Additive Manufacturing Fleet Provisioning for Distributed Edge Deployment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The proliferation of data from IoT sensors and wearables overwhelms the ability to transmit and process data efficiently in value chain networks, leading to complexity and missed opportunities for insight, particularly in centralized data collection due to bandwidth, storage, and processing limitations.
Innovation Solution
Implementing a distributed database system with edge devices that utilize a dynamic ledger, such as a blockchain, to store queries and generate approximate responses based on summary data, enabling efficient data processing and transmission without overwhelming networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If centralized data collection is implemented to process data from IoT sensors and wearables, then data processing capability is improved, but network bandwidth and storage capacity are overwhelmed
Solution Approach 1:
The patent divides the centralized data collection system into distributed edge devices that process data locally. Each edge device segments the overall data processing task, performing filtering, aggregation, and preliminary analysis at the network edge, thereby reducing the volume of data transmitted to central servers while maintaining processing capability.
Solution Approach 2:
The patent introduces a new dimension of data processing by implementing hierarchical architecture with multiple levels (edge devices, regional servers, central cloud). This dimensional change allows data to be processed at appropriate levels, reducing network bandwidth requirements while improving overall system productivity.
2Loss of information
If all raw data from IoT sensors is transmitted to central servers, then data completeness is improved, but network bandwidth consumption increases
Solution Approach 1:
The patent extracts only the essential and relevant data features at the edge devices before transmission. Edge devices perform data filtering, aggregation, and feature extraction, sending only processed insights and anomalies to central servers, thereby maintaining data completeness for decision-making while significantly reducing network bandwidth consumption.
Solution Approach 2:
The patent applies partial action by transmitting only the necessary portion of data (processed insights, aggregated statistics, anomaly detections) rather than all raw sensor data. This selective transmission maintains sufficient data completeness for analytical purposes while optimizing network bandwidth usage.
3Loss of time
If data is processed in real-time at edge devices, then response time is improved, but device complexity increases
Solution Approach 1:
The patent implements preliminary action by pre-configuring edge devices with data processing algorithms, models, and rules during deployment. This preliminary setup enables real-time processing at the edge without requiring complex runtime decision-making, reducing both processing time and operational complexity.
Solution Approach 2:
The patent introduces intermediary components such as standardized protocols, pre-trained machine learning models, and template-based processing pipelines that mediate between raw sensor data and final outputs. These intermediaries simplify edge device complexity while enabling real-time processing capabilities.
Data Source
AI summary
A robotic fleet platform includes a fleet resources data store with a fleet resource inventory indicating additive manufacturing systems that can be provisioned with a set of fleet resources. The fleet resource inventory indicates 3D printing requirements, printing instructions, and a status of each additive manufacturing system. Provisioning rules are accessible to an intelligence layer to ensure compliance. The platform receives a request for a robotic fleet to perform a job and determines a job definition data structure defining tasks. The platform determines a robotic fleet configuration data structure that assigns additive manufacturing systems to one or more of the tasks. The platform determines a respective provisioning configuration for each of the additive manufacturing systems. The platform provisions each additive manufacturing system based on the respective provisioning configuration and the provisioning rules. The platform deploys the robotic fleet based on the robotic fleet configuration data structure to perform the job.