scholarly journals Neural net implementation of steam properties on FPGA

2021 ◽  
Vol 10 (3) ◽  
pp. 186
Author(s):  
R. V. S. Krishna Dutt ◽  
R. Ganesh ◽  
P. Premchand
Keyword(s):  
Neural Network ◽  
Thermodynamic Properties ◽  
Real Time ◽  
Power Plants ◽  
Fractional Part ◽  
Saturation Temperature ◽  
Data Reconciliation ◽  
Simultaneous Estimation ◽  
Sigmoid Function ◽  
Time Data

Real time applications like model predictive control, monitoring and data reconciliation of power plants and industrial processes employ nonlinear mathematical models and require thermodynamic properties and their derivatives of working fluids. Applications like super heater temperature control based on energy balance and real time data reconciliation, require an efficient and a compact method for simultaneous estimation of thermodynamic properties, and their partial derivatives suitable for implementation in field-programmable gate array (FPGA). However, the complex mathematical formulations of these properties prohibit direct implementations in FPGAs. Single artificial neural network (ANN) architecture is used to replace the entire code in higher level languages, running into a few thousand lines. FPGA implementation of a compact neural network for the entire range of thermodynamic properties is presented. Large arguments in sigmoid function are factored into a product of integer and a fractional part which is represented using series approximation with five terms only and the integers are represented in look up table (LUT). This ensures optimum storage and computational burden for the above applications. The ANN is implemented in IEEE 754 floating point with synthesis in Xilinx ISE design suite using Verilog HDL. The results are presented for a typical pressure versus saturation temperature.

Application of Real-Time Field Data to Optimize Drilling Hydraulics Using Neural Network Approach

2015 ◽  
Vol 137 (6) ◽  
Author(s):  
Yanfang Wang ◽  
Saeed Salehi
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Field Data ◽  
Ann Model ◽  
Time Data ◽  
Neural Network Approach ◽  
Lost Circulation ◽  
Drilling Performance ◽  
Artificial Neural Network Ann ◽  
Pump Pressure

Real-time drilling optimization improves drilling performance by providing early warnings in operation Mud hydraulics is a key aspect of drilling that can be optimized by access to real-time data. Different from the investigated references, reliable prediction of pump pressure provides an early warning of circulation problems, washout, lost circulation, underground blowout, and kicks. This will help the driller to make necessary corrections to mitigate potential problems. In this study, an artificial neural network (ANN) model to predict hydraulics was implemented through the fitting tool of matlab. Following the determination of the optimum model, the sensitivity analysis of input parameters on the created model was investigated by using forward regression method. Next, the remaining data from the selected well samples was applied for simulation to verify the quality of the developed model. The novelty is this paper is validation of computer models with actual field data collected from an operator in LA. The simulation result was promising as compared with collected field data. This model can accurately predict pump pressure versus depth in analogous formations. The result of this work shows the potential of the approach developed in this work based on NN models for predicting real-time drilling hydraulics.

Real-Time Thermodynamic Performance Monitoring and Optimum Thermoeconomic Operation of Power Plants

2011 ◽  
Author(s):  
G. Hariharan ◽  
B. Kosanovic
Keyword(s):  
Linear Programming ◽  
Power Plant ◽  
Real Time ◽  
Power Plants ◽  
Operating Conditions ◽  
Recursive Least Squares ◽  
Time Data ◽  
Real Time Data ◽  
One Step ◽  
Inputs And Outputs

The ability of modern power plant data acquisition systems to provide a continuous real-time data feed can be exploited to carry out interesting research studies. In the first part of this study, real-time data from a power plant is used to carry out a comprehensive heat balance calculation. The calculation involves application of the first law of thermodynamics to each powerhouse component. Stoichiometric combustion principles are applied to calculate emissions from fossil fuel consuming components. Exergy analysis is carried out for all components by the combined application of the first and second laws of thermodynamics. In the second part of this study, techniques from the field of System Identification and Linear Programming are brought together in finding thermoeconomically optimum plant operating conditions one step ahead in time. This is done by first using autoregressive models to make short-term predictions of plant inputs and outputs. Then, parameter estimation using recursive least squares is used to determine the relations between the predicted inputs and outputs. The estimated parameters are used in setting up a linear programming problem which is solved using the simplex method. The end result is knowledge of thermoeconomically optimum plant inputs and outputs one step ahead in time.

A hybrid optimization-based recurrent neural network for real-time data prediction

2013 ◽  
Vol 120 ◽  
pp. 547-559 ◽  
Author(s):  
Xiaoxia Wang ◽  
Liangyu Ma ◽  
Bingshu Wang ◽  
Tao Wang
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Recurrent Neural Network ◽  
Hybrid Optimization ◽  
Time Data ◽  
Data Prediction ◽  
Real Time Data

UCS Neural Network Model for Real Time Sand Prediction

2010 ◽  
Vol 2 ◽  
pp. 1-13 ◽  
Author(s):  
Gbenga Folorunso Oluyemi ◽  
Babs Mufutau Oyeneyin ◽  
Chris Macleod
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Data Gathering ◽  
Time Data ◽  
Sand Control ◽  
Exploration And Production ◽  
Measurement While Drilling ◽  
Textural Data ◽  
Potential Evaluation ◽  
Thick Overburden

Exploration and production activities have moved into more challenging deep-water and subsea environments. Many of the clastic reservoirs in these environments are characterized by thick overburden, HP-HT and largely unconsolidated formations with challenging sand management issues. For effective overall field/reservoir management, it is crucial to know if and when sand would fail and be ultimately produced. Field-life sanding potential evaluation and analysis, which seeks to evaluate the sanding potential of reservoir formations during the appraisal stage and all through the development to the abandonment stage, is therefore necessary so that important reservoir/field management decisions regarding sand control deployment can be made. Recent work has identified Unconfined Compressive Strength (UCS) as a key parameter required for the evaluation and analysis of sanding potential of any reservoir formation. There is therefore the need to be able to predict this important sanding potential parameter accurately and in real time to reduce the level of uncertainties usually associated with sanding potential evaluation and analysis. In this work, neural network coded in C++ was trained with log-derived petrophysical, geomechanical and textural data to develop a stand-alone model for predicting UCS. Real-time functionality of this model is guaranteed by real time data gathering via logging while drilling (LWD) and other measurement while drilling (MWD) tools. The choice of neural network over and above other methods and techniques which have been widely used in the industry was informed by its ability to better resolve the widely known complex relationship between petrophysical, textural and geomechanical strength parameters.

scholarly journals Traffic Sign Classification Using Convolutional Neural Network

2021 ◽  
pp. 01-10
Author(s):  
Pranav Kale ◽  
Mayuresh Panchpor ◽  
Saloni Dingore ◽  
Saloni Gaikwad ◽  
Prof. Dr. Laxmi Bewoor
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Autonomous Driving ◽  
Time Data ◽  
Traffic Sign ◽  
Real World Data ◽  
Data Set ◽  
Proposed Model ◽  
Validation Set

In today's world, deep learning fields are getting boosted with increasing speed. Lot of innovations and different algorithms are being developed. In field of computer vision, related to autonomous driving sector, traffic signs play an important role to provide real time data of an environment. Different algorithms were developed to classify these Signs. But performance still needs to improve for real time environment. Even the computational power required to train such model is high. In this paper, Convolutional Neural Network model is used to Classify Traffic Sign. The experiments are conducted on a real-world data set with images and videos captured from ordinary car driving as well as on GTSRB dataset [15] available on Kaggle. This proposed model is able to outperform previous models and resulted with accuracy of 99.6% on validation set. This idea has been granted Innovation Patent by Australian IP to Authors of this Research Paper. [24]

Multi-Parameter Prediction for Steam Turbine Based on Real-Time Data Using Deep Learning Approaches

2021 ◽  
Author(s):  
Lei Sun ◽  
Tianyuan Liu ◽  
Yonghui Xie ◽  
Xinlei Xia
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Power Plant ◽  
Steam Turbine ◽  
Real Time ◽  
Learning Approaches ◽  
Time Data ◽  
Time Parameters ◽  
Process Prediction ◽  
Parameter Prediction

Abstract Accurate and real-time parameters forecasting is of great importance to the turbine control and predictive maintenance which can help the improvement of power system. In this study, deep-learning models including recurrent neural network (RNN) and convolutional neural network (CNN) for multi-parameter prediction are proposed, and are applied to predict real-time parameters of steam turbine based on data from a power plant. Firstly, the prediction results of RNN and CNN models are compared by the overall performance. The two models show good performance on forecasting of six state parameters while RNN performs better. Moreover, the detailed performance on a certain day show that the relative error of two models are both less than 2%. Finally, the influence of model designs including loss function, training size and input time-steps on the performance of RNN model are also explored. The effects of the above parameters on the prediction performance, training and prediction time of the models are studied. The results can provide a reference for model deployment in the power plant. It is convinced that the proposed method has a high potential for dynamic process prediction in actual industrial scenarios through the above research.

Harmonic Monitoring Based on BP Neural Network

2012 ◽  
Vol 532-533 ◽  
pp. 1354-1358
Author(s):  
Bai Fen Liu ◽  
Yun Chen ◽  
Xian Wu Fang
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Bp Neural Network ◽  
Network Theory ◽  
Harmonic Suppression ◽  
Matlab Simulation ◽  
Time Data ◽  
Monitoring Model ◽  
Training Capacity ◽  
Neural Network Theory

This article applies the BP neural network theory into the measuring of harmonics, through the model automatically learn training capacity to create real-time monitoring model of harmonic. And that I am using matlab simulation, to obtained harmonic simulation data. Through this simulation technology to monitor the harmonic and obtain real-time data, the data can provide reference for harmonic suppression.

Sign in / Sign up

Export Citation Format

Share Document