Analytische Chemie
Filtern
Dokumenttyp
- Vortrag (34)
- Zeitschriftenartikel (21)
- Beitrag zu einem Tagungsband (13)
- Posterpräsentation (5)
- Forschungsdatensatz (3)
- Buchkapitel (1)
- Forschungsbericht (1)
Sprache
- Englisch (64)
- Deutsch (13)
- Mehrsprachig (1)
Schlagworte
- Machine learning (14)
- Artificial neural networks (10)
- Geometric Phase (10)
- Coherent Heterodyne (9)
- Distributed Fiber Optic Sensor (9)
- Distributed acoustic sensing (8)
- DAS (7)
- BOFDA (6)
- Industry 4.0 (6)
- Distributed fiber optic sensing (5)
Organisationseinheit der BAM
- 8.6 Faseroptische Sensorik (78) (entfernen)
Eingeladener Vortrag
- nein (34)
A novel distributed acoustic sensing technique is proposed that exploits both phase and amplitude of the Rayleigh backscattered light to quantify the environmental variation. The system employs a wavelength-scanning laser and an imbalanced Mach-Zehnder interferometer to acquire the reflection spectra and the phase of the detected light, respectively. Fading-free and low-frequency measurements are realized via the crosscorrelation of the reflection spectra. The discrete crosscorrelation is used to circumvent the nonlinear frequency sweeping of the laser. Based on the phase of the backscattered light, it is possible to quantify fast environmental variations. The whole system requires no hardware modification of the existing system and its functionality is experimentally validated. The proposed system has the potential to monitor ground motion/movement at very low frequency band like subsidence around mining areas and at high frequency band like earthquakes and vibrations induced by avalanches.
A novel DAS setup based on geometric phases in coherent heterodyne detection is applied for the first time to the characterisation of the Earth’s subsurface. In addition, an optimisation of the proposed setup in terms of its spatial resolution is also presented for the first time. The surface waves are generated by strong blasts of 25 kg of explosives at a dedicated test site. A 10 km dark fiber link in the vicinity of the test site connected to the test setup records the resulting strain signals. The spike-free and low-noise strain data thus obtained minimize post-processing requirements, making the setup a candidate for real-time seismic monitoring. An analysis of the dispersion characteristics of the generated surface waves is performed using a recently reported optimised seismic interferometric technique. Based on the dispersion characteristics, the shear wave velocities of the surface waves as a function of the depth profile of the Earth’s crust are determined using an optimised evolutionary algorithm.
This paper presents reported machine learning approaches in the field of Brillouin distributed fiber optic sensors (DFOSs). The increasing popularity of Brillouin DFOSs stems from their capability to continuously monitor temperature and strain along kilometer-long optical fibers, rendering them attractive for industrial applications, such as the structural health monitoring of large civil infrastructures and pipelines. In recent years, machine learning has been integrated into the Brillouin DFOS signal processing, resulting in fast and enhanced temperature, strain, and humidity measurements without increasing the system’s cost. Machine learning has also contributed to enhanced spatial resolution in Brillouin optical time domain analysis (BOTDA) systems and shorter measurement times in Brillouin optical frequency domain analysis (BOFDA) systems. This paper provides an overview of the applied machine learning methodologies in Brillouin DFOSs, as well as future perspectives in this area.
We present a temperature sensor based on a polymer exhibiting a Lower Critical Solution Temperature (LCST) in aqueous solution encapsulated in a capillary. Parameters are chosen such that the solution exhibits a cloud point in a temperature range of 30° C to 39°C. The characteristic of thermoresponsive polymers with an LCST, is that above that temperature phase separation of the polymer takes place which leads to a temperature-dependent formation of a cloudy suspension. An optical intensity measurement over the desired temperature range is established by an increase of optical attenuation inside the polymer solution caused by a rising temperature. For our purpose, the polymer capillary is connected to transmitter and receiver via a Polymer Optical Fibre (POF). Our intensity measurement is, to the best of our knowledge, a novel method and can be considered simple when compared to existing fibre-based temperature measurement techniques. Due to the lack of electrical components at the probe, this sensor is suitable for measurements in strong electromagnetic fields and environments for which flying sparks are hazardous, i.e., inflammable fluids or gases. Furthermore, all manufactured sensors share the same temperature dependence and, therefore, are well-suited for comparative measurement, e.g., flow measurement systems. With the given temperature range, a body temperature measurement is also suitable.
We present a high-precision fiber-optic temperature sensor based on a polymer possessing a Lower Critical Solution Temperature (LCST) in aqueous solution encapsulated in a capillary. For a temperature higher than the LCST the transparent homogenous polymer solution changes into a suspension which forms an opaque fluid. The resulting temperature-dependent turbidity influences the transmission characteristics measured using a simple fiber-optic system.
The presented development provides a small-sized, robust temperature sensor, patented by the BAM (patent nr.: EP 3 043 161 B1), easy to integrate in many application fields, especially for process monitoring.
Geometric phase measured per beat period in a ϕ-OTDR based on coherent heterodyne detection is used to measure strain. Proposed method is robust to polarisation mismatch fading as a polarisation mismatch between interfering beams is not a hindrance to the measurement of the geometric phase. The Geometric phase is a function of the intensities of the interfering beams as well as the envelope of the beat signal. Its calculation does not require phase unwrapping and accordingly does not suffer the phase unwrapping errors. It is required to be equated with the traditionally measured phase by applying a scaling factor. The spatial resolution of the measured strain is reduced as it is calculated per beat period. Results are verified using a piezo-electric transducer inline a fiber-under-test.
Der Beitrag behandelt verschiedene Themen aus dem H2Safety@BAM-Kompetenzfeld Sensorik, Analytik und zertifizierte Referenzmaterialien (SensRef) mit Schwerpunkt auf Mess- und Prüfverfahren, die verschiedene Analyseverfahren, Sensortechnologien und Ultraschallwellen nutzen. Ein Teil davon ist das Euramet-Vorhaben "MefHySto" zur Metrologie der Wasserstoffspeicherung. Des Weiteren werden Verfahren zur Erkennung von freigesetztem Wasserstoff und zur Bestimmung des Wasserstoff-Luftverhältnisses mithilfe von Gassensoren behandelt. Ein weiterer Aspekt ist die zerstörungsfreie Fehlstellenerkennung mit einem integrierten Zustandsüberwachungssystem, das auf geführten Ultraschallwellen basiert und zur Überwachung der Lebensdauer von Composite-Behältern (Wasserstoffspeicher) dient. Zudem wird die Anwendung faseroptischer Sensorik zur Schadenfrüherkennung an Wasserstoffspeichern diskutiert. Dabei werden erkennbare Dehnungsänderungen an Druckbehältern als Indikatoren genutzt.
A phase-sensitive optical time domain reflectometer based on coherent heterodyne detection of geometric phase in the beat signal of light, is reported for the first time to our knowledge. The use of the geometric phase to extract strain makes it immune to polarisation diversity fading. This is because a polarisation mismatch between the interfering beams is not a hindrance to its measurement. The geometric phase is calculated using the amplitude of the beat signal and individual beam intensities without any need for phase unwrapping. It is measured per beat period and can be equated with the traditionally measured dynamic phase with appropriate scaling. The results show that the system based on the geometric phase successfully measures strain, free from polarisation mismatch fading and phase unwrapping errors, providing a completely novel solution to these problems.
After describing the basics of distributed fiber optic sensing in general and distributed fiber optic acoustic sensing (DAS) in particular, several currently and previously investigated fields of application of DASin infrastructure monitoring and seismic monitoring are presented. A focus is placed on seismic measurements and DAS measurements determining the dynamic responses of concrete structures to certain stimuli.
We report, to our knowledge for the first time on simultaneous distributed temperature and strain sensing in a standard telecom optical fiber using a machine learning assisted Brillouin frequency domain analysis (BOFDA) system. The well-known temperature and strain cross-sensitivity problem is addressed by developing a BOFDA system with a high signal-to-noise ratio and applying machine learning. The spectrum consists of four highly resolved peaks, whose Brillouin frequency shifts are extracted and serve as features for the machine learning algorithms. The spectra result from a 450-m standard SMF-28 optical fiber, and particularly from a segment of 30 m. This fiber segment is coiled around a stretcher and placed in a climate chamber. The applied temperature and strain values range from 20 °C to 40 °C and from 0 µɛ to 1380 µɛ, respectively. The total measurement time to achieve a high SNR and resolve four peaks with a spatial resolution of 6 m is 16 min. To discriminate temperature and strain effects, simple frequentist and more sophisticated Bayesian-based algorithms are employed with the powerful Gaussian process regression (GPR) delivering the best performance in terms of temperature and strain errors, which are found to be 2 °C and 45 µɛ, respectively. These errors are calculated using leave-one-out cross-validation, so that an unbiased estimation of the sensor’s performance is provided.
In this paper, we present a collection of machine learning assisted distributed fiber optic sensors (DFOS) for applications in the field of infrastructure monitoring. We employ advanced signal processing based on artificial neural networks (ANNs) to enhance the performance of the dynamic DFOS for strain and vibration sensing. Specifically, ANNs in comparison to conventional and computationally expensive correlation and linearization algorithms, deliver lower strain errors and speed up the signal processing allowing real time strain monitoring. Furthermore, convolutional neural networks (CNNs) are used to denoise the dynamic DFOS signal and enable useable sensing lengths of up to 100 km. Applications of the machine learning assisted dynamic DFOS in road traffic and railway infrastructure monitoring are demonstrated. In the field of static DFOS, machine learning is applied to the well-known Brillouin optical frequency domain analysis (BOFDA) system. Specifically, CNN are shown to be very tolerant against noisy spectra and contribute towards significantly shorter measurement times. Furthermore, different machine learning algorithms (linear and polynomial regression, decision trees, ANNs) are applied to solve the well-known problem of cross-sensitivity in cases when temperature and humidity are measured simultaneously. The presented machine learning assisted DFOS can potentially contribute towards enhanced, cost effective and reliable monitoring of infrastructures.
Der Beitrag beinhaltet Themen vom H2Safety@BAM-Kompetenzfeld Sensorik, Analytik und zertifizierte Referenzmaterialien (SensRef) mit Fokus auf Mess- und Prüfverfahren mit verschiedenen Sensortechnologien und Ultraschallwellen:
Metrologie zur Wasserstoffspeicherung - Euramet-Vorhaben "MefHySto",
Erkennung von freigesetztem Wasserstoff sowie die Bestimmung des Wasserstoff-Luftverhälntisses mit Gassensoren, zerstörungsfreie Fehlstellenerkennung mit integriertem Zustandsüberwachungssystem basierend auf geführten Ultraschallwellen zur Lebensdauerüberwachung von Composite-Behältern (Wasserstoffspeicher) sowie faseroptische Sensorik zur Schadenfrüherkennung von Wasserstoffspeichern aufgrund erkennbarer Dehnungsänderungen an Druckbehältern.
In this study, an approach for mitigation of LSFD in Φ-OTDR systems was proposed. By using one probe pulse as a reference in a system with two or more probe frequencies, we can remove unwanted low frequency noise that is originally caused by the laser source. Although LSFD is problematic issue, it is not the only source of low frequency noise. Change in temperature, humidity, physical surroundings, environment, etc., can result in such noises. The proposed method; however, is expected to highly suppresses all of these effects, regardless of their source, either in the time or frequency domain.
For comparing reference and probe signals, there are sophisticated methods, rather than normal differentiation, available for use. Some of these methods have a close relationship with CPD methods and can further enhance the results. These methods can be further discussed in an independent research or future work.
The proposed method is very helpful for increasing accuracy in passive and active seismic monitoring, reservoir monitoring, underwater monitoring, etc. It also helps using relatively simpler laser sources and make the whole system price-efficient, as well as processing data without lengthy compensation algorithms.
In this study, a signal processing approach for heterodyne Փ-OTDR and C-OTDR systems that can obtain external perturbation and its frequency content in a faster way is proposed. We can detect vibrations with the same or better SNR using this processing approach, only with a single step and fast calculation. Fig. 12 shows the comparison of the normalized measurement time for the gamma matrix method and the conventional method throughout the three experiments. The speed of processing using a gamma matrix is ~35%–50% faster compared to a conventional method in high frequency test (PZT), low frequency test (walking) and street monitoring test. The processing speed in low frequency test is normally a bit lower than the similar high frequency one, since we must use higher number of time frames. Also, in street test we have higher speed because we can select wider gauges.
Monitoring of construction projects plays increasingly important role in the implementation of growing needs and requirements, especially in geologically difficult areas. This particularly concerns tunnelling and special civil engineering projects. The use of fiber optic sensors for structural health monitoring provides significant economic advantages regarding lower life-cycle costs of the civil infrastructure. We present our achievements in the development of distributed polymer optical fiber sensors based on Rayleigh and Brillouin scattering for early damage detection.
Chemical and pharmaceutical companies have to find new paths to survive successfully in a changing environment, while also finding more flexible ways of product and process development to bring their products to market more quickly – especially high-quality high-end products like fine chemicals or pharmaceuticals. A current approach uses flexible and modular chemical production units, which can produce different high-quality products using multi-purpose equipment with short downtimes between campaigns and reduce the time to market of new products.
NMR spectroscopy appeared as excellent online analytical tool and allowed a modular data analysis approach, which even served as reliable reference method for further Process Analytical Technology (PAT) applications. Using the available datasets, a second data analysis approach based on artificial neural networks (ANN) was evaluated. Therefore, amount of data was augmented to be sufficient for training. The results show comparable performance, while improving the calculation time tremendously. In future, such fully integrated and interconnecting “smart” systems and processes can increase the efficiency of the production of specialty chemicals and pharmaceuticals.
Chemical and pharmaceutical companies need to find new ways to survive successfully in a changing environment, while finding more flexible ways of product and process development to bring their products to market faster - especially high-value, high-end products such as fine chemicals or pharmaceuticals. This is complicated by changes in value chains along a potential circular economy.
One current approach is flexible and modular chemical production units that use multi-purpose equipment to produce various high-value products with short downtimes between campaigns and can shorten time-to-market for new products. Online NMR spectroscopy will play an important role for plant automation and quality control, as the method brings very high linearity, matrix independence and thus works almost calibration-free. Moreover, these properties ideally enable automated and machine-aided data analysis for the above-mentioned applications.
Using examples, this presentation will outline a possible more holistic approach to digitalization and the use of machine-based processes in the production of specialty chemicals and pharmaceuticals through the introduction of integrated and networked systems and processes.
The geometric phase in the beat signal from coherent interference of two frequency-offset light beams is measured using a novel distributed optical fiber sensing setup. In a fiber optic medium, with changing beam intensities, to the best of our knowledge, ours is the first measurement of the mentioned geometric phase. Experimental results of applying a 100-Hz sinusoidal stimulus to a polarization scrambler and a piezoelectric transducer inline to an optical fiber are presented. The results may enable novel distributed fiber sensing techniques.
Brillouin Optical Frequency Domain Analysis (BOFDA) is a powerful and well-established method for static distributed sensing of temperature and strain. Recently, we demonstrated a BOFDA system based on convolutional neural network which shortens the measurement time considerably. In this paper, we apply leave-one-out cross validation to evaluate the generalization performance and provide an unbiased and reliable machine learning model for a time-efficient BOFDA system.
We present our achievements in the development of distributed fiber optic sensing systems based on Brillouin optical frequency-domain analysis for structural health monitoring. The focus of the applications is on the gapless monitoring of geotechnical structures, large area infrastructures and electrical grids. The work includes the latest use of machine learning algorithms to reduce measurement time by coexistent increasing the measurement accuracy.
Brillouin Optical Frequency Domain Analysis (BOFDA) is a powerful and well-established method for static distributed sensing of temperature and strain. Recently, we demonstrated a BOFDA system based on convolutional neural network which shortens the measurement time considerably. In this paper, we apply leave-one-out cross validation to evaluate the generalization performance and provide an unbiased and reliable machine learning model for a time-efficient BOFDA system.
In the last few years, the use of machine learning has emerged in the field of distributed fiber optic sensors as a promising approach to enhance their performance and provide new capabilities. In this study, we use machine learning for simultaneous measurements of temperature and humidity in polyimide (PI)-coated optical fibers based on Brillouin Brillouin optical frequency domain analysis (BOFDA). Different non-linear machine learning algorithms are employed, namely polynomial regression, decision trees and artificial neural networks (ANNs), and their discrimination performance is benchmarked against that of the conventional linear regression. The performance is evaluated using leave-one-out cross-validation to ensure that the models are reliable and able to generalize well on new data. We show that nonlinear machine learning algorithms outperform the conventional linear regression and thus could pave the way towards simultaneous cost-effective temperature and humidity distributed sensing, which has the potential to find attractive new applications in the field of civil and geotechnical engineering, from structural health monitoring of dikes and bridges to subsea cables and long pipelines corrosion detection.
In the last few years, the use of machine learning has emerged in the field of distributed fiber optic sensors as a promising approach to enhance their performance and provide new capabilities. In this study, we use machine learning for simultaneous measurements of temperature and humidity in polyimide (PI)-coated optical fibers based on Brillouin Brillouin optical frequency domain analysis (BOFDA). Different non-linear machine learning algorithms are employed, namely polynomial regression, decision trees and artificial neural networks (ANNs), and their discrimination performance is benchmarked against that of the conventional linear regression. The performance is evaluated using leave-one-out cross-validation to ensure that the models are reliable and able to generalize well on new data. We show that nonlinear machine learning algorithms outperform the conventional linear regression and thus could pave the way towards simultaneous cost-effective temperature and humidity distributed sensing, which has the potential to find attractive new applications in the field of civil and geotechnical engineering, from structural health monitoring of dikes and bridges to subsea cables and long pipelines corrosion detection.
Distributed humidity fiber-optic sensor based on BOFDA using a simple machine learning approach
(2022)
We report, to our knowledge for the first time, on distributed relative humidity sensing in silica polyimide-coated optical fibers using Brillouin optical frequency domain analysis (BOFDA). Linear regression, which is a simple and well-interpretable algorithm in machine learning and statistics, is utilized. The algorithm is trained using as features the Brillouin frequency shifts and linewidths of the fiber’s multipeak Brillouin spectrum. To assess and improve the effectiveness of the regression algorithm, we make use of machine learning concepts to estimate the model’s uncertainties and select the features that contribute most to the model’s performance. In addition to relative humidity, the model is also able to simultaneously provide distributed temperature information addressing the well-known cross-sensitivity effects.
Die verteilte faseroptische akustische Sensorik (DAS) wird vorgestellt, hinsichtlich ihrer Leistungsfähigkeit beschrieben und verschiedenste Anwendungsfelder, z.B. für das Zustandsmonitoring oder für seismische Messungen, beispielhaft gezeigt. Zudem werden mögliche Anwendungsfelder von DAS für den Kontext Kerntechnische Entsorgung (KTE) und Rückbau aufgezeigt.
Intelligent sensor systems, certified reference materials and instrumental analytical-chemical methods contribute to safety and functionality in hydrogen technologies.
This article gives a brief overview of SensRef activities in the Competence Centre H2Safety@BAM on the issues: Analytical methods for the determination of hydrogen purity, certified reference materials as measurement standards with regard to gas quality (primary calibrators) of BAM, test methods for gas sensor systems to detect hydrogen in air as well as the application of fibre-optic sensor systems to monitor the expansion and ageing behaviour of composite containers in hydrogen technologies.
Der Vortrag zum Mess- und Prüfverfahren mit verschiedenen Sensortechnologien und Ultraschallwellen beinhaltet die Themen:
Metrologie zur Wasserstoffspeicherung - Euramet-Vorhaben "MefHySto",
Erkennung von freigesetztem Wasserstoff sowie die Bestimmung des Wasserstoff-Luftverhälntisses mit Gassensoren, zerstörungsfreie Fehlstellenerkennung mit integriertem Zustandsüberwachungssystem basierend auf geführten Ultraschallwellen zur Lebensdauerüberwachung von Composite-Behältern (Wasserstoffspeicher) sowie faseroptische Sensorik zur Schadenfrüherkennung von Wasserstoffspeichern aufgrund erkennbarer Dehnungsänderungen an Druckbehältern.
Mass Spectrometry (MS) and Nuclear Magnetic Resonance Spectroscopy (NMR) are valuable analytical and quality control methods for most industrial chemical processes as they provide information on the concentrations of individual compounds and by-products. These processes are traditionally carried out manually and by a specialist, which takes a substantial amount of time and prevents their utilization for real-time closed-loop process control. This paper presents recent advances from two projects that use Artificial Neural Networks (ANNs) to address the challenges of automation and performance-efficient realizations of MS and NMR. In the first part, a complete toolchain has been realized to develop simulated spectra and train ANNs to identify compounds in MS. In the second part, a limited number of experimental NMR spectra have been augmented by simulated spectra, to train an ANN with better prediction performance and speed than state-of-the-art analysis. These results suggest that, in the context of the digital transformation of the process industry, we are now on the threshold of a strongly simplified use of MS and MRS and the accompanying data evaluation by machine-supported procedures, and can utilize both methods much wider for reaction and process monitoring or quality control.
We present a preliminary investigation on distributed humidity monitoring during the drying process of concrete based on an embedded polymer optical fiber (POF). The water dissipated into the POF changes several properties of the fiber such as refractive index, scattering coefficient and attenuation factor, which eventually alters the Rayleigh backscattered light. The optical time Domain reflectometer (OTDR) technique is performed to acquire the backscattered signal at the wavelengths 650 nm and 500 nm, respectively. Experimental results show that the received signal increases at 650 nm while the fiber attenuation factor clearly increases at 500 nm, as the concrete dries out. In the hygroscopic range, the information retrieved from the signal change at 650 nm agrees well with the measurement result of the electrical humidity sensors also embedded in the concrete sample.
Machine learning predictions of surface migration barriers in nucleation and non-equilibrium growth
(2021)
Machine learning is playing an increasing role in the discovery of new materials and may also facilitate the search for optimum growth conditions for crystals and thin films. Here, we perform kinetic Monte-Carlo simulations of sub-monolayer growth. We consider a generic homoepitaxial growth scenario that covers a wide range of conditions with different diffusion barriers (0.4–0.55 eV) and lateral binding energies (0.1–0.4 eV). These simulations are used as a training data set for a convolutional neural network that can predict diffusion barriers and binding energies. Specifically, a single Monte-Carlo image of the morphology is sufficient to determine the energy barriers with an accuracy of approximately 10 meV and the neural network is tolerant to images with noise and lower than atomic-scale resolution. We believe this new machine learning method will be useful for fundamental studies of growth kinetics and growth optimization through better knowledge of microscopic parameters.
Division 8.6's competencies and work focus areas are shortly outlined and investigations related to pipeline and submarine power cable monitoring using different distributed fiber optic sensing techniques are presented with some results. Furthermore, BAM 8.6 expertise in the field of sensor application, embedding and integration is shown.
The lack of on-line validation procedures for structure-embedded fiber-optical strain sensors, in particular fiber-Bragg-gratings (FBG), resulted in limited applications in structural health monitoring (SHM). Degradation under service conditions and ageing as a result of climatic influences or delamination under load were unsolved Validation issues. This could be overcome by means of an auto-diagnosis procedure based on FBG-sensors coated by electrochemical deposition (ECD) with a magnetostrictive NiFe-coating on top of an adhesive Cu/Cr adhesive layer deposited by physical vapour deposition (PVD) around the FBG strain sensor. This allows at any time under Service a validation of sensor functionality, stability, and reliability. For this purpose, a magnetic strain-proportional reference field is introduced. The optical read-out is realized by the measurement of the Bragg-wavelength shift.
The ratio of resulting strain and exciting magnetic reference field should be constant given that the sensor is in proper function.
In principle, the magnetostrictive coating around the FBG should also work as on-line magnetic field sensor and other applications in material science. One of these applications is the in-situ monitoring of ECD processes as the deposition of the ECD NiFe-layer on the FBG revealed. Challenges are the monitoring of temperature, deposition
stages/thickness, and resulting mechanical stress under given plating conditions. Monitoring problems can be solved by applying a pre-coated FBG to the electrolytic process as the shift of the Bragg wavelength is affected by both the temperature of the electrolyte near the substrate and the stress formation in the growing layer. The experimental FBG set-up and the quantitative determination of temperature- and stress-related strain are described for a nickeliron
electrolyte. The in-situ measurement of Bragg wavelength shifts of a pre-coated FBG during electrochemical deposition allows a detailed analysis of stress states due to changes in the growth morphology of the layer. The separation of mechanical and thermal contributions to this shift provides information on the individual Deposition processes in terms of a process fingerprint.
Time-Efficient Convolutional Neural Network-Assisted Brillouin Optical Frequency Domain Analysis
(2021)
To our knowledge, this is the first report on a machine-learning-assisted Brillouin optical frequency domain analysis (BOFDA) for time-efficient temperature measurements. We propose a convolutional neural network (CNN)-based signal post-processing method that, compared to the conventional Lorentzian curve fitting approach, facilitates temperature extraction. Due to its robustness against noise, it can enhance the performance of the system. The CNN-assisted BOFDA is expected to shorten the measurement time by more than nine times and open the way for applications, where faster monitoring is essential.
The competitiveness of the process industry is based on ensuring the required product quality while making optimum use of equipment, raw materials and energy. Chemical companies have to find new paths to survive successfully in a changing environment, while also finding more flexible ways of product and process development to bring their products to market more quickly – especially high-quality high-end products like fine chemicals or pharmaceuticals. The potential of digital technologies belongs to these.
One way is knowledge-based production, taking into account all essential equipment, process and regulatory data of plants and laboratories. Today, the potential of this data is often not yet consistently used for a comprehensive understanding of production. Another approach uses flexible and modular chemical plants, which can produce different high-quality products using multi-purpose equipment with short downtimes between campaigns and reduce the time to market of new products. Digital transformation is enabling completely new production concepts that are being used increasingly. Intensified continuous production plants also allow for difficult to produce compounds.
This contribution aims to encourage a more holistic approach to the digitalization and use of machine-assisted methods in (bio) process engineering by introduction of integrated and networked systems and processes, which have the potential to speed up the high-quality production of specialty chemicals and pharmaceuticals.