A low-field medium-resolution NMR spectrometer, with an operating frequency of 29 MHz for 1H, has been assessed for on-line process analysis. A flow cell that incorporates a pre-magnetisation region has been developed to minimise the decrease in the signal owing to incomplete polarisation effects. The homogeneous esterification reaction of crotonic acid and 2-butanol was monitored using a simple sampling loop; it was possible to monitor the progression of the reaction through changes in CH signal areas of butanol and butyl crotonate. On-line analysis of heterogeneous water-toluene mixtures proved more challenging and a fast sampling loop system was devised for use with a 5 L reactor. The fast sampling loop operated at a flow rate of 8 L min(-1) and a secondary sampling loop was used to pass a sub-sample through the NMR analyser at a slower (mL min(-1)) rate. It was shown that even with super-isokinetic sampling conditions, unrepresentative sampling could occur owing to inadequate mixing in the reactor. However, it was still possible to relate the 1H NMR signal obtained at a flow rate of 60 mL min(-1) to the composition of the reactor contents.

Batch process performance monitoring has been achieved primarily using process measurements with the extracted information being associated with the physical parameters of the process. With increasing attention now being paid to the application of on-line real-time process analytics through spectrometry, together with the FDA Process Analytical Technologies (PAT) initiative, the use of spectroscopic information for enhanced monitoring of reactions is gaining impetus. The harmonious integration of process data and spectroscopic data then becomes a major challenge. By integrating the process and spectroscopic measurements for multivariate statistical data modelling and analysis, it is conjectured that improved process understanding and fault diagnosis can be achieved. An investigation into combining process and spectral data using multiblock and multiresolution analysis is proposed and the results from the analysis of experimental data from two industrial application studies are presented to demonstrate the improvements achievable in terms of process performance monitoring and fault diagnosis.Le suivi de la performance des procédés discontinus s'effectue principalementà l'aide de mesures de procédés et les informations obtenues sont associées aux paramètres physiques du procédé. Compte tenu de l'attention de plus en plus grande portée maintenantà l'application des techniques analytiques de procédés en temps réel en continu par la spectrométrie, associéeà l'initiative des technologies analytiques de procédés (PAT) de la FDA, l'utilisation des informations spectroscopiques pour mieux suivre les réactions gagnent du terrain. L'intégration harmonieuse des données de procédés et des données spectroscopiques devient alors un défi majeur. En intégrant les mesures de procédés et de spectroscopie pour la modélisation et l'analyse des données statistiques multivariées, on estime pouvoir mieux comprendre les procédés et mieux diagnostiquer les erreurs. Une recherche pour combiner les données spectrales et de procédés utilisant l'analyse multibloc et multirésolution est proposée et les résultats de l'analyse de données expérimentales issues de deuxétudes d'application industrielle sont présentés afin de démontrer les améliorations réalisables en matière de suivi des performances des procédés et de diagnostic des erreurs.

Despite the fact that enterprises are routinely collecting massive amounts of data from customers, only a relatively small body of knowledge engineering (KE) work has addressed methods and application of KE to the design, development, and maintenance of engineering systems and products. A major challenge when applying KE to such applications is that the data is often unstructured and in the form of text exchanges between the customer and the enterprise.While the importance of modelling domain knowledge in order to produce meaningful results from mining unstructured data has been recognized, most approaches are based primarily on the linguistic structure of the text and keyword taxonomies. These approaches share the common issue that the knowledge extraction results are often not properly structured for solving the engineering problem of interest and, therefore, require manual post-processing before they can be applied. Our hypothesis is that the a priori modelling of the engineering problem of interest is crucial for both (1) efficient (rapid) collection, representation, and structuring of domain knowledge; and (2) the proper integration of domain knowledge with analytical KE methods in order facilitate the extraction of useful knowledge.In order to validate our hypothesis, we apply this approach to the important real-world engineering problem of monitoring the occurrence of product failure modes, and thereby product quality, using customer support cases. In order to translate the free-form text provided by the customer into engineering failure modes we use two methods from engineering design, the Function Analysis System Technique (FAST) and Failure Modes and Effects Analysis (FMEA), to provide the necessary domain knowledge model. This model then drives the collection, representation, and structuring of the failure modes for the product of interest. These failure modes are used as the class labels when applying data mining classification techniques (e.g., Support Vector Machine) to the support case data. The labelled support case data then can be aggregated by failure mode in order to compute a number of failure mode metrics that can be used to monitor product quality. We have demonstrated our approach to monitor the quality of a network security product at a large computer networking company using a data set of 100,000 customer support cases.

No abstract

No abstract