Industrial Analytics Platform for Multi-Source Predictive Maintenance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial automation systems face challenges in collectively analyzing diverse data sets from various sources due to different file formats and formats, leading to missed opportunities for insights into plant operations.
Innovation Solution
A cloud-based data ingestion and analysis architecture that integrates and collects data from multiple sources, normalizes it, identifies relationships, and generates metadata to facilitate analytics, enabling predictive maintenance and process supervision through a scalable industrial analytics platform.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data from multiple industrial sources with different file formats are collected and analyzed collectively, then operational insights and predictive maintenance capabilities are improved, but system complexity and data integration challenges increase
Solution Approach 1:
The patent introduces a cloud-based data ingestion platform as an intermediary layer between diverse industrial data sources and analysis tools. This platform receives data in multiple formats (JSON, CSV, XML, etc.), normalizes it to a common structure, and stores it in a unified repository, thereby mediating the complexity of data integration while enabling comprehensive predictive maintenance analytics
Solution Approach 2:
The system transforms data from various file formats into a standardized parameter structure with consistent schemas, data types, and relationships. By changing the parameter representation of incoming data to a common format, the system enables collective analysis without requiring complex format-specific processing for each data source
2Loss of information
If diverse data sets from various industrial sources are integrated and normalized, then comprehensive analytics and performance insights are improved, but data processing time and computational resources increase
Solution Approach 1:
The patent implements preliminary data normalization and validation during the data ingestion phase, before analysis occurs. The system pre-processes incoming data by validating schemas, normalizing formats, and establishing relationships between data items upfront, which eliminates the need for time-consuming processing during actual analytics operations
Solution Approach 2:
The data processing architecture is segmented into distinct modular components: data ingestion module, normalization module, validation module, and analysis module. This segmentation allows each component to specialize in specific tasks, improving overall processing efficiency and enabling parallel operation of independent processing stages
3Adaptability or versatility
If a scalable cloud-based architecture is implemented for industrial analytics, then system adaptability and deployment flexibility are improved, but infrastructure complexity and implementation difficulty increase
Solution Approach 1:
The patent describes a universal cloud-based platform that serves multiple industrial analytics functions through a single system. The platform can ingest data from various sources, perform different types of analysis (predictive maintenance, performance optimization, quality control), and deploy to different environments (cloud, edge, hybrid), thereby achieving multi-functionality that simplifies implementation compared to multiple specialized systems
Solution Approach 2:
The system uses template-based data models and configurable analysis pipelines that can be copied and reused across different industrial applications. Pre-defined schemas, validation rules, and analysis configurations can be replicated and adapted to new data sources and use cases, reducing implementation complexity while maintaining scalability
Data Source
AI summary
A scalable industrial data ingestion and analysis architecture integrates and collects data from multiple diverse sources at one or more industrial facilities. Data sources can include plant-level industrial devices and higher-level business systems. The data can be integrated and collected from multiple sources at an on-premise edge or gateway device, which sends the data to event queues on the cloud platform. The data queues orchestrate and store the data on cloud storage, and an analytics layer performs business analytics or other types of analysis on the stored data to produce various outcomes. Similar analytic platforms can also be implemented at the device level, and analytic functions can be scaled between the device level and higher levels in accordance with the scope of a given analytic function.