Fruchtnicht, Erich (Texas A&M University) | Eaker, Nancy (Texas A&M University) | Fellers, John (Texas A&M University) | Urbanczyk, Brad (Texas A&M University) | Robertson, Christina (Texas A&M University) | Dhakal, Merina (Spelman College) | Colman, Stephanie (Texas A&M University) | Freas-Lutz, Diana (Radford University) | Patterson, Hiram (Texas A&M University) | Bazan, Cristina (Texas A&M University) | Giles, Crystal (Texas A&M University)
THE TEXAS A&M HEALTH SCIENCE CENTER (TAMHSC) and Texas A&M University (TAMU) Environmental Health and Safety (EHS) departments are responsible for ensuring the safety of not only all faculty, staff, students and visitors to geographically dispersed campuses across the state of Texas, but also the public surrounding those campuses. Because the university is a state entity, the preferred disposition route for all university assets is public auction administered by the Surplus department. Each research or academic department within the university determines which of its assets are no longer needed and schedules a pickup through its embedded property management team member. The removal of all unwanted assets is performed either by university personnel or by a private moving company. Although EHS had a policy in place for the decontamination of equipment prior to its release to Surplus, the process of equipment being sent to Surplus itself did not directly include EHS.
An Industrial IoT architecture is presented which enables edge computing of data collected from rotating machinery in a model conducive to multiple use cases. The architecture is compared to traditional "IoT data to the cloud" models and on-premise point solutions, illustrating the effectiveness of computing at the edge with a generic IoT solution. Customer benefits from the solution are presented and discussed. The initial solution framework of asset condition monitoring and predictive maintenance is provided by on-premise data analytics software incorporating historical models of asset behavior. Computer hardware traditionally available only in data centers is available to provide powerful computing capabilities. A wireless communications mesh is implemented to provide secure connectivity between plant assets, computers and workers. A digital twin is constructed and augmented reality methods are implemented to extract information from the raw data. Inclusion of plant personnel from planning, to installation, to implementation has been critical to the acceptance and use of the technology in operations. Implementation of a generic IoT architecture rather than a point solution increases the value obtained from the initial investment as subsequent solution frameworks are added. An IoT platform operating at the "intelligent edge" can be more efficient and less costly than cloud-based solutions, reducing time from acquired data to corrective action. An architecture which accounts for role-based and location-aware data presentation further increases the value of the data to the individual worker. Just bringing sensor data to an IoT cloud platform does not create business value from the data. Ensuring interoperability, connectivity, adherence to industry standards and integration of security and manageability are all prerequisites to architecting a scalable Industrial IoT solution that delivers value to the customer. Additional important benefits to the customer are safety, management of change and personal growth of the employees using the technology.
IBM and Massachusetts Institute of Technology (MIT) recently announced that IBM plans to make a 10-year, $240 million investment to create the MIT-IBM Artificial Intelligence (AI) Lab in partnership with MIT. The new lab will be one of the largest long-term university-industry collaborations to date and will mobilize the talent of more than 100 AI scientists, professors, and students to pursue joint research at IBM's Research Lab in Cambridge, Massachusetts, co-located with the IBM Watson Health and IBM Security headquarters in Kendall Square--and on the neighboring MIT campus. The lab will be co-chaired by Dario Gil, IBM research vice president of AI and IBM Q, and Anantha P. Chandrakasan, dean of MIT's School of Engineering.
Total E&P UK Ltd and Merkle have undertaken a proof of concept project to investigate machine learning image analysis applied to image and video data from onshore and offshore sites, in preparation for the deployment of an autonomous asset inspection ground robot in 2019. The aim is to better understand the feasibility of these methods, and to demonstrate the benefits of robotic inspection with regard to improving safety and efficiency, enhancing data capture and reducing operational costs.
An object detection model was developed based on high-performance open source algorithms. Transfer learning was applied using a custom-built image library and the result is a model able to detect a range of different types of items in the industrial environment including mobile equipment, process equipment, infrastructure and personnel (with and without PPE). The object detection model is used to feed into object classification anomaly detection models to look at the state of selected pieces of identified equipment, such as whether a valve is open or closed, which can be placed in the context of the expected state of the process equipment by relating it to the digital twin for the asset. An additional object detection model was developed to operate as a gas leak detection system for infrared cameras.
The object detection model achieved good results and model performance was driven by the number and quality of images used for the training. An anomaly detection model designed to detect whether ball valves were open or closed delivered good results, with high accuracy and balanced false positive and false negative detection rates. The overall performance of the infrared gas detection model was restricted by the limited volume and variability of the training data, although the false positive detection rate was very low. A significant part of the machine learning was devoted to the development of a consistent labelled image library for oil and gas equipment, infrastructure and gas leaks. Image transformations were tested but boosting the number of images using transforms gave variable results. Additional training and testing data is needed to ensure that the models are as robust as possible, especially for the gas leak detection model. Once the models are productionised and in use, additional data can be used to periodically retrain the models for improved performance.
In addition to the machine learning algorithms, a fundamental aspect of the project is the development of the overall technical architecture, supporting the data science. This includes enabling the transfer of data from inspection robots or other connected camera devices into a data store in a cloud computing environment and returning the results to dashboard systems with different levels of detail depending on user requirements.
This paper will discuss when it is advantageous (in the context of an offshore oil and gas environment) to process data at the network edge (in close proximity to equipment assets) or to stream data to a cloud-based Internet of Things (IoT) platform for analysis. It will offer an objective assessment of both approaches and provide recommendations for securing data in both cases, as part of an overarching cybersecurity strategy.
IoT has opened the door to significant efficiency gains in the oil and gas industry. This is particularly the case in the offshore sector, where there is a pressing need to reduce costs and maximize equipment availability. In some cases, it is advantageous to process data in close proximity to equipment assets (i.e., at the edge). In others, it makes more sense to securely stream data to a cloud- based IoT platform and harness artificial intelligence (AI) to aid in decision making. In certain cases, both architectures can be utilized in compliment to one another.
Many factors need to be taken into consideration when evaluating an edge or cloud-based approach. Some of these include data volume, transmission and processing speed, control of data, cost, etc. Edge computing can be used to streamline and enhance the efficiency of data analytics. In certain applications, this can mean the difference between analyzing a performance failure after the fact, and pre-empting it in the first place, which in the offshore environment could potentially translate into millions of dollars per day.
On the other hand, there are situations where it is beneficial to store large volumes of data on a cloud-based platform. For example, if the goal is to leverage advanced IoT-based industrial analytics to optimize an entire fleet of a certain type of equipment, the cloud may be the best solution. Cybersecurity is another consideration. Attacks on critical infrastructure have risen significantly over the course of the past year. As more Intelligent Electronic Devices (IEDs) are deployed in the oil and gas industry to optimize efficiency, Industrial Control Systems (ICSs) are increasingly vulnerable. As a result, the threat extends beyond proprietary data to mission-critical operational technology (OT) assets and equipment.
Cybersecurity standards and layered, defense-in-depth models have grown in response to the frequency and sophistication of cyber attacks. Additionally, recent advances in cyber defense technology incorporate small, kilobit-sized embedded software agents to monitor networks for anomalies that could signal an intrusion. This paper will explore new cybersecurity threats to oil and gas assets, as well as strategies operators can employ to defend against them, whether using an edge or cloud-based platform, or both.
Risk Assessments are used to assess the impact of alternativedesigns, changes during operations, and compliance of offshore installations against tolerabilitycriteria. Typically, asset information is used to develop a mathematical model; this can beupdated to reflect changes during the facility's lifecycle. This paper examines how the use ofcloud-based technology to develop a Digital Twin improves efficiency. Allowing projectstakeholders full access to the QRA model also enables greater understanding of hazards.
Digital technology pervades all areas of business and societyand offers great advantages to safety engineering relative to traditional approaches. This paperdemonstrates how cloud basedtools canturn the traditional static QRA process into a living QRA which can be updated throughout aninstallation's lifecycle by creating a digital twin. This type of living QRA allows projectstakeholders to change key parameters and assess the effect of these changes on risk levels. Inaddition, the results can be interrogated down to fundamental levels using a Microsoft Power BIdashboard.
The output of QRAs are usually static reports providing anoverview of the detailed work undertaken and a high-level summary of the results which arecompared with tolerability criteria or to demonstrate ALARP. This paper demonstrates howcustomised internet browser tools utilising 2D and 3D graphics may be built on top of the QRA toextract more detail than previously possible and communicate risks in a flexible and interactiveway. It also shows how consistent data management can form a basis for innovating beyond thetraditional approach. This allows a wider range of stakeholders to determine risk drivers, isolatesingle accident scenarios and filter results to a greater depth than is possible through a paperreport and allow a greater understanding of their hazards.
Digitalisation is an increasingly ‘hot topic’ in the process industry. Making use of new technologies to provide greater insights can aid in better and more timelyhazard management whilst reducing costs to stakeholders. Examples of innovations which promote better assessment are provided.
The Internet of Things (loT) has paved the way for significant efficiency gains in the oil and gas industry. One concept that has garnered significant attention is the "digital twin". However, there remains a great deal of confusion surrounding what a digital twin actually is and how it can be harnessed to add value to oil and gas operations. Some use digital twin as a synonym for their 3D plant models, others for their predictive maintenance solutions, or their simulation models. The bottom line is that the digital twin is all of these and more and unless operators look at it holistically, they are likely to miss out on some of the benefits.
Digital twins afford companies a number of advantages that would otherwise not be possible, including the ability to run risk analyses, health assessments, and what-if scenarios in real-time; the ability to train personnel in a 3D immersive, risk-free environment; and the capability to detect faults early before control limits are reached. This paper/ presentation will elaborate on how digital twins can be used to enhance efficiency and will address their use in the wider context of the oil and gas industry – with a particular focus on its impact on reducing risk and cost during both the project and operational phases of the asset lifecycle.
The objective is to demystify the digital twin, outline the advanced capabilities it enables and illustrate how oil and gas operators can use this concept to improve their competitive advantage.
Alkadi, Nasr (Energy Innovation Center, BHGE) | Chow, Jon (Measurement and Sensing, BHGE) | Howe, Katy (Energy Innovation Center, BHGE) | Potyrailo, Radislav (GE Research) | Abdilghanie, Ammar (Energy Innovation Center, BHGE) | Jayaraman, Balaji (Oklahoma State University) | Allamraju, Rakshit (Oklahoma State University) | Westerheide, John (Energy Innovation Center, BHGE) | Corcoran, John 6 (Measurement and Sensing, BHGE) | Di Filippo, Valeria (Energy Innovation Center, BHGE) | Kazempoor, Pejman (Energy Innovation Center, BHGE) | Zoghbi, Bilal (Energy Innovation Center, BHGE) | El-Messidi, Ashraf (Measurement and Sensing, BHGE) | Zhang, Jianmin (Energy Innovation Center, BHGE) | Parkes, Glen (Measurement and Sensing, BHGE)
This paper presents our progress in developing, testing, and implementing a Ubiquitous Sensing Network (USN) for real-time monitoring of methane emissions. This newsensor technology supports environmental management of industrial sites through a decision support system. Upon detection of specific inputs, data is processed before passing it on for appropriate actions
An 18-month project will develop and trial a mobile robot for autonomous operational inspection of Total facilities. A consortium of organizations has set out to tackle one of the more enduring challenges in the North Sea: the nondestructive testing (NDT) of corroded pipes under insulation and engineered temporary pipe wraps. General Electric has launched a subsidiary to develop and sell the use of flying, crawling, and swimming drones for inspections in the oil and gas industry, among others, the company announced. Behind the use of most drones and unmanned aerial vehicles is the issue of safely and legally operating beyond the visual line of sight (BVLOS).