Industrial Process Issue Detection Through Normalized Operating Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing industrial processes lack effective methods for identifying performance issues and improvements in continuous and batch production environments, leading to potential downtime and suboptimal operation.
Innovation Solution
A system and method for identifying issues in industrial processes by obtaining operating data, normalizing it, and using algorithms to detect anomalies, prioritize devices, and recommend actions for improvement, incorporating batch identification and statistical analysis to optimize performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional monitoring methods are used in continuous and batch production environments, then operational simplicity is maintained, but performance issue detection capability deteriorates
Solution Approach 1:
The system segments the complex task of performance monitoring into distinct functional modules: data collection module, data normalization module, anomaly detection module, and recommendation module. Each module handles a specific aspect of the monitoring process, making the overall system more manageable and effective while maintaining operational simplicity through modular design.
Solution Approach 2:
The patent introduces data normalization as an intermediary process between raw data collection and anomaly detection. This normalization layer standardizes diverse operational parameters from different equipment and processes, enabling effective comparison and analysis without requiring complex direct integration of all system components.
2Measurement precision
If comprehensive operating data is collected from all equipment, then detection accuracy improves, but data processing time increases
Solution Approach 1:
The system performs data normalization as a preliminary action before anomaly detection. By standardizing data formats, units, and scales in advance, the system prepares the data for rapid analysis without requiring complex processing during the detection phase, thus reducing overall processing time while maintaining comprehensive data collection.
Solution Approach 2:
The patent transforms raw operating parameters into normalized parameters through mathematical transformations and standardization processes. This parameter change converts diverse, complex data into a unified format that can be processed more efficiently by anomaly detection algorithms, maintaining detection accuracy while reducing processing complexity.
3Measurement precision
If statistical analysis and normalization are applied to all data, then issue identification accuracy improves, but computational complexity increases
Solution Approach 1:
The system applies statistical analysis and normalization to transform raw operating parameters into standardized metrics that are easier to analyze. By changing the parameters from raw, diverse formats to normalized, comparable formats, the system achieves higher issue identification accuracy while reducing the computational complexity of subsequent analysis through standardized data structures.
Data Source
AI summary
A process for identifying improvements in a plant may include obtaining operating data associated with multiple devices in the plant. The process may also include performing at least one calculation relative to the operating data using one or more algorithms. The process may further include normalizing the at least one calculation to obtain normalized values. The process may also include identifying a first device of the plurality of devices that has an issue using the normalized values. The process may further include presenting at least one action for a user to undertake to address the issue via a user interface.