≪ View Page

Unterschiede

Hier werden die Unterschiede zwischen zwei Versionen angezeigt.

Link zu dieser Vergleichsansicht

Nächste Überarbeitung		Vorhergehende Überarbeitung
en:automatisierte_prozessoptimierung [2025/11/24 17:51] – angelegt deppe2en:automatisierte_prozessoptimierung [2026/03/06 11:34] (aktuell) – admin
Zeile 1: Zeile 1:
-====== Automated Process Optimisation ======+====== Automated Process Optimization ====== 
 +====== Automated Process Optimization ======
  
-  *[[en:Automatisierte Prozessoptimierung:Einleitung]] +With Automated Process Optimization, suitable process parameters (e.g. throughput, screw speed, barrel temperature profile) can be determined automaticallyand evaluated against defined target criteria. The optimization is performed using **Particle Swarm Optimization (PSO / swarm intelligence)**.
-  *[[en:Automatisierte Prozessoptimierung:Prozessoptimierung]]+
  
 +**Opening the optimization dialog**
 +
 +To open the optimization wizard, select from the main menu:
 +
 +**Command path:** ''Main menu > Simulation > Optimization…''
 +
 +An optimization wizard with multiple steps will start and guide you through the setup and execution of the optimization task.
 +
 +===== Choose meta machines =====
 +
 +In this step you define **which machine configurations** (meta machines) shall be considered for the optimization.
 +
 +{{ :en_sigma151_dlg_opt_001.png?direct&1000 |Process optimization – Choose meta machines (1/8)}}
 +
 +First, one or more **diameter-independent meta machines** can be selected. A meta machine defines the general screw and barrel layout including feeding positions (e.g. single-stage, two-stage, devolatilization, side feeding, etc.) and serves as a geometry-based framework for the subsequent optimization.
 +
 +=== Functions ===
 +
 +In the upper part of the dialog, the **Directory** field is used to select the folder from which meta machines are loaded.
 +
 +**Filters** are available to narrow down the list of meta machines:
 +
 +  * **Filter by usage**
 +  * **Filter by material**
 +
 +Info: Machines are shown when at least one filter in the category fits.
 +
 +=== Machine list (left) ===
 +
 +On the left, the **Machines** list shows all available meta machines. Entries can be selected for optimization.
 +
 +Buttons:
 +
 +  * **All** – selects all entries
 +  * **Clear** – clears the current selection
 +
 +=== Preview and meta machine information ===
 +
 +On the right, a graphical preview of the selected meta machine is displayed (screw configuration / barrel representation). Below the preview, key data is shown:
 +
 +  * **Number of feedings** (number of feeding locations)
 +  * **Length** (shown as L/D)
 +
 +In addition, a **Comment** field is displayed below the meta machine preview where further meta machine information can be read.
 +
 +===== Choose machine configuration and die =====
 +
 +In this step you define:
 +
 +  * which **machine configuration / modular system** (*.mbk) is used to generate and apply the diameter-independent meta machine (screw and barrel configuration)
 +  * which **die** (default definition or user-defined die at the screw tip) is applied
 +
 +{{ :en_sigma151_dlg_opt_002.png?direct&1000 |Process optimization – Choose configuration (2/8)}}
 +
 +=== Machine configuration ===
 +
 +In the upper area, the machine modular system for the screw and barrel configuration to be optimized must be specified. The selected file is displayed as a path to the *.mbk file.
 +
 +**Available functions:**
 +
 +  * Load machine configuration / modular system
 +  * Import configuration from another process
 +  * **Edit...** – opens the modular system for adjustment (available screw and barrel elements)
 +
 +A graphical preview of the resulting screw/machine configuration is shown below.
 +
 +=== Meta machine navigation ===
 +
 +If multiple meta machines were selected, you can switch between them using:
 +
 +  * **Previous**
 +  * **Next**
 +
 +This allows you to verify whether the selected modular system can represent the chosen meta machines.
 +
 +=== Die ===
 +
 +In the lower area, the die is defined.
 +
 +Options and functions:
 +
 +  * **Default** – uses the predefined default die
 +  * **Other** – allows definition / import of a custom die
 +      - import die from file or another process
 +      - create a new die
 +  * **Edit...** – open and edit die data
 +
 +===== Choose process parameters =====
 +
 +In this step, the **initial process parameters** for each selected meta machine are defined. These parameters form the baseline from which the optimization starts.
 +
 +{{ :en_sigma151_dlg_opt_003.png?direct&1000 |Process optimization – Choose process parameters (3/8)}}
 +
 +The dialog structure is aligned with the standard [[simulation:verfahrensparameter_-_allgemein|process parameter]] workflow.
 +
 +Key functions:
 +
 +  * Navigation between meta machines (**Previous / Next**)
 +  * Display of the active **Meta machine**
 +  * Button **apply to all** (transfers the current settings to all selected meta machines / parameter sets)
 +
 +This enables structured definition of the process parameters.
 +
 +===== Process calculation settings =====
 +
 +In this step you define **which model calculations** are executed within a single SIGMA simulation and under which terminating conditions iterative sub-calculations are stopped.
 +
 +{{ :en_sigma151_dlg_opt_004.png?direct&1000 |Process optimization – Calculation settings (4/8)}}
 +
 +Further information on calculation settings is available [[simulation:berechnung|here]].
 +
 +===== Define targets =====
 +
 +In this step, the **optimization targets** are defined. For the given task, process variables, limits, target values, evaluation methods, and weights are specified.
 +
 +{{ :en_sigma151_dlg_opt_005.png?direct&1000 |Process optimization – Define targets (5/8)}}
 +
 +The overview includes the following columns for all target parameters:
 +
 +  * **Parameters (target variables)**
 +  * **min**
 +  * **max**
 +  * **target**
 +  * **Evaluation method**
 +  * **Weight**
 +
 +=== Target variables ===
 +
 +  * **Throughput**
 +  * **Residence time**
 +  * **Temperature**
 +  * **Specific energy**
 +  * **Fiber end length**
 +  * **Pressure at screw tip**
 +
 +=== Evaluation methods ===
 +
 +In the **Evaluation method** column, different evaluation logics can be selected for each target variable:
 +
 +  * **maximizing** (increasing evaluation; the "max" value is the optimization target)
 +  * **minimizing** (decreasing evaluation; the "min" value is the optimization target)
 +  * **target** (the value defined under "target" is the optimization target)
 +
 +The first priority of the optimization is to find processes within the specified limits. Only afterwards does the algorithm attempt to reach the target values.
 +
 +=== Weighting ===
 +
 +The **Weight** defines how strongly a parameter contributes to the overall rating.
 +
 +  * high weight: strong influence on the overall optimization rating
 +  * low weight: minor influence
 +  * weight = 0: the parameter is not considered
 +
 +=== Additional evaluation options ===
 +
 +  * **Use warnings**
 +  * **Consider melting profile**
 +
 +These options allow warning conditions and melting behavior to be included in the evaluation of the results.
 +
 +===== Optimization settings – PSO strategy =====
 +
 +In this step, the parameters of **PSO (Particle Swarm Optimization / swarm intelligence)** are configured.
 +
 +{{ :en_sigma151_dlg_opt_006.png?direct&1000 |Process optimization – Optimization settings (6/8)}}
 +
 +=== PSO parameters ===
 +
 +  * **Swarm size:** Number of particles (solution candidates) evaluated per iteration (larger swarm size = broader search in parameter space, higher runtime per iteration)
 +  * **Acceleration coefficient C1:** Weighting of the particle movement toward its **local best** (best solution found by the particle itself).
 +  * **Acceleration coefficient C2:** Weighting of the particle movement toward the **global best** (best solution found by the entire swarm).
 +  * **Inertia weight:** Weighting of the velocity component from the **previous iteration**.
 +
 +**General swarm effects:**
 +  * higher inertia weight -> stronger preservation of direction (more exploration)
 +  * lower inertia weight -> stronger focusing / smoother convergence (more exploitation)
 +
 +=== Optimization terminating condition ===
 +
 +You can choose between:
 +
 +  * **Run under minimum deviation**
 +  * **Reached maximum number of iterations**
 +  * **Number of iterations**
 +
 +=== Recommendation ===
 +
 +The default parameter values are suitable for most use cases and are recommended. They can be adjusted if required, e.g. for:
 +
 +  * larger search spaces
 +  * faster coarse optimization runs
 +  * more robust convergence for complex target definitions
 +
 +===== Calculation / Swarm optimization =====
 +
 +In this step, the actual optimization is executed using the settings defined previously.
 +
 +{{ :en_sigma151_dlg_opt_007.png?direct&1000 |Process optimization – Calculation / Swarm optimization (7/8)}}
 +
 +=== Status and log ===
 +
 +**Status**
 +
 +The current calculation state is shown in the upper left area:
 +
 +  * **Calculation in progress**
 +  * remaining time / progress estimate
 +
 +**Buttons**
 +  * **Cancel** – stops the running optimization
 +  * **Perform a new calculation** – recalculates the swarm after optimization inputs have been modified (availability depends on status)
 +  * **Copy** – copies the log output to the clipboard
 +
 +**Log window**
 +
 +The log area lists the calculation steps, e.g.:
 +
 +  * Calculation started
 +  * Initializing swarm
 +  * Swarm initialized
 +  * Starting swarm iteration
 +
 +=== Particle visualization ===
 +
 +In the search-space diagram, particles (individual process candidates) are visualized.
 +
 +  * **x-axis:** Screw speed
 +  * **y-axis:** Throughput
 +
 +The particle color is interpreted using the color scale shown below the diagram.
 +
 +=== Color scale / barrel temperature profile ===
 +
 +Below the diagram, a color scale labeled **Barrel temperature profile** is displayed (e.g. -50 °C to +50 °C). It visualizes a temperature-related parameter or a profile deviation (barrel temperature profile delta).
 +
 +=== Iteration display ===
 +
 +Below the plot:
 +
 +  * **Iteration** (slider / value)
 +
 +This allows visualization of individual iteration states.
 +
 +===== Select results / Save process =====
 +
 +After the optimization is completed, the results (particles / candidate processes) are displayed in a results list.
 +
 +{{ :en_sigma151_dlg_opt_008.png?direct&1000 |Process optimization – Results / Configuration selection (8/8)}}
 +
 +=== Particle list ===
 +
 +Under **Particles**, all calculated candidate processes are listed, typically with their rating in brackets.
 +
 +Functions:
 +
 +  * selection of individual particles
 +  * multi-selection for comparison (checkboxes)
 +  * sorting is typically by rating (descending / best candidate on top)
 +
 +=== Processing parameters ===
 +
 +In the upper right area, the most important result quantities are shown in a table for the selected particles:
 +
 +  * **Throughput [kg/h]**
 +  * **Residence time [s]**
 +  * **Temperature [°C]**
 +  * **Specific energy [kWh/kg]**
 +  * **Fiber end length [µm]**
 +  * **Pressure at screw tip [bar]**
 +  * **Rating [%]**
 +
 +Additionally, a **Weight** row is displayed to document the active evaluation logic.
 +
 +=== Process indicators ===
 +
 +The middle area provides further configuration-related data per selected candidate:
 +
 +  * **Configuration**
 +  * **Meta machine**
 +  * **Screw speed [1/min]**
 +  * **Throughput [kg/h]**
 +  * **Barrel temperature profile (delta) [°C]**
 +
 +This allows direct comparison between candidates.
 +
 +**Particles (preview):** The lower area provides an additional visualization/comparison area for the selected particles.
 +
 +**Create process:** This function generates and saves a SIGMA process from the selected optimization candidate. The wizard can then be closed using **Finish**.
 +
 +===== Notes =====
 +
 +=== Choose target definitions carefully ===
 +
 +  * Do not set limits (min/max) too narrow so that the algorithm has sufficient search space.
 +  * Use target values only where a true setpoint exists (e.g. temperature, pressure).
 +  * Set weights intentionally (e.g. high throughput weight for production optimization; higher temperature/residence-time weight for material-sensitive processing).
 +
 +=== PSO parameters ===
 +
 +  * Start with the **default values**.
 +  * A larger **swarm size** increases the chance of finding good solutions but increases runtime.
 +  * More **iterations** often improve convergence, especially for complex objective functions.
 +
 +=== Result evaluation ===
 +
 +  * Do not focus only on the highest rating; also verify process robustness.
 +  * Compare several particles (e.g. similar rating but different screw speed / barrel temperature profiles).
 +  * Check plausibility of indicators and warnings before final process creation/saving.