Power & Water

Analyze Data, Optimize Performance, Maximize Profits

The unexpected failure of an electrical power plant can create substantial disruption to the downstream power grid. The same holds true when water distribution equipment and pumps fail without warning. To avoid this, FogHorn’s Edge AI platform enables the proactive benefits of predictive maintenance and real-time responsiveness. It also enables ingestion and analysis of sensor data closer to the source rather than the cloud to reduce latency and bandwidth costs.

Use Cases


Lower maintenance costs, improve asset performance and longevity, and maximize yield.


Optimize systems for maximum KPI performance, quickly adjust to changing conditions.


Reduce repair costs, minimize downtime, maximize output, and improve remediation efficiency.


Improve automation, enhance practitioner collaboration, reduce manual data entry and errors.

Asset Performance

Maximize high-value asset output, balance reliability, performance, and cost.

Yield Forecasting

Maximize asset output, predict maintenance needs, improve forecast accuracy.


Monitoring pressure and other conditions related to a machine’s health to prevent pump damage and costly downtime

Centrifugal pumps are widely used across all industrial and commercial sectors such as Power, Water, Oil and Gas, Healthcare, Manufacturing, Utilities, and Transportation.

Cavitation is a condition that can occur in centrifugal pumps when there is a sudden reduction in fluid pressure. Pressure reduction lowers the boiling point of liquids, resulting in the production of vapor bubbles if boiling occurs. This is more likely to happen at the inlet of the pump where pressure is typically lowest. As the vapor bubbles move towards the outlet of the pump where pressure is higher, they rapidly collapse (return to a liquid state) resulting in shock waves that can damage pump components.

FogHorn’s edge intelligence can ingest streaming data from pump sensors and apply real-time analytics to identify any significant changes in pressure and alert operations personnel before damage occurs. It can also send a signal to the main system to automatically move the flow of the fluid to a different pump to prevent damage and reduce maintenance and downtime costs associated with pump cavitation.

Maximize wind power generation with optimized turbine settings

Although wind turbines operate on a centuries old method of using available winds to spin blades mounted to a rotating hub, the scale and sophistication of modern wind turbines requires highly advanced monitoring and operations technology to achieve maximum efficiency and equipment lifespan. It also continuous adjustments to account for never ending fluctuations in wind and weather conditions.

Currently turbine settings are typically driven by limited, physics-based rules. However, to achieve maximum wind power, a solution needs to account for complex turbine design parameters as well as external data sources and this is an area that is challenging for current systems. To optimize the wind output generated by a wind turbine, historical data, analytics and machine learning techniques need to be integrated in a real-time manner and applied to an entire wind farm to optimize total output. By analyzing data from a variety of onboard sensors and SCADA devices, FogHorn’s edge intelligence can be used to enable real-time adjustments to the blade pitch, turbine orientation or yaw, rotor speed, blade tip speed, and electrical power regulation to optimize turbine settings for maximum power output.

FogHorn’s Lightning edge intelligence platform combine data gathered from turbines with wind speed and direction to continuously maximize the wind generated output. Most wind farms are located in remote areas and an edge intelligence solution can provide the advantage of being able to analyze data locally in real-time without relying on continuous wide area network availability. It can manage all machine operation and adjustments autonomously at the edge of the network while delivering selected information that is not time-sensitive to a centralized cloud-based management center where analysis of individual turbine data, as well as entire wind farms, can be processed. The addition of FogHorn’s edge intelligence platform increases energy output, decreases operational costs, and increases turbine uptime.

Anticipating machines failures before they actually happen through predictive analytics

Predictive maintenance prevents unnecessary repairs, maximizes effective asset lifetime, and significantly reduces major failures and downtime. This results in cost savings with an increased return on investment and customer satisfaction. Providing predictive maintenance at the edge and sending only relevant data to the cloud is a lower cost alternative to cloud-only based solutions. It provides real-time actionable insight with extremely low latency and substantially lowers data transfer and storage costs.

The Electric Submersible Pump (ESP) is a long in-ground piece of equipment at the center of an oil well extracting oil from the bottom of the well and pumping it to the surface. Failure of an ESP will stop the entire operation which can take time and result in costly repairs and loss of revenue. FogHorn’s edge predictive maintenance solution can monitor the operational data gathered from the ESP and apply advanced analytics in real-time to predict failures. If a potential failure is detected, the system can automatically stop the pump to prevent damage as well as alert operations to repair or replace the ESP based on current machine health and maintenance models developed by the operators of the ESP. FogHorn’s edge solution can reduce the cost of data transfer to the cloud by preprocessing real-time data at the edge and sending only relevant data to the cloud. It also provides real-time availability without requiring an uninterrupted network connection that cloud-based solutions depend on.

Shifting the focus of data collection and analytics to the edge of the network improves equipment reliability while preventing costly, and potentially disastrous, downtime

The unexpected failure of a steam turbine can create substantial disruption, damage, and economic loss, not only to its power plant but also the downstream power grid and the business and customers who depend on a reliable and continuous source of electricity. To prevent this, predictive maintenance has become a key part of the modern maintenance department. More power utilities are deploying such processes to maximize the reliability of their equipment by detecting potential failures before significant problems arise.

With predictive maintenance, any variance from the “expected behavior” can trigger an alert. These triggers could be based on predetermined performance rules, such as temperature or vibration outside of an acceptable range or be based on deployment of predictive models at the edge that account for historical data. The use of predictive analytics enables users to explore potential root causes and appropriate remedies.

Power plant maintenance is a major undertaking. Deployment of FogHorn’s predictive analytics at the edge allows power plant operators to proactively schedule maintenance in a non-disruptive fashion to avoid outages altogether and to do so in the most cost effective manner. One of the advantages of FogHorn’s intelligent edge solution is that it can respond immediately to any anomaly or malfunction before it becomes a much more serious and costly issue. It also eliminates the need to upload massive amounts of data to remote data centers because many maintenance issues can now be resolved on site using analytics and processing applications deployed at the edge.

The data center or cloud will continue to play a key role by providing overall system management as well as analytics and machine learning functions that require the computing power of a cloud/datacenter. However, by relying on FogHorn’s edge intelligence for critical latency-sensitive functions, utility companies can reduce overall bandwidth and data processing costs and operational delays by sending only non-critical information to the data center or cloud for analysis.