Ensemble deep relevant learning framework for semi-supervised soft sensor modeling of industrial processes

An evolutionary deep learning soft sensor model based on random forest feature selection technique for penicillin fermentation process

Accurate and reliable measurement of key biological parameters during penicillin fermentation is of great significance for improving penicillin production. In this research context, a new hybrid soft sensor model method based on RF-IHHO-LSTM (random forest-improved​ Harris hawks optimization-long short-term memory) is proposed for penicillin fermentation processes. Firstly, random forest (RF) is used for feature selection of the auxiliary variables for penicillin. Next, improvements are made for the Harris hawks optimization (HHO) algorithm, including using elite opposition-based learning strategy (EOBL) in initialization to enhance the population diversity, and using golden sine algorithm (Gold-SA) in the search strategy to make the algorithm accelerate convergence. Then the long short-term memory (LSTM) network is constructed to build a soft sensor model of penicillin fermentation processes. Finally, the hybrid soft sensor model is used to the Pensim platform in simulation experimental research. The simulation test results show that the established soft sensor model, with high accuracy of measurement and good effect, can meet the actual requirements of engineering.

A Data-Driven Semi-Supervised Soft-Sensor Method: Application on an Industrial Cracking Furnace

The cracking furnace is the key equipment of the ethylene unit. Coking in furnace tubes results from the generation of coke during cracking, which will compromise the heat transfer efficiency and lead to shape change of tubes. In order to keep the cracking furnace operating economically and safely, the engineers need to decoke according to the surface temperature of the furnace tube. However, the surface temperature of the furnace tube is difficult to obtain in practice. Due to redundant instrumentation and the high level of process control in cracking furnaces, a large number of operation data have been collected, which makes it possible to predict the surface temperature of furnace tubes based on autocorrelation and cross correlation within and among variables. Traditional prediction methods rely on labeled data samples for training, ignoring the process information contained in a vast amount of unlabeled data. In this work, a data-driven semi-supervised soft-sensor method is proposed. Considering the nonlinear and dynamic relationship among variables, long short-term memory network (LSTM) autoencoder (AE), a deep neural network suitable for the feature extraction of long-term nonlinear series, is used for pre-training to extract process data features from unlabeled and labeled data. Then, principal component analysis (PCA) and mutual information (MI) are applied to remove feature correlation and select features related to target variables, respectively. Finally, the selected data features are utilized to establish a soft-sensor model based on artificial neural network (ANN). Data from an industrial cracking furnace of an ethylene unit is considered to validate the performance of the proposed method. The results show that the prediction error of furnace tube surface temperature is about 1% and successfully aid engineers in determining the optimal time for decoking.

Pseudo-Labeling Optimization Based Ensemble Semi-Supervised Soft Sensor in the Process Industry

Nowadays, soft sensor techniques have become promising solutions for enabling real-time estimation of difficult-to-measure quality variables in industrial processes. However, labeled data are often scarce in many real-world applications, which poses a significant challenge when building accurate soft sensor models. Therefore, this paper proposes a novel semi-supervised soft sensor method, referred to as ensemble semi-supervised negative correlation learning extreme learning machine (EnSSNCLELM), for industrial processes with limited labeled data. First, an improved supervised regression algorithm called NCLELM is developed, by integrating the philosophy of negative correlation learning into extreme learning machine (ELM). Then, with NCLELM as the base learning technique, a multi-learner pseudo-labeling optimization approach is proposed, by converting the estimation of pseudo labels as an explicit optimization problem, in order to obtain high-confidence pseudo-labeled data. Furthermore, a set of diverse semi-supervised NCLELM models (SSNCLELM) are developed from different enlarged labeled sets, which are obtained by combining the labeled and pseudo-labeled training data. Finally, those SSNCLELM models whose prediction accuracies were not worse than their supervised counterparts were combined using a stacking strategy. The proposed method can not only exploit both labeled and unlabeled data, but also combine the merits of semi-supervised and ensemble learning paradigms, thereby providing superior predictions over traditional supervised and semi-supervised soft sensor methods. The effectiveness and superiority of the proposed method were demonstrated through two chemical applications.