Detection of Boiler Tube Leakage Fault in a Thermal Power Plant Using Machine Learning Based Data Mining Technique

2019 ◽  
Author(s):  
Kyu han Kim ◽  
Heung seok Lee ◽  
Jung hwan Kim ◽  
June Ho Park
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Power Plant ◽  
Thermal Power Plant ◽  
Thermal Power ◽  
Boiler Tube ◽  
Data Mining Technique ◽  
Mining Technique

Water pipe failure prediction using AutoML

Facilities ◽  
2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Cheng Zhang ◽  
Zehao Ye
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Prediction Models ◽  
Water Pipe ◽  
Pipe Failure ◽  
Data Mining Technique ◽  
Content Type ◽  
Mining Technique ◽  
Good Potential ◽  
Pipeline Failure

Purpose Owing to the consumption of considerable resources in developing physical pipe prediction models and the fact that the statistical models cannot fit the failure records perfectly, the purpose of this paper is to use data mining method to analyze and predict the risks of water pipe failure via considering attributes and location of pipes in historical failure records. One of the Automatized Machine Learning (AutoML) methods, tree-based pipeline optimization technique (TPOT) was used as the key data mining technique in this research. Design/methodology/approach By considering pipeline attributes, environmental factors and historical pipeline broke/breaks records, a water pipeline failure prediction method is proposed in this research. Regression analysis, genetic algorithm, machine learning, data mining approaches are used to analyze and predict the probability of pipeline failure. TPOT was used as the key data mining technique. A case study was carried out in a specific area in China to investigate the relationships between pipeline broke/breaks and relevant parameters, such as pipeline age, materials, diameter, pipeline density and so on. Findings By integrating the prediction models for individual pipelines and small research regions, a prediction model is developed to describe the probability of water pipe failures and validated by real data. A high fitting degree is achieved, which means a good potential of using the proposed method in reality as a guideline for identifying areas with high risks and taking proactive measures and optimizing the resources allocation for water supply companies. Originality/value Different models are developed to have better prediction on regional or individual pipeline. A comparison between the predicted values with real records has shown that a preliminary model has a good potential in predicting the future failure risks.

scholarly journals MINING SIMILAR PATTERN WITH ATTRIBUTE ORIENTED INDUCTION HIGH LEVEL EMERGING PATTERN (AOI-HEP) DATA MINING TECHNIQUE

2017 ◽  
Vol 79 (7-2) ◽  
Author(s):  
Harco Leslie Hendric Spits Warnars ◽  
Nizirwan Anwar ◽  
Richard Randriatoamanana ◽  
Horacio Emilio Perez Sanchez
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Data Mining ◽  
Similar Pattern ◽  
Frequent Pattern ◽  
Data Mining Technique ◽  
Mining Technique ◽  
High Level ◽  
Concept Attribute ◽  
Emerging Pattern

AOI-HEP (Attribute Oriented Induction High Emerging Pattern) as new data mining technique has been success to mine frequent pattern and is extended to mine similar patterns. AOI-HEP is success to mine 3 and 1 similar patterns from IPUMS and breast cancer UCI machine learning datasets respectively. Meanwhile, the experiments showed that there was no finding similar patterns on adult and census UCI machine learning datasets. The experiments showed that finding AOI-HEP similar pattern in dataset is influenced by learning on chosen high level concept attribute in concept hierarchy and it is applied to AOI-HEP frequent pattern in previous research as well. The experiments chosed high level concept attributes such as workclass, clump thickness, means and marts for adult, breast cancer, census and IPUMS datasets respectively. In order to proof that the chosen high level concept attribute will influences the AOI-HEP similar pattern in dataset, then extended experiments were carried on and the finding were census dataset which had been none AOI-HEP similar pattern, had AOI-HEP similar pattern when learned on high level concept in marital attribute. Meanwhile, Breast cancer which had been had 1 AOI-HEP similar pattern, had none AOI-HEP similar pattern when learned on high level concept in attributes such as cell size, cell shape and bare nuclei. The 2 of 3 finding Similar patterns in IPUMS dataset have strong discriminant rule since having large growth rates such as 1.53% and 3.47%, and having large supports in target dataset such as 4.54% and 5.45 respectively. Moreover, there have small supports in contrasting dataset such as 2.96% and 1.57% respectively.         

scholarly journals Application of machine learning to predict the thermal power plant process condition

2022 ◽  
Vol 2150 (1) ◽  
pp. 012029
Author(s):  
M M Sultanov ◽  
I A Boldyrev ◽  
K V Evseev
Keyword(s):  
Machine Learning ◽  
Power Plant ◽  
Thermal Power Plant ◽  
Input Data ◽  
Data Cleaning ◽  
Thermal Power ◽  
Process Condition ◽  
Process Variables ◽  
Machine Learning Model ◽  
Plant Process

Abstract This paper deals with the development of an algorithm for predicting thermal power plant process variables. The input data are described, and the data cleaning algorithm is presented along with the Python frameworks used. The employed machine learning model is discussed, and the results are presented.

Sign in / Sign up

Export Citation Format

Share Document