A hierarchical structure based on a Deep LSTM Supervised Autoencoder Neural Network (Deep LSTM-SAE NN) is presented for the detection and classification of faults in industrial plants. The proposed methodology has the ability to classify incipient faults that are difficult to detect and diagnose with traditional and many recent methods. Faults are grouped into different subsets according to the degree of difficulty to classify them accurately in the proposed hierarchical structure. External pseudo-random binary signals (PRBS) are injected in the system to enhance the identification of incipient faults. The approach is illustrated on the benchmark process (Tennessee Eastman Process) in order to compare across different methodologies. The efficacy of the proposed method is shown by a comprehensive comparison between many recent and traditional fault detection and diagnosis methods in the literature for Tennessee Eastman Process. The proposed work results in significant improvements in the classification of faults over both multivariate linear model-based strategies and non-hierarchical nonlinear model-based strategies.

There is a growing interest in continuous processing of the biopharmaceutical industry. However, the technology transfer from traditional batch-based processes is considered a challenge as protocol and tools still remain to be established for their usage at the manufacturing scale. Here, we present a model-based approach to design optimized perfusion cultures of Chinese Hamster Ovary cells using only the knowledge captured during small-scale fed-batch experiments. The novelty of the proposed model lies in the simplicity of its structure. Thanks to the introduction of a new catch-all variable representing a bulk of by-products secreted by the cells during their cultivation, the model was able to successfully predict cellular behavior under different operating modes without changes in its formalism. To our knowledge, this is the first experimentally validated model capable, with a single set of parameters, to capture culture dynamic under different operating modes and at different scales.