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

A distributed real-time data prediction framework for large-scale time-series data using stream processing

2017 ◽  
Vol 10 (2) ◽  
pp. 145-165 ◽  
Author(s):  
Kehe Wu ◽  
Yayun Zhu ◽  
Quan Li ◽  
Ziwei Wu
Keyword(s):  
Time Series ◽  
Real Time ◽  
Large Scale ◽  
Time Series Data ◽  
Data Sources ◽  
Series Data ◽  
Time Data ◽  
Content Type ◽  
Data Prediction ◽  
Real Time Data

Purpose The purpose of this paper is to propose a data prediction framework for scenarios which require forecasting demand for large-scale data sources, e.g., sensor networks, securities exchange, electric power secondary system, etc. Concretely, the proposed framework should handle several difficult requirements including the management of gigantic data sources, the need for a fast self-adaptive algorithm, the relatively accurate prediction of multiple time series, and the real-time demand. Design/methodology/approach First, the autoregressive integrated moving average-based prediction algorithm is introduced. Second, the processing framework is designed, which includes a time-series data storage model based on the HBase, and a real-time distributed prediction platform based on Storm. Then, the work principle of this platform is described. Finally, a proof-of-concept testbed is illustrated to verify the proposed framework. Findings Several tests based on Power Grid monitoring data are provided for the proposed framework. The experimental results indicate that prediction data are basically consistent with actual data, processing efficiency is relatively high, and resources consumption is reasonable. Originality/value This paper provides a distributed real-time data prediction framework for large-scale time-series data, which can exactly achieve the requirement of the effective management, prediction efficiency, accuracy, and high concurrency for massive data sources.

scholarly journals Neuro-Fuzzy Logic Based Robust Detection and Isolation of Economizer and Air Pre-Heater Faults in Steam Boiler

2019 ◽  
Vol 8 (4) ◽  
pp. 10727-10733
Keyword(s):  
Neural Network ◽  
Fuzzy Logic ◽  
Real Time ◽  
Logic Model ◽  
Steam Boiler ◽  
Time Data ◽  
Air Preheater ◽  
Neuro Fuzzy ◽  
Real Time Data ◽  
Intelligent Methods

The technique of Fault Detection and Isolation (FDI) of Economizer and Air-preheater of Boiler using Neuro-fuzzy system is presented in this paper. FDI using model based approach and intelligent methods are the current trend applied in space industries, process industries and power plants. Intelligent methods like Fuzzy, Neural network and Neuro-fuzzy methods are simpler for modeling and faster for detection and isolation of faults. Here the water wall type steam boiler which is used for producing steam in fertilizer industry is studied. The proposed scheme is detecting and isolating the faults and failures happens in the economizer and air preheater of boiler. The common faults are corrosion, erosion, cracking of boiler tubes at welding points, tube rupturing, scale formation in the tubes, external ash deposits etc. The inherent non-linearity of boiler makes Neuro-fuzzy logic method suitable for FDI for all possible faults. The detection of faults is carried out by computing residuals, which are the differences between real process output and estimated output by neuro-fuzzy logic model. These estimated outputs were obtained from the neuro-fuzzy logic model which is trained using real time data by Adaptive Neuro-fuzzy Inference Systems (ANFIS). The real time data of economizer and air-preheater of boiler is collected and used for residual generation. The residuals will be formed for two outputs which are playing important role. If the residual exceeds threshold value indicates various faults in the boiler components and makes the proposed FDI scheme robust against process and measurement noises, process modeling error, disturbances and all uncertainties etc. The threshold band is calculated using model error model method. To isolate the faults, the residuals are normalized and its magnitudes are compared with present fault severity limits. More the range of severity more will be the magnitude of faults in the boiler. FDI by neuro-fuzzy method is more advantages as it combines the advantage of artificial neural network and fuzzy logic methods. The neural networks are more adaptable and have more learning ability. Fuzzy systems are dealing with human reasoning and decision making. As a result the designed FDI scheme is more sensitive to faults and less sensitive to uncertainties and disturbances etc. makes the scheme robust. The required data and fault knowledge for the research work is collected from BHEL make 55 tons per hour capacity, water tube type boiler available in Madras fertilizer Limited (MFL), Chennai.

Optimized recurrent neural network with fuzzy classifier for data prediction using hybrid optimization algorithm: Scope towards diverse applications

2020 ◽  
pp. 2050074
Author(s):  
A. S. Prakaash ◽  
K. Sivakumar
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Prediction Model ◽  
Recurrent Neural Network ◽  
Optimization Algorithm ◽  
Fuzzy Regression ◽  
Hybrid Optimization ◽  
Hybrid Optimization Algorithm ◽  
Data Prediction ◽  
Fuzzy Regression Model

Today, data processing has become a challenging task due to the significant increase in the amount of data collected using various sensors. To put up knowledge and forecast the data, the existing data mining techniques compute all numerical attributes in the memory simultaneously. However, the over-abundance of entire factors in the data makes accurate prediction infeasible. This paper attempts to implement a new data prediction model using an optimized machine learning algorithm. The proposed data prediction model involves four main phases: (a) data acquisition, (b) feature extraction, (c) data normalization, and (d) prediction. Initially, few data from the UCI repository like Bike Sharing Dataset, Carbon Nanotubes, Concrete Compressive Strength, Electrical Grid Stability Simulated Data, and SkillCraft-1 Master Table are collected. Further, the feature extraction process extracts the first-order statistics like mean, median, standard deviation, the maximum value of entire data, and the minimum value of entire data, and the second-order statistics like kurtosis, skewness, energy, and entropy. Next, the data or feature normalization is done to arrange the data within a certain limit. The normalized features are then subjected to a hybrid prediction system by integrating the Recurrent Neural Network (RNN) and Fuzzy Regression model. As a modification, the number of hidden neurons in the RNN and membership limits of the Fuzzy Regression model are optimized by a hybrid optimization algorithm by merging the concepts of Whale Optimization Algorithm (WOA) and Cat Swarm Optimization (CSO), which is called the Whale Updated Seek Mode-based CSO (WS-CSO) algorithm. Then, the efficiency of the optimized hybrid classifier for all-time prediction of data in different applications is confirmed based on its valuable performance and comparative analysis.

Sign in / Sign up

Export Citation Format

Share Document