Asset Data Platform Identifying Environmental Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current asset monitoring systems lack the ability to accurately identify and simulate features in environments where assets operate, such as boundaries, navigation routes, and hazards, which hinders efficient asset deployment and operation.
Innovation Solution
An asset data platform that uses image data and asset attribute data to define models for identifying environmental features through a training phase, followed by a run-time phase where these models are applied to detect and simulate features in real-time, enabling improved asset management and operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If image data and asset attribute data are used to define models for identifying environmental features, then measurement precision of environmental features is improved, but device complexity increases
Solution Approach 1:
The system segments the environmental feature identification process into distinct phases: a training phase where models are defined using historical image data and asset attribute data, and a run-time phase where these models are applied to detect features in real-time. This segmentation allows complex identification tasks to be broken down into manageable stages, improving measurement precision while managing computational complexity through phased processing.
Solution Approach 2:
The system performs preliminary action by defining models during a training phase using historical data before actual feature detection is needed. During the run-time phase, these pre-defined models are applied to quickly identify environmental features without reprocessing historical data, thereby achieving high measurement precision while reducing real-time computational requirements.
2Productivity
If models are applied to detect environmental features in real-time, then productivity of asset operation is improved, but loss of time in training phase increases
Solution Approach 1:
The training phase is performed as a preliminary action before actual asset operation begins. During this phase, models are defined using historical image data and asset attribute data. Once trained, these models can be applied in real-time during asset operation to quickly identify environmental features, thereby achieving high productivity while confining the time loss to the training phase rather than ongoing operations.
Solution Approach 2:
The system creates a copy of environmental feature identification capabilities through trained models that can be applied repeatedly during asset operation. These models capture the essence of feature identification from training data, allowing rapid inference during real-time operation without reprocessing the entire training dataset, thus improving productivity while isolating training time to an initial phase.
Data Source
AI summary
Based on an analysis of asset attribute data associated with a plurality of assets, a platform may detect a locality that is a possible instance of a given type of environment, such as a mine or construction site. In response, the platform may obtain image data associated with the detected locality and input that image data into a model that outputs likelihood data indicating a likelihood that any portion of the detected locality comprises a given feature of the given type of environment (e.g., a boundary, navigation route, hazard, etc.), where this model is defined based on training data. Based on the likelihood data, the platform may then generate output data indicating a location of any portion of the detected locality that is likely to comprise the given feature. In turn, the platform may use the output data to simulate asset operation in the detected locality.