ENERGY ASSESSMENT OF URBAN BUILDINGS BASED ON GEOGRAPHIC INFORMATION SYSTEM

2020 ◽  
Vol 15 (3) ◽  
pp. 83-93
Author(s):  
Wei Tian ◽  
Chuanqi Zhu ◽  
Yunliang Liu ◽  
Baoquan Yin ◽  
Jiaxin Shi
Keyword(s):  
Machine Learning ◽  
Sensitivity Analysis ◽  
Energy Saving ◽  
Energy Analysis ◽  
Building Energy ◽  
Learning Models ◽  
Energy Assessment ◽  
Urban Buildings ◽  
Energy Models ◽  
Machine Learning Models

ABSTRACT Urban building energy analysis has attracted more attention as the population living in cities increases as does the associated energy consumption in urban environments. This paper proposes a systematic bottom-up method to conduct energy analysis and assess energy saving potentials by combining dynamic engineering-based energy models, machine learning models, and global sensitivity analysis within the GIS (Geographic Information System) environment for large-scale urban buildings. This method includes five steps: database construction of building parameters, automation of creating building models at the GIS environment, construction of machine learning models for building energy assessment, sensitivity analysis for choosing energy saving measures, and GIS visual evaluation of energy saving schemes. Campus buildings in Tianjin (China) are used as a case study to demonstrate the application of the method proposed in this research. The results indicate that the method proposed here can provide reliable and fast analysis to evaluate the energy performance of urban buildings and determine effective energy saving measures to reduce energy consumption of urban buildings. Moreover, the GIS-based analysis is very useful to both create energy models of buildings and display energy analysis results for urban buildings.

scholarly journals Tuning machine learning models for prediction of building energy loads

2019 ◽  
Vol 47 ◽  
pp. 101484 ◽  
Author(s):  
Saleh Seyedzadeh ◽  
Farzad Pour Rahimian ◽  
Parag Rastogi ◽  
Ivan Glesk
Keyword(s):  
Machine Learning ◽  
Building Energy ◽  
Learning Models ◽  
Machine Learning Models

scholarly journals Comparison of Machine Learning Classifiers for Accurate Prediction of Real-Time Stuck Pipe Incidents

Energies ◽  
2020 ◽  
Vol 13 (14) ◽  
pp. 3683 ◽  
Author(s):  
Javed Akbar Khan ◽  
Muhammad Irfan ◽  
Sonny Irawan ◽  
Fong Kam Yao ◽  
Md Shokor Abdul Rahaman ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sensitivity Analysis ◽  
Sensitivity And Specificity ◽  
Activation Function ◽  
Ann Model ◽  
Learning Models ◽  
Drilling Operation ◽  
Svm Model ◽  
Drilling Operations ◽  
Machine Learning Models

Stuck pipe incidents are one of the contributors to non-productive time (NPT), where they can result in a higher well cost. This research investigates the feasibility of applying machine learning to predict events of stuck pipes during drilling operations in petroleum fields. The predictive model aims to predict the occurrence of stuck pipes so that relevant drilling operation personnel are warned to enact a mitigation plan to prevent stuck pipes. Two machine learning methodologies were studied in this research, namely, the artificial neural network (ANN) and support vector machine (SVM). A total of 268 data sets were successfully collected through data extraction for the well drilling operation. The data also consist of the parameters with which the stuck pipes occurred during the drilling operations. These drilling parameters include information such as the properties of the drilling fluid, bottom-hole assembly (BHA) specification, state of the bore-hole and operating conditions. The R programming software was used to construct both the ANN and SVM machine learning models. The prediction performance of the machine learning models was evaluated in terms of accuracy, sensitivity and specificity. Sensitivity analysis was conducted on these two machine learning models. For the ANN, two activation functions—namely, the logistic activation function and hyperbolic tangent activation function—were tested. Additionally, all the possible combinations of network structures, from [19, 1, 1, 1, 1] to [19, 10, 10, 10, 1], were tested for each activation function. For the SVM, three kernel functions—namely, linear, Radial Basis Function (RBF) and polynomial—were tested. Apart from that, SVM hyper-parameters such as the regularization factor (C), sigma (σ) and degree (D) were used in sensitivity analysis as well. The results from the sensitivity analysis demonstrate that the best ANN model managed to achieve an 88.89% accuracy, 91.89% sensitivity and 86.36% specificity, whereas the best SVM model managed to achieve an 83.95% accuracy, 86.49% sensitivity and 81.82% specificity. Upon comparison, the ANN model is the better machine learning model in this study because its accuracy, sensitivity and specificity are consistently higher than those of the best SVM model. In conclusion, judging from the promising prediction accurateness as demonstrated in the results of this study, it is suggested that stuck pipe prediction using machine learning is indeed practical.

Sign in / Sign up

Export Citation Format

Share Document