Cyclic Plant Operation Setpoint Optimization Using Two-Stage Data Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cyclically executed processes in basic materials industries, such as steel and aluminum, often exhibit significant deviations from cycle to cycle, leading to inconsistent performance in achieving key performance indicators like productivity, product quality, and process costs, which are heavily influenced by various parameters and operating conditions, overwhelming experts and resulting in suboptimal operations.
Innovation Solution
A computer-executed optimization method that uses a plant model and predefined reference values to determine expected values for actual variables, selects relevant data sets based on distance criteria, and calculates setpoints to align target variables with reference values, outputting these to operators or control units for optimal plant operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If a computer-executed optimization method with two-stage data set selection is implemented, then manufacturing precision and consistency of target variables are improved, but device complexity increases
Solution Approach 1:
The data set selection process is divided into two distinct stages: preliminary selection based on first distance criterion and definitive selection based on second distance criterion. This segmentation allows the system to handle complex optimization tasks in manageable steps, improving manufacturing precision through systematic processing while making the overall complexity more tractable through structured decomposition
Solution Approach 2:
Expected values serve as an intermediary element between reference values and actual values. The computer determines expected values based on reference values and plant models, then uses these expected values as the basis for selecting data sets. This intermediary mechanism enables precise control of target variables by providing a reference point for comparison and selection, thereby improving manufacturing precision through indirect but systematic control
2Productivity
If extensive data analysis and two-stage selection processes are used, then productivity and operational efficiency are improved, but loss of time in processing increases
Solution Approach 1:
The first stage of data set selection performs preliminary filtering based on the first distance criterion before the second stage applies the second distance criterion. This preliminary action reduces the volume of data that requires intensive processing in the second stage, thereby improving operational efficiency by pre-organizing and pre-filtering data, while minimizing time loss through progressive refinement rather than exhaustive simultaneous processing
Solution Approach 2:
The time-consuming data analysis task is segmented into two sequential stages with different selection criteria. The first stage handles coarse filtering to reduce data volume, and the second stage performs fine-tuned selection. This segmentation allows the system to achieve high productivity through systematic processing while reducing total processing time by avoiding redundant computations across the entire data set at once
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
A primary industry plant (1) is used to cyclically execute a technical process again and again. The aim of the invention is to optimize the operation of the plant. In order to achieve this aim, a computer (9) calculates, on the basis of predefined reference values (R) for first target variables (Z1) of the technical process, first expected values (E1) for first actual variables (I1) of the technical process such that the first target variables (Z1) come as close as possible to the reference values (R). Subsequently, the computer provisionally selects, among many datasets (D) comprising the first and second target variables (Z1, Z2) and the first and second actual variables (I1, I2) for each individual cycle of the technical process, a number (n2) of datasets (D) in which the first actual variables (I1) are as close as possible to the first expected values (E1). The computer then calculates, on the basis of the predefined reference values (R) and the first expected values (E1), second expected values (E2) for the second actual variables (I2). From the provisionally selected datasets (D), the computer now definitively selects a predetermined second number (n2) of datasets (D) in which the first and the second actual variables (I1, I2) are as close as possible to the first and second expected values (E1, E2). On the basis of these datasets (D), the computer (9) calculates, for a cycle, which is still to be executed, of the technical process, target values (S) for the second target variables (Z2) such that the first target variables (Z1) come as close as possible to the reference values (R). The calculated target values (S) are output by the computer (9) to an operator (13) or a control device (2) of the plant (1).