ZEISS Microscopy Knowledge Base
Help
ZEISS Microscopy Knowledge Base
Search

Technical Cleanliness Analysis (TCA)

This module enables you to evaluate particulate contamination on prepared specimen. The following standards for component cleanliness, oil cleanliness and cleanliness of medical products are supported:

  • VDA 19.1
  • ISO 16232
  • ISO 4406
  • ISO 4407
  • GB/T 14039
  • GB/T 20082
  • NAS 1638
  • SAE AS 4059
  • VDI 2083 (Blatt 1)

Overview

Technical Cleanliness Analysis (TCA) is a software module to evaluate the technical cleanliness of engine components, medical devices, and of fresh and used oils and lubricants.

Dark gallery of particle thumbnails with LENGTH WIDTH AREA labels and category filters M, N, F, A
Example: Technical Cleanliness Analysis (TCA) results of component cleanliness analysis: The gallery shows the detected objects classified by type and ordered top down by length with the option to switch between the display of particle type metallic-shiny (M), non-shiny (N), fibers (F) and artifacts (A). The corresponding particle types for oil cleanliness analysis are fiber (F), particle (P) and artifacts (A).

You can perform rapid particle inspection and revision by using dedicated result views with various filter and sorting options.

Overview of Functionality

The following functional scope is covered.

Functional scope of software module ZEN core Technical Cleanliness Analysis (TCA)

  • Job templates for measurement of particulate contamination with image acquisition and as alternative from earlier acquired images. The result calculation is based on standard templates which can be adapted in the Standard Template Editor.
  • The workflow covers the following:
    • Image acquisition
    • Image analysis
    • Image processing
    • Standard-based result calculation
    • Result presentation in interactive views for fast inspection and revision of detected particles
    • Reports with results of characteristic values and standard specific methods per tested specimen
    • Automated storage of generated results in the data archive
    • Inspection and export of archived data

Functional scope for Correlative Technical Cleanliness Analysis (TCA)

In addition to the described functional scope for TCA, the following features are part of a correlative Technical Cleanliness Analysis workflow:

  • Holder calibration with L-markers.
  • Automated selection of particles from the standard template editor for SEM/EDS analysis.
  • Manual selection of particles from the gallery in the size distribution view for SEM/EDS analysis.
  • Joint particle selection table from 2. and 3. as input for S&F Find (List) tool.

TCA with GxP

The GxP module enables traceable workflows through integrated microscopy hardware and software, and meets the requirements of regulated industries. If GxP is installed, Technical Cleanliness Analysis (TCA) supports it.

Any time you change a setting of a configured workflow, this is logged in an audit trail.

GxP logs if you do the following:

  • If you change the standards to be applied.
  • If you change data in the Particle Segmentation workbench, e.g. the threshold.
  • If you change data in the Size Distribution workbench or in the Edit View. If you change particle types, edit, cut, merge or delete particles or parts of it.

The result of conducted particle revisions is stored to the archive and to the audit trail. The resulting Particle Revision Table is visible in the Browse Results mode and generated independently of an installed GxP module.

Example

  1. GxP module is licensed.
  2. Under Maintenance > Options > GxP > GxP Options, you have activated Require comment on workflow changes.
  3. You have loaded a job template to run it.
  1. In the Standard Selection workbench, change the default standard by deactivating one of the standards.
  2. The Comment parameter changes dialog is displayed.
    Dialog 'Comment parameter changes': VDA 19.1 Standard and Extended changed IsSelected True→False; comment field and OK
  3. Type in a comment and click OK.
  4. The parameter change is saved to the audit trail. If you do not add a comment, you cannot proceed or step back.
  1. Under Maintenance > Audit Trail, you can display the logged changes.
  2. The list of conducted particle revisions is stored additionally to the archive.
  3. You can export the data to your local PC in PDF format.

TCA with Intellesis Object Classification

You have the option to use TCA in combination with Intellesis Object Classification models. The following job templates are provided:

  • Component Cleanliness Testing with Object Classification
  • Component Cleanliness Testing with Object Classification (Loaded Image)
  • Component Cleanliness Testing with S&F and Object Classification
  • Component Cleanliness Testing with S&F and ML Object Classification and HM

As a Supervisor, you can adapt the provided job templates to your needs. To exchange the model in TCA job templates, select the desired model in the Intellesis Object Classification workbench in the Intellesis Object Classification tool.

In case the particle type differentiation using the conventional segmentation method is not sufficient and metallic particles are in brightfield contrast by default very dark or almost black, use the following Intellesis Object Classification models.

TCA with Intellesis Object Classification improves the automated detection of metallic particles, especially the darker ones.

  • Component Cleanliness Object Classification Model (Pol-90, Pol-0)
  • Component Cleanliness Object Classification Model (Pol-90, Pol-45)
  • Component Cleanliness Object Classification Model (Pol-90, Pol-135)
  • MICA.MnM Object Classification Model (Pol-90, Pol-0)

Mica particles are layered silicates which are used as fire protection element in e-mobility. Mica particles are very shiny and therefore often misclassified as metallic shiny particles. With ZEN core v3.13, the Mica Intellesis Object Classification model is available. The Mica model MICA.MnM Object Classification Model (Pol-90, Pol-0) is well suited to classify mica particles automatically as non-shiny.

NOTICE

Blue circular sign with white exclamation mark

Wrong polarization channel combination of model and image

The Pol channel combination of the selected model must be identical to the channel selection in the Tiles Region workbench, which is by default Pol-90 and Pol-135. To decide which channel selection is the best one for your microscope system, see POL Camera Technology.

To tailor the pre-trained TCA Component Cleanliness Object Classification Model model to your needs, see Retraining a Model for TCA.

Retraining a Model for TCA

To customize the pre-trained TCA Component Cleanliness Object Classification Model, you extend the provided ML (machine learning) ML based model by retraining with your own acquired images saved in a conventional TCA job run. To do so, export the archived image to your local file system.

NOTICE

Blue circular sign with white exclamation mark

Existing images in a pre-trained model

Do not remove existing images in a pre-trained ML (machine learning) based model, because the training information added with the corresponding image will be deleted from the model.

  1. The TCA Object Classification images are installed using the Microscopy Installer.
  2. The Manage Templates mode is selected.
  1. From the Show drop-down list, select Intellesis Object Classification Models.
  2. The models are displayed.
  3. Select the desired TCA Object Classification model, and click Copy and Edit Intellesis Object Classification interface for Cleanliness model showing classes Metallic-Shiny, Non-Shiny, Fiber.
  4. The Intellesis Object Classification workbench is displayed showing the mandatory particle type classes for TCA.
    Intellesis UI: model Component Cleanliness Object Classification; classes Metallic-Shiny, Non-Shiny, Fiber
  5. Click Import from Archive or Import Images if you want to import the image from your local disc.
  6. The browser opens.
  7. Select the exported image from the file system for training, and click Open. Be aware that the images you use for training were acquired with the same channel combination that is used in the selected model.
  8. The image and a table containing the IDs of the objects in the image are displayed in the Center Screen Area.
  9. In the classes list, select a class, and in the image, click on an object that belongs to this particle type class. Repeat this for a certain number of particles.
  10. You have labeled the object and assigned it to the selected class indicated by the same color of the corresponding particle type class.
    UI panel listing classes 'Metallic-Shiny, Non-Shiny, Fiber' beside microscopy image with orange and cyan particle outlines
  11. Click Train & Classify.
  12. The model is retrained based on the labeling. A prediction is displayed in the table.
  13. Review the predictions. To do so, in the table, sort the Prediction column table class and then click a predicted object in the table. Check that the algorithm has correctly labeled the object in the image. If you are not sure whether an object is metallic-shiny or not, on the Display tab, activate Single Channel, and activate Pol-135. The metallic-shiny particles will appear with white areas. By selection of the Pol-90 channel, metallic particles must appear black throughout.
    If the results are not precise enough, label additional objects. Click again Train & Classify.
  1. The model is retrained based on the labeling. The model is available at Manage Templates > Intellesis Object Classification Models, e.g. Model Name (1). To change the model name, in the Properties area, click Graphic box showing the word NOTICE, and change the name.

Note that you must select the retrained model again in the TCA job template > Intellesis Object Classification workbench > Intellesis Object Classification tool.

About Filters and Occupancy Rate

The following filter types are used for technical cleanliness analysis:

  • Foamed Membrane Filter
  • Pro: With a flat surface, these filters are suitable for light optical analysis.
  • Con: With their undefined sponge-like structure, this material filters particles which are a lot smaller than the nominal width of the filter pore. The particle load can darken the filter optically due to too many extremely fine particles. Therefore, the light optical evaluation is limited. Additionally, these filters absorb air humidity. If the filters are not dried carefully before starting the image acquisition at a microscope, this air humidity and might affect the result of optical analysis.
  • Mesh Filter
  • Pro: With defined geometrical pore width and a defined separation size, less particles are withheld. Therefore, this facilitates the light optical evaluation. Additionally, these filters absorb less air humidity.
  • Cons: With extreme enlargement or strongly oriented lighting, the structure of the fabric yarns can cause interferences or reflexes at light optical analysis.

Filter Pore Size

The function of the analysis filter is to retain the particles which are relevant to the analysis (ideally only these particles). The pore size of the analysis filter is selected according to the cleanliness specification, i.e. the filter shall be capable of reliably retaining the smallest particle size stipulated in the cleanliness specification. To ensure that elongated particles are also retained, the following rule of thumb applies (recommended by ISO 16232):

Filter pore size = 1/10 to 1/5 the size of the smallest particle size specified, with 1/10 being recommended for larger particles (>50 μm) and 1/5 for smaller particles (<50 μm). This is because smaller particles generally have a more compact shape than larger particles, which tend to have a highly diverse range of shapes (see also graph).

Line graph with gridlines showing rising curve labeled 1, X and Y axes with numeric ticks and arrows
The curve (1) shows the filter pore size: 1/5 to 1/10 of the smallest particle size in µm. On the x-axis the smallest particle size in µm is represented and on the y-axis the filter pore size in µm is represented. (Source: ISO 16232)

Occupancy Rate

The occupancy rate is a measure for the quality of specimen preparation with respect to a certain particle load and estimates the number of particles being still acceptable for an effective, automated image analysis. In general, the inspection time for one filter specimen is getting more and more time-consuming if the recommended occupancy rates per filter type are exceeded or close to the defined limits (mesh filter: ca. 3%; foamed membrane filter: ca. 1.5%). The result are measurement mistakes and the need for increased particle revision steps. As a consequence, the comparability of the analysis results between different systems goes down.

Objects not calculated

Closed, ring-like fibers and fiber agglomerates are considered with the fully enclosed area which might increase the occupancy rate value. If classified as artifacts these objects are not calculated into the occupancy rate.

The basis for standard based calculation is the effective filter area. For more information, see Common Characteristics.

Saving Job Results

When you have finished your analysis, you save your job results to the archive. In the Browse Results mode, you have an overview over your jobs and documents. Here, you can export documents you cannot open in ZEN core, e. g. MS Excel files.

  1. In the Report workbench, click Exit Loop.
  2. The next view is displayed.
  3. Click Save and Close.
  4. The job and the corresponding documents containing the results are saved to the archive.

Saving Tables

Note that the decimals in tables are saved with full accuracy. But they are displayed according to your settings under Maintenance >General Options > Data Tables > Data Table > Decimal Places. By default, the decimals are clipped and not rounded.

If you export a table as MS Excel file to your local PC, you can change the settings within MS Excel when formatting the cell. You can rise the decimals, for example in case you want to reproduce the classification of a particle in Technical Cleanliness Analysis.

ON THIS PAGE

PRODUCTS
ZENX Ray SoftwareEM SoftwareSolutions Lab
ABOUT ZEISS
AboutCareerNewsroomCompliance
Social Media
LinkedInFacebookYouTubeXInstagram
Impressum
Carl-Zeiss-Strasse 22
73447 Oberkochen
Germany
Legal