Cold Storage Monitoring solution: Saving money and reducing spoilage in cold storage environments.

Our Real-Time Cold Storage Monitoring solution.

The solution.

Our customer wanted to improve the way that they monitor their cold chain, end-to-end. To do this, we created a real-time Cold Storage Monitoring solution on our Rayven Platform that integrates all relevant data sources and monitors asset performance and storage refrigeration temperature set-point values, and which alerts and sends notifications when forecasting that temperatures are going to move beyond the optimum set point parameters.

Defining what data to collect is critical.
We started by identifying the key metrics necessary to achieve the desired business outcomes. In this solution these included:

1. Storage refrigeration temperature and humidity readings
2. Storage refrigeration motor performance
3. Storage refrigeration energy performance
4. Light status
5. Door status
6. People counting

Initial goals of the solution.
The first goal of this solution was to connect the different data sources to the Rayven Platform and to:

1. Collect critical refrigeration, temperature and energy data received via a web-based system
2. Define business logic to the application so as to meet the business objectives
3. Provide alarm and alert notifications via email or SMS messages
4. Collect enough historical data to enable the ability to test different logic to diagnose faults
5. Provide the right dashboard to the right user with the right insight across multiple fleets and truck models
6. Test 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 AI + IoT solution:

Security.
The Rayven Platform is built with security as a top priority and our proprietary security architecture ensures that data is secure at all points of the environment.

The solution includes data encryption in transit from device-to-cloud, as well as device authentication; security (Bearer) tokens; SSL, AES and RSA encryption; as well as additional device security checks done via automated polling.

Connectivity.
Once securely connected, an Ethernet cable connection from the cold room to a 4G Gateway was determined to be the best solution. In addition, we used a three phase wireless energy meter to collect energy consumption data, which has its own 4G connectivity and Modbus connectivity.

Data integrity.
To ensure that the data being received by the Cold Storage Monitoring IoT solution was current, it was necessary for us to compare the data in the refrigeration rooms with the dashboards and to construct functionality to back-fill data in the event that communication was ever lost. This process is important to ensure data integrity and give our customer confidence that they can make decisions based on the data.

Industrial Data Science.
The objective of exploratory data analysis was to create a predictive maintenance Machine Learning data model, which included:

1. Refrigeration fault detection and predictive maintenance
2. Forecast time in set point
3. Anomaly detection in temperature drifting
4. Energy forecasting

What’s next?

We are continuing to improve the maintenance forecasting capabilities, using ever-growing data sets. In addition, we plan to add maintenance history records to improve the predictive maintenance modelling for all the assets in the operation.