Predictive maintenance is a topic that has been researched and theorized for decades. With the advent of Industry 4.0 and greater technological capabilities in the form of advanced AI, the concept of predicting the need for maintenance in a system or its components is quickly becoming more of a reality for complex processes. The possibility of estimating remaining useful lifetimes would help businesses with maintenance scheduling to avoid unnecessary maintenance actions, but also process failures. Predicting when maintenance is needed would ensure system or component reparation or replacement before they are degraded to the point of negative product quality impact and production losses. While there are many studies on predictive maintenance and how it can be implemented and used in continuous processes, the research on complex batch processes is minimal. Therefore, this thesis aims to construct a framework based on literature for implementing predictive maintenance in batch processes. Parts of the framework are then applied and validated on a complex batch process in the form of sintering at Seco Tools AB. Recommendations are given on how to implement predictive maintenance and what is required in the company’s specific case based on the sintering process’ agreement with the framework. The framework consists of two main parts with several underlying requirements: Data collection and pre-processing and Predictive models. Evaluating the sintering process based on these requirements reveals that many parts of the framework are already in place or possible to implement, while other areas are lacking. There is a need for data cleaning and data related to component health and issues, while the amount of specific parameter data on temperatures, pressures, and similar variables is large. It is possible to predict these parameters accurately through building, training, and validating linear regression models. These predictions can be used as inputs in future models to predict the Remaining Useful Life (RUL) of components or the entire system. Due to the inherent complexity of the sintering process and similar industrial manufacturing processes, which involve numerous interdependent variables affecting product quality and component health, it is imperative to develop machine learning models and neural networks for future predictive maintenance algorithms. Moreover, as highlighted in this thesis, the attainment of predictive maintenance in an industrial environment necessitates prioritizing augmented data collection on component conditions, investing in hardware to bolster computational power, and acquiring the essential expertise to design and implement tailored predictive maintenance algorithms for dedicated manufacturing processes.

This thesis focuses on data-driven modeling and control of batch and batch-like processes. These processes are highly nonlinear and time-varying which, unlike continuous operations, are characterized by the finite duration of operation and absence of equilibrium conditions. This makes the modeling and control approaches available for continuous processes not readily applicable and requires appropriate adaptations of the available approaches to handle a) batch data structure for modeling and b) a control objective different than that of maintaining a steady-state operation as often encountered in a continuous process. With these considerations, this work adapted the batch subspace identification for modeling and control of a variety of batch and batch-like processes. A particular focus of this work was on the application of the proposed ideas on real engineering systems along with simulated case studies. The applications considered in this work are batch crystallization, a hydrogen plant startup dynamics in a collaboration with Praxair Inc. and a rotational molding process in collaboration with the polymer research group at McMaster University. For the seeded batch crystallization process, subspace identification techniques are adapted to identify a linear time invariant model for the, otherwise, infinite dimensional process. The identified model is then deployed in a linear model predictive control (MPC) strategy to achieve crystal size distribution (CSD) with desired characteristics subject to both manipulated input and product quality constraints. The proposed MPC is shown to achieve superior performance and the ability to respect tighter product quality constraints as well as robustness to uncertainty in comparison to an open loop policy as well as a traditional trajectory tracking policy using classical control. In another contribution, merits of handling data variety in a subspace identification framework was demonstrated on the crystallization process. The proposed approach facilitates the specification of a desired shape of the particle size distribution required at the termination of the batch process. Further, novel model validity constraints are proposed for the subspace identification based control framework. In the collaborative work on hydrogen plant startup, it is recognized as a batch-like process due to its similarity to batch processes. Firstly, in this work a high fidelity model of the Hydrogen unit was developed with relevant startup and shutdown mechanisms. This setup is used to mimic the trends in the key process variables during the startup/shutdown operation. The simulated data is used to identify a state-space model of the process and validated on new simulated startup. Further, the approach was demonstrated on real plant data from one of the Praxair's plants. The predictive capabilities of the model provide ample handle for the plant operator for averting failures and abrupt shutdown of the entire plant. This is expected to have immense economic advantages. Finally, the subspace identification based modeling and control approach was applied to a lab-scale rotational modeling (RM) process. It is a polymer processing technique that is characterized by the placement of a polymer resin inside a mold, subsequent closure of the mold, followed by the simultaneous application of uni-axial (as is the case in the present work) or bi-axial rotation and heat. The resin is deposited on the mold wall where it forms a dense unified layer following which, the mold is cooled while still rotating the mold. Once demolding temperatures are achieved, the finished part is removed from the mold. Its potential as a manufacturing process for polymeric components is limited by a number of concerns including difficulties in process control, in particular, determining efficiently the process operation to yield the desired product consistently, and produce new products. This work has contributed by developing optimal control strategies for the process to achieve user-specified product quality and reject variability across batches. The results obtained demonstrate the merits of the proposed approach. / Thesis / Doctor of Philosophy (PhD)

A presente tese apresenta proposições para o uso da seleção de variáveis no aprimoramento do controle estatístico de processos multivariados (MSPC) em bateladas, a fim de contribuir com a melhoria da qualidade de processos industriais. Dessa forma, os objetivos desta tese são: (i) identificar as limitações encontradas pelos métodos MSPC no monitoramento de processos industriais; (ii) entender como métodos de seleção de variáveis são integrados para promover a melhoria do monitoramento de processos de elevada dimensionalidade; (iii) discutir sobre métodos para alinhamento e sincronização de bateladas aplicados a processos com diferentes durações; (iv) definir o método de alinhamento e sincronização mais adequado para o tratamento de dados de bateladas, visando aprimorar a construção do modelo de monitoramento na Fase I do controle estatístico de processo; (v) propor a seleção de variáveis, com propósito de classificação, prévia à construção das cartas de controle multivariadas (CCM) baseadas na análise de componentes principais (PCA) para monitorar um processo em bateladas; e (vi) validar o desempenho de detecção de falhas da carta de controle multivariada proposta em comparação às cartas tradicionais e baseadas em PCA. O desempenho do método proposto foi avaliado mediante aplicação em um estudo de caso com dados reais de um processo industrial alimentício. Os resultados obtidos demonstraram que a realização de uma seleção de variáveis prévia à construção das CCM contribuiu para reduzir eficientemente o número de variáveis a serem analisadas e superar as limitações encontradas na detecção de falhas quando bancos de elevada dimensionalidade são monitorados. Conclui-se que, ao possibilitar que CCM, amplamente utilizadas no meio industrial, sejam adequadas para banco de dados reais de elevada dimensionalidade, o método proposto agrega inovação à área de monitoramento de processos em bateladas e contribui para a geração de produtos de elevado padrão de qualidade. / This dissertation presents propositions for the use of variable selection in the improvement of multivariate statistical process control (MSPC) of batch processes, in order to contribute to the enhacement of industrial processes’ quality. There are six objectives: (i) identify MSPC limitations in industrial processes monitoring; (ii) understand how methods of variable selection are used to improve high dimensional processes monitoring; (iii) discuss about methods for alignment and synchronization of batches with different durations; (iv) define the most adequate alignment and synchronization method for batch data treatment, aiming to improve Phase I of process monitoring; (v) propose variable selection for classification prior to establishing multivariate control charts (MCC) based on principal component analysis (PCA) to monitor a batch process; and (vi) validate fault detection performance of the proposed MCC in comparison with traditional PCA-based and charts. The performance of the proposed method was evaluated in a case study using real data from an industrial food process. Results showed that performing variable selection prior to establishing MCC contributed to efficiently reduce the number of variables and overcome limitations found in fault detection when high dimensional datasets are monitored. We conclude that by improving control charts widely used in industry to accomodate high dimensional datasets the proposed method adds innovation to the area of batch process monitoring and contributes to the generation of high quality standard products.

In order to meet tight product quality specifications for chemical batch processes, it is vital to monitor and control product quality throughout the batch duration. However, the frequent lack of in situ sensors for continuous monitoring of batch product quality complicates the control problem and calls for novel control approaches. This thesis focuses on the study and application of multivariate statistical methods to control product quality in chemical batch processes. These multivariate statistical methods can be used to identify data-driven prediction models that can be integrated within a model predictive control (MPC) framework. The ideal MPC control strategy achieves end-product quality specifications by performing trajectory tracking during the batch operating time. However, due to the lack of in-situ sensors, measurements of product quality are usually obtained by laboratory assays and are, therefore, inherently intermittent. This thesis proposes a new approach to realise trajectory tracking control of batch product quality in those situations where only intermittent measurements are available. The scope of this methodology consists of: 1) the identification of a partial least squares (PLS) model that works as an estimator of product quality, 2) the transformation of the PLS model into a recursive formulation utilising a moving window technique, and 3) the incorporation of the recursive PLS model as a predictor into a standard MPC framework for tracking the desired trajectory of batch product quality. The structure of the recursive PLS model allows a straightforward incorporation of process constraints in the optimisation process. Additionally, a method to incorporate a nonlinear inner relation within the proposed PLS recursive model is introduced. This nonlinear inner relation is a combination of feedforward artificial neural networks (ANNs) and linear regression. Nonlinear models based on this method can predict product quality of highly nonlinear batch processes and can, therefore, be used within an MPC framework to control such processes. The use of linear regression in addition to ANNs within the PLS model reduces the risk of overfitting and also reduces the computational e↵ort of the optimisation carried out by the controller. The benefits of the proposed modelling and control methods are demonstrated using a number of simulated batch processes.

Yes / The need for the development of clean but still profitable processes and the study of low environmental impact and economically convenient management policies for them are two challenges for the years to come. This paper tries to give a first answer to the second of these needs, limited to the area of discontinuous productions. It deals with the development of a robust methodology for the profitable and clean management of (fed-)batch units under uncertainty, which can be referred to as a robust sustainability-oriented model-based optimization & control strategy. This procedure is specifically designed to ensure elevated process performances along with low-cost utilities usage reduction in real-time, simultaneously allowing for the effect of any external perturbation. In this way, conventional offline methods for process sustainable optimization can be easily overcome since the most suitable management policy, aimed at process sustainability, can be dynamically determined and applied in any operating condition. This leads to a significant step forward with respect to the nowadays options in terms of sustainable process management, that drives towards a cleaner and more energy-efficient future. The proposed theoretical framework is validated and tested on a case study based on the well-known fed-batch version of the Williams-Otto process to demonstrate its tangible benefits. The results achieved in this case study are promising and show that the framework is very effective in case of typical process operation while it is partially effective in case of unusual/unlikely critical process disturbances. Future works will go towards the removal of this weakness and further improvement in the algorithm robustness.