Internal Container Weather Estimation from External Meteorological Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing container management systems face challenges in estimating internal weather conditions without sensors, due to issues like unsynchronized data, high development costs for voyage-specific models, inadequate risk mitigation, unknown contents, and the need for sensor installation costs, which result in economic losses and inefficiencies.
Innovation Solution
A method that uses external weather data to estimate internal container conditions by synchronizing and preprocessing data for training models, allowing for sensor-less monitoring, regular data sampling, and risk mitigation suggestions, even for future shipments and unknown contents, using a system that periodically updates based on shipping information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensors are installed in containers to measure internal environment, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent uses external weather station data as an intermediary to infer internal container conditions. Instead of directly measuring internal environment with sensors, the system obtains external meteorological data (temperature, humidity, pressure) and uses a trained machine learning model to predict internal conditions, thereby avoiding direct sensor installation while achieving measurement goals
Solution Approach 2:
The system creates a virtual copy of the internal sensor environment by training a machine learning model on historical sensor data from containers equipped with sensors. This trained model then serves as a virtual sensor system that can estimate internal conditions for any container based on external weather data, eliminating the need for physical sensors in each container
2Measurement precision
If voyage-specific models are developed for each route, then estimation accuracy is improved, but manufacturing precision and development cost worsen
Solution Approach 1:
The patent develops a universal machine learning model that can estimate internal container conditions for multiple different voyages and routes. The model is trained on diverse historical data from various routes and container types, enabling it to generalize and provide accurate estimates across different scenarios without requiring separate models for each voyage
Solution Approach 2:
The system adapts to different voyages by inputting voyage-specific parameters (route, duration, container type, cargo type) into the trained model. The model adjusts its predictions based on these varying parameters while maintaining the same underlying structure, avoiding the need to redevelop models for each voyage
3Device complexity
If external weather data is used to estimate internal conditions, then device complexity is reduced, but measurement precision worsens due to data asynchronism
Solution Approach 1:
The system performs preliminary actions by collecting and storing external weather data at regular time intervals in advance. This pre-collected data is then synchronized with container event timestamps during the estimation process, ensuring that the most relevant weather conditions are used for each internal condition measurement without requiring simultaneous data collection
Solution Approach 2:
The patent replaces the mechanical synchronization approach (collecting data at exactly the same moment) with a computational approach using machine learning. The trained model learns the temporal relationships and correlations between external weather changes and internal condition changes from historical data, allowing it to accurately estimate internal conditions even when external data timestamps don't perfectly align
Data Source
AI summary
Systems and methods described herein are directed to estimating and managing status of a cargo, which can involve obtaining shipping information of the cargo; extracting a first set of weather information received from one or more databases from one or more locations corresponding to a location and time interval of the shipping information of the cargo; executing pre-processing on the first set of weather information for an input to an internal environmental model that is configured to output an estimate of an internal environment of the cargo; and obtaining the estimate of the internal environment of the cargo from internal environment model based on the input of the pre-processed first set of the weather information; wherein the first set of weather information is periodically resampled in response to updates to the shipping information of the cargo.