Soft Sensor Development Based on Quality-Relevant Slow Feature Analysis and Bayesian Regression with Application to Propylene Polymerization

Data-driven soft sensors are widely used to predict quality indices in propylene polymerization processes to improve the availability of measurements and efficiency. To deal with the nonlinearity and dynamics in propylene polymerization processes, a novel soft sensor based on quality-relevant slow feature analysis and Bayesian regression is proposed in this paper. The proposed method can handle the dynamics of the process better by extracting quality-relevant slow features, which present both the slowly varying characteristic and the correlations with quality indices. Meanwhile, a Bayesian inference model is developed to predict the quality indices, which takes advantages of a probability framework with iterative maximum likelihood techniques for parameter estimation and a sparse constraint for avoiding overfitting. Finally, a case study is conducted with data sampled from a practical industrial propylene polymerization process to demonstrate the effectiveness and superiority of the proposed method.

Monitoring of Biopolymer Production Process Using Soft Sensors Based on Off-Gas Composition Analysis and Capacitance Measurement

This paper focuses on the design of soft sensors for on-line monitoring of the biotechnological process of biopolymer production, in which biopolymers are accumulated in bacteria as an intracellular energy storage material. The proposed soft sensors for on-line estimation of the biopolymer concentration represent an interesting alternative to the traditional off-line analytical techniques of limited applicability for real-time process control. Due to the complexity of biochemical reactions, which make it difficult to create reasonably complex first-principle mathematical models, a data-driven approach to the design of soft sensors has been chosen in the presented study. Thus, regression methods were used in this design, including multivariate statistical methods (PLS, PCR). This approach enabled the creation of soft sensors using historical process data from fed-batch cultivations of the Pseudomonas putida KT2442 strain used for the production of medium-chain-length polyhydroxyalkanoates (mcl-PHAs). Specifically, data from on-line measurements of off-gas composition analysis and culture medium capacitance were used as input to the soft sensors. The resulting soft sensors allow not only on-line estimation of the biopolymer concentration, but also the concentration of the cell biomass of the production bacterial culture. For most of these soft sensors, the estimation error did not exceed 5% of the measurement range. In addition, soft sensors based on capacitance measurement were able to accurately detect the end of the production phase. This study thus offers an innovative and practically relevant contribution to the field of monitoring of bioprocesses used for the production of medium-chain-length biopolymers.

Cyber-Physical LPG Debutanizer Distillation Columns: Machine-Learning-Based Soft Sensors for Product Quality Monitoring

Refineries execute a series of interlinked processes, where the product of one unit serves as the input to another process. Potential failures within these processes affect the quality of the end products, operational efficiency, and revenue of the entire refinery. In this context, implementation of a real-time cognitive module, referring to predictive machine learning models, enables the provision of equipment state monitoring services and the generation of decision-making for equipment operations. In this paper, we propose two machine learning models: (1) to forecast the amount of pentane (C5) content in the final product mixture; (2) to identify if C5 content exceeds the specification thresholds for the final product quality. We validate our approach using a use case from a real-world refinery. In addition, we develop a visualization to assess which features are considered most important during feature selection, and later by the machine learning models. Finally, we provide insights on the sensor values in the dataset, which help to identify the operational conditions for using such machine learning models.

Expert Advisory System for Production Surveillance and Optimization Assisted by Artificial Intelligence

Petroleum Engineers are usually responsible for 50-200 wells. The wells in highly instrumented fields generate 10-20 measurements every few seconds. This makes it difficult to be on top of every well, every day. This challenge carries a significant opportunity cost, therefore the surveillance process requires automation by implementing surveillance-by-exception. Faster identification of problems is great, but not enough unless the required activities are executed in a timely manner. The ability to execute quickly and safely requires a well-structured coordination effort between the different disciplines involved in field operations. In line with ADNOC Digital Transformation strategy, the solution described in this paper intends to couple surveillance by exception (a Petroleum Engineering workflow) with field operations execution (a multi-disciplinary set of workflows in the field). The integration is achieved by creating a simple yet robust action tracking system, and feeding it automatically with new opportunities, so that it is kept up to date. Automatic diagnosis becomes opportunities. Opportunities become activities. Activities are assigned, executed and closed. All activities are tracked on a high level, which provides insights and visibility to all parties on who is doing what, when and how to close the opportunity. The surveillance by exception engine consumes real time measurements from the historian. It then runs a set of soft sensors using full physics, reduced order models, proxy and data driven machine learning models, which utilize most of the measurements. The measured and calculated values are then fed to an expert system, which automatically diagnoses the wells and creates tickets with recommendations to the production engineer. The engineer reviews the ticket and forwards to field operations for execution. The log of activities enables a direct measure of operational effectiveness. This paper describes the philosophy of the system, how it works, lessons learned and the results of implementation across 6 oilfields and 600+ wells in Abu Dhabi.