Industrial Monitoring Research Articles

Compact optical fiber photoacoustic gas sensor with integrated multi-pass cell

Optical fiber acoustic sensors with miniature size and high sensitivity are attractive to develop compact photoacoustic spectroscopy. Here, a compact photoacoustic gas sensor was demonstrated by utilizing a diaphragm-based fiber-optic Fabry-Perot cavity as both the acoustic sensor and the multipass cell. A nanoscale graphite film was used as the flexible diaphragm to increase the acoustic sensitivity of the Fabry-Perot cavity and the cavity inner surface was coated with highly-reflective Au film to form a multipass cell for amplification of the photoacoustic signal. With a laser power of 20 mW at 1532.8 nm, the sensor demonstrated a low detection limit of ∼ 50 ppb for C2H2 gas with an integration time of ∼ 100 s. The optical fiber photoacoustic gas sensor with a millimeter-scale diameter and ppb-level detection limit is promising for trace gas sensing in various areas including industrial process and environmental monitoring.

Understanding catalysts by time-/space-resolved operando methodologies

Heterogeneous catalysis has a central position in our everyday life and it is gaining importance with the changes in our economic model and with the progress of the energetic transition. New generation of catalysts are based on rational design, which is the fruit of thorough investigations in relevant conditions. Operando spectroscopy is the key to obtain the right information to understand the behavior of a catalytic material, as well as to unravel the reaction steps of a process. In the present contribution we have reviewed some of the most representative papers in the domain, focusing on energy-related investigations and on two extremely important aspects such as time and space resolution. We provide our point of view about the different methods and techniques, the shared vision about similarities in catalytic processes, as well as an opinion about the perspectives for future developments, notably in the field of industrial process monitoring.

Digital twins-based process monitoring for wastewater treatment processes

Digital twins are a significant way to achieve fault detection of various smart manufacturing, which provide a new paradigm for complex industrial process monitoring. Wastewater treatment processes play a crucial role in water recycling, its failures may cause risks of adverse environmental impacts. This paper studies the digital twins fault detection framework based on the convolutional autoencoder for wastewater treatment processes monitoring. The designed digital twins fault detection framework can simulate the sludge bulking failure and the toxic impact failure conditions in the virtual space to construct the simulation data with continuous updating through wastewater data. The simulation data is divided into rate of change information sub-block, original sub-block, and cumulative information sub-block using the multi-block modeling strategy to fully explore the hidden information. Further, the sliding window method is utilized to resample the reconstructed sub-blocks to enhance the effects of the detection performance. Bayesian fusion is adopted, and the final decision is made based on the fused statistical value and the control limit. The comparison experiments tested on the digital twins fault detection framework demonstrate the superiority and feasibility of detection performance.

Mechanistic block‐based attention mechanism stacked autoencoder for describing typical unit connection industrial processes and their monitoring

AbstractThe overall information of a process can be obtained through global modelling, and the local information is easily ignored in the research of the industrial process monitoring of unit connection. Thus, finding the global type of faults is easy, but occurs at the expense of drowning out the local faults. The use of block modelling can highlight local information, thereby improving local fault detection capability. However, the connection information between blocks is usually ignored in block modelling, which makes finding fault classes that only affect the connection relationship between blocks difficult. A mechanistic block‐based attention mechanism stacked autoencoder (MB‐AMSAE) monitoring method is proposed in this paper. The industrial process is divided into several parts in accordance with its mechanistic relationships, and each part represents an independent block. Self‐attention is used to focus on the information of each block itself. Cross‐attention is adopted to focus on the information between blocks, and this information is fused to form new blocks. The new block is used as the feature of the original block, and the original block is reconstructed by using a stacked autoencoder. The corresponding control limit is obtained in accordance with the reconstruction ability of normal samples, and whether the working conditions are normal is judged according to the control limit. The proposed algorithm is used in numerical simulation, Tennessee‐Eastman processes, and is compared with other advanced algorithms based on its fault detection capability. Results show the effectiveness of the MB‐AMSAE algorithm in process monitoring.

Highly sensitive surface plasmon resonance sensor with surface modified MoSe2/ZnO composite film for non-enzymatic glucose detection

The rapid and accurate assessment of glucose concentration has been demonstrated to play a significant role in human health, such as the diagnosis and treatment of diabetes, pharmaceutical research and quality monitoring in the food industry, necessitating further development of the performance for glucose sensor especially at low concentrations. However, glucose oxidase-based sensors suffer from crucial restriction in bioactivity because of their poor environmental tolerance. Recently, catalytic nanomaterials with enzyme-mimicking activity, known as nanozymes, have gained considerable interest to overcome the drawback. In this scenario, we report an inspiring surface plasmon resonance (SPR) sensor for non-enzymatic glucose detection employing ZnO nanoparticles and MoSe2 nanosheets composite (MoSe2/ZnO) as sensing film, featuring desirable advantages of high sensitivity and selectivity, lab-free and low cost. The ZnO was used to specifically recognize and bind glucose, and further signal amplification was realized by incorporating of MoSe2 owing to its larger specific surface area and favorable bio-compatibility, as well as high electron mobility. These unique features of MoSe2/ZnO composite film result in an obvious improvement of sensitivity for glucose detection. Experimental results show that the measurement sensitivity of the proposed sensor could reach 72.17 nm/(mg/mL) and a detection limit of 4.16 μg/mL by appropriately optimizing the componential constitutions of MoSe2/ZnO composite. In addition, the favorable selectivity, repeatability and stability are demonstrated as well. This facile and cost-effective work provides a novel strategy for constructing high-performance SPR sensor for glucose detection and a prospective application in biomedicine and human health monitoring.

Dynamic reconstruction principal component analysis for process monitoring and fault detection in the cold rolling industry

An improved method for process monitoring and fault detection called dynamic reconstruction principal component analysis (DRPCA) is proposed. By extracting direct dynamic connections between samples, DRPCA utilizes the overall dynamic information of the training data set and improves the monitoring performance of dynamic industrial processes. In DRPCA, the optimal orthogonal transformation is used to reconstruct the past sub-matrix with the current sub-matrix. The reconstructed increment matrix preserves the raw data’s basic, incremental, and dynamic information as much as possible. In addition to the traditional T-squared and SPE statistics, a new statistic SPE-R is proposed for DRPCA based on the reconstruction accuracy. We evaluate the performance of the proposed method on a cold rolling mill system, and the results show that DRPCA outperforms DPCA and its improved versions in terms of faster computation speed, more timely alerts, higher detection rates, and lower false alarm rates. Our study demonstrates that DRPCA is a superior method for monitoring dynamic processes.

Information-Driven Gas Distribution Mapping for Autonomous Mobile Robots

The ability to sense airborne pollutants with mobile robots provides a valuable asset for domains such as industrial safety and environmental monitoring. Oftentimes, this involves detecting how certain gases are spread out in the environment, commonly referred to as a gas distribution map, to subsequently take actions that depend on the collected information. Since the majority of gas transducers require physical contact with the analyte to sense it, the generation of such a map usually involves slow and laborious data collection from all key locations. In this regard, this paper proposes an efficient exploration algorithm for 2D gas distribution mapping with an autonomous mobile robot. Our proposal combines a Gaussian Markov random field estimator based on gas and wind flow measurements, devised for very sparse sample sizes and indoor environments, with a partially observable Markov decision process to close the robot’s control loop. The advantage of this approach is that the gas map is not only continuously updated, but can also be leveraged to choose the next location based on how much information it provides. The exploration consequently adapts to how the gas is distributed during run time, leading to an efficient sampling path and, in turn, a complete gas map with a relatively low number of measurements. Furthermore, it also accounts for wind currents in the environment, which improves the reliability of the final gas map even in the presence of obstacles or when the gas distribution diverges from an ideal gas plume. Finally, we report various simulation experiments to evaluate our proposal against a computer-generated fluid dynamics ground truth, as well as physical experiments in a wind tunnel.

Temporal dependence Mahalanobis distance for anomaly detection in multivariate spacecraft telemetry series

Spacecraft telemetry data are real-time data as the only basis for ground operation station and management system to judge the working performance and health status of spacecrafts in orbit. Telemetry data are high dimension, strong-dependent, and pseudo-periodic series, which bring great challenges to traditional anomaly detection methods of multivariate parameters. In this case, with the advantages of strong feature extraction and space injection ability, Mahalanobis distance (MD)-based approach has been a strong foundation for industrial system health monitoring. However, the typical MD-based method performs anomaly detection with a fixed threshold for MD series without capturing temporal evolution which cause high false alarms or missing alarms for complex abnormal modes. In this work, the temporal dependence Mahalanobis distance (TDMD) is realized based on multi-factors prediction which can effectively detect contextual and collective anomalies in multivariate telemetry series. Upper and lower limits with time series correlation and dynamic characteristics for the MD of each arriving multivariate point are constructed for online testing. Adequate experiments on simulated and real telemetry series verify the effectiveness and applicability of the proposed method.

A Simple Framework to Generalized Zero-Shot Learning for Fault Diagnosis of Industrial Processes

Dear Editor, This letter provides a simple framework to generalized zero-shot learning for fault diagnosis. For industrial process monitoring, supervised learning and zero-shot learning (ZSL) can only deal with seen and unseen faults, respectively. However, in the online monitoring stage of the actual industrial process, both seen and unseen faults may occur. This makes supervised learning and zero-shot learning impractical in industrial process monitoring. Generalized zero-shot learning (GZSL) can handle this problem, but its implementation process is too complicated. This letter introduces GZSL into industrial process fault diagnosis, and a simple end-to-end framework is provided to implement GZSL-based fault diagnosis. In this framework, GZSL-based fault diagnosis can be realized by using only a binary classification algorithm. Experimental results show that the proposed framework can accomplish this challenging task of GZSL for fault diagnosis.

A quartz crystal microbalance (QCM)-based easy setup device for real-time mass change detection under high-power RF plasma.

Sensing technologies serve a crucial role in monitoring and testing surface properties in biosensors, thin films, and many other industries. Plasma treatments are routinely used in most of these technologies to modify the surfaces of materials. However, due to the high radio frequency (RF) noise in plasma processes, real-time surface tracking is still rather difficult. In this study, we aim to construct an easy-to-set up mass change detection system capable of operating under RF plasma conditions. For this purpose, we have presented a novel technique that utilizes the quartz crystal microbalance sensor to detect mass changes in different plasma environments. The constructed device was then tested under 13.56MHz, 100W plasma atmosphere. The results showed that the resonance frequency of a crystal was successfully measured with 1.0Hz resolution under the impact of plasma-induced high power of RF noise. Moreover, as a preliminary study, we used ethylenediamine (EDA) to track changes in resonance frequency under plasma conditions and observed noise-free signals in frequency-voltage curves. Furthermore, the system's sensitivity was found to be 3.8 ng/Hz, with a test molecule (EDA) deposition of about 380 ng in the RF plasma atmosphere. Overall, this study focused on creating a relatively new approach for detecting the real-time mass change in a strong RF environment, which we believe could be an improved and easy-to-set up technique for plasma-based processes such as surface coating, etching, and activation.

Unsupervised Extraction of Shape-Based Signal Patterns for Incoming Signal Recognition

Coming up with a method to extract meaningful information from sensor signals without prior knowledge is one of the important challenges in machine learning. In the context of this challenge, this paper develops an unsupervised method to extract high-intensity shape-based signal patterns collected by a spintronic sensor for industrial machine condition monitoring. For this purpose, this paper first proposes a feature extraction method inspired by both shapelet transform and wavelet transform. The feature extraction method first extracts unsupervised shapelets, which are then treated as mother wavelets or filters to decompose the signals into their components. In addition, an idea based on the signal symbolic representation is proposed in order to extract signal patterns of various lengths. The signals are summarized with symbols obtained by finding a high-quality clustering result using an internal clustering validation criterion, which makes it suitable for further data mining tasks using far fewer memory resources. Finally, the signal patterns or symbols extracted from recorded data are then used for real-time signal recognition by a measure proposed to compute the similarity of the incoming signal with all the existing symbols. The performance and efficiency of our approach are demonstrated using real datasets.

TC-GATN: Temporal Causal Graph Attention Networks With Nonlinear Paradigm for Multivariate Time-Series Forecasting in Industrial Processes

Multivariate time series (MTS) forecasting plays an important role in industrial process monitoring, control and optimizations. Usually, hierarchical interactive behaviors among industrial MTS have formed complex nonlinear causal characteristics, which greatly hinders the applications of existing predictive models. It is found that graph attention networks (GAT) provide technical ideas to meet this challenge. However, the unknown directed graph and linear conversions of node information make conventional GAT less popular for the industrial fields. In this paper, we propose a novel prediction model termed as temporal causal graph attention networks with nonlinear paradigms (TC-GATN) to adequately capture inherent dependencies on industrial MTS. Specifically, the graph learning algorithm concerning the granger causality (GC) is exploited to extract potential relationships among multiple variables for guiding directional edge connections of the hierarchy. Then, parallel GRU encoders located in the graph neighborhood space are introduced to perform the nonlinear interaction of node features, which accomplishes the adaptive transformation and transmission. The self-attention mechanism is further employed to aggregate encoder hidden states across all stages. Finally, a temporal module is supplemented to process information from the graph layer, achieving satisfactory predictions. The feasibility and effectiveness of the TC-GATN are validated by two actual datasets from the methanol production and the chlorosilane distillation.

Physics-Informed Time-Aware Neural Networks for Industrial Nonintrusive Load Monitoring

Nonintrusive load monitoring enables the situational awareness of appliance-level energy consumption without installing appliance-specific sensors. It has been researched for over thirty years, with deep learning methods being the state-of-the-art solutions. However, current works mainly focus on the residential scenario, and industrial load disaggregation as a more challenging problem from the appliance type perspective is much less investigated. Nevertheless, industrial loads play an important role in energy savings and climate change mitigation and adaptation. Therefore, this paper focuses on the industrial nonintrusive load monitoring problem and proposes a physics-informed time-aware neural network method for it. Herein, multiple features of industrial loads are considered, and the physics relationship among them is leveraged to improve the learning process explicitly. In addition, a two-dimensional convolutional layer is further proposed to encode the timestamp for feature enhancement. Experiments on real-world industrial data from ten appliances will verify the effectiveness of the proposed method.

Industrial CIP Network and Monitoring System with Multiple Communication Protocols Between Allen Bradley Equipment

Industrial CIP Network and Monitoring System with Multiple Communication Protocols Between Allen Bradley Equipment

Deep probabilistic graphical modeling for robust multivariate time series anomaly detection with missing data

Multivariate time series anomaly detection with missing data is one of the most pending issues for industrial monitoring. Due to scarcity of labeled anomalies, most advanced data-driven anomaly detection approaches fall in the unsupervised learning paradigm. As a premise in the presence of missing data, one needs to improve the data quality through data imputation with a separate model. Our concern lies in the consistency between data imputation and unsupervised learning for robust anomaly detection, regarding accurately discovering the spatiotemporal dependence among multiple variables over time. However, the existing practice tends to overlook this consistency and decouple the training process for these two closely linked tasks. This article novelly proposes a probabilistic multivariate time series anomaly detection framework that unifies data imputation and unsupervised learning. A deep probabilistic graphical model abbreviated SCNF is first devised for unsupervised density estimation. A tailored expectation maximization-based optimization scheme is then developed to achieve the joint training of data imputation and unsupervised learning with missing data. The efficacy is experimentally corroborated in several industrial applications, including chemical process, water treatment and network traffic. Briefly, the joint training framework enhances the AUROC of SCNF by averagely 6.34% for three applications under 50% data missing rate.

Nanomaterial-Doped Xerogels for Biosensing Measurements of Xanthine in Clinical and Industrial Applications.

First-generation amperometric xanthine (XAN) biosensors, assembled via layer-by-layer methodology and featuring xerogels doped with gold nanoparticles (Au-NPs), were the focus of this study and involved both fundamental exploration of the materials as well as demonstrated usage of the biosensor in both clinical (disease diagnosis) and industrial (meat freshness) applications. Voltammetry and amperometry were used to characterize and optimize the functional layers of the biosensor design including a xerogel with and without embedded xanthine oxidase enzyme (XOx) and an outer, semi-permeable blended polyurethane (PU) layer. Specifically, the porosity/hydrophobicity of xerogels formed from silane precursors and different compositions of PU were examined for their impact on the XAN biosensing mechanism. Doping the xerogel layer with different alkanethiol protected Au-NPs was demonstrated as an effective means for enhancing biosensor performance including improved sensitivity, linear range, and response time, as well as stabilizing XAN sensitivity and discrimination against common interferent species (selectivity) over time-all attributes matching or exceeding most other reported XAN sensors. Part of the study focuses on deconvoluting the amperometric signal generated by the biosensor and determining the contribution from all of the possible electroactive species involved in natural purine metabolism (e.g., uric acid, hypoxanthine) as an important part of designing XAN sensors (schemes amenable to miniaturization, portability, or low production cost). Effective XAN sensors remain relevant as potential tools for both early diagnosis of diseases as well as for industrial food monitoring.

Unbiased prediction errors for partial least squares regression models: Choosing a representative error estimator for process monitoring

Partial least squares (PLS) regression is widely used to predict chemical analytes from spectroscopic data, thus reducing the need for expensive and time-consuming wet chemical reference analysis in industrial process monitoring. However, predictions via PLS by definition carry sample-specific errors, and estimation of these errors is essential for correct interpretation of results. To increase trust in PLS regression-based predictions, reliable prediction error estimates must be reported. This can be achieved by determining realistic sample-specific prediction errors using an unbiased mean squared prediction error estimate. This work provides a guide for estimating sample-specific prediction errors, showing the importance of choosing an appropriate error estimator prior to deploying PLS models for industrial applications. We reviewed recent and established methods for estimating the sample-specific prediction error and test them through simulation studies. The methods were subsequently applied for estimating prediction errors in two real-life datasets from the food ingredients industry, where near-infrared spectroscopy was used to quantify i) urea in process water and ii) individual protein concentrations in ultrafiltration retentates from a protein fractionation process. Both the simulations and real data examples showed that the mean squared error of calibration is always a downward biased estimator. Although leave-one-out-cross-validation performed surprisingly well in the data analysed in this work, this paper demonstrated that the appropriate choice of error estimator requires the user to make an informed, data-centered decision.

(Invited) From Lab to Fab: The Journey of Waveguide-Enhanced Raman Spectroscopy

WERS, or waveguide-enhanced Raman spectroscopy, is a promising method for sensitive and selective detection of chemical and biological compounds on a chip-scale platform. Here we discuss our ongoing efforts in transitioning WERS from a laboratory test into a technology that can be deployed for commercial applications such as process monitoring in pharmaceutical, petrochemical and agrochemical industries.

Rapid and sensitive determination of Piroxicam by N-doped carbon dots prepared by plant soot

Piroxicam (PX) as a nonsteroidal anti-inflammatory drug (NSAID) can be effectively used for anti-inflammatory and analgesia. However, overdoses may induce side effects such as gastrointestinal ulcers and headaches. Therefore, the assay of piroxicam has considerable significance. In this work, nitrogen-doped carbon dots (N-CDs) was synthesized for PX detection. The fluorescence sensor was fabricated by hydrothermal method with plant soot and ethylenediamine. The strategy exhibited a detection range of 6–200 μg/mL and 250–700 μg/mL with the limited detection of 2 μg/mL. The mechanism of the PX assay base on the fluorescence sensor was the process of electron transfer between the PX and N-CDs. The assay subsequently demonstrated could be successfully used in actual sample. The results indicated that the N-CDs could be a superior candidate nanomaterial for piroxicam monitoring in the healthcare product industry.

Heat release rate of enhanced large-scale open oil slick fires with Outdoor Gas Emission Sampling (OGES) system

The Outdoor Gas Emission Sampling (OGES) system was developed to serve as an economical alternative to expensive industrial gas monitoring equipment. By establishing a sampling plane with four discrete sampling points along the radial direction of the smoke plume, the heat release rate (HRR) was measured for large-scale open oil slick fires. This newfound technique was particularly noteworthy during enhanced burns involving Flame Refluxer™ technology, where it is believed that partial premixing of the fuel and air by the apparatus resulted in a higher HRR than existing flame height correlations would suggest, evident by the HRR calculated using mass burning rate and gas analysis methods, which were in good agreement. Results from OGES show the potential of using point sampling within the plume regime to measure the HRR of fires that exceed the capabilities of conventional hood-based calorimeters, especially when it pertains to large-scale open burns.