Oct-2020

The digital refinery

How MOL used a new approach to data to improve plant diagnostics, adopt alternate crudes and save millions. The petroleum industry is once again in the midst of titanic changes.1

Craig Harclerode
OSIsoft

Article Summary

Declining prices, expanding sources of supply, rising regulatory requirements and, perhaps most importantly of all, a dramatic shift in markets like transportation are forcing companies across the value chain to reconsider long held assumptions about expansion, growth and customer demand.

Luckily, these new challenges are coinciding with advances in big data, Internet of Things (IoT) and predictive analytics and the ability to leverage to process opportunity crudes and be more proactive and predictive in decision making. While the upstream oil industry has been a somewhat enthusiastic adopter of digital technology, the midstream and downstream segments have been conservative and slow to adopt. That is changing with the Industrial Internet of Things (IIoT), advanced analytics and big data. Collectively, we are inundated with marketing messages that are adding confusion and false promises, resulting in a good number of projects that go awry with limited or no business value and, worse, lost opportunity costs.

But we will also see implementations that will effectively serve as a blueprint because they will demonstrate how digital technology can reduce risks and costs while improving asset utilisation, yields, integrity and, most importantly, profitability.

In fact, we already have such an example. MOL, based in Hungary, has been on a journey to reinvent its operations by better leveraging operational data already being generated by its distributed control systems (DCS) and other systems as part of its operations. In 2012, MOL leadership, in response to European competition resulting in low cracked spreads, embarked on a business transformation enabled by digital technologies.

The results? MOL has developed techniques for processing opportunity crudes while minimising the negative consequences such as corrosion, operational issues in areas such as the cokers, and yields. Advanced corrosion analytics such as high temperature hydrogen attach (HTHA) and other forms of predictive corrosion have been implemented across multiple sites. In all, MOL estimates it increased earnings before interest, tax, depreciation and amortisation (EBITDA) by $1 billion over a five year period ending in 2016 through more aggressive data modelling and analytics.

Petroleum Economist named MOL Downstream Company of the Year in 20162 while the FieldComm Group gave the company its Plant of the Year Award for its Danube facility.

Background
MOL is one of Central Europe’s largest downstream companies. It operates four refineries and two petrochemical plants in eight countries along with 2000 filling stations across 13 countries. To organise data across its production facilities, MOL has been using the PI System from OSIsoft since 1998.

The system, which has expanded steadily, is divided into four high availability collectives with a combined total of approximately 400,000 ‘tags’ or data points. More importantly, MOL utilises PI Asset framework with smart asset objects to provide a configurable, dynamic smart operational technology (OT) infrastructure.

Currently, MOL has over 300 smart asset object templates 300 templates, 21,000 elements, and over 61,000 event frames for signalling the occurrence of key parameters or events (see Figure 1). Tibor Komroczki, who leads the Information Integration and Automation team at MOL, refers to the PI System as the MOL common language as it enables the abstraction and nomination of a diverse tag and asset naming, units of measure, and time zones. MOL generates over 80 billion data points per year.

The PI System served primarily as an operations system of record until 2010 when Komroczki led an effort for digital transformation. As a first step, MOL adopted PI Asset Framework to create a so-called ‘digital twin’ of different processes and equipment sets in a facility. With PI Asset Framework, all of the relevant data streams, meta data, calculations and analytics, and alerts and notifications from a process step are combined into a comprehensive, digital replica of the plant. Additionally at this time, it adopted PI Coresight, a visualisation tool for displaying and/or analysing AF models.

Taken together, the smart OT infrastructure with PI Asset Framework, and PI Coresight, MOL had built a self-serve analytics and business intelligence environment where operators and engineers who traditionally used Microsoft Excel can configure their own smart asset objects, combine them like Lego blocks and create their own digital replica and experiment with potential improvements, and then execute changes across the MOL enterprise with governance.

With the smart OT infrastructure in place, MOL established a foundation for higher level efficiencies because it could connect its assets relatively easily and track its performance backwards and forwards. New applications can be added rapidly. Komroczki asserts that greater control over data has enabled MOL to move from managing in a reactive sense to predictive management to management by exception, as indicated by the existence of over 61,000 event frames.

Some of the achievements include improved asset integrity and safety, asset health, improved energy efficiency, increased yield, reduced hydrocarbon loss, improved environmental reporting, and reduced maintenance costs (see Figure 2).

Another plus: MOL reduced its IT costs and reliance on outside vendors because employees were able to quickly build their own functionality on top of their infrastructure and then replicate it across foundries and, in doing so, simplifying and standardising its application and solutions portfolio. Different data streams can also be analysed in tandem so that MOL could determine the full impact (financial, maintenance, energy consumption) on changes to output.

MOL employed analytics to reduce the risk of high temperature hydrogen attacks (HTHA). By studying relevant operational data, the company was able to pinpoint the temperature and pressure parameters that increased the risk of HTHA. They developed a smart asset HTHA application template that was deployed in six units in less than a week. Following the success, it was rolled out across MOL’s plants in 2015 to over 50 pipe nodes.

Advanced analytics potentially can be applied in a wide variety of ways: energy modelling optimisation; the impact and ripple effects of opportunity crudes in areas of corrosion, fouling, and efficiencies; the economic gains to be achieved through opportunity crude processing; better understanding of advanced control; and preventative and prescriptive maintenance (see Figure 3).

Machine Learning
Once MOL had the smart OT infrastructure across its value chain with associated IIoT analytics, focus was turned to machine learning and “big data analytics”. MOL has become one of the first, if not the first, large refiner to adopt Microsoft Azure machine learning in a production environment (see Figure 4). Microsoft Azure works in conjunction with the PI System: operational data is uploaded to the cloud and then analysed across Microsoft’s cloud infrastructure.