Black-box Modeling Approach Research Articles

Optimizing the production of solketal from glycerol: a case study integrating Aspen Plus and a MATLAB subroutine

The use of process simulators has increased dramatically due to their ability to solve complex engineering problems. However, most simulators use a black-box modeling approach, which hinders the application of derivative-based optimization models. This work aims to present a case study of the glycerol ketalization reaction by integrating the Aspen Plus® simulator with MEIGO, an optimization tool available for MATLAB®. The kinetic parameters of the reaction were estimated using a Python algorithm. The simulation was validated, and the optimization of the reactive section was performed using an Enhanced Scatter Search method. After optimization for 80% glycerol conversion, the temperature, acetone:glycerol molar ratio in the reactor feed, and reactor volume were 80 °C, 8.83, and 24.17 m³, respectively, for processing 5.149 m³/h of glycerol. The integration of Aspen Plus® with MATLAB® using the MEIGO add-on is shown as a valid strategy for optimizing complex problems involving black-box models.

Exploring the relationship between LMS interactions and academic performance: A Learning Cycle approach

Research on the relationship between the digital traces of students in Learning Management Systems (LMS) and their academic performance has traditionally been an area of interest in the field of learning analytics. Aiming at achieving high interpretability and generalizability, this study reviews past research, defines a new categorization scheme for interactions in LMS and investigates the relationships between clickstream data of students’ activity and course performance, measured as final grade. The results of the multiple regression analysis of Moodle log data collected from three courses of diverse nature using various classifications of interactions suggest that the new categorization, the CILC (Classification of Interactions based on the Learning Cycle), improves the explanatory power when compared to previous classifications. The analysis suggests that the predictive ability of the models could depend on the delivery mode, with predictions improving as the delivery mode transitions from face-to-face learning to online learning. This finding highlights the need for context-specific considerations about the learning process. Compared to previous research, the analysis also reveals nuances that suggest that the relationships may depend on the instructional design. Finally, the findings also seem to support the notion that increased data quantity and quality may improve predictive models. In summary, the study contributes with valuable insights into the interplay between LMS interactions, course delivery mode, instructional design, and academic performance, and advocates for a balanced exploration of white-box and black-box modeling approaches in learning analytics research.

Black-box modeling of ship maneuvering motion using multi-output least-squares support vector regression based on optimal mixed kernel function

Black-box modeling has been widely used to predict ship maneuvering motion. A novel black-box modeling approach using optimal mixed kernel multi-output least-squares support vector regression (MMLSSVR) based on the artificial hummingbird algorithm (AHA) is proposed in this paper. To improve the performance of the MMLSSVR model, a mixed kernel function that combines a radial basis function and a polynomial kernel function to capture both global and local properties is proposed. The optimal hyper-parameters of the mixed kernel function are determined by the AHA, which employs the linear combination of the mean square error and the determinant of error covariance as the objective function to balance between prediction accuracy and stability. The performance of the proposed method is evaluated using SR108 large container ship data. The experimental results demonstrate that the proposed MMLSSVR model achieves desirable prediction accuracy and strong generalizability for ship maneuvering motion modeling.

A Priori Knowledge-Based Dual Hierarchical RNN for Spatial–Temporal Process Modeling: Using a Multitubular Reactor as a Case Study

Deep learning methods have been rapidly developed in recent decades. In this work, they are extended to model spatial-temporal industrial processes. Instead of pure black-box data-driven modeling approaches, the proposed model encodes the domain knowledge and physical rules governing the spatiotemporal system, called a dual-hierarchical recurrent neural network (DH-RNN). Both spatial and temporal relationships are modeled by multiple RNNs with diverse structures, which need correct specifications of all the interactions between spatial and temporal variables with a priori knowledge of the real process. A more accurate prediction can be obtained with fewer parameters employed in the network. And the effectiveness of the proposed DH-RNN is verified via a real ethylene oxychlorination process.

Design and Implementation of an Incubator with PI Controller for Optimizing the Chicken Egg Incubation Process

This paper describes the design and development of a chicken egg incubator with a structure made of medium-density fiberboard (MDF). The incubator features a temperature control system that integrates a proportional-integral (PI) controller, an Arduino Uno microcontroller, and a regulated light bulb. A display is also included to provide real-time information on temperature, humidity, and the setpoint value, which is set at 37 degrees Celsius to ensure optimal development of the chicks. The Proteus software was utilized for the electrical stimulation of components such as the dimmer and optocouplers. For the mathematical modeling of the incubator, a black box modeling approach was employed to derive the system’s transfer function. Pole cancellation techniques were applied to tune the PI controller, and the controller constants were optimized using Matlab to achieve an optimal system response.

Hybrid analytical surrogate-based process optimization via Bayesian symbolic regression

Modular chemical process simulators are widespread in chemical industries to design and optimize production processes with sufficient accuracy. However, convergence issues and entrapment in local optima during process optimization are still challenges to overcome. To circumvent them, surrogate models of first principles simulations have attracted attention as they are easier to handle, with hybrid surrogates combining data-driven surrogate models with mechanistic equations becoming particularly appealing. In this context, this work explores the use of Bayesian symbolic regression to construct and globally optimize hybrid analytical surrogate models of process flowsheets, where some units are approximated with tailored analytical expressions rather than with neural networks or Gaussian processes, which might be harder to globally optimize. Comparing with other prevalent black-box surrogate modeling & optimization approaches, such as kriging and Bayesian optimization, we find that our approach can find better solutions than those identified with pure black-box methodologies, yet model building is much more computationally demanding.

Multiple-input multiple-output Radial Basis Function Neural Network modeling and model predictive control of a biomass boiler

This study presents a model predictive control of a 4 × 3 Multiple-Input Multiple-Output (MIMO) biomass control system that uses radial basis function (RBF) as an activation function to enhance the control performance. The biomass boiler model is developed from the system identification box in MATLAB by collecting measured input and output data from the 31.5 MW Wonji sugar mill and analyzing the data using black box modeling approach. The major goal of this study is to improve the MIMO control performance of a biomass boiler by utilizing Radial Basis Function Neural Network (RBFNN) to increase model accuracy which ultimately enhances the overall control system. Biomass boilers have four inputs and three outputs. The inputs are airflow 1, airflow 2, water flow and stocker speed (the speed of the motor which feeds bagasse or sugarcane pulp) and outputs are temperature, pressure and drum level. The RBFNN model was programmed using MATLAB R2021a software with system identification toolbox. Shorter settling times of 0.286 s, 1.873 s, and 0.637 s, as well as tolerable overshoots of 0.505%, 1.5%, and 15.698% for temperature, pressure, and level respectively, were achieved with the suggested model predictive controller using RBFNN model. However, when utilizing the identical controller and state space model, the settling times are 2.318 s, 5.461 s, and 6.147 s, with overshoots of 4.737%, 8.152%, and 38.194% for the three variables respectively. The suggested method was compared to the model predictive control (MPC) biomass boiler state space model, which can be considered as a model without RBFNN. The simulation results indicate that the RBFNN-based MPC performed better than the state space model-based MPC. This is because, the state space model is always constant, in contrast to the neural network's active monitoring of boiler dynamics.

The IEQ Occupant Manikin: a holistic indoor environmental quality assessment tool

Indoor environmental quality (IEQ) measurement is a fundamental part of quantifying the performance of any space. Performing measurements and interpreting the results require expensive equipment and specialist knowledge for each parameter. Since holistic IEQ assessment requires investigation of multiple parameters across atmospheric, thermal, acoustic, and visual indoor environment, this is a comprehensive and expensive task. The IEQ Occupant Manikin concept presents an operational holistic IEQ assessment based on measurements of various parameters. The paper presents the development of a prototype manikin equipped with various sensors strategically positioned to best represent the exposure occupants would experience. Since the manikin also physically mimics an occupant in the space, the term occupant-centric measurements is used. In addition, the paper presents a preliminary methodology for the assessment, weighting, and aggregation of individual IEQ parameters towards an overall holistic IEQ assessment. Practical implementation of the work is discussed, including the potential implications for standards on IEQ measurement. The paper reflects upon the future perspectives on using machine learning for a black box modelling approach to tackle the complex issues with the interaction effects between IEQ parameters and relative IEQ parameter weights for holistic assessment. Finally, the paper presents suggestions for future work on the IEQ Occupant Manikin concept.

Anomaly Detection in Batch Manufacturing Processes Using Localized Reconstruction Errors From 1-D Convolutional AutoEncoders

Multivariate batch time-series data sets within Semiconductor manufacturing processes present a difficult environment for effective Anomaly Detection (AD). The challenge is amplified by the limited availability of ground truth labelled data. In scenarios where AD is possible, black box modelling approaches constrain model interpretability. These challenges obstruct the widespread adoption of Deep Learning solutions. The objective of the study is to demonstrate an AD approach which employs 1-Dimensional Convolutional AutoEncoders (1d-CAE) and Localised Reconstruction Error (LRE) to improve AD performance and interpretability. Using LRE to identify sensors and data that result in the anomaly, the explainability of the Deep Learning solution is enhanced. The Tennessee Eastman Process (TEP) and LAM 9600 Metal Etcher datasets have been utilised to validate the proposed framework. The results show that the proposed LRE approach outperforms global reconstruction errors for similar model architectures achieving an AUC of 1.00. The proposed unsupervised learning approach with AE and LRE improves model explainability which is expected to be beneficial for deployment in semiconductor manufacturing where interpretable and trustworthy results are critical for process engineering teams.

Parameter Estimation of a Grid-Tied Inverter Using In Situ Pseudo-Random Perturbation Sources

Inverters are playing an increasingly important role in the electrical utility grid due to the proliferation of renewable energy sources. Obtaining inverter models with accurate parameters is, therefore, essential for grid studies and design. In this paper, a methodology to estimate the output impedance and parameters of a residential grid-tied inverter is proposed. The methodology is first verified through simulation. A sensitivity analysis is conducted to determine the influence of the filter and controller parameters on the output impedance of the inverter. The simulated output impedance, voltage, and current are used in a parameter estimation methodology to obtain filter and controller parameters. It is shown that up to seven parameters can be estimated accurately. The proposed methodology is further investigated through a practical experiment. Two perturbation sources, the pseudo-random binary sequence perturbation and pseudo-random impulse sequence perturbation, are used, in turn, to perturb a residential grid-tied inverter that delivers up to 1.6 kW with the aim of obtaining its output impedance. The output impedances obtained through both pseudo-random sources are compared. It is shown that a pseudo-random binary sequence perturbation source applied in series between the grid and the inverter under test allows for the best estimation of the grid-tied inverter’s output impedance. A black-box modeling approach aimed at estimating an analytical transfer function of the output impedance from experimental data is also discussed.

Model-based and Koopman-based predictive control: a braking control systems comparison

Anti-locking Braking systems are crucial safety systems in modern vehicles. In this work, we investigate the possibility to use Model Predictive Control (MPC) for braking systems by considering three different models identified from data. Specifically, we consider two models, whose structure and the identification procedure are driven by physics principles, and a third black-box modeling approach that relies on Koopman theory. By comparing the effectiveness of the three resulting MPC schemes in a high-fidelity simulation environment, we show that Koopman-based MPC can generally be a viable solution for the design of braking controllers, which might not be the case of nonlinear MPC or approximated scheme like the second one we test.

Design variable structure fuzzy control based on deep neural network model for servomechanism drive system

This paper presents a new scheme for variable structure (VS) fuzzy PD controller. The rule base of the fuzzy PD controller is tuned online. The purpose of the proposed controller is to track accurately a preselected position command for the servomechanism system. Therefore, this study establishes a model using a black-box modeling approach; simulations were performed based on real-time data collected by LabVIEW and processed using MATLAB. The input signal for the servomechanism driver is a pseudo-random binary sequence that considers violent excitation in the frequency interval. The candidate models were obtained using linear least squares, nonlinear least squares, and deep neural network (DNN). The validation results proved that the identified model based on DNN has the smallest mean square errors. Then, the DNN identified model was used to design the proposed control techniques. A comparison had been executed between the VS fuzzy PD control, the conventional PD control, and the fixed structure fuzzy PD control. The experimental results confirm the proposed VS fuzzy PD control can absorb the nonlinear behavior of the system. The speed regulation test, it reduces the rise time from 50% to 56%. While continuously changing in speed, it has the smallest tracking error (0.412 inches).

Energy Modeling and Model Predictive Control for HVAC in Buildings: A Review of Current Research Trends

Buildings use up to 40% of the global primary energy and 30% of global greenhouse gas emissions, which may significantly impact climate change. Heating, ventilation, and air-conditioning (HVAC) systems are among the most significant contributors to global primary energy consumption and carbon gas emissions. Furthermore, HVAC energy demand is expected to rise in the future. Therefore, advancements in HVAC systems’ performance and design would be critical for mitigating worldwide energy and environmental concerns. To make such advancements, energy modeling and model predictive control (MPC) play an imperative role in designing and operating HVAC systems effectively. Building energy simulations and analysis techniques effectively implement HVAC control schemes in the building system design and operation phases, and thus provide quantitative insights into the behaviors of the HVAC energy flow for architects and engineers. Extensive research and advanced HVAC modeling/control techniques have emerged to provide better solutions in response to the issues. This study reviews building energy modeling techniques and state-of-the-art updates of MPC in HVAC applications based on the most recent research articles (e.g., from MDPI’s and Elsevier’s databases). For the review process, the investigation of relevant keywords and context-based collected data is first carried out to overview their frequency and distribution comprehensively. Then, this review study narrows the topic selection and search scopes to focus on relevant research papers and extract relevant information and outcomes. Finally, a systematic review approach is adopted based on the collected review and research papers to overview the advancements in building system modeling and MPC technologies. This study reveals that advanced building energy modeling is crucial in implementing the MPC-based control and operation design to reduce building energy consumption and cost. This paper presents the details of major modeling techniques, including white-box, grey-box, and black-box modeling approaches. This paper also provides future insights into the advanced HVAC control and operation design for researchers in relevant research and practical fields.

The ARX and ARMAX Models for Thermoelectric Cooling on Glass Windows: A Comparative Study

Thermoelectric cooling (TEC), in particular, can be combined with a heat sink for local cooling, but they can also be integrated into electronic chips for point-to-point cooling. The study aims to develop a dynamic model of a cooling system integrated with TEC for glass window. The main target of this study is to develop a dynamic model of a cooling system integrated with TEC. The black box modelling approach in producing a mathematical model was selected based on the ARMAX and ARX model that corresponds to the actual dynamic state of the cooling system. The best model was finalized based on the best match on curve patterns when comparing the real and estimated models using the system identification tools in MATLAB, and also having the least error. The accuracy of the models was compared and analysed. The results showed that the 4th order of the ARMAX model produced a higher best fitting and standard deviation values of 80.23% and 0.027592 compared to the 4th order of the ARX model of 78.14% and 0.030769 respectively. This system accuracy is almost within the acceptable range for most error calculations in the validation method. Yet, this cooling system integrated with TEC is found more suitable for the 4th order of the ARMAX model when compared to the ARX model due to the noise parameter in the ARMAX model. Nevertheless, the noise order in this system is not dominant, therefore, whenever the noise order of the system in the ARMAX model is high than the second structure (nb), the number of errors is also high. In addition, the ARMAX model is found incapable of achieving the highest fitting due to the losses from the dynamic environment and losses from the TEC itself. Still, the use of this black box model used in this study is a significant variation where system parameters can be identified even offline.

Model Öngörülü Kontrol ile DA Motor Konum Kontrolü

Bu çalışmada sabit mıknatıslı fırçalı doğru akım (DA) motor sisteminin konum kontrolü için modern kontrol yöntemlerinden model öngörülü kontrolcü tasarımı gerçekleştirilmiş ve önerilen kontrolcü tasarımı farklı testler ile gerçek zamanlı olarak doğrulanmıştır. Ele alınan sistem modeli, sistem tanımlama yöntemlerinden kara kutu modeli yaklaşımı ile elde edilmiştir. Deneysel veri setleri ile elde edilen sistem modeli üzerinden model öngörülü kontrolcü tasarımı geliştirilmiştir. Geliştirilen tasarımcı modeli, Matlab destekli Waijung blok seti ve STM32F4 uygulama geliştirme kiti kullanılarak gerçek zamanlı olarak gerçekleştirilmiştir. Farklı referans girişleri ve parametre değişimleri altında kontrolcü performansı test edilmiştir. Sistem çıkışının tüm referans girişleri başarılı bir şekilde takip etmesi ve değişen sistem parametrelerine rağmen başarısını sürdürmesi önerilen kontrolcü tasarımını doğrulamıştır. Ayrıca klasik kontrol yaklaşımlarından PID denetleyici ile sonuçlar karşılaştırılarak model öngörülü kontrolcü üstünlüğü deneysel sonuçlarla vurgulanmıştır.

Identification of ARX Model for Thermoelectric Cooling on Glass Windows

Thermoelectric cooling (TEC) is a solid-state heat pump that uses the Peltier effect to dissipate the heat generated by the electronic packaging system. TECs are widely used in aerospace, military, scientific work and industry due to small size, lack of moving parts, and ease of integration. In this study, a cooling system integrated with TEC is developed in a testing area (lecturer’s office) with the aim to reduce the temperature of the hot glass window area due to solar radiation that passes through it. This cooling system used direct TEC, for keeping the cooling temperature on the window to about 26 °C which is equivalent to an air conditioning setting temperature of 26 °C set during the experiment. This work includes experimental and modelling studies conducted on cooling systems integrated with TEC. The main target of this study is to develop a dynamic model of a cooling system integrated with TEC. The black box modelling approach in producing a mathematical model was selected based on the ARX model that corresponds to the actual dynamic state of the cooling system. The best model was finalized based on the best match on curve patterns when comparing the real and estimated models using the system identification tools in MATLAB, and also had the least error. The accuracy of the models was compared and analysed. The results showed that the 4th order of the ARX model produced a higher best fitting and standard deviation values of 78.14% and 0.030769. This system accuracy is almost within the acceptable range for most error calculations in the validation method. In addition, the ARX model is found incapable of achieving the highest fitting due to the losses from the dynamic environment and losses from the TEC itself. Still, the use of this black box model used in this study is a significant variation where system parameters can be identified even offline.

Black-box Modeling of Converters in Renewable Energy Systems for EMC Assessment: Overview and Discussion of Available Models

The development of renewable energy systems interfaced with the grid by power electronic converters leads to increasing issues of electromagnetic coexistence between power and communication lines, as well as severe power quality issues, such as total harmonic distortion at the consumer side. Therefore, high-frequency modeling of renewable energy systems is of great importance to guide the design and development of distribution networks involving renewable sources. Owing to system complexity, black-box modeling approaches offer more advantages than traditional circuit modeling, as far as electromagnetic compatibility (EMC) analysis and filter design are the targets. In this study, different black-box modeling techniques for power converters are introduced and systematically analyzed. First, the general theory of black-box modeling is explained. Subsequently, three different modeling approaches are compared in terms of accuracy and the required experimental setup. Finally, the possible limitations of black-box modeling of power converters are investigated and discussed.

Deep Neural Network System Identification for Servomechanism System

This paper presents a systematic technique for designing the input signal to identify the one-stage servomechanism system. Sources of nonlinearities such as friction and backlash consider an obstacle to obtaining an accurate model. Also, most such systems suffer from a lack of system parameters data. So, this study establishes a model using the black-box modeling approach; simulations are performed based on real-time data collected by LabVIEW software and processed using MATLAB System Identification toolbox. The input signal for the servomechanism system driver is a pseudo-random binary sequence that considers violent excitation in the frequency interval and the output signal is the corresponding stage speed measured by rotary encoder. The candidate models were obtained using linear least squares, nonlinear least squares, and Deep Neural Network (DNN). The validation results proved that the identified model based on DNN has the smallest mean square errors compared to other candidate models.

Nonlinear modeling of industrial boiler NOx emissions

ABSTRACT Pollutant emissions into the atmosphere are recognized as a significant problem in fossil fuel combustion. The pollution emission measurement in industrial boilers is difficult and expensive but fundamental for monitoring and controlling. Frequently continuous emissions monitoring (CEM) system is out of service or useless due to obsolescence, high maintenance cost, and so on or simply is not installed. When a system for measuring pollutant emissions is not available, an alternative method must be employed to get the pollutant emission value. According to the black-box model approach, this article describes the nonlinear modeling of NOx emissions from a utility boiler. Bayesian-Gaussian (BG), multilayer perceptron (MLP), and Volterra polynomial basis functions (VPBF) neural networks are developed for model benchmarking. Experimental data from a utility boiler was acquired in order to model definition and evaluation. The models process three boiler variables oxygen excess, fuel mass flow and flue gas recirculation gates for NOx emission estimation. Models with BG show better performance than models with MLP and VPBF for NOx prediction. Implications: The technology to control NOx emissions generated by combustion operates under strict regulations. In order to reduce NOx emissions, theoretical models of NOx generation have been studied extensively, including nitrogen chemistry and the dynamic flow of gas particles which is very complex. The new technology trends would require the continuous measurement of high precision NOx emissions to achieve further reductions in NOx emissions. Currently, NOx emissions are measured by a Continuous Emission Monitoring system, which turns out to be extremely expensive and difficult to maintain, so alternative low-cost solutions are desirable. Our contribution shows how algorithms based on different artificial intelligence techniques are viable and quality alternatives for the measurement of continuous NOx emissions. The NOx emissions models based on IA algorithms are viable alternatives that have versatility and self-tuning capacity due to the fact that they are based on boiler operation parameters which have valuable information few explored nowadays.

Soft Sensor for Melt Index Prediction Based on Long Short-Term Memory Network

This paper presents a soft sensor model for melt index (MI) prediction in an industrial polymerization process based on long short-term memory (LSTM) network. MI is one of the important specifcations that determine the quality and grade of thermoplastic polymers. However, lack of online measurement of MI makes it difcult to monitor and control the quality of polymer products. Thus, there has been a great efort to build accurate soft sensor models to predict MI with easy-to-measure process variables by using black-box modeling approaches. However, real chemical processes have strong nonlinearity and complicated temporal correlations between the process and quality variables, which is very challenging for traditional static black-box models to handle. Recently, LSTM network that is an advanced form of recurrent neural network (RNN) has shown great advantages in capturing and modeling the long-term dynamic nature of complex industrial processes. We develop an LSTM-based MI prediction model for an industrial styrene-acrylonitrile (SAN) polymerization process in Korea. The developed model provides the most accurate predictions compared to other soft sensor models based on partial least squares (PLS), support vector machines (SVM), Gaussian process regression (GPR), and feedforward artificial neural network (ANN).