Improving the longevity, resilience, and performance of power networks through AI + IoT solutions.
Distribution transformers are one of the main component of our power grids and as such, they need to be adequately maintained to prevent them from failing and to ensure that power is reliably and adequately transmitted at a rated voltage without interruption. Outside of causing blackouts, a poor quality power supply will result in increased power and production losses to the suppler, as well as cause other equipment to be damaged or fail, reducing it’s lifespan.
Detecting problems and fixing them rapidly before they become failures or can cause broader damage is, therefore, critically important for both utility companies and their end-customers – which is where AI + IoT solutions can help.
Our Power Distribution Transformer Monitoring & Fault Detection AI + IoT solution
We helped our client to collect real-time data from Power Distribution Transformers’ PLCs, weather reports and from 4G energy meters, combining data sets to identify new performance metrics, maintenance insights and improve fault detection. As Power Distribution Transformer types vary, one of the key features of our solution was that it be extremely flexible.
Defining what data to collect is critical
In order to create the solution, we started by identifying the data needed to deliver the desired business outcomes. In this solution these included:
- Energy consumption
- Transformer voltages
- Current and predicted temperature and humidity
- Oil level
- Operating status
- Weather data
Initial goals of the solution
The first goal of the IoT solution was to connect it to the transformers, PLCs and external weather service in order to collect data in a consistent and reliable manner, and ensure its quality and integrity. To do this, we included the following features in the solution:
- Monitoring of critical operational data received from the equipment via a web-based system
- Implementation of device management monitoring
- Creating business logic for the application to meet the business objectives
- Providing alarm and alert notifications via email or SMS messages to identify issues
- Collection of historical data to enable energy consumption forecasting and fault detection
- Multiple dashboards to provide the right users with the right insights
- Testing of the application, making sure all of the above goals are met based on the below solution architecture
Before go-live, we tested four critical aspects of the solution:
The Rayven AI + IoT platform is built with security as a top priority.
Rayven’s proprietary security architecture ensures data is secure at all points of the IoT environment. The solution includes data encryption in transit and is encrypted from device to cloud (device-dependent). Devices are authenticated using device keys (device-dependent) and 256-bit SSL encryption is used between end-user devices (PCs, tablets, mobile phones) and the cloud, which protects confidentiality, data integrity and availability. In transit from device to cloud, we have SHA-256 with RSA Encryption, automated at-rest encryption using 256-bit AES encryption (optional), and during use (from cloud to screen) SHA-256 with RSA Encryption. The solution additionally conducts device security checks via automated polling and/or pull request as well as having security (Bearer) tokens that authenticate devices and services, meaning that keys don’t need to be sent on the network.
Once securely online with the solution, the PLC’s were connected to the 4G energy meter, which acts also as a gateway. This configuration means that you only need a small, one-off investment with cabling and gateway connection to set up the solution, and then incur only minimal costs to maintain the connection in the form of a monthly 4G data sim fee. The combination of a secure and encrypted transmission path together with a dedicated, direct connection means that the solution has a fast and secure connection without needing to involve their internal IT team.
Your ability to make the right decisions is reliant on the integrity of the data that you collect. Ensuring that you have reliable connectivity means that your data is always up-to-date and that you can rely on it to make critical business decisions in real-time. It was, therefore, essential for us to test that the raw data matched the dashboards and to build-in capability to back-fill data in sequence in the event that communication ever goes down, so that there would never be gaps in data flows to the IoT platform.
Industrial Data Science
The objective of the exploratory data analysis was to identify trends in the data, which included:
- Energy usage patterns compared with temperature and humidity
- Maintenance and failure alerts
We are gathering data that will help us to build models of energy forecasting, fault detection and predictive maintenance, further improving the way that the company maintains their distribution assets.
The data sources used to deliver the Power Distribution Transformer Monitoring & Fault Detection AI + IoT solution
New and existing data was used to create the custom applications and business insights that come from the AI + IoT solution:
Key features of our Power Distribution Transformer Monitoring & Fault Detection AI + IoT solution
All of these features were customized to fit the customers specific business objectives.
Identify when filter pressures are rising, system checks fail, or when compressor motors start to misbehave and take proactive action.
Easily and securely onboard, configure, monitor, and remotely manage your IoT devices at scale. Make sure they are always performing as expected, and get alerts and notifications if not, to ensure your devices are always transmitting and that your data does not get lost on the way.
Alarms & alerts
Receive immediate SMS and email alerts for energy alarms, PAC warnings and alarms, or when any metric crosses your preset thresholds.
Continuous monitoring of energy consumption including power factor, current, voltage, and frequency
Ensure that there is a process in place to have the right people respond based on agreed protocols.
Create custom reporting dashboards and schedule them to be sent periodically to any specific user or user group.
Our Power Distribution Transformer Monitoring & Fault Detection AI + IoT solution delivers real business outcomes
Lower cost of maintenance
Sending maintenance crews to carry out visual inspections or responding to false alarms is time consuming and expensive. Using real-time data to send maintenance crews to areas which need maintenance reduces costs and increases the level of service performance.
Better resource utilization
Sending technicians to monitor equipment or to ‘fix-as-fail’ is not a good use of your technicians’ time or your money. Send technicians out when they are needed, with knowledge of what’s wrong, how to fix and with everything they need to complete the job and increase efficiency.
Reduce energy consumption
Compare PAC performance across a site or across an entire grid to discover what makes some units more efficient than others and to inform future purchasing decisions.
Centralized, continuous real-time monitoring allows you to proactively repair and maintain equipment, improving uptime and customer service.
A better understanding of downtime and rate losses will give you greater predictability and greater confidence that you can meet your future production targets.
Better customer service
Knowing when issues happen before assets fail means less downtime and a better customer service, providing real-time reporting and access to the performance provides confidence in the asset and your service capability.
Did you know?
Pricing & plans
Simple, fair pricing that scales with your business model.
Rayven integrates with any asset, device or system.
Create a custom solution in weeks, not months.
Discover opportunities for business improvement.