Industrial IoT Anomaly Detection With Adaptive Sampling and Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional device monitoring methods in industrial IoT suffer from incomplete data collection, inefficiency in failure diagnosis, and long response times, making it difficult to meet the needs of modern industrial production for efficient and reliable device operation.
Innovation Solution
A system and method for determining device anomalies using an industrial IoT, involving a device management platform that generates data collection instructions, determines data anomaly degrees, and adjusts sampling and storage rates based on data source identification to provide real-time monitoring and accurate diagnosis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional manual checking methods are used for device monitoring, then device operation simplicity is maintained, but monitoring completeness and diagnostic efficiency deteriorate
Solution Approach 1:
The system enables devices to automatically collect, transmit, and analyze their own operational data through embedded sensors and processors. The anomaly detection system performs self-diagnosis by comparing real-time data against historical patterns, eliminating the need for manual checking while maintaining operational simplicity for end users.
Solution Approach 2:
An intermediate data processing layer is introduced between sensors and users, which automatically aggregates, analyzes, and interprets raw device data. This intermediary system handles complex monitoring tasks behind the scenes while presenting simplified information to users, resolving the contradiction between comprehensive monitoring and system simplicity.
2Measurement precision
If fixed sampling rate data collection is used, then data collection simplicity is maintained, but diagnostic accuracy and response time deteriorate
Solution Approach 1:
The sampling rate is transformed from a fixed parameter to a dynamic one that automatically adjusts based on device operational state and anomaly detection needs. The system increases sampling frequency when anomalies are detected and reduces it during normal operation, achieving high diagnostic accuracy while maintaining manageable data collection complexity through automated adaptation.
Solution Approach 2:
The system dynamically changes the sampling rate parameter based on real-time conditions, device type, and anomaly severity. This parameter adaptation allows the system to optimize diagnostic accuracy for different scenarios without requiring manual configuration, resolving the contradiction between precision and operational simplicity.
3Productivity
If uniform storage allocation is used for all devices, then storage management simplicity is maintained, but data retrieval efficiency and anomaly detection speed deteriorate
Solution Approach 1:
Storage resources are segmented and allocated dynamically based on device characteristics, data importance, and anomaly detection requirements. Critical devices and anomaly-related data receive higher storage priority and faster access pathways, while normal operational data uses standard storage. This segmentation enables efficient data retrieval without requiring complex manual storage management.
Solution Approach 2:
Different storage quality levels are applied to different data types and devices based on their specific needs. High-priority devices receive optimized storage with faster retrieval, while standard devices use conventional storage. This localized quality differentiation improves overall system productivity without imposing uniform complexity across all storage operations.
4Reliability
If low sampling rate is used, then energy consumption and data processing load are reduced, but anomaly detection capability and response time deteriorate
Solution Approach 1:
The system employs periodic sampling with variable intervals rather than continuous high-rate sampling. During normal operation, data is collected at lower intervals to conserve energy, while the system periodically performs anomaly checks. When anomalies are detected, the sampling rate increases automatically, achieving reliable anomaly detection with reduced overall energy consumption through rhythmic, adaptive sampling patterns.
Data Source
AI summary
A method and a system for determining a device anomaly based on an industrial Internet of things (IoT). The method includes: generating a data collection instruction based on a preset sampling rate; obtaining, based on the data collection instruction, operation data of at least one target device; determining a data anomaly degree for the at least one target device based on the operation data; in response to determining that the data anomaly degree satisfies a preset condition, determining an abnormal device based on the data source identification of the operation data; generating an anomaly warning instruction based on the abnormal device and the data anomaly degree corresponding to the abnormal device; based on the data anomaly degree, generating and sending a sampling adjustment instruction; and based on the data anomaly degree, generating and sending a storage adjustment instruction.