Plant Process Workflow Modeling for Manual Procedure Compliance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for guiding operators through manual procedures in plant operations are insufficient, relying heavily on operator experience and diligence, and lack effective monitoring and compliance with specified rules.
Innovation Solution
A method to generate a process model by mining historical log data to translate operator actions into a workflow model that guides and monitors the execution of manual procedures, using statistical properties of process variables and set point changes, and integrating machine learning for set point recommendations and warning signals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If special operator displays or event batch recipe systems are provided to guide operators, then the reliability of manual procedure execution is improved, but the complexity of the system increases and the quality still depends on operator experience and diligence
Solution Approach 1:
The system automatically mines historical log data to generate process models without requiring manual configuration or complex setup. The process model generation is performed autonomously by analyzing past operator actions and translating them into structured workflows, eliminating the need for complex manual programming while improving reliability
Solution Approach 2:
The system creates process models by copying and analyzing historical operator actions from log data. Instead of requiring complex manual programming, the system replicates successful past procedures into structured process models that can be automatically executed and monitored, reducing system complexity while maintaining reliability
2Device complexity
If manual procedure execution relies on operator experience and diligence, then the system complexity is reduced, but the reliability and quality of execution deteriorate
Solution Approach 1:
The system continuously monitors operator actions against the generated process model and provides feedback on compliance. The process model serves as a reference framework that automatically evaluates whether operators are following correct procedures, improving execution quality without requiring complex real-time control systems
Solution Approach 2:
The system performs preliminary analysis of historical log data to generate process models before actual procedure execution. By pre-processing historical data and creating structured workflows in advance, the system establishes reliable execution frameworks without adding complexity to real-time operations
3Adaptability or versatility
If historical log data is mined to generate process models, then the adaptability to different plant conditions is improved, but the complexity of data processing increases
Solution Approach 1:
The system autonomously mines and processes historical log data without requiring complex manual data preparation or configuration. The automatic data mining process handles diverse plant conditions adaptively, generating appropriate process models from raw historical data while keeping the interface simple for operators
Solution Approach 2:
The process model generation system handles multiple types of plant processes and conditions through a single unified approach. By using general data mining techniques that work across different plant sections and procedure types, the system achieves broad adaptability without requiring separate complex processing systems for each scenario
Data Source
Figure 1
Figure 2a~2b
Figure 3a
AI summary
A method (100) for generating a process model modeling a manual mode procedure instance of a plant process is proposed, the procedure instances comprising a related sequence of operational actions, i.e. mining of historical plant logs to generate a workflow model, including the steps of: Providing a plurality of log events (S1) of a plurality of operational actions (110) of the plant process; Selecting a plurality of related sequences of manual mode operational actions (S2) from the plurality of log events; Filtering the plurality of related sequences of manual mode operational actions according to an individual plant section (S3); Identifying a sequential order (S4) from the plurality of filtered related sequences of the manual mode operational actions; Determining statistical properties of values of related process variables and/or statistical properties of values of related set point changes (S5) to each sequential ordered manual mode operational action from the plurality of filtered related sequences of the manual mode operational actions; Generating the process model (S6) of the manual mode procedure instance by arranging related manual mode operational actions with the sequential order of each operational action assigned with the statistical properties of the values of related process variables and/or assigned with the statistical properties of the values of the related set point changes.