◽  
pp. 1199 ◽  
Author(s):  
G. Martinelli ◽  
R. Perfetti
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Fir Filters

scholarly journals A Frequency Pattern Mining Model Based on Deep Neural Network for Real-Time Classification of Heart Conditions

Healthcare ◽  
2020 ◽  
Vol 8 (3) ◽  
pp. 234 ◽  
Author(s):  
Hyun Yoo ◽  
Soyoung Han ◽  
Kyungyong Chung
Keyword(s):  
Neural Network ◽  
Big Data ◽  
Fourier Transform ◽  
Fast Fourier Transform ◽  
Real Time ◽  
Normal Control ◽  
Input Data ◽  
Deep Neural Network ◽  
Pattern Mining ◽  
F Measure

Recently, a massive amount of big data of bioinformation is collected by sensor-based IoT devices. The collected data are also classified into different types of health big data in various techniques. A personalized analysis technique is a basis for judging the risk factors of personal cardiovascular disorders in real-time. The objective of this paper is to provide the model for the personalized heart condition classification in combination with the fast and effective preprocessing technique and deep neural network in order to process the real-time accumulated biosensor input data. The model can be useful to learn input data and develop an approximation function, and it can help users recognize risk situations. For the analysis of the pulse frequency, a fast Fourier transform is applied in preprocessing work. With the use of the frequency-by-frequency ratio data of the extracted power spectrum, data reduction is performed. To analyze the meanings of preprocessed data, a neural network algorithm is applied. In particular, a deep neural network is used to analyze and evaluate linear data. A deep neural network can make multiple layers and can establish an operation model of nodes with the use of gradient descent. The completed model was trained by classifying the ECG signals collected in advance into normal, control, and noise groups. Thereafter, the ECG signal input in real time through the trained deep neural network system was classified into normal, control, and noise. To evaluate the performance of the proposed model, this study utilized a ratio of data operation cost reduction and F-measure. As a result, with the use of fast Fourier transform and cumulative frequency percentage, the size of ECG reduced to 1:32. According to the analysis on the F-measure of the deep neural network, the model had 83.83% accuracy. Given the results, the modified deep neural network technique can reduce the size of big data in terms of computing work, and it is an effective system to reduce operation time.

Sign in / Sign up

Export Citation Format

Share Document