ParticleTensorAI® PTA2 is the two-channel configuration of the ParticleTensorAI® measurement platform. It combines the LSS2 optical probe with the IMEA control unit for AI-based analysis of synchronized time-resolved light-scattering signals.
PTA2 records two optical detector signals simultaneously. Instead of reducing these signals immediately to individual droplet or particle parameters, the measurement data are retained over a defined acquisition interval and transformed into a multidimensional representation for ParticleTensorAI® analysis.
The second detector channel provides additional information about the same spray or particle flow. The AI model can therefore analyze not only the structure of each signal sequence but also relationships between the two synchronized detector channels.
PTA2 System Configuration
PTA2 consists of the LSS2 optical measurement probe, the IMEA control and acquisition unit, and the ParticleTensorAI® analysis software.
| Component | PTA2 Configuration | Function |
|---|---|---|
| Optical probe | LSS2 | Generates the measurement region and detects time-resolved scattered light |
| Detector channels | 2 | Records two synchronized optical signal streams |
| Control unit | IMEA | Signal acquisition, buffering, processing and communication |
| Evaluation | ParticleTensorAI® | AI-based analysis of buffered multi-channel signal sequences |
Measurement Principle
The LSS2 optical probe generates a specifically shaped illumination field. Droplets or particles passing through the measurement region scatter light toward two optical detector channels.
The motion of particles through the spatial illumination field produces characteristic time-dependent light-scattering signals. Both detector channels record synchronized information from the same measurement process.
In PTA2 operation, IMEA retains these signals over a defined acquisition interval. The synchronized signal streams are then transformed into the data representation used by the ParticleTensorAI® model.
Particles → LSS2 → Two synchronized signal streams → IMEA buffer → ParticleTensorAI® → AI result
Two-Channel ParticleTensorAI®
The defining feature of PTA2 is the simultaneous acquisition of two time-resolved detector channels.
The second detector channel provides more than simply an additional copy of the measurement. Depending on the optical arrangement, the two signals can contain complementary information about particle passage, signal shape, intensity, timing, and the optical response of the measured particle population.
The ParticleTensorAI® model can therefore analyze:
- signal structures within each detector channel
- signal amplitudes and waveform shapes
- temporal signal sequences
- time relationships between detector channels
- particle or droplet event density
- overlapping signal structures
- statistical patterns within each acquisition interval
- relationships between both synchronized detector channels
From Two Signal Streams to a Multidimensional Tensor
ParticleTensorAI® does not need to reduce the two detector signals immediately to a small set of predefined numerical parameters. Instead, larger portions of the measured signal information can be preserved.
The synchronized detector data are collected over a defined measurement interval and organized into a multidimensional representation. This representation allows the AI model to process temporal information and detector-to-detector relationships together.
Detector 1 + Detector 2 → Buffered measurement interval → Multidimensional representation → AI model → Classification or process parameter
The exact tensor structure can be adapted to the measurement task, acquisition configuration, and AI model.
Trigger-Free Signal Analysis
PTA2 can analyze buffered signal sequences without requiring every droplet or particle event to be identified individually before the AI evaluation.
This can be advantageous when particle events occur in rapid succession, signal amplitudes vary, or several light-scattering signals overlap.
Instead of discarding complex measurement intervals because individual signals cannot always be separated reliably, ParticleTensorAI® can retain these structures and make them available to the AI model.
AI-Based Evaluation
PTA2 is designed for AI-based evaluation. The relationship between the two-channel optical signal structure and the required measurement result is learned from suitable reference data.
Depending on the application, an AI model can be developed to distinguish different spray conditions, particle populations, materials, or process states.
The second detector channel increases the amount of measurement information available to the model and can provide additional features that are not present in a single-channel configuration.
Possible Measurement and Analysis Results
The available output depends on the optical configuration, training data, reference information, and AI model developed for the application.
Possible PTA2 applications include:
- spray condition classification
- particle or droplet classification
- detection of process changes
- comparison of atomizer operating conditions
- material-related spray characterization
- analysis of changes in optical particle properties
- monitoring of stable and unstable spray conditions
- AI-based quality monitoring
- trend and process-state analysis
Material-Related Characterization
Light-scattering signals depend not only on the size and velocity of droplets or particles. Optical and material-related properties can also influence the measured signal structure.
With two synchronized detector channels, PTA2 provides additional information about these optical interactions. An AI model can investigate whether changes in material composition or particle properties produce characteristic changes in one or both signal channels.
This makes PTA2 suitable as a development platform for measurement tasks that go beyond conventional particle size and velocity analysis.
AI Model Development
PTA2 requires training and validation data representative of the intended measurement task. During development, synchronized optical signals are recorded under defined reference conditions and assigned to known classes or reference quantities.
The model is trained using part of the measurement dataset and subsequently validated using independent data that were not used for training.
Important factors include:
- quality of the reference measurements
- range of operating conditions
- material and optical properties
- stability of the optical configuration
- relationship between the two detector channels
- number and diversity of measurement cases
- selected AI model architecture
- similarity between training and application conditions
Customer-specific applications may therefore require an individual measurement, training, and validation campaign.
LSS2 Optical Probe
The LSS2 is the two-channel optical measurement probe used by PTA2. It creates the measurement region and provides two synchronized time-resolved light-scattering signals.
The optical probe is connected to IMEA by optical fibers, allowing the measurement location to be separated from the acquisition and processing electronics.
| Parameter | LSS2 |
|---|---|
| Measurement principle | Time-resolved light scattering |
| Active detector channels | 2 |
| Wavelength | 405 nm |
| Dimensions | 182 × 74.9 × 32 mm |
| Compatible control unit | IMEA |
IMEA Control Unit
The IMEA control unit provides synchronized two-channel acquisition, buffering, processing, host communication, and interfaces for laboratory or industrial integration.
In PTA2 operation, IMEA is configured to preserve synchronized light-scattering signal sequences for ParticleTensorAI® analysis rather than reducing the measurement immediately to individual particle parameters.
| Parameter | IMEA |
|---|---|
| Optical signal inputs | 2 |
| Host communication | Ethernet |
| Digital inputs | 4 × 24 V |
| Digital outputs | 4 × 24 V |
| Analog inputs | 4 × 4–20 mA |
| Analog outputs | 4 × 4–20 mA |
| Trigger | Trigger input and output |
| Dimensions | 251 × 211 × 109 mm |
Process Monitoring
PTA2 can analyze consecutive measurement intervals during an operating spray or particle process. Each interval can be evaluated by the trained AI model and converted into an application-specific process result.
Possible outputs include classifications, predicted parameters, probability values, trend information, or indicators describing changes relative to a reference state.
The use of two detector channels provides additional information that can improve the distinction between different process or material states when these differences are represented in the measured optical signals.
Industrial Integration
PTA2 can be integrated into laboratory test rigs, development installations, spray equipment, atomizers, and industrial production systems.
IMEA provides interfaces for exchanging measurement results, status information, and control signals with external equipment.
- Ethernet communication
- digital inputs and outputs
- 4–20 mA analog inputs and outputs
- external trigger input and output
- transfer of AI-generated process values
- integration into monitoring and automation systems
Typical PTA2 Applications
- AI-based spray classification
- paint and coating process monitoring
- material-related spray characterization
- detection of process changes
- comparison of atomizer operating conditions
- quality monitoring
- analysis of complex spray states
- research on multi-channel optical particle signatures
- development of application-specific AI models
- industrial process monitoring
Application-Specific Configuration
PTA2 can be adapted to the measurement task. The final configuration depends on the spray or particle system, material, optical properties, expected concentration, operating conditions, installation environment, available reference data, and required analysis result.
Possible adaptations include:
- optical probe geometry
- working distance
- measurement region
- detector arrangement
- mechanical integration
- optical configuration
- acquisition interval
- buffer configuration
- tensor representation
- AI model
- output parameters
- industrial interfaces
PTA2 and SQA2 Use the Same Hardware Platform
PTA2 and SprayQuantAI® SQA2 use the same LSS2 optical probe and IMEA control-unit hardware. The difference lies in how the two synchronized signals are acquired and evaluated.
| Parameter | SQA2 | PTA2 |
|---|---|---|
| Optical probe | LSS2 | LSS2 |
| Control unit | IMEA | IMEA |
| Detector channels | 2 | 2 |
| Primary data unit | Individual particle event | Buffered synchronized signal sequence |
| Evaluation concept | Individual-event evaluation | Tensor-based AI analysis |
| Evaluation | Classical or AI-based | AI-based |
| Typical focus | Quantitative droplet measurement and spray monitoring | Complex signal, material and process characterization |
The hardware therefore remains the same, while firmware, acquisition workflow, data representation, and evaluation software determine whether the platform operates as SQA2 or PTA2.
PTA1, PTA2 or PTA4?
The standard ParticleTensorAI® configurations differ mainly in the number of synchronized optical detector channels and therefore in the amount of optical information available to the AI model.
| System | Optical Probe | Control Unit | Detector Channels | Characteristic |
|---|---|---|---|---|
| PTA1 | LSS1 | ZEON | 1 | Compact single-channel configuration |
| PTA2 | LSS2 | IMEA | 2 | Two synchronized optical channels |
| PTA4 | LSS4 | CLEON | 4 | Most extensive standard multi-channel configuration |
PTA1 provides the most compact configuration. PTA2 adds a second synchronized optical channel and therefore enables the AI model to analyze detector-to-detector relationships. PTA4 provides four synchronized channels for applications requiring the most extensive standard optical signal representation.
Scientific Background
ParticleTensorAI® builds on research in time-resolved light-scattering measurements, machine-learning-based particle characterization, and AI-assisted analysis of complex optical signal data.
The underlying research investigates how optical signals from droplets and particles can be used not only for conventional particle measurements but also for detecting material-related and process-related information.
Selected References
[1] Schaefer, W.; Li, L. Particle characterization by analyzing light scattering signals with a machine learning approach. Applied Optics 2024, 63(29), 7701–7707. https://doi.org/10.1364/AO.531346
[2] Schaefer, W.; Fleck, S.; Haas, M.; Jakobs, T. Optical measurement method for monitoring high-mass-concentration slurry sprays: An experimental study. Photonics 2025, 12(7), 673. https://doi.org/10.3390/photonics12070673
[3] Schäfer, W.; Jakobs, T.; Stegmann, P. AI-assisted monitoring of coal particles within droplets in a coal monoethylene glycol slurry spray. 41st International Symposium on Combustion, Kyoto, Japan, 2026. KITopen ID 1000196272. https://doi.org/10.5445/IR/1000196272
Related Pages
- ParticleTensorAI® Overview
- ParticleTensorAI® PTA1
- ParticleTensorAI® PTA4
- LSS2 Optical Probe
- IMEA Control Unit
- SprayQuantAI® SQA2
For an application-specific PTA2 configuration, contact ai-quanton with information about the spray or particle system, material, operating conditions, available reference data, and required analysis result.
