Food production exceeds global demand by 20% and yet we can’t feed the world’s population with 1.3 billion tons of food wasted or lost every year in the supply chain. This equates to anywhere between 30-40% of perishable food lost after harvest on the farm. Ensuring consistent refrigeration to prevent food from spoiling throughout the supply chain from storage, to trucks, to warehouses, to grocery stores and restaurants via cold chain monitoring is essential. Predicting lapses in proper temperatures with AI is even better.
IoT + AI Blueprint:
Assemble the collection of components displayed below to address the use case of reducing food loss due to improper temperatures throughout the supply chain.
Sensor(s)
Temperature: Measure Refrigeration Temperature Levels to Prevent Spoilage
Humidity: Prevent Condensation from Too Much Humidity
Power: Monitor Refrigeration Voltage to Detect Power Interruptions or Performance Issues
Single Board Computer (SBC): Raspberry Pi, NVIDIA Jetson, Orange Pi (If AC Power Available)
Power Options
Lithium-Ion Polymer (LiPo) Batteries
Power Over Ethernet (PoE)
AC Power (Utility | Mains | Wall Outlet)
Network(s)
Ethernet: If Present Within a Given Space for High Bandwidth Scenarios
Wi-Fi: If Available for Indoor, High Bandwidth Scenarios
Bluetooth: For Short Range, Low Bandwidth Scenarios
LoRa: Create Low Bandwidth Coverage Needed to Reach Internet Access
Cellular: If Coverage Available and Cost-Effective for High Bandwidth Scenarios
Satellite: When No Terrestrial Coverage Options are Available for Medium Bandwidth Scenarios
Digital Twin Modeling
Cold Storage on Farms
Trucks
Warehouses
Grocery Store Coolers and Freezers
Restaurant Walk In Coolers and Freezers
Data Processing + Storage Location(s)
Edge: In Cold Storage, Trucks, Warehouses, Grocery Stores, and Restaurants
Cloud: Filtered Data Relayed from Edge to Monitor Entire Cold Chain
Streaming Analytics
Compare Sensor Data Values to Defined Setpoints, KPI Value Ranges and Thresholds
Filter out Duplicate Sensor Data Value Readings
Automation
Green KPI: No Action.
Yellow KPI: Warn Notification for Awareness When Sensor Values are Trending Towards Unsafe Temperatures or Potential Compressor Failure
Red KPI: Alert Notification for Facilities, Maintenance, or Refrigeration Technicians to take Action to Repair Compressor and Keep Food Cold
People
Deploy and Maintain Solution
SMEs Define KPIs and Actions
Facilities Management Personnel, Maintenance Team, and Refrigeration Technicians
Security
Uniquely Identify Each Device
TLS 1.3 Encryption for Data in Transit
Encrypt Data at Rest
Validate Device Messages to Ensure they use Expected Data Format
Rotate Security Tokens
Limit IP Address Ranges
AI Anomaly Detection
Zero Trust: Reauthenticate Device Messages Through Every Step of the System
Artificial Intelligence
Machine Learning Time Series Forecasting Model to Predict Likely Refrigeration Compressor Failures
Machine Learning Time Series Forecasting Model to Predict Improper Temperatures
IoT Platform
Device SDK Captures Sensor Data from Physical Twin and Securely Sends it as a JSON Payload to the IoT Platform Along with a Unique Identifier and Security Token
IoT Platform Captures, Authenticates, and Saves Incoming Device + Sensor Data to a Message Queue
Background Process Takes Queued Data and Hydrates the Digital Twin by Saving it to a Database Table that Mimics the Structure of the Physical Twin
AI Model is Trained and Retrained with Digital Twin Dataset of Current and Historical Data Where Properties of Twin are Mapped to ML Features
Hot Path Data is Sent to Streaming Analytics to Facilitate Real Time Alerting and Automation
Same Hot Path Data is Also Sent to AI Model for Inferencing to Predict Future Occurrences
Rob is a writer, teacher, speaker, world traveller and undersea explorer. He's also a thought leader in the areas of enterprise mobility and the Internet of Things.
