Echo State Network Based Soft Sensor for Monitoring and Fault Detection of Industrial Processes

Highlights

• An ESN-based system is developed for fault detection of industrial processes

• The system can attest whether the predictions can be used to replace measurements

• ESNs are used for the first time to detect faults in real assets of O&G industry

• Successful performance, confirmed potential to use at real industry in real time

• Wide anticipation in fault detection, enabling operational and economic gains

Abstract

In this paper a semi-automatic computationally inexpensive system is developed and implemented for monitoring and fault detection of industrial processes. The system uses a soft sensor based on Echo State Networks (ESN) and is able to capture the non-linear dynamic relationships in the process data, making it convenient for real-time monitoring applications. The soft sensor is set to simulate normal operating conditions, so that when the process is governed by other causes, possibly in failure, high residues occur and allow the failure identification. In addition, the system monitors the reliability of the model predictions by tracking the internal states of the ESN dynamic reservoir, indicating whether the model predictions can be used instead of the measured data. The system is successfully applied to the Mackey-Glass Anomaly Benchmark (MGAB) and to the monitoring of critical pieces of equipment of a real oil and gas plant.

Introduction

The management of industrial processes has been carried out in the last decades based mostly on corrective and preventive maintenance programs (CM/PM). These strategies, even though well established in the industrial environment, are quite expensive, since, in most cases, they require the operation to be stopped in order to perform the maintenance tasks, compromising the process availability. With the increasing complexity of the industries in the 21st century, inserted in an ever-growing competitive scenario, where the operation must be clean, safe and of high productivity, more modern and efficient technologies for of industrial assets management must be adopted (Jardine et al., 2006).

This is particularly important for the oil and gas industry, where ecological issues related to global warming and the consequent need in reducing CO₂ emissions, with forecasts showing the increasing replacement of oil by other cleaner energy sources. One can also cite the operational safety issues, in which faults can put both the health of operators and the process itself at risk. Finally, there is a strong geopolitical influence in this sector, which is prevalent in the well-known and cyclical oil crises (Hwang et al., 2018).

To achieve such results, companies are investing in proactive maintenance schemes, through the continuous prognosis of the processes condition, so that the monitoring can provide conditions for decision making about maintenance in a more reasonable time frame, before or as soon as the faults happen (Vachtsevanos et al., 2007; Muller et al., 2008). These strategies are generally referred to as conditional-based monitoring (CBM) and can maximize the useful life of the equipment, reduce maintenance costs, avoiding faults and increasing the operational availability of the process. In this context, digital monitoring tools based on data and machine learning are increasingly occupying the application space in industrial environments. In general, this monitoring approach is based on transforming the data collected by sensors distributed throughout the process into statistical indicators for the integrity of the monitored process (Karpenko et al., 2001; Wang, 2007; Du et al., 2013).

It is common to build monitoring systems based on the use of Non-linear AutoRegressive Moving Average with eXogenous input (NARMAX) models, using delayed inputs to consider the dynamic behavior of the systems, or on recurrent neural networks (RNN), known as universal approximators of dynamic systems (Funahashi & Nakamura, 1993; Du et al., 2013). However, the use of RNN in real-time applications is often hampered by training methods, based on gradient descent, generally implemented as backpropagation-through-time technique (BPTT) (Werbos, 1990), which presents very slow convergence features and no guaranteed global convergence, suffering from the known problems of bifurcations (Vega et al., 2008) and vanishing gradient (Hochreiter, 1998).

Reservoir Computing (RC), when only the output layer is fitted, with the internal synaptic weights of the network model being selected at random, was developed to overcome these training problems (Lukoševičius & Jaeger, 2009). A particular type of RC, the Echo State Networks (ESN) (Jaeger, 2001) have become popular due to its the ability to capture the dynamic relationships among the data with closed solutions for training, making them simpler and computationally cheaper than traditional RNN (Antonelo et al., 2017; Jordanou et al. 2019; Dias et al., 2019).

As usual with other types of neural networks, the major limitation on the use of ESN is the lack of methods to select the large number of hyperparameters. The most used methods for adjustment of hyperparameters (Grid Search and Random Search) suffer with the multidimensionality of the search space and often provide models with poor fit quality, generated without the appropriate selection of the hyperparameters, discouraging the application of ESN to solve real-world problems (Jaeger, 2005; Behar et al., 2013).

Some works published in different areas proposed the use of ESNs for monitoring and fault detection. Nevertheless, this area is still incipient, as most of these works have not been implemented in real world industrial environments, using synthetic data or controlled data collected in pilot experimental units. For example, Morando et al. (2013, 2015) used ESNs to create a fuel cell aging model, while Fan et al. (2016) used ESNs to predict faults in air compressor equipment based on synthetic data. Xie & Zhang (2017) applied ESNs for fault detection in rotating machinery and showed that the technique was quite robust and can provide good results even when the available data set is small. Particularly, Ribeiro et al. (2018) applied ESNs to detect leaks from a pilot unit piping. More recently, ESNs were used to monitor the performances of wind turbine gearboxes (Wu et al., 2019) and the transmission condition of 3D printers (Zhang et al., 2019).

In the scenario of chemical and petrochemical industries, the implemented CBM generally uses more traditional techniques, such as Principal Component Analysis (PCA) and Canonical Correlate Analysis (CCA) (Thorsen & Dalva, 1995; Ly et al., 2009).

Particularly, the use of ESNs in this industrial segment is even more incipient. These applications involve the use of ESN models to compose predictive control structures or to predict some relevant output variable of the process, which frequently cannot be measured regularly in line due to the aggressiveness of the environment or even the inexistence of appropriate sensors. Antonelo et al. (2017) used ESN models to estimate the downhole pressure using real data obtained from sensors available in an operating oil well. The measurements of this pressure are useful to map regions of instability (slugging) in the oil lift process. Jordanou et al. (2019) employed an online adaptive controller based on ESNs in diverse scenarios for control of an oil production platform. As a matter of fact, ESN models proved useful for derivation of model-based control laws, having been used effectively for control of complex dynamic systems. For instance, Dias et al. (2019) showed that ESN models are able to model the gas lift process in oil wells very closely and reported the use of ESNs as the internal models of predictive controllers that were able to deal with measurement noise, unmeasured disturbances and complex dynamic transitions. However, it must be emphasized that, to the best of our knowledge, published reports have not described the used of ESN models for purposes of monitoring and fault detection in chemical processes using real data.

Based on the previous paragraphs, in the present manuscript an ESN-based system is developed and implemented for process monitoring and fault detection, and some characteristics and relative advantages of using these models are discussed. The system uses known procedures for data cleaning, variable and hyperparameters selection to build ESN models that are employed as soft sensors to describe and monitor the regular operation of the analyzed process. For the hyperparameters selection, the Tree Parzen Estimator (TPE) (Bergstra et al., 2011) is used, which is a Bayesian-inspired sequential optimization method that reduces the amount of objective function evaluations in order to reduce the computational effort of the method, making real-time implementations possible.

Based on the formulation of the soft sensors, the proposed methodology, in addition to monitoring and detecting faults, also monitors the reliability of the model predictions, attesting, for example, whether the data predicted by the model in a faulty situation can be used to replace the measured data. In order to do that, the internal states of the ESN reservoir are tracked, so that the modification of the internal state values provides valuable information about the occurrence of process changes while the stability of the internal state values provides information about the reliability of the operation. Additionally, tracking of internal state values also provides indications about the need to retrain the model, which can be very important since the complex and real industrial processes tend to evolve naturally to other operational conditions, without necessarily indicating a fault behavior, either due to aging of equipment or changes in the quality of raw materials, among many other possible reasons (Kruger & Xie, 2012).

The proposed monitoring system is initially tested with synthetic time series datasets generated by the Mackey-Glass Equation (Mackey & Glass, 1977), which is a widely used benchmark in the field of nonlinear dynamic analysis, more specifically in time series forecasting, being especially used in the context of ESNs (Jaeger & Haas, 2004; Wang & Yan, 2015; Løkse et al., 2017; Liu & Zhang, 2020). In addition, ESNs are used here for the first time to detect faults in real assets of the oil and gas industry, monitoring the operation conditions of equipment installed in a plant of Petrobras (Petróleo Brasileiro S.A.). As described in previous studies (Clavijo et al., 2019, 2021), the monitored pieces of equipment are key components of an oil and gas fiscal metering station and are indeed very important, because the measurements they provide are related to allocation and custody transfer of product streams of the platform.

The proposed methodology is presented in Section 2, as well as the ESN structure and TPE Optimization procedure, which are the key parts of the proposed monitoring procedure. In addition, the monitored systems, MGAB model and Fiscal Metering Station are presented in detail. The obtained monitoring results are discussed in Section 3, while the conclusions are presented in Section 4.