This document describes the journey taken over the years by the Milazzo Refinery, together with the Contractors, to achieve and maintain levels of excellence for the health and safety of all workers. The last step in this process was the "Safety Pact" between all parties involved in health and safety aspects. The Pact is updated and renewed every year with increasingly challenging objectives.
The Pact is based on the following innovative methods: STOP - ANALYZE - THINK - DO procedure. It is based on the self-evaluation risk which is a procedure that every employee has to follow before starting any activity Safety "Pills". Short meetings take place on the contractors working area aimed at analyzing good or and bad practice observed during the works execution Housekeeping Coordinator. New role dedicated to manage all the issues related with the housekeeping of the working areas Rewarding system to evaluate behaviours adopted in the working area: bonus/malus points to workers depending on their particular attention for safety.
STOP - ANALYZE - THINK - DO procedure. It is based on the self-evaluation risk which is a procedure that every employee has to follow before starting any activity
Safety "Pills". Short meetings take place on the contractors working area aimed at analyzing good or and bad practice observed during the works execution
Housekeeping Coordinator. New role dedicated to manage all the issues related with the housekeeping of the working areas
Rewarding system to evaluate behaviours adopted in the working area: bonus/malus points to workers depending on their particular attention for safety.
The Safety Pact was thought and implemented as a first field test during a Major Turnaround (TA) and as a possible innovative tool to define rules and goals between RAM and Contractors, with the purpose of improving safety during turnaround activities and achieving the most important target of ZERO INJURIES. Following turnaround completion RaM and Contractors make a balance of the results analyzing performance index and making plan to improve weak area in the future.
The implementation of a formal signed Safety Pact between RaM dramatically increased engagement of different companies (client + contractors) towards safety and allowed RaM to achieve ZERO INJURIES during the Turnaround activities. Moreover it has been observed an improvement of the housekeeping, a reduction of non-compliances for dangerous behaviour and a widespread application of RaM procedure for scaffoldings.
The success of this kind of approach suggested RaM to adopt the safety pact to every refinery turnaround (both major and minor ones) but also extend it to each single refinery maintenance activity.
Antipova, Ksenia (Skolkovo Institute of Science and Technology, Digital Petroleum) | Klyuchnikov, Nikita (Skolkovo Institute of Science and Technology, Digital Petroleum) | Zaytsev, Alexey (Skolkovo Institute of Science and Technology, Digital Petroleum) | Gurina, Ekaterina (Skolkovo Institute of Science and Technology, Digital Petroleum) | Romanenkova, Evgenia (Skolkovo Institute of Science and Technology, Digital Petroleum) | Koroteev, Dmitry (Skolkovo Institute of Science and Technology, Digital Petroleum)
Majority of the accidents while drilling have a number of premonitory symptoms notable during continuous drilling support. Experts can usually recognize such symptoms, however, we are not aware of any system that can do this job automatically. We have developed a Machine learning algorithm which allows detecting anomalies using the drilling support data (drilling telemetry). The algorithm automatically extracts patterns of premonitory symptoms and then recognizes them during drilling.
The machine learning model is based on Gradient Boosting decision trees. The model analyzes real time drilling parameters within a sliding 4-hour window. For each measurement, the model calculates the probability of an accident and warns about anomaly of particular type, if the probability exceeds the selected threshold.
Our training sample comes from 20+ oilfields and consists of sections related to 80+ accidents of the following types: stuck pipe, mud loss, gas-oil-water show, washout of pipe string, failure of drilling tool, packing formation, that occurred while drilling, trip-in, trip-out, reaming; the sample also includes more than 700 sections without accidents.
We have designed the prediction model to work during drilling new wells and to distinguish the normal drilling process from the faulty one. One can configure the anomaly threshold to balance amount of false alarms and the number of missed accidents.
To evaluate quality of the model we measure data science metrics and check an industry-driven criterion. The model can identify 40 accidents from about 80 with high confidence, whereas for the others there is still a room for improvement. Our findings suggest that including more accidents of underrepresented types will improve quality. Other data science metrics also support aptitude of the model. Finally, having data from multiple heterogeneous oilfields, we expect that the model will generalize well to new ones.
This paper presents a good practice of development and implementation of a data-driven model for automatic supervision of continuous drilling. In particular, the model described in the paper will assist specialists with drilling accidents prediction, optimize their work with data and reduce the nonproductive time associated with the accidents by up to 20%.
Production and drilling activities in offshore installation are one of the most necessary activities of human society. To drill a subsea well and raise the crude oil to a platform, by itself, presents a series of risks. Associated with this activity, when the crude oil reaches the topside of the platform, there are a number of operations that prepare the oil and gas to be exported to land by pipelines or oil tanker vessels, which involves equipment and process that take high temperatures, high pressure and high flow rates. Understanding the dynamics of the factors that can affect the interaction of operators with all these offshore complex systems is critical, because the loss of control of these systems can cause serious accidents, resulting in injuries to workers, environmental damage, loss of production and geopolitical crises. Accidents in the oil and gas offshore installations, such as drilling rigs and FPSOs, can have tragic consequences and all efforts should be targeted to prevent its recurrence. Therefore, from the perspective of current technological developments, it is essential to consider the influence of Human Factors in the risk management of offshore industrial plants.
Workplace safety is a main objective of any company working in the oil and gas business. The processes have been developed and established over the past decades based on individual experiences and causal pathways. The exhaustion of technical and administrative barriers has led to the introduction of behavioral safety. Recent advances in data technology and machine learning have disrupted many businesses and processes and can lead to a new paradigm in workplace safety as well.
In this case study we demonstrate the application of data science and predictive analytics to aid the HSE function and prevent accidents. We have analyzed operational and accident data from the past 10 years at a leading oil and gas company to quantify the effectiveness of their safety programs.
We have determined how many accidents each program actually prevents, and is able to prevent in an optimal setting. We have determined the optimal level of engagement for each program, and at what level diminishing returns set in.
We have further developed a predictive model to forecast the occurrence of accidents one month ahead of time. In this way the HSE function is able to focus on 15% of locations to control 69% of the accidents. The forecast was also able to predict accidents at locations where one would traditionally not expect accidents to happen, such as locations with low activity.
This paper shows the potential for improvement that is possible with the emerging big data, artificial intelligence and machine learning tools specifically in the field of workplace safety.
Learning is a "linear process" for workers. It includes studying and understanding basic systems, normal procedures, and emergency procedures in an operational setting. Therefore, they must be developed for the frontline worker, from the frontline worker's perspective and in their words. Step by step procedures will describe the operation of equipment and the interaction of co-workers in the operational context without leaving the frontline worker any questions or assumptions - it is written with concept of operational-need-to-know. Once completed, they will capture the optimum efficient processes and improve your safety management system.
By borrowing best practices from the airline industry several oil and gas companies have been able to implement a system that prevents and traps human error. My presentation will share with your audience that the foundation to safety and efficiency is the creation of standard work for operators and contractors. Standard work that delivers quality work based on the development of procedures and checklists that work in harmony on the rig floor. We will highlight our success measured by the increased efficiency in fracking by over 300%, a reduction in crane incidents by 50% and the reduction of fatal control of work errors. All through the development of a standardization department which became the center for excellence for the operator and the contractor.
Standardization regarding operational procedures are still a new concept within the industry. Our team has produced tangible results which will be shared with the SPE membership in order to demonstrate the effectiveness of standardization and the increased safety and efficiency from it.
Long-term studies of oil spill responders are urgently needed as oil spills continue to occur. To this end, the prospective Deepwater Horizon (DWH) Oil Spill Coast Guard Cohort study was established . DWH oil spill responders and nonresponders who were members of the US Coast guard were included. A team of researchers from the University of Houston is working with the oil industry to develop new ways to predict when an offshore drilling rig is at risk for a potentially catastrophic accident.
Aberdeen’s Opex Group and an industrial behavioral psychologist are designing a tool that will combine data from diagnostic surveys with historical data on oil and gas accidents and spills. The major accident of 6 July 1988, when Britain’s Piper Alpha facility caught fire and exploded, remains one of the worst imaginable scenarios for everyone working in and with the petroleum industry. Its lessons are still relevant. The Piper Alpha incident in the UK North Sea had a profound impact on the development of process safety culture and legislation around the world. With the great crew change already taking place, this column reflects on the disaster to ensure that its lessons are not forgotten.
In process industries, major accidents can result in numerous severe injuries or fatalities. This study reviews the broken human factors and barriers leading to these events and highlights key aspects of a technological-risk-assessment processes. Considering most of the rigs deal with human-machine interface systems, the role of human factors is at the heart of any successful operation. Eye-tracking technology can be useful in real-time operation centers where ocular movement data can improve the professionals’ performance. The Step Change in Safety Human Factors Workgroup strives to improve basic knowledge and understanding of human factors to ensure related risks are managed and controlled properly.
This paper provides an overview of the company’s journey toward preventing significant process-safety incidents. Each step involved in this journey plays a key part. By focusing the improvement of the process on individual steps, the overall learning process has improved significantly. In process industries, major accidents can result in numerous severe injuries or fatalities. This study reviews the broken human factors and barriers leading to these events and highlights key aspects of a technological-risk-assessment processes.
Colorado Gov. John Hickenlooper recently said the home explosion in Firestone, Colorado, that killed two people was a “freak accident.” But a new study by the Colorado School of Public Health indicates that accidents like this may not be so uncommon. The company that owns a gas well linked to a fatal home explosion in Colorado says it will permanently shut down that well and two others in the neighborhood. Anadarko Petroleum announced on its website on 16 May that it is permanently disconnecting 1-in.-diameter