Real-world Industrial Processes Research Articles

Mathematical analysis for flow of hybrid nanofluid over a vertical stretchable surface: Assisting and opposing flows

Research Problem: The importance of improving the temperature properties of commonly used fluids in industrial processes is being addressed in this research. Nanofluids, which are composed of extremely small particles dispersed in common liquids such as water or petrol, are the main subject of this area of study. Using a vertically stretchable surface subjected to thermal radiation, the study examines the heat transfer behavior and efficiency of nanofluids. Methodology: Nanofluids that convey heat are studied by applying the fundamental rules of fluid physics to the variables that control their motion. To measure the amount of energy transferred, a nanofluid model is used. Similarity transformations are used to convert the system’s differential equations into ordinary differential equations (ODEs). The subsequent set of nonlinear ODEs is solved using numerical methods. Utilizing graphical analysis, patterns of velocity and temperature may be seen, and their responses to changes in other parameters can be investigated. Implications: This research has important implications for our knowledge of how nanofluids act in heat transfer applications, especially when exposed to thermal radiation and working with vertically stretchy surfaces. The effects of flow direction and thermal conductivity on distributions of velocity and temperature were elucidated, among other important results. More effective heating and cooling systems may be possible as a result of these findings, which have consequences for improving heat transfer processes in industrial environments. Future Work: To better understand how nanofluids behave in heat transfer applications, future studies might investigate more complicated situations and boundary circumstances. It may be possible to optimize nanofluid formulations by studying the impact of various nanoparticle kinds and concentrations on heat transfer efficiency. Research could be more applicable to real-world industrial processes if the numerical results were experimentally validated.

From United Steel to Waymo: industrializing simulation

AbstractThe use of computers for simulation work can be traced back to the 1950s, and the pioneering work of Stafford Beer, KD Tocher and others at Cybor House in Sheffield, UK, the research and development (R&D) department of British steelmakers, United Steel. This innovative simulation work sought to offer an abstracted, ‘total’ environment of the steelmaking process in which different operational activities could be modeled. Critical to this work was the ability of computer simulations to perform such modelling at a fraction of the cost, wasting fewer material resources, and in a considerably shorter timeframe. Such work can be understood as the earliest example of the application of industrial-scale ‘automated computation’ to a real-world industrial process. Similarly indebted to the early principles of computer simulation, Waymo engineers are also engaged in the building of so-called ‘conflict typologies’ designed to encode material properties of everyday driving interactions between road users, rather than simply road users themselves. Through ‘motion planning’, coupled with the categorization of driving interactions, Waymo engineers build instrumental understanding of their own system’s purported intelligence in navigating everyday driving situations. Functioning as ‘generative mechanisms’ rather than simply evaluative devices, engineers seek to industrialize—instrumentalize, scale up, rationalize—everyday driving knowledge. Through conflict typologies, instrumental knowledge of the actual capacities of autonomous vehicles is industrialized, materialized, and realized.

Multi-objective optimization for sustainable and economical polycarbonate production with reaction kinetics inference for real-world industrial process

Polycarbonate has a wide range of applications in electronic devices and medicine because of its remarkable properties such as transparency and mechanical strength. However, the polycarbonate production process using diphenyl carbonate leads to the inevitable generation of nitrogen oxide (NOx) from byproduct incineration. Therefore, it is essential to optimize the process conditions while simultaneously considering the production costs and NOx emissions. Herein, we propose a multi-objective optimization model for sustainable and economical polycarbonate production using a high-fidelity reaction model for real-world industrial processes. Additionally, a data-driven model was developed using industrial data to identify the operating conditions that minimize NOx emissions and maximize profitability. Four of the ten reaction parameters were selected through variance-based global sensitivity analysis, and the posterior distribution of each parameter was determined through Bayesian inference. In addition, NOx emissions were predicted using the data-driven model developed from industrial data. A process model with coefficients of determination above 0.7 and a data-driven model with R-squared value above 0.99 for pilot-scale experimental and industrial data were generated using our approach. The Pareto optimality, identified based on the developed models, suggested operating conditions that optimize both economic and environmental benefits. Consequently, NOx emissions could be reduced by 27.2%–27.4% and the unit costs of production could be reduced by 0.8%–1.6% compared with the base case.

Computation-guided engineering of distal mutations in an artificial enzyme.

Artificial enzymes are valuable biocatalysts able to perform new-to-nature transformations with the precision and (enantio-)selectivity of natural enzymes. Although they are highly engineered biocatalysts, they often cannot reach catalytic rates akin those of their natural counterparts, slowing down their application in real-world industrial processes. Typically, their designs only optimise the chemistry inside the active site, while overlooking the role of protein dynamics on catalysis. In this work, we show how the catalytic performance of an already engineered artificial enzyme can be further improved by distal mutations that affect the conformational equilibrium of the protein. To this end, we subjected a specialised artificial enzyme based on the lactococcal multidrug resistance regulator (LmrR) to an innovative algorithm that quickly inspects the whole protein sequence space for hotpots which affect the protein dynamics. From an initial predicted selection of 73 variants, two variants with mutations distant by more than 11 Å from the catalytic pAF residue showed increased catalytic activity towards the new-to-nature hydrazone formation reaction. Their recombination displayed a 66% higher turnover number and 14 °C higher thermostability. Microsecond time scale molecular dynamics simulations evidenced a shift in the distribution of productive enzyme conformations, which are the result of a cascade of interactions initiated by the introduced mutations.

Students’ project for instrumentation and automation of a manually operated torsion testing machine with educational purposes

From the pedagogical point of view, a very interesting initiative for engineering schools is to engage their students in design, renovation, or maintenance projects of laboratory equipment. It allows engineering students to work on real projects, with all the difficulties that arise in field testing, and to gain hands-on experience from the confrontation of practical situations and challenges, which presents positive outcomes regarding learning objectives and program appreciation. This article presents an engineering project developed by students for instrumentation and automation of an old manually operated torsion testing machine, for execution of accurate mechanical tests and reliable physical replications of real-world industrial processes on laboratory scale. An electrical resistive furnace is incorporated into the torsion testing machine to also allow hot torsion tests with controlled temperature. In addition to students’ skills development, this project yields a completely functional instrumented and automated torsion testing machine, with a controlled temperature electrical furnace and other features that have been used in Bachelor, Master, and Doctoral projects, laboratory classes, and new research.

A Faster Dynamic Feature Extractor and Its Application to Industrial Quality Prediction

The unsupervised dynamic models have been applied to various tasks in the process industry due to their excellent ability to represent the process dynamics. The recurrent-network-based dynamic feature extractor is a typical unsupervised dynamic model which extracts the dynamic data features using a recurrent encoder network. However, the recurrent-network-based dynamic feature extractor has low computational efficiency due to its recurrent nature, which prevents the model from being used for large-scale data sets. To improve computational efficiency, a new dynamic feature extractor called TempoATTNE-DFE is proposed in this work. In TempoATTNE-DFE, a new encoder structure is developed, which can be implemented in parallel for data sequences. Meanwhile, a kind of attention mechanism is proposed to extract the dynamic features within the input sequence. The proposed TempoATTNE-DFE can achieve higher computational efficiency in offline training and online inference. To evaluate the effectiveness of TempoATTNE-DFE, it is applied to the quality prediction task and validated with a numerical example and two real-world industrial processes. The application results demonstrate that TempoATTNE-DFE can achieve better prediction performance compared to other state-of-the-art methods. In addition, compared with the recurrent-network-based dynamic feature extractor, TempoATTNE-DFE gains <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ 1.29\times$</tex-math></inline-formula> speedup in training and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ 2.45\times$</tex-math></inline-formula> speedup in inference on the blast furnace data set.

Multivariate Deep Reconstruction Neural Network for Multi-step-ahead Prediction of Industrial Process Quality Variables

In industrial processes, deep learning has been widely used to solve the soft sensing problem. Multi-step-ahead prediction is one of the most challenging problems in the field of soft sensors. Recently, N-Beats has been proposed as a promising deep neural architecture for multi-step prediction, but it can only be used for univariate time series prediction, not for industrial soft sensor modeling. Inspired by N-Beats, a novel deep learning model, multivariate deep reconstruction neural network (MDRNN), is proposed for multivariate time series prediction in this work. MDRNN is designed on the basis of a doubly residual structure with a deep stack of fully-connect layers. MDRNN inherits the merits of N-Beats and incorporates the “doubly residual stacking” idea into the industrial soft sensor modeling to improve the prediction accuracy. To evaluate the feasibility and effectiveness of the proposed MDRNN, it is applied to the quality prediction task and validated with two real-world industrial processes. The application results demonstrated that the proposed MDRNN can achieve higher prediction accuracy compared to the existing N-Beats and Multilayer Perceptron (MLP)-based methods.

Data-driven modeling of multimode chemical process: Validation with a real-world distillation column

Real-world industrial processes frequently operate in different modes such as start-up, transient, and steady-state operation. Since different operating modes are governed by different process dynamics, deriving a single data-driven model representing the entire operation of such multimode processes is not a viable option. A reasonable solution to this problem is to develop a separate model for each operating mode, which requires the extraction of data for each operating mode from raw data. Based on this viewpoint, this work develops a data-driven modeling approach using clustering and featuring selection techniques to improve the quality of raw data and develop a predictive model for a multimode industrial process. In particular, the developed method focuses on training a steady-state predictive model as monitoring steady-state conditions is crucial for achieving the desired product quality. Firstly, K-means clustering is performed to extract data describing the steady-state operation mode from the available raw data. Next, feature selection is applied to the clustered data using Pearson’s correlation coefficient to identify input features relevant to target features. Finally, an LSTM model is trained using the clustered data and identified features to predict the steady-state operation. The validity and effectiveness of the developed method are demonstrated using a real-world 2,3-Butanediol distillation process dataset.

Deep Drawing of AISI 304 Blanks with Polymer Punches Produced by Additive Manufacturing: Effects of Process Scalability

Rapid tooling is a methodology which aims to integrate additive manufacturing into the production of tools to be used in casting, forming or machining processes. In forming, rapid tooling is applied in the production of metallic or plastic tools that guarantee good performance in small- and medium-sized batch production. However, most punches tested to date have dimensions measured in millimeters and are therefore unsuitable for typical real-world industrial processes. In this study, the performance of plastic punches with geometries designed for industrial application was investigated. A deep drawing process involving AISI 304 blanks was created for the manufacturing of cups. Experimental and numerical analyses were conducted to measure the quality of the cups produced and the behaviour of the punches involved. The results indicate that when punch dimensions increase, a more precise cup geometry is produced (99% of drawing depth, 98% of cup precision on the fillet radius, and roundness error equal to 0.53%).

Dynamic Probabilistic Predictable Feature Analysis for Multivariate Temporal Process Monitoring

Dynamic statistical process monitoring methods have been widely studied and applied in modern industrial processes. These methods aim to extract the most predictable temporal information and develop the corresponding dynamic monitoring schemes. However, measurement noise is widespread in real-world industrial processes, and ignoring its effect will lead to suboptimal modeling and monitoring performance. In this article, a probabilistic predictable feature analysis (PPFA) is proposed for multivariate time series modeling, and a multistep dynamic predictive monitoring scheme is developed. The model parameters are estimated with an efficient expectation–maximization algorithm, where the genetic algorithm and the Kalman filter are designed and incorporated. Furthermore, a novel dynamic statistical monitoring index, the dynamic index, is proposed as an important supplement of T2 and SPE to detect dynamic anomalies. The effectiveness of the proposed algorithm is demonstrated via its application on the three-phase flow facility and a medium-speed coal mill.

A novel random subspace method considering complementarity between unsupervised and supervised deep representation features for soft sensors

Unsupervised and supervised deep learning extract effective and abstract features from different perspectives, which have been successfully applied in soft sensors. However, few studies have fused them and explored the complementary effect between the two kinds of features, which limits the utilization of comprehensive prediction information. To address the problem, a novel random subspace method with stacked auto-encoder (SAE) and bidirectional long short-term memory (Bi-LSTM), named RS-SBL, is proposed for soft sensors. Firstly, unsupervised and supervised deep representation features are extracted by SAE and Bi-LSTM, respectively. Secondly, to leverage the complementarity of the fusion features, an improved random subspcae (RS) method with a structure sparsity learning model is designed to discriminate the relative importance of different features and generate ensemble prediction results. Finally, the experiments on two real-world industrial nonlinear processes demonstrate that the proposed RS-SBL with the feature fusion strategy improves the prediction performance, and outperforms the other comparison soft sensor models.

Parameterisation of domain knowledge for rapid and iterative prototyping of knowledge-based systems

In critical infrastructure applications, timely and consistent fault detection and diagnosis is an increasingly important operational process, especially in the energy sector where safety is of the utmost importance. To realise this, engineers have to manually analyse data acquired from several assets using predefined diagnostic processes, but this is a time-consuming process requiring significant amounts of specialist expert knowledge. Data-driven approaches to support fault detection and diagnosis, and other similar problems, can produce accurate results comparable to what the engineers can achieve in a fraction of the time. However, the majority of these data-driven techniques are black box techniques and lack explainability which is often necessary for explaining decisions about critical assets in the power generation industry. Knowledge-based systems, such as rule-based expert systems have been shown to provide not only accurate decisions but also the explanation and reasoning behind these decisions in some related applications. However, there is a significant time cost associated with the development of knowledge-based systems, and in particular with the knowledge elicitation process, where the domain expert’s knowledge is formalised and is encoded into the system. This challenge is commonly referred to as the knowledge elicitation bottleneck.In this paper, we present a novel approach to performing the knowledge elicitation using a set of symbolic primitives (rise, fall, fluctuate, and stable) to parameterise typical time-series condition monitoring data. The knowledge is represented by using a common language that can easily be communicated with (and from) the domain experts. This allows for the quick and accurate elicitation of the domain experts knowledge, but also the formalisation and implementation of the knowledge into a rapidly produced diagnostic system. Further to this, due to the parametrisation of the knowledge, it is possible to iteratively improve the knowledge base by updating these parameters based on new unseen data. This approach was applied to the Tennessee Eastman dataset, which is simulated data of a real-world industrial process. It was found that by using this approach it was possible to accurately and quickly capture the knowledge required to detect several faults within the case study dataset, but also provided fully explained reasons why each fault was detected by relating the explanations to the symbolic primitives previously defined.

Inter-Relational Mahalanobis SAE with semi-supervised strategy for fault classification in chemical processes

Since industrial process data often presents strong correlations, high complexity, and nonlinear patterns, a proficient deep learning model is required for the fault classification task. Recent researches have shown that deep learning models like stacked autoencoder (SAE) are able to learn deep abstract features from complex process data. Nevertheless, a traditional SAE cannot extract the informative fault-relevant features and data distribution features from industrial process data, which are necessary for effective fault classification in industrial processes. Thus, this study proposes a semi-supervised Inter-Relational Mahalanobis SAE (IRM-SAE) model to learn inter-relational distribution and fault-relevant dynamic features of process data for fault classification. First, the Inter-Relational Mahalanobis loss is introduced into the original objective function of SAE to learn meaningful inter-relational distribution features within the data. Then, an active time frame technique is developed to preprocess the input data to capture the dynamic features of the data. Furthermore, to fully utilize both labeled and unlabeled data in industrial processes, the semi-supervised strategy is introduced to learn fault-related features for better fault classification. To validate the performance of the proposed model, it is applied on the Tennessee–Eastman process and a real-world industrial hydrocracking process. The experimental results show that the proposed model has higher fault classification performance compared to other deep learning models.

Concurrent Multilayer Fault Monitoring with Nonlinear Latent Variable Regression

Latent variable regression (LVR) constructs the latent structure by maximizing the projection of quality variables on the latent spaces of the process variables, which has demonstrated its effectiveness over other multivariate statistical methods in terms of quality-relevant monitoring. However, it cannot be applied to model most real-world industrial processes due to its implicit linear assumption on the data. To overcome this issue, the kernel trick is designed to develop its nonlinear counterpart. Further, a novel concurrent kernel LVR (CKLVR) method is proposed for multilayer modeling with subsequent decomposition, which separates the process and data spaces comprehensively into five subspaces. The corresponding monitoring statistics are also developed for each subspace extracted by CKLVR, with each serving a particular monitoring purpose. Case studies including a numerical simulation, Dow’s Refining Process, and the Tennessee Eastman Process are employed to illustrate the performance of the proposed algorithm.

A Roadmap towards an Automated Warehouse Digital Twin: current implementations and future developments

Automation and digitization increase the effectiveness and efficiency of logistics processes. In warehousing, Automated Storage and Retrieval Systems (AS/RS) are largely adopted due to their considerable advantages over traditional warehousing, namely high space utilization, shorter cycle times and improved inventory control. To further enhance such advantages, warehouse operations can be digitized via a Digital Twin (DT) which retrieves data from the real-world industrial process, mimics its behaviour and feeds specific inputs back to the real-world process, after elaboration from a simulation-based digital model. This work presents a DT proposal for a real-world AS/RS system, highlighting its current implementations together with its future developments.

Fusion-Based Supply Chain Collaboration Using Machine Learning Techniques

Supply Chain Collaboration is the network of various entities that work cohesively to make up the entire process. The supply chain organizations’ success is dependent on integration, teamwork, and the communication of information. Every day, supply chain and business players work in a dynamic setting. They must balance competing goals such as process robustness, risk reduction, vulnerability reduction, real financial risks, and resilience against just-in-time and cost-efficiency. Decision-making based on shared information in Supply Chain Collaboration constitutes the recital and competitiveness of the collective process. Supply Chain Collaboration has prompted companies to implement the perfect data analytics functions (e.g., data science, predictive analytics, and big data) to improve supply chain operations and, eventually, efficiency. Simulation and modeling are powerful methods for analyzing, investigating, examining, observing and evaluating real-world industrial and logistic processes in this scenario. Fusion-based Machine learning provides a platform that may address the issues/limitations of Supply Chain Collaboration. Compared to the Classical probable data fusion techniques, the fused Machine learning method may offer a strong computing ability and prediction. In this scenario, the machine learning-based Supply Chain Collaboration model has been proposed to evaluate the propensity of the decision-making process to increase the efficiency of the Supply Chain Collaboration.

A Case Study on the Utilization of 3D CAD Design Education applying IC-PBL

A Case Study on the Utilization of 3D CAD Design Education applying IC-PBL

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

Deep learning has been growing in popularity for soft sensor modeling of nonlinear industrial processes, infeuality-related variables. However, applications may be highly nonlinear, and the quantity of labeled samples is considerably limited. The extraction of relevant information from abundant unlabeled data is becoming an area of increasing interest in soft-sensor development. A novel ensemble deep relevant learning soft sensor (EDRLSS) modeling framework based on stacked autoencoder (SAE), mutual information (MI), and bagging-based strategy is proposed. SAE is trained layer-by-layer with MI analysis conducted between targeted outputs and learned hidden representations to evaluate and weight the current layer representations. The proposed method eliminates irrelevant information and weights the retained features to highlight the most relevant representations. Thus, the approach extracts deep representative information. Besides, a bagging-based ensemble strategy is applied to improve the soft-sensor performance and reliability. Two real-world industrial nonlinear processes are used to evaluate the EDRLSS framework performance. The results show enhanced prediction performance compared to other state-of-the-art and traditional methods.

Data-driven adaptive control of wide-area non-linear systems with input and output saturation: A power system application

In this paper, a Data-Driven Adaptive Controller is proposed for wide-area Multi-Input and Multi-Output (MIMO) non-linear systems featuring input–output saturations. Complexity has always been a major concern in the modeling and control of real-world industrial processes. Traditionally, researchers look for simplified and enough precise models of these systems. However, with the significant advancement in sensor and communication technologies, a considerable amount of data is available from the process which may compensate for the lack of precise models. The emerging data-driven control systems perform both identification and control actions based on data collected from the process, making the system less dependent on a pre-identified model. In this context, an efficient MIMO Data-Driven Adaptive Control (MIMO-DDAC) is designed in this paper for stabilizing a class of unknown non-linear systems. A recursive modeling/control process is proposed for the MIMO systems in the presence of saturation in sensors and actuators, and its stability and performance are mathematically proved. This approach is applied to the load frequency control problem in an interconnected multi-area power grid in the presence of governor saturation, load and parametric uncertainties. Simulation results reveal the effectiveness of the proposed method.

Industrial Semi-Supervised Dynamic Soft-Sensor Modeling Approach Based on Deep Relevant Representation Learning.

Soft sensors based on deep learning have been growing in industrial process applications, inferring hard-to-measure but crucial quality-related variables. However, applications may present strong non-linearity, dynamicity, and a lack of labeled data. To deal with the above-cited problems, the extraction of relevant features is becoming a field of interest in soft-sensing. A novel deep representative learning soft-sensor modeling approach is proposed based on stacked autoencoder (SAE), mutual information (MI), and long-short term memory (LSTM). SAE is trained layer by layer with MI evaluation performed between extracted features and targeted output to evaluate the relevance of learned representation in each layer. This approach highlights relevant information and eliminates irrelevant information from the current layer. Thus, deep output-related representative features are retrieved. In the supervised fine-tuning stage, an LSTM is coupled to the tail of the SAE to address system inherent dynamic behavior. Also, a k-fold cross-validation ensemble strategy is applied to enhance the soft-sensor reliability. Two real-world industrial non-linear processes are employed to evaluate the proposed method performance. The obtained results show improved prediction performance in comparison to other traditional and state-of-art methods. Compared to the other methods, the proposed model can generate more than 38.6% and 39.4% improvement of RMSE for the two analyzed industrial cases.