A recent study by Rodrigo R. de Oliveira et al. applied NIRONE sensors in two out of three PAT processes described in the paper for Fluidized bed drying of pharmaceutical granules as well as Polyester production process (paper submitted).
Process analytical technologies (PAT) applied to process monitoring and control typically provide multiple outputs from several sensors or a variety of model outputs from a single multivariate sensor. This study shows how Near Infrared (NIR) spectral sensor data can be manipulated and computed using data fusion strategies for the combination of sensor and/or model outputs in the developing multivariate statistical process control (MSPC) models.
This is explored in this study through three real process examples which combine outputs from multivariate models coming from the same sensor uniquely. According to the researchers: “These examples show clearly the flexibility in the choice of model outputs (e.g. key properties prediction by multivariate calibration, process profiles issued from a multivariate resolution method) and the benefit of using MSPC models based on fused information including model outputs towards those based on raw single sensor outputs for both process control and diagnostic and interpretation of abnormal process situations. The data fusion strategy proposed is of general applicability for any analytical or bioanalytical process that produces several sensors and/or model outputs.”
Near infrared spectroscopy (NIR) has been established as a key tool for process analysis technology (PAT). NIR is an effective technique for Physico-chemical data collection to process development as well as for monitoring and controlling the manufacturing processes.
The NIRONE Sensors are a robust alternative for process monitoring. These are robust to vibration and temperature changes and easy to install. Several studies have shown that the NIR spectra of the NIRONE sensors are of high quality to deliver spectral data with the same accuracy as commercial spectrometers in a system with an extremely low signal to noise ratio.
The MEMS chip spectrometer can be mass-produced and has a small enough form factor to be integrated into the next generation of plant sensors. NIRONE sensors are a cost-effective alternative to be applied in multi-point real-time process analytics and control even in high numbers compared to many traditional NIR solutions.
Read also a related study: Process Monitoring of Moisture Content and Mass Transfer Rate in a Fluidised Bed with a Low Cost Inline MEMS NIR Sensor
Read also our blog: Industry 4.0 and how smart sensors make the difference.
For further information on the Spectral Engines’ MEMS-based NIR spectral sensors please read more at:
