Raman laser intensity and sample clarification on biochemical monitoring over Zika-VLP upstream stages.

In the current biopharmaceutical scenario, constant bioprocess monitoring is crucial for the quality and integrity of final products. Thus, process analytical techniques, such as those based on Raman spectroscopy, have been used as multiparameter tracking methods in pharma bioprocesses, which can be combined with chemometric tools, like Partial Least Squares (PLS) and Artificial Neural Networks (ANN). In some cases, applying spectra pre-processing techniques before modeling can improve the accuracy of chemometric model fittings to observed values. One of the biological applications of these techniques could have as a target the virus-like particles (VLP), a vaccine production platform for viral diseases. A disease that has drawn attention in recent years is Zika, with large-scale production sometimes challenging without an appropriate monitoring approach. This work aimed to define global models for Zika VLP upstream production monitoring with Raman considering different laser intensities (200 mW and 495 mW), sample clarification (with or without cells), spectra pre-processing approaches, and PLS and ANN modeling techniques. Six experiments were performed in a benchtop bioreactor to collect the Raman spectral and biochemical datasets for modeling calibration. The best models generated presented a mean absolute error and mean relative error respectively of 3.46 × 105 cell/mL and 35 % for viable cell density (Xv); 4.1 % and 5 % for cell viability (CV); 0.245 g/L and 3 % for glucose (Glc); 0.006 g/L and 18 % for lactate (Lac); 0.115 g/L and 26 % for glutamine (Gln); 0.132 g/L and 18 % for glutamate (Glu); 0.0029 g/L and 3 % for ammonium (NH4+); and 0.0103 g/L and 2 % for potassium (K+). Sample without conditioning (with cells) improved the models' adequacy, except for Glutamine. ANN better predicted CV, Gln, Glu, and K+, while Xv, Glc, Lac, and NH4+ presented no statistical difference between the chemometric tools. For most of the assessed experimental parameters, there was no statistical need for spectra pre-filtering, for which the models based on the raw spectra were selected as the best ones. Laser intensity impacts quality model predictions in some parameters, Xv, Gln, and K+ had a better performance with 200 mW of intensity (for PLS, ANN, and ANN, respectively), for CV the 495 mW laser intensity was better (for PLS), and for the other biochemical variables, the use of 200 or 495 mW did not impact model fitting adequacy.

Intelligent process monitoring of smart polymer composites using large area graphene coated fabric sensor.

Herein, we report the development of an online process monitoring system for vacuum-assisted resin transfer molding (VARTM) process using large area graphene coated in-situ fabric sensor. Besides imparting excellent mechanical properties to the final composites, these sensors provide critical information during the composite processing including detecting defects and evaluating processing parameters. The obtained information can be used to create a digital passport of the manufacturing phase to develop a cost-effective production technique and fabricate high-quality composites.  The fabric sensor was produced using a scalable dip-coating process by coating 1-, 3- or 5-layers of thermally reduced graphene oxide (rGO) onto glass fabric surface according to the number of dips of the fabrics into GO solution. The electrical resistances from all electrode pairs were simultaneously and continuously recorded during distinct stages of the VARTM process to determine the relative conductance. During the vacuum cycle, the range of relative conductance increased with the number of coated rGO layers, with the 5-layer rGO-coated sensor showing the highest conductance range of 16.9 %. Additionally, it was observed that the 5-layer coated sensor showed a consistent decrease in conductance during the infusion phase due to the fluid flow pressure dominating the resin electrical conductivity.

Integration of just-in-time learning with variational autoencoder for cell culture process monitoring based on Raman spectroscopy.

Protein production in the biopharmaceutical industry necessitates the utilization of multiple analytical techniques and control methodologies to ensure both safety and consistency. To facilitate real-time monitoring and control of cell culture processes, Raman spectroscopy has emerged as a versatile analytical technology. This technique, categorized as a Process Analytical Technology, employs chemometric models to establish correlations between Raman signals and key variables of interest. One notable approach for achieving real-time monitoring is through the application of just-in-time learning (JITL), an industrial soft sensor modeling technique that utilizes Raman signals to estimate process variables promptly. The conventional Raman-based JITL method relies on the K-nearest neighbor (KNN) algorithm with Euclidean distance as the similarity measure. However, it falls short of addressing the impact of data uncertainties. To rectify this limitation, this study endeavors to integrate JITL with a variational autoencoder (VAE). This integration aims to extract dominant Raman features in a nonlinear fashion, which are expressed as multivariate Gaussian distributions. Three experimental runs using different cell lines were chosen to compare the performance of the proposed algorithm with commonly utilized methods in the literature. The findings indicate that the VAE-JITL approach consistently outperforms partial least squares, convolutional neural network, and JITL with KNN similarity measure in accurately predicting key process variables.

Quantitative at-line monitoring of enzymatic hydrolysis using benchtop diffusion nuclear magnetic resonance spectroscopy.

Benchtop diffusion nuclear magnetic resonance (NMR) spectroscopy was used to perform quantitative monitoring of enzymatic hydrolysis. The study aimed to test the feasibility of the technology to characterize enzymatic hydrolysis processes in real time. Diffusion ordered spectroscopy (DOSY) was used to measure the signal intensity and apparent self-diffusion constant of solubilized protein in hydrolysate. The NMR technique was tested on an enzymatic hydrolysis reaction of red cod, a lean white fish, by the endopeptidase alcalase at 50°C. Hydrolysate samples were manually transferred from the reaction vessel to the NMR equipment. Measurement time was approximately 3 min per time point. The signal intensity from the DOSY experiment was used to measure protein concentration and the apparent self-diffusion constant was converted into an average molecular weight and an estimated degree of hydrolysis. These values were plotted as a function of time and both the rate of solubilization and the rate of protein breakdown could be calculated. In addition to being rapid and noninvasive, DOSY using benchtop NMR spectroscopy has an advantage compared with other enzymatic hydrolysis characterization methods as it gives a direct measure of average protein size; many functional properties of proteins are strongly influenced by protein size. Therefore, a method to give protein concentration and average size in real time will allow operators to more tightly control production from enzymatic hydrolysis. Although only one type of material was tested, it is anticipated that the method should be applicable to a broad variety of enzymatic hydrolysis feedstocks.

Polarization transfer methods for quantitative analysis of flowing mixtures with benchtop 13C NMR spectroscopy.

Benchtop NMR spectroscopy is attractive for process monitoring; however, there are still drawbacks that often hamper its use, namely, the comparatively low spectral resolution in 1H NMR, as well as the low signal intensities and problems with the premagnetization of flowing samples in 13C NMR. We show here that all these problems can be overcome by using 1H-13C polarization transfer methods. Two ternary test mixtures (one with overlapping peaks in the 1H NMR spectrum and one with well-separated peaks, which was used as a reference) were studied with a 1 T benchtop NMR spectrometer using the polarization transfer sequence PENDANT (polarization enhancement that is nurtured during attached nucleus testing). The mixtures were analyzed quantitatively in stationary as well as in flow experiments by PENDANT enhanced 13C NMR experiments, and the results were compared with those from the gravimetric sample preparation and from standard 1H and 13C NMR spectroscopy. Furthermore, as a proxy for a process monitoring application, continuous dilution experiments were carried out, and the composition of the mixture was monitored in a flow setup by 13C NMR benchtop spectroscopy with PENDANT. The results demonstrate the high potential of polarization transfer methods for applications in quantitative process analysis with benchtop NMR instruments, in particular with flowing samples.

Brewing alcohol 101: An undergraduate experiment utilizing benchtop NMR for quantification and process monitoring.

In recent years there has been a renewed interest in benchtop NMR. Given their lower cost of ownership, smaller footprint, and ease of use, they are especially suited as an educational tool. Here, a new experiment targeted at upper-year undergraduates and first-year graduate students follows the conversion of D-glucose into ethanol at low-field. First, high and low-field data on D-glucose are compared and students learn both the Hz and ppm scales and how J-coupling is field-independent. The students then acquire their own quantitative NMR datasets and perform the quantification using an Electronic Reference To Access In Vivo Concentration (ERETIC) technique. To our knowledge ERETIC is not currently taught at the undergraduate level, but has an advantage in that internal standards are not required; ideal for following processes or with future use in flow-based benchtop monitoring. Using this quantitative data, students can relate a simple chemical process (fermentation) back to more complex topics such as reaction kinetics, bridging the gaps between analytical and physical chemistry. When asked to reflect on the experiment, students had an overwhelmingly positive experience, citing agreement with learning objectives, ease of understanding the protocol, and enjoyment. Each of the respondents recommended this experiment as a learning tool for others. This experiment has been outlined for other instructors to utilize in their own courses across institutions, with the hope that a continued expansion of low-field NMR will increase accessibility and learning opportunities at the undergraduate level.

Development of a Nuclear Fuel Dissolution Monitor Based on Raman Spectroscopy.

The processing of spent nuclear fuel and other nuclear materials is a critical component of nuclear material management with implications for global security. The first step of fuel processing is dissolution, with several charges of fuel sequentially added to a batch of solvent. The incomplete dissolution of a charge precludes the addition of the next charge. As the dissolution takes place in a heated, highly corrosive and radiological vessel, direct monitoring of the process is not possible. We discuss the use of Raman spectroscopy to indirectly monitor dissolution through an analysis of the gaseous emissions from the dissolver. Challenges associated with the implementation of Raman spectroscopy include the composition and physical characteristics of the offgas stream and the impact of operating conditions. Nonetheless, we observed that NO2 concentrations serve as a reliable indicator of process activity and correlate to the amount of fuel material that remains undissolved. These results demonstrate the promise of the method for monitoring nuclear material dissolution.

Multi-Sensory Tool Holder for Process Force Monitoring and Chatter Detection in Milling.

Sensor-based monitoring of process and tool condition in milling is a key technology for improving productivity and workpiece quality, as well as enabling automation of machine tools. However, industrial implementation of such monitoring systems remains a difficult task, since they require high sensitivity and minimal impact on CNC machines and cutting conditions. This paper presents a novel multi-sensory tool holder for measurement of process forces and vibrations in direct proximity to the cutting tool. In particular, the sensor system has an integrated temperature sensor, a triaxial accelerometer and strain gauges for measurement of axial force and bending moment. It is equipped with a self-sufficient electric generator and wireless data transmission, allowing for a tool holder design without interfering contours. Milling and drilling experiments with varying cutting parameters are conducted. The measurement data are analyzed, pre-processed and verified with reference signals. Furthermore, the suitability of all integrated sensors for detection of dynamic instabilities (chatter) is investigated, showing that bending moment and tangential acceleration signals are the most sensitive regarding this monitoring task.

NMR in Battery Anode Slurries with a V-Shaped Sensor.

Inline analytics in industrial processes reduce operating costs and production rejection. Dedicated sensors enable inline process monitoring and control tailored to the application of interest. Nuclear Magnetic Resonance is a well-known analytical technique but needs adapting for low-cost, reliable and robust process monitoring. A V-shaped low-field NMR sensor was developed for inline process monitoring and allows non-destructive and non-invasive measurements of materials, for example in a pipe. In this paper, the industrial application is specifically devoted to the quality control of anode slurries in battery production. The characterization of anode slurries was performed with the sensor to determine chemical composition and detect gas inclusions. Additionally, flow properties play an important role in continuous production processes. Therefore, the in- and outflow effects were investigated with the V-shaped NMR sensor as a basis for the future determination of slurry flow fields.

Characterization of Flow with a V-Shaped NMR Sensor.

Quality control in a production plant shows its maximum potential in the form of inline measurements. Defects and imperfections can be detected early and directly, and waste and costs can be reduced. Nuclear Magnetic Resonance offers a wide range of applications but requires dedicated adaptation to the respective process and material conditions. A V-shaped low-field NMR sensor was developed for non-invasive inline measurements on anode slurries in a battery production plant. In battery production, inline monitoring of the quality of anode slurries is demanded, offering the possibility of predictive control of the following process steps. Methods of low-field NMR to determine flow properties were adapted to the desired application. Further, magnetic resonance imaging measurements were made to determine the flow properties of model substances and anode slurries, thus providing verification. The sensor measurements show the ability to measure the flow behavior of, amongst other fluids, anode slurries in a form suitable for inline quality control in a battery production plant.

An End-to-End Inclination State Monitoring Method for Collaborative Robotic Drilling Based on Resnet Neural Network.

The collaborative robot can complete various drilling tasks in complex processing environments thanks to the high flexibility, small size and high load ratio. However, the inherent weaknesses of low rigidity and variable rigidity in robots bring detrimental effects to surface quality and drilling efficiency. Effective online monitoring of the drilling quality is critical to achieve high performance robotic drilling. To this end, an end-to-end drilling-state monitoring framework is developed in this paper, where the drilling quality can be monitored through online-measured vibration signals. To evaluate the drilling effect, a Canny operator-based edge detection method is used to quantify the inclination state of robotic drilling, which provides the data labeling information. Then, a robotic drilling inclination state monitoring model is constructed based on the Resnet network to classify the drilling inclination states. With the aid of the training dataset labeled by different inclination states and the end-to-end training process, the relationship between the inclination states and vibration signals can be established. Finally, the proposed method is verified by collaborative robotic drilling experiments with different workpiece materials. The results show that the proposed method can effectively recognize the drilling inclination state with high accuracy for different workpiece materials, which demonstrates the effectiveness and applicability of this method.

Convolutional Neural Networks for Raw Signal Classification in CNC Turning Process Monitoring.

This study addresses the need for advanced machine learning-based process monitoring in smart manufacturing. A methodology is developed for near-real-time part quality prediction based on process-related data obtained from a CNC turning center. Instead of the manual feature extraction methods typically employed in signal processing, a novel one-dimensional convolutional architecture allows the trained model to autonomously extract pertinent features directly from the raw signals. Several signal channels are utilized, including vibrations, motor speeds, and motor torques. Three quality indicators-average roughness, peak-to-valley roughness, and diameter deviation-are monitored using a single model, resulting in a compact and efficient classifier. Training data are obtained via a small number of experiments designed to induce variability in the quality metrics by varying feed, cutting speed, and depth of cut. A sliding window technique augments the dataset and allows the model to seamlessly operate over the entire process. This is further facilitated by the model's ability to distinguish between cutting and non-cutting phases. The base model is evaluated via k-fold cross validation and achieves average F1 scores above 0.97 for all outputs. Consistent performance is exhibited by additional instances trained under various combinations of design parameters, validating the robustness of the proposed methodology.

Causal Learning: Monitoring Business Processes Based on Causal Structures.

Conventional methods for process monitoring often fail to capture the causal relationships that drive outcomes, making hard to distinguish causal anomalies from mere correlations in activity flows. Hence, there is a need for approaches that allow causal interpretation of atypical scenarios (anomalies), allowing to identify the influence of operational variables on these anomalies. This article introduces (CaProM), an innovative technique based on causality techniques, applied during the planning phase in business process environments. The technique combines two causal perspectives: anomaly attribution and distribution change attribution. It has three stages: (1) process events are collected and recorded, identifying flow instances; (2) causal learning of process activities, building a directed acyclic graphs (DAGs) represent dependencies among variables; and (3) use of DAGs to monitor the process, detecting anomalies and critical nodes. The technique was validated with a industry dataset from the banking sector, comprising 562 activity flow plans. The study monitored causal structures during the planning and execution stages, and allowed to identify the main factor behind a major deviation from planned values. This work contributes to business process monitoring by introducing a causal approach that enhances both the interpretability and explainability of anomalies. The technique allows to understand which specific variables have caused an atypical scenario, providing a clear view of the causal relationships within processes and ensuring greater accuracy in decision-making. This causal analysis employs cross-sectional data, avoiding the need to average multiple time instances and reducing potential biases, and unlike time series methods, it preserves the relationships among variables.

Design of experiments for micellar electrokinetic chromatography method development for the monitoring of water-soluble vitamins in cell culture medium.

Biopharmaceutical production takes place in complex processes which should be thoroughly understood. Therefore, the iConsensus project focuses on developing a monitoring platform integrating several process analytical technology tools for integrated, automated monitoring of the biopharmaceutical process. Water-soluble vitamin monitoring using (microchip) capillary electrophoresis (CE) is part of this platform. This work comprises the development of conventional CE methods as the first part towards integrated vitamin monitoring. The vitamins were divided based on their physical-chemical properties to develop two robust methods. Previously, a method for the analysis of cationic vitamins (pyridoxine, pyridoxal, pyridoxamine, thiamine and nicotinamide) in cell culture medium was developed. This work focused on the development of a micellar electrokinetic chromatography method for anionic and neutral vitamins (riboflavin, d-calcium pantothenate, biotin, folic acid, cyanocobalamin and ascorbic acid). By employing multivariate design of experiments, the background electrolyte (BGE) could be optimised within one experiment testing only 11 BGEs. The optimised BGE conditions were 200 mM borate with 77 mM sodium dodecyl sulphate at a pH of 8.6. Using this BGE, all above-mentioned cationic, anionic and neutral vitamins could be separated in clean samples. In cell culture medium, most anionic and neutral vitamins could be separated. Combining the two methods allows for analysis of cationic, anionic and neutral vitamins in cell culture medium samples. The next step towards integrated vitamin monitoring includes transfer to microchip CE. Due to the lack of fast and reliable methods for vitamin monitoring, the developed capillary methods could be valuable as stand-alone at-line process analytical technology solutions as well.

Advances in bioreactor control for production of biotherapeutic products.

Advanced control strategies are well established in chemical, pharmaceutical, and food processing industries. Over the past decade, the application of these strategies is being explored for control of bioreactors for manufacturing of biotherapeutics. Most of the industrial bioreactor control strategies apply classical control techniques, with the control system designed for the facility at hand. However, with the recent progress in sensors, machinery, and industrial internet of things, and advancements in deeper understanding of the biological processes, coupled with the requirement of flexible production, the need to develop a robust and advanced process control system that can ease process intensification has emerged. This has further fuelled the development of advanced monitoring approaches, modeling techniques, process analytical technologies, and soft sensors. It is seen that proper application of these concepts can significantly improve bioreactor process performance, productivity, and reproducibility. This review is on the recent advancements in bioreactor control and its related aspects along with the associated challenges. This study also offers an insight into the future prospects for development of control strategies that can be designed for industrial-scale production of biotherapeutic products.

Fault Monitoring Based on the VLSW-MADF Test and DLPPCA for Multimodal Processes.

Actual industrial processes often exhibit multimodal characteristics, and their data exhibit complex features, such as being dynamic, nonlinear, multimodal, and strongly coupled. Although many modeling approaches for process fault monitoring have been proposed in academia, due to the complexity of industrial data, challenges remain. Based on the concept of multimodal modeling, this paper proposes a multimodal process monitoring method based on the variable-length sliding window-mean augmented Dickey-Fuller (VLSW-MADF) test and dynamic locality-preserving principal component analysis (DLPPCA). In the offline stage, considering the fluctuation characteristics of data, the trend variables of data are extracted and input into VLSW-MADF for modal identification, and different modalities are modeled separately using DLPPCA. In the online monitoring phase, the previous moment's historical modal information is fully utilized, and modal identification is performed only when necessary to reduce computational cost. Finally, the proposed method is validated to be accurate and effective for modal identification, modeling, and online monitoring of multimodal processes in TE simulation and actual plant data. The proposed method improves the fault detection rate of multimodal process fault monitoring by about 14% compared to the classical DPCA method.

Investigating Machine Learning and Control Theory Approaches for Process Fault Detection: A Comparative Study of KPCA and the Observer-Based Method.

The paper focuses on the importance of prompt and efficient process fault detection in contemporary manufacturing industries, where product quality and safety protocols are critical. The study compares the efficiencies of two techniques for process fault detection: Kernel Principal Component Analysis (KPCA) and the observer method. Both techniques are applied to observe water volume variation within a hydraulic system comprising three tanks. PCA is an unsupervised learning technique used for dimensionality reduction and pattern recognition. It is an extension of Principal Component Analysis (PCA) that utilizes kernel functions to transform data into higher-dimensional spaces, where it becomes easier to separate classes or identify patterns. In this paper, KPCA is applied to detect faults in the hydraulic system by analyzing the variation in water volume. The observer method originates from control theory and is utilized to estimate the internal states of a system based on its output measurements. It is commonly used in control systems to estimate the unmeasurable or hidden states of a system, which is crucial for ensuring proper control and fault detection. In this study, the observer method is applied to the hydraulic system to estimate the water volume variations within the three tanks. The paper presents a comparative study of these two techniques applied to the hydraulic system. The results show that both KPCA and the observer method perform similarly in detecting faults within the system. This similarity in performance highlights the efficacy of these techniques and their potential adaptability in various fault diagnosis scenarios within modern manufacturing processes.

Modelling and Predictive Monitoring of Business Processes under Uncertainty with Reinforcement Learning.

The analysis of business processes based on their observed behavior recorded in event logs can be performed with process mining. This method can discover, monitor, and improve processes in various application domains. However, the process models produced by typical process discovery methods are difficult for humans to understand due to their high complexity (the so-called "spaghetti-like" process models). Moreover, these methods cannot handle uncertainty or perform predictions because of their deterministic nature. Recently, researchers have been developing predictive approaches for running business cases of processes. This paper focuses on developing a predictive business process monitoring approach using reinforcement learning (RL), which has been successful in other contexts but not yet explored in this area. The proposed approach is evaluated in the banking sector through a use case.

Inline NMR via a Dedicated V-Shaped Sensor.

Process monitoring and control require dedicated and reliable measures which reflect the status of the process under investigation. Although nuclear magnetic resonance is known to be a versatile analytical technique, it is only seldomly found in process monitoring. Single-sided nuclear magnetic resonance is one well known approach for being applied in process monitoring. The dedicated V-sensor is a recent approach that allows the inline investigation of materials in a pipe non-destructively and non-invasively. An open geometry of the radiofrequency unit is realized using a tailored coil, enabling the sensor to be applied for manifold mobile applications in in-line process monitoring. Stationary liquids were measured, and their properties were integrally quantified as the basis for successful process monitoring. The sensor, in its inline version, is presented along with its characteristics. An exemplary field of application is battery production in terms of anode slurries; thus, the first results on graphite slurries will demonstrate the added value of the sensor in process monitoring.

Development of the Tele-Measurement of Plasma Uniformity via Surface Wave Information (TUSI) Probe for Non-Invasive In-Situ Monitoring of Electron Density Uniformity in Plasma Display Fabrication Process.

The importance of monitoring the electron density uniformity of plasma has attracted significant attention in material processing, with the goal of improving production yield. This paper presents a non-invasive microwave probe for in-situ monitoring electron density uniformity, called the Tele-measurement of plasma Uniformity via Surface wave Information (TUSI) probe. The TUSI probe consists of eight non-invasive antennae and each antenna estimates electron density above the antenna by measuring the surface wave resonance frequency in a reflection microwave frequency spectrum (S11). The estimated densities provide electron density uniformity. For demonstration, we compared it with the precise microwave probe and results revealed that the TUSI probe can monitor plasma uniformity. Furthermore, we demonstrated the operation of the TUSI probe beneath a quartz or wafer. In conclusion, the demonstration results indicated that the TUSI probe can be used as an instrument for a non-invasive in-situ method for measuring electron density uniformity.