According to a Kimberlite research, just 3.65 days of unplanned downtime a year can cost an oil and gas company $5.037 million. An average offshore oil and gas company experiences about 27 days of unplanned downtime a year, which can amount to $38 million in losses. In some cases, this number can go to as much as $88 million.

To eliminate the risk of unexpected equipment failures and maximize return on assets, oil and gas companies search for new, more efficient maintenance methods. In this article, we’ll break down why predictive maintenance driven by IIoT (industrial Internet of Things) is worth considering.

How Does It Work?

In a nutshell, IIoT-driven predictive maintenance leverages data fetched from equipment’s sensors (e.g. temperature, vibration, flow rate sensors etc.) to identify whether there are anomalies in equipment behavior and forecast whether a piece of equipment is likely to fail within a certain timeframe. The simplified process looks as follows:

Step 1. Collecting IoT data

Predictive maintenance starts with collecting the data from equipment’s potential failure points (e.g., shaft bearings of vacuum pumps) with the help of sensors. It’s good to have a data set that illustrates equipment’s health and performance throughout its lifetime and shows identifiable failures. Data scientists will use this data set as the base for creating predictive models.

Step 2. Adding context

For better reliability and accuracy of future predictive models, IoT data is combined with equipment metadata (model, configuration, operational settings, etc.), equipment usage history, and maintenance data. This data can be fetched from ERP (enterprise-resource planning), EAM (enterprise-asset management), EMS (enterprise-management system), and other enterprise systems.

Step 3. Searching for patterns

Data scientists examine the combined data set of IoT and context data to identify dependencies and make technical assumptions regarding the potential failure signals and usage patterns leading to failures.

Step 4. Creating predictive models

The essence of the stage boils down to running the combined data set through machine learning algorithms to identify equipment failure patterns and, based on them, build predictive models. The models are tested for accuracy and, once approved, used to predict the likelihood of equipment failure.

As more data becomes available, the models are updated, retrained, and tested again, so that they are accurate and representative of reality.

What to Maintain?

IIoT has the power to increase equipment productivity and reduce unplanned downtime across the three segments of the oil and gas industry: upstream (exploration and production), midstream (transportation and storage), and downstream (refining and processing).

Upstream

On average, 42% of development, exploration, and drilling equipment is more than 15 years old and works at only 77% of its maximum productivity. To mitigate this shortcoming, upstream oil and gas companies can leverage IIoT-driven predictive maintenance.

In upstream, IIoT-driven predictive maintenance is applied to monitor the health of equipment for exploration, development, and drilling, as well as its components: submersible pumps, separators, condensers, pressure valves, heat exchangers, flare stacks, compressors, turbines, etc.

For that, potential failure points are equipped with pressure, temperature, torque, vibration, flow rate, and other types of sensors. A predictive maintenance solution ingests sensor readings, combines them with context data, runs the data set through machine learning algorithms and creates predictive models, which are then used to identify equipment failures and provide early warning notifications of developing issues.

Midstream

Midstream sector leverages IIoT to ensure safety and reliability of the piping, crude oil treatment systems, and gas treating equipment. Fiber-optic distributed acoustic sensors, ultrasonic sensors, and temperature sensing systems detect sound variations signaling of liquid (e.g. crude oil) leakages, while hydrocarbon sensing cables are used to detect hydrocarbon leaks.

The data from sensors is combined with contextual data (e.g., the data from export facilities, geolocation, and weather data, etc.) and analyzed against predictive models. Once an abnormal deviation in sensor readings is detected, an IIoT solution triggers an alert, notifying maintenance specialists of a pipeline malfunction.

Downstream

In the U.S. alone, refineries lose $6.6 billion due to unplanned downtime. One of the major downtime causes is poor refinery equipment maintenance.

In downstream, some of the most critical and common components to maintain are pumps and compressors in oil distillation units, diesel hydrotreating units, fluid catalytic cracking units, and sulfur recovery units, as well as preheat trains in the crude units.

Combining the data from vibration, temperature, and flow rate sensors attached to the potential faulty points with production and environmental data, and correlating this data with predictive models, refineries get the ability to predict whether a component is likely to fail long before a problem arises.

Benefits

Applying IIoT-driven predictive maintenance solutions helps oil and gas companies reap substantial benefits, including:

  • Improving asset reliability and driving cost savings

IoT-driven predicative maintenance solutions help oil and gas companies forecast equipment breakdowns before they can have a significant impact on oil and gas companies’ safety levels and bottomlines. Schneider Electric reports that applying IoT-enabled predictive maintenance solutions can help save $4 million due to early identification of rotating machinery damage, $500,000 due to early identification of coupling failures, $370,000 due to early identification of heat exchanger valve problems, and more.

  • Enhancing operational efficiency

IoT-driven predictive maintenance solutions improve asset utilization and increase productivity by making operations more flexible and agile. By comparing the operational data across multiple pieces of equipment, IoT solutions help estimate machines’ utilization, identify the periods of best performance, and establish best practices to improve performance across the entire oil and gas supply chain: from exploration to refining.

  • Decreasing environmental footprint

While oil and gas sector produces 29% of methane emissions, the greenhouse effect of methane is 86 times higher than that of CO2. In the U.S. alone, the oil and gas industry causes 1 million tons of powerful pollutant methane into the environment every year due to leakages. IIoT helps oil and gas companies identify and reduce pipeline leaks, thus, decrease environmental damage.

Challenges and Limitations

Although O&G industry is the most promising and successful adopter of IoT-driven predictive maintenance solutions, there are certain limitations that can complicate the adoption:

  • Connecting legacy equipment to an IoT solution

O&G companies have been using management systems like SCADA (supervisory control and data acquisition) for years. However, 80% of the legacy equipment is connected to a local network and cannot function across TCP/IP networks. Although there are physical gateways that can translate between legacy systems and newer protocols, the integration challenge is still to be resolved.

  • The need to have sufficient amounts of asset data

For a reliable prediction, it’s desirable to have a sensor data set gathered throughout a machine’s lifecycle and indicating an identifiable failure. Gathering the required amount of data can take up to a year, which can delay the solution implementation.

  • Operating in the areas with poor communications coverage

Oil and gas operations require a diverse set of complex assets, which often operate in remote and hard-to-access locations with poor network signal, while Wi-Fi and Bluetooth have relatively short range and require many stations with short distances between them in order to get good coverage. A communications network disruption can lead to asset data not being available or available with delays, which can result in missed failure signals and, ultimately, equipment failure.

Outcomes

IoT-driven predictive maintenance can be applied to improve equipment reliability throughout the oil and gas industry segments, starting from exploration and development through storage and transportation all the way to refining and processing. The U.S. Dept. of Energy states that applying IoT-driven solutions for equipment maintenance helps oil and gas companies increase production output by 25%, achieve a 30% reduction in maintenance costs, and a 45% reduction in equipment downtime.

Boris Shiklo, CTO at ScienceSoft