Real-Time Microseismic Mapping Helps Understanding Hydraulic Fracture Geometry, Drainage Patterns, and Oilfield Development Optimization: A Case Study in the Changqing Field

2014 ◽  
Author(s):  
Hongjun Lu ◽  
Chengwang Wang ◽  
Qi Yin ◽  
Xiaohu Bai ◽  
Guangjie Zheng ◽  
...  
Keyword(s):  
Real Time ◽  
Hydraulic Fracture ◽  
Fracture Geometry ◽  
Drainage Patterns ◽  
Oilfield Development

Data Analytics to Help Improve Hydraulic Fracture Geometry Prediction Using Support Vector Regression: Case Study

2020 ◽  
Author(s):  
Avinash Wesley ◽  
Bharat Mantha ◽  
Ajay Rajeev ◽  
Aimee Taylor ◽  
Mohit Dholi ◽  
...  
Keyword(s):  
Support Vector Regression ◽  
Hydraulic Fracture ◽  
Data Analytics ◽  
Support Vector ◽  
Fracture Geometry

Fiber Optic Deployed Behind Cemented Casing in a Vertical Deep Tight Gas Well Used to Enhance Hydraulic Fracturing, Monitoring and Diagnostics

2021 ◽  
Author(s):  
Ahmed Rashid Al-Jahdhami ◽  
Juan Carlos Chavez ◽  
Shaima Abdul Aziz Al-Farsi
Keyword(s):  
Real Time ◽  
Surface Pressure ◽  
Hydraulic Fracture ◽  
Fiber Optic ◽  
Integrated Analysis ◽  
Radioactive Tracers ◽  
Distributed Temperature Sensing ◽  
Time Data ◽  
Fracture Geometry ◽  
Fracture Simulation

Abstract The use of fiber optic (FO) to obtain distributed sensing be it Distributed Temperature Sensing (DTS), Distributed Acoustic Sensing (DAS) or Distributed Strain Sensing (DSS) is a well & reservoir surveillance engineer's dream. The ability to obtain real-time live data has proven useful not only for production monitoring but during fracture stimulation as well. A trial the first of its kind in Petroleum Development Oman (PDO) used fiber optic cable cemented in place behind casing to monitor the fracture operations. Several techniques are used to determine fracture behaviour and geometry e.g. data fracs, step down test and after closure analysis. All these use surface pressure readings that can be limited due to uncertainty in friction pressure losses and the natural complexity in the formation leading to very different interpretations. Post frac data analysis and diagnostics also involves importing the actual frac data into the original model used to design the frac in order to calibrate the strains (tectonics), width exponent (frac fluid efficiency) and the relative permeability. Monitoring the frac using DAS and DTS proved critical in understanding a key component in fracture geometry; frac height. The traditional method to determine fracture height is to use radioactive tracers (RA). But these are expensive and the data only available after the job (after drilling the plugs and cleaning the wellbore). In contrast fiber optic can provide real time data throughout the frac stages including the proppant free PAD stage which tracers can't. The comparison of DTS and Radioactive Tracers showed very good agreement suggesting that DTS could replace RA diagnostic. Hydraulic fracture stimulation operations in well-xx was the first one of its kind to be monitored with fiber optic. The integrated analysis of the available logs allowed us to benchmark various information and gain confidence in the conclusions. This helped fine tune the model for future wells for a more optimized zonal targeting and hydraulic fracture design. In this paper we will share the detailed evaluation of the fracture propagation behaviour and how combining the fiber optic data with the surface pressure, pumping rates and tracer logs in conjunction with a fracture simulation platform where a detailed geomechanical and subsurface characterization data is incorporated to get a more accurate description of fracture geometry.

Pollution based real time control strategies for combined sewer systems

1997 ◽  
Vol 36 (8-9) ◽  
pp. 331-336 ◽  
Author(s):  
Gabriela Weinreich ◽  
Wolfgang Schilling ◽  
Ane Birkely ◽  
Tallak Moland
Keyword(s):  
Real Time ◽  
Control Strategies ◽  
Ammonia Nitrogen ◽  
Simple Extension ◽  
Real Time Control ◽  
Time Control ◽  
Sewer Systems ◽  
Receiving Waters ◽  
Tunnel System

This paper presents results from an application of a newly developed simulation tool for pollution based real time control (PBRTC) of urban drainage systems. The Oslo interceptor tunnel is used as a case study. The paper focuses on the reduction of total phosphorus Ptot and ammonia-nitrogen NH4-N overflow loads into the receiving waters by means of optimized operation of the tunnel system. With PBRTC the total reduction of the Ptot load is 48% and of the NH4-N load 51%. Compared to the volume based RTC scenario the reductions are 11% and 15%, respectively. These further reductions could be achieved with a relatively simple extension of the operation strategy.

scholarly journals A Computer Vision-Based Occupancy and Equipment Usage Detection Approach for Reducing Building Energy Demand

Energies ◽  
2020 ◽  
Vol 14 (1) ◽  
pp. 156
Author(s):  
Paige Wenbin Tien ◽  
Shuangyu Wei ◽  
John Calautit
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Energy Demand ◽  
Energy Savings ◽  
Internal Heat ◽  
Electrical Equipment ◽  
Building Energy ◽  
Hvac Systems ◽  
Equipment Usage

Because of extensive variations in occupancy patterns around office space environments and their use of electrical equipment, accurate occupants’ behaviour detection is valuable for reducing the building energy demand and carbon emissions. Using the collected occupancy information, building energy management system can automatically adjust the operation of heating, ventilation and air-conditioning (HVAC) systems to meet the actual demands in different conditioned spaces in real-time. Existing and commonly used ‘fixed’ schedules for HVAC systems are not sufficient and cannot adjust based on the dynamic changes in building environments. This study proposes a vision-based occupancy and equipment usage detection method based on deep learning for demand-driven control systems. A model based on region-based convolutional neural network (R-CNN) was developed, trained and deployed to a camera for real-time detection of occupancy activities and equipment usage. Experiments tests within a case study office room suggested an overall accuracy of 97.32% and 80.80%. In order to predict the energy savings that can be attained using the proposed approach, the case study building was simulated. The simulation results revealed that the heat gains could be over or under predicted when using static or fixed profiles. Based on the set conditions, the equipment and occupancy gains were 65.75% and 32.74% lower when using the deep learning approach. Overall, the study showed the capabilities of the proposed approach in detecting and recognising multiple occupants’ activities and equipment usage and providing an alternative to estimate the internal heat emissions.

scholarly journals DOLARS, a Distributed On-Line Activity Recognition System by Means of Heterogeneous Sensors in Real-Life Deployments—A Case Study in the Smart Lab of The University of Almería

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 405
Author(s):  
Marcos Lupión ◽  
Javier Medina-Quero ◽  
Juan F. Sanjuan ◽  
Pilar M. Ortigosa
Keyword(s):  
Real Time ◽  
Activity Recognition ◽  
Real Life ◽  
Recognition System ◽  
Machine Learning Algorithms ◽  
Sensor Data ◽  
Heterogeneous Sensors ◽  
On Line ◽  
The University

Activity Recognition (AR) is an active research topic focused on detecting human actions and behaviours in smart environments. In this work, we present the on-line activity recognition platform DOLARS (Distributed On-line Activity Recognition System) where data from heterogeneous sensors are evaluated in real time, including binary, wearable and location sensors. Different descriptors and metrics from the heterogeneous sensor data are integrated in a common feature vector whose extraction is developed by a sliding window approach under real-time conditions. DOLARS provides a distributed architecture where: (i) stages for processing data in AR are deployed in distributed nodes, (ii) temporal cache modules compute metrics which aggregate sensor data for computing feature vectors in an efficient way; (iii) publish-subscribe models are integrated both to spread data from sensors and orchestrate the nodes (communication and replication) for computing AR and (iv) machine learning algorithms are used to classify and recognize the activities. A successful case study of daily activities recognition developed in the Smart Lab of The University of Almería (UAL) is presented in this paper. Results present an encouraging performance in recognition of sequences of activities and show the need for distributed architectures to achieve real time recognition.

Sign in / Sign up

Export Citation Format

Share Document